CN115131093A - Abnormal order management method and related device - Google Patents

Abstract

The application provides an abnormal order management method and a related device, wherein the method comprises the following steps: when the order meets a first preset condition or a second preset condition, adjusting the order state of the order to be abnormal, and setting the abnormal processing state of the order to be processed; carrying out circulation processing on the order to obtain a circulation processing result of the order, and adjusting the abnormal processing state of the order to be processed; when the abnormal processing state of the order is processed, carrying out accountability judgment on the order to obtain an accountability judgment result of the order; and updating the settlement information of each responsible party based on the responsibility judgment result of the order. The automatic aging monitoring mode and the manual reporting mode are combined, abnormal orders are timely circulated and processed, the problem that efficiency is low due to manual reporting is avoided, misjudgment caused by automatic division is avoided, the abnormal orders can be fully processed by effectively combining the automatic aging monitoring mode and the manual reporting mode, processing efficiency is higher, and accuracy is higher.

Description

Abnormal order management method and related device

technical field

The present application relates to the technical fields of supply chain, logistics and transportation, and deep learning, and in particular, to a method for managing abnormal orders and related devices.

Background technique

Supply Chain (Supply Chain) refers to the network structure composed of raw material suppliers, manufacturers, distributors, retailers and final consumers involved in the process of product production and circulation through connections with upstream and downstream members. , that is, a network composed of enterprises and business departments involved in the process of material acquisition, material processing, and delivery of finished products to users.

In the past supply chain, after the customer placed an order (order), when the order was overtime, out of stock, unable to deliver under special circumstances, etc., it was all reported manually and the order status was fed back. This method has low processing efficiency. , when the order volume is huge, it cannot be effectively dealt with.

Patent CN111553624A discloses a method and system for comprehensive analysis of global logistics information. The method includes: the steps of entering transportation package information: entering the information of the transportation package; verifying; data persistence; logistics track information collection and state analysis steps: obtaining logistics Unfinished transportation package information; Collect corresponding logistics track information; Requirements; logistics timeliness analysis steps: obtain the logistics information of logistics transportation and parcels that need to be analyzed; notify according to the analysis results and the results of comprehensive scoring and comparison of logistics services. The above method is based on a set of platform timeliness assessment rules to monitor whether the various transportation timeliness indicators of the logistics transporter meet the standards. Misjudgment may occur because the preset platform timeliness assessment rules cannot cover all situations, causing the interests of the party who are judged to be responsible. Fang is dissatisfied.

Based on this, the present application provides an abnormal order management method and a related device to solve the above-mentioned problems in the prior art.

SUMMARY OF THE INVENTION

The purpose of this application is to provide an abnormal order management method and related devices, which combine the automatic aging monitoring method and the manual reporting method, so as to timely transfer and process abnormal orders, avoid the inefficiency problem of only relying on manual reporting, and avoid relying on automatic The misjudgment caused by the division, the effective combination of the two can fully cover the processing of abnormal orders, making the processing of abnormal orders more efficient and more accurate.

The purpose of this application adopts the following technical solutions to achieve:

In a first aspect, the present application provides a method for managing abnormal orders, the method comprising:

When the order meets the first preset condition or the second preset condition, adjust the order status of the order to abnormal, and set the abnormal processing status of the order to pending;

Perform circulation processing on the order to obtain a circulation processing result of the order, and adjust the abnormal processing status of the order to processed;

When the abnormal processing status of the order is processed, the order is judged to obtain the judgment result of the order, and the judgment result of the order is used to indicate the responsible party of the order and its corresponding the amount of liability;

Based on the judgment result of the order, update the settlement information of each of the responsible parties;

Wherein, that the order satisfies the first preset condition means:

Acquiring the length of time that the order is in the order state to be shipped, so as to obtain the time to be shipped of the order, and when it is detected that the time to be shipped of the order is not less than the first preset time, determine that the order satisfies the the first preset condition;

That the order satisfies the second preset condition means:

When an abnormal marking operation for the order is received, in response to the abnormal marking operation, it is determined that the order satisfies the second preset condition.

The beneficial effect of the technical solution is that: the automatic aging monitoring method (or the automatic reporting method) is combined with the manual reporting method, and the abnormal orders are processed in a timely manner, which avoids the inefficiency problem of relying only on manual reporting, and also avoids completely relying on manual reporting. The misjudgment caused by automatic division, the effective combination of the two can fully cover the processing of abnormal orders, making the processing of abnormal orders more efficient and more accurate. On the one hand, a first preset condition (or an automatic reporting condition) is set for obtaining the first type of abnormal order, that is, an abnormal order detected by the automatic aging monitoring method. Orders with a long duration are listed as abnormal orders. On the other hand, a second preset condition (or manual reporting condition) is set for obtaining the second type of abnormal orders, that is, the abnormal orders marked by manual reporting. for abnormal orders. This application uses the following methods to deal with abnormal orders: if there is an order that meets any of the above two types of conditions, adjust its order status to abnormal, and set its abnormal processing status to pending; For each order, carry out the circulation processing (such as return, refund, reissue, reissue, reminder, etc., in case of misjudgment, the order can continue the normal delivery process), and update its abnormal processing status to processed; For these orders whose abnormal processing status is processed, judgment (determining the responsible party and the amount of the judgment) and recovery (that is, updating the settlement information of the relevant responsible parties, for example, one or more responsible parties) are performed. It can not only monitor (or track) whether each order is abnormal in real time, but also deal with abnormal orders in a timely manner, so that they can be transferred to the follow-up link, so as to prevent them from staying in the unresolved state for a long time, which will lead to many problems in the entire supply chain. The dissatisfaction of each related party will improve the experience of each related party in using the supply chain. At the same time, in addition to the order status, an exception processing status is also set to complete the tracking and processing of abnormal orders, which reflects the importance attached to abnormal orders, and it is convenient for managers to use the exception processing status as a starting point to deal with pending orders in the exception processing status. Processed, processed and other types of screening, sorting, etc., urge the relevant staff to deal with abnormal orders quickly and preferentially. In addition, this part of the data (order information, relevant responsible parties, amount of judgment, etc.) including the abnormal processing status can be independently mined and analyzed to learn the subdivision types, causes and corresponding processing methods of abnormal orders. Avoid generating more abnormal orders.

In some optional embodiments, the method further includes:

When it is detected that the to-be-delivered duration of the order is not less than the second preset duration and less than the first preset duration, adjusting the order status of the order to an early warning;

Wherein, the second preset duration is smaller than the first preset duration.

The beneficial effect of the technical solution is that in the process of automatically monitoring the aging of the order, not only the abnormal aging can be set (once the pending delivery time of the order is greater than or equal to the first preset time, the order status will automatically change to abnormal), but also can be set Early warning time limit (once the pending delivery time of the order is greater than or equal to the second preset time period and less than the first preset time period, the order status will automatically change to early warning), which is used to monitor that an abnormality has not yet occurred, but an abnormality may occur (for example, no urge the relevant personnel to process and prioritize the orders as soon as possible after seeing the relevant warning signs, so as to prevent these early warning orders from becoming abnormal orders, and adopt the above preventive measures to actively and actively reduce the probability of orders becoming abnormal orders .

In some optional embodiments, the method further includes:

When the order status of the order is abnormal or early warning, a display image corresponding to the order is generated, and the display image is used to indicate different order statuses of the order by using different display modes;

The display image is displayed using a display device.

The beneficial effect of the technical solution is that: when the display device displays the order, different display methods are used to indicate the different order status of the order. An exclamation mark is used to indicate abnormal orders; or a yellow text highlight color (that is, the text background color) can be used to indicate an early warning order, and a red text highlight color can be used to indicate an early warning order; or a yellow font color can be used to indicate an early warning order, with red The font color of the text indicates abnormal orders; or you can use underline text to indicate early warning orders, and use slanted text to indicate abnormal orders, etc.; compared with the text content itself, different display methods can intuitively and conspicuously reflect the difference in order status. , so as to cleverly use technical means to visually enable the staff to quickly understand whether an order is an early warning order or an abnormal order, and which orders are early warning orders and which orders are abnormal orders, thus shortening the time for staff to learn from numerous orders. The time for locating early warning orders and abnormal orders has improved the overall efficiency of staff processing early warning orders and abnormal orders.

In some optional implementations, performing the circulation processing on the order to obtain a circulation processing result of the order includes:

Circulation processing is performed on the order by using a preset circulation processing rule to obtain a circulation processing result of the order; or,

When a circulation processing operation for the order is received, a circulation processing result of the order is acquired in response to the circulation processing operation.

The beneficial effect of the technical solution is that: the order can be automatically transferred by using the preset transfer processing rules, so as to obtain the transfer processing result; the order can also be manually processed by manual operation. The same as the mechanism for generating abnormal orders, it also adopts a combination of automatic and manual methods to improve the efficiency of circulation processing by using preset circulation processing rules, or use manual processing methods to deal with abnormal orders with complex situations. , to ensure that the results of the order transfer processing are reasonable and reliable, and can gain the trust of all stakeholders.

In some optional embodiments, the judging of the order to obtain a judging result of the order includes:

Input the order information of the order into the judging model to obtain the responsible party of the order and its corresponding judging ratio;

Calculate the product of the order amount of the order and the liability ratio of each of the responsible parties to obtain the amount of liability corresponding to each of the responsible parties;

Wherein, the training process of the judgment model includes:

Acquiring a training set, the training set includes a plurality of training data, and each of the training data includes order information of a sample order and labeling data of the responsible party of the sample order and its corresponding judging ratio;

For each training data in the training set, the following processing is performed:

Input the order information of the sample order in the training data into a preset deep learning model to obtain the prediction data of the responsible party of the sample order and its corresponding judging ratio;

Update the model parameters of the deep learning model based on the predicted data and labeling data of the responsible party of the sample order and its corresponding liability ratio;

Check whether the preset training end condition is met; if yes, use the trained deep learning model as the judging model; if not, continue to train the deep learning model by using the next training data.

The beneficial effect of the technical solution is that: the judgment model can be obtained by training a large amount of training data, and can be used for different input data (that is, the order information of the order, such as the order number, creation time, expected delivery time, delivery address, Consignee address, consignee name, consignee phone number, collection point, carrier, distribution center, express network, scan record, item name, item type, item quantity, item weight, item volume, weather type, delivery The corresponding output data (that is, the responsible party of the order and its corresponding judging ratio) are predicted to obtain the corresponding output data, which has a wide range of applications and a high level of intelligence. Through design, an appropriate amount of neuron computing nodes and a multi-layer computing hierarchy are established, and the appropriate input layer and output layer can be selected to obtain a preset deep learning model. Through the learning and tuning of the preset deep learning model, The functional relationship from input to output is established. Although the functional relationship between input and output cannot be found 100%, it can approach the realistic relationship as much as possible. The judging model obtained from this training can obtain orders based on the order information of the order. The responsible party and its corresponding liability ratio, and the calculation results are highly accurate and reliable. After obtaining the judging ratio of each responsible party, the product of the order amount and the judging ratio of each responsible party can be obtained, and the corresponding judging amount of each responsible party can be obtained. That is to say, the judgment result is obtained in two steps. The first step determines one or more responsible parties (and their liability ratio), and the second step determines the amount of one or more responsible parties. (calculated based on the liability ratio and the order amount). When designing the liability model, what is considered is not the direct output of the judgment amount, but the output of the judgment ratio. In the training set, the correlation between sample orders with similar judgment ratios is higher, rather than the similar judgment amount. There is a higher degree of correlation between the sample orders of , so it is more realistic and more suitable for cases where the amount of judgment varies but the situation is similar.

In some optional implementations, the updating of the settlement information of each responsible party based on the judgment result of the order includes:

Based on the judgment result of the order, detecting whether each of the responsible parties satisfies the preset punitive judgment conditions;

When it is detected that the responsible party satisfies the punitive judgment condition, the amount of the responsible party's judgment is adjusted by using a preset punitive judgment rule;

A confirmation operation for the amount of liability is received by the interactive device, and in response to the confirmation operation, the settlement information of the responsible party is updated with the adjusted amount of liability.

The beneficial effect of the technical solution is that: after using the judging model to identify the responsible party intelligently (that is, the object that needs to be responsible for the abnormal order is clarified), each responsibility can be detected according to the preset punitive judgment conditions. Whether the party meets the conditions, if so, the default punitive judgment rules will be used to automatically adjust the amount of the responsible party's liability (for example, double, 5 times, 10 times, etc.), the purpose is to serve as a warning , to avoid repeat offenses, but whether the result of this automatic adjustment is appropriate still needs to be confirmed manually, that is to say, the responsible party is not directly updated after the adjustment of the amount. This kind of punitive judgment is reasonable and correct before it can be truly implemented. In the entire punitive judgment process, the aforementioned automatic detection and adjustment steps are used to improve efficiency, and the subsequent manual confirmation steps are used to ensure accuracy, so as to avoid inappropriate and unreasonable judgments causing the responsible party’s rebound or even resistance and confrontation. It is beneficial to reduce the generation of abnormal orders, and does not affect the normal development of follow-up work.

In some optional embodiments, the order includes multiple sub-orders;

That the order satisfies the first preset condition means:

Acquire the duration that each sub-order of the order is in the pending order state, and use the maximum duration among these durations as the pending transport duration of the order, and when it is detected that the pending transport duration of the order is not less than the first duration When the preset time period is used, it is determined that the order meets the first preset condition;

That the order satisfies the second preset condition means:

When an abnormal marking operation for at least one sub-order of the order is received, in response to the abnormal marking operation, it is determined that the order satisfies the second preset condition.

The beneficial effect of the technical solution is that: each order can include multiple sub-orders, and for each order, when at least one of its sub-orders has not been delivered over time, it is confirmed that the order meets the first preset condition, and when at least one of its sub-orders is manually When marked as an abnormal order, it is determined that the order meets the second preset condition. In practical applications, customers often place orders in a consolidated manner for convenience or to enjoy discounts. It is common for each order to contain multiple items, but these items may be stored in different warehouses, so the order needs to be split out Corresponding multiple sub-orders, and complete the transportation and even distribution for each sub-order. At this time, if any one of the sub-orders fails to be delivered on time, it will lead to a bad shopping experience for customers on a psychological level. Therefore, as long as any sub-order is not delivered over time or is marked as abnormal, the entire order will be classified as abnormal. , in order to tilt resources to these abnormal orders and complete the rapid disposal of these orders, which can meet the needs of specific applications.

In a second aspect, the present application provides an abnormal order management device, the device comprising:

an abnormal order module, configured to adjust the order status of the order to abnormal when the order meets the first preset condition or the second preset condition, and set the abnormal processing status of the order to pending;

an order processing module, configured to perform circulation processing on the order to obtain a circulation processing result of the order, and adjust the abnormal processing status of the order to processed;

The order judging module is used for judging the order when the abnormal processing status of the order is processed to obtain the judging result of the order, and the judging result of the order is used to indicate the order the responsible party and the corresponding amount of the judgment;

A settlement update module, configured to update the settlement information of each of the responsible parties based on the judgment result of the order;

Wherein, that the order satisfies the first preset condition means:

Acquiring the length of time that the order is in the order state to be shipped, so as to obtain the time to be shipped of the order, and when it is detected that the time to be shipped of the order is not less than the first preset time, determine that the order satisfies the the first preset condition;

That the order satisfies the second preset condition means:

When an abnormal marking operation for the order is received, in response to the abnormal marking operation, it is determined that the order satisfies the second preset condition.

In some optional embodiments, the apparatus further includes:

an early warning order module, configured to adjust the order status of the order to early warning when it is detected that the to-be-delivered duration of the order is not less than the second preset duration and less than the first preset duration;

Wherein, the second preset duration is smaller than the first preset duration.

In some optional embodiments, the apparatus further includes:

a display control module, configured to generate a display image corresponding to the order when the order status of the order is abnormal or early warning, and the display image is used to indicate different order statuses of the order by using different display modes;

The image display module is used for displaying the display image by using a display device.

In some optional implementations, the order processing module is used to:

Circulation processing is performed on the order by using a preset circulation processing rule to obtain a circulation processing result of the order; or,

When a circulation processing operation for the order is received, a circulation processing result of the order is acquired in response to the circulation processing operation.

In some optional embodiments, the order judging module is used to:

Input the order information of the order into the judging model to obtain the responsible party of the order and its corresponding judging ratio;

Calculate the product of the order amount of the order and the liability ratio of each of the responsible parties to obtain the amount of liability corresponding to each of the responsible parties;

Wherein, the training process of the judgment model includes:

Acquiring a training set, the training set includes a plurality of training data, and each of the training data includes order information of a sample order and labeling data of the responsible party of the sample order and its corresponding judging ratio;

For each training data in the training set, the following processing is performed:

Input the order information of the sample order in the training data into a preset deep learning model to obtain the prediction data of the responsible party of the sample order and its corresponding judging ratio;

Update the model parameters of the deep learning model based on the predicted data and labeling data of the responsible party of the sample order and its corresponding liability ratio;

Check whether the preset training end condition is met; if yes, use the trained deep learning model as the judging model; if not, continue to train the deep learning model by using the next training data.

In some optional implementations, the settlement update module is used to:

Based on the judgment result of the order, detecting whether each of the responsible parties satisfies the preset punitive judgment conditions;

When it is detected that the responsible party satisfies the punitive judgment condition, the amount of the responsible party's judgment is adjusted by using a preset punitive judgment rule;

A confirmation operation for the amount of liability is received by the interactive device, and in response to the confirmation operation, the settlement information of the responsible party is updated with the adjusted amount of liability.

In some optional embodiments, the order includes multiple sub-orders;

That the order satisfies the first preset condition means:

Acquire the duration that each sub-order of the order is in the pending order state, and use the maximum duration among these durations as the pending transport duration of the order, and when it is detected that the pending transport duration of the order is not less than the first duration When the preset time period is used, it is determined that the order meets the first preset condition;

That the order satisfies the second preset condition means:

When an abnormal marking operation for at least one sub-order of the order is received, in response to the abnormal marking operation, it is determined that the order satisfies the second preset condition.

In a third aspect, the present application provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

In a fourth aspect, the present application provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps of any one of the above methods are implemented.

Description of drawings

The present application will be further described below with reference to the accompanying drawings and embodiments.

FIG. 1 shows a schematic flowchart of an abnormal order management method provided by the present application.

FIG. 2 shows a schematic flowchart of another abnormal order management method provided by the present application.

FIG. 3 shows a schematic flowchart of another abnormal order management method provided by the present application.

FIG. 4 shows a schematic flowchart of an order judgment provided by the present application.

FIG. 5 shows a schematic flow chart of updating settlement information provided by the present application.

FIG. 6 shows a flow chart of an exception management service provided by the present application.

FIG. 7 shows a schematic structural diagram of an abnormal order management apparatus provided by the present application.

FIG. 8 shows a structural block diagram of an electronic device provided by the present application.

FIG. 9 shows a schematic structural diagram of a program product provided by the present application.

Detailed ways

The technical solutions in the present application will be described below with reference to the accompanying drawings and specific embodiments of the present application. It should be noted that, on the premise of no conflict, the embodiments or technical features described below may be Any combination forms new embodiments.

In this application, "at least one" means one or more, and "plurality" means two or more. "And/or", which describes the relationship between the related objects, means that there can be three kinds of relationships, for example, A and/or B, it can mean that A exists alone, A and B exist at the same time, and B exists alone, where A, B can be singular or plural. The character "/" generally indicates that the associated objects are an "or" relationship. "At least one item(s) below" or similar expressions thereof refer to any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (a) of a, b or c, can represent: a, b, c, a and b, a and c, b and c, a and b and c, where a, b and c can be It can be single or multiple. It is worth noting that "at least one item(s)" can also be interpreted as "one item(s) or more(s)".

It should also be noted that, in this application, words such as "exemplary" or "such as" are used to mean serving as an example, illustration or illustration. Any implementation or design described herein as "exemplary" or "such as" should not be construed as preferred or advantageous over other implementations or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present the related concepts in a specific manner.

[Method implementation]

Referring to FIG. 1 , FIG. 1 shows a schematic flowchart of an abnormal order management method provided by the present application.

The method includes:

Step S101: when the order meets the first preset condition or the second preset condition, adjust the order status of the order to abnormal, and set the abnormal processing status of the order to pending;

Step S102: performing circulation processing on the order to obtain a circulation processing result of the order, and adjusting the abnormal processing status of the order to processed;

Step S103: When the abnormal processing status of the order is processed, the order is judged to obtain the judgment result of the order, and the judgment result of the order is used to indicate the responsible party of the order and its corresponding amount of liability;

Step S104: Based on the judgment result of the order, update the settlement information of each of the responsible parties;

Wherein, that the order satisfies the first preset condition means:

Acquiring the length of time that the order is in the order state to be shipped, so as to obtain the time to be shipped of the order, and when it is detected that the time to be shipped of the order is not less than the first preset time, determine that the order satisfies the the first preset condition;

That the order satisfies the second preset condition means:

When an abnormal marking operation for the order is received, in response to the abnormal marking operation, it is determined that the order satisfies the second preset condition.

As a result, the automatic aging monitoring method (or the automatic reporting method) and the manual reporting method are combined, and the abnormal orders are processed in a timely manner, which avoids the inefficiency problem of relying only on manual reporting, and also avoids errors caused by completely relying on automatic division. The effective combination of the two can fully cover the processing of abnormal orders, making the processing of abnormal orders more efficient and more accurate.

On the one hand, a first preset condition (or an automatic reporting condition) is set for obtaining the first type of abnormal order, that is, an abnormal order detected by the automatic aging monitoring method. Orders with a long duration are listed as abnormal orders.

On the other hand, a second preset condition (or manual reporting condition) is set for obtaining the second type of abnormal orders, that is, the abnormal orders marked by manual reporting. for abnormal orders.

This application uses the following methods to deal with abnormal orders: if there is an order that meets any of the above two types of conditions, adjust its order status to abnormal, and set its abnormal processing status to pending; For each order, it is processed in circulation, and its abnormal processing status is updated to be processed; then for these orders whose abnormal processing status is processed, judgment (determining the responsible party and the amount of judgment) and recovery (that is, updating The settlement information of the relevant responsible party, such as one or more responsible parties).

It can not only monitor (or track) whether each order is abnormal in real time, but also deal with abnormal orders in a timely manner, so that they can be transferred to the follow-up link, so as to prevent them from staying in the unresolved state for a long time, which will lead to many problems in the entire supply chain. The dissatisfaction of each related party will improve the experience of each related party in using the supply chain.

At the same time, in addition to the order status, an exception processing status is also set to complete the tracking and processing of abnormal orders, which reflects the importance attached to abnormal orders, and it is convenient for managers to use the exception processing status as a starting point to deal with pending orders in the exception processing status. Processed, processed and other types of screening, sorting, etc., urge the relevant staff to deal with abnormal orders quickly and preferentially.

In addition, this part of the data (order information, relevant responsible parties, amount of judgment, etc.) including the abnormal processing status can be independently mined and analyzed to learn the subdivision types, causes and corresponding processing methods of abnormal orders. Avoid generating more abnormal orders.

The abnormal order management method provided by this application, for example, can be applied to the logistics industry (including express delivery, takeaway, errands, railway transportation, etc.) and other industries that require transportation (or distribution).

The abnormal order in this application refers to the order whose order status is abnormal. Similarly, an early warning order hereinafter refers to an order whose order status is early warning.

The order status may include, for example, Pending Assignment, Pending Shipment, In Shipment, Dispatching, Signed For, Returning, Refunding, Returned, Refunded, and Exception. In a specific application scenario, since an order is created, the order status is initially set to pending distribution; after planning the transportation route and assigning transportation vehicles for the order, the order status of the order is adjusted to pending delivery; when the order is When the corresponding item is in transit, the order status is adjusted to be in delivery; when the item corresponding to the order is on the delivery road, the order status is adjusted to be in delivery; when the item corresponding to the order is signed by the consignee or the collection point, The order status is adjusted to have been signed; the adjustment of the above order status can be done automatically or manually.

When an abnormal situation occurs in the above links, such as when the delivery is not delivered over time, the order status of the order is automatically adjusted to be abnormal. Another example is that when the item is damaged or lost, the order status of the order is marked as abnormal by staff A, and staff B communicates with the customer who placed the order to refund after telephone communication, and the order status is adjusted to refund, When the refund arrives, the order status is adjusted to Refunded.

The exception handling status may include, for example, pending, processing, and processed. In a specific application scenario, the order status of an order is adjusted to abnormal, and the abnormal processing status of the order is initialized to pending; when a staff member processes the order, the abnormal processing status of the order is adjusted to Processing; when the order is processed, the exception processing status of the order is adjusted to processed. Orders whose exception processing status is processed can continue to be processed, and their exception processing status can remain unchanged.

This application does not limit the status identifiers of various statuses in the order status and the abnormal processing status, which can be represented by, for example, one or more of Chinese, letters, numbers, symbols, and icons.

The circulation process in this application refers to the process of transferring an abnormal order to the next order status. For example, the circulation process may include return, refund, reissue, reissue, reminder, etc. The corresponding next order status may be, for example, Is pending return, pending refund, pending assignment, pending assignment, shipping, etc. It also allows the order to continue the normal shipping process against false positives.

This application does not limit the responsible party, for example, it may be any one or more of the related parties. Relevant parties may include, for example, logistics companies (or express delivery companies), staff of logistics companies, customers (of logistics companies), carriers, drivers, collection outlets, customers who place orders on e-commerce platforms, etc. The customers of the logistics company can be, for example, the sellers of the e-commerce platform, or can be enterprises and institutions, and can also be individuals.

In a specific application scenario, an order becomes an abnormal order because carrier A loses the goods. The responsible party for the order is carrier A, and the corresponding judgment amount is the insured value of the lost goods of 2,000 yuan. Based on the judgment result, the settlement information of carrier A is updated. When carrier A adopts the monthly settlement method, the monthly settlement amount of carrier A is deducted by RMB 2,000.

In another specific application scenario, an order becomes an abnormal order because customer B (here, the customer refers to the merchant who delivered the goods) misses one accessory when delivering the order. The responsible party for the order is customer B, and the corresponding judgment The amount of responsibility is 10 yuan, and based on the judgment result, the settlement information of customer B is updated. When customer B adopts the monthly settlement method, the monthly settlement amount of this customer B is increased by 10 yuan.

The first preset duration in this application and the second preset duration in the following are preset durations, and the application does not limit the specific values of the two, as long as the first preset duration is greater than the second preset duration That's it. The first preset duration may be, for example, 20 hours, 24 hours, 28 hours, and the like, and the second preset duration may be, for example, 8 hours, 12 hours, 16 hours, and the like.

The present application does not limit the manner of receiving various (manual) operations, for example, an interaction device may be used to receive operations. The operations are divided according to input modes, for example, text input operations, audio input operations, video input operations, key input operations, and the like may be included. These operations may include, for example, an exception marking operation and the following flow processing operations, confirmation operations, and the like.

This application does not limit the interactive device, which can be, for example, a mobile phone, a tablet computer, a notebook computer, a desktop computer, a server, a smart wearable device, a workstation, or a console.

Referring to FIG. 2, FIG. 2 shows a schematic flowchart of another abnormal order management method provided by the present application.

In some optional embodiments, the method further includes:

Step S105: when it is detected that the to-be-delivered duration of the order is not less than the second preset duration and less than the first preset duration, adjust the order status of the order to an early warning;

Wherein, the second preset duration is smaller than the first preset duration.

Therefore, in the process of automatically monitoring the order aging, not only can an abnormal aging be set (once the pending delivery time of the order is greater than or equal to the first preset duration, the order status will automatically become abnormal), but also an early warning aging (once the order will be shipped) The pending delivery time is greater than or equal to the second preset time period and less than the first preset time period, the order status will automatically change to an early warning), which is used to monitor that an abnormality has not yet occurred, but an abnormality may occur (for example, no one has processed it or processed too much Orders that are slow), urge relevant personnel to process and prioritize them as soon as possible after seeing the relevant warning signs, so as to prevent these early warning orders from becoming abnormal orders, and adopt the above preventive measures to actively and actively reduce the probability of orders becoming abnormal orders.

Referring to FIG. 3 , FIG. 3 shows a schematic flowchart of another abnormal order management method provided by the present application.

In some optional embodiments, the method further includes:

Step S106: when the order status of the order is abnormal or early warning, a display image corresponding to the order is generated, and the display image is used to indicate different order statuses of the order by using different display modes;

Step S107: Display the display image by using a display device.

Therefore, when the display device displays the order, different display modes are used to indicate different order states of the order. For example, an early warning order can be indicated by adding a yellow exclamation mark before the order number, and abnormal orders can be indicated by adding a red exclamation mark before the order number; Red text highlighted color indicates early warning order; or yellow font color can be used to indicate early warning order, and red font color can be used to indicate abnormal order; .

Compared with the text content itself, different display methods can intuitively and conspicuously reflect the different order statuses, so as to make clever use of technical means to visually enable the staff to quickly understand whether an order is an early warning order or an abnormal order, and which The order is an early warning order and which orders are abnormal orders. In this way, the time for staff to locate early warning orders and abnormal orders from a large number of orders is shortened, and the overall efficiency of staff processing early warning orders and abnormal orders is improved.

The present application does not limit the display device, which may be, for example, an electronic device with a display function, such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, and a smart wearable device.

In some optional implementation manners, the step S102 may include:

Circulation processing is performed on the order by using a preset circulation processing rule to obtain a circulation processing result of the order; or,

When a circulation processing operation for the order is received, a circulation processing result of the order is acquired in response to the circulation processing operation.

Therefore, the order can be automatically transferred by using the preset transfer processing rules, so as to obtain the transfer processing result; the order can also be manually transferred by manual operation.

The same as the mechanism for generating abnormal orders, it also adopts a combination of automatic and manual methods to improve the efficiency of circulation processing by using preset circulation processing rules, or use manual processing methods to deal with abnormal orders with complex situations. , to ensure that the results of the order transfer processing are reasonable and reliable, and can gain the trust of all stakeholders.

In this application, the preset flow processing rules are preset rules, which can be manually set. For example, for an order with a specific keyword "out of stock" in the order information, the reissue (stock) process can be automatically performed, and the order status can be adjusted to be allocated. For another example, for an order with a specific code "E04" in the order information (for example, the code is used to indicate the need for delivery restrictions, and the delivery range of the customer who placed the order has been unable to complete the delivery), the order closing and refund processing can be automatically executed, and Adjust the order status to Refunded.

Referring to FIG. 4 , FIG. 4 shows a schematic flowchart of judging an order provided by the present application.

In some optional implementation manners, the step S103 may include:

Step S201: Input the order information of the order into the judging model to obtain the responsible party of the order and its corresponding judging ratio;

Step S202: Calculate the product of the order amount of the order and the liability ratio of each of the responsible parties to obtain the amount of liability corresponding to each of the responsible parties;

Wherein, the training process of the judgment model includes:

Acquiring a training set, the training set includes a plurality of training data, and each of the training data includes order information of a sample order and labeling data of the responsible party of the sample order and its corresponding judging ratio;

For each training data in the training set, the following processing is performed:

Input the order information of the sample order in the training data into a preset deep learning model to obtain the prediction data of the responsible party of the sample order and its corresponding judging ratio;

Update the model parameters of the deep learning model based on the predicted data and labeling data of the responsible party of the sample order and its corresponding liability ratio;

Check whether the preset training end condition is met; if yes, use the trained deep learning model as the judging model; if not, continue to train the deep learning model by using the next training data.

Therefore, the liability model can be trained from a large amount of training data, and can predict the corresponding output data (ie the responsible party of the order and its corresponding liability ratio) for different input data (ie, the order information of the order). Wide range and high level of intelligence.

The order information may include, for example, order number, creation time, expected delivery time, delivery address, delivery address, consignee name, consignee phone number, collection point, carrier, distribution center, express delivery point, scan Records, item name, item type, item quantity, item weight, item volume, weather type, delivery restriction type, etc.

For example, the scan records may include scan records of arrival scans (at the time of delivery), loading scans, unloading scans, dispatch scans, signature scans, and the like. Each scan record may include, for example, scan time, scan site identifier, scan device identifier, and the like.

For example, when carrier C loses the order item during delivery, the responsible party output by the judging model can include carrier C and driver D who specifically carries the order item, and the corresponding culpability ratio of carrier C and driver D can be 50% and 50%, respectively.

For another example, when the order has not been delivered over time, and the reason is manually checked, and it is found that the arrival is scanned and missed, the responsible party output by the judging model can be the pickup person E of the logistics company, and the corresponding proportion of the culprit For example, it can be 20%.

For another example, when the delivery restriction type corresponding to the delivery address of the ordering customer F is "Affected Delivery Scope", the delivery cannot be completed due to the needs of delivery restrictions. At this time, the responsible party output by the judgment model can be the missing For saving value or ordering customer F, the corresponding judging ratio is, for example, 0.

Through design, an appropriate amount of neuron computing nodes and a multi-layer computing hierarchy are established, and the appropriate input layer and output layer can be selected to obtain a preset deep learning model. Through the learning and tuning of the preset deep learning model, The functional relationship from input to output is established. Although the functional relationship between input and output cannot be found 100%, it can approach the realistic relationship as much as possible. The judging model obtained from this training can obtain orders based on the order information of the order. The responsible party and its corresponding liability ratio, and the calculation results are highly accurate and reliable.

After obtaining the judging ratio of each responsible party, the product of the order amount and the judging ratio of each responsible party can be obtained, and the corresponding judging amount of each responsible party can be obtained.

That is to say, the judgment result is obtained in two steps. The first step determines one or more responsible parties (and their liability ratio), and the second step determines the amount of one or more responsible parties. (calculated based on the liability ratio and the order amount).

When designing the liability model, what is considered is not the direct output of the judgment amount, but the output of the judgment ratio. In the training set, the correlation between sample orders with similar judgment ratios is higher, rather than the similar judgment amount. There is a higher degree of correlation between the sample orders of , so it is more realistic and more suitable for cases where the amount of judgment varies but the situation is similar.

In some optional embodiments, the present application may use the above training process to train to obtain a liability model, and in other optional embodiments, the present application may use a pre-trained liability model.

In some optional implementations, for example, keyword extraction may be performed on relevant data corresponding to orders that have been judged in the past to obtain order information of sample orders, that is, these sample orders may be real historical orders. Of course, the order information of the sample order can also be automatically generated using the generative network of the GAN model.

Among them, the GAN model is the Generative Adversarial Network, which consists of a generative network and a discriminant network. The generative network randomly samples from the latent space as input, and its output needs to mimic the real samples in the training set as much as possible. The input of the discriminant network is the real sample or the output of the generative network, and its purpose is to distinguish the output of the generative network from the real sample as much as possible. The generative network, on the other hand, tries to fool the discriminative network as much as possible. The two networks fight against each other and constantly adjust the parameters. The ultimate goal is to make the discriminant network unable to judge whether the output result of the generation network is true. Using the GAN model can generate order information for multiple sample orders, which can be used in the training process of the judgment model, which can effectively reduce the amount of data collected from the original data and greatly reduce the cost of data collection and labeling.

This application does not limit the acquisition method of the labeling data, for example, manual labeling, automatic labeling or semi-automatic labeling may be adopted. When the sample order adopts the historical order, the labeling data of the responsible party and the judging ratio corresponding to the sample order can be obtained by keyword extraction.

This application does not limit the training process of the judgment model, for example, the training method of the above-mentioned supervised learning, or the training method of semi-supervised learning, or the training method of unsupervised learning can be adopted.

This application does not limit the preset training end condition, which may be, for example, that the number of training times reaches a preset number of times (the preset number of times is, for example, 1, 3, 10, 100, 1000, 10000, etc.), or it can be It means that the training data in the training set has completed one or more training sessions, or the total loss value obtained in this training is not greater than the preset loss value.

In some other optional implementation manners, the step S103 may include:

The judgment amount for each of the responsible parties is received by the interactive device as the judgment amount corresponding to each of the responsible parties.

Referring to FIG. 5, FIG. 5 shows a schematic flowchart of updating settlement information provided by the present application.

In some optional implementation manners, the step S104 may include:

Step S301: Based on the judgment result of the order, detect whether each of the responsible parties satisfies a preset punitive judgment condition;

Step S302: when it is detected that the responsible party satisfies the punitive liability conditions, the pre-set punitive liability rules are used to adjust the amount of the responsible party's judgment;

Step S303: Use the interactive device to receive a confirmation operation for the judgment amount, and in response to the confirmation operation, update the settlement information of the responsible party with the adjusted judgment amount.

Therefore, after using the judgment model to identify the responsible party intelligently (that is, the object that needs to be responsible for the abnormal order is clarified), it is also possible to detect whether each responsible party meets the conditions according to the preset punitive judgment conditions. If it is satisfied, the pre-set punitive judgment rules will be used to automatically adjust the amount of the responsible party's liability (for example, double, 5, 10, etc.), the purpose is to play a warning role and avoid repeat offenses. Whether the result of this automatic adjustment is appropriate still needs to be confirmed manually, that is to say, the accountable party is not directly updated with the settlement information after the adjustment of the amount, and manual verification is required here to confirm the punitive judgment. It is reasonable and correct in order to be truly implemented.

In the entire punitive judgment process, the aforementioned automatic detection and adjustment steps are used to improve efficiency, and the subsequent manual confirmation steps are used to ensure accuracy, so as to avoid inappropriate and unreasonable judgments causing the responsible party’s rebound or even resistance and confrontation. It is beneficial to reduce the generation of abnormal orders, and does not affect the normal development of follow-up work.

The punitive judgment conditions and punitive liability rules in this application are preset conditions and rules, which can be manually set. For example, the punitive judgment condition may be that a single responsible party is fully responsible (that is, the responsible party's corresponding judgment and liability ratio is 100%), and the judgment amount is greater than 10,000 yuan. The corresponding punitive judgment rule is: if a single responsible party is fully responsible, and the judgment amount is more than 10,000 yuan, the judgment amount shall be adjusted by 2 times (that is, the adjusted judgment amount is twice the amount before the adjustment) ; If a single responsible party is fully responsible, and the amount of the judgment is more than 100,000 yuan, the amount of the judgment shall be adjusted by 3 times. When a single responsible party intentionally causes heavy losses, punitive judgment can act as a deterrent and warning.

For example, if an order is abnormal due to the loss of valuables, the responsible party is Carrier G, the liability ratio is 100%, and the amount of liability is 50,000 yuan. At this time, it is judged that Carrier G satisfies the preset punitive judgment. Conditions, the pre-set punitive liability rules are used to adjust the amount of liability, and the adjusted amount of liability is 100,000 yuan.

In some optional embodiments, the order may include multiple sub-orders;

That the order satisfies the first preset condition means:

Acquire the duration that each sub-order of the order is in the pending order state, and use the maximum duration among these durations as the pending transport duration of the order, and when it is detected that the pending transport duration of the order is not less than the first duration When the preset time period is used, it is determined that the order meets the first preset condition;

That the order satisfies the second preset condition means:

When an abnormal marking operation for at least one sub-order of the order is received, in response to the abnormal marking operation, it is determined that the order satisfies the second preset condition.

Thus, each order may include multiple sub-orders, and for each order, when at least one of its sub-orders has not been delivered over time, it is confirmed that the order meets the first preset condition, and when at least one of its sub-orders is manually marked as an abnormal order It is determined that the order satisfies the second preset condition.

In practical applications, customers often place orders in a consolidated manner for convenience or to enjoy discounts. It is common for each order to contain multiple items, but these items may be stored in different warehouses, so the order needs to be split out Corresponding multiple sub-orders, and complete the transportation and even distribution for each sub-order. That is to say, each sub-order corresponds to one waybill, and one order corresponds to multiple sub-orders and multiple waybills.

At this time, if any one of the sub-orders fails to be delivered on time, it will lead to a bad shopping experience for customers on a psychological level. Therefore, as long as any sub-order is not delivered over time or is marked as abnormal, the entire order will be classified as abnormal. , in order to tilt resources to these abnormal orders and complete the rapid disposal of these orders, which can meet the needs of specific applications.

Referring to FIG. 6, FIG. 6 shows a flow chart of an exception management service provided by the present application.

Reporting method 1: automatic aging monitoring

1. Order timeliness monitoring, set the delivery timeliness of orders, and specify timeliness alarm rules. Aging alarms are divided into two categories: early warning and abnormal.

Specifically, a threshold value is judged for the pending delivery time of the order, and the order is automatically classified into an early warning order (warning type) or an abnormal order (abnormal type). For example, an order with a waiting time of 12 hours to 24 hours is set as an early warning order, and an order with a waiting time of more than 24 hours is set as an abnormal order.

2. After the order is classified as an early warning order, it will enter the time-limited alarm list, and at the same time, the alarm information will be sent to the applet and PC to notify the relevant staff.

When displaying the order, the “alarm” icon is used for the warning, and the “timeout” is used for the timeout exception, which is displayed according to the report type name (ie, the warning type or the exception type).

The aging alarm list may include fields such as order number, type, first time, second time, status, etc., and the aging alarm list may also include serial number, order number, item, waybill number, license plate number, warning type, alarm time, request Completion time, alarm rule, actual operation time, warning status, order time and other fields. The meaning of each field is shown in Table 1.

Table 1 Field meanings of the aging alarm list

The alarm types in the aging alarm list, for example, can include delivery overtime warning, receipt overtime warning, etc., which can be configured in the dictionary.

Reporting method 2: Manually report exceptions

Manually report exceptions through the driver applet and the PC-side order waybill exception management office.

Orders that automatically generate time-limiting exceptions and manually reported abnormal orders are merged into exception management.

Automatically generated exceptions and reported exceptions have different types and can be identified by the field of "Reporting Path". The exception processing status of each order defaults to pending, which can be changed to processing after processing, and changed to processed after processing is completed. The processed ones can continue to be processed, and the exception processing status remains unchanged.

Judging the responsible party that caused the order exception, the exception judging list used to store the judging information may include, for example, the exception (order) number, whether the judging, responsible party, judging item, judging amount (yuan) and other fields , the meaning of each field is shown in Table 2.

Table 2 The meaning of the fields of the abnormal judgment list

[Apparatus Embodiment]

Referring to FIG. 7, FIG. 7 shows a schematic structural diagram of an abnormal order management apparatus provided by the present application.

The present application also provides an abnormal order management device, the specific implementation of which is consistent with the implementation described in the foregoing method implementation and the technical effects achieved, and some contents will not be repeated.

The device includes:

An abnormal order module 101, configured to adjust the order status of the order to be abnormal when the order meets the first preset condition or the second preset condition, and set the abnormal processing status of the order to pending;

an order processing module 102, configured to perform circulation processing on the order to obtain a circulation processing result of the order, and adjust the abnormal processing status of the order to processed;

The order judging module 103 is used for judging the order when the abnormal processing state of the order is processed to obtain the judging result of the order, and the judging result of the order is used to indicate the The responsible party of the order and its corresponding judgment amount;

a settlement update module 104, configured to update the settlement information of each of the responsible parties based on the judgment result of the order;

Wherein, that the order satisfies the first preset condition means:

Acquiring the length of time that the order is in the order state to be shipped, so as to obtain the time to be shipped of the order, and when it is detected that the time to be shipped of the order is not less than the first preset time, determine that the order satisfies the the first preset condition;

That the order satisfies the second preset condition means:

When an abnormal marking operation for the order is received, in response to the abnormal marking operation, it is determined that the order satisfies the second preset condition.

Continuing to refer to FIG. 7 , in some optional embodiments, the apparatus may further include:

an early warning order module 105, configured to adjust the order status of the order to early warning when it is detected that the to-be-delivered duration of the order is not less than the second preset duration and less than the first preset duration;

Wherein, the second preset duration is smaller than the first preset duration.

Continuing to refer to FIG. 7 , in some optional embodiments, the apparatus may further include:

A display control module 106, configured to generate a display image corresponding to the order when the order status of the order is abnormal or early warning, and the display image is used to indicate different order statuses of the order by using different display modes;

The image display module 107 is used for displaying the display image by using a display device.

In some optional embodiments, the order processing module 102 may be used to:

Circulation processing is performed on the order by using a preset circulation processing rule to obtain a circulation processing result of the order; or,

When a circulation processing operation for the order is received, a circulation processing result of the order is acquired in response to the circulation processing operation.

In some optional embodiments, the order judging module 103 may be used to:

Input the order information of the order into the judging model to obtain the responsible party of the order and its corresponding judging ratio;

Calculate the product of the order amount of the order and the liability ratio of each of the responsible parties to obtain the amount of liability corresponding to each of the responsible parties;

Wherein, the training process of the judgment model includes:

Acquiring a training set, the training set includes a plurality of training data, and each of the training data includes order information of a sample order and labeling data of the responsible party of the sample order and its corresponding judging ratio;

For each training data in the training set, the following processing is performed:

Input the order information of the sample order in the training data into a preset deep learning model to obtain the prediction data of the responsible party of the sample order and its corresponding judging ratio;

Update the model parameters of the deep learning model based on the predicted data and labeling data of the responsible party of the sample order and its corresponding liability ratio;

Check whether the preset training end condition is met; if yes, use the trained deep learning model as the judging model; if not, continue to train the deep learning model by using the next training data.

In some optional implementations, the settlement update module 104 may be used to:

Based on the judgment result of the order, detecting whether each of the responsible parties satisfies the preset punitive judgment conditions;

When it is detected that the responsible party satisfies the punitive judgment condition, the amount of the responsible party's judgment is adjusted by using a preset punitive judgment rule;

A confirmation operation for the amount of liability is received by the interactive device, and in response to the confirmation operation, the settlement information of the responsible party is updated with the adjusted amount of liability.

In some optional embodiments, the order may include multiple sub-orders;

That the order satisfies the first preset condition means:

Acquire the duration that each sub-order of the order is in the pending order state, and use the maximum duration among these durations as the pending transport duration of the order, and when it is detected that the pending transport duration of the order is not less than the first duration When the preset time period is used, it is determined that the order meets the first preset condition;

That the order satisfies the second preset condition means:

When an abnormal marking operation for at least one sub-order of the order is received, in response to the abnormal marking operation, it is determined that the order satisfies the second preset condition.

[Equipment implementation]

The present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of any of the above methods when executing the computer program, and the specific implementation is The method is consistent with the implementation manner and the technical effect achieved in the above-mentioned method implementation manner, and some contents will not be repeated.

Referring to FIG. 8, FIG. 8 shows a structural block diagram of an electronic device 200 provided by the present application.

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.

Memory 210 may include readable media in the form of volatile memory, such as random access memory (RAM) 211 and/or cache memory 212 , and may further include read only memory (ROM) 213 .

The memory 210 further stores a computer program, and the computer program can be executed by the processor 220, so that the processor 220 implements the steps of any one of the above methods.

The memory 210 may also include a utility 214 having at least one program module 215 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some of these examples. Such combinations may include implementations of network environments.

Accordingly, the processor 220 can execute the computer programs described above, and can execute the utility 214 .

The processor 220 may adopt one or more Application Specific Integrated Circuits (ASIC, Application Specific Integrated Circuit), DSP, Programmable Logic Device (PLD, Programmable Logic Device), Complex Programmable Logic Device (CPLD, Complex Programmable Logic Device), field programmable Field-Programmable Gate Array (FPGA) or other electronic components.

Bus 230 may be a local bus representing one or more of several types of bus structures, including a memory bus or memory controller, peripheral bus, graphics acceleration port, processor, or any bus structure using a variety of bus structures.

The electronic device 200 may also communicate with one or more external devices 240 such as keyboards, pointing devices, Bluetooth devices, etc., as well as with one or more devices capable of interacting with the electronic device 200, and/or with the electronic device 200 can communicate with any device (eg, router, modem, etc.) that can communicate with one or more other computing devices. Such communication may take place through the input output interface 250 . Also, the electronic device 200 may communicate with one or more networks (eg, a local area network (LAN), a wide area network (WAN), and/or a public network such as the Internet) through a network adapter 260 . The network adapter 260 may communicate with other modules of the electronic device 200 through the bus 230 . It should be understood that, although not shown, other hardware and/or software modules may be used in conjunction with 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 platform, etc.

[Medium implementation]

The present application also provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps of any one of the above methods are implemented, and the specific implementation method thereof is the same as the above method. The embodiments described in the embodiments and the technical effects achieved are the same, and some contents will not be repeated.

Referring to FIG. 9, FIG. 9 shows a schematic structural diagram of a program product provided by the present application.

The program product is used to implement any of the above methods. The program product may take the form of a portable compact disk read only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto, and in this application, a readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples (non-exhaustive list) of readable storage media include: electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

A computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave with readable program code embodied thereon. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A readable storage medium can also be any readable medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing. Program code for carrying out 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++, etc., as well as conventional procedural programming languages Programming languages such as C or similar. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server execute on. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (eg, using an Internet service provider business via an Internet connection).

This application is described from the viewpoints of purpose of use, efficiency, progress and novelty, etc., and has complied with the functional enhancement and use requirements emphasized by the patent law. It is only an example, and does not limit this application. Therefore, all structures, devices, features, etc. that are similar to or similar to those of this application, that is, all equivalent replacements or modifications made according to the scope of the patent application of this application, shall belong to this application. within the scope of protection of the patent application.

Claims (10)

1. A method for managing abnormal orders, wherein the method comprises: When the order meets the first preset condition or the second preset condition, adjust the order status of the order to abnormal, and set the abnormal processing status of the order to pending; Perform circulation processing on the order to obtain a circulation processing result of the order, and adjust the abnormal processing status of the order to processed; When the abnormal processing status of the order is processed, the order is judged to obtain the judgment result of the order, and the judgment result of the order is used to indicate the responsible party of the order and its corresponding the amount of liability; Based on the judgment result of the order, update the settlement information of each of the responsible parties; Wherein, that the order satisfies the first preset condition means: Acquiring the length of time that the order is in the order state to be shipped, so as to obtain the time to be shipped of the order, and when it is detected that the time to be shipped of the order is not less than the first preset time, determine that the order satisfies the the first preset condition; That the order satisfies the second preset condition means: When an abnormal marking operation for the order is received, in response to the abnormal marking operation, it is determined that the order satisfies the second preset condition. 2. The abnormal order management method according to claim 1, wherein the method further comprises: When it is detected that the to-be-delivered duration of the order is not less than the second preset duration and less than the first preset duration, adjusting the order status of the order to an early warning; Wherein, the second preset duration is smaller than the first preset duration. 3. The abnormal order management method according to claim 2, wherein the method further comprises: When the order status of the order is abnormal or early warning, a display image corresponding to the order is generated, and the display image is used to indicate different order statuses of the order by using different display modes; The display image is displayed using a display device. 4. The abnormal order management method according to claim 1, characterized in that, performing the circulation processing on the order to obtain the circulation processing result of the order, comprising: Circulation processing is performed on the order by using a preset circulation processing rule to obtain a circulation processing result of the order; or, When a circulation processing operation for the order is received, a circulation processing result of the order is acquired in response to the circulation processing operation. 5. The abnormal order management method according to claim 1, characterized in that, the judging the order is performed to obtain a judging result of the order, comprising: Input the order information of the order into the judging model to obtain the responsible party of the order and its corresponding judging ratio; Calculate the product of the order amount of the order and the liability ratio of each of the responsible parties to obtain the amount of liability corresponding to each of the responsible parties; Wherein, the training process of the judgment model includes: Acquiring a training set, the training set includes a plurality of training data, and each of the training data includes order information of a sample order and labeling data of the responsible party of the sample order and its corresponding judging ratio; For each training data in the training set, the following processing is performed: Input the order information of the sample order in the training data into a preset deep learning model to obtain the prediction data of the responsible party of the sample order and its corresponding judging ratio; Update the model parameters of the deep learning model based on the predicted data and labeling data of the responsible party of the sample order and its corresponding liability ratio; Check whether the preset training end condition is met; if yes, use the trained deep learning model as the judging model; if not, continue to train the deep learning model by using the next training data. 6. The abnormal order management method according to claim 5, wherein the updating of the settlement information of each of the responsible parties based on the judgment result of the order comprises: Based on the judgment result of the order, detecting whether each of the responsible parties satisfies the preset punitive judgment conditions; When it is detected that the responsible party satisfies the punitive judgment condition, the amount of the responsible party's judgment is adjusted by using a preset punitive judgment rule; A confirmation operation for the amount of liability is received by the interactive device, and in response to the confirmation operation, the settlement information of the responsible party is updated with the adjusted amount of liability. 7. The abnormal order management method according to claim 1, wherein the order comprises a plurality of sub-orders; That the order satisfies the first preset condition means: Acquire the duration that each sub-order of the order is in the pending order state, and use the maximum duration among these durations as the pending transport duration of the order, and when it is detected that the pending transport duration of the order is not less than the first duration When the preset time period is used, it is determined that the order meets the first preset condition; That the order satisfies the second preset condition means: When an abnormal marking operation for at least one sub-order of the order is received, in response to the abnormal marking operation, it is determined that the order satisfies the second preset condition. 8. An abnormal order management device, characterized in that the device comprises: an abnormal order module, configured to adjust the order status of the order to abnormal when the order meets the first preset condition or the second preset condition, and set the abnormal processing status of the order to pending; an order processing module, configured to perform circulation processing on the order to obtain a circulation processing result of the order, and adjust the abnormal processing status of the order to processed; The order judging module is used for judging the order when the abnormal processing status of the order is processed to obtain the judging result of the order, and the judging result of the order is used to indicate the order the responsible party and the corresponding amount of the judgment; A settlement update module, configured to update the settlement information of each of the responsible parties based on the judgment result of the order; Wherein, that the order satisfies the first preset condition means: Acquiring the length of time that the order is in the order state to be shipped, so as to obtain the time to be shipped of the order, and when it is detected that the time to be shipped of the order is not less than the first preset time, determine that the order satisfies the the first preset condition; That the order satisfies the second preset condition means: When an abnormal marking operation for the order is received, in response to the abnormal marking operation, it is determined that the order satisfies the second preset condition. 9. An electronic device, characterized in that the electronic device comprises a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the processor implements any one of claims 1-7 steps of the method. 10. 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, implements the steps of the method of any one of claims 1-7.

Images