Robot order sending processing method, intelligent device and computer readable storage medium

Abstract

The invention provides a robot order sending processing method, intelligent equipment and a computer readable storage medium. The robot order dispatching processing method comprises the following steps: obtaining the to-be-delivered order quantity and the order quantity of each floor of a robot delivery area in a target time period; based on the order quantity of each floor and the order distribution configuration information of the robot delivery area, performing strategy planning to obtain a target order distribution strategy of the target time period; when the to-be-delivered order quantity is greater than a preset order quantity threshold value, setting the order dispatching mode of the target time period as an automatic order dispatching mode; and when the target time period is entered and the target time period is an automatic order sending mode, robot order sending processing is carried out according to the target order sending strategy. The method can reduce the order waiting time, and improves the order delivery efficiency on the basis of improving the utilization rate of the robot.

Description

Technical Field

[0001] The present application relates to the field of robotics technology, and in particular to a robot dispatch processing method, an intelligent device, and a computer-readable storage medium. Background Art

[0002] With the further maturity of robot technology and the increasing demand of consumers for automated services, robots are being applied to more and more scenarios, such as hotels, retail, warehousing and logistics. Order delivery is an important application of robots. At present, the robot delivery order scenario includes two processes: picking and delivery: first, the picker picks the goods for the robot, and then the robot completes the delivery process of the corresponding order. In related technologies, in order to improve the utilization rate of robots, a collection order delivery method is adopted. After the user places an order, the order is collected. After the collection is successful, the order is sent to the robot. The robot enters the picking task. After completing the picking of all orders in the collection order, the robot performs the delivery task. However, when the order production process and the pickup time are uncertain, the order waiting time for delivery is long, and this collection order delivery method is inefficient. Summary of the invention

[0003] The present application provides a robot dispatch processing method, an intelligent device and a computer-readable storage medium, which can reduce order waiting time and improve order delivery efficiency on the basis of improving robot utilization.

[0004] In a first aspect, the present application provides a robot dispatch processing method, the method comprising:

[0005] Obtain the number of orders to be delivered and the number of orders on each floor in the robot delivery area during the target time period;

[0006] Performing strategy planning based on the order volume on each floor and the dispatch configuration information of the robot delivery area to obtain a target dispatch strategy for the target time period;

[0007] When the quantity of the orders to be delivered is greater than a preset order quantity threshold, the order dispatching mode for the target time period is set to an automatic order dispatching mode;

[0008] When entering the target time period and the target time period is in automatic order dispatching mode, robot order dispatching is performed according to the target order dispatching strategy.

[0009] In some embodiments, the strategy planning based on the order volume on each floor and the dispatch configuration information of the robot delivery area to obtain the target dispatch strategy for the target time period includes:

[0010] Determine the value range of each variable in the order dispatching strategy variable group based on the order quantity of each floor and the order dispatching configuration information;

[0011] Based on the value range of each variable in the dispatch strategy variable group and the preset constraint conditions, the value of each variable in the dispatch strategy variable group is planned to obtain multiple dispatch strategies of the dispatch strategy variable group;

[0012] Obtaining an objective function value of each dispatching strategy, wherein the objective function value includes at least one of the total number of robots, the total delivery time, and the total delivery distance;

[0013] When the preset planning stop condition is met, the dispatching strategy with the optimal objective function value is output from multiple dispatching strategies as the target dispatching strategy for the target time period.

[0014] In some embodiments, the dispatch strategy variable group includes a stop floor variable, a robot identification variable, and a shift time point variable, and the dispatch configuration information includes robot configuration information and a maximum order-matching duration;

[0015] The determining of the value range of each variable in the order dispatching strategy variable group based on the order quantity of each floor and the order dispatching configuration information includes:

[0016] Determine a first value range of a stop floor variable in the dispatch strategy variable group based on the order quantity on each floor of the delivery area of ​​the robot;

[0017] Determining a second value range of the robot identification variable in the dispatch strategy variable group based on the robot configuration information of the robot delivery area;

[0018] Based on the maximum order-matching time in the robot delivery area, a third value range of the shift time point variable in the order dispatching strategy variable group is determined.

[0019] In some embodiments, obtaining the number of orders to be delivered and the number of orders on each floor in the robot delivery area in the target time period includes:

[0020] Acquire the first attribute data of each sub-time period of the historical time period and the order volume of each sub-time period, wherein the duration of the sub-time period is the same as the duration of the target time period;

[0021] Acquire second attribute data of the target time period, wherein the second attribute data includes at least one of time characteristics, weather characteristics, and crowd flow distribution characteristics;

[0022] Predicting based on the first attribute data of each sub-time period, the order quantity of each sub-time period and the second attribute data to obtain the order quantity to be delivered;

[0023] Based on the quantity of orders to be delivered and the floor distribution data of the robot delivery area, the quantity of orders on each floor of the robot delivery area in the target time period is determined.

[0024] In some embodiments, the step of performing prediction based on the first attribute data of each sub-time period, the order quantity of each sub-time period, and the second attribute data to obtain the quantity of orders to be delivered includes:

[0025] Perform coding processing based on the order volume of each sub-time period to obtain a coding sequence of the order volume of the historical time period;

[0026] Performing encoding processing based on the first attribute data of each sub-time period to obtain an attribute encoding sequence of the historical time period;

[0027] Performing encoding processing on the second attribute data to obtain attribute encoding features of the target time period;

[0028] The order quantity to be delivered is obtained by performing a prediction based on the order quantity coding sequence, the attribute coding sequence and the attribute coding features of the target time period.

[0029] In some embodiments, the step of performing prediction based on the order quantity coding sequence, the attribute coding sequence, and the attribute coding features of the target time period to obtain the order quantity to be delivered includes:

[0030] Extracting multi-level information based on the attribute coding sequence and the attribute coding features of the target time period to obtain multi-level attribute fusion features of the target time period;

[0031] The order quantity to be delivered is obtained by performing a prediction based on the order quantity coding sequence, the attribute coding sequence and the multi-precision attribute fusion feature.

[0032] In some embodiments, the floor distribution data includes the floor type of each floor in the robot delivery area and the flow of people on each floor, and determining the order quantity on each floor of the robot delivery area in the target time period based on the order quantity to be delivered and the floor distribution data of the robot delivery area includes:

[0033] Based on the floor type of each floor and the flow of people on each floor, obtain the proportion of the order volume on each floor;

[0034] The order quantity of each floor is determined based on the order quantity proportion of each floor and the order quantity to be delivered.

[0035] In some embodiments, the method further comprises:

[0036] When the quantity of orders to be delivered is less than or equal to a preset order quantity threshold, the order dispatching mode for the target time period is set to a manual order dispatching mode;

[0037] When entering the target time period and the target time period is in manual order dispatching mode, in response to a QR code scanning result request instruction of the target robot, sending the order status of the target robot to the front end;

[0038] In response to the order distribution request of the front end for the target robot, the order is distributed to the target robot according to the distribution order information carried in the order distribution request.

[0039] In a second aspect, the present application also provides an intelligent device, which includes a processor and a memory, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, it executes any one of the robot order processing methods provided in the present application.

[0040] In a third aspect, the present application also provides a computer-readable storage medium on which a computer program is stored, and the computer program is loaded by a processor to execute the robot order processing method.

[0041] In the present application, on the first hand, when the number of orders to be delivered is greater than the preset order quantity threshold, the dispatching mode of the target time period is set to the automatic dispatching mode. When the target time period is entered and the target time period is in the automatic dispatching mode, the robot dispatches the orders according to the target dispatching strategy, and automatically allocates the orders. Since the automatic allocation of orders does not cause a long waiting time for the orders to be delivered when the order quantity is large, the order delivery efficiency can be improved on the basis of improving the robot utilization rate. On the second hand, since the robot dispatches the orders according to the target dispatching strategy in the automatic dispatching mode, the complex and cumbersome order selection operations are reduced while ensuring the timeliness, thereby improving the order delivery efficiency. On the third hand, the target dispatching strategy for the target time period is obtained by performing strategy planning based on the order quantity on each floor and the dispatching configuration information of the robot delivery area. Since the order quantity on each floor can be used for strategy planning, the robot dispatching strategy is more rationalized, and the repetition rate of the robot driving on the same floor is reduced to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0043] Figure 1 It is a schematic block diagram of the structure of a smart device provided in an embodiment of the present application;

[0044] Figure 2It is a flow chart of a robot dispatch processing method provided in an embodiment of the present application;

[0045] Figure 3 This is a schematic diagram of an embodiment of step 201 provided in an embodiment of the present application;

[0046] Figure 4 It is a schematic diagram of a framework structure of an order prediction model provided in an embodiment of the present application;

[0047] Figure 5 It is another schematic diagram of the framework structure of the order prediction model provided in the embodiment of the present application;

[0048] Figure 6 It is a flowchart of an embodiment of step 202 provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0050] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0051] In the description of the embodiments of the present application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0052] In order to enable any person skilled in the art to implement and use the present application, the following description is provided. In the following description, details are listed for the purpose of explanation. It should be understood that those of ordinary skill in the art can recognize that the present application can also be implemented without using these specific details. In other examples, the known process will not be elaborated in detail to avoid unnecessary details that make the description of the present application embodiment obscure. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the widest range of principles and features disclosed in accordance with the embodiments of the present application.

[0053] The embodiment of the present application provides a robot dispatch processing method, an intelligent device and a computer-readable storage medium. The intelligent device may be a mobile robot, a mobile phone, a computer, etc.

[0054] Some embodiments of the present application are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0055] Figure 1 It is a schematic block diagram of the structure of a smart device provided in an embodiment of the present application.

[0056] like Figure 1 As shown, the smart device 100 includes a processor 101 and a memory 102 , and the processor 101 and the memory 102 are connected via a bus 103 , such as a PCIe (Peripheral Component Interconnect Express) bus.

[0057] Specifically, the processor 101 is used to provide computing and control capabilities to support the operation of the entire smart device 100. The processor 101 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0058] Specifically, the memory 102 may be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a mobile hard disk.

[0059] Those skilled in the art will understand that Figure 1 The structure shown in the figure is merely a block diagram of a partial structure related to the embodiment of the present application, and does not constitute a limitation on the smart device to which the embodiment of the present application is applied. The specific smart device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0060] The processor 101 is used to run the computer program stored in the memory 102, and implement any one of the robot dispatch processing methods provided in the embodiments of the present application when executing the computer program. For example, the processor 101 is used to run the computer program stored in the memory 102, and can implement the following steps when executing the computer program:

[0061] Obtain the quantity of to-be-delivered orders and the quantity of orders on each floor in a target time period in a robot delivery area; perform strategy planning based on the quantity of orders on each floor and the dispatch configuration information of the robot delivery area to obtain a target dispatch strategy for the target time period; when the quantity of to-be-delivered orders is greater than a preset order quantity threshold, set the dispatch mode for the target time period to an automatic dispatch mode; when entering the target time period and the target time period is in automatic dispatch mode, perform robot dispatch processing according to the target dispatch strategy.

[0062] In some embodiments, the processor 101 is used to run a computer program stored in the memory 102, and when executing the computer program, the following steps may be implemented:

[0063] Based on the order quantity of each floor and the dispatch configuration information, determine the value range of each variable in the dispatch strategy variable group; based on the value range of each variable in the dispatch strategy variable group and preset constraints, plan the value of each variable in the dispatch strategy variable group to obtain multiple dispatch strategies of the dispatch strategy variable group; obtain the objective function value of each dispatch strategy, wherein the objective function value includes at least one of the total number of robots, the total delivery time, and the total delivery distance; when the preset planning stop condition is met, output the dispatch strategy with the optimal objective function value from the multiple dispatch strategies as the target dispatch strategy for the target time period.

[0064] In some embodiments, the dispatch strategy variable group includes a stop floor variable, a robot identification variable, and a shift time point variable, the dispatch configuration information includes robot configuration information and a maximum order combination time, and the processor 101 is used to run a computer program stored in the memory 102, and when executing the computer program, the following steps can be implemented:

[0065] Based on the order quantity on each floor of the robot delivery area, a first value range of the stop floor variable in the dispatch strategy variable group is determined; based on the robot configuration information of the robot delivery area, a second value range of the robot identification variable in the dispatch strategy variable group is determined; based on the maximum order combination time in the robot delivery area, a third value range of the shift time point variable in the dispatch strategy variable group is determined.

[0066] In some embodiments, the processor 101 is used to run a computer program stored in the memory 102, and when executing the computer program, the following steps may be implemented:

[0067] Obtain first attribute data of each sub-time period of a historical time period and the order volume of each sub-time period, wherein the duration of the sub-time period is the same as the duration of the target time period; obtain second attribute data of the target time period, wherein the second attribute data includes at least one of time characteristics, weather characteristics, and crowd flow distribution characteristics; make predictions based on the first attribute data of each sub-time period, the order volume of each sub-time period, and the second attribute data to obtain the order volume to be delivered; determine the order volume on each floor of the robot delivery area in the target time period based on the order volume to be delivered and the floor distribution data of the robot delivery area.

[0068] In some embodiments, the processor 101 is used to run a computer program stored in the memory 102, and when executing the computer program, the following steps may be implemented:

[0069] Encoding is performed based on the order quantity of each sub-time period to obtain the order quantity coding sequence of the historical time period; encoding is performed based on the first attribute data of each sub-time period to obtain the attribute coding sequence of the historical time period; encoding is performed on the second attribute data to obtain the attribute coding characteristics of the target time period; prediction is performed based on the order quantity coding sequence, the attribute coding sequence and the attribute coding characteristics of the target time period to obtain the order quantity to be delivered.

[0070] In some embodiments, the processor 101 is used to run a computer program stored in the memory 102, and when executing the computer program, the following steps may be implemented:

[0071] Based on the attribute coding sequence and the attribute coding features of the target time period, multi-precision information extraction is performed to obtain the multi-precision attribute fusion features of the target time period; based on the order quantity coding sequence, the attribute coding sequence and the multi-precision attribute fusion features, prediction is performed to obtain the order quantity to be delivered.

[0072] In some embodiments, the floor distribution data includes the floor type of each floor in the robot delivery area and the flow of people on each floor. The processor 101 is used to run the computer program stored in the memory 102, and when executing the computer program, the following steps can be implemented:

[0073] Based on the floor type of each floor and the flow of people on each floor, the proportion of order volume on each floor is obtained; based on the proportion of order volume on each floor and the number of orders to be delivered, the order volume on each floor is determined.

[0074] In some embodiments, the processor 101 is used to run a computer program stored in the memory 102, and when executing the computer program, the following steps may be implemented:

[0075] When the quantity of orders to be delivered is less than or equal to a preset order quantity threshold, the order dispatching mode of the target time period is set to manual order dispatching mode; when entering the target time period and the target time period is in manual order dispatching mode, in response to the QR code scanning result request instruction of the target robot, the order status of the target robot is sent to the front end; in response to the order distribution request of the front end for the target robot, the order is allocated to the target robot according to the distribution order information carried in the order distribution request.

[0076] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the intelligent device described above can refer to the corresponding process in the following robot dispatching processing method embodiment, and will not be repeated here.

[0077] In the following, Figure 1 The robot dispatch processing method provided by the embodiment of the present application is described in detail by taking the smart device shown in as the execution subject of the robot dispatch processing method as an example. For the sake of simplicity and convenience of description, the execution subject will be omitted in the subsequent method embodiments. Figure 1 The scenario is only used to explain the robot dispatching processing method provided in the embodiment of the present application, but does not constitute a limitation on the application scenario of the robot dispatching processing method provided in the embodiment of the present application.

[0078] See also Figure 2 , Figure 2 201 to 204, wherein:

[0079] 201. Obtain the number of orders to be delivered and the number of orders on each floor in the robot delivery area during the target time period.

[0080] Among them, the robot delivery area can be buildings, such as hotels, office buildings, etc.

[0081] Among them, the order in this embodiment can be a take-out order (the delivery address of the take-out order can be outside the robot delivery area or inside the robot delivery area), an express delivery order, etc.

[0082] There are many ways to implement step 201, illustratively including:

[0083] (1) In some embodiments, the number of orders to be delivered and the number of orders on each floor can be statistically obtained based on the actual order data of the robot delivery area in the target time period. For example, after the user places an order through the order terminal (such as the order applet), the new order (such as a takeout order) will be sent to the backend; or the manager of the robot delivery area can actively upload the order (such as a courier order just delivered to the hotel lobby) to the backend; the backend will add the new order or the newly uploaded order as an unscheduled order to the order pool to be scheduled; the number of orders in the order pool to be scheduled in the target time period can be counted as the number of orders to be delivered. And based on the delivery address of each order in the order pool to be scheduled in the target time period, the number of orders on each floor is statistically obtained.

[0084] (2) In some embodiments, since it is necessary to use the order volume on each floor to plan the target dispatching strategy, in order to avoid the problem of low planning accuracy of the target dispatching strategy due to the real-time nature of order data update, and thus avoid the problem of invalid planning of the target dispatching strategy, the order volume on each floor at the target time can also be predicted. Figure 3 As shown, step 201 may specifically include the following steps 2011 to 2014:

[0085] 2011. Obtain first attribute data of each sub-time period of a historical time period and the order volume of each sub-time period.

[0086] The historical time period may be the past n hours, n days, n weeks, n months, etc. There is no restriction on the historical time period.

[0087] Among them, the sub-time period is the period for analyzing order characteristics. For example, if the historical time period is the past n hours, the sub-time period can be 1 hour, if the historical time period is the past n days, the sub-time period can be 1 day, and so on. The length of the sub-time period is the same as the length of the target time period.

[0088] The first attribute data of each sub-time period includes at least one of the time characteristics, weather characteristics, and crowd flow distribution characteristics of each sub-time period.

[0089] Specifically, the actual order data of each sub-time period of the historical time period may be used to count the order volume of each sub-time period.

[0090] 2012. Obtain second attribute data of the target time period, wherein the second attribute data includes at least one of time characteristics, weather characteristics, and crowd flow distribution characteristics.

[0091] For example, if the target time period is the current day, then the current time characteristics (such as month, whether it is a holiday, etc.), weather characteristics (such as cloudy, sunny, etc.), crowd distribution characteristics (such as hotel occupancy rate, etc.) and other information can be obtained as the second attribute data of the target time period.

[0092] 2013. Perform prediction based on the first attribute data of each sub-time period, the order quantity of each sub-time period and the second attribute data to obtain the quantity of orders to be delivered.

[0093] There are many ways to implement step 2013, which include, for example:

[0094] ① In some embodiments, prediction is performed using the order quantity coding sequence, the attribute coding sequence, and the attribute coding features of the target time period. At this time, step 2013 may specifically include the following steps A1 to A4:

[0095] A1. Perform coding processing based on the order volume of each sub-time period to obtain a coding sequence of the order volume of the historical time period.

[0096] Specifically, Figure 4 As shown, the trained order prediction model can be called to implement step 2013. The trained order prediction model can include an order quantity encoding module, an attribute encoding module, a first sequence processing module, a second sequence processing module, and a prediction module. The order quantity encoding module can be a One-Hot vector model, etc., and the attribute encoding module can be a Word2Vec model, etc.

[0097] Exemplarily, first, encoding processing is performed based on the order quantity of each sub-time period to obtain the order quantity coding features of each sub-time period, wherein the order quantity of each sub-time period can be encoded by the order quantity encoding module of the order prediction model, and the order quantity coding features of each sub-time period are obtained and then input into the first sequence processing module; then, the order quantity coding features of each sub-time period are sequentially spliced ​​together by the first sequence processing module according to the order of each sub-time period to obtain a sequence of order quantity coding features as the order quantity coding sequence of the historical time period.

[0098] A2. Perform encoding processing based on the first attribute data of each sub-time period to obtain an attribute encoding sequence of the historical time period.

[0099] Exemplarily, first, encoding processing is performed based on the first attribute data of each sub-time period to obtain the attribute coding features of each sub-time period, wherein the first attribute data of each sub-time period can be encoded by the attribute coding module of the order prediction model to obtain the attribute coding features of each sub-time period and then input into the second sequence processing module; then, the attribute coding features of each sub-time period are sequentially spliced ​​together by the second sequence processing module according to the chronological order of each sub-time period to obtain a sequence of attribute coding features as the attribute coding sequence of the historical time period.

[0100] A3. Encode the second attribute data to obtain attribute coding features of the target time period.

[0101] The second attribute data of the target time period can be encoded by the attribute encoding module of the order prediction model to obtain the attribute encoding features of the target time period.

[0102] A4. Predicting based on the order quantity coding sequence, the attribute coding sequence and the attribute coding features of the target time period to obtain the order quantity to be delivered.

[0103] Specifically, after obtaining the order quantity coding sequence of the historical time period, the sequence is input into the prediction module of the order prediction model, after obtaining the attribute coding sequence of the historical time period, the sequence is input into the prediction module of the order prediction model, and after obtaining the attribute coding feature of the target time period, the sequence is input into the prediction module, and the prediction module of the prediction model is used to predict the order quantity to be delivered based on the order quantity coding sequence, the attribute coding sequence, and the attribute coding feature of the target time period. In this way, by predicting based on the order quantity coding sequence, the attribute coding sequence, and the attribute coding feature of the target time period, the association between the order quantity coding sequence and the attribute coding sequence can be captured, thereby mining the potential features between the order quantity and the attribute data, and improving the accuracy of predicting the order quantity to be delivered using the attribute coding feature of the target time period.

[0104] ② In some embodiments, prediction is performed based on the order quantity coding sequence, the attribute coding sequence and the multi-precision attribute fusion feature. At this time, step 2013 may specifically include the following steps B1 to B5:

[0105] B1. Perform coding processing based on the order volume of each sub-time period to obtain a coding sequence of the order volume of the historical time period.

[0106] Specifically, Figure 5As shown, the trained order prediction model can be called to implement step 2013. The trained order prediction model can include an order quantity encoding module, an attribute encoding module, a first sequence processing module, a second sequence processing module, a multi-level information extraction module, and a prediction module. The multi-level information extraction module can be a Transformer structure based on an attention mechanism.

[0107] B2. Perform encoding processing based on the first attribute data of each sub-time period to obtain an attribute encoding sequence of the historical time period.

[0108] B3. Encode the second attribute data to obtain attribute coding features of the target time period.

[0109] The implementation of steps B1 to B3 is similar to that of steps A1 to A3. For details, please refer to the relevant instructions above and will not be repeated here.

[0110] B4. Extract multi-precision information based on the attribute coding sequence and the attribute coding features of the target time period to obtain multi-precision attribute fusion features of the target time period.

[0111] Specifically, in the multi-precision information extraction module that is input into the prediction model after obtaining the attribute coding sequence, and in the multi-precision information extraction module that is input into the prediction model after obtaining the attribute coding features of the target time period, through the multi-precision information extraction module, first, the attribute coding features of the target time period are spliced ​​into the attribute coding sequence in chronological order to obtain a new sequence; then, the new sequence is divided into multiple levels of detail to obtain multiple subsequences of different time details; each subsequence of each time detail is encoded respectively to obtain the coding features of each subsequence of each time detail; the coding features of multiple subsequences of different time details are fused to obtain the multi-precision attribute fusion features of the target time period.

[0112] B5. Predict the order quantity to be delivered based on the order quantity coding sequence, the attribute coding sequence and the multi-precision attribute fusion feature.

[0113] Specifically, after obtaining the order quantity coding sequence of the historical time period, the sequence is input into the prediction module of the order prediction model, after obtaining the attribute coding sequence of the historical time period, the sequence is input into the prediction module of the order prediction model, and after obtaining the multi-precision attribute fusion feature of the target time period, the sequence is input into the prediction module, and the prediction module of the prediction model is used to predict the order quantity to be delivered based on the order quantity coding sequence, the attribute coding sequence and the multi-precision attribute fusion feature. In this way, by predicting based on the multi-precision attribute fusion feature, attribute feature subsequences of different precisions can be captured, thereby mining the deep relationship between the order quantity and the attribute data, and improving the prediction accuracy of the order quantity to be delivered.

[0114] 2014. Determine the order quantity on each floor of the robot delivery area in a target time period based on the quantity of orders to be delivered and the floor distribution data of the robot delivery area.

[0115] In some embodiments, the floor distribution data includes the floor type of each floor in the robot delivery area and the flow of people on each floor. The order volume share of each floor can be obtained based on the floor type of each floor and the flow of people on each floor; the order volume of each floor can be determined based on the order volume share of each floor and the number of orders to be delivered.

[0116] 202. Perform strategy planning based on the order quantity on each floor and the dispatch configuration information of the robot delivery area to obtain a target dispatch strategy for the target time period.

[0117] For example, Figure 6 As shown, step 202 may specifically include the following steps 2021 to 2024:

[0118] 2021. Based on the order quantity on each floor and the order dispatch configuration information, determine the value range of each variable in the order dispatch strategy variable group.

[0119] Depending on the settings of the variables, there are many ways to implement step 2021. The following takes cases ①, ② and ③ as examples:

[0120] ① In some embodiments, each variable in the dispatch strategy variable group includes a stop floor variable, a robot identification variable, and a shift time point variable. At this time, step 2021 may specifically include steps C1 to C3:

[0121] C1. Determine a first value range of the stop floor variable in the dispatch strategy variable group based on the order quantity on each floor of the robot delivery area.

[0122] For ease of understanding, some of the names involved in the embodiments of this application are first introduced below:

[0123] 1. Robot identification Ri: indicates the identification of the robot used in the i-th shift.

[0124] 2. Shift time point Ti: indicates the time point when the i-th shift completes distribution and starts delivery.

[0125] 3. Stopping floors {Aij}: is an array of length j, indicating the stopping floors of each order in the i-th shift, where J is the maximum number of orders allowed for each shift. The stopping floor Aij can be 0 or any floor value within the robot's delivery area. 0 means no floor is passed.

[0126] 4. Dispatch strategy: Each dispatch strategy is used to indicate the shift information of the target time period (including the robot identification Ri, shift time point Ti, and stop floors {Aij} of each shift i). During the strategy process in step 202, multiple dispatch strategies may be generated, and finally one is selected as the target dispatch strategy for the target time period.

[0127] 5. Order delivery process: It includes two processes: picking and delivering. First, the picking staff completes the picking of the corresponding order for the robot, and then the robot completes the delivery process of the corresponding order.

[0128] In an embodiment of the present application, a dispatch strategy variable group such as (Ri, Ti, {Aij}) is constructed. When the values ​​of each variable in the dispatch strategy variable group (such as Ri, Ti and {Aij}) are determined, a dispatch strategy can be obtained: the robot identifier Ri of each shift i, the shift time point Ti, and the stop floor {Aij}. Therefore, according to the dispatch strategy (such as the required number of robots obtained by counting the robot identifiers Ri of each shift), robots can be configured for the robot delivery area (such as enabling certain robots in the robot delivery area so that the number of working robots is equal to the required number of robots obtained by planning) for order delivery in the target time period, and according to the dispatch strategy (such as the robot identifier Ri of each shift i and the shift time point Ti), the corresponding robot is assigned goods, and according to the dispatch strategy (such as the stop floor {Aij}), the corresponding robot is controlled to complete the delivery process of the corresponding order.

[0129] Among them, the first value range refers to the value range of the variable of the stop floor. In some embodiments, a floor identification set can be used to maintain the first value range. For example, assuming that the robot delivery area has 3 floors: floor 1 has 2 orders, floor 2 has 3 orders, and floor 3 has 4 orders, then the first value range can be {F1, F1, F2, F2, F2, F3, F3, F3, F3}, where F1, F2, and F3 respectively indicate that the stop floors are floor 1, floor 2, and floor 3. In order to ensure that each order can be delivered, each time a dispatch strategy is planned in step 2022, the stop floors in the dispatch strategy include each value in the first value range.

[0130] C2. Determine a second value range of the robot identification variable in the dispatch strategy variable group based on the robot configuration information of the robot delivery area.

[0131] The second value range refers to the value range of the robot identification variable.

[0132] At this time, the dispatch configuration information may include the robot configuration information of the robot delivery area, and the robot configuration information includes but is not limited to the number of available robots, the names of each robot, the models of each robot, etc. At this time, the value range of the robot identification variable in the dispatch strategy variable group may be set based on the robot configuration information of the robot delivery area. Among them, each robot in the robot delivery area may be identified by a serial number, name or model, so as to obtain a second value range of each robot identification.

[0133] C3. Determine a third value range of the shift time point variable in the dispatch strategy variable group based on the maximum order-matching time in the robot delivery area.

[0134] Among them, the third value range refers to the value range of the shift time point variable.

[0135] The dispatch configuration information may include the maximum order-matching time in the robot delivery area. At this time, the latest shift time point in the target time period is determined based on the maximum order-matching time period and the start time point of the target time period; the second value range of the shift time point variable is determined based on the start time point of the target time period and the latest shift time point of the target time period.

[0136] ② In some embodiments, each variable in the dispatch strategy variable group includes a stop floor variable and a robot identification variable. At this time, step 2021 may specifically include steps D1 to D2:

[0137] D1. Determine a first value range of a stop floor variable in the dispatch strategy variable group based on the order quantity on each floor of the delivery area of ​​the robot;

[0138] D2. Determine a second value range of the robot identification variable in the dispatch strategy variable group based on the robot configuration information of the robot delivery area.

[0139] ③ In some embodiments, each variable in the dispatch strategy variable group includes a stop floor variable and a shift time point variable. At this time, step 2021 may specifically include steps E1 to E2:

[0140] E1. Determine a first value range of the stop floor variable in the order dispatch strategy variable group based on the order quantity on each floor of the robot delivery area.

[0141] E2. Determine a third value range of the shift time point variable in the dispatch strategy variable group based on the maximum order-matching time in the robot delivery area.

[0142] 2022. Based on the value range of each variable in the order dispatching strategy variable group and preset constraints, plan the value of each variable in the order dispatching strategy variable group to obtain multiple order dispatching strategies of the order dispatching strategy variable group.

[0143] Among them, the preset constraints include but are not limited to the maximum one-way order quantity of the robot, the shift interval of the same robot, and each order can only be delivered by one robot.

[0144] Specifically, in some embodiments, first, when planning the values ​​of the dispatch strategy variable group for the first time, under the condition that the preset constraints are met, according to the value range of each variable in the dispatch strategy variable group, a value is selected for each variable in the dispatch strategy variable group and set as the value of the corresponding variable. After the values ​​of each variable in the dispatch strategy variable group are set, a planned dispatch strategy can be obtained; then, when planning the values ​​of the dispatch strategy variable group for the second time and each time thereafter, based on the values ​​of each variable obtained in the previous planning, any variable can be selected from the dispatch strategy variable group as the variable for this planning; under the condition that the preset constraints are met, a value is randomly selected in the value range of the variable for this planning to change the value of the variable for this planning in the dispatch strategy variable group. By analogy, multiple planning can be performed, and a dispatch strategy can be obtained each time the values ​​of the dispatch strategy variable group are planned.

[0145] 2023. Obtain the objective function value of each order dispatching strategy.

[0146] The objective function value includes at least one of the total number of robots, the total delivery time, the total delivery distance, and the total number of shifts.

[0147] Depending on the setting of the objective function, there are many ways to implement step 2024. <1> , <2> and <3> For example:

[0148] <1> , the objective function value is the total number of robots. At this time, the objective function is a function for calculating the total number of robots. Step 2024 may specifically include: based on the robot identification of each shift of each dispatch strategy, counting the total number of robots for each dispatch strategy. For example, a dispatch strategy variable group such as (Ri, Ti, {Aij}) is constructed. When the values ​​of each variable (such as Ri, Ti and {Aij}) in the dispatch strategy variable group are determined, a dispatch strategy can be obtained: the robot identification Ri of each shift i, the shift time point Ti, and the stop floor {Aij}), so that the robot identification Ri of each shift i in the dispatch strategy can be recorded as one robot according to the same robot identification, and the total number of robots in the dispatch strategy can be counted.

[0149] <2> , the objective function value is the total delivery time. At this time, the objective function is a function for calculating the total delivery time. Step 2024 may specifically include: based on the stopping floors of each shift of each dispatch strategy, counting the delivery time of each shift of each dispatch strategy; based on the delivery time of each shift of each dispatch strategy, counting the total delivery time of each dispatch strategy.

[0150] <3> , the objective function value is the total delivery distance. In this case, the objective function is a function that calculates the total delivery distance (such as M is the total number of shifts for this dispatching strategy, d i Represents the delivery distance of the i-th shift) Step 2024 may specifically include: based on the stopping floors of each shift of each dispatch strategy, counting the delivery distance of each shift of each dispatch strategy; based on the delivery distance of each shift of each dispatch strategy, counting the total delivery distance of each dispatch strategy.

[0151] <4> , the objective function value includes the total number of robots, the total delivery time and the total delivery distance. At this time, step 2024 may specifically include: based on the robot identification of each shift of each dispatch strategy, counting the total number of robots of each dispatch strategy; based on the stopping floors of each shift of each dispatch strategy, counting the delivery time of each shift of each dispatch strategy; based on the delivery time of each shift of each dispatch strategy, counting the total delivery time of each dispatch strategy; based on the stopping floors of each shift of each dispatch strategy, counting the delivery distance of each shift of each dispatch strategy; based on the delivery distance of each shift of each dispatch strategy, counting the total delivery distance of each dispatch strategy.

[0152] 2024. When the preset planning stop condition is met, the dispatching strategy with the optimal objective function value is output from multiple dispatching strategies as the target dispatching strategy for the target time period.

[0153] In some embodiments, the objective function value is the total number of robots. In this case, the dispatch strategy with the least total number of robots can be output from multiple dispatch strategies as the target dispatch strategy.

[0154] In some implementations, the objective function value is the total delivery time efficiency. In this case, the dispatch strategy with the highest total delivery time efficiency can be output from multiple dispatch strategies as the target dispatch strategy.

[0155] In some implementations, the objective function value is the total delivery distance. In this case, the dispatch strategy with the shortest total delivery distance can be output from multiple dispatch strategies as the target dispatch strategy.

[0156] In some implementations, the objective function value includes the total number of robots and the total delivery time. In this case, the dispatch strategy with the highest total delivery time can be selected from multiple dispatch strategies; then, from the dispatch strategies with the highest total delivery time, the dispatch strategy with the least total number of robots can be output as the target dispatch strategy.

[0157] 203. When the quantity of the orders to be delivered is greater than a preset order quantity threshold, the order dispatching mode in the target time period is set to an automatic order dispatching mode.

[0158] Among them, the specific value of the preset order quantity threshold can be set according to the actual business scenario requirements, and there is no restriction on the specific value of the preset order quantity threshold here.

[0159] On the one hand, when the number of orders to be delivered is greater than the preset order volume threshold, the dispatch mode for the target time period is set to automatic dispatch mode, so that orders can be automatically grouped and distributed. Since automatic grouping of orders does not cause a long waiting time for orders to be delivered when the order volume is large, automatic dispatch can reduce complex and tedious order selection operations while ensuring timeliness, thereby improving order delivery efficiency.

[0160] On the other hand, when the quantity of orders to be delivered is less than or equal to the preset order quantity threshold, the dispatch mode of the target time period is set to manual dispatch mode; in this way, the automatic dispatch mode can be turned off during the time period with low order quantity, avoiding the problem of excessive waiting time due to automatic order combination, and improving order delivery efficiency. When entering the target time period and the target time period is in manual dispatch mode, in response to the target robot's QR code scanning result request instruction, the order status of the target robot is sent to the front end; in response to the front end's order distribution request for the target robot, the order is distributed to the target robot according to the distribution order information carried in the order distribution request, so that the target robot completes the delivery process of the corresponding order. For example, taking a distribution system including a front-end, a back-end, a robot and an order end (such as an ordering mini program) as an example, after a user places an order through the order end (such as an ordering mini program), the new order will be sent to the back-end; the back-end will add the new order as an unscheduled order to the pool of orders to be dispatched; the delivery personnel scan the QR code labeled on the robot through the front-end (such as a mobile phone, a gun, etc.) to enter the robot's delivery page, and the front-end requests the current robot information from the back-end; on the delivery page provided by the front-end, the delivery personnel can view the robot information (such as the robot's abnormal status, delivery status, order status, etc.), complete the robot delivery process (such as selecting delivery orders and delivery slots for the robot), etc. After the delivery personnel selects the order, the front-end will send the selected delivery order information to the back-end, and the back-end will assign the corresponding order to the target robot according to the delivery order information.

[0161] 204. When entering the target time period and the target time period is in automatic order dispatching mode, robot order dispatching is performed according to the target order dispatching strategy.

[0162] Exemplarily, when entering the target time period and the target time period is in automatic dispatch mode, the required number of robots for the target time period is obtained by counting the shift information corresponding to the target dispatch strategy (such as the robot identification Ri of each shift); robots are configured for the robot delivery area (such as enabling certain robots in the robot delivery area so that the number of working robots is equal to the required number of robots obtained by planning); and according to the shift information corresponding to the target dispatch strategy (such as the robot identification Ri of each shift, the shift time point Ti, and the stop floors {Aij}), orders for corresponding stop floors {Aij} are assigned to corresponding robots, so that the corresponding robots complete the delivery process of the corresponding orders.

[0163] From the above content, it can be seen that, on the first hand, by setting the dispatch mode of the target time period to the automatic dispatch mode when the number of orders to be delivered is greater than the preset order volume threshold, when entering the target time period and the target time period is in the automatic dispatch mode, the robot dispatches orders according to the target dispatch strategy, and can automatically allocate orders. Since the automatic allocation of orders when the order volume is large will not cause the order to wait for a long time before delivery can begin, the delivery efficiency can be improved on the basis of improving the robot utilization rate; on the second hand, since the robot dispatches orders according to the target dispatch strategy can be automatically processed in the automatic dispatch mode, the complex and cumbersome order selection operations are reduced while ensuring timeliness, thereby improving the order delivery efficiency; on the third hand, by performing strategy planning based on the order volume of each floor and the dispatch configuration information of the robot delivery area, the target dispatch strategy for the target time period is obtained. Since the order volume of each floor can be used for strategy planning, the robot dispatch strategy is more reasonable, and the repetition rate of the robot driving on the same floor is reduced to a certain extent.

[0164] A person of ordinary skill in the art can understand that all or part of the steps in the above-mentioned robot dispatching processing method can be completed by instructions, or by controlling related hardware through instructions. The instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0165] To this end, an embodiment of the present application provides a computer-readable storage medium, in which a plurality of computer programs are stored, and the computer program can be loaded by a processor to execute any robot dispatch processing method provided in the embodiment of the present application. For example, the computer program can be loaded by a processor to execute the following steps:

[0166] Obtain the quantity of to-be-delivered orders and the quantity of orders on each floor in a target time period in a robot delivery area; perform strategy planning based on the quantity of orders on each floor and the dispatch configuration information of the robot delivery area to obtain a target dispatch strategy for the target time period; when the quantity of to-be-delivered orders is greater than a preset order quantity threshold, set the dispatch mode for the target time period to an automatic dispatch mode; when entering the target time period and the target time period is in automatic dispatch mode, perform robot dispatch processing according to the target dispatch strategy.

[0167] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0168] In the above-mentioned robot dispatch processing method, computer-readable storage medium, and intelligent device embodiments, the description of each embodiment has its own emphasis. For parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process and beneficial effects of the above-described computer-readable storage medium, intelligent device, and its corresponding units can refer to the description of the robot dispatch processing method in the above embodiment, and will not be repeated here.

[0169] The above is a detailed introduction to a robot dispatch processing method, an intelligent device and a computer-readable storage medium provided in an embodiment of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A robot dispatch processing method, characterized in that: The method comprises: Obtain the number of orders to be delivered and the number of orders on each floor in the robot delivery area during the target time period; Performing strategy planning based on the order volume on each floor and the dispatch configuration information of the robot delivery area to obtain a target dispatch strategy for the target time period; When the quantity of the orders to be delivered is greater than a preset order quantity threshold, the order dispatching mode for the target time period is set to an automatic order dispatching mode; When entering the target time period and the target time period is in automatic order dispatching mode, robot order dispatching is performed according to the target order dispatching strategy.

2. The robot dispatch processing method according to claim 1, characterized in that: The strategy planning is performed based on the order quantity of each floor and the dispatch configuration information of the robot delivery area to obtain the target dispatch strategy for the target time period, including: Determine the value range of each variable in the order dispatching strategy variable group based on the order quantity of each floor and the order dispatching configuration information; Based on the value range of each variable in the dispatch strategy variable group and the preset constraint conditions, the value of each variable in the dispatch strategy variable group is planned to obtain multiple dispatch strategies of the dispatch strategy variable group; Obtaining an objective function value of each dispatching strategy, wherein the objective function value includes at least one of the total number of robots, the total delivery time, and the total delivery distance; When the preset planning stop condition is met, the dispatching strategy with the optimal objective function value is output from multiple dispatching strategies as the target dispatching strategy for the target time period.

3. The robot dispatch processing method according to claim 2, characterized in that: The dispatch strategy variable group includes a stop floor variable, a robot identification variable, and a shift time point variable, and the dispatch configuration information includes robot configuration information and a maximum order-matching duration; The determining of the value range of each variable in the order dispatching strategy variable group based on the order quantity of each floor and the order dispatching configuration information includes: Determine a first value range of a stop floor variable in the dispatch strategy variable group based on the order quantity on each floor of the delivery area of ​​the robot; Determining a second value range of the robot identification variable in the dispatch strategy variable group based on the robot configuration information of the robot delivery area; Based on the maximum order-matching time in the robot delivery area, a third value range of the shift time point variable in the order dispatching strategy variable group is determined.

4. The robot dispatch processing method according to claim 1, characterized in that: The method of obtaining the number of orders to be delivered and the number of orders on each floor in the robot delivery area during the target time period includes: Acquire the first attribute data of each sub-time period of the historical time period and the order volume of each sub-time period, wherein the duration of the sub-time period is the same as the duration of the target time period; Acquire second attribute data of the target time period, wherein the second attribute data includes at least one of time characteristics, weather characteristics, and crowd flow distribution characteristics; Predicting based on the first attribute data of each sub-time period, the order quantity of each sub-time period and the second attribute data to obtain the order quantity to be delivered; Based on the quantity of orders to be delivered and the floor distribution data of the robot delivery area, the quantity of orders on each floor of the robot delivery area in the target time period is determined.

5. The robot dispatch processing method according to claim 4, characterized in that: The step of performing prediction based on the first attribute data of each sub-time period, the order quantity of each sub-time period and the second attribute data to obtain the quantity of orders to be delivered includes: Perform coding processing based on the order volume of each sub-time period to obtain a coding sequence of the order volume of the historical time period; Performing encoding processing based on the first attribute data of each sub-time period to obtain an attribute encoding sequence of the historical time period; Performing encoding processing on the second attribute data to obtain attribute encoding features of the target time period; The order quantity to be delivered is obtained by performing a prediction based on the order quantity coding sequence, the attribute coding sequence and the attribute coding features of the target time period.

6. The robot dispatch processing method according to claim 5, characterized in that: The step of performing prediction based on the order quantity coding sequence, the attribute coding sequence and the attribute coding features of the target time period to obtain the order quantity to be delivered includes: Extracting multi-level information based on the attribute coding sequence and the attribute coding features of the target time period to obtain multi-level attribute fusion features of the target time period; The order quantity to be delivered is obtained by performing a prediction based on the order quantity coding sequence, the attribute coding sequence and the multi-precision attribute fusion feature.

7. The robot dispatch processing method according to claim 4, characterized in that: The floor distribution data includes the floor type of each floor in the robot delivery area and the flow of people on each floor. The determining the order quantity on each floor of the robot delivery area in the target time period based on the order quantity to be delivered and the floor distribution data of the robot delivery area includes: Based on the floor type of each floor and the flow of people on each floor, obtain the proportion of the order volume on each floor; The order quantity of each floor is determined based on the order quantity proportion of each floor and the order quantity to be delivered.

8. The robot dispatch processing method according to claim 1, characterized in that: The method further comprises: When the quantity of orders to be delivered is less than or equal to a preset order quantity threshold, the order dispatching mode for the target time period is set to a manual order dispatching mode; When entering the target time period and the target time period is in manual order dispatching mode, in response to a QR code scanning result request instruction of the target robot, sending the order status of the target robot to the front end; In response to the order distribution request of the front end for the target robot, the order is distributed to the target robot according to the distribution order information carried in the order distribution request.

9. A smart device, characterized in that: It includes a processor and a memory, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the robot dispatching processing method as described in any one of claims 1 to 8 is executed.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is loaded by a processor to execute the robot dispatching processing method described in any one of claims 1 to 8.

Images