Multi-responsibility subject meal damage responsibility judgment method, storage medium and program product

Abstract

The invention discloses a multi-responsibility subject meal damage responsibility judgment method, a storage medium and a program product, and belongs to the technical field of computers. The method comprises the following steps: when a server side receives an audit result which is sent by a merchant side and does not support a refund application and a user application platform intervenes in processing, identifying whether a commodity package in a loss voucher has a problem or not through a visual identification capability model, and when the identification result is that the commodity package has the problem, sending the loss voucher to the server side; and obtaining a packaging score accumulated by the merchant on the platform, judging a relationship between the merchant packaging score and a first threshold value, and when the merchant packaging score is lower than the first threshold value, judging that the merchant and the rider carry responsibilities together. Aiming at a scene that an existing instant distribution meal damage responsibility judgment link is complex and difficult to judge, the method prevents a non-leakage problem from flowing into a downstream responsibility judgment link of a system through a visual recognition capability model to affect the accuracy of a responsibility judgment result, and clarifies the right and obligation of each role through quoting a merchant package score capable of reflecting an objective condition, thereby improving the accuracy of the responsibility judgment result. The responsibility judgment accuracy and the platform processing efficiency are improved, and the dispute problem processing cost is reduced.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method for determining liability for loss of instant delivery goods, an electronic device, and a computer-readable storage medium. Background Art

[0002] In the fulfillment and delivery process of food delivery, problems such as "meal scattering and leakage" and "wrong delivery" often occur. The existing processing method is to support users to initiate a refund application for problematic orders, and the system will refund the user after reviewing and approving the refund application. For the determination of responsibility for transaction disputes, most of them require the joint efforts of the system and humans. Limited by existing technical capabilities, there are mainly the following problems: 1) Lack of ability to restore the actual business situation through system technology. In the stage of determining the facts after the problem occurs, the system lacks card control of user behavior and submitted credentials; 2) In the stage of system responsibility determination, with the influx of invalid data due to the lack of card control upstream, the number of misjudgments and missed judgments in the responsibility determination link increases; 3) In the stage of system responsibility determination, only any one party among users / merchants / riders / platforms can be determined for responsibility. During the fulfillment process, if the system cannot recognize valid credentials, it can only judge unilateral responsibility through partial feature data. Inaccurate judgments will lead to subsequent complaints, which will lead to a significant increase in manual service costs.

[0003] In scenarios where it is unclear what the food damage is, due to limitations in the tools and capabilities for judging liability, only a single responsible party can be forcibly identified. The definition of responsibility is not reasonable, resulting in a damaged experience for relevant roles and a waste of the platform's human costs. Summary of the invention

[0004] The present application provides a method for determining liability for loss of goods for instant delivery, an electronic device, and a computer-readable storage medium. The method uses a visual recognition capability model to prevent non-leakage problems from flowing into the downstream liability determination link of the system and affecting the accuracy of the liability determination results. The method also uses a merchant packaging score that can reflect the objective situation to clarify the rights and obligations of each party, improve the accuracy of liability determination and the efficiency of platform processing, and reduce the cost of handling disputes.

[0005] In a first aspect, an embodiment of the present application provides a method for determining liability for meal damages by multiple responsible entities, the method being applied to a server and characterized by comprising:

[0006] Receiving a refund application for an ongoing order sent by a user, wherein the refund application carries a loss certificate;

[0007] Sending the refund application to the merchant side, and waiting for the merchant to review the refund application, wherein the merchant is the merchant providing food service for the order;

[0008] When receiving the review result of the refund application being rejected from the merchant, identifying whether there is packaging damage and / or product leakage in the loss voucher through the visual recognition capability model;

[0009] When the identification result is that the order has the problem, obtaining the packaging score accumulated by the merchant on the platform, and determining the relationship between the merchant packaging score and the first threshold;

[0010] When the merchant's packaging score is lower than a first threshold, it is determined that the merchant and the rider are jointly responsible. When the merchant's packaging score is greater than or equal to the first threshold, it is determined that the rider is responsible. The rider is the rider who provides delivery services for the order.

[0011] Furthermore, after receiving the refund application and before sending the refund application to the merchant, the method further includes:

[0012] Determine whether the loss voucher is valid by using a visual recognition capability model, and when the loss voucher is valid, send the refund application to the merchant end;

[0013] When the loss certificate is invalid, the current refund application is rejected and a prompt is sent to the user terminal to re-upload a valid loss certificate.

[0014] Further, the prompts sent to the user terminal to re-upload the valid loss voucher are counted;

[0015] After determining that the loss certificate is invalid and before rejecting the current refund application, the method further includes:

[0016] Query and determine whether the number of prompts sent to the user end to re-upload the valid loss voucher has reached a second threshold. When the number of prompts does not reach the second threshold, send a prompt to the user end to re-upload the valid loss voucher. When the number of prompts reaches the second threshold, send the refund application to the merchant end.

[0017] Preferably, the judgment conditions for the validity of the loss voucher include: the loss voucher meets the system requirements, or the damaged packaging and / or product leakage can be identified from the loss voucher through a visual recognition capability model.

[0018] Preferably, the packaging points accumulated by the merchant on the platform are generated based on the ratings or star ratings of the meal packaging given by users in historical orders.

[0019] Furthermore, determining the relationship between the merchant packaging score and the first threshold value further includes:

[0020] Query and determine the relationship between the number of historical orders of the merchant and a third threshold;

[0021] When the merchant's packaging score is lower than a first threshold and the merchant's historical order quantity is greater than or equal to a third threshold, it is determined that the merchant and the rider are jointly responsible;

[0022] When the merchant's packaging score is greater than or equal to a first threshold and the merchant's historical order quantity is greater than or equal to a third threshold, or when the merchant's historical order quantity is lower than the third threshold, it is determined that the rider is responsible.

[0023] Furthermore, after the service end completes the meal damage determination, the method further includes:

[0024] Send the judgment result to the merchant end and / or the rider end, so that the merchant end and / or the rider end display the judgment result to the merchant and / or the rider, and the judgment result at least includes the reason for the judgment, the proportion of meal loss sharing, the amount of meal loss compensation, and a prompt for filing a complaint;

[0025] Receive a response to the judgment result returned by the merchant side and / or the rider side, mark the refund application as approved, perform a refund operation through the original transaction link to which the order belongs, and send a refund reminder to the user side.

[0026] Further, receiving a complaint application sent by the merchant and / or the rider through the merchant terminal and / or the rider terminal, wherein the complaint application carries other credentials, and the other credentials include text, pictures, audio and / or video;

[0027] The complaint application is processed through the accountability system. When the accountability system is able to determine the responsible party, the accountability result is sent to the merchant end and / or the rider end again, so that the merchant end and / or the rider end can show the accountability result to the merchant and / or the rider. The accountability result at least includes the reason for the accountability, the proportion of meal loss sharing, the amount of meal loss compensation, and a prompt for transferring to manual service;

[0028] When the processing result is that the merchant and / or the rider are not responsible, it is determined that the platform shall compensate for the meal loss of the corresponding liability portion of the merchant and / or the rider;

[0029] When the accountability system determines that the matter cannot be handled, it is transferred to manual service for processing.

[0030] In a second aspect, an embodiment of the present application further discloses a computer device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that the processor executes the computer program to implement the steps of determining the loss of instant delivery goods as described in any one of items 1 to 8.

[0031] In a third aspect, an embodiment of the present application provides a computer program product, including a computer program, characterized in that when the program is executed by a processor, the steps of determining the loss liability of instant delivery goods as described in any one of claims 1 to 8 are implemented.

[0032] The method for judging responsibility for meal damage by multiple responsible entities disclosed in the embodiment of the present application is applied to the service end. At the stage of determining the facts when a problem occurs, guidance on user behavior and control of submitted loss vouchers are added. Merchant packaging scores are introduced at the stage of determining responsibility by the system. Merchants' assessment of the quality of meal packaging is formed through the packaging scores. Combined with the recognition of loss vouchers by the large model system, a comprehensive determination is made as to which entity or entities, including users / merchants / riders / platforms, shall bear the corresponding responsibility. This solves the technical problem in the prior art that a large number of complaints are caused by the inaccurate judgment of unilateral responsibility by the system. By building the ability to judge and handle shared responsibilities among multiple parties, the rationality of the judgment is improved, unnecessary complaints are reduced, and thus the cost of manual services is reduced.

[0033] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0035] Figure 1 It is a schematic diagram of a flow chart for determining liability for loss of instant delivery goods disclosed in the first aspect of the embodiment of the present application;

[0036] Figure 2 It is one of the platform credit judgment process diagrams disclosed in the first aspect of the embodiment of the present application;

[0037] Figure 3 It is a schematic diagram of the loss voucher card control process disclosed in the first aspect of the embodiment of the present application;

[0038] Figure 4 This is the second schematic diagram of the platform credit judgment process disclosed in the first aspect of the embodiment of the present application;

[0039] Figure 5 A block diagram schematically shows an electronic device for executing the method according to the present application;

[0040] Figure 6 The schematic diagram shows a storage medium for holding or carrying a program for implementing the method according to the present application. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0042] The following is a detailed description of a method for determining liability for loss of instant delivery goods disclosed in this application in conjunction with a specific implementation method.

[0043] In the instant delivery fulfillment scenario, it is common to find that the goods are leaking or the packaging is damaged after receiving the goods. If losses are caused, in the embodiment of the present application, the user can initiate a refund application through the user terminal for this issue and upload the loss certificate in the refund application. Figure 1 As shown, a method for determining liability for loss of instant delivery goods is disclosed in one embodiment of the present application, and the method is applied to the server.

[0044] Step 101, receiving a refund application for an order after delivery fulfillment sent by a user, wherein the refund application carries a loss certificate.

[0045] The user terminal is usually a local life app used by users to place instant delivery orders. After the product packaging is damaged or leaks, causing losses to the user, the user can initiate a refund application for the instant delivery order through the user terminal. The user terminal will prompt the user to upload the loss certificate when initiating a refund application.

[0046] Preferably, the user terminal will be prompted to upload a loss certificate in the form of a picture or video, and it is recommended to provide a text description. Furthermore, the loss certificate can be set to correspond to the type of problem. For example, if the package is damaged, leaked, mis-shipped or mis-delivered, you need to upload a picture or video to prove it, but if it is missing, you can only upload a text description.

[0047] Step 102, sending the refund application to the merchant side, waiting for the merchant to review the refund application, the merchant is the merchant providing commodity services for the order.

[0048] The refund application is sent to the merchant side, and the merchant can judge whether the merchant itself is responsible for the user loss of the order based on the pictures or videos and text descriptions in the refund application loss certificate presented by the merchant side.

[0049] When the merchant believes that it is fully or mainly responsible and is willing to bear the user's losses, it can send an operation to support the user's refund application through the merchant side. After receiving the instruction, the server will refund the user according to the original payment path of the instant delivery order. When the merchant believes that it has no responsibility, or even if it has responsibility, it is unwilling to bear the user's losses, the merchant can send an operation to reject the user's refund application through the merchant side.

[0050] The user can check the option of requiring platform intervention when submitting a refund application through the user terminal, or can initiate a request for platform intervention through the user terminal after receiving a message forwarded by the service terminal to the user terminal that the merchant does not support user refunds.

[0051] The above-mentioned operation of reviewing the refund application by the merchant first allows issues that are the merchant's responsibility, such as packaging problems, wrong shipments, etc., to be handled directly, thereby increasing the speed of handling the responsibility and reducing the cost of the process.

[0052] Step 103, when receiving the review result of the merchant side that the refund application is not supported, and the user applies for the platform to intervene in the processing, the visual recognition capability model is used to identify whether there is packaging damage or product leakage in the loss certificate.

[0053] In this embodiment, the refund process is mainly explained by the reasons of damaged or leaked product packaging, but after training, the visual recognition model of this application can also identify the situation of wrong order delivery. For example, the visual recognition model identifies whether it is wrong delivery by comparing the order photo in the user's refund voucher with the system order, and determines whether it is wrong delivery by comparing the product photo in the refund voucher with the product in the order.

[0054] The server in the embodiment of the present application has a visual recognition capability model, which can be trained to recognize damaged product packaging, product leakage, wrong order delivery, wrong order delivery, etc. Before the server applies the visual recognition capability model, model training is required.

[0055] Before model training, you need to collect a large number of pictures of goods and various packaging, including normal and damaged samples. Label these pictures, especially mark the damaged areas, so as to provide clear supervision information for the model. Data enhancement techniques such as rotation, scaling, and cropping can be applied to increase the diversity of image data and improve the generalization ability of the model. You can use pre-trained image classification or object detection models, such as ResNet, Effici entNet, or YOLO. When more advanced semantic segmentation is required, you can consider models such as U-Net or Mask R-CNN.

[0056] Use the labeled data to fine-tune the pre-trained model, including dividing the training set and validation set, and adjusting the model's hyperparameters, such as learning rate, different product packaging sizes, etc. Use appropriate loss functions, such as cross entropy and focal loss, for damage and spill detection problems. Evaluate the trained model. You can evaluate the model performance on the validation set, including using indicators such as precision, recall, and F1 score to understand the model's accuracy in product identification, package damage, and food spill identification.

[0057] Deploy the trained visual recognition model to the production environment. The server can be a cloud server, cluster device, etc. In actual applications, the performance of the model is continuously monitored to collect feedback from users, merchants, riders, and platform customer service on product damage and leakage, including comments, text, and recordings. The model is continuously improved based on the problems and the recognition accuracy is improved.

[0058] When receiving the audit result sent by the merchant that the refund application is not supported, check whether the user has applied for platform intervention. In the refund application interface provided to the user by the user end, the application for platform intervention is checked by default, and the user can also not check the application for platform intervention. When receiving the audit result sent by the merchant that the refund application is not supported, and the service end detects that the user has chosen not to apply for platform intervention, it terminates the processing of the user's refund application and feeds back the processing result to the user through the user end.

[0059] When the audit result of the refund application not being supported is received from the merchant, and the service end detects that the user chooses to apply for platform intervention, the visual recognition capability model is used to identify whether there are problems such as damaged packaging or food spillage in the loss voucher. When it is determined that the order has the problem, step 104 is executed. If after identifying the loss voucher, there is no problem such as damaged packaging, food spillage, or wrong delivery, the user's refund application will be rejected, and the reason for the rejection will be prompted to the user. After receiving the rejected refund application, the user can initiate a refund application again and upload loss vouchers such as pictures or videos that can prove the relevant losses, such as damaged or leaked product packaging. Through this mechanism, the platform intervention can make judgments based on the facts of the order problem, and the judgment results will be more objective.

[0060] Step 104, when the identification result is that the package is damaged or the product is leaking, the platform credit judgment process is entered. One implementation method of the process is as follows: Figure 2 shown.

[0061] In the past, after the platform intervened in the accountability process, if the product packaging was damaged or the product leaked, the platform would first determine that it was the rider's responsibility because it could not know the facts. If the rider filed an appeal, the merchant would need to handle the appeal application. If the rider could prove that he was not at fault, the merchant would be held responsible. If both parties had sufficient reasons and reasonable evidence, the platform would be held responsible. The above process is not only complicated, but also takes up a lot of resources. It is also unreasonable to force a single party to be responsible. Therefore, the packaging points accumulated by the merchants on the platform are introduced into the platform credit accountability process of the present invention to make it possible to build accountability and disposal capabilities for multi-party sharing of responsibilities.

[0062] In this embodiment, the service end obtains the packaging score accumulated by the merchant on the platform and determines the relationship between the merchant packaging score and the first threshold. The packaging score accumulated by the merchant on the platform is generated based on the user's rating or star rating of the food packaging in the historical order. For the merchant's historical orders, users will evaluate the product packaging, for example, between 1-5 points or 1 star-5 stars. The packaging score accumulated by the merchant on the platform can be the average of the previous ratings of the product packaging, and the first threshold can be set to 4.8 points, for example.

[0063] With the development of the instant delivery market, merchants can use packaging boxes and bags with better anti-leakage performance. For liquid products such as milk tea and soup, there is still a possibility of leakage during transportation bumps, so merchants need to add packaging materials to prevent liquid products from leaking, such as wrapping plastic film around the parts of liquid products that are prone to leaking. Whether the merchant uses better sealing packaging and performs additional anti-leakage treatment on liquid packaging will become the basis for users to score the packaging of instant delivery products.

[0064] Preferably, in the user interface for order evaluation, the association between the rating level and the packaging problem can be given, and the user can be prompted by a pop-up window when the user clicks the score or star label, without taking up additional space in the evaluation page. For example, 5 points or 5 stars correspond to the merchant using better sealed packaging and additional leakage treatment for liquid packaging, 4 points or 4 stars correspond to the merchant not performing additional leakage treatment for liquid packaging, and 3 points or less can indicate various problems with the packaging material itself, such as poor sealing of the packaging material, easy breakage of the packaging material, etc. Through targeted scoring and star accumulation, the service end can set a more reasonable first threshold in the platform credit judgment process.

[0065] Preferably, in an evaluation system where there is a corresponding relationship between the rating level and the packaging problem, in order to make the packaging score accumulated by the merchant more accurate, for orders with textual evaluations, the textual evaluation content can be analyzed by semantic recognition. If the score corresponding to the packaging problem can be understood from the textual evaluation, and the score is very different from the user's score on the product packaging, the packaging score after semantic understanding is recorded to the server, but the evaluation result presented to the user by the user end is not changed. Through semantic mining, the merchant's historical evaluation can also be processed, so as to correct the merchant's packaging score and make the packaging score as accurate as possible.

[0066] When the service side determines that the packaging score accumulated by the merchant on the platform is lower than the first threshold, it determines that the merchant and the rider are jointly responsible. When the service side determines that the packaging score accumulated by the merchant on the platform is greater than or equal to the first threshold, it determines that the rider is responsible. The rider is the rider who provides delivery services for the order.

[0067] When the merchant's accumulated packaging score on the platform is lower than the first threshold, it means that from the historical orders, the merchant is more likely to have packaging problems. When the goods leak, it is more reasonable to initially determine that the merchant and the rider are jointly responsible. When the merchant's accumulated packaging score on the platform is greater than or equal to the first threshold, it means that the merchant's packaging quality has always been relatively high. When the goods leak, it is more reasonable to initially determine that the rider is responsible.

[0068] In the scenario where the merchant and the rider are initially determined to be jointly responsible, the merchant and the rider can initially bear 50% of the responsibility respectively. The judgment result and the amount of meal loss will be transmitted to the merchant and / or the rider respectively. If the merchant and / or the rider have objections to the judgment result, they can further appeal to the platform by providing proof.

[0069] In other implementations, merchants or riders can choose a liability ratio that they do not agree with when they file a complaint. For example, if the platform determines that the rider is responsible for 50% of the costs, but the merchant believes that the packaging cannot be damaged without being dropped or pressed, and is only willing to bear 20% of the losses, the merchant can file a complaint for the 30% liability that the rider does not agree with and provide proof.

[0070] If during the complaint process, both parties admit fault, or both parties deny fault and both parties cannot prove that they are not at fault, in order to ensure transaction security, both parties can continue to be deemed to be at fault. During the complaint process, the service end can adjust the liability ratio based on the credentials provided by both parties through visual recognition capability models and / or manual methods, and transmit the judgment results and meal loss amount to the merchant end and / or the rider end for display. If both the merchant and the rider can prove that they are not at fault, and the user also provides valid evidence to prove that the food is damaged, the platform will be held responsible.

[0071] In other implementations of the present application, multiple thresholds can be set for the merchant packaging score, thereby forming multiple threshold intervals. Different threshold periods correspond to different responsibility ratios. The lower the merchant packaging score, the greater the responsibility to be borne.

[0072] In this implementation, the packaging scores accumulated by merchants on the platform are introduced during the system's responsibility determination stage. The packaging scores are used to form merchants' assessment of the quality of food packaging. Combined with the large model system's identification of loss vouchers, a comprehensive determination is made as to which one or several entities, the user / merchant / rider / platform, should bear the corresponding responsibility. This solves the technical problem in the prior art of a large number of complaints caused by inaccurate system judgment of unilateral responsibility, improves the rationality of judgment, and reduces service costs.

[0073] In other embodiments of the present application, step 101 further includes the following steps: Figure 3 As shown, the visual recognition capability model is called in advance to determine whether the loss certificate uploaded by the user is valid. When the loss certificate is valid, the refund application is sent to the merchant.

[0074] The judgment conditions for the validity of the loss voucher include: the loss voucher meets the system requirements, and / or the visual recognition capability model can be used to identify damaged packaging and / or spilled food from the loss voucher. For food damage caused by damaged packaging and spilled food, the visual recognition capability model is used to prioritize the identification of loss vouchers such as photos or videos to see if they meet the system requirements for this refund application type, such as whether the food in the order exists in the voucher, and then identify whether there is spilled food in the loss voucher, such as whether the packaging is damaged, whether the food is overflowing, whether it is missing, etc. In the case of wrong shipment or wrong delivery, whether the photos of the wrongly shipped or wrongly delivered orders and the wrongly shipped goods are uploaded in accordance with the system requirements.

[0075] When the loss voucher is invalid, the current refund request is rejected, a prompt is sent to the user end to re-upload a valid loss voucher, and the prompt sent to the user end to re-upload the valid loss voucher is counted. Query and determine whether the number of prompts sent to the user end to re-upload the valid loss voucher has reached a second threshold, when the number of prompts does not reach the second threshold, send a prompt to the user end to re-upload the valid loss voucher, and when the number of prompts reaches the second threshold, send the refund application to the merchant end.

[0076] The purpose of the above prompt is to regulate and guide users to upload loss vouchers. It is appropriate to set the second threshold to a lower value of 1 to 3 times. After the purpose of prompting and regulating user behavior is achieved, even if the system determines that the uploaded voucher is invalid, it will continue to send a refund application to the merchant to proceed with the subsequent steps. At the same time, the above implementation method also adds card control for loss vouchers submitted by users. For example, for refund applications for damage and leakage, invalid vouchers such as non-leaking pictures and online pictures submitted by users are identified and rejected to prevent non-leaking problems from flowing into the downstream judgment link of the system and affecting the judgment results and accuracy.

[0077] In other embodiments of the present application, when determining the relationship between the merchant packaging score and the first threshold in step 104, if Figure 4 The method further comprises the following steps:

[0078] Query and determine the relationship between the number of historical orders of the merchant and the third threshold value. When the merchant's packaging score is lower than the first threshold and the number of historical orders of the merchant is greater than or equal to the third threshold, it is determined that the merchant and the rider are jointly responsible. When the merchant's packaging score is greater than or equal to the first threshold and the number of historical orders of the merchant is greater than or equal to the third threshold, or when the number of historical orders of the merchant is lower than the third threshold, it is determined that the rider is responsible.

[0079] The third threshold is a threshold set for the number of historical orders of the merchant, which can indicate whether the packaging score accumulated by the merchant has a reference value. When the number of historical orders of the merchant is greater than or equal to the third threshold, the packaging score accumulated by the merchant is likely to explain the quality of the merchant's food packaging. Therefore, the packaging score accumulated by the merchant will be considered to determine the liability for meal damage. When the number of historical orders of a merchant is less than the third threshold, such as a newly opened merchant, the number of orders is in the single digits, and the probability that the accumulated packaging score is significantly different from the actual situation is high. Therefore, it can be not used as a reference. The initial judgment is made by the rider, and the merchant's responsibility is further proved through the rider's complaint.

[0080] In other embodiments of the present application, in step 104, the accountability result is sent to the merchant side and / or the rider side, so that the merchant side and / or the rider side display the accountability result to the merchant and / or the rider, and the accountability result at least includes the reason for the accountability, the proportion of meal loss sharing, the amount of meal loss compensation, and a prompt to initiate an appeal. The server receives the response to the accountability result returned by the merchant side and / or the rider side, marks the refund application as approved, performs a refund operation through the original transaction link to which the order belongs, and sends a refund reminder to the user side.

[0081] The response to the judgment result returned by the above-mentioned merchant side and / or rider side can be either a response of acknowledging the judgment result or a response of initiating an appeal against the judgment result. For users, the application to enter the platform credit judgment process has provided a valid loss certificate, or has been determined by the visual recognition model at least once to be damaged, leaked, mis-sent or mis-delivered. Therefore, the service side marks the refund application as approved, performs the refund operation through the original transaction link to which the order belongs, and sends a refund reminder to the user side, so that the user's rights and interests are protected in a timely manner.

[0082] The server receives a complaint application sent by the merchant and / or rider through the merchant side and / or the rider side, and the complaint application carries other credentials, including text, pictures, audio and / or video.

[0083] The complaint application is processed through the accountability system. When the accountability system is able to determine the responsible party, the accountability result is sent to the merchant side and / or the rider side again, so that the merchant side and / or the rider side can show the accountability result to the merchant and / or the rider. The accountability result at least includes the reason for the accountability, the proportion of meal loss sharing, the amount of meal loss compensation, and a prompt to transfer to manual service. When the processing result is that the merchant and / or the rider are not responsible, it is determined that the platform will pay the meal loss compensation for the corresponding part of the responsibility of the merchant and / or the rider. When the accountability system determines that it is unable to determine whether the merchant and / or the rider are responsible, it is transferred to manual service for processing.

[0084] Although this application also includes subsequent processing methods such as online complaints and manual processing, compared with the existing technology that can only determine the responsibility of one party among users / merchants / riders / platforms, this application not only covers the situation where merchants and riders are jointly responsible, but also, for the proportion of responsibility that merchants and / or riders do not agree with, after providing reasonable evidence and reasons, it can also be obtained that the proportion of responsibility that is not agreed with is borne by the user or platform, that is, the processing results also include the situation where users and / or merchants and / or riders and / or platforms are jointly responsible. That is, by introducing the relatively objective data of merchant packaging points, a product solution capability for multiple responsible entities to share responsibilities is established, so that there is a more objective basis for shared responsibility in the instant delivery meal damage judgment scenario. That is, for the existing instant delivery meal damage judgment link that is complex and difficult to judge, the visual recognition capability model is used to avoid non-leakage problems from flowing into the downstream judgment link of the system to affect the accuracy of the judgment results, and by citing the merchant packaging points that can reflect the objective situation, the rights and obligations of each party are clarified, the accuracy of the judgment and the efficiency of the platform processing are improved, and the cost of handling disputes is greatly reduced.

[0085] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0086] The above is a detailed introduction to a method for determining liability for loss of instant delivery goods provided by the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and scope of application. In summary, the content of this specification should not be understood as a limitation on the present application.

[0087] The various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components in the electronic device according to the embodiment of the present application. The present application can also be implemented as a device or apparatus program (e.g., computer program and computer program product) for executing part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0088] For example, Figure 5An electronic device that can implement the method according to the present application is shown. The electronic device can be a PC, a mobile terminal, a personal digital assistant, a tablet computer, etc. The electronic device traditionally includes a processor 510 and a memory 520 and a program code 530 stored on the memory 520 and can be run on the processor 510, and the processor 510 implements the method described in the above embodiment when executing the program code 530. The memory 520 can be a computer program product or a computer-readable medium. The memory 520 can be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk or a ROM. The memory 520 has a storage space 5201 for the program code 530 of the computer program for executing any method step in the above method. For example, the storage space 5201 for the program code 530 can include various computer programs for implementing the various steps in the above method respectively. The program code 530 is a computer-readable code. These computer programs can be read from one or more computer program products or written into the one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks. The computer program includes a computer readable code, and when the computer readable code is executed on an electronic device, the electronic device is caused to execute the method according to the above embodiment.

[0089] The embodiment of the present application also discloses a computer program product, including a computer program, which, when executed by a processor, implements the steps of determining liability for loss of instant delivery goods as described in the first embodiment of the present application.

[0090] Such a computer program product may be a computer-readable storage medium, which may have a computer-readable storage medium having a Figure 5 The memory 520 in the electronic device shown in the figure is similar to the storage segment, storage space, etc. The program code can be compressed and stored in the computer-readable storage medium in an appropriate form. The computer-readable storage medium is generally as shown in the reference Figure 6 The portable or fixed storage unit. Generally, the storage unit includes computer readable code 530', which is a code read by a processor. When the code is executed by the processor, each step in the method described above is implemented.

[0091] The term "one embodiment", "embodiment" or "one or more embodiments" herein means that a particular feature, structure or characteristic described in conjunction with the embodiment is included in at least one embodiment of the present application. In addition, please note that the examples of the term "in one embodiment" here do not necessarily all refer to the same embodiment.

[0092] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0093] In the claims, any reference signs placed between brackets shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present application may be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for determining liability for loss of instant delivery goods, the method being applied to a service end, characterized in that: include: Receiving a refund application for an order after delivery fulfillment sent by a user, wherein the refund application carries a loss certificate; Determine whether the loss voucher is valid through a visual recognition capability model. If the loss voucher is invalid, reject the current refund request and send a prompt to the user to re-upload a valid loss voucher; When the loss certificate is valid, the refund application is sent to the merchant, and the merchant is waiting for the merchant to review the refund application. The merchant is the merchant that provides the commodity service for the order; When receiving the review result of the merchant side that the refund application is not supported and the user applies for the platform to intervene in the processing, the visual recognition capability model is used to identify whether there is packaging damage and / or product leakage in the loss voucher; If the identification result shows that the order does not have the above-mentioned problem, the refund application will be rejected. If the order has the above-mentioned problem, the liability judgment system will determine whether the merchant and / or rider shall bear the responsibility.

2. The method according to claim 1, characterized in that: When the order has the problem, the liability judgment system determines whether the merchant and / or rider shall bear the responsibility, including: The liability judgment system obtains the packaging score accumulated by the merchant on the platform, and judges the relationship between the merchant packaging score and the first threshold; When the merchant's packaging score is lower than a first threshold, it is determined that the merchant and the rider are jointly responsible. When the merchant's packaging score is greater than or equal to the first threshold, it is determined that the rider is responsible. The rider is the rider who provides delivery services for the order.

3. The method according to claim 1 or 2, characterized in that: Counting the prompts sent to the user terminal to re-upload the valid loss voucher; After determining that the loss voucher is invalid and before rejecting the current refund request, the method further includes: Query and determine whether the number of prompts sent to the user end to re-upload the valid loss voucher has reached a second threshold. When the number of prompts does not reach the second threshold, send a prompt to the user end to re-upload the valid loss voucher. When the number of prompts reaches the second threshold, send the refund application to the merchant end.

4. The method according to claim 1 or 2, characterized in that: The conditions for judging whether the loss voucher is valid include: the loss voucher meets the system requirements, or the visual recognition capability model can be used to identify package damage and / or product leakage from the loss voucher.

5. The method according to claim 2, characterized in that: The packaging points accumulated by the merchants on the platform are generated based on the ratings or star ratings of food packaging by users in historical orders.

6. The method according to claim 5, characterized in that The determining the relationship between the merchant packaging score and the first threshold further includes: Query and determine the relationship between the number of historical orders of the merchant and a third threshold; When the merchant's packaging score is lower than a first threshold and the merchant's historical order quantity is greater than or equal to a third threshold, it is determined that the merchant and the rider are jointly responsible; When the merchant's packaging score is greater than or equal to a first threshold and the merchant's historical order quantity is greater than or equal to a third threshold, or when the merchant's historical order quantity is lower than the third threshold, it is determined that the rider is responsible.

7. The method according to any one of claims 1 to 6, characterized in that: After the service end completes the meal damage determination, the method further includes: Send the judgment result to the merchant end and / or the rider end, so that the merchant end and / or the rider end display the judgment result to the merchant and / or the rider, and the judgment result at least includes the reason for the judgment, the proportion of meal loss sharing, the amount of meal loss compensation, and a prompt for filing a complaint; Receive a response to the judgment result returned by the merchant side and / or the rider side, mark the refund application as approved, perform a refund operation through the original transaction link to which the order belongs, and send a refund reminder to the user side.

8. The method according to claim 7, characterized in that Receive a complaint application sent by the merchant and / or rider through the merchant terminal and / or the rider terminal, where the complaint application carries other credentials, including text, pictures, audio and / or video; The complaint application is processed through the accountability system. When the accountability system is able to determine the responsible party, the accountability result is sent to the merchant end and / or the rider end again, so that the merchant end and / or the rider end can show the accountability result to the merchant and / or the rider. The accountability result at least includes the reason for the accountability, the proportion of meal loss sharing, the amount of meal loss compensation, and a prompt for transferring to manual service; When the processing result is that the merchant and / or the rider are not responsible, it is determined that the platform shall compensate for the meal loss of the corresponding liability portion of the merchant and / or the rider; When the accountability system determines that the matter cannot be handled, it is transferred to manual service for processing.

9. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of determining liability for loss of instant delivery goods as described in any one of items 1 to 8.

10. A computer program product, comprising a computer program, characterized in that When the program is executed by a processor, the steps of determining liability for loss of instant delivery goods as described in any one of claims 1 to 8 are implemented.

Images