Delivery warning method, device, computer equipment and storage medium

Abstract

The present application relates to a delivery warning method, device, computer equipment and storage medium. The method comprises: obtaining waybill information of the goods to be delivered, the waybill information includes first parameter data; querying a first warning value corresponding to the first parameter data, the first warning value is determined based on historical waybill data; according to the first warning value, generating warning information for reminding to perform inspection operations on the goods to be delivered. The use of this method can increase the scope of waybills for warning and effectively prevent the risk of malicious claims or customer complaints.

Description

Technical Field

[0001] The present application relates to the field of logistics technology, and in particular to a delivery warning method, device, computer equipment and storage medium. Background Art

[0002] With the increasing demand for logistics and transportation services, express delivery services play an increasingly important role in society. In order to save delivery time, most couriers do not open the boxes for inspection when delivering parcels, which gives some malicious claims or complaints an opportunity to cause losses to logistics companies. Therefore, it is necessary to identify the risk level of claims or customer complaints for the waybills to be delivered, and accordingly remind the couriers to take preventive measures such as unpacking and inspection, taking photos for evidence, etc., to reduce malicious claims or customer complaints.

[0003] Traditional technology only considers early warning for some special waybills (such as insured waybills) when delivering parcels, and the scope of early warning is not comprehensive enough. Summary of the invention

[0004] Based on this, it is necessary to provide a delivery warning method, device, computer equipment and storage medium with a wide range of applications in response to the above technical problems.

[0005] A delivery warning method, the method comprising:

[0006] Obtaining waybill information of the goods to be dispatched, wherein the waybill information includes first parameter data;

[0007] Querying a first warning value corresponding to the first parameter data, where the first warning value is determined based on historical waybill data;

[0008] According to the first warning value, a warning message is generated for prompting an inspection operation to be performed on the goods to be dispatched.

[0009] A delivery warning device, comprising:

[0010] An acquisition module, used to acquire waybill information of the goods to be delivered, wherein the waybill information includes first parameter data;

[0011] A query module, used to query a first warning value corresponding to the first parameter data, wherein the first warning value is determined based on historical waybill data;

[0012] The early warning module is used to generate early warning information for reminding the inspection operation of the goods to be dispatched according to the first early warning value.

[0013] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0014] Obtaining waybill information of the goods to be dispatched, wherein the waybill information includes first parameter data;

[0015] Querying a first warning value corresponding to the first parameter data, where the first warning value is determined based on historical waybill data;

[0016] According to the first warning value, a warning message is generated for prompting an inspection operation to be performed on the goods to be dispatched.

[0017] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0018] Obtaining waybill information of the goods to be dispatched, wherein the waybill information includes first parameter data;

[0019] Querying a first warning value corresponding to the first parameter data, where the first warning value is determined based on historical waybill data;

[0020] According to the first warning value, a warning message is generated for prompting an inspection operation to be performed on the goods to be dispatched.

[0021] The above-mentioned delivery warning method, device, computer equipment and storage medium obtain the waybill information of the goods to be delivered, and the waybill information includes the first parameter data; query the first warning value corresponding to the first parameter data, and the first warning value is determined based on the historical waybill data; according to the first warning value, generate warning information for reminding to inspect the goods to be delivered. The corresponding warning information is generated accordingly, which is applicable to various types of waybill delivery warnings and has a wide range of applications. The delivery personnel can inspect the goods on the spot when delivering the goods based on the warning information, thereby effectively preventing the risk of malicious claims or customer complaints in the later stage. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic diagram of a process of a delivery warning method in one embodiment;

[0023] Figure 2 is a flow chart of a method for determining a first warning value in one embodiment;

[0024] Figure 3 It is a flowchart of a step of determining a first warning value corresponding to each target parameter data based on the historical waybill volume, historical claims data and historical complaint data corresponding to each target parameter data in an embodiment;

[0025] Figure 4 A flowchart of a step of determining a first warning value corresponding to each target parameter data based on the historical claim settlement rate, the historical average claim settlement amount and the historical complaint rate corresponding to each target parameter data in one embodiment;

[0026] Figure 5 A schematic diagram of a process of a delivery warning method in one embodiment;

[0027] Figure 6 It is a structural block diagram of a delivery warning device in one embodiment;

[0028] Figure 7 is an internal structure diagram of a computer device in one embodiment;

[0029] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0031] In one embodiment, Figure 1 As shown, a delivery warning method is provided. This embodiment uses the method applied to a server as an example. It can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps S102 to S106.

[0032] S102, obtaining waybill information of the goods to be delivered, wherein the waybill information includes first parameter data.

[0033] The goods to be dispatched refer to the goods that have not been signed for. The waybill information usually includes the waybill number, the sender's related data, the recipient's related data and the goods related data (such as the type of goods, weight, whether it is insured, etc.). In this embodiment, the first parameter data refers to the recipient identification data.

[0034] S104, querying a first warning value corresponding to the first parameter data, where the first warning value is determined based on historical waybill data.

[0035] Historical waybill data refers to waybill data within a historical period (e.g., the last six months, three months, etc.), each waybill data corresponds to a historical waybill, and each waybill data is associated with a sender identification data and a recipient identification data. The first warning value corresponding to the first parameter data is used to characterize the possibility that the recipient identified by the first parameter data will make a claim or complaint. The larger the first warning value, the higher the possibility that the corresponding recipient will make a claim or complaint.

[0036] Specifically, the corresponding interface can be called to query the first warning value corresponding to the first parameter data from the stored warning value set. In one embodiment, the warning value set may contain the first warning values ​​corresponding to all parameter data, and all parameter data include the sender identification data and the recipient identification data associated with each historical waybill data. It can be understood that for the same parameter data, it may be the sender identification data associated with a historical waybill data and the recipient identification data associated with another historical waybill data. If the object identified by a parameter data (as the sender or the recipient, or as the sender and the recipient at the same time) has a claim or complaint behavior in the historical period, the first warning value corresponding to the parameter data is greater than zero. If the object identified by a parameter data has not had a claim or complaint behavior in the historical period, the first warning value corresponding to the parameter data is zero.

[0037] In other embodiments, the warning value set may also only include the first warning value corresponding to the target parameter data, and the object identified by the target parameter data has had claims or complaints in the historical period. In this case, it can be understood that when the corresponding first warning value cannot be found in the warning value set according to the first parameter data, that is, the object identified by the first parameter data has not had claims or complaints in the historical period, and at this time, the first warning value corresponding to the first parameter data can be directly determined to be zero.

[0038] S106: Generate warning information for reminding a user to inspect the goods to be dispatched according to the first warning value.

[0039] The early warning information can be sent to the delivery end in the form of text or voice to remind the delivery personnel to conduct on-the-spot inspection of the goods when delivering them to the recipient. The inspection operation may include but is not limited to unpacking for inspection, taking photos for evidence, etc.

[0040] In one of the embodiments, the step of generating a warning message for reminding to perform an inspection operation on the goods to be dispatched according to the first warning value may specifically include: when the first warning value meets the warning condition, generating a warning message for reminding to perform an inspection operation on the goods to be dispatched. Specifically, when the first warning value is greater than or equal to the first threshold value, it is determined that the first warning value meets the warning condition. Among them, the first threshold value can be flexibly set according to actual needs and is not limited here. For example, when the value range of the first warning value is 0 to 10, the first threshold value can be set to 3, so that when the first warning value is greater than or equal to 3, a warning message is generated. The warning message may include the first warning value.

[0041] In the above-mentioned delivery warning method, the waybill information of the goods to be delivered is obtained, and the waybill information includes the first parameter data; the first warning value corresponding to the first parameter data is queried, and the first warning value is determined based on the historical waybill data; according to the first warning value, a warning information for reminding to inspect the goods to be delivered is generated. The corresponding warning information is generated accordingly, which is applicable to various types of waybill delivery warnings and has a wide range of applications. The delivery personnel can inspect the goods on the spot when delivering the goods based on the warning information, thereby effectively preventing the risk of malicious claims or customer complaints in the later stage.

[0042] In one embodiment, Figure 2 As shown, the method for determining the first warning value includes the following steps S202 to S206.

[0043] S202, obtaining historical waybill data within a historical period, and determining the historical waybill data associated with each target parameter data from the historical waybill data.

[0044] In one embodiment, the historical period is selected from the last six months. For example, if the current date is 2020 / 12 / 5, the historical period can be 2020 / 6 / 1 to 2020 / 11 / 30. The target parameter data is used to identify the target object that has had claims or complaints during the historical period. The target parameter data corresponds to the target object one by one. Complaints can include but are not limited to complaints about loss, damage, fresh food quality, express delivery temperature loss, cold transportation and other behaviors.

[0045] S204, according to the historical waybill data associated with each target parameter data, obtain the historical waybill quantity, historical claims data and historical complaint data corresponding to each target parameter data.

[0046] Historical claim data refers to waybill data for which claims have occurred, and historical complaint data refers to waybill data for which complaints have occurred. In one embodiment, historical claim data includes: historical claim amounts, and historical claim amounts corresponding to historical claim amounts; historical complaint data includes: historical complaint amounts.

[0047] The target object identified by the target parameter data may make claims or complaints as both the sender and the receiver. When the target object has only made claims or complaints when it was the sender, the historical waybill volume is the historical shipment volume, the historical claim volume is the number of waybill volumes with claims in the historical shipment volume, the historical claim amount is the total claim amount corresponding to the number of waybill volumes with claims in the historical shipment volume, and the historical complaint volume is the number of waybill volumes with complaints in the historical shipment volume.

[0048] When the target object has only made claims or complaints when acting as the recipient, the historical waybill volume is the historical receipt volume, the historical claim volume is the number of waybill that has made claims in the historical receipt volume, the historical claim amount is the total claim amount corresponding to the number of waybill that has made claims in the historical receipt volume, and the historical complaint volume is the number of waybill that has made complaints in the historical receipt volume.

[0049] When the target object has had claims or complaints as both the sender and the recipient, the historical waybill volume is the sum of the historical shipping volume and the historical receipt volume, the historical claims volume is the sum of the waybill volume with claims in the historical shipping volume and the waybill volume with claims in the historical receipt volume, the historical claim amount is the sum of the total compensation amount corresponding to the waybill volume with claims in the historical shipping volume and the total compensation amount corresponding to the waybill volume with claims in the historical receipt volume, and the historical complaint volume is the sum of the waybill volume with complaints in the historical shipping volume and the waybill volume with complaints in the historical receipt volume.

[0050] S206, determining a first warning value corresponding to each target parameter data based on the historical waybill volume, historical claims data, and historical complaint data corresponding to each target parameter data.

[0051] In one embodiment, Figure 3 As shown, based on the historical waybill volume, historical claims data and historical complaint data corresponding to each target parameter data, the step of determining the first warning value corresponding to each target parameter data may specifically include the following steps S302 to S306.

[0052] S302, obtaining the historical claim settlement rate corresponding to each target parameter data according to the ratio of the historical claim settlement amount corresponding to each target parameter data to the historical waybill amount.

[0053] In one embodiment, the ratio of the historical claims volume to the historical waybill volume corresponding to the target parameter data is used as the historical claims rate corresponding to the target parameter data. For example, assuming that the historical mailing volume corresponding to a target parameter data is 10 and the historical receipt volume is 100, if there are no waybills with claims in the historical mailing volume and the number of waybills with claims in the historical receipt volume is 5, then the historical claims rate corresponding to the target parameter data is 5 / 100; if the number of waybills with claims in the historical mailing volume is 1 and there are no waybills with claims in the historical receipt volume, then the historical claims rate corresponding to the target parameter data is 1 / 10; if the number of waybills with claims in the historical mailing volume is 1 and the number of waybills with claims in the historical receipt volume is 5, then the historical claims rate corresponding to the target parameter data is 6 / 110.

[0054] S304, obtaining the historical average claim amount corresponding to each target parameter data according to the ratio of the historical claim amount corresponding to each target parameter data to the historical claim amount.

[0055] Since the average claims for different waybills vary greatly and may range from 0 to millions, in one embodiment, the ratio of the historical claims corresponding to each target parameter data to the historical claims amount is smoothed and standardized to obtain the historical average claims corresponding to each target parameter data, thereby reducing the absolute difference in the data.

[0056] In one embodiment, the calculation formula of the historical average claim amount (represented by y) can be as follows: y=log(x+1), where x represents the ratio of the historical claim amount to the historical claim volume. For example, assuming that the historical shipment volume corresponding to a target parameter data is 10, and the historical receipt volume is 100, if there is no waybill with claims in the historical shipment volume, and the number of waybill with claims in the historical receipt volume is 5, and the corresponding total compensation is 10,000 yuan, then the historical average compensation amount corresponding to the target parameter data is log(10000 / 5+1); if the number of waybill with claims in the historical shipment volume is 1, and the corresponding total compensation is 10 yuan, and there is no waybill with claims in the historical receipt volume, then the historical average compensation amount corresponding to the target parameter data is log(10 / 1+1); if the number of waybill with claims in the historical shipment volume is 1, and the corresponding total compensation is 10 yuan, and the number of waybill with claims in the historical receipt volume is 5, and the corresponding total compensation is 10,000 yuan, then the historical average compensation amount corresponding to the target parameter data is log(10010 / 6+1).

[0057] After smoothing and normalizing with the log function, for target objects with successful claims (claim amount>0), the average claim amount approximately follows a normal distribution, which is closer to the actual business scenario. When the average claim amount is small, the difference between the average claim amounts of different target objects is more obvious, and a unit increase in the average claim amount has a greater impact on the warning value; when the average claim amount is large, the difference between the average claim amounts of different target objects decreases, and a unit increase in the average claim amount has little impact on the warning value.

[0058] S306, obtaining the historical complaint rate corresponding to each target parameter data according to the ratio of the historical complaint volume corresponding to each target parameter data to the historical waybill volume.

[0059] In one embodiment, the ratio of the historical complaint volume to the historical waybill volume corresponding to the target parameter data is used as the historical complaint rate corresponding to the target parameter data. For example, assuming that the historical mailing volume corresponding to a target parameter data is 10 and the historical receipt volume is 100, if there are no waybill complaints in the historical mailing volume, and the number of waybill complaints in the historical receipt volume is 5, then the historical complaint rate corresponding to the target parameter data is 5 / 100; if the number of waybill claims in the historical mailing volume is 1, and there are no waybill complaints in the historical receipt volume, then the historical complaint rate corresponding to the target parameter data is 1 / 10; if the number of waybill complaints in the historical mailing volume is 1, and the number of waybill complaints in the historical receipt volume is 5, then the historical complaint rate corresponding to the target parameter data is 6 / 110.

[0060] S308, determining the first warning value corresponding to each target parameter data based on the historical claim rate, historical average claim amount and historical complaint rate corresponding to each target parameter data.

[0061] The value range of the historical claim rate and historical complaint rate corresponding to the target parameter data is 0-1, and it is a skewed distribution, mainly concentrated in the low value area, that is, the probability of most target objects initiating claims or complaints is relatively low, and the claims or complaints are accidental events. The historical average claim amount after smoothing and standardization is approximately normally distributed, with a value range of 0-∞. As a result, the distribution differences between different features (such as the historical claim rate and the historical average claim amount, or the historical complaint rate and the historical average claim amount) are very large and not comparable. Based on this, the historical claim rate, historical complaint rate and historical average claim amount are standardized to reduce the distribution differences between different features and make them comparable.

[0062] In one embodiment, Figure 4 As shown, the step of determining the first warning value corresponding to each target parameter data based on the historical claim rate, historical average claim amount and historical complaint rate corresponding to each target parameter data may specifically include the following steps S402 to S408.

[0063] S402, obtaining the claim rate index value corresponding to each target parameter data according to the historical claim rate, claim rate reference value and claim rate difference weight corresponding to each target parameter data.

[0064] In one embodiment, a weighted-RSigmoid normalization function is used to normalize the historical claim rate. The specific formula may be as follows:

[0065]

[0066] Among them, L i represents the claim rate index value corresponding to the i-th target parameter data, xi represents the historical claim rate corresponding to the i-th target parameter data, x0 represents the claim rate reference value, and ω1 represents the claim rate difference weight. The claim rate difference weight can be set according to actual needs and is not limited here. In one embodiment, since the historical claim rate is severely skewed and most of it is distributed around 0, the difference is not obvious. Therefore, a larger claim rate difference weight (for example, set to 10) can be set to weigh the differences between different features.

[0067] In one embodiment, the method for determining the claim rate reference value includes: determining the claim rate corresponding to the preset quantile according to the historical claim rate corresponding to each target parameter data as the claim rate reference value. The preset quantile can be set according to the actual situation and is not limited here. For example, the preset quantile is the median, and x0 can be determined by the following median function: x0 = median[x1,…,x i ,…,x n1 ], where x i >0, n1 represents the number of target parameter data with a historical claim settlement rate greater than zero. In addition, the preset quantile may also be other quantiles such as 30%, 40%, etc.

[0068] S404, obtaining the claim amount index value corresponding to each target parameter data according to the historical average claim amount, the average claim amount reference value and the claim amount difference weight corresponding to each target parameter data.

[0069] In one embodiment, a weighted-RSigmoid normalization function is used to normalize the historical average claim amount. The specific formula may be as follows:

[0070]

[0071] Among them, M i represents the average claim value corresponding to the i-th target parameter data, y i Represents the historical average claim amount corresponding to the i-th target parameter data, y0 represents the average claim amount reference value, and ω2 represents the average claim amount difference weight. The average claim amount difference weight can be set according to actual needs and is not limited here. In one embodiment, since the average claim amounts corresponding to different target parameter data vary greatly, a smaller average claim amount difference weight (for example, set to 1) can be set relative to the claim rate difference weight (for example, set to 10) to weigh the differences between different features.

[0072] In one embodiment, the method for determining the average claim reference value includes: determining the average claim corresponding to a preset quantile according to the historical average claim corresponding to each target parameter data as the average claim reference value. The preset quantile can be set according to the actual situation and is not limited here. For example, the preset quantile is the median, and y0 can be determined by the following median function: y0 = median[y1,…,y i ,…,y n2 ], where y i >0, n2 represents the number of target parameter data with the historical average claim amount greater than zero. In addition, the preset quantile may also be other quantiles such as 30%, 40%, etc.

[0073] S406, obtaining the complaint rate index value corresponding to each target parameter data according to the historical complaint rate, complaint rate reference value and complaint rate difference weight corresponding to each target parameter data.

[0074] In one embodiment, a weighted-RSigmoid normalization function is used to normalize the historical complaint rate. The specific formula may be as follows:

[0075]

[0076] Among them, T i represents the complaint rate index value corresponding to the i-th target parameter data, z i Represents the historical complaint rate corresponding to the i-th target parameter data, z0 represents the complaint rate reference value, and ω3 represents the complaint rate difference weight. The complaint rate difference weight can be set according to actual needs and is not limited here. In one embodiment, since the historical complaint rate is severely skewed and most of it is distributed around 0, the difference is not obvious. Therefore, a larger complaint rate difference weight (for example, set to 10) can be set to weigh the differences between different features.

[0077] In one embodiment, the method for determining the reference value of the complaint rate includes: determining the complaint rate corresponding to the preset quantile according to the historical complaint rate corresponding to each target parameter data as the reference value of the complaint rate. The preset quantile can be set according to the actual situation and is not limited here. For example, the preset quantile is the median, and z0 can be determined by the following median function: z0 = median[z1,…,z i ,…,z n3 ], where z i >0, n3 represents the number of target parameter data with a historical complaint rate greater than zero. In addition, the preset quantile may also be other quantiles such as 30%, 40%, etc.

[0078] In the above embodiment, each feature (historical claim rate, historical average claim amount, and historical complaint rate) is mapped to the range of (0,1) through the weighted-RSigmoid normalization function, and a difference weight is introduced. The larger the difference weight, the more important the corresponding feature is, and the greater the impact of the slight difference in the feature on the warning value result. By setting the difference weight, the values ​​of different distributions in the same quantile interval (for example, the distributions of feature F1 and feature F2 are concentrated near the 30% quantile, but the difference between the two values ​​is large) will be approximately mapped to the same level, thereby eliminating the differences in the distribution of different features as much as possible and improving the rationality of the warning value.

[0079] S408, determining the first warning value corresponding to each target parameter data according to the claim settlement rate index value, claim amount index value and complaint rate index value corresponding to each target parameter data.

[0080] In one embodiment, the step of determining the first warning value corresponding to each target parameter data according to the claim rate index value, claim amount index value and complaint rate index value corresponding to each target parameter data can specifically be: performing weighted summation on the claim rate index value, claim amount index value and complaint rate index value corresponding to each target parameter data to obtain the first warning value corresponding to each target parameter data.

[0081] The specific calculation formula of the first warning value can be as follows:

[0082] E i =a1*L i +a2*M i +a3*T i

[0083] Among them, E i represents the first warning value corresponding to the i-th target parameter data, a1, a2 and a3 represent the index weights of the claim rate index value, the claim amount index value and the complaint rate index value respectively, and the values ​​of a1, a2 and a3 can be set according to actual needs and are not limited here. In one embodiment, if the actual business scenario pays more attention to the company's losses in order to achieve the control of claim costs, a higher weight can be set for the claim amount index value, that is, a2 takes a larger value, for example, a1, a2 and a3 are set to 0.35, 0.4 and 0.25 respectively.

[0084] The range of each indicator value obtained through the aforementioned embodiment is 0 to 1. In other embodiments, each indicator value can be multiplied by 10 to further standardize each indicator value to the range of 0 to 10, so that the range of the first warning value obtained based on the above calculation formula is also 0 to 10. Accordingly, the first warning value can be described by a score (0 to 10 points). The larger the first warning value, that is, the higher the score, means that the target object identified by the corresponding target parameter data is more likely to initiate a claim or complaint.

[0085] In one embodiment, when the waybill information also includes a declared value, and when it is determined that the warning condition is met based on the declared value, a warning message is generated to remind the user to perform an inspection operation on the goods to be dispatched.

[0086] Specifically, when the declared value is greater than or equal to the preset value, it can be determined that the warning condition is met, and at this time, a warning message can be directly generated to remind the delivery person to inspect the goods to be delivered. The preset value can be set according to the actual situation and is not limited here. For example, if the preset value is set to 1,000 yuan, when the declared value in the waybill information is greater than or equal to 1,000 yuan, the delivery person is reminded to inspect the goods on the spot when delivering them to the recipient.

[0087] In one embodiment, when the declared value is greater than or equal to the preset value, a second warning value is obtained according to the declared value, and according to the second warning value, warning information is generated for reminding to perform inspection operations on the goods to be dispatched.

[0088] A mapping relationship between the declared value and the second warning value can be established in advance, and the corresponding second warning value can be obtained according to the declared value and the mapping relationship. In one embodiment, the mapping relationship is as follows:

[0089]

[0090] Wherein, v represents the declared value, and f(v) represents the second warning value. When the second warning value is greater than or equal to the second threshold, a warning message is generated to remind the goods to be inspected. The second threshold can be flexibly set according to actual needs and is not limited here. For example, when the value range of the second warning value is 0 to 10, the second threshold can be set to 3, so that when the second warning value is greater than or equal to 3, a warning message is generated. The warning message may include the second warning value.

[0091] In one embodiment, when the declared value is less than the preset value, the step of querying the first warning value corresponding to the first parameter data is entered.

[0092] In this embodiment, it is pre-determined whether the waybill information includes the declared value and the size relationship between the declared value and the preset value is determined. When the waybill information includes the declared value and the declared value is greater than or equal to the preset value, the warning information is directly generated. When the waybill information does not include the declared value, or includes the declared value but the declared value is less than the preset value, the step of querying the first warning value corresponding to the first parameter data is entered, and the warning information is generated according to the first warning value. Based on this, combined with the waybill's declared value and parameter data, the claim or complaint risk of the waybill is warned from multiple dimensions, thereby improving the accuracy of the warning.

[0093] In one embodiment, the method further includes the following steps: querying whether the first parameter data belongs to a data blacklist; when the first parameter data belongs to the data blacklist, generating warning information for reminding to perform inspection operations on the goods to be delivered; when the first parameter data does not belong to the data blacklist, entering the step of querying the first warning value corresponding to the first parameter data.

[0094] The data blacklist may include, but is not limited to, parameter data recorded by manual customer service for identifying malicious claims or complaint objects, and the corresponding interface may be called to query whether the data blacklist contains the first parameter data. When the first parameter data is included in the data blacklist, an early warning message is directly generated. In other embodiments, the warning value range is set to 0 to 10. When the first parameter data is included in the data blacklist, the third warning value of the waybill is determined (named the third warning value here to distinguish it from the first warning value and the second warning value in the previous text), and the early warning message is generated according to the third warning value. Specifically, the third warning value may be recorded as the maximum value of 10, and the third warning value may be included in the early warning message.

[0095] When the data blacklist does not contain the first parameter data, the step of querying the first warning value corresponding to the first parameter data is entered, and warning information is generated according to the first warning value. Based on this, the data blacklist is further combined to make the warning range cover more claim or complaint risk objects, thereby improving the accuracy of the warning.

[0096] In one embodiment, after obtaining the waybill information of each cargo to be delivered, the waybill for subsequent early warning judgment is screened out according to the waybill information. When the waybill information does not meet the requirements (such as the waybill number or the consignee is empty), the waybill is filtered out; when the consigned object type contained in the waybill information is a document type (such as documents, bills, books and picture albums, etc.), the waybill is filtered out; when it is determined according to the waybill information that the waybill is an insured waybill, the waybill is filtered out (for insured waybill, the courier is more sensitive and no reminder is required). After filtering out the above waybills, the remaining waybills are identified, and the waybills with high claims or complaint risks are identified, and the early warning information is sent to the delivery end. After receiving the early warning information, the delivery end reminds the delivery person to open the box for inspection and take photos on the delivery page, thereby improving the sensitivity of the delivery person, thereby effectively preventing malicious claims and complaints and reducing management costs.

[0097] In one embodiment, Figure 5 As shown, a delivery warning method is provided, including the following steps S501 to S507.

[0098] S501, obtaining waybill information of the goods to be dispatched, where the waybill information includes first parameter data;

[0099] S502, check whether the waybill information contains the declared value, if so, go to step S503, if not, go to step S505.

[0100] S503, determine whether the declared value is greater than or equal to the preset value, if so, proceed to step S504, if not, proceed to step S505.

[0101] S504: Obtain a second warning value according to the declared value, and generate warning information according to the second warning value.

[0102] S505, query whether the first parameter data belongs to the data blacklist, if so, go to step S506, if not, go to step S507.

[0103] S506: Determine a third warning value, and generate warning information according to the third warning value.

[0104] S507, querying a first warning value corresponding to the first parameter data, and generating warning information according to the first warning value.

[0105] For the detailed description of steps S501 to S507, please refer to the above embodiment, which will not be repeated here. In this embodiment, the declared value of the waybill, the data blacklist and the first parameter data are combined to warn the claim or complaint risk of the waybill in multiple dimensions, thereby improving the accuracy of the warning.

[0106] In one embodiment, the implementation effect of the delivery warning method of the previous embodiment is evaluated, and the following analysis is respectively conducted from the perspectives of execution, claims settlement, and liability determination.

[0107] Get the number of waybills that the delivery personnel are reminded to perform unpacking inspection (indicated by Q) and the number of waybills that the delivery personnel have performed unpacking inspection in Q (indicated by Q) during the target period after implementation. Y Indicates the number of waybills for which the courier does not perform unpacking inspection in Q N Q Y The number of waybills with claims (in Q Y_Y Q Y The total compensation for claims (in P Y_Y Q N The number of waybills with claims (in Q N_Y Q N The total compensation for claims (in P N_Y Q Y_Y The number of waybills that are assigned to the staff (using Q Y_Y_1 Q Y_Y The number of waybills assigned to the dispatcher (in Q Y_Y_2 Q N_Y The number of waybills that are assigned to the staff (using Q N_Y_1 indicates), and Q N_Y The number of waybills assigned to the dispatcher (in Q N_Y_2 express).

[0108] Analyze the execution of the delivery personnel when they receive the unpacking inspection reminder to obtain the execution rate: Execution rate = Q Y / Q.

[0109] The main purpose of the unpacking inspection function is to prevent malicious claims, minimize claims, and reasonably control claims costs. Based on this, the claims of executed and unexecuted waybills are analyzed to obtain the claim rate and average claim amount: Executed claim rate = Q Y_Y / Q Y , non-execution claim rate = Q N_Y / Q N , average claim amount = P Y_Y / Q Y_Y , average claim amount not executed = P N_Y / Q N_Y .

[0110] The unpacking inspection function is mainly aimed at the delivery process. Based on this, the situation of assigning responsibility to the delivery personnel is analyzed to obtain the proportion of assigned responsibility: the proportion of assigned responsibility to the delivery personnel = Q Y_Y_2 / Q Y_Y_1 , the proportion of delivery personnel who do not fulfill their responsibilities = QN_Y_2 / Q N_Y_1 .

[0111] In one embodiment, the evaluation results are shown in Table 1 below:

[0112] Table 1

[0113]

[0114] From the results in the table above, we can see that the unpacking inspection reminder can effectively reduce the cost of claims and achieve reasonable control of claims costs. In addition, the unpacking inspection can effectively reduce the proportion of responsibility assigned to the delivery personnel, so that there is more sufficient evidence for claim determination, which helps to promote fair and just claim determination.

[0115] It should be understood that, although the steps in each flow chart involved in the above-described embodiment are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a portion of the steps in each flow chart involved in the above-described embodiment may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the steps or stages in other steps.

[0116] In one embodiment, Figure 6 As shown, a delivery warning device 600 is provided, comprising: an acquisition module 610, a query module 620 and a warning module 630, wherein:

[0117] The acquisition module 610 is used to acquire the waybill information of the goods to be delivered, and the waybill information includes the first parameter data.

[0118] The query module 620 is used to query the first warning value corresponding to the first parameter data, and the first warning value is determined based on the historical waybill data.

[0119] The warning module 630 is used to generate warning information for reminding to inspect the goods to be dispatched according to the first warning value.

[0120] In one embodiment, the device further includes a determination module for determining the first warning value. The determination module includes: an acquisition unit, a processing unit and a determination unit, wherein:

[0121] The acquisition unit is used to acquire historical waybill data within a historical period, and determine the historical waybill data associated with each target parameter data from the historical waybill data.

[0122] The processing unit is used to obtain the historical waybill quantity, historical claims data and historical complaint data corresponding to each target parameter data according to the historical waybill data associated with each target parameter data.

[0123] A determination unit is used to determine the first warning value corresponding to each target parameter data based on the historical waybill volume, historical claims data and historical complaint data corresponding to each target parameter data.

[0124] In one embodiment, the historical claims data includes: historical claims volume, and historical claims corresponding to the historical claims volume, and the historical complaint data includes: historical complaints. When the determination unit determines the first warning value corresponding to each target parameter data based on the historical waybill volume, historical claims data, and historical complaint data corresponding to each target parameter data, it is specifically used to: obtain the historical claims rate corresponding to each target parameter data according to the ratio of the historical claims volume corresponding to each target parameter data to the historical waybill volume; obtain the historical average claims corresponding to each target parameter data according to the ratio of the historical claims corresponding to each target parameter data to the historical claims volume; obtain the historical complaint rate corresponding to each target parameter data according to the ratio of the historical complaints corresponding to each target parameter data to the historical waybill volume; determine the first warning value corresponding to each target parameter data based on the historical claims rate, historical average claims, and historical complaint rate corresponding to each target parameter data.

[0125] In one embodiment, when the determination unit obtains the historical average claim amount corresponding to each target parameter data based on the ratio of the historical claim amount corresponding to each target parameter data to the historical claim amount, it is specifically used to: smooth and normalize the ratio of the historical claim amount corresponding to each target parameter data to the historical claim amount to obtain the historical average claim amount corresponding to each target parameter data.

[0126] In one embodiment, when the determination unit determines the first warning value corresponding to each target parameter data based on the historical claim rate, historical average claim amount and historical complaint rate corresponding to each target parameter data, it is specifically used to: obtain the claim rate index value corresponding to each target parameter data according to the historical claim rate, claim rate reference value and claim rate difference weight corresponding to each target parameter data; obtain the claim amount index value corresponding to each target parameter data according to the historical average claim amount, average claim amount reference value and claim amount difference weight corresponding to each target parameter data; obtain the complaint rate index value corresponding to each target parameter data according to the historical complaint rate, complaint rate reference value and complaint rate difference weight corresponding to each target parameter data; determine the first warning value corresponding to each target parameter data according to the claim rate index value, claim amount index value and complaint rate index value corresponding to each target parameter data.

[0127] In one embodiment, when the determination unit determines the first warning value corresponding to each target parameter data based on the claim rate index value, claim amount index value and complaint rate index value corresponding to each target parameter data, it is specifically used to: perform weighted summation of the claim rate index value, claim amount index value and complaint rate index value corresponding to each target parameter data to obtain the first warning value corresponding to each target parameter data.

[0128] In one embodiment, the determination unit is further used to determine the claim rate corresponding to the preset percentile based on the historical claim rates corresponding to each target parameter data as a claim rate reference value.

[0129] In one embodiment, the determination unit is further used to determine the historical average claim amount corresponding to a preset percentile based on the historical average claim amount corresponding to each target parameter data, as a reference value for the average claim amount.

[0130] In one embodiment, the determination unit is further used to: determine the historical complaint rate corresponding to a preset quantile according to the historical complaint rate corresponding to each target parameter data, as a complaint rate reference value.

[0131] In one embodiment, the warning module 630 is also used to: when the waybill information also includes a declared value, and when it is determined that the warning condition is met based on the declared value, generate warning information for reminding to inspect the goods to be delivered.

[0132] In one embodiment, the device further comprises a processing module for obtaining a second warning value according to the declared value when the declared value is greater than or equal to the preset value. The warning module 630 is also used to generate warning information for reminding to perform inspection operations on the goods to be dispatched according to the second warning value.

[0133] In one embodiment, the processing module is further used to: when the declared value is less than a preset value, enter the step of querying a first warning value corresponding to the first parameter data.

[0134] In one embodiment, the query module 620 is further used to query whether the first parameter data belongs to the data blacklist. The warning module 630 is further used to generate warning information for reminding to perform inspection operations on the goods to be delivered when the first parameter data belongs to the data blacklist. The processing module is further used to enter the step of querying the first warning value corresponding to the first parameter data when the first parameter data does not belong to the data blacklist.

[0135] For the specific definition of the delivery warning device, please refer to the definition of the delivery warning method above, which will not be repeated here. Each module in the above-mentioned delivery warning device can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0136] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a delivery warning method is implemented.

[0137] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a delivery warning method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0138] Those skilled in the art will understand that Figure 7 or Figure 8The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0139] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0140] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0141] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-mentioned method embodiments.

[0142] It should be understood that the terms "first", "second", etc. in the above embodiments are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. For the description of the numerical range, the term "multiple" is understood to be equal to or greater than two.

[0143] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0144] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0145] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A delivery warning method, characterized in that: The method comprises: Acquire waybill information of the goods to be dispatched, wherein the waybill information includes first parameter data, wherein the first parameter data includes consignee identification data; Querying a first warning value corresponding to the first parameter data, where the first warning value is determined based on historical waybill data; The method for determining the first warning value includes: obtaining historical waybill data within a historical period, determining the historical waybill data associated with each target parameter data from the historical waybill data, wherein the target parameter data is used to identify the target object that has had a claim or complaint behavior within the historical period; obtaining the historical waybill volume, historical claim data and historical complaint data corresponding to each target parameter data based on the historical waybill data associated with each target parameter data; determining the historical claim rate, historical average claim amount and historical complaint rate corresponding to each target parameter data based on the historical waybill volume, historical claim data and historical complaint data corresponding to each target parameter data; determining the first warning value corresponding to each target parameter data based on the historical claim rate, historical average claim amount and historical complaint rate corresponding to each target parameter data; According to the first warning value, a warning message is generated for prompting an inspection operation to be performed on the goods to be dispatched.

2. The method according to claim 1, characterized in that The historical claims data includes: historical claims amount, and historical claims amount corresponding to the historical claims amount; the historical complaint data includes: historical complaint amount; Determining the historical claim rate, historical average claim amount and historical complaint rate corresponding to each target parameter data respectively according to the historical waybill volume, historical claim data and historical complaint data corresponding to each target parameter data includes: Obtaining the historical claim settlement rate corresponding to each target parameter data according to the ratio of the historical claim settlement amount to the historical waybill amount corresponding to each target parameter data; According to the ratio of the historical claim amount corresponding to each target parameter data to the historical claim amount, the historical average claim amount corresponding to each target parameter data is obtained; According to the ratio of the historical complaint volume corresponding to each target parameter data to the historical waybill volume, the historical complaint rate corresponding to each target parameter data is obtained.

3. The method according to claim 2, characterized in that The step of obtaining the historical average claim amount corresponding to each target parameter data according to the ratio of the historical claim amount to the historical claim amount includes: The ratio of the historical claim amount to the historical claim settlement amount corresponding to each target parameter data is smoothed and standardized to obtain the historical average claim amount corresponding to each target parameter data.

4. The method according to claim 1, characterized in that: The determining of the first warning value corresponding to each target parameter data based on the historical claim rate, the historical average claim amount and the historical complaint rate corresponding to each target parameter data includes: According to the historical claim rates, claim rate reference values ​​and claim rate difference weights corresponding to the target parameter data, the claim rate index values ​​corresponding to the target parameter data are obtained, wherein the claim rate difference weights are used to weigh the differences between the historical claim rates corresponding to the target parameter data. The process of obtaining the claim rate index values ​​is expressed by the formula: L i represents the claim rate index value corresponding to the i-th target parameter data, x i represents the historical claim rate corresponding to the i-th target parameter data, x0 represents the claim rate reference value, and ω1 represents the claim rate difference weight; According to the historical average claim amount, the average claim amount reference value and the claim amount difference weight corresponding to each of the target parameter data, the claim amount index value corresponding to each of the target parameter data is obtained, wherein the claim amount difference weight is used to weigh the difference between the historical average claim amounts corresponding to each of the target parameter data. The process of obtaining the claim rate index value is expressed by the formula: M i Indicates the claim value corresponding to the i-th target parameter data, y i represents the historical average claim amount corresponding to the i-th target parameter data, y0 represents the average claim amount reference value, and ω2 represents the average claim amount difference weight; According to the historical complaint rate, complaint rate reference value and complaint rate difference weight corresponding to each target parameter data, the complaint rate index value corresponding to each target parameter data is obtained, wherein the complaint rate difference weight is used to weigh the difference between the historical complaint rates corresponding to each target parameter data, and the process of obtaining the complaint rate index value is expressed by the formula: T i represents the complaint rate index value corresponding to the i-th target parameter data, z i represents the historical complaint rate corresponding to the i-th target parameter data, z0 represents the reference value of the complaint rate, and ω3 represents the difference weight of the complaint rate; According to the claim rate index value, claim amount index value and complaint rate index value corresponding to each of the target parameter data, the first warning value corresponding to each of the target parameter data is determined.

5. The method according to claim 4, characterized in that Determining the first warning value corresponding to each target parameter data according to the claim settlement rate index value, claim settlement amount index value, and complaint rate index value corresponding to each target parameter data includes: The claim rate index value, claim amount index value and complaint rate index value corresponding to each of the target parameter data are weightedly summed to obtain the first warning value corresponding to each of the target parameter data.

6. The method according to claim 4, characterized in that Include at least one of the following: Item 1: The method for determining the claim rate reference value comprises: determining the claim rate corresponding to a preset quantile as the claim rate reference value according to the historical claim rates corresponding to each of the target parameter data; Item 2: The method for determining the average claim settlement reference value includes: determining the historical average claim settlement corresponding to a preset quantile according to the historical average claim settlement corresponding to each of the target parameter data as the average claim settlement reference value; Item 3: The method for determining the complaint rate reference value includes: determining the historical complaint rate corresponding to a preset quantile based on the historical complaint rate corresponding to each of the target parameter data, as the complaint rate reference value.

7. The method according to claim 1, characterized in that Also includes: When the waybill information also includes a declared value, and when it is determined that the warning condition is met based on the declared value, a warning message is generated to remind the user to perform an inspection operation on the goods to be dispatched.

8. The method according to claim 7, characterized in that Also includes at least one of the following two: Item 1: when the declared value is greater than or equal to the preset value, a second warning value is obtained according to the declared value, and according to the second warning value, a warning message is generated for reminding to inspect the goods to be dispatched; Item 2: When the declared value is less than the preset value, entering the step of querying the first warning value corresponding to the first parameter data.

9. The method according to claim 1, characterized in that: Also includes: Query whether the first parameter data belongs to the data blacklist; When the first parameter data belongs to the data blacklist, generating early warning information for reminding to perform inspection operations on the goods to be dispatched; When the first parameter data does not belong to the data blacklist, the step of querying a first warning value corresponding to the first parameter data is entered.

10. A delivery warning device, characterized in that: The device comprises: An acquisition module, used to acquire waybill information of the goods to be delivered, wherein the waybill information includes first parameter data, wherein the first parameter data includes consignee identification data; A query module, used to query a first warning value corresponding to the first parameter data, wherein the first warning value is determined based on historical waybill data; The device further comprises a determination module, configured to determine the first warning value; The determination module comprises: The acquisition unit is used to acquire historical waybill data within a historical period, and determine the historical waybill data associated with each target parameter data from the historical waybill data, wherein the target parameter data is used to identify the target object that has had a claim or complaint behavior within the historical period; the processing unit is used to obtain the historical waybill volume, historical claim data and historical complaint data corresponding to each target parameter data based on the historical waybill data associated with each target parameter data; the determination unit is used to determine the historical claim rate, historical average claim amount and historical complaint rate corresponding to each target parameter data based on the historical waybill volume, historical claim data and historical complaint data corresponding to each target parameter data; based on the historical claim rate, historical average claim amount and historical complaint rate corresponding to each target parameter data, determine the first warning value corresponding to each target parameter data; The early warning module is used to generate early warning information for reminding the inspection operation of the goods to be dispatched according to the first early warning value.

11. The device according to claim 10, characterized in that The historical claims data include: historical claims volume, and historical claims amounts corresponding to the historical claims volume, and the historical complaint data include: historical complaints volume; the determination unit is also used to obtain the historical claims rate corresponding to each target parameter data according to the ratio of the historical claims volume corresponding to each target parameter data to the historical waybill volume; obtain the historical average claims amount corresponding to each target parameter data according to the ratio of the historical claims amount corresponding to each target parameter data to the historical claims volume; obtain the historical complaint rate corresponding to each target parameter data according to the ratio of the historical complaints volume corresponding to each target parameter data to the historical waybill volume.

12. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images