Tag push method, device, electronic device, and computer-readable storage medium

Abstract

The present application provides a tag pushing method, device, electronic device, and computer-readable storage medium for pushing tags of outlets in an arbitration system to associated platforms. The method includes: obtaining arbitration data of the outlet in the current settlement cycle; detecting whether the arbitration data of the outlet in the current settlement cycle meets the preset conditions corresponding to each tag, respectively, to obtain the tag of the outlet in the current settlement cycle; when the tag of the outlet in the current settlement cycle does not match the tag of the outlet in the previous settlement cycle, pushing the tag of the outlet in the current settlement cycle to one or more associated platforms of the arbitration system to update the tag of the outlet in each of the associated platforms. The tags of each outlet determined in the arbitration system in the current settlement cycle are synchronized to other associated platforms, so that the associated platforms can quickly and timely obtain the accurate tags of each outlet.

Description

Technical Field

[0001] The present application relates to the technical fields of logistics and deep learning, and in particular to a label pushing method, device, electronic device, and computer-readable storage medium. Background Art

[0002] During express delivery, many orders are delayed from being delivered to customers on time, with guaranteed quality, and in sufficient quantity for various reasons. Orders experiencing delivery issues require an arbitration system to determine responsibility and settle claims. Previously, arbitration orders (orders entering the arbitration system are referred to as arbitration orders) were processed manually, with tags added to each branch, basic branch assessment information output, and manual synchronization to other platforms (systems). This method was inefficient, time-consuming, and unable to handle large volumes of orders or branches simultaneously.

[0003] Based on this, the present application provides a tag push method, device, electronic device and computer-readable storage medium to solve the problems existing in the above-mentioned prior art. Summary of the Invention

[0004] The purpose of this application is to provide a tag push method, device, electronic device and computer-readable storage medium to obtain arbitration data of each outlet in each settlement cycle, automatically identify the tag corresponding to each outlet and push it to the associated platform, so that the associated platform can quickly obtain relevant information.

[0005] The purpose of this application is achieved by the following technical solutions:

[0006] In a first aspect, the present application provides a tag push method for pushing tags of nodes in an arbitration system to an associated platform, the method comprising:

[0007] Obtaining arbitration data of the outlet in the current settlement period, the arbitration data of the outlet in the current settlement period is used to indicate one or more of the following: the number of confirmed tickets for unreasonable charges, the number of confirmed tickets for service quality complaints, the number of confirmed tickets for failure to provide upstairs service, the number of tickets for false signatures and false problem items, the proportion of confirmed tickets for delivery delays, the number of items approved by weight and square difference categories, and the number of tickets for irregular packaging errors;

[0008] respectively detecting whether the arbitration data of the outlet in the current settlement period meets the preset conditions corresponding to each tag, so as to obtain the tag of the outlet in the current settlement period;

[0009] When the tag of the outlet in the current settlement cycle does not match the tag of the outlet in the previous settlement cycle, the tag of the outlet in the current settlement cycle is pushed to one or more associated platforms of the arbitration system to update the tag of the outlet in each of the associated platforms.

[0010] The beneficial effect of this technical solution is that: first, the arbitration data of the outlet in the current settlement cycle is obtained, and the arbitration data is respectively tested to see whether it meets the preset conditions corresponding to each tag, thereby obtaining the outlet's tag in the current settlement cycle. When the outlet's tag in the current settlement cycle does not match the tag in the previous settlement cycle, the tag of the outlet on the associated platform is updated. In other words, after obtaining the arbitration data of each outlet in the current settlement cycle, the tag of the current settlement cycle can be automatically detected for it, and then the tag of the outlet can be compared to see whether it has changed compared with the previous settlement cycle. If it has changed, the outlet's tag on the associated platform needs to be updated. Because the arbitration data can indicate one or more of the following: the number of tickets for illegal charges, the number of tickets for service quality complaints, the number of tickets for failure to provide upstairs service, the number of tickets for false receipts and false problem items, the proportion of tickets for delivery delays, the number of items approved for weight and square difference categories, and the number of tickets for irregular packaging errors, in actual applications, according to the different preset conditions corresponding to each tag, the arbitration data can be compared with the preset conditions corresponding to each tag to determine the outlet's tag. The advantage of this is that (unlike the information recommendation process which requires setting a large number of labels for massive data), the number of labels in the arbitration system is limited (the number does not exceed a preset threshold, such as 7, 8, 10, 20, 50, 100, etc.), so the preset conditions corresponding to each label can be set in advance (for example, numerical conditions for one or more arbitration data). For each network point, the arbitration data of the network point is tested separately to see whether it meets the preset conditions corresponding to each label, and whether each label is used as the label corresponding to the network point is determined one by one. This matching method has a limited total amount of calculation and a high accuracy of the calculation result. As long as the arbitration data is correct, the label added to the network point will not be wrong. It is suitable for platforms such as arbitration systems that value fairness and where misjudgment can have a significant impact. The labels of each outlet determined in the arbitration system during the current settlement cycle are synchronized to other related platforms, so that the related platforms can quickly and timely obtain the accurate labels of each outlet (in the current settlement cycle), which facilitates the subsequent grade adjustment, settlement method adjustment, task allocation, business adjustment, etc. for each outlet in the related platforms, so as to achieve the purpose of clear, timely and accurate rewards and punishments, and supervise and encourage each outlet to provide high-quality services.

[0011] In some optional implementations, obtaining the arbitration data of the outlet in the current settlement cycle includes:

[0012] When the number of orders of the outlet in the current settlement period is not less than the first quantity threshold or the number of arbitration orders is not less than the second quantity threshold, obtaining order information of the arbitration orders of the outlet in the current settlement period;

[0013] Based on the order information of the arbitration order of the outlet in the current settlement period, the arbitration data of the outlet in the current settlement period is obtained.

[0014] The beneficial effect of this technical solution is that it is statistically significant only when the number of orders at the outlet in the current settlement cycle (i.e., the current settlement cycle) is large, or the number of arbitration orders at the outlet in the current settlement cycle is large, to avoid the situation where the error is too large when the number of orders or the number of arbitration orders is too small. In addition, if the number of orders at a certain outlet each month is too small, the value of labeling it is low, and there is no need to use the method provided by this application to calculate the corresponding label, resulting in a waste of computing resources and computing power. When the total number of orders at the outlet is large or the number of arbitration orders is large, by obtaining the order information that needs to be arbitrated uploaded by various departments in the arbitration system (database), the arbitration data of the outlet in the current settlement cycle is obtained, and the order processing situation is evaluated. The obtained arbitration data is detailed, accurate, and highly automated, which is convenient for assessing logistics outlets.

[0015] In some optional implementations, obtaining arbitration data of the outlet in the current settlement period based on order information of arbitration orders of the outlet in the current settlement period includes:

[0016] Based on the order information of arbitration orders of the outlet in the current settlement cycle, a classification result of each arbitration order is obtained, where the classification result is used to indicate at least one of the following: whether arbitrary charges are established, whether complaints about service quality are established, whether complaints about failure to provide door-to-door service are established, whether there are false signatures and false problem items, whether delivery delays are established, whether the weight and dimensions difference categories are approved, and whether irregular packaging errors are established;

[0017] Based on the classification result of each arbitration order, the arbitration data of the outlet in the current settlement cycle is obtained.

[0018] This technical solution has the beneficial effect of utilizing the order information of arbitration orders to obtain classification results for arbitration orders. This classification result can indicate whether the branch has engaged in excessive charges, service quality complaints, failure to provide door-to-door service, false signatures and false problem items, delivery delays, weight and volume discrepancies, or irregular packaging. Furthermore, based on the classification results of all arbitration orders within the branch's corresponding current settlement period, the branch's arbitration data for the current settlement period can be obtained. Obtaining arbitration data using this method clearly identifies the classification results for each arbitration order, achieving transparency and openness in the arbitration processing process, high reliability, and ease of traceability and accountability.

[0019] In some optional implementations, obtaining a classification result of each arbitration order based on order information of the arbitration order of the outlet in the current settlement cycle includes:

[0020] Inputting the order information of each arbitration order of the outlet in the current settlement period into the classification model to obtain a classification result for each arbitration order;

[0021] The training process of the order classification model includes:

[0022] Obtaining a training set, the training set including a plurality of training data, each of the training data including order information of a sample arbitration order and labeled data of a classification result of the sample arbitration order;

[0023] For each training data in the training set, perform the following processing:

[0024] Inputting the order information of the sample arbitration orders in the training data into a preset deep learning model to obtain prediction data of the classification results of the sample arbitration orders;

[0025] updating the model parameters of the deep learning model based on the predicted data and the labeled data of the classification results of the sample arbitration orders;

[0026] Check whether the preset training end condition is met; if so, use the trained deep learning model as the order classification model; if not, continue training the deep learning model using the next training data.

[0027] The beneficial effect of this technical solution is that the order classification model can be trained by a large amount of training data, and can predict the corresponding output data (i.e., the classification result of the arbitration order, such as whether the outlet has any random charges, service quality complaints, failure to provide upstairs service, false signatures and false problem items, delivery delays, weight and volume differences, irregular packaging, etc.) for different input data (i.e., the order information of the arbitration order, such as the order number, creation time, expected delivery time, shipping address, delivery address, consignee name, consignee phone number, collection point, carrier, distribution center, express delivery point, scanning record, item name, item type, item quantity, item weight, item volume, weather type, epidemic prevention and control type, etc.). It has a wide range of applications and a high level of intelligence. By designing, establishing an appropriate number of neuron computing nodes and a multi-layer operation hierarchy, and selecting appropriate input and output layers, a preset deep learning model can be obtained. Through learning and tuning of the preset deep learning model, a functional relationship from input to output is established. Although the functional relationship between input and output cannot be found 100%, the actual correlation relationship can be approached as closely as possible. The order classification model trained in this way can obtain the classification results of arbitration orders based on the order information of arbitration orders, and the calculation results are highly accurate and reliable.

[0028] In some optional embodiments, the labels include customer service labels and operation quality control labels;

[0029] The customer service labels include: low poor service quality, medium poor service quality, and high poor service quality;

[0030] The operation quality control labels include: low level of weight theft and prescription theft, medium level of weight theft and prescription theft, high level of weight theft and prescription theft, and irregular packaging errors.

[0031] The beneficial effect of this technical solution is that it divides labels into two categories: customer service labels generated by arbitration orders uploaded by the customer service department, and operational quality control labels generated by arbitration orders uploaded by the operational quality control department. In other words, two types of labels are set based on the upload source of the arbitration order (customer service department and operational quality control department) to reflect the problems existing in the branch's customer service and operational quality control, such as poor service quality (uploaded by the customer service department) and problems such as weight theft, irregularities in packaging, and irregularities in packaging (uploaded by the operational quality control department). This allows the labels to reflect the branch's service level and operational quality control in a three-dimensional and detailed manner. Compared to setting only customer service labels or operational quality control labels, these two dimensions can more comprehensively assess the branch's overall level.

[0032] In some optional implementations, respectively detecting whether the arbitration data of the outlet in the current settlement period meets a preset condition corresponding to each tag to obtain the tag of the outlet in the current settlement period includes:

[0033] respectively detecting whether the arbitration data of the outlets in the current settlement period meet the preset conditions corresponding to each of the customer service tags;

[0034] When it is detected that the arbitration data of the outlet in the current settlement period meets the preset conditions corresponding to at least one of the customer service tags, the customer service tags that meet the conditions in the current settlement period are added to the tags of the outlet in the current settlement period;

[0035] When it is detected that the arbitration data of the outlet in the current settlement period does not meet the preset conditions corresponding to any customer service label, detecting whether the arbitration data of the outlet in the previous settlement period meets the preset conditions corresponding to each customer service label;

[0036] When it is detected that the arbitration data of the outlet in the previous settlement period meets the preset conditions corresponding to at least one of the customer service tags, the customer service tags that meet the conditions in the previous settlement period are added to the tags of the outlet in the current settlement period;

[0037] When it is detected that the arbitration data of the branch in the previous settlement period does not meet the preset conditions corresponding to any customer service label, cancel the customer service label of the branch in the current settlement period;

[0038] respectively detecting whether the arbitration data of the outlets in the current settlement period meet the preset conditions corresponding to each of the operation quality control labels;

[0039] When it is detected that the arbitration data of the outlet in the current settlement period meets the preset conditions corresponding to at least one of the operation quality control tags, the operation quality control tags that meet the conditions in the current settlement period are added to the tags of the outlet in the current settlement period;

[0040] When it is detected that the arbitration data of the outlet in the current settlement period does not meet the preset conditions corresponding to any operation quality control label, the operation quality control label of the outlet in the current settlement period is cancelled.

[0041] The beneficial effect of this technical solution is that: for customer service tags, once they are tagged, they can only be cancelled if there are no customer service tags for two consecutive settlement cycles. That is to say, it not only depends on whether the preset conditions of the customer service tags are met in the current settlement cycle, but also whether the preset conditions of the customer service tags are met in the previous settlement cycle. The customer service tags can only be cancelled if the preset conditions of the customer service tags are not met for two consecutive settlement cycles (that is, the latest two settlement cycles); and for operation quality control tags, after they are tagged, they can be cancelled as long as the preset conditions of the operation quality control tags are not met in the current settlement cycle. In comparison, customer service labels are retroactive (the past here refers to the previous settlement cycle), while operational quality control labels are not retroactive. This is because the problems corresponding to customer service labels are relatively more serious. This is a setting made based on the specific circumstances in actual applications. Treating customer service labels and operational quality control labels differently is part of refined management, because the problems reflected by operational quality control labels may be unintentional mistakes or unconscious actions, while the problems reflected by customer service labels are more serious and severe in nature, and are often subjective and intentional mistakes. Imposing more severe disciplinary measures can help outlets correctly recognize the seriousness of customer service issues and achieve the effect of promoting improvement through assessment.

[0042] In some optional implementations, the process of updating the label of the network point in each of the associated platforms includes:

[0043] Clearing existing tags of the outlet in the associated platform;

[0044] The received label of the outlet in the current settlement period is used as the label of the outlet in the associated platform.

[0045] The beneficial effect of this technical solution is that when updating the outlet labels in the associated platform, the existing labels are first cleared and then the outlet labels are reset. Compared with comparing each existing label one by one to see whether it needs to be retained and then determining whether a new label needs to be added, this is convenient and fast, and the update efficiency is high.

[0046] In a second aspect, the present application provides a label pushing device for pushing labels of network points in an arbitration system to an associated platform, the device comprising:

[0047] a data acquisition module, configured to acquire arbitration data of the outlet in the current settlement period, wherein the arbitration data of the outlet in the current settlement period is used to indicate one or more of the following: the number of confirmed tickets for unreasonable charges, the number of confirmed tickets for service quality complaints, the number of confirmed tickets for failure to provide upstairs service, the number of tickets for false receipts and false problem items, the proportion of confirmed tickets for delivery delays, the number of items approved for weight and square difference categories, and the number of tickets for irregular packaging errors;

[0048] a tag acquisition module, configured to detect whether the arbitration data of the outlet in the current settlement period meets the preset conditions corresponding to each tag, so as to obtain the tag of the outlet in the current settlement period;

[0049] A label update module is used to push the label of the outlet in the current settlement cycle to one or more associated platforms of the arbitration system to update the label of the outlet in each of the associated platforms when the label of the outlet in the current settlement cycle does not match the label of the outlet in the previous settlement cycle.

[0050] In some optional implementations, the data acquisition module includes:

[0051] an information acquisition unit, configured to acquire order information of arbitration orders of the outlet in the current settlement period when the number of orders of the outlet in the current settlement period is not less than a first quantity threshold or the number of arbitration orders is not less than a second quantity threshold;

[0052] The data acquisition unit is used to obtain the arbitration data of the outlet in the current settlement period based on the order information of the arbitration order of the outlet in the current settlement period.

[0053] In some optional implementations, the data acquisition unit includes:

[0054] a classification result subunit, configured to obtain a classification result for each arbitration order based on order information of the arbitration order of the outlet in the current settlement cycle, wherein the classification result is used to indicate at least one of the following: whether arbitrary charges are established, whether complaints about service quality are established, whether complaints about non-provided upstairs service are established, whether there are false signatures and false problem items, whether delivery delays are established, whether the weight and square difference categories are approved, and whether irregular packaging errors are established;

[0055] The arbitration data subunit is used to obtain the arbitration data of the outlet in the current settlement cycle based on the classification result of each arbitration order.

[0056] In some optional embodiments, the classification result subunit is used to:

[0057] Inputting the order information of each arbitration order of the outlet in the current settlement period into the classification model to obtain a classification result for each arbitration order;

[0058] The training process of the order classification model includes:

[0059] Obtaining a training set, the training set including a plurality of training data, each of the training data including order information of a sample arbitration order and labeled data of a classification result of the sample arbitration order;

[0060] For each training data in the training set, perform the following processing:

[0061] Inputting the order information of the sample arbitration orders in the training data into a preset deep learning model to obtain prediction data of the classification results of the sample arbitration orders;

[0062] updating the model parameters of the deep learning model based on the predicted data and the labeled data of the classification results of the sample arbitration orders;

[0063] Check whether the preset training end condition is met; if so, use the trained deep learning model as the order classification model; if not, continue training the deep learning model using the next training data.

[0064] In some optional embodiments, the labels include customer service labels and operation quality control labels;

[0065] The customer service labels include: low poor service quality, medium poor service quality, and high poor service quality;

[0066] The operation quality control labels include: low level of weight theft and prescription theft, medium level of weight theft and prescription theft, high level of weight theft and prescription theft, and irregular packaging errors.

[0067] In some optional embodiments, the tag acquisition module includes a first detection unit and a second detection unit;

[0068] The first detection unit is used for:

[0069] respectively detecting whether the arbitration data of the outlets in the current settlement period meet the preset conditions corresponding to each of the customer service tags;

[0070] When it is detected that the arbitration data of the outlet in the current settlement period meets the preset conditions corresponding to at least one of the customer service tags, the customer service tags that meet the conditions in the current settlement period are added to the tags of the outlet in the current settlement period;

[0071] When it is detected that the arbitration data of the outlet in the current settlement period does not meet the preset conditions corresponding to any customer service label, detecting whether the arbitration data of the outlet in the previous settlement period meets the preset conditions corresponding to each customer service label;

[0072] When it is detected that the arbitration data of the outlet in the previous settlement period meets the preset conditions corresponding to at least one of the customer service tags, the customer service tags that meet the conditions in the previous settlement period are added to the tags of the outlet in the current settlement period;

[0073] When it is detected that the arbitration data of the branch in the previous settlement period does not meet the preset conditions corresponding to any customer service label, cancel the customer service label of the branch in the current settlement period;

[0074] The second detection unit is used for:

[0075] respectively detecting whether the arbitration data of the outlets in the current settlement period meet the preset conditions corresponding to each of the operation quality control labels;

[0076] When it is detected that the arbitration data of the outlet in the current settlement period meets the preset conditions corresponding to at least one of the operation quality control tags, the operation quality control tags that meet the conditions in the current settlement period are added to the tags of the outlet in the current settlement period;

[0077] When it is detected that the arbitration data of the outlet in the current settlement period does not meet the preset conditions corresponding to any operation quality control label, the operation quality control label of the outlet in the current settlement period is cancelled.

[0078] In some optional implementations, the process of updating the label of the network point in each of the associated platforms includes:

[0079] Clearing existing tags of the outlet in the associated platform;

[0080] The received label of the outlet in the current settlement period is used as the label of the outlet in the associated platform.

[0081] In a third aspect, the present application provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above methods when executing the computer program.

[0082] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any of the above methods are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] The present application is further described below with reference to the accompanying drawings and implementation methods.

[0084] Figure 1 A flow chart of a tag push method provided in this application is shown.

[0085] Figure 2 A schematic diagram of a process for obtaining arbitration data provided by the present application is shown.

[0086] Figure 3 A schematic diagram of another process for obtaining arbitration data provided by the present application is shown.

[0087] Figure 4 A schematic diagram of a process for obtaining customer service tags of an outlet provided by this application is shown.

[0088] Figure 5 A schematic diagram of a process for obtaining operation quality control labels of outlets provided in this application is shown.

[0089] Figure 6 A schematic diagram of a process for updating labels of outlets in an associated platform provided by the present application is shown.

[0090] Figure 7 A structural schematic diagram of a label pushing device provided in this application is shown.

[0091] Figure 8 The figure shows a structural block diagram of an electronic device provided by the present application.

[0092] Figure 9 A schematic diagram of the structure of a program product provided by this application is shown. DETAILED DESCRIPTION

[0093] The technical solutions in this application will be described below in conjunction with the accompanying drawings and specific implementation methods of this application. It should be noted that, under the premise of no conflict, the various implementation methods or technical features described below can be arbitrarily combined to form a new implementation method.

[0094] In this application, "at least one" means one or more, and "more" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, a and b, a and c, b and c, a and b and c, where a, b and c can be single or multiple. It is worth noting that "at least one" can also be interpreted as "one or more items".

[0095] It should also be noted that, in this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" or "for example" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0096] [Method Implementation Method]

[0097] See also Figure 1 , Figure 1 A flowchart of a tag push method provided by this application is shown.

[0098] The tag pushing method is used to push tags of network points in the arbitration system to the associated platform, and the method includes:

[0099] Step S101: Obtaining arbitration data of the outlet in the current settlement period, wherein the arbitration data of the outlet in the current settlement period is used to indicate one or more of the following: the number of confirmed tickets for unreasonable charges, the number of confirmed tickets for service quality complaints, the number of confirmed tickets for failure to provide upstairs service, the number of tickets for false receipts and false problem items, the proportion of confirmed tickets for delivery delays, the number of approved items for weight and square discrepancies, and the number of tickets for irregular packaging errors;

[0100] Step S102: detecting whether the arbitration data of the outlet in the current settlement period meets the preset conditions corresponding to each tag, so as to obtain the tag of the outlet in the current settlement period;

[0101] Step S103: When the tag of the outlet in the current settlement cycle does not match the tag of the outlet in the previous settlement cycle, the tag of the outlet in the current settlement cycle is pushed to one or more associated platforms of the arbitration system to update the tag of the outlet in each of the associated platforms.

[0102] Therefore, we first obtain the arbitration data of the outlet in the current settlement cycle, and then detect whether these arbitration data meet the preset conditions corresponding to each label, so as to obtain the label of the outlet in the current settlement cycle. When the label of the outlet in the current settlement cycle does not match that of the previous settlement cycle, the label of the outlet on the associated platform is updated.

[0103] That is to say, after obtaining the arbitration data of each outlet in the current settlement cycle, it can automatically detect the label of the current settlement cycle, and then compare whether the label of the outlet has changed compared with the previous settlement cycle. If it has changed, the label of the outlet on the associated platform needs to be updated.

[0104] Since the arbitration data can indicate one or more of the following: the number of tickets for illegal charges, the number of tickets for service quality complaints, the number of tickets for failure to provide upstairs service, the number of tickets for false signatures and false problem items, the proportion of tickets for delivery delays, the number of items that have passed the review of weight and quantity differences, and the number of tickets for irregular packaging errors in the current settlement cycle, in actual applications, the above arbitration data can be compared with the preset conditions corresponding to each label according to the different preset conditions corresponding to each label to determine the label of the outlet.

[0105] The advantage of this is that (unlike the information recommendation process which requires setting a large number of labels for massive data), the number of labels in the arbitration system is limited (the number does not exceed a preset threshold, such as 7, 8, 10, 20, 50, 100, etc.), so the preset conditions corresponding to each label can be set in advance (for example, numerical conditions for one or more arbitration data). For each network point, the arbitration data of the network point is tested separately to see whether it meets the preset conditions corresponding to each label, and whether each label is used as the label corresponding to the network point is determined one by one. This matching method has a limited total amount of calculation and a high accuracy of the calculation result. As long as the arbitration data is correct, the label added to the network point will not be wrong. It is suitable for platforms such as arbitration systems that value fairness and where misjudgment can have a significant impact.

[0106] The labels of each outlet determined in the arbitration system during the current settlement cycle are synchronized to other related platforms, so that the related platforms can quickly and timely obtain the accurate labels of each outlet (in the current settlement cycle), which facilitates the subsequent grade adjustment, settlement method adjustment, task allocation, business adjustment, etc. for each outlet in the related platforms, so as to achieve the purpose of clear, timely and accurate rewards and punishments, and supervise and encourage each outlet to provide high-quality services.

[0107] This application does not limit the associated platforms of the arbitration system, which may include, for example, one or more of a user center, a supply chain platform, a logistics order platform, and an e-commerce platform.

[0108] Data exchange and synchronization can occur between the aforementioned platforms, and this application does not impose any restrictions on this. For example, orders on a logistics order platform may come partially from merchants who place orders through e-commerce platforms (such as Taobao, JD.com, Pinduoduo, and Douyin), and partially from businesses and individuals who place orders through mini-programs (such as WeChat, Alipay, and Meituan).

[0109] In a specific application scenario, the e-commerce platform can display the label of each outlet at the front desk, so that merchants on the e-commerce platform can fully understand whether each outlet has problems with poor customer service quality or non-standard and substandard operation quality control services. On the premise of full understanding, they can choose suitable outlets to cooperate with, protect the interests of merchants, and avoid merchants unknowingly choosing outlets with poor service quality, resulting in inadequate logistics services, attracting negative reviews from shopping customers, and affecting merchant profits.

[0110] This application does not limit the settlement period. The length of each settlement period can be one day, one week, one month, three months, six months, one year, etc.

[0111] As an example, each billing cycle lasts one month. Assume that today is June 1, 2022, the current billing cycle is from May 1, 2022 to May 31, 2022, and the previous billing cycle is from April 1, 2022 to April 30, 2022.

[0112] The number of "illegible charging" cases in this application can be understood as the number of orders (i.e., the number of orders) where illegal charging has been complained about or investigated and verified by arbitration personnel. Specifically, if an order from branch A involving illegal charging becomes an arbitration order, and after being uploaded by the customer service department and verified by arbitration personnel as an illegal charging case, the number of "illegible charging" cases for branch A will be increased by 1 (i.e., one more).

[0113] The number of upheld service quality complaints in this application can be understood as the number of service quality complaints that have been verified by the arbitrators. Specifically, if an order from Branch B involves a complaint about poor service quality and becomes an arbitration order, and after being uploaded by the customer service department and verified by the arbitrators as a genuine case of poor service quality, the number of upheld service quality complaints for Branch B will be increased by 1.

[0114] The number of upheld complaints regarding non-availability of service in this application can be understood as the number of orders where complaints regarding non-availability of service were verified by the arbitrators. Specifically, if an order from Branch C involving a complaint regarding non-availability of service becomes an arbitration order, and after being uploaded by the customer service department and verified by the arbitrators as indeed occurring, the number of upheld complaints regarding non-availability of service for Branch C will be increased by 1.

[0115] The number of false receipts and false problem items in this application can be understood as the number of orders with false receipts or false problem items that have been verified by arbitration personnel. Specifically, if an order at branch D involves a false receipt or false problem item and becomes an arbitration order, and after being uploaded by the customer service department and the arbitration personnel verify that a false receipt or false problem item has been found, the number of false receipts and false problem items for branch D will be increased by 1.

[0116] The percentage of delivery delay cases in this application refers to the percentage of orders with delivery delays (within the current settlement period) in all orders (i.e., all orders delivered to this outlet within the current settlement period). This can be understood as the ratio of the number of orders with delivery delays verified by the arbitration personnel to the total number of orders for this outlet. Specifically, an order from outlet E involving a delivery delay becomes an arbitration order. After being uploaded by the customer service department, the arbitration personnel verify that a delivery delay does exist. In this case, the number of delivery delay orders for outlet E is increased by 1.

[0117] The number of approved weight and square discrepancies in this application can be understood as the number of orders with weight and square discrepancies verified by arbitration personnel. Specifically, if an order from branch F involves a weight and square discrepancy and becomes an arbitration order, and after being uploaded by the Operations Quality Control Department and verified by arbitration personnel as a true weight and square discrepancy, the number of approved weight and square discrepancies for branch F will be increased by 1.

[0118] In this application, the number of irregular packaging error tickets can be understood as the number of orders with irregular packaging that have been verified by the arbitration personnel. Specifically, if an order from branch G involves irregular packaging and becomes an arbitration order, and after being uploaded by the Operations Quality Control Department and verified by the arbitration personnel as indeed containing irregular packaging, the number of irregular packaging error tickets for branch G will be increased by 1.

[0119] The number of tags in each settlement period can be 0, 1 or more.

[0120] In the present application, the mismatch between the label of the outlet in the current settlement period and the label of the outlet in the previous settlement period may refer to a situation where the two are inconsistent.

[0121] For example, if the outlet's labels in the current settlement cycle are "medium poor service quality" and "low weight and quantity theft", and the labels in the previous settlement cycle are "low poor service quality" and "irregular packaging errors", the two do not match.

[0122] For example, if the outlet's labels in the current settlement cycle are "medium poor service quality" and "low stealing and heavy and square stealing", and the label in the previous settlement cycle was "medium poor service quality", the two do not match.

[0123] For example, if the outlet's label in the current settlement cycle is "medium-poor service quality" and its label in the previous settlement cycle is "high-quality theft and high-price theft", the two do not match.

[0124] In some optional embodiments, the method may further include: when the tag of the outlet in the current settlement period matches the tag of the outlet in the previous settlement period, performing no operation. Specifically, there is no need to update the tag of the outlet in any associated platform, that is, the tags of the outlet in all associated platforms remain unchanged.

[0125] See also Figure 2 , Figure 2 A schematic diagram of a process for obtaining arbitration data provided by the present application is shown.

[0126] In some optional implementations, step S101 may include:

[0127] Step S201: When the number of orders of the outlet in the current settlement period is not less than a first quantity threshold or the number of arbitration orders is not less than a second quantity threshold, obtaining order information of the arbitration orders of the outlet in the current settlement period;

[0128] Step S202: based on the order information of the arbitration order of the outlet in the current settlement period, obtaining the arbitration data of the outlet in the current settlement period.

[0129] Therefore, it is statistically significant only when the outlet has a large number of orders in the current settlement cycle (i.e., this settlement cycle) or the outlet has a large number of arbitration orders in the current settlement cycle, to avoid the situation where the statistical results have excessive errors when the number of orders or arbitration orders is too small.

[0130] In addition, if the number of orders at a certain outlet each month is too small, the value of labeling it is low, and there is no need to use the method provided in this application to calculate its corresponding label, resulting in a waste of computing resources and computing power.

[0131] When the total number of orders at an outlet is large or the number of arbitration orders is large, the order processing situation can be evaluated by obtaining the order information that needs to be arbitrated uploaded by various departments in the arbitration system (database), obtaining the arbitration data of the outlet in the current settlement cycle, and the high degree of automation of the obtained arbitration data.

[0132] This application does not limit the first quantity threshold and the second quantity threshold. The first quantity threshold can be, for example, 10, 100, 1000, 10,000, etc., and the second quantity threshold can be, for example, 1, 2, 3, 5, 10, 20, 30, 50, 100, 1000, etc. The first quantity threshold is usually greater than the second quantity threshold because arbitration orders are often a minority of all logistics orders, generally not exceeding 5% and rarely exceeding 20%.

[0133] This application does not limit order information. Order information may include, for example, order number, creation time, expected delivery time, shipping address, receiving address, consignee name, consignee phone number, collection point, carrier, distribution center, express delivery point, scanning record, item name, item type, item quantity, item weight, item volume, weather type, epidemic prevention and control type, etc.

[0134] In some other optional implementations, step S101 may include:

[0135] When the number of orders of the outlet in the current settlement period is not less than a first quantity threshold and the number of arbitration orders is not less than a second quantity threshold, obtaining order information of the arbitration orders of the outlet in the current settlement period;

[0136] Based on the order information of the arbitration order of the outlet in the current settlement period, the arbitration data of the outlet in the current settlement period is obtained.

[0137] See also Figure 3 , Figure 3 A schematic diagram of another process for obtaining arbitration data provided by the present application is shown.

[0138] In some optional implementations, step S202 may include:

[0139] Step S301: Based on the order information of the arbitration orders of the outlet in the current settlement cycle, a classification result of each arbitration order is obtained, where the classification result is used to indicate at least one of the following: whether there is an illegal charge, whether there is a complaint about service quality, whether there is a complaint about not providing door-to-door service, whether there is a false signature and false problem item, whether there is a delivery delay, whether the weight and square difference category is approved, and whether there is an irregular packaging error;

[0140] Step S302: Based on the classification result of each arbitration order, the arbitration data of the outlet in the current settlement cycle is obtained.

[0141] Therefore, the classification results of the arbitration orders are obtained using the order information of the arbitration orders. This classification result can indicate whether the outlet has any unreasonable charges, complaints about service quality, failure to provide door-to-door service, false signatures and false problem items, delivery delays, weight and volume differences, irregular packaging, etc. on the arbitration order. Then, based on the classification results of all arbitration orders in the current settlement period corresponding to the outlet, the arbitration data of the outlet in the current settlement period can be obtained.

[0142] Obtaining arbitration data in the above manner can clearly locate the classification results of each arbitration order, making the arbitration processing process transparent and open, highly reliable, and easy to trace and determine.

[0143] In some optional implementations, step S301 may include:

[0144] Inputting the order information of each arbitration order of the outlet in the current settlement period into the classification model to obtain a classification result for each arbitration order;

[0145] The training process of the order classification model includes:

[0146] Obtaining a training set, the training set including a plurality of training data, each of the training data including order information of a sample arbitration order and labeled data of a classification result of the sample arbitration order;

[0147] For each training data in the training set, perform the following processing:

[0148] Inputting the order information of the sample arbitration orders in the training data into a preset deep learning model to obtain prediction data of the classification results of the sample arbitration orders;

[0149] updating the model parameters of the deep learning model based on the predicted data and the labeled data of the classification results of the sample arbitration orders;

[0150] Check whether the preset training end condition is met; if so, use the trained deep learning model as the order classification model; if not, continue training the deep learning model using the next training data.

[0151] Therefore, the order classification model can be trained by a large amount of training data, and can predict the corresponding output data for different input data (that is, the classification results of the arbitration order, such as whether the outlet has any random charges, service quality complaints, no upstairs service, false signatures and false problem items, delivery delays, weight and size differences, irregular packaging, etc.). It has a wide range of applications and a high level of intelligence.

[0152] By designing, establishing an appropriate number of neuron computing nodes and a multi-layer operation hierarchy, and selecting appropriate input and output layers, a preset deep learning model can be obtained. Through learning and tuning of the preset deep learning model, a functional relationship from input to output is established. Although the functional relationship between input and output cannot be found 100%, the actual correlation relationship can be approached as closely as possible. The order classification model trained in this way can obtain the classification results of arbitration orders based on the order information of arbitration orders, and the calculation results are highly accurate and reliable.

[0153] In some optional implementations, the present application may adopt the above-mentioned training process to train an order classification model. In other optional implementations, the present application may adopt a pre-trained order classification model.

[0154] In some optional implementations, for example, keyword extraction can be performed on relevant data corresponding to past arbitration orders to obtain order information for sample arbitration orders. In other words, these sample arbitration orders can be real historical arbitration orders. Of course, the order information for the sample arbitration orders can also be automatically generated using the generative network of the GAN model.

[0155] The GAN model, or Generative Adversarial Network, consists of a generator network and a discriminator network. The generator network randomly samples from the latent space as input, and its output is required to closely mimic real samples from the training set. The discriminator network receives real samples or the output of the generator network as input, with the goal of distinguishing the generator network output from real samples as much as possible. The generator network, in turn, is tasked with deceiving the discriminator network as much as possible. The two networks compete with each other, constantly adjusting their parameters, with the ultimate goal of making it impossible for the discriminator network to determine whether the generator network's output is genuine. The GAN model can be used to generate order information for multiple sample arbitration orders for use in the training of order classification models, effectively reducing the amount of raw data collected and significantly lowering the costs of data collection and annotation.

[0156] This application does not limit the method for obtaining annotated data; for example, manual annotation, automatic annotation, or semi-automatic annotation can be used. When the sample arbitration order uses a historical arbitration order, keyword extraction can be performed on the relevant data corresponding to the historical arbitration order to obtain annotated data corresponding to the classification result of the sample arbitration order. In other words, through keyword extraction, the relevant data corresponding to the historical arbitration order can be used to obtain the order information of the historical arbitration order and the annotated data of the classification result.

[0157] This application does not limit the training process of the order classification model. For example, it can adopt the above-mentioned supervised learning training method, or it can adopt the semi-supervised learning training method, or it can adopt the unsupervised learning training method.

[0158] This application does not limit the preset training end conditions. For example, it can be that the number of training times reaches a preset number (the preset number is, for example, 1 time, 3 times, 10 times, 100 times, 1000 times, 10,000 times, etc.), or it can be that all the training data in the training set complete one or more trainings, or it can be that the total loss value obtained from this training is not greater than the preset loss value.

[0159] In some other optional implementations, step S301 may include:

[0160] For each arbitration order of the outlet in the current settlement cycle, a classification operation for each arbitration order is received using an interactive device, and a classification result for each arbitration order is obtained in response to the classification operation.

[0161] This application does not limit the interactive device. The interactive device can be, for example, a mobile phone, a tablet computer, a laptop computer, a desktop computer, a smart wearable device or other smart terminal device, or the interactive device can be a console or a workstation.

[0162] This application does not limit the way of receiving various (manual) operations using interactive devices. Operations can be divided according to input methods, for example, including text input operations, audio input operations, video input operations, key operations, mouse operations, keyboard operations, smart stylus operations, etc.

[0163] In some optional embodiments, the labels include customer service labels and operation quality control labels;

[0164] The customer service labels include: low poor service quality, medium poor service quality, and high poor service quality;

[0165] The operation quality control labels include: low level of weight theft and prescription theft, medium level of weight theft and prescription theft, high level of weight theft and prescription theft, and irregular packaging errors.

[0166] Different orders are handled by different departments. The Customer Service Department is responsible for following up on cargo logistics, handling customer complaints, recording and answering customer inquiries, and coordinating solutions for customer issues. The Operations and Quality Control Department is responsible for quality and safety management, organizing, coordinating, inspecting, and evaluating operations throughout the implementation process. They are also responsible for controlling the quality and timeliness of intermediate links such as logistics, transportation, and sorting. Different arbitration orders, generated at different stages and for different reasons and uploaded to different departments, can be categorized as either Customer Service Department arbitration orders or Operations and Quality Control Department arbitration orders.

[0167] Therefore, the labels are divided into two categories, namely customer service labels (corresponding to the arbitration orders uploaded by the customer service department) and operation quality control labels (corresponding to the arbitration orders uploaded by the operation quality control department).

[0168] That is to say, two types of labels are set based on the upload sources of arbitration orders (customer service department and operation quality control department) to reflect the problems existing in the customer service and operation quality control of the outlets, such as poor service quality (uploaded by the customer service department) and problems such as weight theft and irregular packaging (uploaded by the operation quality control department). This allows the labels to reflect the service level and operation quality control of the outlets in a three-dimensional and refined manner. Compared with only setting customer service labels or operation quality control labels, the two dimensions can more comprehensively assess the comprehensive level of the outlets.

[0169] This application does not limit the preset conditions corresponding to each tag. In a specific application scenario, the preset conditions corresponding to each tag are as follows:

[0170] For customer service tags:

[0171] ① The number of tickets for illegal charges is ≥ 1

[0172] ② The number of successful complaints about service quality is ≥ 1

[0173] ③ The number of complaints that the upstairs service was not provided and the number of votes received is ≥ 1

[0174] ④ The number of false signatures and false problem tickets is ≥ 1

[0175] ⑤ The percentage of confirmed delivery delay tickets is ≥ 2%; (The percentage of confirmed delivery delay tickets is the ratio of the number of delivery delay orders to the number of deliveries in the current settlement period).

[0176] The preset condition corresponding to the label "poor service quality" is: the arbitration data of the outlet in the current settlement cycle meets 3 and only 3 of the above 5 conditions.

[0177] The preset condition corresponding to the label "poor service quality" is: the arbitration data of the outlet in the current settlement cycle meets 4 and only 4 of the above 5 conditions.

[0178] The preset condition corresponding to the label "high poor service quality" is: the arbitration data of the outlet in the current settlement cycle meets five of the above five conditions.

[0179] Among them, arbitration events are calculated based on the settlement review time, and the dispatch volume is calculated based on the dispatch time.

[0180] For operation quality control tags, statistics are based on settlement review time:

[0181] The preset condition for the label "Low weight and low volume" is: the number of items that have passed the review in the weight and volume difference category is not less than 5 and less than 10;

[0182] The preset conditions for the label "Weight Difference and Quantity Difference" are: the number of items that have passed the weight difference and quantity difference review is not less than 10 and less than 15, and the weight difference is not less than 500kg and less than 1000kg;

[0183] The default conditions for the label "Weight Difference, Volume Difference, and Height Difference" are: the number of items that have passed the weight and volume difference review is not less than 15, and the weight difference is not less than 1000kg;

[0184] The preset condition corresponding to the label "Irregular Packaging Error" is: the number of irregular packaging error tickets ≥ 3 tickets.

[0185] It should be noted that the numerical examples in the above specific application scenarios are merely examples and should not be understood as limitations on this application.

[0186] See also Figure 4 and Figure 5 , Figure 4 The following is a flow chart of obtaining customer service tags of a branch provided by the present application. Figure 5 A schematic diagram of a process for obtaining operation quality control labels of outlets provided in this application is shown.

[0187] In some optional implementations, step S102 may include:

[0188] Step S401: respectively detecting whether the arbitration data of the outlets in the current settlement period meet the preset conditions corresponding to each customer service tag;

[0189] Step S402: When it is detected that the arbitration data of the outlet in the current settlement period meets the preset conditions corresponding to at least one of the customer service tags, the customer service tags that meet the conditions in the current settlement period are added to the tags of the outlet in the current settlement period;

[0190] Step S403: When it is detected that the arbitration data of the outlet in the current settlement period does not meet the preset conditions corresponding to any customer service tag, detecting whether the arbitration data of the outlet in the previous settlement period meets the preset conditions corresponding to each customer service tag;

[0191] Step S404: When it is detected that the arbitration data of the outlet in the previous settlement period meets the preset conditions corresponding to at least one of the customer service tags, the customer service tags that meet the conditions in the previous settlement period are added to the tags of the outlet in the current settlement period;

[0192] Step S405: when it is detected that the arbitration data of the outlet in the previous settlement period does not meet any preset conditions corresponding to the customer service class label, cancel the customer service class label of the outlet in the current settlement period;

[0193] Step S501: respectively detecting whether the arbitration data of the outlets in the current settlement period meet the preset conditions corresponding to each of the operation quality control tags;

[0194] Step S502: When it is detected that the arbitration data of the outlet in the current settlement period meets the preset conditions corresponding to at least one of the operation quality control tags, the operation quality control tags that meet the conditions in the current settlement period are added to the tags of the outlet in the current settlement period;

[0195] Step S503: when it is detected that the arbitration data of the outlet in the current settlement period does not meet the preset conditions corresponding to any operation quality control label, the operation quality control label of the outlet in the current settlement period is cancelled.

[0196] Therefore, once a branch is labeled with a customer service tag, it will need to be free of the customer service tag for two consecutive settlement cycles before it can be removed. In other words, it depends not only on whether the preset conditions of the customer service tag are met in the current settlement cycle, but also on whether the preset conditions of the customer service tag are met in the previous settlement cycle. The customer service tag can only be removed if the preset conditions of the customer service tag are not met for two consecutive settlement cycles (i.e., the two most recent settlement cycles, or the two most recent settlement cycles). In other words, once a branch is labeled with a customer service tag, as long as the branch's arbitration data in the current settlement cycle or the previous settlement cycle meets the preset conditions of any customer service tag, it will be impossible to remove the branch's customer service tag; the customer service tag can only be removed if the branch's arbitration data in the most recent two settlement cycles does not meet the preset conditions corresponding to any customer service tag (i.e., the preset conditions of each customer service tag are not met).

[0197] As for operation quality control labels, once an outlet is labeled, the label can be cancelled as long as the current settlement cycle does not meet the preset conditions of the operation quality control label.

[0198] In comparison, customer service labels are retroactive (the past here refers to the previous settlement cycle), while operational quality control labels are not retroactive. This is because the problems corresponding to customer service labels are relatively more serious. This is a setting made based on the specific circumstances in actual applications. Treating customer service labels and operational quality control labels differently is part of refined management, because the problems reflected by operational quality control labels may be unintentional mistakes or unconscious actions, while the problems reflected by customer service labels are more serious and severe in nature, and are often subjective and intentional mistakes. Imposing more severe disciplinary measures can help outlets correctly recognize the seriousness of customer service issues and achieve the effect of promoting (service capability) improvement through assessment.

[0199] In a specific application scenario, the label of branch H in the previous settlement cycle is "medium poor service quality". The arbitration data in the current settlement cycle meets the preset condition of the label "low poor service quality". Then the label of branch H in the current settlement cycle includes "low poor service quality".

[0200] In another specific application scenario, the labels of outlet I in the previous settlement cycle are "medium poor service quality" and "low stealing and heavy stealing", and the arbitration data in the current settlement cycle meets the preset conditions of the label "medium poor service quality", then the label of outlet I in the current settlement cycle includes "medium poor service quality".

[0201] In another specific application scenario, the labels of outlet J in the previous settlement cycle are "medium poor service quality" and "low stealing and hedging", and the arbitration data in the current settlement cycle meets the preset conditions of the label "low stealing and hedging", and the arbitration data in the previous settlement cycle meets the preset conditions of the label "medium poor service quality", then the labels of outlet J in the current settlement cycle include "medium poor service quality" and "low stealing and hedging".

[0202] In another specific application scenario, the labels of branch K in the previous settlement cycle are "medium poor service quality" and "low stealing and heavy stealing", and the arbitration data in the current settlement cycle meets the preset conditions of the label "low stealing and heavy stealing", and the arbitration data in the previous settlement cycle does not meet the preset conditions of any customer service labels, then the labels of branch K in the current settlement cycle include "low stealing and heavy stealing".

[0203] In another specific application scenario, the labels of outlet L in the previous settlement cycle are "medium poor service quality" and "low stealing and counterfeiting", the arbitration data in the current settlement cycle does not meet the preset conditions of any label, and the arbitration data in the previous settlement cycle does not meet the preset conditions of any customer service label (but the arbitration data in the previous settlement cycle meets the preset conditions of the label "low stealing and counterfeiting"), then the label of outlet L in the current settlement cycle is cancelled.

[0204] See also Figure 6 , Figure 6 A schematic diagram of a process for updating labels of outlets in an associated platform provided by the present application is shown.

[0205] In some optional implementations, the process of updating the label of the network point in each of the associated platforms may include:

[0206] Step S601: Clear the existing tags of the outlet in the associated platform;

[0207] Step S602: Using the received label of the outlet in the current settlement period as the label of the outlet in the associated platform.

[0208] Therefore, when updating the outlet labels in the associated platform, first clear the existing labels and then reset the outlet labels. Compared with comparing each existing label one by one to see whether it needs to be retained and then determining whether a new label needs to be added, this is convenient and fast, and the update efficiency is high.

[0209] In one specific application scenario, the label of the branch in each associated platform can be updated immediately after the current settlement process ends. In another specific application scenario, each settlement cycle lasts for one month. The current settlement cycle is from May 1, 2022 to May 31, 2022, and the previous settlement cycle was from April 1, 2022 to April 30, 2022. The label of the branch in each associated platform can be updated on the 1st of each month.

[0210] In some optional embodiments, the method may further include:

[0211] The label of each network point in the associated platform is displayed using a display device.

[0212] The display device may be, for example, a separate display screen or an interactive device with a display function.

[0213] [Device Implementation Method]

[0214] See also Figure 7 , Figure 7 A structural schematic diagram of a label pushing device provided in this application is shown.

[0215] The present application also provides a label pushing device, the specific implementation of which is consistent with the implementation and technical effects recorded in the above-mentioned method implementation, and some contents will not be repeated here.

[0216] The label pushing device is used to push the labels of the network points in the arbitration system to the associated platform, and the device includes:

[0217] The data acquisition module 101 is used to obtain arbitration data of the outlet in the current settlement period, where the arbitration data of the outlet in the current settlement period is used to indicate one or more of the following: the number of confirmed tickets for unreasonable charges, the number of confirmed tickets for service quality complaints, the number of confirmed tickets for failure to provide upstairs service, the number of tickets for false signatures and false problem items, the proportion of confirmed tickets for delivery delays, the number of approved items for weight and square discrepancies, and the number of tickets for irregular packaging errors;

[0218] The tag acquisition module 102 is used to detect whether the arbitration data of the network point in the current settlement period meets the preset conditions corresponding to each tag, so as to obtain the tag of the network point in the current settlement period;

[0219] The label update module 103 is used to push the label of the outlet in the current settlement cycle to one or more associated platforms of the arbitration system to update the label of the outlet in each of the associated platforms when the label of the outlet in the current settlement cycle does not match the label of the outlet in the previous settlement cycle.

[0220] In some optional implementations, the data acquisition module 101 may include:

[0221] an information acquisition unit, configured to acquire order information of arbitration orders of the outlet in the current settlement period when the number of orders of the outlet in the current settlement period is not less than a first quantity threshold or the number of arbitration orders is not less than a second quantity threshold;

[0222] The data acquisition unit is used to obtain the arbitration data of the outlet in the current settlement period based on the order information of the arbitration order of the outlet in the current settlement period.

[0223] In some optional implementations, the data acquisition unit may include:

[0224] a classification result subunit, configured to obtain a classification result for each arbitration order based on order information of the arbitration order of the outlet in the current settlement cycle, wherein the classification result is used to indicate at least one of the following: whether arbitrary charges are established, whether complaints about service quality are established, whether complaints about non-provided upstairs service are established, whether there are false signatures and false problem items, whether delivery delays are established, whether the weight and square difference categories are approved, and whether irregular packaging errors are established;

[0225] The arbitration data subunit is used to obtain the arbitration data of the outlet in the current settlement cycle based on the classification result of each arbitration order.

[0226] In some optional embodiments, the classification result subunit may be used to:

[0227] Inputting the order information of each arbitration order of the outlet in the current settlement period into the classification model to obtain a classification result for each arbitration order;

[0228] The training process of the order classification model includes:

[0229] Obtaining a training set, the training set including a plurality of training data, each of the training data including order information of a sample arbitration order and labeled data of a classification result of the sample arbitration order;

[0230] For each training data in the training set, perform the following processing:

[0231] Inputting the order information of the sample arbitration orders in the training data into a preset deep learning model to obtain prediction data of the classification results of the sample arbitration orders;

[0232] updating the model parameters of the deep learning model based on the predicted data and the labeled data of the classification results of the sample arbitration orders;

[0233] Check whether the preset training end condition is met; if so, use the trained deep learning model as the order classification model; if not, continue training the deep learning model using the next training data.

[0234] In some optional embodiments, the labels may include customer service labels and operation quality control labels;

[0235] The customer service labels include: low poor service quality, medium poor service quality, and high poor service quality;

[0236] The operation quality control labels include: low level of weight theft and prescription theft, medium level of weight theft and prescription theft, high level of weight theft and prescription theft, and irregular packaging errors.

[0237] In some optional implementations, the tag acquisition module 102 may include a first detection unit and a second detection unit;

[0238] The first detection unit is used for:

[0239] respectively detecting whether the arbitration data of the outlets in the current settlement period meet the preset conditions corresponding to each of the customer service tags;

[0240] When it is detected that the arbitration data of the outlet in the current settlement period meets the preset conditions corresponding to at least one of the customer service tags, the customer service tags that meet the conditions in the current settlement period are added to the tags of the outlet in the current settlement period;

[0241] When it is detected that the arbitration data of the outlet in the current settlement period does not meet the preset conditions corresponding to any customer service label, detecting whether the arbitration data of the outlet in the previous settlement period meets the preset conditions corresponding to each customer service label;

[0242] When it is detected that the arbitration data of the outlet in the previous settlement period meets the preset conditions corresponding to at least one of the customer service tags, the customer service tags that meet the conditions in the previous settlement period are added to the tags of the outlet in the current settlement period;

[0243] When it is detected that the arbitration data of the branch in the previous settlement period does not meet the preset conditions corresponding to any customer service label, cancel the customer service label of the branch in the current settlement period;

[0244] The second detection unit is used for:

[0245] respectively detecting whether the arbitration data of the outlets in the current settlement period meet the preset conditions corresponding to each of the operation quality control labels;

[0246] When it is detected that the arbitration data of the outlet in the current settlement period meets the preset conditions corresponding to at least one of the operation quality control tags, the operation quality control tags that meet the conditions in the current settlement period are added to the tags of the outlet in the current settlement period;

[0247] When it is detected that the arbitration data of the outlet in the current settlement period does not meet the preset conditions corresponding to any operation quality control label, the operation quality control label of the outlet in the current settlement period is cancelled.

[0248] In some optional implementations, the process of updating the label of the network point in each of the associated platforms may include:

[0249] Clearing existing tags of the outlet in the associated platform;

[0250] The received label of the outlet in the current settlement period is used as the label of the outlet in the associated platform.

[0251]

Equipment Implementation Method

[0252] The present application also provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any of the above methods are implemented. The specific implementation method is consistent with the implementation method and the technical effect achieved in the implementation method of the above method, and some contents will not be repeated here.

[0253] See also Figure 8 , Figure 8 A structural block diagram of an electronic device 200 provided in this application is shown.

[0254] The electronic device 200 may include, for example, at least one memory 210 , at least one processor 220 , and a bus 230 connecting different platform systems.

[0255] The memory 210 may include a readable medium in the form of a volatile memory, such as a random access memory (RAM) 211 and / or a cache memory 212 , and may further include a read-only memory (ROM) 213 .

[0256] The memory 210 also stores a computer program, which can be executed by the processor 220, so that the processor 220 implements the steps of any of the above methods.

[0257] The memory 210 may also include a utility 214 having at least one program module 215, such program module 215 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0258] Accordingly, the processor 220 may execute the aforementioned computer program and the utility 214 .

[0259] The processor 220 may be implemented as one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field programmable gate arrays (FPGAs), or other electronic components.

[0260] Bus 230 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0261] The electronic device 200 may also communicate with one or more external devices 240, such as a keyboard, pointing device, Bluetooth device, etc., and may also communicate with one or more devices capable of interacting with the electronic device 200, and / or any device that enables the electronic device 200 to communicate with one or more other computing devices (e.g., a router, a modem, etc.). Such communication may be performed via an input / output interface 250. Furthermore, the electronic device 200 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 260. The network adapter 260 may communicate with other modules of the electronic device 200 via the bus 230. It should be understood that, although not shown in the figures, other hardware and / or software modules may be used in conjunction with the electronic device 200, including but not limited to microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0262]

Medium Implementation Method

[0263] The present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of any of the above methods. Its specific implementation method is consistent with the implementation method and the technical effect achieved in the implementation method of the above method, and some contents will not be repeated here.

[0264] See also Figure 9 , Figure 9 A schematic diagram of the structure of a program product provided by this application is shown.

[0265] The program product is used to implement any of the above methods. The program product can be a portable compact disc read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited to this. In this application, a readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or device. The program product can use any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can 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 readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0266] A computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, carrying 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 thereof. The readable storage medium may also be any readable medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, or any suitable combination thereof. The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as C or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a standalone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. Where a remote computing device is involved, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0267] This application is explained from the perspectives of purpose of use, effectiveness, progress and novelty, and has complied with the functional enhancement and use requirements emphasized by the Patent Law. The above description and drawings of this application are only preferred embodiments of this application and are not intended to limit this application. Therefore, all structures, devices, features, etc. that are similar or identical to those of this application, that is, all equivalent replacements or modifications made in accordance with the scope of the patent application of this application, should fall within the scope of protection of the patent application of this application.

Claims

1. A tag push method, characterized in that: The method for pushing tags of nodes in the arbitration system to a related platform includes: Obtaining arbitration data of the outlet in the current settlement period, the arbitration data of the outlet in the current settlement period is used to indicate one or more of the following: the number of confirmed tickets for unreasonable charges, the number of confirmed tickets for service quality complaints, the number of confirmed tickets for failure to provide upstairs service, the number of tickets for false signatures and false problem items, the proportion of confirmed tickets for delivery delays, the number of items approved by weight and square difference categories, and the number of tickets for irregular packaging errors; respectively detecting whether the arbitration data of the outlet in the current settlement period meets the preset conditions corresponding to each tag, so as to obtain the tag of the outlet in the current settlement period; When the tag of the outlet in the current settlement cycle does not match the tag of the outlet in the previous settlement cycle, push the tag of the outlet in the current settlement cycle to one or more associated platforms of the arbitration system to update the tag of the outlet in each of the associated platforms; The labels include customer service labels and operation quality control labels; The cancellation of customer service labels requires that the preset conditions are not met for two consecutive settlement cycles, while the cancellation of operation quality control labels only requires that the preset conditions are not met in the current settlement cycle; The obtaining of arbitration data of the outlet in the current settlement cycle includes: When the number of orders of the outlet in the current settlement period is not less than the first quantity threshold or the number of arbitration orders is not less than the second quantity threshold, obtaining order information of the arbitration orders of the outlet in the current settlement period; Based on the order information of the arbitration order of the outlet in the current settlement period, the arbitration data of the outlet in the current settlement period is obtained.

2. The tag push method according to claim 1, characterized in that: The obtaining, based on order information of arbitration orders of the outlet in the current settlement period, arbitration data of the outlet in the current settlement period includes: Based on the order information of arbitration orders of the outlet in the current settlement cycle, a classification result of each arbitration order is obtained, where the classification result is used to indicate at least one of the following: whether arbitrary charges are established, whether complaints about service quality are established, whether complaints about failure to provide door-to-door service are established, whether there are false signatures and false problem items, whether delivery delays are established, whether the weight and dimensions difference categories are approved, and whether irregular packaging errors are established; Based on the classification result of each arbitration order, the arbitration data of the outlet in the current settlement cycle is obtained.

3. The tag push method according to claim 2, characterized in that: The obtaining of a classification result of each arbitration order based on the order information of the arbitration order of the outlet in the current settlement cycle includes: Inputting the order information of each arbitration order of the outlet in the current settlement period into the classification model to obtain a classification result for each arbitration order; The training process of the order classification model includes: Obtaining a training set, the training set including a plurality of training data, each of the training data including order information of a sample arbitration order and labeled data of a classification result of the sample arbitration order; For each training data in the training set, perform the following processing: Inputting the order information of the sample arbitration orders in the training data into a preset deep learning model to obtain prediction data of the classification results of the sample arbitration orders; updating the model parameters of the deep learning model based on the predicted data and the labeled data of the classification results of the sample arbitration orders; Check whether the preset training end condition is met; if so, use the trained deep learning model as the order classification model; if not, continue training the deep learning model using the next training data.

4. The tag push method according to claim 1, wherein: The customer service labels include: low poor service quality, medium poor service quality, and high poor service quality; The operation quality control labels include: low level of weight theft and prescription theft, medium level of weight theft and prescription theft, high level of weight theft and prescription theft, and irregular packaging errors.

5. The tag push method according to claim 1, characterized in that: The detecting whether the arbitration data of the network point in the current settlement period satisfies the preset conditions corresponding to each tag to obtain the tag of the network point in the current settlement period includes: respectively detecting whether the arbitration data of the outlets in the current settlement period meet the preset conditions corresponding to each of the customer service tags; When it is detected that the arbitration data of the outlet in the current settlement period meets the preset conditions corresponding to at least one of the customer service tags, the customer service tags that meet the conditions in the current settlement period are added to the tags of the outlet in the current settlement period; When it is detected that the arbitration data of the outlet in the current settlement period does not meet the preset conditions corresponding to any customer service label, detecting whether the arbitration data of the outlet in the previous settlement period meets the preset conditions corresponding to each customer service label; When it is detected that the arbitration data of the outlet in the previous settlement period meets the preset conditions corresponding to at least one of the customer service tags, the customer service tags that meet the conditions in the previous settlement period are added to the tags of the outlet in the current settlement period; When it is detected that the arbitration data of the branch in the previous settlement period does not meet the preset conditions corresponding to any customer service label, cancel the customer service label of the branch in the current settlement period; respectively detecting whether the arbitration data of the outlets in the current settlement period meet the preset conditions corresponding to each of the operation quality control labels; When it is detected that the arbitration data of the outlet in the current settlement period meets the preset conditions corresponding to at least one of the operation quality control tags, the operation quality control tags that meet the conditions in the current settlement period are added to the tags of the outlet in the current settlement period; When it is detected that the arbitration data of the outlet in the current settlement period does not meet the preset conditions corresponding to any operation quality control label, the operation quality control label of the outlet in the current settlement period is cancelled.

6. The tag push method according to claim 1, characterized in that: The process of updating the label of the network point in each associated platform includes: Clearing existing tags of the outlet in the associated platform; The received label of the outlet in the current settlement period is used as the label of the outlet in the associated platform.

7. A label pushing device, characterized in that: The device is used to push the tags of the network points in the arbitration system to the associated platform, including: a data acquisition module, configured to acquire arbitration data of the outlet in the current settlement period, wherein the arbitration data of the outlet in the current settlement period is used to indicate one or more of the following: the number of confirmed tickets for unreasonable charges, the number of confirmed tickets for service quality complaints, the number of confirmed tickets for failure to provide upstairs service, the number of tickets for false receipts and false problem items, the proportion of confirmed tickets for delivery delays, the number of items approved for weight and square difference categories, and the number of tickets for irregular packaging errors; a tag acquisition module, configured to detect whether the arbitration data of the outlet in the current settlement period meets the preset conditions corresponding to each tag, so as to obtain the tag of the outlet in the current settlement period; a label updating module, configured to, when the label of the outlet in the current settlement period does not match the label of the outlet in the previous settlement period, push the label of the outlet in the current settlement period to one or more associated platforms of the arbitration system, so as to update the label of the outlet in each of the associated platforms; The labels include customer service labels and operation quality control labels; The cancellation of customer service labels requires that the preset conditions are not met for two consecutive settlement cycles, while the cancellation of operation quality control labels only requires that the preset conditions are not met in the current settlement cycle; The obtaining of arbitration data of the outlet in the current settlement cycle includes: When the number of orders of the outlet in the current settlement period is not less than the first quantity threshold or the number of arbitration orders is not less than the second quantity threshold, obtaining order information of the arbitration orders of the outlet in the current settlement period; Based on the order information of the arbitration order of the outlet in the current settlement period, the arbitration data of the outlet in the current settlement period is obtained.

8. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images