Method and device for automatically executing order processing, equipment and medium

Abstract

The invention provides a method, device and equipment for automatically executing order processing and a medium, the method is applied to the field of data processing, and the method comprises the following steps: obtaining real-time parameters of a rider and order parameters associated with a current order; based on the real-time parameters and / or order parameters of the rider, whether a first preset condition is met or not is judged in real time; when the first preset condition is met, first voice reminding for the rider is automatically triggered; performing intention recognition on the first voice instruction responded by the rider; and determining whether to automatically execute the target processing action based on the intention recognition result. According to the method, when the execution condition meeting the order processing action is detected, the voice prompt is automatically triggered, and the order processing action is automatically executed for the rider based on the voice instruction replied by the rider, so that the order processing process is more intelligent, the frequency of manual operation of the rider in the order processing process is reduced, and the user experience is improved. And the distribution experience of the rider is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing, and more particularly, to a method, apparatus, device, and medium for automatically executing order processing in the field of data processing. Background Art

[0002] Currently, in the field of business processing, the execution process of event operations of related businesses lacks perception and analysis of actual scenarios, that is, whether event operations need to be executed depends entirely on the user's manual judgment.

[0003] For example, taking the takeaway delivery business as an example, when the rider is delivering takeaways, the delivery process is roughly divided into the following stages: receiving the order → arriving at the store → picking up the food → delivering → delivering. The processing procedures related to the above-mentioned stages of the delivery process often require manual operation by the rider. For example, taking the processing procedure of the arrival at the store stage as an example, in the current related technologies, after the rider arrives at the merchant, the rider clicks the "Confirm Arrival at the Store" control in the takeaway delivery application (Application, App) interface to complete the processing action of reporting the arrival at the store.

[0004] During the process of the rider performing the above-mentioned reporting to the store, if it is inconvenient for the rider to operate, the above-mentioned manual clicking operation will increase the rider's operating difficulty and reduce the rider's delivery experience. Summary of the Invention

[0005] The present application provides a method, apparatus, device and medium for automatically executing order processing. The method can automatically trigger a voice reminder when it detects that the execution conditions of the order processing action are met during the rider's order processing process, and automatically execute the order processing action for the rider based on the voice instructions replied by the rider, thereby making the order processing process more intelligent, reducing the frequency of manual operations of the rider during the order processing process, and improving the rider's delivery experience.

[0006] In a first aspect, a method for automatically executing order processing is provided, which is applied to a server, and the method includes: obtaining the real-time parameters of the rider and the order parameters associated with the current order; based on the real-time parameters of the rider and / or the order parameters, determining in real time whether a first preset condition is met; when the first preset condition is met, automatically triggering a first voice reminder to the rider, and the first voice reminder is used to remind whether to execute the target processing action associated with the current order; performing intent recognition on the first voice instruction of the rider in response to the first voice reminder; and determining whether to automatically execute the target processing action based on the intention recognition result.

[0007] In the above technical solution, a method for automatically executing order processing is provided during the process of the rider processing the order. The specific implementation process is: the server can determine whether the real-time parameters of the rider and the order parameters associated with the current order meet the first preset conditions. When the first preset condition is met, the rider is given a first voice reminder. The above process can match the conditions in real time during the rider's delivery process, and actively remind the rider, reducing the intervention of manual judgment. When the conditions are met, the first voice reminder is triggered, and the rider's reply instruction is recognized for its intention, which can take into account the rider's subjective wishes in the automatic processing process, improve the accuracy of automatic execution and the rider's satisfaction. The above-mentioned method of automatically executing target processing actions can replace the rider's manual execution operations, simplify the rider's operating procedures, thereby reducing the complexity of operations, and improve the order processing efficiency when the rider is not convenient to click, thereby improving the rider's delivery experience.

[0008] In combination with the first aspect, in some possible implementations, the target processing action includes reporting to the store, the rider's real-time parameters include the rider's location, the order parameters include the merchant's location and the target order status, and when the target order status is in the grabbed order status and meets at least one of the following items, it is judged that the first preset condition is met: the rider's location is within the coverage area of ​​the first signal associated with the merchant's location; the rider's location is within the first preset range associated with the merchant's location; the distance between the rider's location and the merchant's location is less than or equal to the first preset distance.

[0009] In the above technical solution, when judging whether the rider has arrived at the merchant, a comprehensive judgment is made through multiple conditions, which can accurately determine from multiple dimensions whether to report the rider to the store. This improves the accuracy of the judgment and timing of the reminder to report to the store, making the execution process of reporting to the store more precise.

[0010] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the target processing action includes reporting the meal pickup, the real-time parameters of the rider include the rider's arrival time at the store and the rider's location, and the order parameters include the merchant's meal delivery status, the merchant's location, and the target order status. When the target order status is the arrived at the store status and meets at least one of the following items, it is judged that the first preset condition is met: the rider's arrival time at the store is greater than or equal to the first preset time; the merchant's meal delivery status is the delivered status; the rider's location arrives at the merchant's location and then moves away from the merchant's location and the merchant's meal delivery status is the delivered status.

[0011] In the above technical solution, after the order is reported to the store, during the rider's meal pickup process, the need for a store report is automatically determined based on the rider's arrival time, the merchant's meal delivery status, and the rider's and merchant's locations. This multi-dimensional parameter combination not only improves the accuracy of store report reminders, but also reduces the tediousness of manual operations and the probability of forgetting to report to the store through automated triggering of reminders, thus avoiding delays in the order delivery process and improving the rider's delivery efficiency.

[0012] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the target processing action includes reporting delivery, the real-time parameters of the rider include the rider's location, the order parameters include the user location to be delivered and the target order status, and when the target order status is the food has been picked up status and meets at least one of the following items, it is judged that the first preset condition is met: the rider's location is within the coverage area of ​​the second signal associated with the user's location; the rider's location is within the second preset range associated with the user's location; the distance between the rider's position and the user's location is less than or equal to the second preset distance.

[0013] In the above technical solution, when judging whether the rider has arrived at the user, a comprehensive judgment is made through multiple conditions, which can accurately determine from multiple dimensions whether to report and remind the rider, thereby improving the accuracy of the judgment and timing of the reporting and delivery reminder, making the execution process of reporting and delivery more precise.

[0014] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the intention recognition of the first voice instruction of the rider in response to the first voice reminder includes: performing intention recognition on the first voice instruction based on the LLM model; when the intention recognition is successful, obtaining the intention recognition result; and determining whether to automatically execute the target processing action based on the intention recognition result includes: when the intention recognition result is to automatically execute the target processing action, sending a target processing instruction to the user terminal so that the user terminal executes the target processing action, and the target processing instruction includes the execution steps of the target processing action.

[0015] In the above technical solution, after receiving the first voice command, the server can accurately identify the rider's current intention by performing intent recognition on the first voice command. When the rider confirms to automatically execute the target processing action, the server sends the target processing instruction to the user terminal, causing the user terminal to automatically execute the target processing action, reducing human intervention and alleviating the rider's workload. It also provides a flexible way for the rider to execute the target processing action when it is inconvenient for the rider to operate.

[0016] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the determination of whether to automatically execute the target processing action based on the intention recognition result includes: when the intention recognition result is not to automatically execute the target processing action, automatically triggering a second voice reminder to the rider again within a second preset time period, and the second voice reminder is used to remind whether to execute the target processing action.

[0017] In the above technical solution, when the rider determines not to automatically execute the target processing action, in order to avoid delays in the execution of the target processing action, the server can remind the rider again after a period of time to avoid order timeouts caused by the rider forgetting to execute.

[0018] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, when the first voice instruction is not detected or the intention recognition of the first voice instruction fails, the method also includes: obtaining the waiting execution time corresponding to the target processing action; when the waiting execution time is greater than or equal to the third preset time, automatically triggering a third voice reminder to the rider, and the third voice reminder is used to remind whether to execute the target processing action; obtaining the second voice instruction of the rider in response to the third voice reminder, and determining whether to automatically execute the target processing action in response to the second voice instruction.

[0019] In the above technical solution, if the rider does not respond or the intent recognition fails, the server can determine whether the execution process of the current target processing action has timed out based on the waiting time for the target processing action. If the timeout is about to occur, the rider will be proactively reminded, reducing the psychological burden caused by the timeout.

[0020] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the target processing action includes reporting to the store and / or reporting to pick up the meal. When the first voice instruction is not detected or the first voice instruction intention recognition fails, the method also includes: obtaining the rider location, the merchant location and the user location to be delivered; when the distance between the rider location and the merchant location is greater than or equal to the third preset distance, and the distance between the rider location and the user location is less than or equal to the fourth preset distance, automatically triggering a fourth voice reminder for the rider, and the fourth voice reminder is used to remind whether to execute the report to the store and / or report to pick up the meal; obtaining the third voice instruction of the rider in response to the fourth voice reminder, and in response to the third voice instruction, determining whether to automatically execute the report to the store and / or the report to pick up the meal.

[0021] In the above technical solution, when the target processing action is at least one of reporting to the store and reporting to pick up the food, when the rider does not respond or the intention recognition fails, if the server determines through distance detection that the rider is on the way to deliver the food, it can intelligently remind the rider to report to the store and / or report to pick up the food in time, thereby reducing the serious order timeout problem caused by process omissions.

[0022] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the target processing action includes reporting and delivery. When the first voice instruction is not detected or the intention recognition of the first voice instruction fails, the method also includes: obtaining the rider's location and the user's location to be delivered; when the rider's location reaches the user's location and then moves away from the user's location, automatically triggering a fifth voice reminder for the rider, and the fifth voice reminder is used to remind the rider whether to execute the reporting and delivery; obtaining the fourth voice instruction of the rider in response to the fifth voice reminder, and determining whether to automatically execute the reporting and delivery in response to the fourth voice instruction.

[0023] In the above technical solution, if the rider has not confirmed delivery, the server can automatically perform location matching. If the location matching result shows that the rider has arrived at the user's location and then moved away, it means that the rider has completed the delivery. The server can remind the rider to report delivery in time and update the order status in a timely manner to avoid order timeouts.

[0024] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the order parameters also include the user's remarks on the current order, and the method also includes: when the remarks information of the current order indicates that the rider is prohibited from contacting the user by phone, automatically triggering a sixth voice reminder for the rider, and the sixth voice reminder is used to remind the rider that the rider is prohibited from contacting by phone, and / or, the sixth voice reminder is used to remind the rider to place the goods of the current order at the target location; when there is no instruction for the rider in the remarks information of the current order, automatically triggering a seventh voice reminder for the rider, and the seventh voice reminder is used to remind the rider to contact the user by phone.

[0025] In the above technical solution, during the order processing process, voice reminders are used to enable the rider to deliver food according to the user's notes, which can avoid user complaints caused by the rider's failure to check the notes in time, reduce the platform's customer complaint handling costs, and improve user delivery satisfaction.

[0026] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, when the number of the current orders is multiple, after determining whether to automatically execute the target processing action based on the intention recognition result, the method also includes: performing an eighth voice reminder to the rider, and the eighth voice reminder is used to inquire about the target order that the rider currently needs to process; obtaining the fifth voice instruction of the rider in response to the eighth voice reminder, and in response to the fifth voice instruction, determining whether to automatically execute the target processing action of the target order according to the intention recognition result.

[0027] In the above technical solution, when the rider currently has multiple orders to process, after intention recognition, the server can further inquire about the target orders currently to be processed by the rider, avoiding operational errors caused by misselected orders. The rider does not need to manually check the order list for confirmation, which simplifies the order processing process and reduces the complexity of the rider's operations.

[0028] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, when the first preset condition is met, the method also includes: sending a display instruction of a target pop-up window to the user terminal, so that the user terminal displays the target pop-up window, and the target pop-up window includes an execution control of the target processing action, and the execution control is used to enable the rider to click to manually execute the target processing action.

[0029] In addition to the automatic execution of the target processing action in the above technical solution, this application also provides a manual execution method for the target processing action. After the server triggers the first voice reminder, a pop-up window containing the execution control of the target processing action can also be synchronously displayed, so that the rider can continue to complete the target processing action manually if the automatic execution is unsuccessful, thereby improving the flexibility of the execution of the target processing action.

[0030] On the second aspect, a method for automatically executing order processing is provided, which is applied to a user end, and the method includes: obtaining the real-time parameters of the rider; sending the real-time parameters of the rider and the order parameters to the server, so that the server determines in real time whether a first preset condition is met based on the real-time parameters of the rider and / or the order parameters associated with the current order; receiving a first voice reminder sent by the server and broadcasting it, the first voice reminder is automatically triggered by the server when the first preset condition is met, and the first voice reminder is used to remind whether to execute the target processing action associated with the current order; obtaining the first voice instruction of the rider in response to the first voice reminder and sending it to the server, so that the server recognizes the intention of the first voice instruction, and determines whether to automatically execute the target processing action based on the intention recognition result.

[0031] In combination with the second aspect, in some possible implementations, the target processing action includes reporting to the store, the rider's real-time parameters include the rider's location, the order parameters include the merchant's location and the target order status, and when the target order status is in the grabbed order status and meets at least one of the following items, it is judged that the first preset condition is met: the rider's location is within the coverage area of ​​the first signal associated with the merchant's location; the rider's location is within the first preset range associated with the merchant's location; the distance between the rider's location and the merchant's location is less than or equal to the first preset distance.

[0032] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the target processing action includes reporting the meal pickup, the real-time parameters of the rider include the rider's arrival time at the store and the rider's location, and the order parameters include the merchant's meal delivery status, the merchant's location, and the target order status. When the target order status is the arrived at the store status and meets at least one of the following items, it is judged that the first preset condition is met: the rider's arrival time at the store is greater than or equal to the first preset time; the merchant's meal delivery status is the delivered status; the rider's location arrives at the merchant's location and then moves away from the merchant's location and the merchant's meal delivery status is the delivered status.

[0033] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the target processing action includes reporting delivery, the real-time parameters of the rider include the rider's location, the order parameters include the user location to be delivered and the target order status, and when the target order status is the food has been picked up status and meets at least one of the following items, it is judged that the first preset condition is met: the rider's location is within the coverage area of ​​the second signal associated with the user's location; the rider's location is within the second preset range associated with the user's location; the distance between the rider's position and the user's location is less than or equal to the second preset distance.

[0034] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the intention recognition result is obtained when the server successfully recognizes the intention of the first voice instruction based on the LLM model; and the method also includes: receiving a target processing instruction sent by the server, the target processing instruction is triggered by the server when the intention recognition result is to automatically execute the target processing action, and the target processing instruction includes the execution steps of the target processing action; in response to the target processing instruction, executing the target processing action.

[0035] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the method also includes: receiving and broadcasting a second voice reminder sent by the server, the second voice reminder being triggered again by the server at a second preset time length when the intention recognition result is not to automatically execute the target processing action, and the second voice reminder is used to remind whether to execute the target processing action.

[0036] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, when the first voice instruction is not detected or the first voice instruction intention recognition fails, the method also includes: receiving a third voice reminder sent by the server and broadcasting it, the third voice reminder is automatically triggered by the server when the waiting execution time of the target processing action is greater than or equal to the third preset time length, and the third voice reminder is used to remind whether to execute the target processing action; obtaining the second voice instruction of the rider in response to the third voice reminder and sending it to the server, so that the server responds to the second voice instruction and determines whether to automatically execute the target processing action.

[0037] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the target processing action includes reporting to the store and / or reporting to pick up the meal. When the first voice instruction is not detected or the first voice instruction intention recognition fails, the method also includes: obtaining the rider's location; sending the rider's location to the server; receiving a fourth voice reminder sent by the server and broadcasting it, the fourth voice reminder being automatically triggered by the server when the distance between the rider's location and the merchant's location is greater than or equal to a third preset distance, and the distance between the rider's location and the user's location to be delivered is less than or equal to the fourth preset distance, the fourth voice reminder being used to remind whether to execute the reporting to the store and / or reporting to pick up the meal; obtaining the third voice instruction of the rider in response to the fourth voice reminder and sending it to the server, so that the server responds to the third voice instruction and determines whether to automatically execute the reporting to the store and / or the reporting to pick up the meal.

[0038] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the target processing action includes reporting and delivery. When the first voice instruction is not detected or the first voice instruction intention recognition fails, the method also includes: obtaining the rider's position; sending the rider's position to the server; receiving the fifth voice reminder sent by the server and broadcasting it. The fifth voice reminder is automatically triggered by the server when the rider's position reaches the user location to be delivered and then moves away from the user location. The fifth voice reminder is used to remind whether to execute the reporting and delivery; obtaining the fourth voice instruction of the rider in response to the fifth voice reminder and sending it to the server, so that the server responds to the fourth voice instruction and determines whether to automatically execute the reporting and delivery.

[0039] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the order parameters also include the user's remarks on the current order, and the method also includes: receiving and broadcasting a sixth voice reminder sent by the server, the sixth voice reminder being automatically triggered when the server indicates in the remarks information of the current order that the rider is prohibited from contacting the user by phone, the sixth voice reminder being used to remind the rider that the rider is prohibited from contacting by phone, and / or the sixth voice reminder being used to remind the rider to place the goods of the current order at the target location; receiving and broadcasting a seventh voice reminder sent by the server, the seventh voice reminder being automatically triggered when the server has no instructions for the rider in the remarks information of the current order, the seventh voice reminder being used to remind the rider to contact the user by phone.

[0040] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, when the number of the current orders is multiple, the method also includes: receiving and broadcasting the eighth voice reminder sent by the server, and the eighth voice reminder is used to inquire about the target order that the rider currently needs to process; obtaining the fifth voice instruction of the rider in response to the eighth voice reminder and sending it to the server, so that the server responds to the fifth voice instruction and determines whether to automatically execute the target processing action of the target order based on the intention recognition result.

[0041] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the method also includes: receiving a display instruction of a target pop-up window sent by the server, the target pop-up window including an execution control of the target processing action, the execution control being used to enable the rider to click to manually execute the target processing action; and displaying the target pop-up window in response to the display instruction of the target pop-up window.

[0042] For the corresponding beneficial effects of the method in the above-mentioned second aspect or any possible implementation of the second aspect, please refer to the beneficial effects of the method in the above-mentioned first aspect or any possible implementation of the first aspect, and no further details will be given here.

[0043] According to a third aspect, a device for automatically executing order processing is provided, which is applied to a server and includes: an acquisition module for acquiring the real-time parameters of the rider and the order parameters associated with the current order; a processing module for determining in real time whether a first preset condition is met based on the real-time parameters of the rider and / or the order parameters; the processing module is also used to automatically trigger a first voice reminder to the rider when the first preset condition is met, and the first voice reminder is used to remind whether to execute a target processing action associated with the current order; the processing module is also used to perform intent recognition on the first voice instruction of the rider in response to the first voice reminder; the processing module is also used to determine whether to automatically execute the target processing action based on the intention recognition result.

[0044] In combination with the third aspect, in some possible implementations, the target processing action includes reporting to the store, the rider's real-time parameters include the rider's location, the order parameters include the merchant's location and the target order status, and when the target order status is the order-grabbed status and meets at least one of the following items, it is judged that the first preset condition is met: the rider's location is within the coverage area of ​​the first signal associated with the merchant's location; the rider's location is within the first preset range associated with the merchant's location; the distance between the rider's location and the merchant's location is less than or equal to the first preset distance.

[0045] In combination with the third aspect and the above-mentioned implementation methods, in some possible implementation methods, the target processing action includes reporting the meal pickup, the real-time parameters of the rider include the rider's arrival time at the store and the rider's location, and the order parameters include the merchant's meal delivery status, the merchant's location, and the target order status. When the target order status is the arrived at the store status and meets at least one of the following items, it is judged that the first preset condition is met: the rider's arrival time at the store is greater than or equal to the first preset time; the merchant's meal delivery status is the delivered status; the rider's location arrives at the merchant's location and then moves away from the merchant's location and the merchant's meal delivery status is the delivered status.

[0046] In combination with the third aspect and the above-mentioned implementation methods, in some possible implementation methods, the target processing action includes reporting delivery, the real-time parameters of the rider include the rider's location, the order parameters include the user location to be delivered and the target order status. When the target order status is the food has been picked up status and at least one of the following items is met, it is judged that the first preset condition is met: the rider's location is within the coverage area of ​​the second signal associated with the user's location; the rider's location is within the second preset range associated with the user's location; the distance between the rider's position and the user's location is less than or equal to the second preset distance.

[0047] In combination with the third aspect and the above-mentioned implementation methods, in some possible implementation methods, the processing module is specifically used to: perform intent recognition on the first voice instruction based on the LLM model; when the intent recognition is successful, obtain the intent recognition result; and when the intent recognition result is to automatically execute the target processing action, send a target processing instruction to the user terminal so that the user terminal executes the target processing action, and the target processing instruction includes the execution steps of the target processing action.

[0048] In combination with the third aspect and the above-mentioned implementation methods, in some possible implementation methods, the processing module is also used to: when the intention recognition result is not to automatically execute the target processing action, automatically trigger a second voice reminder to the rider again within a second preset time period, and the second voice reminder is used to remind whether to execute the target processing action.

[0049] In combination with the third aspect and the above-mentioned implementation methods, in some possible implementation methods, when the first voice instruction is not detected or the intention recognition of the first voice instruction fails, the processing module is also used to: obtain the waiting execution time corresponding to the target processing action; when the waiting execution time is greater than or equal to the third preset time, automatically trigger a third voice reminder to the rider, and the third voice reminder is used to remind whether to execute the target processing action; obtain the second voice instruction of the rider in response to the third voice reminder, and determine whether to automatically execute the target processing action in response to the second voice instruction.

[0050] In combination with the third aspect and the above-mentioned implementation methods, in some possible implementation methods, the target processing action includes reporting to the store and / or reporting to pick up the meal. When the first voice instruction is not detected or the first voice instruction intention recognition fails, the processing module is also used to: obtain the rider location, the merchant location and the user location to be delivered; when the distance between the rider location and the merchant location is greater than or equal to the third preset distance, and the distance between the rider location and the user location is less than or equal to the fourth preset distance, automatically trigger a fourth voice reminder for the rider, and the fourth voice reminder is used to remind whether to execute the report to the store and / or report to pick up the meal; obtain the third voice instruction of the rider in response to the fourth voice reminder, and in response to the third voice instruction, determine whether to automatically execute the report to the store and / or the report to pick up the meal.

[0051] In combination with the third aspect and the above-mentioned implementation methods, in some possible implementation methods, the target processing action includes reporting and delivery. When the first voice instruction is not detected or the intention recognition of the first voice instruction fails, the processing module is also used to: obtain the rider's location and the user's location to be delivered; when the rider's location reaches the user's location and then moves away from the user's location, automatically trigger a fifth voice reminder for the rider, and the fifth voice reminder is used to remind whether to execute the reporting and delivery; obtain the fourth voice instruction of the rider in response to the fifth voice reminder, and determine whether to automatically execute the reporting and delivery in response to the fourth voice instruction.

[0052] In combination with the third aspect and the above-mentioned implementation methods, in some possible implementation methods, the order parameters also include the user's remarks on the current order, and the processing module is also used to: when the remarks information of the current order indicates that the rider is prohibited from contacting the user by phone, automatically triggering a sixth voice reminder for the rider, and the sixth voice reminder is used to remind the rider that the rider is prohibited from contacting by phone, and / or, the sixth voice reminder is used to remind the rider to place the goods of the current order at the target location; when there is no instruction for the rider in the remarks information of the current order, automatically triggering a seventh voice reminder for the rider, and the seventh voice reminder is used to remind the rider to contact the user by phone.

[0053] In combination with the third aspect and the above-mentioned implementation methods, in some possible implementation methods, when the number of the current orders is multiple, after determining whether to automatically execute the target processing action based on the intention recognition result, the processing module is also used to: perform an eighth voice reminder on the rider, and the eighth voice reminder is used to inquire about the target order that the rider currently needs to process; obtain the fifth voice instruction of the rider in response to the eighth voice reminder, and in response to the fifth voice instruction, determine whether to automatically execute the target processing action of the target order according to the intention recognition result.

[0054] In combination with the third aspect and the above-mentioned implementation methods, in some possible implementation methods, when the first preset condition is met, the processing module is also used to: send a display instruction of the target pop-up window to the user terminal, so that the user terminal displays the target pop-up window, and the target pop-up window includes an execution control of the target processing action, and the execution control is used to enable the rider to click to manually execute the target processing action.

[0055] In a fourth aspect, a device for automatically executing order processing is provided, which is applied to a user end and includes: an acquisition module for acquiring the real-time parameters of the rider; a sending module for sending the real-time parameters of the rider to the server, so that the server can determine in real time whether a first preset condition is met based on the real-time parameters of the rider and / or the order parameters associated with the current order; a receiving module for receiving and broadcasting a first voice reminder sent by the server, wherein the first voice reminder is automatically triggered by the server when the first preset condition is met, and the first voice reminder is used to remind whether to execute the target processing action associated with the current order; the acquisition module is also used to acquire the first voice instruction of the rider in response to the first voice reminder and send it to the server, so that the server can perform intent recognition on the first voice instruction, and determine whether to automatically execute the target processing action based on the intention recognition result.

[0056] In combination with the fourth aspect, in some possible implementations, the target processing action includes reporting to the store, the rider's real-time parameters include the rider's location, the order parameters include the merchant's location and the target order status, and when the target order status is in the grabbed order status and meets at least one of the following items, it is judged that the first preset condition is met: the rider's location is within the coverage area of ​​the first signal associated with the merchant's location; the rider's location is within the first preset range associated with the merchant's location; the distance between the rider's location and the merchant's location is less than or equal to the first preset distance.

[0057] In combination with the fourth aspect and the above-mentioned implementation methods, in some possible implementation methods, the target processing action includes reporting the meal pickup, the real-time parameters of the rider include the rider's arrival time at the store and the rider's location, and the order parameters include the merchant's meal delivery status, the merchant's location, and the target order status. When the target order status is the arrived at the store status and meets at least one of the following items, it is judged that the first preset condition is met: the rider's arrival time at the store is greater than or equal to the first preset time; the merchant's meal delivery status is the delivered status; the rider's location arrives at the merchant's location and then moves away from the merchant's location and the merchant's meal delivery status is the delivered status.

[0058] In combination with the fourth aspect and the above-mentioned implementation methods, in some possible implementation methods, the target processing action includes reporting delivery, the real-time parameters of the rider include the rider's location, the order parameters include the user location to be delivered and the target order status. When the target order status is the food has been picked up status and meets at least one of the following items, it is judged that the first preset condition is met: the rider's location is within the coverage area of ​​the second signal associated with the user's location; the rider's location is within the second preset range associated with the user's location; the distance between the rider's position and the user's location is less than or equal to the second preset distance.

[0059] In combination with the fourth aspect and the above-mentioned implementation methods, in some possible implementation methods, the intention recognition result is obtained when the server successfully recognizes the intention of the first voice instruction based on the LLM model; and the receiving module is also used to: receive a target processing instruction sent by the server, which is triggered by the server when the intention recognition result is to automatically execute the target processing action, and the target processing instruction includes the execution steps of the target processing action; and execute the target processing action in response to the target processing instruction.

[0060] In combination with the fourth aspect and the above-mentioned implementation methods, in some possible implementation methods, the receiving module is also used to: receive and broadcast a second voice reminder sent by the server, and the second voice reminder is triggered again by the server at a second preset time when the intention recognition result is not to automatically execute the target processing action. The second voice reminder is used to remind whether to execute the target processing action.

[0061] In combination with the fourth aspect and the above-mentioned implementation methods, in some possible implementation methods, when the first voice instruction is not detected or the first voice instruction intention recognition fails, the receiving module is also used to: receive and broadcast a third voice reminder sent by the server, and the third voice reminder is automatically triggered by the server when the waiting execution time of the target processing action is greater than or equal to the third preset time length. The third voice reminder is used to remind whether to execute the target processing action; the acquisition module is also used to: obtain the second voice instruction of the rider in response to the third voice reminder and send it to the server, so that the server responds to the second voice instruction and determines whether to automatically execute the target processing action.

[0062] In combination with the fourth aspect and the above-mentioned implementation methods, in some possible implementation methods, the target processing action includes reporting to the store and / or reporting to pick up the meal. When the first voice instruction is not detected or the first voice instruction intention recognition fails, the acquisition module is also used to: obtain the rider's location; the sending module is also used to: send the rider's location to the server; the receiving module is also used to: receive a fourth voice reminder sent by the server and broadcast it. The fourth voice reminder is automatically triggered by the server when the distance between the rider's location and the merchant's location is greater than or equal to a third preset distance, and the distance between the rider's location and the user's location to be delivered is less than or equal to the fourth preset distance. The fourth voice reminder is used to remind whether to execute the reporting to the store and / or reporting to pick up the meal; the acquisition module is also used to: obtain the third voice instruction of the rider in response to the fourth voice reminder and send it to the server, so that the server responds to the third voice instruction and determines whether to automatically execute the reporting to the store and / or the reporting to pick up the meal.

[0063] In combination with the fourth aspect and the above-mentioned implementation methods, in some possible implementation methods, the target processing action includes reporting and delivery. When the first voice instruction is not detected or the intention recognition of the first voice instruction fails, the acquisition module is also used to: obtain the rider's position; the sending module is also used to: send the rider's position to the server; the receiving module is also used to: receive the fifth voice reminder sent by the server and broadcast it. The fifth voice reminder is automatically triggered by the server when the rider's position reaches the user location to be delivered and then moves away from the user location. The fifth voice reminder is used to remind whether to execute the reporting and delivery; the acquisition module is also used to: obtain the fourth voice instruction of the rider in response to the fifth voice reminder and send it to the server, so that the server responds to the fourth voice instruction and determines whether to automatically execute the reporting and delivery.

[0064] In combination with the fourth aspect and the above-mentioned implementation methods, in some possible implementation methods, the order parameters also include the user's remarks on the current order, and the receiving module is further used to: receive and broadcast the sixth voice reminder sent by the server, the sixth voice reminder is automatically triggered when the server indicates in the remarks information of the current order that the rider is prohibited from contacting the user by phone, and the sixth voice reminder is used to remind the rider that the rider is prohibited from contacting by phone, and / or, the sixth voice reminder is used to remind the rider to place the goods of the current order at the target location; receive and broadcast the seventh voice reminder sent by the server, the seventh voice reminder is automatically triggered when the server has no instructions for the rider in the remarks information of the current order, and the seventh voice reminder is used to remind the rider to contact the user by phone.

[0065] In combination with the fourth aspect and the above-mentioned implementation methods, in some possible implementation methods, when the number of the current orders is multiple, the receiving module is also used to: receive the eighth voice reminder sent by the server and broadcast it, and the eighth voice reminder is used to inquire about the target order that the rider currently needs to process; the acquisition module is also used to: obtain the fifth voice instruction of the rider in response to the eighth voice reminder and send it to the server, so that the server responds to the fifth voice instruction and determines whether to automatically execute the target processing action of the target order based on the intention recognition result.

[0066] In combination with the fourth aspect and the above-mentioned implementation methods, in some possible implementation methods, the receiving module is also used to: receive a display instruction of a target pop-up window sent by the server, the target pop-up window including an execution control of the target processing action, the execution control being used to enable the rider to click to manually execute the target processing action; and display the target pop-up window in response to the display instruction of the target pop-up window.

[0067] In a fifth aspect, an electronic device is provided, comprising a memory and a processor. The memory is configured to store executable program code, and the processor is configured to call and run the executable program code from the memory, so that the electronic device executes the method of the first aspect or any possible implementation of the first aspect.

[0068] In a sixth aspect, an electronic device is provided, comprising a memory and a processor. The memory is configured to store executable program code, and the processor is configured to call and run the executable program code from the memory, so that the electronic device executes the method of the second aspect or any possible implementation of the second aspect.

[0069] In the seventh aspect, a computer program product is provided, which includes: computer program code, which, when running on a computer, enables the computer to execute the method in the above-mentioned first aspect or any possible implementation of the first aspect, or to execute the method in the above-mentioned second aspect or any possible implementation of the second aspect.

[0070] In an eighth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation of the first aspect, or executes the method in the above-mentioned second aspect or any possible implementation of the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 This is a schematic diagram of a graphical user interface (GUI) for manually grabbing an order provided in an embodiment of the present application;

[0072] Figure 2 This is a GUI diagram for manually reporting to a store provided in an embodiment of the present application;

[0073] Figure 3 This is a schematic diagram of a GUI for waking up an artificial intelligence assistant through voice, provided in an embodiment of the present application;

[0074] Figure 4 This is a schematic diagram of a GUI for going online via voice provided in an embodiment of the present application;

[0075] Figure 5 This is a schematic diagram of a GUI for grabbing orders and planning meal pickup routes by voice, provided in an embodiment of the present application;

[0076] Figure 6 This is a schematic diagram of a GUI for reporting to a store via voice provided in an embodiment of the present application;

[0077] Figure 7 This is a schematic diagram of a GUI for reporting meal pickup via voice provided in an embodiment of the present application;

[0078] Figure 8 This is a schematic diagram of a GUI for planning a food delivery route by voice provided in an embodiment of the present application;

[0079] Figure 9 This is a schematic diagram of a GUI delivered via voice reporting provided in an embodiment of the present application;

[0080] Figure 10 This is a flowchart for automatically executing order processing provided by an embodiment of the present application;

[0081] Figure 11 This is a schematic flow chart of a method for automatically executing order processing provided in an embodiment of the present application;

[0082] Figure 12 is a schematic flow chart of another method for automatically executing orders provided in an embodiment of the present application;

[0083] Figure 13 This is an interactive flow chart for automatically executing order processing according to an embodiment of the present application;

[0084] Figure 14 This is another interactive flow chart for automatically executing order processing provided by an embodiment of the present application;

[0085] Figure 15 This is a schematic diagram of the structure of a device for automatically executing order processing provided by an embodiment of the present application;

[0086] Figure 16 This is a structural diagram of another device for automatically executing order processing provided by an embodiment of the present application;

[0087] Figure 17 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0088] Figure 18 It is a structural diagram of another electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0089] The following will clearly and thoroughly describe the technical solutions in this application in conjunction with the accompanying drawings. In the description of the embodiments of this application, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more than two.

[0090] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0091] Before introducing the solutions of the embodiments of the present application, the professional terms that may be involved in the embodiments of the present application are first explained.

[0092] Natural Language Processing (NLP): is an interdisciplinary field of computer science, artificial intelligence (AI) technology, and linguistics, which aims to enable computers to understand, interpret, and generate human language. The core goal of NLP is to enable machines to process natural language, including text and speech, like humans through algorithms and models, and to achieve effective communication between humans and machines. Specifically, NLP mainly includes natural language understanding (NLU) and natural language generation (NLG). The goal of NLU is to convert human language into a form that can be processed by computers; the goal of NLG is to convert computer-generated information into natural language form for output or interaction.

[0093] Tongyi Cloud Text-to-Speech (TTS): Provides text-to-speech services that convert text into natural and fluent language output based on deep learning technology.

[0094] Tongyi Cloud Automatic Speech Recognition (ASR): Provides automatic speech recognition services that convert human speech into text in real time using deep learning technology.

[0095] Reach platform: A customer contact or message push platform based on Tongyi Cloud, mainly responsible for information reception, processing and distribution, to achieve accurate reach in various business scenarios.

[0096] Intelligent agent conversation: includes intelligent customer service or intelligent assistants, etc., which are used to receive instructions, analyze and process them, generate responses, and output feedback.

[0097] Before introducing the solution of the embodiment of the present application, the application scenario of the embodiment of the present application is first introduced.

[0098] Currently, in the field of business processing, the execution process of event operations of related businesses lacks perception and analysis of actual scenarios, that is, whether event operations need to be executed depends entirely on the user's manual judgment.

[0099] For example, when delivering food, the delivery process is roughly divided into the following stages: receiving the order (or grabbing the order) → arriving at the store → picking up the food → delivering it → delivering it. Currently, the relevant technologies often require manual operation of the delivery process in these stages.

[0100] For example, taking the processing flow of the store arrival stage as an example, based on the takeaway delivery app installed on the user end (i.e., the rider's smart device), the rider can enter the order interface by clicking on the takeaway delivery app and accept the order by clicking. In addition, the order interface also includes a "route planning" icon. After the order is successfully accepted, the rider can also click on the "route planning" icon on the order interface. In response to the click operation, the user end can display the store arrival interface, which displays the store arrival path planned based on the rider's location and the merchant's location, as well as the real-time distance between the rider's location and the merchant's location. Based on the store arrival path, the rider can go to the merchant according to the instructions of the store arrival path. In addition, the store arrival interface also includes a "confirm arrival" control. As the rider rushes to the merchant, the store arrival path and real-time distance will be updated in real time. The rider can determine whether he has arrived at the merchant based on the distance displayed on the store arrival interface. When the rider determines that he has arrived at the merchant, he can click on the "confirm arrival" control in the store arrival interface to complete the processing action of reporting the arrival at the store to indicate that the current rider has arrived at the store.

[0101] Below through Figures 1 to 2 A detailed introduction is given to the process of the rider manually performing the "report to the store" processing action.

[0102] Figure 1 This is a GUI schematic diagram of a manual order grabbing method provided in an embodiment of the present application.

[0103] For example, Figure 1 (a) in FIG. 1 shows an interface 101 displayed by the user terminal in unlock mode. Figure 1 As shown in (a) of FIG. 1 , the interface 101 displays a weather clock component and multiple applications. The applications include phone, messaging, settings, and food delivery software (hereinafter referred to as "Application A"). It should be understood that the interface 101 may also include other applications, which are not limited in this embodiment of the application.

[0104] like Figure 1 As shown in (a), after the rider clicks the icon of application A in the interface 101, the user terminal displays the following in response to the rider's click operation: Figure 1 (b) shows the display interface 102 of the pending order page of Application A, or the display interface 102 can also be referred to as the "homepage of Application A." Display interface 102 displays a list of orders currently pending, an "order setup" icon, a "route planning" icon, a "go online now" control, a "personal center" icon, and a rider's work status display box. This embodiment of the application does not limit the display content, font size, or display format of the display interface 102.

[0105] On the display interface 102, the order list of orders to be grabbed can display one or more order parameters of the orders to be grabbed, and the rider can view more order parameters of the orders to be grabbed by sliding up and down. Optionally, the order parameters of each order to be grabbed include one or more contents such as the name of the merchant (or store) associated with the order, the merchant location, the user location to be delivered, the estimated delivery time, the basic delivery fee, the grabbing control of the order, the distance between the rider and the merchant location, and the distance between the rider and the user location to be delivered. For example, Figure 1 As shown in (b) in the order list of orders to be grabbed, the order parameters of the first order to be grabbed include the merchant name A Merchant (XXX Store), the merchant location is the storefront at X Floor, Unit X, No. X, Row X, District X, City X, Province, the user location to be delivered is XX-X, Unit X, Floor X, XX, Community X, District X, City X, the estimated delivery time is within 30 minutes, the basic delivery fee is 3.9, the order grabbing control of the order, the distance between the rider and the merchant location is 969m, and the distance between the rider and the user location to be delivered is 1.5km.

[0106] In addition, the working status display box of the display interface 102 includes a status icon and a status prompt word, which is used to indicate whether the rider's working status is activated. Figure 1 As shown in (b), when the rider has not started working, the work status display box displays the "waiting to go online" status icon and the "offline" status prompt word, which is used to indicate that the rider's work status is not activated.

[0107] When the rider starts working, he can click the "Go online now" control in the lower right corner of the display interface 102. In response to the click operation, the user terminal displays the following Figure 1 The display interface 103 of the page to be grabbed as shown in (c) in FIG. Figure 1 In the display interface 102 shown in (b), the status icon in the work status display box in the display interface 103 switches to the "online" status icon, and the status prompt switches from "offline" to "online", indicating that the rider's work status has been activated. In addition, when the rider is online, the control in the lower right corner of the display interface 103 switches from the original "online now" control to the "refresh order" control, which allows the rider to refresh the order list in the display interface 103 in real time during the delivery process.

[0108] Based on the list of orders to be grabbed displayed in the display interface 103, the rider can receive the delivery service of at least one corresponding order by clicking the "grab order" control of at least one order.

[0109] For example, Figure 1As shown in (c) in the figure, in the display interface 103, the rider clicks the "grab order" control of the first order in the list of orders to be grabbed. In response to the click operation, the interactive state of the "grab order" control switches from an activated state to a grayed-out state. Optionally, the embodiment of the present application does not limit the number of orders that the rider can grab in the display interface 103. The embodiment of the present application is described by taking the number of grabbed orders as 1 as an example.

[0110] After the order is completed, Figure 2 This section describes how to manually report an order to the store after grabbing it.

[0111] Figure 2 This is a GUI diagram for manually executing a report to a store provided in an embodiment of the present application.

[0112] For example, combined Figure 1 In (c), in the display interface 103, after the order is completed, the rider can click the "route planning" icon in the display interface 103. In response to the click operation, the user terminal displays the following Figure 2 The display interface 201 of the pickup page shown in (a) (or, the store arrival interface 201). The display interface 201 includes a navigation path display area, order parameters of the pickup order, an "online chat" icon, a "contact" icon, and a "confirm store arrival" control. The navigation path display area displays the navigation path between the merchant location and the rider location (i.e., the store arrival path or the pickup path), as well as a distance prompt box between the merchant location and the rider location. The distance display box is used to display the distance prompt text between the rider location and the merchant location.

[0113] For example, Figure 2 As shown in (a) in the figure, the navigation path display area of ​​the display interface 201 displays the navigation path between the location of merchant A (XXX store) and the rider's location, and the distance prompt text in the distance prompt box is "2km away", which is used to indicate that the distance between the current rider's location and the merchant's location is 2km.

[0114] Riders can follow the navigation path displayed in the navigation path display area to go to the merchant to pick up the meal. As the rider goes to the merchant, the navigation path and distance prompt text will also be updated in real time. Riders can determine whether they have arrived at the merchant based on the distance between their own location and the merchant's location. After confirming arrival at the merchant, the rider can manually report to the store by clicking the "Confirm Arrival" control.

[0115] like Figure 2As shown in (b) in the figure, the navigation path displayed in the navigation path display area in the display interface 202 changes, and the distance prompt text is "12m away", which is used to indicate that the distance between the current rider position and the merchant position is 12m. The rider determines that he has arrived near the merchant's location and manually clicks the "Confirm Arrival" control. In response to the click operation, the user end can change the interactive state of the "Confirm Arrival" control from an activated state to a gray state (not shown in the figure), so that the user end determines that the rider has arrived at the merchant's location and can enter the subsequent process, such as reminding the merchant to serve the food as soon as possible.

[0116] Through the above example, the rider can complete the report to the store through manual click operations during the delivery process.

[0117] The problem caused by the above manual operation is that when it is inconvenient for the rider to operate, the above manual click operation method is not smart enough, which increases the difficulty of the rider's operation and reduces the rider's delivery experience.

[0118] Based on the above problems, an embodiment of the present application provides a method for automatically executing order processing. During the process of the rider processing an order, when it is detected that the execution conditions of the order processing action are met, the method can automatically trigger a voice reminder and automatically execute the order processing action for the rider based on the voice instructions replied by the rider, thereby making the order processing process more intelligent, reducing the frequency of manual operations of the rider during the order processing process, and improving the rider's delivery experience.

[0119] Below through Figures 3 to 9 , the entire process of intelligent execution from going online to order processing provided by the embodiment of the present application is introduced. The above-mentioned entire process involves the interaction between the user terminal and the server corresponding to the user terminal. Among them, the user terminal is used to receive the rider's needs and send them to the server. The server is used to determine the corresponding execution instructions based on the rider's needs and send them to the user terminal. The user terminal further performs operations related to the rider's needs according to the execution instructions.

[0120] Figure 3 This is a schematic diagram of a GUI for waking up an artificial intelligence assistant through voice, provided in an embodiment of the present application.

[0121] For example, Figure 3 (a) shows the interface 301 displayed by the user terminal in the unlock mode, specifically Figure 1 The interface 101 shown in (a) is the same interface. For details, please refer to the aforementioned Figure 1 There is an introduction to interface 101 in , so I will not repeat it here.

[0122] After the rider clicks the icon of application A in interface 301, in response to the click operation, the user terminal displays the following Figure 3FIG. 3 is a display interface 302 of the order-to-be-grabbed page of application A shown in (b).

[0123] It should be understood that in the embodiment of the present application, an artificial intelligence (AI) assistant (hereinafter collectively referred to as the "AI assistant") is built into the food delivery platform's application A. During the order processing process, the AI ​​assistant can interact with the rider through voice, so that the user end automatically executes the order processing process based on the results of the voice interaction.

[0124] It should be noted that the AI ​​smart assistant is a visual interaction carrier that can carry intelligent interaction functions in an intuitive and vivid way. It refers to the technology or tool that carries information through graphical and dynamic interface elements and supports riders to complete human-computer interaction through intuitive operations (for example, dragging, clicking, voice wake-up, etc.).

[0125] Optionally, when the interface 302 is displayed after application A is just started in the user terminal, the AI ​​smart assistant can be displayed on the display interface 302 by default, or it can be selected based on the rider's manual settings whether to be displayed on the display interface 302.

[0126] For example, Figure 3 As shown in (b), when the rider clicks the icon of application A in interface 301 to enter display interface 302, display interface 302 displays the icon 3021 of the AI ​​smart assistant by default.

[0127] Another exemplary reference Figure 1 As shown in (b), when the rider clicks the icon of application A in interface 301 to enter display interface 302, the display interface 302 does not display the icon 3021 of the AI ​​smart assistant. Figure 1 The display interface 102 shown in (b) is exactly the same.

[0128] In this case, the rider can manually set the display status of the AI ​​smart assistant icon 3021 to on in the display setting interface of the AI ​​smart assistant, thereby manually triggering the user end to display the AI ​​smart assistant icon 3021 in the display interface 302.

[0129] The embodiment of the present application does not limit the display method of the icon 3021 of the above-mentioned AI smart assistant.

[0130] When the display interface 302 displays the icon 3021 of the AI ​​smart assistant, when there is no voice interaction between the rider and the AI ​​smart assistant, the icon 3021 of the AI ​​smart assistant can be displayed on the display interface 302 in a static or cyclical manner, indicating that the working status of the AI ​​smart assistant is "sleep state".

[0131] For example, Figure 3 As shown in (b), when the rider and the AI ​​smart assistant have not yet started voice interaction, a static AI smart assistant icon 3021 is displayed at the bottom of the right column of the display area of ​​the display interface 302.

[0132] Optionally, in addition to being displayed at the bottom of the right column, the AI ​​smart assistant icon 3021 may also be displayed at any location in the display area of ​​the display interface 302. For example, in the display area of ​​the display interface 302, the rider may drag and release the AI ​​smart assistant icon 3021 to move the AI ​​smart assistant icon 3021 from the bottom of the right column to any location after the drag, thereby achieving flexible display of the AI ​​smart assistant icon 3021.

[0133] Optionally, the icon 3021 of the AI ​​smart assistant can also be other virtual images that can interact intelligently with the rider; in addition to static display, the icon 3021 of the AI ​​smart assistant can also repeat simple actions (for example, turning in circles), etc., which is not limited in the embodiments of the present application.

[0134] In addition, other display contents of the display interface 302 are Figure 1 The display interface 102 shown in (b) is identical to that shown in FIG. Figure 1 The display interface 102 is introduced in , which will not be repeated here.

[0135] In one possible implementation, when a rider needs to interact with the AI ​​smart assistant through voice, the rider can wake up the AI ​​smart assistant by inputting a wake-up voice.

[0136] Specifically, when a rider opens App A for the first time, a pop-up window for setting microphone permissions will appear on the user end. The rider can set microphone permissions to "Always Allow" or "Always Allow During Use." After the microphone permission is enabled, when the rider needs to wake up the AI ​​smart assistant, they can do so by entering a wake-up voice prompt.

[0137] For example, the rider can wake up the AI ​​assistant by using the wake-up voice "Xiaohang Xiaohang" or "Xiaoniao Xiaoniao". In response to the wake-up voice, the user terminal can display the following Figure 3 The display interface 303 of the page to be grabbed of the order is shown in (c).

[0138] Optionally, the wake-up word of the illustrated AI smart assistant may also be a wake-up word that may be used in actual applications, such as "Xiaoe Xiaoe", or "Xiaoe Xiaoe", etc., which is not limited in the embodiments of the present application.

[0139] In another possible implementation, when the rider needs to interact with the AI ​​assistant through voice, he can also click Figure 3 In response to the click operation, the user terminal may display the following AI smart assistant icon 3021 in a stationary state: Figure 3 The display interface 303 shown in (c) in FIG.

[0140] Compared with the display interface 302 , the static AI smart assistant icon 3021 is no longer displayed in the display interface 303 . A pop-up window 3031 is displayed at the bottom of the display area of ​​the display interface 303 to indicate that the current AI smart assistant is in the awake state.

[0141] That is to say, when the AI ​​smart assistant is hidden or permanently displayed in a floating state, the AI ​​smart assistant is in a dormant state; when the AI ​​smart assistant is displayed through a pop-up window, the AI ​​smart assistant is in an awake state.

[0142] For example, Figure 3 The pop-up window 3031 shown in (c) includes the AI ​​smart assistant icon 3021, a close control, a default welcome message - "Hi, I am an AI smart assistant, how can I help you?" and the text corresponding to the default request voice - try saying "start work".

[0143] The rider clicks the close control in the pop-up window 3031. In response to the click operation, the user end can close the pop-up window 3031 to end the current voice interaction process. At the same time, the AI ​​smart assistant switches back to the "sleep state", thereby resuming the static display in the display interface 303.

[0144] Optionally, the embodiment of the present application does not limit the display position and display size of the pop-up window 3031. For example, in the display interface 303, the rider can control the pop-up window 3031 to move to any position in the display area of ​​the display interface 303 by dragging. The rider can also control the pop-up window 3031 to be reduced or enlarged at a certain ratio by zooming in or out. When the display size of the pop-up window 3031 changes, the text font displayed in the pop-up window 3031 can also be enlarged or reduced accordingly. This operation is also applicable to any of the pop-up windows mentioned below.

[0145] Through the above Figure 3 The rider can wake up the AI ​​smart assistant by following the interface operation process shown.

[0146] After the AI ​​assistant is awakened, Figure 4 This article introduces the process of how riders can automatically go online through voice.

[0147] Figure 4 This is a schematic diagram of a GUI for going online via voice provided in an embodiment of the present application.

[0148] For example, see Figure 3 In (c), after the user terminal displays the pop-up window 3031 on the display interface 303, when the user terminal receives the first round of request voice input by the rider - "start work", it can automatically display the following Figure 4 The display interface 401 of the page to be grabbed as shown in (a) of FIG. A pop-up window 4011 is displayed at the bottom of the display area of ​​the display interface 401. The first round of request voice refers to the first request voice input by the rider after the AI ​​smart assistant is awakened.

[0149] For example, Figure 4 As shown in (a) in the figure, the pop-up window 4011 includes the icon 3021 of the AI ​​smart assistant, the interactive status prompt text - "Xiao E is listening...", the text corresponding to the first round of request voice - "Start working" and the close control. Among them, the interactive status prompt text is used to indicate whether the AI ​​smart assistant is in a listening state or a broadcasting state during the voice interaction between the AI ​​smart assistant and the rider. The listening state means that the AI ​​smart assistant is receiving the rider's voice, and the broadcasting state means that the AI ​​smart assistant is broadcasting the voice for the rider. For example, the interactive status prompt text in the pop-up window 4011 - "Xiao E is listening...", indicates that the current AI smart assistant is receiving the rider's request voice.

[0150] Optionally, the interactive status prompt text used to indicate that the AI ​​smart assistant is in a listening state may also be other prompt texts, such as "Please state your current needs", which is not limited in this embodiment of the present application.

[0151] In the display interface 401, when the rider clicks the close control, in response to the click operation, the user end can close the pop-up window 4011 to end the current voice interaction process. At the same time, the AI ​​smart assistant returns to the "sleep state".

[0152] In response to the first round of request voice - "start work", the user terminal can send the first round of request voice to the server. The server determines the corresponding start-up execution instruction based on the first round of request voice and sends it to the user terminal. In response to the start-up execution instruction, the user terminal can display the following Figure 4 The display interface 402 of the page to be grabbed as shown in (b) of FIG. The display area of ​​the display interface 402 displays the execution result of the user terminal responding to the first round of request voice (or starting to execute the instruction).

[0153] For example, Figure 4As shown in (b) of Figure 402 , in response to the first round of voice request "Start Work," the user's terminal displays the following results: the status icon in the work status display box switches to the "Online" status icon, and the status prompt changes from "Offline" to "Online," indicating that the rider's work status has been activated. The control displayed in the lower right corner of display interface 402 switches from the original "Go Online Now" control to the "Refresh Orders" control, allowing the rider to refresh the list of pending orders in display interface 402 in real time during the delivery process.

[0154] In addition, display interface 402 also includes a pop-up window 4021. Pop-up window 4021 includes the AI ​​assistant icon 3021, the interactive status prompt text "Xiao E is reporting", a close control, and the prompt text of the above execution result - "Online". The interactive status prompt text - "Xiao E is reporting" indicates that the AI ​​assistant is currently broadcasting a voice message to the rider. The specific broadcast voice message is the voice message of the prompt text of the above execution result.

[0155] Optionally, the interactive status prompt text used to indicate that the AI ​​smart assistant is in the broadcast state may also be other prompt texts, such as "The operation has been successfully performed for you", which is not limited in the embodiment of the present application.

[0156] In display interface 402, when the rider clicks the close control, the user terminal can close pop-up window 4021 in response to the click operation to end the current voice interaction process. At the same time, the AI ​​smart assistant returns to the "sleep state".

[0157] After the first round of voice request response is completed, if the rider has not yet input the second round of voice request, the user terminal can display the following Figure 4 The display interface 403 of the page to be grabbed as shown in (c) of FIG. A pop-up window 4031 is displayed at the bottom of the display area of ​​the display interface 403.

[0158] For example, Figure 4 As shown in (c) in the figure, the pop-up window 4031 includes the AI ​​assistant icon 3021, the interactive status prompt text - "Xiao E is listening", a close control and a waiting to receive voice icon 4032. Among them, the waiting to receive voice icon 4032 is used to indicate that the AI ​​assistant is waiting for the rider to input a new round of request voice.

[0159] In display interface 403, when the rider clicks the close control, the user terminal can close pop-up window 4031 in response to the click operation to end the current voice interaction process. At the same time, the AI ​​smart assistant returns to the "sleep state".

[0160] Specifically, to prevent the pop-up window 4031 from being displayed continuously in the display interface 403 due to the rider not inputting a new voice request for a long time, the technician can pre-set the display duration of the pop-up window 4031. When the waiting time for the AI ​​smart assistant to receive the voice request reaches the preset display duration, the user terminal automatically closes the pop-up window 4031 and controls the AI ​​smart assistant to return to the "sleep state".

[0161] Optionally, in order to facilitate the rider to understand the display duration of pop-up window 4031, pop-up window 4031 may also include a countdown for the preset display duration or a prompt text for the preset display duration, such as "Please enter a new operation request voice within xxx seconds, or wait for the remaining time to receive the voice for xx seconds."

[0162] The other contents of the above display interface 402 and display interface 403 are the same as Figure 1 The display interface 103 shown in (c) is exactly the same as that shown in FIG. For details, please refer to the relevant introduction of the display interface 103, which will not be repeated here.

[0163] Through the above Figure 4 As shown in the interface operation process, the rider can make a voice request to enable the user end to automatically perform the online operation.

[0164] Below through Figure 5 This article introduces how riders can automatically grab orders through voice during the order processing process, and how to plan the pickup route through voice after successfully grabbing the order.

[0165] Figure 5 This is a GUI schematic diagram for grabbing orders and planning meal pickup routes through voice, provided in an embodiment of the present application.

[0166] For example, see Figure 4 In (c), the user terminal receives the second round of request voice - "Please help me grab the order" within the preset display time corresponding to the pop-up window 4031, and can display the following Figure 5 The display interface 501 of the page to be grabbed as shown in (a) of FIG. A pop-up window 5011 is displayed at the bottom of the display area of ​​the display interface 501.

[0167] For example, Figure 5 As shown in (a), the pop-up window 5011 includes the icon 3021 of the AI ​​smart assistant, the interactive status prompt text - "Xiao E is listening to...", the closing control and the text corresponding to the second round of request voice - "Please help me grab the order."

[0168] In the display interface 501, when the rider clicks the close control, in response to the click operation, the user end can close the pop-up window 5011 to end the current voice interaction process. At the same time, the AI ​​smart assistant returns to the "sleep state".

[0169] In response to the second round of request voice - "Please help me grab the order", the user terminal can send the second round of request voice to the server. The server determines the corresponding grab order execution instruction based on the second round of request voice and sends it to the user terminal. In response to the grab order execution instruction, the user terminal can display the following Figure 5 The display interface 502 of the page to be grabbed as shown in (b) of FIG. The display area of ​​the display interface 502 displays the execution result of the user terminal responding to the second round of request voice (or the grab order execution instruction).

[0170] For example, Figure 5 As shown in (b), in the display interface 502, the user terminal responds to the second round of request voice - "Please help me grab the order", and the execution result is specifically: the "Grab the order" control of the first order in the order list to be grabbed changes from the original activated state to the gray state, and the text label corresponding to the control changes from the original "Grab the order" to "Order grabbed".

[0171] In addition, a pop-up window 5021 is displayed at the bottom of the display area of ​​display interface 502. Pop-up window 5021 includes the AI ​​assistant icon 3021, the interactive status prompt text - "Xiao E is reporting", a close control, and the prompt text of the above execution result - "Order grabbed". The interactive status prompt text - "Xiao E is reporting" indicates that the AI ​​assistant is currently broadcasting a voice message to the rider, and the broadcast voice message is the voice message of the above execution result prompt text.

[0172] In the display interface 502, when the rider clicks the close control, in response to the click operation, the user end can close the pop-up window 5021 to end the current voice interaction process. At the same time, the AI ​​smart assistant returns to the "sleep state".

[0173] After successfully responding to the second round of request voice, such as Figure 4 As shown in (c), when the rider has not yet input the third round of request voice, the user terminal can switch the pop-up window 5021 at the bottom of the display area of ​​the display interface 502 to a pop-up window 4031 to wait for receiving the third round of request voice input by the rider. For specific display content, please refer to the aforementioned Figure 4 The introduction in (c) will not be repeated here.

[0174] When the user terminal receives the third round of request voice within the preset display time, it can display the following Figure 5 In the display interface 503 of the page to be ordered shown in (c), a pop-up window 5031 is displayed at the bottom of the display area of ​​the display interface 503.

[0175] For example, Figure 5As shown in (c), the pop-up window 5031 includes the AI ​​smart assistant icon 3021, the interactive status prompt text - "Xiao E is listening...", the close control and the text corresponding to the third round of request voice - "Please help me plan a route to pick up the food."

[0176] In the display interface 503, when the rider clicks the close control, in response to the click operation, the user end can close the pop-up window 5031 to end the current voice interaction process. At the same time, the AI ​​smart assistant returns to the "sleep state".

[0177] In response to the third round of request voice - "Please help me plan a meal pickup route", the user terminal can send the third round of request voice to the server. The server determines the corresponding meal pickup route execution instruction based on the third round of request voice and sends it to the user terminal. In response to the meal pickup route execution instruction, the user terminal can display the following Figure 5 The display interface 504 of the pickup page shown in (d) in FIG. The display area of ​​the display interface 504 displays the execution result of the user terminal responding to the third round of request voice (or the meal pickup path execution instruction).

[0178] For example, Figure 5 As shown in (d) in the figure, the display interface 504 includes a navigation path display area. When the user receives the third round of voice request - "Please help me plan a route for picking up the food", the execution result is specifically: the navigation path display area is displayed in the display interface 504. The navigation path display area includes the pickup route and a distance prompt box between the rider's location and the merchant's location. The distance prompt box displays the distance prompt text between the rider's location and the merchant's location - "2km away from the pickup", indicating that the rider's location and the merchant's location are currently 2km apart.

[0179] When the user switches from display interface 503 to display interface 504, it means that the rider currently needs to go to the merchant to pick up the meal. In order to facilitate the rider to contact the merchant and perform subsequent store reporting processing, the display icons at the bottom of the display area of ​​display interface 504 are correspondingly switched to the "Online Chat" icon and the "Contact" icon, and the display control is switched to the "Confirm Arrival" control.

[0180] In addition, a pop-up window 5041 appears at the bottom of the display area of ​​display interface 504. This pop-up window includes the AI ​​assistant icon 3021, the interactive status prompt text "Xiao'e is reporting," a close control, and the prompt text of the aforementioned execution result, "A pickup route has been planned for you." The interactive status prompt text "Xiao'e is reporting" indicates that the AI ​​assistant is currently reporting a voice message to the rider. The specific broadcast voice message is the voice message of the aforementioned execution result prompt text.

[0181] In display interface 504, when the rider clicks the close control, the user terminal can close pop-up window 5041 in response to the click operation to end the current voice interaction process. At the same time, the AI ​​smart assistant returns to the "sleep state".

[0182] Similarly, after successfully responding to the third round of voice requests, Figure 4 As shown in (c), when the rider has not yet input the fourth round of request voice, the user terminal can switch the pop-up window from pop-up window 5041 to pop-up window 4031 in the display interface 504 to wait for receiving the fourth round of request voice input by the rider. For specific display content, please refer to the aforementioned Figure 4 The introduction in (c) will not be repeated here.

[0183] It should be understood that it usually takes a long time for a rider to pick up the food from the merchant, which may exceed the preset display time corresponding to pop-up window 4031. During this process, if the user end does not receive a new round of request voice within the preset display time, the AI ​​smart assistant can be restored to the "sleep state".

[0184] After planning the pickup route, the rider can follow the route displayed in the navigation area to the merchant. As the rider travels to the merchant, the server can obtain the rider's location in real time through the user's terminal. Based on this, the server can determine in real time whether the rider has reached the merchant's vicinity based on the rider's location and the merchant's location, and decide whether to remind the rider to report to the store through the user's terminal.

[0185] Below through Figure 6 This article describes how to automatically report orders to stores during order processing.

[0186] Figure 6 This is a GUI schematic diagram for reporting to a store via voice provided in an embodiment of the present application.

[0187] For example, Figure 6 As shown in (a), combined with Figure 5 In (d), when the rider goes to the merchant to pick up the food, the server will control the user end to update the food pickup path in the navigation path display area in real time, as well as the distance between the rider's location and the merchant's location. When the server determines that the distance between the rider's location and the merchant's location is relatively close, it can control the user end to display the following information: Figure 6 The display interface 601 of the pickup page shown in (a) of FIG. The display interface 601 includes a navigation path display area. The distance prompt box in the navigation path display area displays the distance prompt text between the current rider position and the merchant position - "12m away from pickup", indicating that the distance between the rider position and the merchant position is 12m, indicating that the rider is currently close to the merchant.

[0188] In this case, the display interface 601 also includes a pop-up window 6011, which includes the icon 3021 of the AI ​​smart assistant, the interactive status prompt text - "Xiao E is reporting", the report to the store prompt text - "You have arrived at merchant A (XXX store), do you want to report to the store?" and a close control. Among them, the report to the store prompt text - "You have arrived at merchant A (XXX store), do you want to report to the store?" is used to remind the rider that the current distance to the merchant is close, and whether it is necessary to perform the processing action of reporting to the store. The interactive status prompt text - "Xiao E is reporting" indicates that the current AI smart assistant is broadcasting a voice, and the broadcast voice is the voice corresponding to the report to the store prompt text (i.e., the report to the store prompt voice).

[0189] Optionally, the voice / text for reporting the store arrival prompt may also be “You have arrived at merchant A (XXX store), do you want to confirm your arrival at the store?” This embodiment of the present application does not limit this.

[0190] In display interface 601, when the rider clicks the close control, the user terminal can close pop-up window 6011 in response to the click operation to end the current voice interaction process. At the same time, the AI ​​smart assistant returns to the "sleep state".

[0191] After receiving the rider's reply to the store report prompt, the user terminal can display the following Figure 6 The display interface 602 of the pickup page shown in (b) of FIG. A pop-up window 6021 is displayed at the bottom of the display area of ​​the display interface 602.

[0192] For example, Figure 6 As shown in (b), the pop-up window 6021 includes the AI ​​smart assistant icon 3021, the interactive status prompt text - "Xiao E is listening...", the text corresponding to the reply voice - "Please help me report to the store" and the close control.

[0193] Optionally, the reply voice / text can also be "Please help me confirm arrival at the store", "Report arrival at the store", "Confirm arrival at the store", etc., which is not limited in this embodiment of the present application.

[0194] In display interface 602, when the rider clicks the close control, the user terminal can close pop-up window 6021 in response to the click operation to end the current voice interaction process. At the same time, the AI ​​smart assistant returns to the "sleep state".

[0195] In response to the rider's reply voice to the store report prompt voice, the user terminal can send the reply voice to the server. The server determines the processing instruction of the store report based on the reply voice and sends it to the user terminal. In response to the processing instruction of the store report, the user terminal can display the following information: Figure 6The display interface 603 of the pickup page shown in (c) of FIG. The display interface 603 includes the execution result of the user terminal for the above reply voice (or the processing instruction of reporting to the store).

[0196] For example, Figure 6 As shown in (c), in response to the rider's reply voice, the execution result displayed on the user end is specifically: in the display interface 603, the interactive state of the "Confirm Arrival at Store" control is switched from the activated state to the grayed state, and the text label of the control is switched from "Confirm Arrival at Store" to "Arrived at Store".

[0197] In addition, a pop-up window 6031 is located at the bottom of the display area of ​​display interface 603. This pop-up window includes the AI ​​assistant icon 3021, a close control, and the interactive status prompt text "Xiao E is reporting," along with the aforementioned prompt text for the execution result, "Your delivery has been reported to the store." The interactive status prompt text "Xiao E is reporting" indicates that the AI ​​assistant is currently broadcasting a voice message to the rider. The specific broadcast voice message is the voice message of the aforementioned prompt text for the execution result.

[0198] In display interface 603, when the rider clicks the close control, the user terminal can close pop-up window 6031 in response to the click operation to end the current voice interaction process. At the same time, the AI ​​smart assistant returns to the "sleep state".

[0199] In another implementation, Figure 6 In the display interface 601 shown in (a), the pop-up window 6011 also includes a "Close" control and a "Confirm Arrival at the Store" control. After the AI ​​smart assistant reminds the rider whether to report to the store, in addition to automatically executing the report to the store upon receiving the rider's reply voice, the rider can manually execute the report to the store by clicking the "Confirm Arrival at the Store" control in the pop-up window 6011, or manually cancel the report to the store by clicking the "Close" control in the pop-up window 6011.

[0200] Correspondingly, when the rider clicks the "Confirm Arrival at Store" control in the pop-up window 6011, the interactive state of the "Confirm Arrival at Store" control in the display interface 601 will also become grayed out, and the text label in the control will switch from "Confirm Arrival at Store" to "Arrived at Store".

[0201] Through the above Figure 6 As shown in the interface operation process, the rider can use voice request to enable the user end to automatically complete the report to the store process.

[0202] After confirming your arrival at the store, Figure 7 This article introduces how to automatically report and pick up meals during order processing.

[0203] Figure 7This is a GUI schematic diagram for reporting meal pickup via voice provided in an embodiment of the present application.

[0204] For example, see Figure 6 As shown in (c), after the user terminal reports the arrival at the store, the processing result of the arrival at the store can be fed back to the server, and the server updates the order status to arrived at the store. Furthermore, the server can use the moment when the order status is updated to arrived at the store as the starting moment to time the time the rider waits for the meal to be picked up, and obtain the rider's waiting time for the meal. In the embodiment of the present application, a preset waiting time for the meal can be pre-set. During the process of waiting for the meal to be picked up, the server can determine whether the waiting time for the meal has reached the preset waiting time for the meal.

[0205] When it is detected that the waiting time for picking up the meal reaches the preset waiting time for picking up the meal, the server can control the user terminal to display the following Figure 7 In the display interface 701 of the pickup page shown in (a), the bottom of the display area of ​​the display interface 701 includes a pop-up window 7011.

[0206] For example, Figure 7 As shown in (a) of FIG, pop-up window 7011 includes AI assistant icon 3021, interactive status prompt text—"Xiao E is reporting," prompt text for reporting meal pickup—"We have detected that you have been waiting for a long time to pick up your meal. Would you like to report your meal pickup?" and a close control. The interactive status prompt text—"Xiao E is reporting"—indicates that the AI ​​assistant is currently broadcasting a voice message. The broadcast voice message corresponds to the prompt text for reporting meal pickup (i.e., the voice message for reporting meal pickup).

[0207] In the display interface 701, when the rider clicks the close control, the user terminal can close the pop-up window 7011 in response to the click operation to end the current voice interaction process. At the same time, the AI ​​smart assistant returns to the "sleep state".

[0208] In addition, compared with Figure 6 In (c), when the rider arrives at the store and waits to pick up the food, Figure 7 The icons and controls at the bottom of (a) will also switch accordingly. Figure 7 As shown in (a), the icons at the bottom of the display interface 701 include an “order setting” icon, a “route planning” icon, a “cancel order” control, and a “pick up goods” control.

[0209] After receiving the rider's reply to the pickup reminder voice, the user terminal can display the following Figure 7 The display interface 702 of the pickup page shown in (b) of FIG. A pop-up window 7021 is displayed at the bottom of the display area of ​​the display interface 702.

[0210] For example, Figure 7As shown in (b), the pop-up window 7021 includes the AI ​​smart assistant icon 3021, the interactive status prompt text - "Xiao E is listening...", the text corresponding to the reply voice - "Please help me report to pick up the meal" and the close control.

[0211] Optionally, the reply voice / text may also be “Please help me confirm to pick up the meal”, “Confirm to pick up the meal”, etc., which is not limited in this embodiment of the present application.

[0212] In the display interface 702, when the rider clicks the close control, the user terminal can close the pop-up window 7021 in response to the click operation to end the current voice interaction process. At the same time, the AI ​​smart assistant returns to the "sleep state".

[0213] In response to the rider's reply voice corresponding to the report pickup prompt voice, the user terminal can send the reply voice to the server. The server determines the processing instruction for reporting pickup based on the reply voice and sends it to the user terminal. In response to the processing instruction for reporting pickup, the user terminal can display the following information: Figure 7 The display interface 703 of the pickup page shown in (c) of FIG. The display interface 703 includes the execution result of the user terminal for the above reply voice (or the processing instruction of reporting the pickup).

[0214] For example, Figure 7 As shown in (c), in response to the rider's reply voice, the execution result displayed on the user end is specifically: in the display interface 703, the interactive state of the "Pick up" control is switched from the activated state to the grayed state, and the text label of the control is switched from "Pick up" to "Picked up".

[0215] In addition, the bottom of the display area of ​​display interface 703 includes a pop-up window 7031. Pop-up window 7031 includes the AI ​​assistant icon 3021, the interaction status prompt text - "Xiao'e is reporting", the prompt text of the above execution result - "Your meal has been reported for pickup", and a close control. The interaction status prompt text - "Xiao'e is reporting" indicates that the AI ​​assistant is currently broadcasting a voice message to the rider. The specific broadcast voice message is the voice message of the above execution result prompt text.

[0216] In the display interface 703, when the rider clicks the close control, in response to the click operation, the user end can close the pop-up window 7031 to end the current voice interaction process. At the same time, the AI ​​smart assistant returns to the "sleep state".

[0217] In another implementation, Figure 7In the display interface 701 shown in (a), the pop-up window 7011 also includes a "Close" control and a "Confirm Pickup" control. After the AI ​​smart assistant reminds the rider whether to report the pickup, in addition to automatically executing the pickup report upon receiving the rider's reply voice, the rider can manually report the pickup by clicking the "Confirm Pickup" control in the pop-up window 7011, or manually cancel the pickup report by clicking the "Close" control in the pop-up window 7011.

[0218] Correspondingly, when the rider clicks the "Confirm Pickup" control in the pop-up window 7011, the interactive state of the "Pickup" control in the display interface 701 will also become grayed out, and the text label in the control will switch from "Pickup" to "Picked Up".

[0219] Through the above Figure 7 As shown in the interface operation process, the rider can use voice request to enable the user end to automatically complete the report of picking up the meal.

[0220] After completing the report to pick up the meal, the following Figure 8 This article introduces how to trigger the meal delivery route planning process during order processing.

[0221] Figure 8 This is a schematic diagram of a GUI for planning a food delivery route by voice according to an embodiment of the present application.

[0222] For example, see Figure 7 As shown in (c) in the figure, after reporting the order, the user terminal can feed back the result of the order to the server, and the server will update the order status to "ordered". When receiving a new round of request voice from the rider, the user terminal can display the following information: Figure 8 In the display interface 801 of the pickup page shown in (a), a pop-up window 8011 is displayed at the bottom of the display area of ​​the display interface 801.

[0223] For example, Figure 8 As shown in (a), the pop-up window 8011 includes the AI ​​smart assistant icon 3021, the rider's new round of request voice - "Please help me plan the delivery route", the interaction status prompt text - "Xiao E is listening" and the close control.

[0224] In the display interface 801, when the rider clicks the close control, in response to the click operation, the user end can close the pop-up window 8011 to end the current voice interaction process. At the same time, the AI ​​smart assistant returns to the "sleep state".

[0225] In response to the rider's new round of request voice, the user terminal can send the new round of voice to the server. The server determines the corresponding delivery path execution instruction based on the new round of request voice and sends it to the user terminal. In response to the delivery path execution instruction, the user terminal can display the following information: Figure 8 The display interface 802 of the to-be-delivered page shown in (b) of FIG. The display interface 802 includes the execution result of the user terminal for the above-mentioned request voice (or the delivery path execution instruction).

[0226] For example, Figure 8 As shown in (b) in the figure, the display interface 802 includes a navigation path display area. The user terminal responds to the rider's voice request - "Please help me plan the delivery route", and the execution result is specifically: the navigation path display area is displayed in the display interface 802. The navigation path display area includes the delivery route and a distance prompt box between the rider's location and the user's location. The distance prompt box displays the distance prompt text between the rider's location and the user's location - "2.5km away from delivery", indicating that the distance between the rider's location and the user's location is 2.5km.

[0227] In addition, a pop-up window 8021 appears at the bottom of the display area of ​​display interface 802. This pop-up window includes the AI ​​assistant icon 3021, the interactive status prompt text "Xiao E is reporting," a close control, and the prompt text for the aforementioned execution result, "A delivery route has been planned for you." The interactive status prompt text "Xiao E is reporting" indicates that the AI ​​assistant is currently broadcasting a voice message to the rider. The specific broadcast voice message is the voice message for the aforementioned execution result prompt text.

[0228] In display interface 802, when the rider clicks the close control, the user terminal can close pop-up window 8021 in response to the click operation to end the current voice interaction process. At the same time, the AI ​​smart assistant returns to the "sleep state".

[0229] In addition, the display icons and display controls at the bottom of the display area in the display interface 802 are also switched accordingly. Figure 8 As shown in (b), compared with Figure 8 In (a), the display icons at the bottom of the display area switch to the "Online Chat" icon and the "Contact" icon, and the display control switches to the "I Have Delivered" control.

[0230] Based on the delivery route displayed in display interface 802, the rider can deliver the meal to the user's location. During the delivery process, the server can control the user terminal to update the navigation route and distance prompt text in the navigation display area in real time based on the rider's location and the user's location. The server can also determine that the rider is close to the user's location based on the rider's location and the user's location.

[0231] Below through Figure 9This section describes how to automatically report delivery when a rider delivers food to a user's location.

[0232] Figure 9 This is a GUI schematic diagram provided in an embodiment of the present application and delivered via voice reporting.

[0233] For example, during the delivery process, when the server detects that the rider's location is close to the user's location, the user terminal can be controlled to display the following information: Figure 9 The display interface 901 of the to-be-delivered page shown in (a) of FIG. The display interface 901 includes a navigation path display area. The distance prompt box in the navigation path display area displays the distance prompt text between the current rider position and the user position - "10m away from delivery", indicating that the distance between the rider position and the user position is 10m, indicating that the rider is currently close to the user.

[0234] In this case, the display interface 901 also includes a pop-up window 9011, which includes the icon 3021 of the AI ​​smart assistant, the interactive status prompt text - "Xiao E is reporting", the report delivery prompt text - "It is detected that you have arrived at the delivery location, do you want to report the delivery?" and a close control. Among them, the report delivery prompt text - "It is detected that you have arrived at the delivery location, do you want to report the delivery?" is used to remind the rider that the current distance from the user is close to whether the reporting and delivery processing action needs to be executed. The interactive status prompt text - "Xiao E is broadcasting" indicates that the current AI smart assistant is broadcasting a voice, and the broadcast voice is the voice corresponding to the report delivery prompt text (that is, the report delivery prompt voice).

[0235] In display interface 901, when the rider clicks the close control, the user terminal can close pop-up window 9011 in response to the click operation to end the current voice interaction process. At the same time, the AI ​​smart assistant returns to the "sleep state".

[0236] After receiving the rider’s reply to the delivery notification voice, the user terminal can display the following Figure 9 The display interface 902 of the to-be-delivered page shown in (b) of FIG. A pop-up window 9021 is displayed at the bottom of the display area of ​​the display interface 902.

[0237] For example, Figure 9 As shown in (b), the pop-up window 9021 includes the AI ​​smart assistant icon 3021, the interactive status prompt text - "Xiao E is listening...", the text corresponding to the reply voice - "Please help me report the delivery" and the close control.

[0238] In display interface 902, when the rider clicks the close control, the user terminal can close pop-up window 9021 in response to the click operation to end the current voice interaction process. At the same time, the AI ​​smart assistant returns to the "sleep state".

[0239] In response to the above reply voice, the user terminal can send the reply voice to the server. The server determines the corresponding execution instruction of the report and sends it to the user terminal based on the reply voice. In response to the execution instruction of the report, the user terminal can display the following Figure 9 The display interface 903 of the page to be delivered shown in (c) of FIG. The display interface 903 includes the execution result of the user terminal for the above reply voice (or the execution instruction of the report delivery).

[0240] For example, Figure 9 As shown in (c), in the display interface 903, when the user terminal receives the reply voice of the delivery reporting prompt voice - "Please help me report the delivery", the execution result is specifically: the interactive state of the "I have delivered" control changes from the activated state to the grayed state.

[0241] In addition, a pop-up window 9031 is displayed at the bottom of the display area of ​​display interface 903. Pop-up window 9031 includes the AI ​​assistant icon 3021, the interactive status prompt text "Xiao'e is reporting", the prompt text of the above execution result - "The report has been delivered to you", and a close control. The interactive status prompt text - "Xiao'e is reporting" indicates that the AI ​​assistant is broadcasting a voice message, which is the voice message corresponding to the prompt text of the above execution result.

[0242] In display interface 903, when the rider clicks the close control, the user terminal can close pop-up window 9031 in response to the click operation to end the current voice interaction process. At the same time, the AI ​​smart assistant returns to the "sleep state".

[0243] In another implementation, the pop-up window 9011 in the display interface 901 may further include a "Close" control and a "Confirm Delivery" control. After the AI ​​smart assistant reminds the rider whether to report the delivery, in addition to automatically executing the report delivery upon receiving the rider's reply voice, the rider can manually execute the report delivery by clicking the "Confirm Delivery" control in the pop-up window 9011, or manually cancel the report delivery by clicking the "Close" control in the pop-up window 9011.

[0244] Thus, through the above Figures 3 to 9 , riders can intelligently implement a series of order processing processes by interacting with AI smart assistants and servers.

[0245] In passing Figures 3 to 9 After introducing the GUI diagram for implementing order processing in the embodiment of the present application, the following Figure 10 The overall implementation process of the embodiment of the present application is introduced.

[0246] It should be understood that the method of automatically executing order processing provided in the embodiment of the present application can be applied to the server corresponding to the food delivery platform, and can also be applied to the user end. Here, the user end refers to the smart device on which the App of the food delivery platform is installed, that is, the smart device on the rider's side. Specifically, during the rider's delivery process, the server can intelligently determine whether it is necessary to execute the order processing action based on a variety of parameters. When the order processing action needs to be executed, the server sends an instruction to the rider's user end, and the user end controls the icon of the AI ​​smart assistant in the food delivery application to give a voice prompt according to the instruction. The following is through Figure 10 The processing process of the above server is introduced.

[0247] Figure 10 This is a flowchart for implementing automatic order processing provided by an embodiment of the present application.

[0248] For example, Figure 10 As shown in the figure, according to the various processes of the server in the order processing process, the server can be divided into the following different functional modules: business module, intelligent agent conversation module, NLP intent recognition module and contact platform module.

[0249] During the order processing on the server, the functions of the above modules are as follows:

[0250] The business module is used to obtain scenario event matching based on the rider's real-time parameters and the order parameters associated with the current order. Scenario event matching specifically refers to determining whether the rider's real-time parameters and order parameters meet the corresponding prompt conditions.

[0251] For example, see the above Figures 3 to 9 As shown in , when the server detects that the rider arrives at the merchant and determines that the prompt conditions for reporting to the store are met, the corresponding scene event is "Report to the store"; when the server detects that the rider has completed picking up the meal and determines that the prompt conditions for reporting picking up the meal are met, the corresponding scene event is "Report picking up the meal"; when the server detects that the rider has completed delivering the meal and determines that the prompt conditions for reporting delivery are met, the corresponding scene event is "Report delivery".

[0252] Optionally, in an embodiment of the present application, the business module can provide four types of services, namely, forward operation business, abnormal operation business, rider care business and rider basic business. Different businesses correspond to different business units, and each business unit is used to match scene events for the business it manages.

[0253] Among them, positive operation business refers to the related business when the rider handles the order normally and smoothly, such as reporting store business, reporting meal pickup business or reporting delivery business.

[0254] Abnormal operations refer to unexpected, sudden situations or operations that do not conform to normal procedures when the rider handles the order. For example, traffic congestion operations and weather warning operations.

[0255] Rider care services refer to services related to rider work experience, rights and interests reminders, and daily life care. For example, rider welfare services and birthday reminder services.

[0256] Rider basic business refers to the rider's basic information, training business and other related businesses.

[0257] The following takes the forward operation business of reporting to the store as an example. Figure 10 The processing process of the server is introduced in the following.

[0258] See also Figure 6 As shown in (a), after the order is successfully grabbed, the server can obtain the order parameters associated with the current order (for example, the merchant location) and the rider's real-time parameters (for example, the rider's location). When the rider is on the way to the merchant, the forward operation business subunit in the business module can determine whether the rider has arrived at the merchant based on the rider's location and the merchant's location. When the rider arrives at the merchant, the server can determine that the "report to store" scenario event has been successfully matched.

[0259] For example, Figure 10 As shown in , when the business module determines that the "report to store" scenario event has been matched successfully, the above scenario event can be sent to the intelligent agent session, and the intelligent agent session will perform rule verification to determine whether to send a notification to the user end.

[0260] Specifically, the content of the rule verification of the intelligent agent conversation includes: detecting whether the user end is performing voice interaction, or whether the message is expired.

[0261] When the rule verification is successful, the intelligent agent conversation module sends a "report to store" scenario event to the contact platform module, so that the contact platform module sends the scenario event to the user end.

[0262] When the user receives the "report to store" scenario event, the AI ​​smart assistant can play a voice reminder of the scenario event, for example Figure 6 As shown in (a) in the figure, the voice reminder currently played by the AI ​​smart assistant is - "You have arrived at merchant A (XXX store), do you want to report to the store?"

[0263] After the user terminal has finished broadcasting the voice reminder of the above-mentioned scenario event, the user terminal can collect the rider's reply voice in response to the above-mentioned voice reminder.

[0264] Optionally, a preset waiting time may be set in the embodiment of the present application.

[0265] When the user terminal does not detect the rider's reply voice within the preset waiting time, the interaction process ends.

[0266] When the user terminal detects the rider's reply voice within the preset waiting time, the user terminal can convert the above reply voice into text information through Tongyi Cloud ASR and send it to the server.

[0267] After the server receives the text information of the reply voice, it can send the text information corresponding to the reply voice to the intelligent agent conversation module. The intelligent agent conversation module will perform intent recognition on the above text information by calling the NLP intention recognition module, thereby identifying the rider's intention and obtaining the intention recognition result.

[0268] The NLP intent recognition module further sends the intent recognition results to the agent conversation module.

[0269] If intent recognition is successful, the agent conversation module determines whether the current intent is an execution intent. If the current intent is an execution intent, the agent conversation module can obtain the execution steps of the current scene event and send them to the user end in the form of processing instructions, so that the user end can automatically execute the processing instructions and report it to the store.

[0270] When intent recognition fails or the current intention is not an execution intention, the intelligent agent conversation module can control the AI ​​voice assistant to conduct multiple rounds of conversations with the rider, and further recognize the rider's reply voice in the multiple rounds of conversations to continue to obtain intent recognition results and repeat the above process.

[0271] Below through Figure 11 A method for automatically executing order processing provided in an embodiment of the present application is introduced. It should be understood that the method is applied to a server.

[0272] Figure 11 This is a schematic flowchart of a method for automatically executing order processing provided in an embodiment of the present application.

[0273] For example, Figure 11 As shown, the method 1100 includes the following steps S1101 to S1105.

[0274] S1101, obtain the rider's real-time parameters and the order parameters associated with the current order.

[0275] After a rider goes online and completes an order, the completed order becomes the current order. The rider's processing of a current order primarily involves the following stages: arriving at the store, picking up the order, and then delivering it.

[0276] Optionally, the rider can complete the process of going online and grabbing orders through manual click operations, or can use voice commands to allow the user end to automatically complete the process of going online and grabbing orders.

[0277] For example, Figure 1 As shown in (a)-(c) in the figure, the rider can manually click the "Go Online Now" control to complete the online process. After completing the online process, the rider can also manually click the "Grab Order" control of an order in the order list to complete the order grabbing process.

[0278] Another example, Figures 3 to 5 As shown, the rider can also interact with the AI ​​smart assistant in the food delivery application through voice, so that the user end can automatically complete the process of going online and grabbing orders. When the rider is processing the current order, based on the method for automatically executing order processing provided by the embodiment of this application, the server can determine whether the conditions for voice reminders to the rider are currently met by obtaining the rider's real-time parameters and the order parameters associated with the current order.

[0279] Optionally, the rider's real-time parameters include but are not limited to the rider's location, and the order parameters associated with the current order include but are not limited to the merchant's location, the user's location, and the target order status of the current order.

[0280] For example, while the rider is processing an order, the user can obtain the rider's location in real time and send it to the server. Regarding the merchant's location and user's location, once the user successfully places an order, the new order is successfully created. The server can obtain the order parameters associated with each successfully created order and generate a unique order ID for each successfully created order. At the same time, the server will send the order parameters and order ID associated with the successfully created order to the user.

[0281] After a rider successfully grabs an order using any of the above methods, the user terminal determines the order ID associated with the successfully grabbed order and sends it to the server. Based on the order ID, the server determines the specific order and the order parameters associated with the current order. These order parameters include the merchant location and user location associated with the current order.

[0282] For the target order status of the current order, different processing stages correspond to different order statuses. After the order is successfully grabbed, the user terminal can send the successful grab result to the server. In response to the successful grab result, the server determines the current order and updates the target order status of the current order to the grabbed state; when the rider completes the store arrival stage, the user terminal can send the store arrival result to the server. In response to the store arrival result, the server updates the target order status of the current order to the store arrival status; when the rider completes the meal pickup stage, the user terminal can send the meal pickup result to the server. In response to the meal pickup result, the server updates the target order status of the current order to the meal pickup status; when the rider completes the meal delivery stage, the user terminal can send the delivery result to the server. In response to the delivery result, the server updates the target order status of the current order to the delivered state.

[0283] Through the above process, the server can obtain the rider's real-time parameters and the order parameters associated with the current order.

[0284] S1102: Based on the rider's real-time parameters and / or order parameters, determine in real time whether the first preset condition is met.

[0285] After obtaining the rider's real-time parameters and order parameters, the server can determine whether the first preset condition is met to determine whether a voice reminder is needed for the rider.

[0286] It should be understood that the stages involved in the rider's processing of the current order include arriving at the store, picking up the order, and delivering the order. Different processing stages correspond to different first preset conditions. While the rider is processing the current order, the server can determine in real time whether the first preset condition is met based on the rider's real-time parameters and / or order parameters.

[0287] S1103: When the first preset condition is met, a first voice reminder is automatically triggered to the rider, and the first voice reminder is used to remind whether to execute the target processing action associated with the current order.

[0288] In the embodiment of the present application, different processing stages correspond to different target processing actions, and executing the target processing action means completing the processing stage corresponding to the target processing action. Optionally, the target processing action includes reporting arrival at the store, reporting pickup, and reporting delivery.

[0289] The corresponding action for the arrival phase is "Report Arrival to Store," and executing "Report Arrival to Store" completes the arrival phase. The corresponding action for the pickup phase is "Report Pickup," and executing "Report Pickup to Store" completes the pickup phase. The corresponding action for the delivery phase is "Report Delivery," and executing "Report Delivery to Store" completes the delivery phase. In other words, executing the target action for a given processing phase completes that phase.

[0290] Based on this, during the store arrival phase, the server determines that the first preset condition is met based on real-time parameters and order parameters, and determines that the rider has arrived at the merchant, thereby reminding the rider whether to report to the store. During the meal pickup phase, the server determines that the first preset condition is met based on real-time parameters and order parameters, and determines that the rider has completed meal pickup, thereby reminding the rider whether to report meal pickup. During the meal delivery phase, the server determines that the first preset condition is met based on real-time parameters and order parameters, and determines that the rider has delivered the meal, thereby reminding the rider whether to report delivery.

[0291] Specifically, when prompting the rider to execute the target processing action, the server may send a first voice reminder to the user terminal, which then reads the reminder. The first voice reminder is used to prompt the rider to execute the target processing action associated with the current order. If the target processing action is different, the first preset condition and the content of the first voice reminder will also change accordingly.

[0292] For example, Figure 6 As shown in (a) in the figure, if the target processing action is to report to the store, when the server detects that the first preset condition is met, it will automatically trigger the first voice reminder to the rider - "You have arrived at merchant A (XXX store), do you want to report to the store?"

[0293] S1104: Perform intent recognition on the first voice instruction of the rider in response to the first voice reminder.

[0294] After broadcasting the first voice reminder, the user terminal can obtain the first voice instruction in response to the first voice reminder by the rider, and send the first voice instruction to the server.

[0295] Furthermore, when the user terminal receives the first voice command, in order to ensure the timeliness of the first voice command, the embodiment of the present application can pre-set the waiting time for receiving the first voice command. Figure 4 The preset display duration of the pop-up window 4031 shown in (c) in FIG.

[0296] Optionally, the waiting time for receiving may be 30 seconds.

[0297] In one scenario, if the user terminal receives the first voice command within the waiting time, the first voice command can be sent to the server. After receiving the first voice command, the server can perform intent recognition on the first voice command to determine the purpose of the rider's current expression.

[0298] In one possible implementation, performing intent recognition on the first voice instruction of the rider in response to the first voice reminder includes:

[0299] Perform intent recognition on the first voice command based on the LLM model;

[0300] When intent recognition succeeds, get the intent recognition result.

[0301] When performing intent recognition on the first voice instruction, the server may perform intent recognition through an NLP model, specifically, performing intent recognition on the first voice instruction through a large language model (LLM) model in the NLP model.

[0302] Specifically, when the LLM model is used to perform intent recognition on the first voice command, the server can convert the audio signal of the first voice command into a text string through the ASR model. By performing text cleaning, word segmentation and feature extraction on the text string, the text is split into multiple words and converted into a token sequence that can be recognized by the LLM model. Each word corresponds to the identity identification number (Identity Document, ID) of the trained token. The processed text is spliced ​​with the prompt template of the LLM model as the input of the LLM model. When the intent recognition is successful, the LLM model outputs the probability distribution of each intent category. Among them, the intent category corresponding to the maximum probability in the probability distribution is the intent recognition result.

[0303] S1105: Determine whether to automatically execute the target processing action based on the intention recognition result.

[0304] After successful intent recognition, the intent recognition results include positive results and negative results. A positive result determines that the target processing action will be automatically executed, while a negative result determines that the target processing action will not be automatically executed.

[0305] In one possible implementation, determining whether to automatically execute a target processing action based on an intent recognition result includes:

[0306] When the intention recognition result is to automatically execute the target processing action, a target processing instruction is sent to the user terminal to enable the user terminal to execute the target processing action. The target processing instruction includes execution steps of the target processing action.

[0307] When the rider determines to automatically execute the target processing action, the server can determine the execution steps corresponding to the target processing action based on the target processing action.

[0308] Specifically, the technician can pre-set different target processing actions and the execution steps corresponding to the different target processing actions, and store them in the server. Based on this, the server can query and obtain the corresponding execution steps based on the current target processing action.

[0309] For example, if the target action is to report to the store, after the server performs intent recognition on the first voice command, the intent recognition result is the intent of "confirm to execute report to the store." The server can determine the execution steps of reporting to the store based on the target action.

[0310] like Figure 6 As shown in (c), the execution steps of reporting arrival at the store may be: switching the "Confirm Arrival at Store" control from an activated state to a grayed-out state.

[0311] After determining the execution steps of the target processing action, the server can generate a target processing instruction and send it to the user terminal. In response to the target processing instruction sent by the server, the user terminal can execute the target processing action according to the execution steps corresponding to the target processing action.

[0312] In the above technical solution, after receiving the first voice command, the server can accurately identify the rider's current intention by performing intent recognition on the first voice command. When the rider confirms to automatically execute the target processing action, the server sends the target processing instruction to the user terminal, causing the user terminal to automatically execute the target processing action, reducing human intervention and alleviating the rider's workload. It also provides a flexible way for the rider to execute the target processing action when it is inconvenient for the rider to operate.

[0313] In another possible implementation, determining whether to automatically execute the target processing action based on the intent recognition result includes:

[0314] When the intention recognition result is not to automatically execute the target processing action, a second voice reminder is triggered again to the rider within the second preset time period. The second voice reminder is used to remind the rider whether to execute the target processing action.

[0315] When the rider determines not to automatically perform the target processing action, in order to avoid delays in the execution of the target processing action, the server can give the rider a second voice reminder again after a second preset time period to remind the rider again whether to perform the target processing action.

[0316] Optionally, the second preset time length may be 5 minutes, and the embodiment of the present application does not limit the value of the second preset time length.

[0317] Optionally, the second voice reminder may be the same as or different from the first voice reminder. The embodiment of the present application does not limit the content of the second voice reminder.

[0318] Furthermore, when the intention recognition result is not to automatically execute the target processing action, in order to avoid the rider's disgust, the embodiment of the present application can set the reminder duration or number of reminders.

[0319] For example, the technician can set the preset reminder duration to 10 minutes or the preset reminder frequency to 5. If the user terminal does not perform the target processing operation after the second voice reminder, if the first preset condition is still met, the server can continue to trigger the voice reminder within 10 minutes at the preset reminder frequency, or the server can remind the rider multiple times according to the preset reminder frequency.

[0320] In the above technical solution, when the rider determines not to automatically execute the target processing action, in order to avoid delays in the execution of the target processing action, the server can remind the rider again after a period of time to avoid order timeouts caused by the rider forgetting to execute.

[0321] It should be understood that the above description is based on the current order quantity of 1 for example, but in the actual delivery process, the number of orders that a rider grabs at one time may also be multiple, that is, the number of current orders is multiple. In view of the above situation, the embodiment of the present application has also made further optimizations when reminding.

[0322] In one possible implementation, when the current order quantity is multiple, after determining whether to automatically execute the target processing action based on the intention recognition result, the method further includes:

[0323] The eighth voice reminder is given to the rider, and the eighth voice reminder is used to inquire about the target order that the rider currently needs to process;

[0324] Obtain the fifth voice instruction of the rider in response to the eighth voice reminder, and in response to the fifth voice instruction, determine whether to automatically execute the target processing action of the target order based on the intention recognition result.

[0325] When there are multiple orders, the server may not include the specific order for which the target processing action is currently being executed when sending the first voice reminder. For example, assuming there are three orders, the server will determine that the order parameters and the rider's real-time parameters of one order meet the first preset condition based on the rider's real-time parameters and the order parameters of the three orders. The first voice reminder may read, "We have detected that you have arrived at the merchant. Do you want to report your arrival?"

[0326] In this case, after the first voice instruction recognition of the rider is completed, the server needs to give the rider an eighth voice reminder again to confirm with the rider the target order that currently needs to be processed.

[0327] For example, taking the current number of orders as 3, the corresponding merchant names are "A, B and C", and the eighth voice reminder can be "It is detected that you currently have multiple orders. Which merchant among A, B and C is the target order you need to process?"

[0328] After receiving the fifth voice instruction from the rider in response to the eighth voice reminder, the server can determine the target order that the rider is to process. Further, the server determines whether to automatically execute the target processing action for the target order based on the aforementioned intention recognition result.

[0329] For example, if the target action is to report to the store, the server's recognition result of the first voice command is to automatically execute the report to the store. There are currently three orders, each with merchants named "A, B, and C." The rider identifies the target order as the one for merchant A. Therefore, the server automatically executes the report to the store for merchant A.

[0330] In the above technical solution, when the rider currently has multiple orders to process, after intention recognition, the server can further inquire about the target orders currently to be processed by the rider, avoiding operational errors caused by misselected orders. The rider does not need to manually check the order list for confirmation, which simplifies the order processing process and reduces the complexity of the rider's operations.

[0331] In another embodiment, when there are multiple orders, the server determines that a first preset condition is met based on the rider's real-time parameters and the order parameters of multiple current orders. The server can further determine which order currently meets the first preset condition based on the rider's location and the order parameters of multiple current orders, thereby triggering a first voice reminder to the rider. The first voice reminder includes the name of the order that meets the first preset condition, or the name of the merchant that meets the first preset condition.

[0332] After receiving the first voice instruction from the rider in response to the first voice reminder, the server can perform intent recognition on the first voice instruction and determine whether to automatically execute the target processing action based on the intent recognition result. In this case, the target processing action specifically refers to the target processing action for the order that meets the first preset condition.

[0333] In another scenario, if the user terminal does not receive the first voice instruction or the server fails to recognize the first voice instruction (that is, the first voice instruction does not contain any intention), the server can also remind the rider again.

[0334] In one possible implementation, when the first voice command is not detected or the first voice command intention recognition fails, the method further includes:

[0335] Get the waiting execution time corresponding to the target processing action;

[0336] When the waiting execution time is greater than or equal to the third preset time, a third voice reminder is automatically triggered to the rider, and the third voice reminder is used to remind the rider whether to execute the target processing action;

[0337] A second voice instruction of the rider in response to the third voice reminder is obtained, and in response to the second voice instruction, it is determined whether to automatically execute the target processing action.

[0338] For any target processing action, after the user terminal broadcasts the first voice reminder, if the server does not receive the first voice instruction sent by the user terminal within the waiting time, or the server fails to recognize the intention of the first voice instruction, the server can further obtain the waiting execution time corresponding to the target processing action to determine whether the execution of the target processing action is about to be or has been delayed. Among them, the waiting execution time corresponding to the target processing action refers to the time from the completion of the previous processing action of the target processing action to the completion of the target processing action, that is, the processing time corresponding to the processing stage corresponding to the target processing action.

[0339] For example, if the target action is to report for meal pickup, and the previous action is to report to the store, the waiting execution duration for reporting for meal pickup refers to the time between the completion of reporting to the store and the completion of reporting for meal pickup, i.e., the processing duration for the meal pickup stage.

[0340] After the user completes the store arrival report, it can send the arrival result to the server. The server determines that the store arrival report is complete and enters the pickup phase, with the target action being the pickup report. The server can start counting the waiting time for the pickup report action, starting from the completion of the store arrival report.

[0341] The third preset duration refers to a critical execution duration for determining whether the execution of the target processing action is delayed. Optionally, the third preset durations corresponding to different target processing actions may be the same or different, and this embodiment of the application does not limit this.

[0342] When the waiting execution time of the target processing action is greater than or equal to the third preset time, the server determines that there is a delay in the execution process of the target processing action, and can send a third voice reminder to the user terminal so that the user terminal broadcasts the third voice reminder to remind the rider whether to execute the target processing action.

[0343] Optionally, the third voice reminder may have the same content as the first voice reminder or may be different, which is not limited in this embodiment of the present application.

[0344] For example, Figure 6As shown in (a), the target processing action is to report to the store. After the user terminal broadcasts the first voice reminder - "You have arrived at Merchant A (XXX store), do you want to report to the store?", if the first voice instruction responded by the rider is not detected or the first voice instruction intention recognition fails, the waiting execution time for reporting to the store is obtained. When the waiting execution time is greater than or equal to the third preset time corresponding to reporting to the store, the server determines that there is a delay in the execution process of reporting to the store, and the server can send the third voice reminder to the user terminal again to enable the user terminal to broadcast. For example, the third voice reminder can be "You have arrived at Merchant A (XXX store), do you want to report to the store?", or the third voice reminder can also be "It is detected that there is a delay in your current reporting to the store process, do you want to report to the store?"

[0345] After the user terminal has finished broadcasting the third voice reminder, similar to the process of broadcasting the first voice reminder, the embodiment of the present application can also set the waiting time for receiving the second voice instruction. Optionally, the waiting time for receiving can be the same as the waiting time for receiving the first voice instruction, or it can be different, and the embodiment of the present application does not limit this.

[0346] When the rider responds to the second voice command, after the server receives the second voice command sent by the user end, it can perform intent recognition on the second voice command in the same way as the first voice command to determine whether to automatically execute the target processing action.

[0347] When the second voice command intention is successfully recognized, if the intention recognition result is to automatically execute the target processing action, the server can send the target processing instruction to the user terminal to enable the user terminal to execute the target processing action. If the intention recognition result is not to automatically execute the target processing action, or the second voice command is not detected, or the second voice command intention recognition fails, the server can continue to provide voice reminders to the rider at the preset reminder frequency.

[0348] In the above technical solution, if the rider does not respond or the intent recognition fails, the server can determine whether the execution process of the current target processing action has timed out based on the waiting time for the target processing action. If the timeout is about to occur, the rider will be proactively reminded, reducing the psychological burden caused by the timeout.

[0349] Furthermore, when the server does not detect the first voice command or fails to recognize the intention of the first voice command, in order to avoid false detection caused by environmental factors, the server can first give a voice reminder to the rider before obtaining the waiting execution time.

[0350] In one possible implementation, when the first voice command is not detected or the first voice command intention recognition fails, the method further includes:

[0351] Automatically trigger the rider to confirm the intention, which is used to remind the rider whether to execute the target processing action;

[0352] Performing intention recognition on the rider's intention confirmation instruction in response to the intention confirmation reminder;

[0353] When the intention recognition result of the intention confirmation instruction is not to automatically execute the target processing action, or the intention confirmation instruction is not detected, or the intention confirmation instruction recognition fails, the waiting execution time corresponding to the target processing action is obtained;

[0354] When the waiting execution time is greater than or equal to the third preset time, a third voice reminder is automatically triggered to the rider, and the third voice reminder is used to remind the rider whether to execute the target processing action;

[0355] A second voice instruction of the rider in response to the third voice reminder is obtained, and in response to the second voice instruction, it is determined whether to automatically execute the target processing action.

[0356] In this way, when the server detects that the real-time parameters and / or order parameters meet the first preset conditions and issues the first voice reminder to the rider for the first time, if the server does not receive the first voice instruction, it may be because the environment is too noisy or the rider's voice is too soft, and the user end did not detect the first voice instruction. Alternatively, it may be because the rider's expression is unclear or the rider speaks in dialect, resulting in the server's intention recognition failure. In both cases, the server can issue another intention confirmation reminder to the rider to eliminate the influence of the above uncertain factors.

[0357] Optionally, the intention confirmation reminder may have the same content as the second voice reminder, or may have different content.

[0358] For example, Figure 6 As shown in (a), the target processing action is to report to the store. After the user terminal broadcasts the first voice reminder - "You have arrived at merchant A (XXX store), do you want to report to the store?", if the first voice instruction responded by the rider is not detected or the first voice instruction intention recognition fails, the server will send the intention confirmation reminder to the user terminal so that the user terminal can broadcast it. For example, the intention confirmation reminder can be "You have arrived at merchant A (XXX store), do you want to report to the store?", or the intention confirmation reminder can also be "Your reply voice was not detected, do you want to report to the store?", or the intention confirmation reminder can also be "Sorry, I don't understand what you mean, do you want to report to the store?"

[0359] Similar to the subsequent process of the first voice reminder, when the server does not receive the intention confirmation instruction in response from the rider, or the intention confirmation instruction fails to be recognized, or the intention confirmation instruction is not to automatically execute the report to the store, it means that the rider is not sure to automatically execute the report to the store. The server can further obtain the waiting execution time for reporting to the store to determine whether a timeout reminder is needed.

[0360] After introducing the overall implementation process of the embodiment of the present application, the detailed process of the condition judgment process and the processing process corresponding to each target processing action will be introduced below.

[0361] It should be understood that the target processing actions include reporting arrival at the store, reporting pickup, and reporting delivery. Steps S1102 to S1105 can be applied to the conditional judgment process and processing process of any target processing action.

[0362] (1) The target processing action is reporting to the store

[0363] (1) Condition judgment process

[0364] When a rider is on his way to a merchant, the server can use the rider's location and the merchant's location to determine whether to report the arrival at the store.

[0365] In one possible implementation, the target processing action includes reporting to the store, the rider's real-time parameters include the rider's location, and the order parameters include the merchant's location and the target order status. When the target order status is "claimed" and at least one of the following conditions is met, it is determined that the first preset condition is met:

[0366] The rider's location is within the coverage area of ​​the first signal associated with the merchant's location;

[0367] The rider's location is within the first preset range associated with the merchant's location;

[0368] The distance between the rider's location and the merchant's location is less than or equal to a first preset distance.

[0369] When the target processing action is to report to the store, when the server determines whether the first preset condition is met, the rider's real-time parameters include the rider's location, and the order parameters include the merchant's location and the target order status.

[0370] When the rider is on their way to the merchant, it means that the current rider has already grabbed the order. Therefore, the target order status of the current order is the grabbed order status. In the grabbed order status, the server can further combine the following three methods to determine whether the first preset condition is met.

[0371] The first method is to determine whether the rider's location is within the coverage of a first signal associated with the merchant's location. The first signal refers to a wireless signal set up at the merchant's location.

[0372] Optionally, the wireless signal includes a Wireless Fidelity (WiFi) signal and a beacon signal of a Bluetooth beacon.

[0373] The received signal strength indicator (RSSI) of the wireless signal is closely related to the distance. In an embodiment of the present application, when the target processing action is to report to the store, the distance refers to the distance between the rider and the merchant. Regardless of whether the wireless signal is a WiFi signal or a beacon signal, according to the relationship between the RSSI of the signal and the distance, the farther the rider is from the merchant, the smaller the RSSI of the wireless signal; the closer the rider is to the merchant, the larger the RSSI of the wireless signal.

[0374] Therefore, in the embodiment of the present application, the coverage area of ​​the first signal can be set according to the RSSI of the first signal. The coverage area of ​​the first signal specifically refers to an area where the RSSI of the first signal is greater than or equal to a first preset RSSI.

[0375] Optionally, depending on the wireless signal, the first preset RSSI includes a first preset RSSI corresponding to a WiFi signal and / or a first preset RSSI corresponding to a beacon signal. The first preset RSSI corresponding to the WiFi signal may be the same as or different from the first preset RSSI corresponding to the beacon signal, and this is not limited in this embodiment of the present application.

[0376] When the rider is heading to the merchant, the user terminal will automatically scan the various WiFi signals near the rider's location, obtain the RSSI of each WiFi signal, and send it to the server. After obtaining the RSSI of each WiFi scanned by the user terminal, the server can match the WiFi signal identifier of each WiFi signal with the merchant's WiFi signal identifier. After matching, the server determines whether the RSSI of the merchant's WiFi signal scanned by the user terminal is greater than the first preset RSSI corresponding to the WiFi signal. If so, the server determines that the rider's location is in the coverage area of ​​the first signal, that is, the rider has arrived at the merchant.

[0377] Alternatively, if a Bluetooth beacon is configured at the merchant, it will periodically broadcast a beacon signal. The user end can receive the broadcast signal from the Bluetooth beacon, obtain the RSSI of the beacon signal, and send it to the server. The server can determine whether the RSSI of the beacon signal is greater than or equal to the first preset RSSI corresponding to the beacon signal. If so, the server determines that the rider's location is within the coverage of the first signal, that is, the rider has arrived at the merchant.

[0378] The second method is to determine whether the rider's position is within the first preset range associated with the merchant's location. The first preset range refers to the area of ​​interest (AOI) corresponding to the merchant's location. AOI refers to a specific area or range of interest in a specific scenario, which is generally divided artificially. In this embodiment of the present application, the AOI associated with the merchant's location is an area centered on the merchant's location and composed of various locations within the first preset distance interval from the merchant's location.

[0379] When an AOI is set at the merchant location, the server can match the rider's location with each location within the AOI associated with the merchant location. If a match is successful, the server determines that the rider's location is within the first preset range, that is, the rider has arrived at the merchant.

[0380] The third method is to determine whether the distance between the rider's location and the merchant's location is less than or equal to a first preset distance. Optionally, the first preset distance is 10m, 20m, 100m, 200m, etc. The embodiment of the present application does not limit the value of the first preset distance.

[0381] After the server obtains the rider's location and the merchant's location, it can determine the distance between the rider's location and the merchant's location in real time. If the distance is greater than a first preset distance, it indicates that the rider is currently far away from the merchant. If the distance is less than or equal to the first preset distance, the server determines that the rider has arrived at the merchant.

[0382] When the target order status is the grabbed order status, and the server determines that the rider has arrived at the merchant through any method, it can be determined that the first preset condition is met.

[0383] In the above technical solution, when judging whether the rider has arrived at the merchant, a comprehensive judgment is made through multiple conditions, which can accurately determine from multiple dimensions whether to report the rider to the store. This improves the accuracy of the judgment and timing of the reminder to report to the store, making the execution process of reporting to the store more precise.

[0384] Furthermore, when entering a store, the rider generally switches from outdoors to indoors. When determining whether the rider has arrived at the store using any of the three methods mentioned above, it can also be combined with whether the rider's location is indoors. Taking the first method as an example, when the server detects that the rider's location is within the coverage area of ​​the first signal associated with the merchant's location, if the rider's location is determined to be indoors, then the rider is determined to have arrived at the merchant.

[0385] The server can obtain whether the rider's location is indoors or outdoors in the following way.

[0386] For example, the server can determine whether the rider's location is indoors or outdoors by matching the rider's location with the location on the map.

[0387] As another example, when a rider is rushing to a store, the server can obtain the RSSI of the WiFi signal scanned by the user end and determine whether the rider is indoors or outdoors based on the RSSI value. If the RSSI value is large, the rider is determined to be indoors; if the RSSI value is small, the rider is determined to be outdoors.

[0388] In another exemplary embodiment, the server may further obtain the rider's motion state and determine whether the rider is indoors or outdoors based on the rider's motion state. Optionally, the rider's motion state includes walking, riding, or stationary.

[0389] Specifically, the user terminal is generally equipped with an acceleration sensor. In the embodiment of the present application, different acceleration ranges corresponding to different motion states can be pre-set. The server can obtain the rider's acceleration through the acceleration sensor and compare the acceleration with the above-mentioned different acceleration ranges to determine the rider's motion state.

[0390] When the rider's motion state is riding, the server determines that the rider's position is outdoors; when the rider's motion state is walking or stationary, the server determines that the rider's position is indoors.

[0391] Furthermore, in order to avoid and eliminate abnormal fluctuations caused by coordinate drift or sensor noise, the embodiment of the present application also proposes a correction strategy for the rider's position.

[0392] The server can obtain the rider's position within a certain period of time obtained in the above manner. The rider's position within a certain period of time constitutes a position sequence. For example, the position sequence within a certain period of time may be "indoor, indoor, indoor, outdoor, indoor, indoor, indoor".

[0393] As shown in the example above, the location sequence "outdoor" may indicate abnormal location fluctuations caused by coordinate drift or sensor noise. To eliminate these abnormal fluctuations, the server corrects the location sequence to "indoor, indoor, indoor, indoor, indoor, indoor, indoor."

[0394] In addition, if at the same time, the server determines that the rider's motion state is riding, the rider's location is determined to be outdoor based on the rider's motion state. If the rider's location is determined to be indoor based on the geographic location, the server ultimately determines that the rider's location is outdoor.

[0395] Similarly, if at the same moment, the server determines that the rider's motion state is stationary, then the rider's location is determined to be indoors based on the rider's motion state. However, if the rider's location is determined to be outdoor based on the geographic location, but the RSSI of the WiFi signal is strong, then the server ultimately determines that the rider's location is indoors.

[0396] Based on this, when the target order status is the grabbed order status and meets at least one of the following conditions, it is determined that the first preset condition is met:

[0397] The rider's location is within the coverage area of ​​the first signal associated with the merchant's location, and the rider's location is indoors;

[0398] The rider's location is within the first preset range associated with the merchant's location, and the rider's location is indoors;

[0399] The distance between the rider's location and the merchant's location is less than or equal to a first preset distance, and the rider's location is indoors.

[0400] When the target order status is the grabbed order status, and the server determines that the rider has arrived at the merchant through any method, it can be determined that the first preset condition is met.

[0401] (2) Voice reminder process

[0402] When the target processing action is to report to the store, the server determines that the first preset condition is met and can send a first voice reminder to the user terminal so that the user terminal can broadcast it through the AI ​​smart assistant to remind the rider whether to execute the report to the store associated with the current order. The first voice reminder is specifically a reminder to report to the store, that is, Figure 6 The voice prompt for reporting to the store.

[0403] Optionally, when the user terminal plays the reminder to report to the store through the AI ​​smart assistant, the user terminal can also synchronously display the text corresponding to the reminder to report to the store.

[0404] For example, Figure 6 As shown in (a), the merchant name is Merchant A (XXX Store), and the merchant location is the storefront at Unit X, Floor X, No. X, Row X, District X, XX City, XX Province. When the rider is heading to the merchant, if the server determines that the rider's location and the merchant's location are 12m apart, a reminder to report to the store can be sent to the user terminal, so that the user terminal can broadcast it through the AI ​​smart assistant. Correspondingly, the user terminal can also display a pop-up window 6011 on the display interface 601. The pop-up window 6011 includes the text corresponding to the reminder to report to the store - "You have arrived at Merchant A (XXX Store), do you want to report to the store?" The AI ​​smart assistant also broadcasts the voice of "You have arrived at Merchant A (XXX Store), do you want to report to the store?"

[0405] (3) Intent Recognition Process

[0406] After the reminder to report to the store is played, if the user terminal receives the first voice instruction of the rider for the reminder to report to the store, the first voice instruction can be sent to the server. The server recognizes the intention of the first voice instruction to determine whether to automatically execute the report to the store. The first voice instruction is specifically the reply voice of the reminder to report to the store, that is, Figure 6The reply voice message for the store visit notification.

[0407] Please refer to the above description for the specific intent recognition process, which will not be repeated here.

[0408] If the server successfully recognizes the voice response to the store report reminder, and the recognized intent is to automatically execute the store report, the server can determine the steps for executing the store report and send them to the user terminal in the form of target processing instructions for execution. The target processing instructions here are the store report processing instructions mentioned above.

[0409] For example, Figure 6 As shown in (b) of the figure, the rider's voice reply is "Please help me report to the store." After the server recognizes the intent of the voice reply, it automatically executes the store report. The server can determine that the steps for executing the store report are: switching the interactive state of the "Confirm Arrival" control from active to grayed out, and switching the text label of the "Confirm Arrival" control from "Confirmed Arrival" to "Arrived." Based on this execution step, the server generates a target processing instruction and sends it to the user.

[0410] like Figure 6 As shown in (c), in the display interface 603, after receiving the target processing instruction, the user terminal can switch the interactive state of the "Confirm Arrival at Store" control from the activated state to the grayed state according to the execution steps of reporting arrival at the store, and switch the text label of the "Confirm Arrival at Store" control from "Confirmed Arrival at Store" to "Arrived at Store".

[0411] (4) Exception handling process

[0412] In another scenario, when the intention recognition result is not to automatically execute the target processing action, the server can send a second voice reminder to the user terminal for broadcast after a second preset time period.

[0413] Optionally, the second voice reminder can be the same as the store report reminder. Figure 6 As shown in (a) in the figure, the second voice reminder may be "You have arrived at Merchant A (XXX Store). Do you want to check in?" Alternatively, the second voice reminder may be different from the check-in reminder. For example, the second voice reminder may be "It is detected that you have met the check-in conditions. To avoid a check-in timeout, do you want to check in?"

[0414] In another scenario, if the server does not detect the first voice command, or the first voice command intention recognition fails, it means that the rider has not yet decided to automatically execute the report to the store. The server can obtain the waiting execution time for reporting to the store to determine whether there is a delay in the execution process of reporting to the store.

[0415] If the server determines that the waiting time for reporting to the store is greater than or equal to the third preset time period corresponding to reporting to the store, the server sends a third voice reminder to the user terminal, so that the user terminal can read it through the AI ​​smart assistant. The third voice reminder is used to remind the user whether to report to the store.

[0416] Optionally, the third voice reminder may be the same as the store report reminder or may be different, and this embodiment of the present application does not limit this.

[0417] For example, Figure 6 As shown in (a), the target processing action is to report to the store. After the user terminal broadcasts the reminder of reporting to the store - "You have arrived at Merchant A (XXX store), do you want to report to the store?", if the first voice instruction responded by the rider is not detected or the first voice instruction intention recognition fails, the waiting execution time for reporting to the store is obtained. When the waiting execution time is greater than or equal to the third preset time corresponding to reporting to the store, the server determines that there is a delay in the execution process of reporting to the store, and the server can send the third voice reminder to the user terminal again to enable the user terminal to broadcast. For example, the third voice reminder can be "You have arrived at Merchant A (XXX store), do you want to report to the store?", or the third voice reminder can also be "It is detected that there is a delay in your current reporting to the store process, do you want to report to the store?"

[0418] After the user terminal broadcasts the third voice reminder, if the user terminal receives the second voice instruction of the rider in response to the third voice reminder, after the server receives the second voice instruction sent by the user terminal, it can perform intent recognition on the second voice instruction in the same way as the first voice instruction to determine whether to automatically execute the report to the store.

[0419] When the second voice command is successfully recognized, and the result of the recognition is to automatically report the vehicle to the store, the server can send the target processing instruction to the user terminal to enable the user terminal to execute the report to the store. If the result of the recognition is not to automatically report the vehicle to the store, or the second voice command is not detected, or the recognition of the second voice command fails, the server can continue to provide voice reminders to the rider at the preset reminder frequency.

[0420] After the server sends the target processing instruction to the user terminal through the above process, the user terminal can feedback the execution completion result to the server after executing the execution step of reporting to the store in response to the target processing instruction of the server.

[0421] For example, Figure 6As shown in (c) in the figure, if the user terminal has already reported the delivery to the store for the rider, the display interface 603 will display a pop-up window 6031, which will display the prompt text "The delivery has been reported to the store for you", and the AI ​​smart assistant will simultaneously play the prompt voice "The delivery has been reported to the store for you". Furthermore, the user terminal can also send the result of "Delivery has arrived at the store" to the server. In response to this result, the server determines that the target order status has been updated from the "Order has been grabbed" status to the "Delivery has arrived at the store" status, thus entering the pickup phase.

[0422] (2) The target processing action is to report and pick up the meal

[0423] (1) Condition judgment process

[0424] When the rider is on his way to the merchant, the server can use the following process to determine whether to report the meal pickup.

[0425] In one possible implementation, the target processing action includes reporting a meal pickup. The rider's real-time parameters include the rider's arrival time and location. The order parameters include the merchant's meal delivery status, merchant location, and target order status. When the target order status is "arrived at the store" and at least one of the following conditions is met, the first preset condition is determined to be met:

[0426] The rider's arrival time at the store is greater than or equal to the first preset time;

[0427] The merchant's meal delivery status is "Delivered";

[0428] The rider arrives at the merchant's location and then moves away from the merchant's location, and the merchant's meal delivery status is already delivered.

[0429] Specifically, when the target action is to report a meal pickup, the server determines whether the first pre-set condition is met. The rider's real-time parameters include not only the rider's location but also the rider's arrival time. The order parameters include not only the merchant's location and the target order status but also the merchant's meal delivery status.

[0430] For example, when the server detects that the target order status is "arrived at the store," it indicates that the current order processing phase has reached the meal pickup phase. The server can use the moment when the target order status is "arrived at the store" as the starting moment to time the rider's arrival time. During the period when meal pickup is not reported, the server calculates the time between the above starting moment and the current moment to obtain the rider's arrival time. The rider's arrival time is the time the rider waits to pick up the meal.

[0431] Regarding the merchant's meal delivery status, after the user completes the order, the server will generate a QR code based on the order parameters and send it to the merchant. Based on this QR code, when the merchant has finished delivering the meal, it can scan the QR code to send a meal delivery completion signal to the server, which is used to indicate that the meal delivery status has been delivered. Therefore, during the order processing process, if the server receives a meal delivery completion signal, it determines that the merchant's meal delivery status has been delivered. On the contrary, if the server does not receive a meal delivery completion signal, it determines that the merchant's meal delivery status has not been delivered.

[0432] When the rider arrives at the store and waits to pick up the food, it means that the current rider has arrived at the store. Therefore, the target order status of the current order is the arrived state. In the arrived state, the server can further combine the following three methods to determine whether the first preset condition is met.

[0433] The first method is to determine whether the rider’s arrival time at the store is greater than or equal to the first preset time.

[0434] Optionally, the first preset time is the normal time it takes for a merchant to serve a meal. For example, the first preset time may be 10 minutes.

[0435] The server can compare the rider's arrival time with the first preset time. If the rider's arrival time is greater than or equal to the first preset time, it is considered that the rider has picked up the meal.

[0436] The second method is to determine whether the merchant’s food delivery status is already delivered.

[0437] During the meal pickup process, the server can detect in real time whether it has received the meal delivery completion signal sent by the merchant. If the delivery completion signal is detected, the merchant's meal delivery status is determined to be delivered, and the server determines that the rider has received the meal.

[0438] The third method is to judge based on the merchant’s food delivery status, merchant location and rider location.

[0439] During the rider's meal pickup process, the rider's location coincides with or is very close to the merchant's location; on the contrary, when the rider's location is far away from the merchant's location, it means that the rider may have already picked up the meal and left the merchant.

[0440] If the server detects that the driver has arrived at the merchant's location first, it means that the driver is waiting to pick up the food. If the server further detects that the driver has moved away from the merchant's location, it means that the driver has left the merchant. In this case, if the server also obtains the merchant's food delivery status as delivered, it means that the driver has already picked up the food and just left the merchant.

[0441] When the target order status is "arrived at the store" and the server determines in any way that the rider has picked up the food, it can be determined that the first preset condition is met.

[0442] In the above technical solution, after the order is reported to the store, during the rider's meal pickup process, the need for a store report is automatically determined based on the rider's arrival time, the merchant's meal delivery status, and the rider's and merchant's locations. This multi-dimensional parameter combination not only improves the accuracy of store report reminders, but also reduces the tediousness of manual operations and the probability of forgetting to report to the store through automated triggering of reminders, thus avoiding delays in the order delivery process and improving the rider's delivery efficiency.

[0443] (2) Voice reminder process

[0444] When the target processing action is to report and pick up the meal, and the server determines that the first preset condition is met, the first voice reminder can be sent to the user terminal, so that the user terminal can broadcast it through the AI ​​smart assistant to remind the rider whether to execute the report and pick up the meal associated with the current order. The first voice reminder is specifically a reminder to report and pick up the meal, that is, Figure 7 The voice prompt for reporting meal pickup.

[0445] Optionally, when the user terminal plays the reminder to report the meal pickup through the AI ​​smart assistant, the user terminal can also synchronously display the text corresponding to the reminder to report the meal pickup.

[0446] For example, Figure 7 As shown in (a) in the figure, when the rider is waiting for the meal to be served, if the server determines that the rider's waiting time for the meal has reached a first preset time, it can send a reminder to report the meal to the user terminal, which will be announced by the user terminal through the AI ​​smart assistant. Correspondingly, the user terminal can also display a pop-up window 7011 on the display interface 701. The pop-up window 7011 includes the text corresponding to the reminder to report the meal - "It is detected that you have been waiting for a long time to pick up the meal. Do you want to report the meal for you?" The AI ​​smart assistant also broadcasts the voice message "It is detected that you have been waiting for a long time to pick up the meal. Do you want to report the meal for you?"

[0447] (3) Intent Recognition Process

[0448] After the reminder to report the meal is broadcast, if the user terminal receives the first voice instruction from the rider for the reminder to report the meal, the first voice instruction can be sent to the server. The server further performs intent recognition on the first voice instruction to determine whether to automatically execute the report to pick up the meal. When the target processing action is to report the meal, the first voice instruction is specifically the reply voice of the reminder to report the meal, that is, Figure 7 The reply voice message for the report pickup reminder.

[0449] Please refer to the above description for the specific intent recognition process, which will not be repeated here.

[0450] If the server successfully recognizes the first voice command's intent, and the successful recognition of the intent is to automatically execute the meal pickup report, the server can determine the execution steps for the meal pickup report and send them to the user terminal in the form of a target processing instruction for execution. The target processing instruction here is the aforementioned meal pickup report processing instruction.

[0451] For example, Figure 7 As shown in (b) of the figure, the rider's voice reply is "Please help me report the pickup." After the server recognizes the intent of the reply, it automatically executes the pickup request. The server can determine that the execution steps for the pickup request are: switching the interactive state of the "Pick Up" control from active to grayed out, and switching the text label of the "Pick Up" control from "Pick Up" to "Picked Up." Based on this execution step, the server generates a target processing instruction and sends it to the user.

[0452] like Figure 7 As shown in (c), in the display interface 703, after receiving the target processing instruction, the user terminal can switch the interactive state of the "Pick up" control from the active state to the gray state according to the execution steps of reporting the meal pickup, and switch the text label of the "Pick up" control from "Pick up" to "Picked up".

[0453] (4) Exception handling process

[0454] In another scenario, when the intention recognition result is not to automatically execute the target processing action, the server can send the second voice reminder to the user terminal again after the second preset time period, so that the user terminal can broadcast it.

[0455] Optionally, the second voice reminder can be the same as the reminder for reporting meal pickup. Figure 7 As shown in (a) above, the second voice reminder may be, "We have detected that you have been waiting for a long time to pick up your meal. Do you want to report your meal for pickup?" Alternatively, the second voice reminder may be different from the reminder for reporting your meal for pickup. For example, the second voice reminder may be, "We have detected that you have met the conditions for reporting your meal for pickup. To avoid a timeout for reporting your meal for pickup, do you want to report your meal for pickup?"

[0456] In another scenario, if the server does not detect the first voice command, or fails to recognize the intent of the first voice command, it means that the rider has not yet confirmed the automatic execution of the report for pickup. The server can obtain the waiting execution time for the report for pickup to determine whether there is a delay in the execution process of the report for pickup. Among them, the waiting execution time for the report for pickup is the aforementioned length of time the rider arrives at the store or waits for pickup.

[0457] When the server determines that the waiting time for reporting and picking up the meal is greater than or equal to the third preset time, the server sends a third voice reminder to the user terminal, so that the user terminal can read it through the AI ​​smart assistant. The third voice reminder is used to remind whether to execute the report and pick up the meal.

[0458] Optionally, the third voice reminder may be the same as or different from the content of the reported meal pickup reminder, and this embodiment of the present application does not limit this.

[0459] For example, Figure 7 As shown in (a), the target processing action is to report meal pickup. After the user terminal broadcasts the reminder for reporting meal pickup - "It is detected that you have been waiting for meal pickup for a long time, do you want to report meal pickup for you", if the first voice instruction responded by the rider is not detected or the first voice instruction intention recognition fails, the waiting execution time for reporting meal pickup is obtained. When the waiting execution time is greater than or equal to the third preset time corresponding to reporting meal pickup, the server determines that there is a delay in the execution process of reporting meal pickup, and the server can send the third voice reminder to the user terminal again to enable the user terminal to broadcast. For example, the third voice reminder can be "It is detected that you have been waiting for meal pickup for a long time, do you want to report meal pickup for you", or the third voice reminder can also be "It is detected that there is a delay in your current reporting meal pickup process, do you want to report meal pickup for you".

[0460] After the user terminal broadcasts the third voice reminder, if the user terminal receives the second voice instruction of the rider in response to the third voice reminder, after the server receives the second voice instruction sent by the user terminal, it can perform intent recognition on the second voice instruction in the same way as the first voice instruction to determine whether to automatically execute the report for picking up the meal.

[0461] If the second voice command is successfully recognized, and the result of the recognition is to automatically report and pick up the meal, the server can send the target processing instruction to the user terminal to enable the user terminal to execute the report and pick up the meal. If the result of the recognition is not to automatically report and pick up the meal, or the second voice command is not detected, or the recognition of the second voice command fails, the server can continue to provide voice reminders to the rider at the preset reminder frequency.

[0462] After the server sends the target processing instruction to the user terminal through the above process, the user terminal can feedback the execution result to the server after executing the execution step of reporting the meal pickup in response to the target processing instruction of the server.

[0463] For example, Figure 7As shown in (c) of the figure, if the user has already reported the order for the rider to pick up the food, a pop-up window 7031 will appear on the display interface 703. This pop-up window 7031 displays the text "The order has been reported for pickup," and the AI ​​assistant simultaneously broadcasts the voice prompt "The order has been reported for pickup." Furthermore, the user can also send the pickup result to the server. In response to this result, the server determines that the target order status has been updated from the "Delivered to the Store" status to the "Picked Up" status, thus entering the delivery phase.

[0464] In another scenario, for at least one of the two target processing actions of reporting arrival at the store or reporting meal pickup, if the server does not detect the first voice command, or fails to recognize the intent of the first voice command, the server may determine whether there is a delay in the execution of the target processing action by not only the waiting execution time of the target processing action but also by location matching.

[0465] In one possible implementation, the target processing action includes reporting arrival at the store and / or reporting pickup. When the first voice command is not detected or the first voice command fails to be recognized, the method further includes:

[0466] Get the location of the rider, the merchant, and the user to be delivered;

[0467] When the distance between the rider's location and the merchant's location is greater than or equal to the third preset distance, and the distance between the rider's location and the user's location is less than or equal to the fourth preset distance, a fourth voice reminder is automatically triggered to the rider, and the fourth voice reminder is used to remind the rider whether to report to the store and / or report to pick up the meal;

[0468] Obtain a third voice instruction in which the rider responds to the fourth voice reminder, and determine whether to automatically execute reporting to the store and / or reporting to pick up the meal in response to the third voice instruction.

[0469] In the first case, when the target processing action is to report to the store, if the server does not receive the first voice command or fails to recognize the first voice command, the rider location, merchant location and user location to be delivered can be obtained.

[0470] If the server does not execute the report to the store, if the server detects that the distance between the rider's location and the merchant's location is greater than or equal to the third preset distance, and the distance between the rider's location and the user's location is less than or equal to the fourth preset distance, it means that the rider is currently far away from the merchant and close to the user, that is, the rider is on the way to deliver the food. This situation indicates that there is a delay in the execution process of reporting to the store. The server sends the fourth voice reminder to the user terminal, so that the user terminal broadcasts it to prompt the rider whether to execute the report to the store.

[0471] Optionally, the fourth voice reminder may be the same as or different from the store arrival report reminder and / or the third voice reminder when the target processing action is store arrival report. For example, the fourth voice reminder may be "A delay has been detected in your store arrival report. Do you want to report your store arrival?"

[0472] After receiving the rider's third voice instruction for the fourth voice reminder, the server can perform intent recognition on the third voice instruction in the same way as the first and second voice instructions to determine whether to automatically report it to the store.

[0473] In the second case, when the target processing action is to report the meal pickup, if the server does not receive the first voice command or fails to recognize the first voice command, it can also obtain the rider location, merchant location and user location to be delivered.

[0474] In the case that the server does not execute the report to pick up the meal, if the server detects that the distance between the rider's position and the merchant's position is greater than or equal to the third preset distance, and the distance between the rider's position and the user's position is less than or equal to the fourth preset distance, it means that the rider is currently far away from the merchant and close to the user, that is, the rider is on the way to deliver the meal. This situation not only indicates that there is a delay in the execution process of reporting to the store, but also that there is a delay in the execution process of reporting to pick up the meal. The server sends the fourth voice reminder to the user terminal, so that the user terminal broadcasts it to prompt the rider whether to execute the report to pick up the meal.

[0475] Optionally, the fourth voice reminder may be the same as or different from the reminder for reporting meal pickup and / or the third voice reminder when the target processing action is reporting meal pickup. For example, the fourth voice reminder may be "A delay has been detected in your current reporting of meal pickup. Do you want to report your meal pickup?"

[0476] After receiving the rider's third voice instruction in response to the fourth voice reminder, the server can perform intent recognition on the third voice instruction in the same way as the first and second voice instructions to determine whether to automatically report the meal pickup.

[0477] In the third case, when the target action is to report to the store or to report for pickup, unlike the two previous cases, this indicates that the rider has not confirmed the automatic execution of either reporting to the store or reporting for pickup. Therefore, the first voice reminder corresponding to the first voice command may be a reminder to report for pickup, or a reminder to report for pickup and a reminder to report to the store.

[0478] When the server does not detect the first voice command or fails to recognize the intent of the first voice command, the server can obtain the rider location, the merchant location, and the location of the user to be delivered.

[0479] If the server detects that the distance between the rider's location and the merchant's location is greater than or equal to the third preset distance, and the distance between the rider's location and the user's location is less than or equal to the fourth preset distance, it means that the rider is currently far away from the merchant and close to the user, that is, the rider is on the way to deliver the food. This situation indicates that there is a delay in the execution process of reporting to the store and the execution process of reporting to pick up the food. The server sends the fourth voice reminder to the user terminal, so that the user terminal broadcasts it to prompt the rider whether to execute the report to the store and report to pick up the food.

[0480] After receiving the rider's third voice instruction in response to the fourth voice reminder, the server can perform intent recognition on the third voice instruction in the same way as the first and second voice instructions to determine whether to automatically execute the report to the store and the report to pick up the meal.

[0481] In the above technical solution, when the target processing action is at least one of reporting to the store and reporting to pick up the food, when the rider does not respond or the intention recognition fails, if the server determines through distance detection that the rider is on the way to deliver the food, it can intelligently remind the rider to report to the store and / or report to pick up the food in time, thereby reducing the serious order timeout problem caused by process omissions.

[0482] (3) The target processing action is reporting and delivery

[0483] (1) Condition judgment process

[0484] When the rider is on the way to the merchant, the server can determine whether to report the delivery in the following way.

[0485] In one possible implementation, the target processing action includes reporting delivery, the rider's real-time parameters include the rider's location, and the order parameters include the location of the user to be delivered and the target order status. When the target order status is "picked up" and at least one of the following conditions is met, the first preset condition is determined to be met:

[0486] The rider's position is within the coverage area of ​​the second signal associated with the user's position;

[0487] The rider's position is within a second preset range associated with the user's position;

[0488] The distance between the rider position and the user position is less than or equal to a second preset distance.

[0489] When the target processing action is to report and deliver, when the server determines whether the first preset condition is met, the rider's real-time parameters include the rider's location, and the order parameters include the user location associated with the current order and the target order status.

[0490] When the rider is on the way to deliver the food, it means that the current rider has already picked up the food. Therefore, the target order status of the current order is the Picked Up status. In the Picked Up status, the server can further combine the following three methods to determine whether the first preset condition is met.

[0491] The first method is to determine whether the rider's location is within the coverage of a second signal associated with the user's location. The second signal refers to a wireless signal set at the user's location.

[0492] Optionally, the wireless signal includes a WiFi signal and a beacon signal of a Bluetooth beacon.

[0493] Similar to the setting method of the coverage area of ​​the first signal, the embodiment of the present application can set the coverage area of ​​the second signal according to the RSSI of the second signal. The coverage area of ​​the second signal specifically refers to the area where the RSSI of the second signal is greater than or equal to the second preset RSSI.

[0494] Optionally, depending on the wireless signal, the second preset RSSI includes a second preset RSSI corresponding to a WiFi signal and / or a second preset RSSI corresponding to a beacon signal. The second preset RSSI corresponding to the WiFi signal may be the same as or different from the second preset RSSI corresponding to the beacon signal, and this is not limited in this embodiment of the present application.

[0495] When the rider is delivering food, the user terminal will automatically scan the various WiFi signals near the rider's location, obtain the RSSI of each WiFi signal, and send it to the server. After obtaining the RSSI of each WiFi scanned by the user terminal, the server can match the WiFi signal identifier of each WiFi signal with the user's WiFi signal identifier. After matching, the server determines whether the RSSI of the user WiFi signal scanned by the user terminal is greater than the second preset RSSI corresponding to the WiFi signal. If so, the server determines that the rider's location is within the coverage area of ​​the second signal, that is, the rider has arrived at the user.

[0496] Alternatively, if a Bluetooth beacon is configured at the user's location, the Bluetooth beacon will periodically broadcast a beacon signal. The user can receive the broadcast signal from the Bluetooth beacon, obtain the RSSI of the beacon signal, and send it to the server. The server can determine whether the RSSI of the beacon signal is greater than or equal to the second preset RSSI corresponding to the beacon signal. If so, the server determines that the rider's location is within the coverage of the second signal, that is, the rider has arrived at the user's location.

[0497] The second method is to determine whether the rider's position is within a second preset range associated with the user's position. The second preset range refers to the AOI corresponding to the user's position. The AOI associated with the user's position is an area centered on the user's position and consisting of all positions within the second preset distance interval from the user's position.

[0498] When an AOI is set at the user's location, the server can match the rider's location with each location within the AOI associated with the user's location. If a match is successful, the server determines that the rider's location is within the second preset range, that is, the rider has arrived at the user.

[0499] The third method is to determine whether the distance between the rider's position and the user's position is less than or equal to a second preset distance. Optionally, the second preset distance can be the same as or different from the first preset distance. For example, the second preset distance can be 100m, 200m, 50m, etc. The embodiment of the present application does not limit the value of the second preset distance.

[0500] After the server obtains the rider's location and the user's location, it can determine the distance between the rider's location and the user's location in real time. If the distance is greater than a second preset distance, it indicates that the rider is currently far away from the user. If the distance is less than or equal to the second preset distance, the server determines that the rider has reached the user.

[0501] When the target order status is the food has been picked up status, and the server determines through any method that the rider has arrived at the user, it can be determined that the first preset condition is met.

[0502] In the above technical solution, when judging whether the rider has arrived at the user, a comprehensive judgment is made through multiple conditions, which can accurately determine from multiple dimensions whether to report and remind the rider, thereby improving the accuracy of the judgment and timing of the reporting and delivery reminder, making the execution process of reporting and delivery more precise.

[0503] (2) Voice reminder process

[0504] When the target processing action is reporting and delivery, the server determines that the first preset condition is met and can send a first voice reminder to the user terminal so that the user terminal can broadcast it through the AI ​​smart assistant to remind the rider whether to execute the reporting and delivery associated with the current order. The first voice reminder is specifically a reporting and delivery reminder, that is, Figure 9 The report delivery prompt voice in.

[0505] Optionally, when the user terminal plays the report delivery reminder through the AI ​​smart assistant, the user terminal can also synchronously display the text corresponding to the report delivery reminder.

[0506] For example, Figure 9As shown in (a) of the figure, when a delivery driver is delivering food to a user, if the server determines that the distance between the driver and the user is 10 meters, a delivery report reminder can be sent to the user terminal, which then receives a notification via the AI ​​assistant. Correspondingly, the user terminal can also display a pop-up window 9011 on display interface 901. This pop-up window 9011 includes the text corresponding to the delivery report reminder—"You have arrived at the delivery location. Do you want to report your arrival?"—and the AI ​​assistant simultaneously broadcasts the voice message "You have arrived at the delivery location. Do you want to report your arrival?"

[0507] (3) Intent Recognition Process

[0508] After the report delivery reminder is broadcast, if the user terminal receives the rider's first voice instruction for the report delivery reminder, the first voice instruction can be sent to the server. The server further performs intent recognition on the first voice instruction to determine whether to automatically execute the report delivery. When the target processing action is report delivery, the first voice instruction is specifically the reply voice of the report delivery reminder, that is, Figure 9 The reply voice to the report delivery prompt voice.

[0509] Please refer to the above description for the specific intent recognition process, which will not be repeated here.

[0510] If the server successfully recognizes the voice reply to the delivery notification, and the recognition is successful, the delivery notification will be automatically executed, the server can determine the delivery notification execution steps and send them to the user terminal in the form of target processing instructions for execution. The target processing instructions here are the delivery notification processing instructions mentioned above.

[0511] For example, Figure 9 As shown in (b), the rider's first voice command is "Please report my delivery." After the server recognizes the reply voice intent, the intent recognition result is to automatically execute the delivery report. The server can determine that the execution step for reporting the delivery is to switch the interactive state of the "I have delivered" control from active to grayed out. Based on this execution step, the server generates a target processing instruction and sends it to the user.

[0512] like Figure 9 As shown in (c), in the display interface 903, after receiving the target processing instruction, the user terminal can switch the interactive state of the "I have delivered" control from the activated state to the grayed state according to the execution steps of reporting the delivery.

[0513] (4) Exception handling process

[0514] In another scenario, when the intention recognition result is not to automatically execute the target processing action, the server can send the second voice reminder to the user terminal again after the second preset time period, so that the user terminal can broadcast it.

[0515] Optionally, the second voice reminder can be the same as the report delivery reminder. Figure 9 As shown in (a) above, the second voice reminder may be "We have detected that you have arrived at the delivery location. Do you want to report delivery?" Alternatively, the second voice reminder may be different from the delivery report reminder. For example, the second voice reminder may be "We have detected that you have met the delivery report conditions. To avoid a delivery report timeout, do you want to report delivery?"

[0516] In another scenario, if the server does not detect the first voice command, or the first voice command intention recognition fails, it means that the rider has not yet determined to automatically execute the report delivery. The server can obtain the waiting execution time of the report delivery to determine whether there is a delay in the execution process of the report delivery.

[0517] When the server determines that the waiting time for report delivery is greater than or equal to the third preset time for report delivery, the server sends a third voice reminder to the user terminal, so that the user terminal can broadcast the third voice reminder through the AI ​​smart assistant. The third voice reminder is used to remind whether to execute the report delivery.

[0518] Optionally, the third voice reminder may be the same as the reporting and delivery reminder, or may be different, and this embodiment of the present application does not limit this.

[0519] For example, Figure 9 As shown in (a), the target processing action is reporting and delivery. After the user terminal broadcasts the reporting and delivery reminder - "It is detected that you have arrived at the delivery location, do you want to report the delivery?", if the first voice instruction responded by the rider is not detected or the first voice instruction intention recognition fails, the waiting execution time for reporting and delivery is obtained. When the waiting execution time is greater than or equal to the third preset time corresponding to the reporting and delivery, the server determines that there is a delay in the execution process of reporting and delivery, and the server can send the third voice reminder to the user terminal again to enable the user terminal to broadcast. For example, the third voice reminder can be "It is detected that you have arrived at the delivery location, do you want to report the delivery?", or the third voice reminder can also be "It is detected that there is a delay in your current reporting and delivery process, do you want to report the delivery for you?"

[0520] After the user terminal broadcasts the third voice reminder, if the user terminal receives the second voice instruction of the rider in response to the third voice reminder, after the server receives the second voice instruction sent by the user terminal, it can perform intent recognition on the second voice instruction in the same way as the first voice instruction to determine whether to automatically execute the report and delivery.

[0521] When the second voice command is successfully recognized, and the recognition result indicates that the report is automatically executed, the server can send the target processing instruction to the user terminal to enable the user terminal to execute the report. If the recognition result indicates that the report is not automatically executed, or the second voice command is not detected, or the recognition result indicates that the second voice command fails, the server can continue to provide voice reminders to the rider at the preset reminder frequency.

[0522] After the server sends the target processing instruction to the user terminal through the above process, the user terminal can feed back the execution completion result to the server after executing the reporting and delivery execution steps in response to the target processing instruction of the server.

[0523] For example, Figure 9 As shown in (c), when the user terminal has already reported the delivery for the rider, the display interface 603 displays a pop-up window 6031, which displays the prompt text "Delivery has been reported for you", and the AI ​​smart assistant simultaneously broadcasts the prompt voice "Delivery has been reported for you". Furthermore, the user terminal can also send the result of delivery to the server. In response to this result, the server determines that the target order status has been updated from the picked-up status to the delivered status, thereby ending the processing flow of the current order.

[0524] In another scenario, for the target processing action of reporting and delivery, if the server does not detect the first voice command, or the first voice command intention recognition fails, in addition to judging whether there is a delay in the execution process of reporting and delivery through the waiting execution time of reporting and delivery, the server can also achieve it through location matching.

[0525] In one possible implementation, the target processing action includes reporting and delivery. When the first voice command is not detected or the first voice command intention recognition fails, the method further includes:

[0526] Get the location of the rider and the user to be delivered;

[0527] When the rider reaches the user's location and then moves away from the user's location, the fifth voice reminder is automatically triggered to remind the rider whether to report and deliver the goods;

[0528] Obtain the fourth voice instruction of the rider in response to the fifth voice reminder, and determine whether to automatically execute the report delivery in response to the fourth voice instruction.

[0529] When the target processing action is to report delivery, the first voice reminder is a report delivery reminder. When the server does not detect the first voice command or fails to recognize the intent of the first voice command, the rider's location and the user's location can also be obtained.

[0530] When the server detects that the rider's location has reached the user's location and then moved away from the user's location, that is, the server detects that the distance between the rider's location and the user's location first decreases and then increases, it means that the rider has completed the delivery and left the user. In this case, there is a delay in the execution process of reporting and delivery. The server can send a fifth voice reminder to the user end, so that the user end can control the AI ​​smart assistant to play it. The fifth voice reminder is used to remind whether to execute the report and delivery.

[0531] Optionally, the fifth voice reminder may be the same as the report delivery reminder or may be different. For example, the fifth voice reminder may be "It is detected that there is a delay in your current report delivery. Do you want to report it for you?"

[0532] After receiving the rider's fourth voice instruction in response to the fifth voice reminder, the server can perform intent recognition on the fourth voice instruction in the same way as the first and second voice instructions to determine whether to automatically execute the report and delivery.

[0533] In the above technical solution, if the rider has not confirmed delivery, the server can automatically perform location matching. If the location matching result shows that the rider has arrived at the user's location and then moved away, it means that the rider has completed the delivery. The server can remind the rider to report delivery in time and update the order status in a timely manner to avoid order timeouts.

[0534] In addition, no matter which target processing action is performed, in addition to executing the target processing action through automatic triggering, the server can also provide a way for the rider to manually execute the target processing action.

[0535] In one possible implementation, when the first preset condition is met, the method further includes:

[0536] A display instruction of a target pop-up window is sent to the user terminal so that the user terminal displays the target pop-up window. The target pop-up window includes an execution control of the target processing action. The execution control is used to enable the rider to click to manually execute the target processing action.

[0537] Specifically, when the server determines that the first preset condition is met, in addition to sending the first voice reminder to the user terminal, it also sends a target pop-up window display instruction so that the user terminal displays a pop-up window corresponding to the first voice reminder. Different target processing actions correspond to different target pop-ups.

[0538] For example, Figure 6 As shown in (a), combined with the above introduction, when the target processing action is to report to the store, the user terminal will not only broadcast the reminder of reporting to the store, but also display a pop-up window 6011 containing the text corresponding to the reminder of reporting to the store.

[0539] As can be seen in the image, pop-up window 6011 includes text related to the store arrival reminder, and is the target pop-up window. Pop-up window 6011 also includes a "Confirm Arrival" control, which is the control for executing the store arrival report. Riders can manually execute the store arrival report by clicking this control.

[0540] Another example, Figure 7 As shown in (a), combined with the above introduction, when the target processing action is to report meal pickup, the user terminal will not only broadcast the reminder to report meal pickup, but also display a pop-up window 7011 containing the text corresponding to the reminder to report meal pickup.

[0541] As can be seen in the image, pop-up window 7011 includes text corresponding to the pickup report reminder, and this pop-up window 7011 is the target pop-up window. Pop-up window 7011 also includes a "Confirm Pickup" control, which is the execution control for reporting pickup. The rider can manually execute the pickup report by clicking this control.

[0542] Another example, Figure 9 As shown in (a), combined with the above introduction, when the target processing action is to report delivery, the user terminal will not only broadcast the report delivery reminder, but also display a pop-up window 9011 containing the text corresponding to the report delivery reminder.

[0543] As can be seen in the image, pop-up window 9011 includes text corresponding to the delivery report reminder, and this pop-up window 9011 is the target pop-up window. Pop-up window 9011 also includes a "Confirm Delivery" control, which is the control for executing the delivery report. The rider can manually execute the delivery report by clicking this control.

[0544] In addition to the automatic execution of the target processing action in the above technical solution, this application also provides a manual execution method for the target processing action. After the server triggers the first voice reminder, a pop-up window containing the execution control of the target processing action can also be synchronously displayed, so that the rider can continue to complete the target processing action manually if the automatic execution is unsuccessful, thereby improving the flexibility of the execution of the target processing action.

[0545] In addition, for any processing stage in the order processing, in order to ensure the user's delivery experience during the processing, the server can also remind the user of the notes.

[0546] In one possible implementation, the order parameters also include user comments on the current order, and the method further includes:

[0547] When the note information of the current order indicates that the rider is prohibited from contacting the user by phone, the sixth voice reminder is automatically triggered to the rider, and the sixth voice reminder is used to remind the rider that telephone contact is prohibited, and / or the sixth voice reminder is used to remind the rider to place the goods of the current order at the target location;

[0548] When there is no instruction for the rider in the remarks of the current order, the seventh voice reminder to the rider is automatically triggered. The seventh voice reminder is used to remind the rider to contact the user by phone.

[0549] Specifically, for any order, when the order is successfully created or generated, the order parameters include not only the merchant location and user location, but also the user's notes on the current order. Therefore, the server can directly obtain the user's notes on the current order based on the order parameters associated with the current order.

[0550] During the order processing process, the server can provide voice reminders to the rider based on the note information at any time.

[0551] Specifically, the technician can create a keyword library based on multiple preset keywords related to the remark information and store it in the server. Keywords include positive keywords and negative keywords.

[0552] Optionally, positive keywords include telephone contact, telephone connection, and phone call, and negative keywords include no telephone contact, don't call, no phone call, prohibit telephone contact, and send message contact, etc.

[0553] Based on the pre-established keyword library, after receiving the note information of the current order, the server can perform word segmentation processing on the note information to obtain multiple keywords. The server further matches each of the multiple keywords with the preset keywords in the keyword library to identify the requirements contained in the current user's note information.

[0554] In one scenario, if the note information of the current order includes negative keywords related to telephone contact, such as no calls, no calls, no telephone contact, etc., the server can further determine whether the note information includes the target location for the product (meal) specified by the user.

[0555] When the server can determine that the note information of the current order does not include the target location, the server sends a sixth voice reminder to the user terminal to remind the rider to prohibit contacting the user by phone.

[0556] When the server determines that the note information of the current order contains the target location, the server sends a sixth voice reminder to the user terminal to remind the rider of the target location of the goods of the current order, or reminds the rider to prohibit contacting the user by phone and reminds the rider of the target location of the goods of the current order.

[0557] In another scenario, if the note information of the current order does not contain any instructions from the user to the rider, the server can also obtain the user's phone number through the order parameters, and trigger the seventh voice reminder based on the user's phone number and send it to the user end. The seventh voice reminder is used to remind the rider to contact the user by phone.

[0558] In the above technical solution, during the order processing process, voice reminders are used to enable the rider to deliver food according to the user's notes, which can avoid user complaints caused by the rider's failure to check the notes in time, reduce the platform's customer complaint handling costs, and improve user delivery satisfaction.

[0559] Next, pass Figure 12 Another method for automatically executing order processing provided in an embodiment of the present application is introduced.

[0560] Figure 12 This is a schematic flow chart of another method for automatically executing orders provided in an embodiment of the present application. It should be understood that this method is applied to the user end.

[0561] For example, Figure 12 As shown, the method 1200 includes steps S1201 to S1204.

[0562] S1201, obtain the rider's real-time parameters.

[0563] During the order processing, the user terminal can obtain the rider's real-time parameters. The specific acquisition process is described in the above step S1101 and will not be repeated here.

[0564] S1202, sending the rider's real-time parameters to the server, so that the server can determine in real time whether the first preset condition is met based on the rider's real-time parameters and / or the order parameters associated with the current order.

[0565] After obtaining the real-time parameters, the user terminal can send the real-time parameters to the server. At the same time, the server can directly obtain the order parameters associated with the current order and can determine in real time whether the first preset condition is met based on the real-time parameters and / or the order parameters associated with the current order.

[0566] The stages involved in the rider's processing of the current order include arriving at the store, picking up the order, and delivering the order. Different stages correspond to different first preset conditions. While the rider is processing the current order, the server can determine in real time whether the first preset condition is met based on the rider's real-time parameters and / or order parameters.

[0567] S1203, receiving and broadcasting a first voice reminder sent by the server. The first voice reminder is automatically triggered by the server when a first preset condition is met. The first voice reminder is used to remind whether to execute a target processing action associated with the current order.

[0568] Different processing stages correspond to different target processing actions, and executing a target processing action means completing the processing stage corresponding to the target processing action. Optionally, the target processing action includes reporting arrival at the store, reporting pickup, and reporting delivery.

[0569] Specifically, when reminding the rider whether to execute the target processing action, the server can send a first voice reminder to the user terminal. The first voice reminder is used to remind the rider whether to execute the target processing action associated with the current order. When the target processing action is different, the first preset condition and the content of the first voice reminder will also change accordingly. After the user terminal receives the first voice reminder, it can be broadcasted through the AI ​​smart assistant.

[0570] S1204, obtaining the first voice instruction of the rider in response to the first voice reminder and sending it to the server, so that the server recognizes the intention of the first voice instruction and determines whether to automatically execute the target processing action based on the intention recognition result.

[0571] After broadcasting the first voice reminder, the user terminal can obtain the first voice instruction in response to the first voice reminder by the rider, and send the first voice instruction to the server.

[0572] After receiving the first voice instruction, the server can perform intent recognition on the first voice instruction to determine the purpose currently expressed by the rider.

[0573] In one possible implementation, the intent recognition result is obtained when the server successfully recognizes the intent of the first voice command based on the LLM model;

[0574] And, the method further comprises:

[0575] Receive a target processing instruction sent by the server. The target processing instruction is triggered by the server when the intention recognition result is to automatically execute the target processing action. The target processing instruction includes the execution steps of the target processing action;

[0576] In response to the target processing instruction, a target processing action is performed.

[0577] When performing intent recognition on the first voice instruction, the server can perform intent recognition on the first voice instruction using the LLM model in the NLP model. When the server succeeds in intent recognition, an intent recognition result can be obtained.

[0578] The specific server intention identification process is described in step S1104 and will not be repeated here.

[0579] When the intent recognition result is to automatically execute the target processing action, the server can determine the execution steps of the target processing action and send them to the user end in the form of target processing instructions.

[0580] After receiving the target instruction, the user terminal may execute the target processing action according to the execution steps of the target processing action in the target processing instruction.

[0581] The process of determining the execution steps of the specific target processing action and the process of the user end executing the target processing action can be found in the introduction of the aforementioned step S1104, which will not be repeated here.

[0582] In another possible implementation, the method further includes:

[0583] Receive the second voice reminder sent by the server and broadcast it. The second voice reminder is triggered again by the server at the second preset time when the intention recognition result is not to automatically execute the target processing action. The second voice reminder is used to remind whether to execute the target processing action.

[0584] If the rider decides not to automatically execute the target processing action, the server can issue a second voice reminder to the rider after a second preset time to avoid delays in the execution of the target processing action. After receiving the second voice reminder, the user terminal can control the AI ​​smart assistant to broadcast it.

[0585] It should be understood that the above description is based on the current order quantity of 1 for example, but in the actual delivery process, the number of orders that a rider grabs at one time may also be multiple, that is, the number of current orders is multiple. In view of the above situation, the embodiment of the present application has also made further optimizations when reminding.

[0586] In one possible implementation, when the number of current orders is multiple, after obtaining the first voice instruction of the rider in response to the first voice reminder and sending it to the server, the method further includes:

[0587] Receive and broadcast the eighth voice reminder sent by the server. The eighth voice reminder is used to inquire about the target order that the rider currently needs to process;

[0588] The fifth voice instruction of the rider in response to the eighth voice reminder is obtained and sent to the server, so that the server responds to the fifth voice instruction and determines whether to automatically execute the target processing action of the target order.

[0589] When the number of the current orders is multiple, please refer to the introduction of the aforementioned method S1100 for the specific processing process, which will not be repeated here.

[0590] In another scenario, if the user terminal does not receive the first voice instruction or the server fails to recognize the first voice instruction (that is, the first voice instruction does not contain any intention), the server can also remind the rider again.

[0591] In one possible implementation, when the first voice command is not detected or the first voice command intention recognition fails, the method further includes:

[0592] Receive and broadcast a third voice reminder sent by the server. The third voice reminder is automatically triggered by the server when the waiting execution time corresponding to the target processing action is greater than or equal to the third preset time. The third voice reminder is used to remind whether to execute the target processing action;

[0593] The second voice instruction of the rider in response to the third voice reminder is obtained and sent to the server, so that the server responds to the second voice instruction and determines whether to automatically perform the target processing action.

[0594] For any target processing action, after the user terminal broadcasts the first voice reminder, if the server does not receive the first voice instruction sent by the user terminal within the waiting time, or the server fails to recognize the intention of the first voice instruction, the server can further obtain the waiting execution time corresponding to the target processing action to determine whether there is a delay in the execution of the target processing action.

[0595] The above process of reminding the rider based on the waiting execution time of the target processing action when the first voice command is not detected or the first voice command intention recognition fails is specifically described in the aforementioned method 1100 and will not be repeated here.

[0596] After introducing the overall implementation process of the embodiment of the present application, the detailed process of the condition judgment process and the processing process corresponding to each target processing action will be introduced below.

[0597] It should be understood that target processing actions include reporting arrival at the store, reporting pickup, and reporting delivery.

[0598] (1) The target processing action is reporting to the store

[0599] (1) Condition judgment process

[0600] When a rider is on his way to a merchant, the server can use the rider's location and the merchant's location to determine whether to report the arrival at the store.

[0601] In one possible implementation, the target processing action includes reporting to the store, the rider's real-time parameters include the rider's location, and the order parameters include the merchant's location and the target order status. When the target order status is "claimed" and at least one of the following conditions is met, it is determined that the first preset condition is met:

[0602] The rider's location is within the coverage area of ​​the first signal associated with the merchant's location;

[0603] The rider's location is within the first preset range associated with the merchant's location;

[0604] The distance between the rider's location and the merchant's location is less than or equal to a first preset distance.

[0605] When the target processing action is to report to the store, when the server determines whether the first preset condition is met, the rider's real-time parameters include the rider's location, and the order parameters include the merchant's location and the target order status.

[0606] When the rider is on his way to the merchant, it means that the current rider has completed the order. Therefore, the target order status of the current order is the order-grabbed state. In the order-grabbed state, the server can further combine the above parameters to determine whether the first preset condition is met.

[0607] Specifically, the process of the server determining whether the real-time parameters and order parameters meet the first preset condition can be found in the introduction of the aforementioned method S1100 and will not be repeated here.

[0608] (2) Voice reminder process

[0609] When the target processing action is to report to the store, the server determines that the first preset condition is met and can send a first voice reminder to the user terminal.

[0610] After the user receives the first voice reminder, it will be broadcasted through the AI ​​smart assistant to remind the rider whether to execute the report to the store associated with the current order. The first voice reminder is specifically the report to the store reminder, that is, Figure 6 The voice prompt for reporting to the store.

[0611] (3) Intent Recognition Process

[0612] After the reminder to report to the store is played, if the user terminal receives the first voice instruction of the rider for the reminder to report to the store, the first voice instruction can be sent to the server. The server recognizes the intention of the first voice instruction to determine whether to automatically execute the report to the store. The first voice instruction is specifically the reply voice of the reminder to report to the store, that is, Figure 6 The reply voice message for the store visit notification.

[0613] If the server successfully recognizes the voice response to the store report reminder, and the recognized intent is to automatically report the store, the server can determine the steps for executing the store report and send them to the user in the form of a target processing instruction. The user will execute the store report according to the steps contained in the target processing instruction.

[0614] (4) Exception handling process

[0615] In another scenario, when the intention recognition result is not to automatically execute the target processing action, the server can send a second voice reminder to the user terminal for broadcast after a second preset time period.

[0616] In another scenario, if the server does not detect the first voice command, or fails to recognize the first voice command intent, it means that the rider has not yet confirmed the automatic execution of the report to the store. The server can obtain the waiting execution time of the report to the store and send it to the server, and determine whether there is a delay in the execution process of the report to the store.

[0617] For details of the above exception handling process, please refer to the introduction in the aforementioned method S1100, which will not be repeated here.

[0618] (2) The target processing action is to report and pick up the meal

[0619] (1) Condition judgment process

[0620] When the rider is on his way to the merchant, the server can use the following process to determine whether to report the meal pickup.

[0621] In one possible implementation, the target processing action includes reporting a meal pickup. The rider's real-time parameters include the rider's arrival time and location. The order parameters include the merchant's meal delivery status, merchant location, and target order status. When the target order status is "arrived at the store" and at least one of the following conditions is met, the first preset condition is determined to be met:

[0622] The rider's arrival time at the store is greater than or equal to the first preset time;

[0623] The merchant's meal delivery status is "Delivered";

[0624] The rider arrives at the merchant's location and then moves away from the merchant's location, and the merchant's meal delivery status is already delivered.

[0625] When the rider arrives at the store and waits to pick up the food, it means that the current rider has arrived at the store. Therefore, the target order status of the current order is the arrived state. In the arrived state, the server can further combine the above methods to determine whether the first preset condition is met.

[0626] For the specific condition judgment process, please refer to the introduction in the aforementioned method S1100, which will not be repeated here.

[0627] (2) Voice reminder process

[0628] When the target processing action is to report meal pickup, and the server determines that the first preset condition is met, the first voice reminder can be sent to the user terminal.

[0629] After the user receives the first voice reminder, it is broadcasted through the AI ​​smart assistant to remind the rider whether to execute the report pickup associated with the current order. The first voice reminder is specifically the report pickup reminder, which is Figure 7 The voice prompt for reporting meal pickup.

[0630] (3) Intent Recognition Process

[0631] After the reminder to report the meal is broadcast, if the user terminal receives the first voice instruction from the rider for the reminder to report the meal, the first voice instruction can be sent to the server. The server further performs intent recognition on the first voice instruction to determine whether to automatically execute the report to pick up the meal. When the target processing action is to report the meal, the first voice instruction is specifically the reply voice of the reminder to report the meal, that is, Figure 7 The reply voice message for the report pickup reminder.

[0632] If the server successfully recognizes the intent of the first voice command, and the recognized intent is to automatically report and pick up the meal, the server can determine the execution steps for reporting and picking up the meal and send them to the user terminal in the form of a target processing instruction. The user terminal executes the report and pick up the meal according to the execution steps for reporting and picking up the meal contained in the target processing instruction.

[0633] (4) Exception handling process

[0634] In another scenario, when the intention recognition result is not to automatically execute the target processing action, the server can send the second voice reminder to the user terminal again for broadcast after the second preset time period.

[0635] In another scenario, if the server does not detect the first voice command, or the first voice command intention recognition fails, it means that the rider has not yet decided to automatically execute the report to pick up the meal. The server can obtain the waiting execution time for reporting the meal to pick up the meal to determine whether there is a delay in the execution process of reporting the meal to pick up the meal.

[0636] In another scenario, for at least one of the two target processing actions of reporting arrival at the store or reporting meal pickup, if the server does not detect the first voice command, or fails to recognize the intent of the first voice command, the server may determine whether there is a delay in the execution of the target processing action by not only the waiting execution time of the target processing action but also by location matching.

[0637] In one possible implementation, the target processing action includes reporting arrival at the store and / or reporting pickup. When the first voice command is not detected or the first voice command intent recognition fails, the method further includes:

[0638] Get the location of the rider, the merchant, and the user to be delivered;

[0639] Send the rider location, merchant location, and user location to the server;

[0640] Receive and broadcast a fourth voice reminder sent by the server. The fourth voice reminder is automatically triggered by the server when the distance between the rider's location and the merchant's location is greater than or equal to the third preset distance, and the distance between the rider's location and the user's location is less than or equal to the fourth preset distance. The fourth voice reminder is used to remind whether to report to the store and / or report to pick up the meal;

[0641] The third voice instruction of the rider in response to the fourth voice reminder is obtained and sent to the server, so that the server responds to the third voice instruction and determines whether to automatically execute the report to the store and / or report to pick up the meal.

[0642] For details of the above exception handling process, please refer to the introduction in the aforementioned method S1100, which will not be repeated here.

[0643] (3) The target processing action is reporting and delivery

[0644] (1) Condition judgment process

[0645] When the rider is on the way to the merchant, the server can determine whether to report the delivery in the following way.

[0646] In one possible implementation, the target processing action includes reporting delivery, the rider's real-time parameters include the rider's location, and the order parameters include the location of the user to be delivered and the target order status. When the target order status is "picked up" and at least one of the following conditions is met, the first preset condition is determined to be met:

[0647] The rider's position is within the coverage area of ​​the second signal associated with the user's position;

[0648] The rider's position is within a second preset range associated with the user's position;

[0649] The distance between the rider position and the user position is less than or equal to a second preset distance.

[0650] When the rider is on the way to deliver the food, it means that the current rider has already picked up the food. Therefore, the target order status of the current order is the Picked Up status. In the Picked Up status, the server can further combine the above parameters to determine whether the first preset condition is met.

[0651] For the specific condition judgment process, please refer to the introduction in the aforementioned method S1100, which will not be repeated here.

[0652] (2) Voice reminder process

[0653] When the target processing action is reporting and delivery, the server determines that the first preset condition is met and can send a first voice reminder to the user terminal.

[0654] After the user receives the first voice reminder, it will be broadcasted through the AI ​​smart assistant to remind the rider whether to execute the report delivery associated with the current order. The first voice reminder is specifically a report delivery reminder, that is, Figure 9 The report delivery prompt voice in.

[0655] (3) Intent Recognition Process

[0656] After the report delivery reminder is broadcast, if the user terminal receives the rider's first voice instruction for the report delivery reminder, the first voice instruction can be sent to the server. The server further performs intent recognition on the first voice instruction to determine whether to automatically execute the report delivery. When the target processing action is report delivery, the first voice instruction is specifically the reply voice of the report delivery reminder, that is, Figure 9 The reply voice to the report delivery prompt voice.

[0657] If the server successfully recognizes the voice reply to the report delivery reminder, and the recognition is successful, the report delivery will be automatically executed. The server can determine the execution steps for the report delivery and send them to the user in the form of a target processing instruction. The user will execute the report delivery according to the execution steps of the report delivery contained in the target processing instruction.

[0658] (4) Exception handling process

[0659] In another scenario, when the intention recognition result is not to automatically execute the target processing action, the server can send the second voice reminder to the user terminal again for broadcast after the second preset time period.

[0660] In another scenario, if the server does not detect the first voice command, or the first voice command intention recognition fails, it means that the rider has not yet determined to automatically execute the report delivery. The server can obtain the waiting execution time of the report delivery to determine whether there is a delay in the execution process of the report delivery.

[0661] In another scenario, for the target processing action of reporting and delivery, if the server does not detect the first voice command, or the first voice command intention recognition fails, in addition to judging whether there is a delay in the execution process of reporting and delivery through the waiting execution time of reporting and delivery, the server can also achieve it through location matching.

[0662] In one possible implementation, the target processing action includes reporting and delivery. When the first voice command is not detected or the first voice command intention recognition fails, the method further includes:

[0663] Get the location of the rider and the user to be delivered;

[0664] Send the rider's location and the user's location to the server;

[0665] Receive and broadcast the fifth voice reminder sent by the server. The fifth voice reminder is automatically triggered by the server when the rider's position reaches the user's position and then moves away from the user's position. The fifth voice reminder is used to remind whether to execute the report delivery;

[0666] The fourth voice instruction of the rider in response to the fifth voice reminder is obtained and sent to the server, so that the server responds to the fourth voice instruction and determines whether to automatically execute the report delivery.

[0667] The above exception handling process can be found in the introduction of the aforementioned method S1100 and will not be repeated here.

[0668] In addition, no matter which target processing action is performed, in addition to executing the target processing action through automatic triggering, the server can also provide a way for the rider to manually execute the target processing action.

[0669] In one possible implementation, the method further includes:

[0670] Receive a display instruction of a target pop-up window sent by the server, where the target pop-up window includes an execution control for a target processing action, where the execution control is used to enable the rider to click on it to manually execute the target processing action;

[0671] In response to the display instruction of the target pop-up window, the target pop-up window is displayed.

[0672] For details on the display process of the above pop-up window, please refer to the introduction in the aforementioned method S1100, which will not be repeated here.

[0673] In addition, for any processing stage in the order processing, in order to ensure the user's delivery experience during the processing, the server can also remind the user of the notes.

[0674] In one possible implementation, the order parameters also include user comments on the current order, and the method further includes:

[0675] Receive and broadcast the sixth voice reminder sent by the server. The sixth voice reminder is automatically triggered when the server indicates in the notes of the current order that the rider is prohibited from contacting the user by phone. The sixth voice reminder is used to remind the rider that telephone contact is prohibited, and / or the sixth voice reminder is used to remind the rider to place the goods of the current order at the target location;

[0676] Receive the seventh voice reminder sent by the server and broadcast it. The seventh voice reminder is automatically triggered by the server when there is no instruction for the rider in the remarks information of the current order. The seventh voice reminder is used to remind the rider to contact the user by phone.

[0677] For details of the above-mentioned note prompt process, please refer to the introduction in the aforementioned method S1100, which will not be repeated here.

[0678] In summary, in the process of riders processing orders, a method for automatically executing order processing is provided. The specific implementation process is as follows: the server can determine whether the real-time parameters of the rider and the order parameters associated with the current order meet the first preset conditions. When the first preset conditions are met, the rider is given a first voice reminder. The above process can match conditions in real time during the rider's delivery process, and actively remind the rider, reducing the intervention of manual judgment. When the conditions are met, the first voice reminder is triggered, and the rider's reply instructions are recognized for their intentions. This can take into account the rider's subjective wishes during the automatic processing process, thereby improving the accuracy of automatic execution and the rider's satisfaction. The above-mentioned method of automatically executing target processing actions can replace the rider's manual execution operations, simplify the rider's operating procedures, thereby reducing the complexity of operations, improving order processing efficiency when it is inconvenient for the rider to click, and improving the rider's delivery experience.

[0679] Next, pass Figure 13 The interaction process between the server and the user end during the above order processing is introduced.

[0680] Figure 13 This is an interactive flow chart for automatically executing order processing in an embodiment of the present application.

[0681] For example, Figure 13 As shown, the method 1300 for automatically executing order processing includes steps S1301-S1326.

[0682] For example, Figure 13 As shown, during the interaction between the server and the user, see Figure 10 The server includes various services, a reach platform, Tongyi Cloud TTS, Tongyi Cloud ASR, intelligent conversation, and NLP services. The user end can interact with the server based on the rider's input voice or demand instructions, and then execute the required items corresponding to the rider's demand instructions.

[0683] It should be noted that the user end is equipped with an AI smart assistant, which can realize intelligent interaction with the rider.

[0684] S1301: Each business in the server performs scene recognition based on the rider's real-time parameters and the order parameters associated with the current order.

[0685] Specifically, during the process of automatically executing order processing, the server can judge whether the first preset condition is met based on the rider's real-time parameters and the order parameters associated with the current order to determine whether it is necessary to automatically execute the target processing action associated with the current order.

[0686] As mentioned above, target processing actions include reporting arrival, reporting pickup, and reporting delivery. For each target processing action, the server determines whether the first pre-set condition is met based on real-time parameters and order parameters. This can be considered a "scene recognition." The result of scene recognition is whether a scene event is generated.

[0687] For example, when the target processing action is to report to the store, the server can determine that the first preset condition is met based on the real-time parameters and the order parameters associated with the current order. The corresponding scenario event is the "report to the store" scenario event.

[0688] S1302, each business in the server sends the identified scene events to the agent session.

[0689] When each business is performing scene recognition, when it is recognized that the real-time parameters and order parameters meet a certain scene event, each business sends the recognized scene event to the intelligent agent session.

[0690] S1303, the intelligent agent session performs rule verification, and when the rule verification is successful, sends a scene event to the touch platform.

[0691] See also Figure 10 As shown, upon receiving a scene event, the agent session can perform rule verification. This rule verification includes determining whether the current user terminal is currently performing voice interaction, whether the current user terminal has enabled microphone permissions, and whether the current scene event has expired.

[0692] When the agent session determines that the user has enabled the microphone permission and the current scene event has not expired, the scene event is sent to the server's reach platform.

[0693] S1304, the touch platform in the server sends the scene event to the user end.

[0694] In step S1303, when the agent session determines that the rule verification is passed or successful, a scene event is sent to the touch platform, which further sends the scene event to the user end.

[0695] S1305: The user terminal determines the reminder text of the scene event and sends it to the Tongyi Cloud TTS in the server.

[0696] When the user terminal receives a scene event, it determines that a voice reminder is required for the rider.

[0697] Specifically, when the user terminal gives a voice reminder to the rider, it can first determine the reminder text corresponding to the scene event locally.

[0698] Specifically, different scene events correspond to different reminder texts. Taking the current scene event as "report to the store" as an example, the user terminal can determine the reminder text corresponding to "report to the store".

[0699] The user terminal can send the reminder text of the scene event to the Tongyi Cloud TTS in the server, so that the Tongyi Cloud TTS converts the reminder text of the above scene event into the corresponding first voice reminder.

[0700] S1306, the user terminal receives the first voice reminder sent by Tongyiyun TTS in the server.

[0701] Tongyi Cloud TTS uses text-to-speech technology to convert the reminder text of scene events into the first voice reminder, which can be returned to the user end.

[0702] In addition, the process of determining the first voice reminder in the above S1302-S1306 can also be that the intelligent agent conversation in the server directly determines the reminder text corresponding to the scene event after the rule verification is successful, and converts it through TTS in the server to obtain the first voice reminder, and then sends it to the user end.

[0703] S1307: The user terminal broadcasts a first voice reminder.

[0704] After the user terminal receives the first voice reminder, it can control the AI ​​smart assistant to broadcast the first voice reminder to remind the rider whether to automatically perform the target processing action.

[0705] For example, if the scene event is "report to the store", the first voice reminder can be: "It is detected that you have arrived at the merchant, do you want to report to the store?"

[0706] S1308, the user terminal receives the rider's first voice instruction.

[0707] After the user terminal broadcasts the first voice reminder, if the rider responds to the first voice instruction, the user terminal can obtain the first voice instruction.

[0708] S1309, the user terminal sends the first voice command to the Tongyi Cloud ASR in the server.

[0709] After the user terminal receives the first voice instruction, it can send the first voice instruction to Tongyi Cloud ASR, so that Tongyi Cloud ASR performs voice-to-text processing on the first voice instruction, thereby obtaining first text information corresponding to the first voice instruction.

[0710] S1310, the user terminal receives the first text message sent by the Tongyi Cloud ASR of the server.

[0711] Tongyi Cloud ASR performs speech-to-text processing on the first voice command, and after obtaining the first text information, the first text information can be sent to the user terminal.

[0712] S1311, the agent session in the server receives the first text message sent by the user terminal.

[0713] After receiving the first text message sent by Tongyi Cloud ASR, the user terminal sends the first text message to the intelligent agent session for intent recognition.

[0714] S1312, the NLP service in the server receives the first text message sent by the agent conversation.

[0715] After receiving the first text message sent by the user terminal, the agent session sends the first text message to the NLP service for intent recognition.

[0716] S1313, the agent session in the server receives the intent recognition result sent by the NLP service.

[0717] Exemplarily, after receiving the first text message sent by the agent conversation, the NLP service performs intent recognition on the first text message.

[0718] When intent recognition is successful, the intent recognition result can be obtained and sent to the agent session.

[0719] Optionally, when the intent recognition of the first text information is successful, the intent recognition result includes automatically executing the target processing action or not automatically executing the target processing action.

[0720] Optionally, the method for performing intent recognition on the first text information may refer to the aforementioned intent recognition method, which will not be described in detail here.

[0721] S1314, when the intention recognition result is to automatically execute the target processing action, the intelligent agent conversation in the server determines the execution steps of the target processing action.

[0722] When the agent session receives the intent recognition result sent by the NLP service and the intent recognition result is to automatically execute the target processing action, the agent session can determine the execution steps of the target processing action and generate the target processing instructions.

[0723] S1315, the user end receives the target processing instruction sent by the intelligent agent session in the server.

[0724] The agent session sends target processing instructions to the user end.

[0725] S1316: The user terminal automatically executes the target processing action and broadcasts a success prompt voice.

[0726] After receiving the target processing instruction sent by the intelligent agent session, the user end automatically executes the target processing action according to the target processing instruction and plays a success prompt voice.

[0727] Optionally, a success prompt voice is used to prompt the rider that the target processing action has been automatically performed.

[0728] S1317, when the intention recognition result is that the target processing action is not automatically executed or the intention recognition fails, the intelligent agent session in the server sends the Nth voice reminder to the user terminal.

[0729] When the agent session fails to recognize the intent sent by the NLP service, or the intent recognition result is that the target processing action is not automatically executed, it can send the Nth reminder voice to the user end again.

[0730] Here, steps S1317 to S1325 are steps that are executed in a loop.

[0731] If intent recognition fails or the intent recognition result indicates that the target action will not be automatically executed, the server obtains the number of conversations in the current round and determines whether the number of conversations is less than a preset number. If the number of conversations is less than the preset number, the server executes S1317-S1325. If the number of conversations is greater than or equal to the preset number, the server executes S1326 and plays a success or failure prompt.

[0732] Optionally, the preset number of times may be 6, 7, etc. The preset number of times may be determined according to actual conditions and is not specifically limited here.

[0733] S1318: The user terminal broadcasts the Nth voice reminder.

[0734] When the intention recognition fails, or the intention recognition result is that the target processing action is not automatically executed, after the user end receives the Nth voice reminder sent by the server, the Nth voice reminder can be broadcast to the rider.

[0735] S1319, the user terminal receives the Nth voice instruction corresponding to the Nth voice reminder.

[0736] After the user terminal receives the Nth voice reminder and broadcasts it, if the rider responds, the user terminal can receive the rider's Nth voice instruction.

[0737] S1320, the user terminal sends the Nth voice command to the Tongyi Cloud ASR in the server.

[0738] Similar to the processing method of the first voice command, after receiving the Nth voice command, the user terminal can call the Tongyi Cloud ASR in the server to perform voice-to-text processing on the Nth voice command to obtain the Nth text information.

[0739] S1321, the user terminal receives the Nth text information sent by Tongyi Cloud ASR in the server.

[0740] The Tongyi Cloud ASR in the server performs speech-to-text processing on the Nth voice command, and after obtaining the Nth text information, the Nth text information can be sent to the user end.

[0741] S1322, the intelligent agent session in the server receives the Nth text message sent by the user terminal.

[0742] After receiving the Nth text message, the user terminal may send the Nth text message to the agent session in the server.

[0743] S1323, the NLP service in the server receives the Nth text message sent by the agent conversation.

[0744] After receiving the Nth text message sent by the user end, the intelligent agent session can send the Nth text message to the NLP service for intent recognition.

[0745] S1324, the agent session in the server receives the intent recognition result sent by the NLP service.

[0746] After receiving the Nth text message sent by the agent session, the NLP service performs intent recognition. If the intent recognition is successful, it obtains the intent recognition result and sends the intent recognition result to the agent session.

[0747] S1325, the user terminal receives the target processing instruction sent by the intelligent agent session in the server, or does not perform the target processing action, or fails to recognize the intention.

[0748] When the intelligent agent session receives the intention recognition result sent by the NLP service and automatically executes the target processing action, it can determine the target processing instruction and send it to the user end. After the user end receives the target processing instruction, it executes S1326.

[0749] If the intention recognition result is that the target processing action is not automatically executed or the intention recognition fails, and the current number of dialogues is less than the preset number, S1317-S1325 are executed. If the number of dialogues is greater than or equal to the preset number, it is determined that the interaction has failed, and S1326 can be executed.

[0750] S1326, when the intention recognition result is to automatically execute the target processing action, the user end automatically executes the target processing action and broadcasts a success prompt voice; when the intention recognition fails or the intention recognition result is not to automatically execute the target processing action, the user end broadcasts a failure prompt voice.

[0751] When the user end receives the target processing instruction sent by the intelligent agent session, it automatically executes the target processing action and broadcasts a success prompt voice to prompt the rider that the target processing action has been automatically executed.

[0752] When the user receives an intent recognition result from the agent session indicating that the target action is not automatically executed or that the intent recognition fails, a failure prompt is broadcasted to inform the rider that the target action is not currently being executed. For example, the failure prompt could be "Current execution failed, target action not executed."

[0753] In addition, after the user end broadcasts the failure prompt voice, when the rider's re-entered voice command is received, the aforementioned intention recognition steps can be continued.

[0754] In an embodiment of the present application, in addition to the above-mentioned server automatically performing scene matching to remind the rider whether to automatically perform the target processing action, an embodiment of the present application also provides a voice interaction actively initiated by the rider to enable the user end to automatically perform the target processing action.

[0755] Below through Figure 14 , the interactive process of the rider actively initiating voice interaction and enabling the user end to automatically execute the target processing action is introduced.

[0756] Figure 14 This is another interactive flowchart for automatically executing order processing provided by an embodiment of the present application.

[0757] For example, Figure 14 As shown, when the user actively initiates voice interaction, compared with Figure 13 The server no longer includes various services and contact platforms. Instead, the rider actively activates the AI ​​assistant. The method 1400 for automatically executing order processing includes the following steps S1401-S1423.

[0758] S1401: The user terminal detects the wake-up word input by the rider.

[0759] The wake-up word is the wake-up voice mentioned above, which is used to wake up the AI ​​smart assistant in dormant state.

[0760] For example, in combination with the above introduction, the wake-up voice can be "Little bird, little bird" or "I'm a little hungry, little hungry" to wake up the AI ​​smart assistant.

[0761] S1402, the Tongyi Cloud TTS in the server receives the response information of the wake-up word sent by the user terminal.

[0762] Optionally, the response information of the wake-up word is used to respond to the rider, informing the rider that the AI ​​smart assistant has been awakened.

[0763] For example, Figure 3 As shown in (c), when the wake-up word is "Xiaoe Xiaoe", the response message of the wake-up word is "Hi, I am an AI smart assistant, how can I help you?"

[0764] It is understood that the wake-up word response information shown above is one of the possible implementations. The wake-up word response information can be fixed; for example, the response information can be "I'm here, what's up" or "Listening, go ahead." The wake-up word response information can be determined based on actual circumstances and is not specifically limited here.

[0765] S1403, the user terminal receives the voice information of the response information sent by Tongyiyun TTS in the server.

[0766] When the user terminal receives the wake-up word, it sends the response information of the wake-up word to Tongyi Cloud TTS, so that Tongyi Cloud TTS converts the response information of the wake-up word into voice information and sends the voice information of the response information to the user terminal.

[0767] S1404: The user terminal plays the voice message.

[0768] When the user terminal receives the voice message of the response message sent by Tongyiyun TTS, the voice message is played on the user terminal to enable the rider to input the actual needs.

[0769] S1405, the user terminal detects the rider's first voice command.

[0770] and Figure 13 As described in , after the AI ​​smart assistant is awakened, the user end can detect the first voice command actively input by the rider in real time.

[0771] For example, when the rider reports to the store, the first voice instruction may be "Please help me report to the store."

[0772] The first voice command actively input by the rider can be understood as Figure 13 The first voice instruction received after the rider is notified through the first voice reminder.

[0773] S1406, the user terminal sends the first voice command to the Tongyi Cloud ASR in the server.

[0774] S1407, the user terminal receives the first text message sent by the Tongyi Cloud ASR of the server.

[0775] S1408, the agent session in the server receives the first text message sent by the user terminal.

[0776] S1409, the NLP service in the server receives the first text message sent by the agent conversation.

[0777] S1410, the agent session in the server receives the intent recognition result sent by the NLP service.

[0778] S1411, when the intention recognition result is to automatically execute the target processing action, the intelligent agent conversation in the server determines the execution steps of the target processing action.

[0779] S1412, the user end receives the target processing instruction sent by the intelligent agent session in the server.

[0780] S1413: The user terminal automatically executes the target processing action and broadcasts a success prompt voice.

[0781] S1414, when the intention recognition result is that the target processing action is not automatically executed or the intention recognition fails, the intelligent agent session in the server sends the Nth voice reminder to the user terminal.

[0782] S1415, the user terminal broadcasts the Nth voice reminder.

[0783] S1416 , the user terminal receives the Nth voice instruction corresponding to the Nth voice reminder.

[0784] S1417, the user terminal sends the Nth voice command to the Tongyi Cloud ASR in the server.

[0785] S1418, the user terminal receives the Nth text information sent by Tongyi Cloud ASR in the server.

[0786] S1419, the intelligent agent session in the server receives the Nth text message sent by the user terminal.

[0787] S1420, the NLP service in the server receives the Nth text information sent by the agent conversation.

[0788] S1421, the agent session in the server receives the intent recognition result sent by the NLP service.

[0789] S1422, the user terminal receives the target processing instruction sent by the intelligent agent session in the server, or does not perform the target processing action, or fails to recognize the intention.

[0790] S1423, when the intention recognition result is to automatically execute the target processing action, the user end automatically executes the target processing action and broadcasts a success prompt voice; when the intention recognition fails or the intention recognition result is not to automatically execute the target processing action, the user end broadcasts a failure prompt voice.

[0791] The above steps S1406 to S1423 can refer to the above Figure 13 There is an introduction to steps S1309 to S1326 in , which will not be repeated here.

[0792] It should be understood that the above examples are intended to help those skilled in the art understand the embodiments of the present application, and are not intended to limit the embodiments of the present application to the specific numerical values ​​or specific scenarios illustrated. Those skilled in the art can obviously make various equivalent modifications or variations based on the above examples, and such modifications or variations also fall within the scope of the embodiments of the present application.

[0793] Figure 15 This is a structural diagram of a device for automatically executing order processing provided in an embodiment of the present application.

[0794] For example, Figure 15 As shown, the device 1500 is applied to a server, and the device 1500 includes:

[0795] Acquisition module 1501, used to obtain the rider's real-time parameters and order parameters associated with the current order;

[0796] The processing module 1502 is configured to determine in real time whether a first preset condition is satisfied based on the rider's real-time parameters and / or the order parameters;

[0797] The processing module 1502 is further configured to automatically trigger a first voice reminder to the rider when a first preset condition is met, wherein the first voice reminder is used to remind the rider whether to execute a target processing action associated with the current order;

[0798] The processing module 1502 is further configured to perform intention recognition on the rider's first voice instruction in response to the first voice reminder;

[0799] The processing module 1502 is further configured to determine whether to automatically execute the target processing action based on the intention recognition result.

[0800] In one possible implementation, the target processing action includes reporting to the store, the rider's real-time parameters include the rider's location, the order parameters include the merchant's location and the target order status, and when the target order status is the grabbed order status and meets at least one of the following conditions, it is judged that the first preset condition is met: the rider's location is within the coverage area of ​​the first signal associated with the merchant's location; the rider's location is within the first preset range associated with the merchant's location; the distance between the rider's location and the merchant's location is less than or equal to the first preset distance.

[0801] In one possible implementation, the target processing action includes reporting the meal pickup, the real-time parameters of the rider include the rider's arrival time at the store and the rider's location, the order parameters include the merchant's meal delivery status, the merchant's location, and the target order status. When the target order status is the arrived-at-store status and meets at least one of the following conditions, it is determined that the first preset condition is met: the rider's arrival time at the store is greater than or equal to the first preset time; the merchant's meal delivery status is the delivered status; the rider's location arrives at the merchant's location and then moves away from the merchant's location, and the merchant's meal delivery status is the delivered status.

[0802] In one possible implementation, the target processing action includes reporting delivery, the rider's real-time parameters include the rider's location, the order parameters include the user's location to be delivered and the target order status. When the target order status is the food has been picked up status and at least one of the following items is met, it is judged that the first preset condition is met: the rider's location is within the coverage area of ​​the second signal associated with the user's location; the rider's location is within the second preset range associated with the user's location; the distance between the rider's location and the user's location is less than or equal to the second preset distance.

[0803] In one possible implementation, the processing module 1502 is specifically used to: perform intent recognition on the first voice instruction based on the LLM model; when the intent recognition is successful, obtain the intent recognition result; and when the intent recognition result is to automatically execute the target processing action, send a target processing instruction to the user terminal so that the user terminal executes the target processing action, and the target processing instruction includes the execution steps of the target processing action.

[0804] In one possible implementation, the processing module 1502 is also used to: when the intention recognition result is not to automatically execute the target processing action, automatically trigger a second voice reminder to the rider again within a second preset time period, and the second voice reminder is used to remind whether to execute the target processing action.

[0805] In one possible implementation, when the first voice instruction is not detected or the first voice instruction intention recognition fails, the processing module 1502 is also used to: obtain the waiting execution time corresponding to the target processing action; when the waiting execution time is greater than or equal to a third preset time, automatically trigger a third voice reminder to the rider, and the third voice reminder is used to remind whether to execute the target processing action; obtain the second voice instruction of the rider in response to the third voice reminder, and determine whether to automatically execute the target processing action in response to the second voice instruction.

[0806] In one possible implementation, the target processing action includes reporting to the store and / or reporting to pick up the meal. When the first voice instruction is not detected or the first voice instruction intention recognition fails, the processing module 1502 is also used to: obtain the rider location, the merchant location and the user location to be delivered; when the distance between the rider location and the merchant location is greater than or equal to a third preset distance, and the distance between the rider location and the user location is less than or equal to a fourth preset distance, automatically trigger a fourth voice reminder for the rider, and the fourth voice reminder is used to remind whether to execute the reporting to the store and / or reporting to pick up the meal; obtain the third voice instruction of the rider in response to the fourth voice reminder, and in response to the third voice instruction, determine whether to automatically execute the reporting to the store and / or reporting to pick up the meal.

[0807] In one possible implementation, the target processing action includes reporting and delivery. When the first voice instruction is not detected or the first voice instruction intention recognition fails, the processing module 1502 is also used to: obtain the rider's location and the user's location to be delivered; when the rider's location reaches the user's location and then moves away from the user's location, automatically trigger a fifth voice reminder for the rider, and the fifth voice reminder is used to remind whether to execute the reporting and delivery; obtain the fourth voice instruction of the rider in response to the fifth voice reminder, and determine whether to automatically execute the reporting and delivery in response to the fourth voice instruction.

[0808] In one possible implementation, the order parameters also include the user's remarks on the current order, and the processing module 1502 is also used to: when the remarks information of the current order indicates that the rider is prohibited from contacting the user by phone, automatically trigger a sixth voice reminder for the rider, and the sixth voice reminder is used to remind the rider that the rider is prohibited from contacting by phone, and / or, the sixth voice reminder is used to remind the rider to place the goods of the current order at the target location; when there is no instruction for the rider in the remarks information of the current order, automatically trigger a seventh voice reminder for the rider, and the seventh voice reminder is used to remind the rider to contact the user by phone.

[0809] In one possible implementation, when the number of the current orders is multiple, after determining whether to automatically execute the target processing action based on the intention recognition result, the processing module 1502 is also used to: provide the rider with an eighth voice reminder, and the eighth voice reminder is used to inquire about the target order that the rider currently needs to process; obtain the fifth voice instruction of the rider in response to the eighth voice reminder, and in response to the fifth voice instruction, determine whether to automatically execute the target processing action of the target order according to the intention recognition result.

[0810] In one possible implementation, when the first preset condition is met, the processing module 1502 is also used to: send a display instruction of a target pop-up window to the user terminal, so that the user terminal displays the target pop-up window, and the target pop-up window includes an execution control of the target processing action, and the execution control is used to enable the rider to click to manually execute the target processing action.

[0811] Figure 16 This is a structural diagram of another device for automatically executing order processing provided in an embodiment of the present application.

[0812] For example, Figure 16 As shown, the device 1600 is applied to a user terminal, and the device 1600 includes:

[0813] An acquisition module 1601 is used to acquire the rider's real-time parameters;

[0814] A sending module 1602 is configured to send the rider's real-time parameters to a server, so that the server determines in real time whether a first preset condition is met based on the rider's real-time parameters and / or order parameters associated with the current order;

[0815] Receiving module 1603, configured to receive and announce a first voice reminder sent by the server, wherein the first voice reminder is automatically triggered by the server when the first preset condition is met, and the first voice reminder is used to remind whether to execute a target processing action associated with the current order;

[0816] The acquisition module 1601 is also used to obtain the first voice instruction of the rider in response to the first voice reminder and send it to the server, so that the server can recognize the intention of the first voice instruction and determine whether to automatically execute the target processing action based on the intention recognition result.

[0817] In one possible implementation, the target processing action includes reporting to the store, the rider's real-time parameters include the rider's location, the order parameters include the merchant's location and the target order status, and when the target order status is the grabbed order status and meets at least one of the following conditions, it is judged that the first preset condition is met: the rider's location is within the coverage area of ​​the first signal associated with the merchant's location; the rider's location is within the first preset range associated with the merchant's location; the distance between the rider's location and the merchant's location is less than or equal to the first preset distance.

[0818] In one possible implementation, the target processing action includes reporting the meal pickup, the real-time parameters of the rider include the rider's arrival time at the store and the rider's location, the order parameters include the merchant's meal delivery status, the merchant's location, and the target order status. When the target order status is the arrived-at-store status and meets at least one of the following conditions, it is determined that the first preset condition is met: the rider's arrival time at the store is greater than or equal to the first preset time; the merchant's meal delivery status is the delivered status; the rider's location arrives at the merchant's location and then moves away from the merchant's location, and the merchant's meal delivery status is the delivered status.

[0819] In one possible implementation, the target processing action includes reporting delivery, the rider's real-time parameters include the rider's location, the order parameters include the user's location to be delivered and the target order status. When the target order status is the food has been picked up status and at least one of the following items is met, it is judged that the first preset condition is met: the rider's location is within the coverage area of ​​the second signal associated with the user's location; the rider's location is within the second preset range associated with the user's location; the distance between the rider's location and the user's location is less than or equal to the second preset distance.

[0820] In one possible implementation, the intent recognition result is obtained when the server successfully recognizes the intent of the first voice instruction based on the LLM model; and the receiving module 1603 is also used to: receive a target processing instruction sent by the server, which is triggered by the server when the intent recognition result is to automatically execute the target processing action, and the target processing instruction includes the execution steps of the target processing action; and execute the target processing action in response to the target processing instruction.

[0821] In one possible implementation, the receiving module 1603 is also used to: receive and broadcast a second voice reminder sent by the server, where the second voice reminder is triggered again by the server within a second preset time period when the intention recognition result is not to automatically execute the target processing action, and the second voice reminder is used to remind whether to execute the target processing action.

[0822] In one possible implementation, when the first voice instruction is not detected or the first voice instruction intention recognition fails, the receiving module 1603 is also used to: receive and broadcast a third voice reminder sent by the server, the third voice reminder is automatically triggered by the server when the waiting execution time of the target processing action is greater than or equal to a third preset time, and the third voice reminder is used to remind whether to execute the target processing action; the acquisition module 1601 is also used to: obtain the second voice instruction of the rider in response to the third voice reminder and send it to the server, so that the server responds to the second voice instruction and determines whether to automatically execute the target processing action.

[0823] In one possible implementation, the target processing action includes reporting to the store and / or reporting to pick up the meal. When the first voice instruction is not detected or the first voice instruction intention recognition fails, the acquisition module 1601 is further used to: obtain the rider's location; the sending module 1602 is further used to: send the rider's location to the server; the receiving module 1603 is further used to: receive a fourth voice reminder sent by the server and broadcast it. The fourth voice reminder is automatically triggered by the server when the distance between the rider's location and the merchant's location is greater than or equal to a third preset distance, and the distance between the rider's location and the user's location to be delivered is less than or equal to the fourth preset distance. The fourth voice reminder is used to remind whether to execute the reporting to the store and / or reporting to pick up the meal; the acquisition module 1601 is further used to: obtain the third voice instruction of the rider in response to the fourth voice reminder and send it to the server, so that the server responds to the third voice instruction and determines whether to automatically execute the reporting to the store and / or the reporting to pick up the meal.

[0824] In one possible implementation, the target processing action includes reporting and delivery. When the first voice instruction is not detected or the first voice instruction intention recognition fails, the acquisition module 1601 is also used to: obtain the rider's position; the sending module 1602 is also used to: send the rider's position to the server; the receiving module 1603 is also used to: receive the fifth voice reminder sent by the server and broadcast it. The fifth voice reminder is automatically triggered by the server when the rider's position reaches the user location to be delivered and then moves away from the user location. The fifth voice reminder is used to remind whether to execute the reporting and delivery; the acquisition module 1601 is also used to: obtain the fourth voice instruction of the rider in response to the fifth voice reminder and send it to the server, so that the server responds to the fourth voice instruction and determines whether to automatically execute the reporting and delivery.

[0825] In one possible implementation, the order parameters also include the user's remarks on the current order, and the receiving module 1603 is further used to: receive and broadcast the sixth voice reminder sent by the server, the sixth voice reminder is automatically triggered when the server indicates in the remarks information of the current order that the rider is prohibited from contacting the user by phone, and the sixth voice reminder is used to remind the rider that telephone contact is prohibited, and / or, the sixth voice reminder is used to remind the rider to place the goods of the current order at the target location; receive and broadcast the seventh voice reminder sent by the server, the seventh voice reminder is automatically triggered when the server has no instructions for the rider in the remarks information of the current order, and the seventh voice reminder is used to remind the rider to contact the user by phone.

[0826] In one possible implementation, when the number of the current orders is multiple, the receiving module 1603 is also used to: receive the eighth voice reminder sent by the server and broadcast it, and the eighth voice reminder is used to inquire about the target order that the rider currently needs to process; the acquisition module 1601 is also used to: obtain the fifth voice instruction of the rider in response to the eighth voice reminder and send it to the server, so that the server responds to the fifth voice instruction and determines whether to automatically execute the target processing action of the target order based on the intention recognition result.

[0827] In one possible implementation, the receiving module 1603 is also used to: receive a display instruction of a target pop-up window sent by the server, the target pop-up window including an execution control for the target processing action, the execution control being used to enable the rider to click to manually execute the target processing action; and display the target pop-up window in response to the display instruction of the target pop-up window.

[0828] Figure 17 1 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. It should be understood that the electronic device is specifically the server described above.

[0829] For example, Figure 17 As shown, the electronic device 1700 includes: a memory 1701 and a processor 1702, wherein the memory 1701 stores an executable program code 17011, and the processor 1702 is used to call and execute the executable program code 17011 to perform a method for automatically executing order processing.

[0830] Figure 18 1 is a schematic diagram of the structure of another electronic device provided in an embodiment of the present application. It should be understood that the electronic device is specifically the user terminal described above.

[0831] For example, Figure 18As shown, the electronic device 1800 includes: a memory 1801 and a processor 1802, wherein the memory 1801 stores an executable program code 18011, and the processor 1802 is used to call and execute the executable program code 18011 to perform a method for automatically executing order processing.

[0832] In this embodiment, the electronic device can be divided into functional modules according to the above-described method example. For example, each functional module can be mapped to a specific function, or two or more functions can be integrated into a single processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and represents only a logical functional division. In actual implementation, other division methods may be used.

[0833] When the functional modules are divided according to their functions, the electronic device may include an acquisition module and a processing module, or an acquisition module, a sending module, and a receiving module. It should be noted that all relevant contents of the various steps involved in the above method embodiments can be referred to in the functional description of the corresponding functional modules and will not be repeated here.

[0834] The electronic device provided in this embodiment is used to execute the above-mentioned method of automatically executing order processing, and thus can achieve the same effect as the above-mentioned implementation method.

[0835] In the case of an integrated unit, the electronic device may include a processing module and a storage module. The processing module may be used to control and manage the operation of the electronic device, and the storage module may be used to support the electronic device in executing relevant program codes and data.

[0836] The processing module may be a processor or controller that implements or executes the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processing system (DSP) and a microprocessor, and the storage module may be a memory.

[0837] This embodiment also provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer executes the above-mentioned related method steps to implement a method for automatically executing order processing in the above-mentioned embodiment.

[0838] This embodiment als...

Claims

1. A method for automatically executing order processing, characterized in that: Applied to a server, the method includes: Get the rider's real-time parameters and the order parameters associated with the current order; Based on the real-time parameters of the rider and / or the order parameters, determining in real time whether a first preset condition is met; When a first preset condition is met, a first voice reminder is automatically triggered to the rider, where the first voice reminder is used to remind the rider whether to execute the target processing action associated with the current order; performing intention recognition on the first voice instruction of the rider in response to the first voice reminder; Determine whether to automatically execute the target processing action based on the intention recognition result.

2. The method according to claim 1, characterized in that The target processing action includes reporting to the store, the rider's real-time parameters include the rider's location, and the order parameters include the merchant's location and the target order status. When the target order status is the grabbed order status and at least one of the following conditions is met, it is determined that the first preset condition is met: The rider's location is within the coverage area of ​​the first signal associated with the merchant's location; The rider's position is within a first preset range associated with the merchant's position; The distance between the rider's position and the merchant's position is less than or equal to a first preset distance.

3. The method according to claim 1 or 2, characterized in that The target processing action includes reporting meal pickup. The rider's real-time parameters include the rider's arrival time and location. The order parameters include the merchant's meal delivery status, merchant location, and target order status. When the target order status is "arrived at the store" and at least one of the following conditions is met, the first preset condition is determined to be met: The rider's arrival time at the store is greater than or equal to the first preset time; The food delivery status of the merchant is already delivered; After the rider's position reaches the merchant's position, it moves away from the merchant's position and the merchant's meal delivery status is already delivered.

4. The method according to claim 1 or 2, characterized in that The target processing action includes reporting delivery, the rider's real-time parameters include the rider's location, and the order parameters include the location of the user to be delivered and the target order status. When the target order status is the food has been picked up and at least one of the following conditions is met, it is determined that the first preset condition is met: The rider's position is within the coverage area of ​​the second signal associated with the user's position; The rider's position is within a second preset range associated with the user's position; The distance between the rider position and the user position is less than or equal to a second preset distance.

5. The method according to claim 1 or 2, characterized in that The performing intention recognition on the first voice instruction of the rider in response to the first voice reminder includes: Performing intent recognition on the first voice command based on the LLM model; When the intent recognition is successful, obtaining the intent recognition result; Furthermore, determining whether to automatically execute the target processing action based on the intention recognition result includes: When the intention recognition result is to automatically execute the target processing action, a target processing instruction is sent to the user terminal to enable the user terminal to execute the target processing action, and the target processing instruction includes the execution steps of the target processing action.

6. A method for automatically executing order processing, characterized in that: Applied to a user terminal, the method includes: Get the rider's real-time parameters; Sending the rider's real-time parameters to a server, so that the server determines in real time whether a first preset condition is met based on the rider's real-time parameters and / or order parameters associated with the current order; receiving a first voice reminder sent by the server and announcing the first voice reminder, where the first voice reminder is automatically triggered by the server when the first preset condition is met, and the first voice reminder is used to remind whether to execute a target processing action associated with the current order; The first voice instruction of the rider in response to the first voice reminder is obtained and sent to the server, so that the server recognizes the intention of the first voice instruction and determines whether to automatically execute the target processing action based on the intention recognition result.

7. The method according to claim 6, characterized in that The target processing action includes reporting to the store, the rider's real-time parameters include the rider's location, and the order parameters include the merchant's location and the target order status. When the target order status is the grabbed order status and at least one of the following conditions is met, it is determined that the first preset condition is met: The rider's location is within the coverage area of ​​the first signal associated with the merchant's location; The rider's position is within a first preset range associated with the merchant's position; The distance between the rider's position and the merchant's position is less than or equal to a first preset distance.

8. The method according to claim 6 or 7, characterized in that The target processing action includes reporting meal pickup. The rider's real-time parameters include the rider's arrival time and location. The order parameters include the merchant's meal delivery status, merchant location, and target order status. When the target order status is "arrived at the store" and at least one of the following conditions is met, the first preset condition is determined to be met: The rider's arrival time at the store is greater than or equal to the first preset time; The food delivery status of the merchant is already delivered; After the rider's position reaches the merchant's position, it moves away from the merchant's position and the merchant's meal delivery status is already delivered.

9. The method according to claim 6 or 7, characterized in that The target processing action includes reporting delivery, the rider's real-time parameters include the rider's location, and the order parameters include the location of the user to be delivered and the target order status. When the target order status is the food has been picked up and at least one of the following conditions is met, it is determined that the first preset condition is met: The rider's position is within the coverage area of ​​the second signal associated with the user's position; The rider's position is within a second preset range associated with the user's position; The distance between the rider position and the user position is less than or equal to a second preset distance.

10. The method according to claim 6 or 7, characterized in that The intention recognition result is obtained when the server successfully recognizes the intention of the first voice instruction based on the LLM model; And, the method further comprises: receiving a target processing instruction sent by the server, where the target processing instruction is triggered by the server when the intention recognition result is to automatically execute the target processing action, and the target processing instruction includes execution steps of the target processing action; In response to the target processing instruction, the target processing action is performed.

Images