Operation execution method and device of intelligent equipment, processor and vehicle

Abstract

The invention discloses an operation execution method and device of intelligent equipment, a processor and a vehicle. The method comprises the steps that the priority of at least one target job to be executed is obtained, an initial task allocation strategy of the target job is determined based on the priority, the priority is used for representing the sequence of triggering at least one intelligent device to execute the target job, and the initial task allocation strategy is used for representing that the target job is executed according to the priority; distributing a rule of the target job to at least one intelligent device; adjusting the initial task allocation strategy at least based on the state information of the at least one intelligent device to obtain a target job allocation strategy; determining a to-be-moved target path of the target intelligent equipment based on the first position of the target intelligent equipment and the second position corresponding to the target operation; and according to the target path, controlling the target intelligent equipment to move to the operation position so as to execute the target operation. The technical problem that the operation cannot be effectively executed on the intelligent equipment is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle logistics, in particular to a work execution method and device of an intelligent device, a processor and a vehicle. BACKGROUND

[0002] At present, in order to avoid the problem that the efficiency of human execution of target work is low and prone to errors, intelligent devices can be introduced to improve work accuracy. However, the target work execution mechanism of the intelligent device is often too simple, for example, the target work execution of the intelligent device is performed according to the order of creation of the target work. The above target work execution mode depending on the fixed order is prone to delay of high-priority target work (task), and the intelligent device may also be idle for a long time when executing the target work, which cannot be fully utilized. Therefore, there is still a technical problem that the work of the intelligent device cannot be effectively executed.

[0003] At present, there is no effective solution to the technical problem that the work of the intelligent device cannot be effectively executed. SUMMARY

[0004] The embodiments of the present application provide a work execution method and device of an intelligent device, a processor and a vehicle, to at least solve the technical problem that the work of the intelligent device cannot be effectively executed.

[0005] According to an aspect of an embodiment of the present application, a work execution method of an intelligent device is provided. The method comprises: obtaining a priority of at least one target work to be executed, and determining an initial task allocation strategy of the target work based on the priority, wherein the priority is used to indicate the order of triggering at least one intelligent device to execute the target work, and the initial task allocation strategy is used to indicate the rule of allocating the target work to the at least one intelligent device according to the priority; adjusting the initial task allocation strategy based on at least state information of the at least one intelligent device to obtain a target work allocation strategy, wherein the state information is used to indicate the idle degree of the intelligent device, the target work allocation strategy is used to indicate the rule of allocating the target work to a target intelligent device in the at least one intelligent device, and the state information of the target intelligent device meets a state information threshold; determining a target path to be moved by the target intelligent device based on a first position where the target intelligent device is located and a second position corresponding to the target work, wherein the second position is used to indicate the position of the work site where the target intelligent device executes the target work; and controlling the target intelligent device to move to the work site according to the target path to execute the target work.

[0006] Optionally, the initial task allocation strategy of the target job is determined based on the priority, including: determining a first initial task allocation strategy, a second initial task allocation strategy and / or a third initial task allocation strategy of the target job based on the priority, wherein the first initial task allocation strategy is used to represent a rule of allocating the target job to at least one smart device according to the order of the creation time of the target job, the second initial task allocation strategy is used to represent a rule of allocating the target job to at least one smart device according to the arrangement order of the importance of the target job, and the third initial task allocation strategy is used to represent a rule of allocating the target job to at least one smart device according to the arrangement order of the distance between the second position and the first position of at least one smart device; and determining the initial task allocation strategy from the first initial task allocation strategy, the second initial task allocation strategy and / or the third initial task allocation strategy.

[0007] Optionally, the first initial task allocation strategy of the target job is determined based on the priority, including: in response to the number of target jobs being multiple, generating a first priority according to the order of the creation time of the multiple target jobs; and generating the first initial task allocation strategy according to the first priority, wherein the allocation time of the corresponding first initial task allocation strategy of the target job with the first priority greater than a priority threshold is earlier than the allocation time of the corresponding first initial task allocation strategy of the target job with the first priority less than the priority threshold.

[0008] Optionally, the second initial task allocation strategy of the target job is determined based on the priority, including: in response to the number of target jobs being multiple, generating a second priority according to the importance of the target job, wherein the importance is used to represent the importance of the target job; and generating the second initial task allocation strategy according to the second priority, wherein the allocation time of the corresponding second initial task allocation strategy of the target job with the second priority greater than a priority threshold is earlier than the allocation time of the corresponding second initial task allocation strategy of the target job with the second priority less than the priority threshold.

[0009] Optionally, the third initial task allocation strategy of the target job is determined based on the priority, including: obtaining the first position of at least one smart device in an idle state; in response to the number of target jobs being multiple, generating a third priority according to the distance between the second position of the multiple target jobs and the first position; and generating the third initial task allocation strategy according to the third priority, wherein the allocation time of the corresponding third initial task allocation strategy of the target job with the third priority greater than a priority threshold is earlier than the allocation time of the corresponding third initial task allocation strategy of the target job with the third priority less than the priority threshold.

[0010] Optionally, the method further comprises: determining a job scene of the target job to be executed, and determining an adjustment strategy of the initial task allocation strategy based on the job scene, wherein the adjustment strategy is used to represent a rule of adjusting the initial task allocation strategy; and adjusting the initial task allocation strategy based on at least the state information of the intelligent device to obtain the target job allocation strategy, comprising: adjusting the initial task allocation strategy based on at least the state information of the at least one intelligent device according to the adjustment strategy to obtain the target job allocation strategy.

[0011] Optionally, the job scene comprises a first job scene, the first job scene is used to represent that the target job is allocated to the intelligent device corresponding to the first position whose distance to the second position is less than the distance threshold, and adjusting the initial task allocation strategy based on at least the state information of the at least one intelligent device according to the adjustment strategy to obtain the target job allocation strategy comprises: in response to the job scene being the first job scene and the target job to be executed being detected, obtaining a distance difference between the first position of the at least one intelligent device in the idle state and the second position; and in response to the distance difference being less than or equal to the distance threshold, determining that the target job allocation strategy is a first target job allocation strategy, wherein the first target job allocation strategy is used to represent a rule of allocating the target job to the intelligent device in the idle state whose distance difference is less than the distance threshold.

[0012] Optionally, the job scene comprises a second job scene, the second job scene is used to represent that the target job with a priority higher than a priority threshold is allocated to the intelligent device in the idle state, and adjusting the initial task allocation strategy based on at least the state information of the at least one intelligent device according to the adjustment strategy to obtain the target job allocation strategy comprises: in response to the job scene being the second job scene and the intelligent device in the idle state being detected, obtaining a target job set to be executed in a target area of the intelligent device, wherein the target area is a region centered on the intelligent device in the idle state; and based on the target job set, determining that the target job allocation strategy is a second target job allocation strategy, wherein the second target job allocation strategy is used to represent a rule of allocating the target job to the intelligent device in the idle state according to the priority of at least one target job to be executed in the target job set.

[0013] Optionally, the method further comprises: obtaining the remaining power of the intelligent device and the remaining mileage of the intelligent device; in response to the remaining power being less than or equal to a remaining power threshold and the remaining mileage satisfying a distance between the intelligent device and the corresponding charging device, determining a charging driving path of the intelligent device; and controlling the intelligent device to move to a position where the charging device is located to charge according to the charging driving path.

[0014] Optionally, the method further comprises: obtaining the number of tasks executed by the at least one smart device in the target period and / or the execution duration of the job; in response to the number of tasks executed being less than or equal to a number threshold and / or the execution duration of the job being less than or equal to a duration threshold, adjusting the priority of the at least one smart device in the next period of the target period, wherein the adjusted priority of the at least one smart device is greater than the priority of the at least one smart device before adjustment; in response to the number of tasks executed being greater than the number threshold and / or the execution duration of the job being greater than the duration threshold, adjusting the priority of the task assigned to the at least one smart device in the next period, wherein the adjusted priority of the at least one smart device is greater than the priority of the at least one smart device before adjustment.

[0015] Optionally, the target path to be moved by the target smart device is determined based on the first position of the target smart device and the second position corresponding to the target job, comprising: determining a candidate path set based on the first position and the second position, wherein the candidate path set comprises at least one candidate path; and determining the target path from the candidate path set.

[0016] Optionally, the target path is determined from the candidate path set, comprising: in response to the number of at least one smart device in an idle state at the current time being multiple, deleting the target path of at least one smart device other than the current smart device from the candidate path set to obtain a target candidate path set of the current smart device; and determining the candidate path with the shortest duration required for performing the target job in the target candidate path set as the target path of the current smart device.

[0017] According to another aspect of the embodiments of the present application, an apparatus for performing a job of a smart device is also provided. The apparatus can comprise: an obtaining unit configured to obtain a priority of at least one target job to be performed, and determine an initial task assignment strategy of the target job based on the priority, wherein the priority is used to indicate the order of triggering at least one smart device to perform the target job, and the initial task assignment strategy is used to indicate the rule of assigning the target job to the at least one smart device according to the priority; an adjusting unit configured to adjust the initial task assignment strategy based on at least state information of the smart device to obtain a target job assignment strategy, wherein the state information is used to indicate the idle degree of the smart device, the target job assignment strategy is used to indicate the rule of assigning the target job to a target smart device in the at least one smart device, and the state information of the target smart device satisfies a state information threshold; a determining unit configured to determine a target path to be moved by the target smart device based on a first position of the target smart device and a second position corresponding to the target job, wherein the second position is used to indicate the position of a job site at which the target smart device performs the target job; and a control unit configured to control the target smart device to move to the job site according to the target path to perform the target job.

[0018] According to another aspect of the embodiments of the present application, a computer readable storage medium is also provided. The computer readable storage medium includes a stored program, wherein the program, when executed by an apparatus in which the computer readable storage medium is located, controls the apparatus to perform the job execution method of the smart device according to the embodiments of the present application.

[0019] According to another aspect of the embodiments of the present application, a processor is also provided. The processor is configured to execute a program, wherein the program, when executed, performs the job execution method of the smart device according to the embodiments of the present application.

[0020] According to another aspect of the embodiments of the present application, a computer program product is also provided. The computer program product includes a computer program, which, when executed by a processor, implements the job execution method of the smart device according to the embodiments of the present application.

[0021] According to another aspect of the embodiments of the present application, a vehicle is also provided. The vehicle is configured to perform the job execution method of the smart device according to the embodiments of the present application.

[0022] In the embodiments of the present application, for the problem of task allocation for smart devices, an initial task allocation strategy can be formulated according to the priority order of the to-be-executed job tasks, the task is allocated to the smart device, the initial task allocation strategy is dynamically adjusted according to the real-time state information of the smart device, and a target job allocation strategy is obtained, so as to ensure that the job task can be allocated to the target smart device suitable for execution. After the target smart device and the target job are determined, the target path of the target smart device moving to the job position can be calculated according to the current position (corresponding to the first position) of the target smart device and the position (corresponding to the second position) of the target job, so that the target smart device moves to the job position according to the planned target path to execute the target job. The above method overcomes the job execution mode depending on a fixed order in the related art, which causes the high-priority task to be delayed, and the smart device may also be idle for a long time when executing the job. The above method achieves the technical effect of effectively executing the job of the smart device, and solves the technical problem that the job of the smart device cannot be effectively executed. BRIEF DESCRIPTION OF DRAWINGS

[0023] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

[0024] Figure 1 is a flowchart of a job execution method of a smart device according to an embodiment of the present application;

[0025] Figure 2is a flow chart of a method for task allocation and path optimization of a smart device according to an embodiment of the present application;

[0026] Figure 3 is a schematic diagram of a smart device performing a target task according to an embodiment of the present application;

[0027] Figure 4 is a schematic diagram of a topological map according to an embodiment of the present application;

[0028] Figure 5 is a schematic diagram of a node conflict according to an embodiment of the present application;

[0029] Figure 6 is a schematic diagram of a head-on conflict according to an embodiment of the present application;

[0030] Figure 7 is a schematic diagram of an overtaking conflict according to an embodiment of the present application;

[0031] Figure 8 is a schematic diagram of a task execution device of a smart device according to an embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to make the personnel in the art better understand the present application scheme, the technical scheme in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0034] According to an embodiment of the present application, an embodiment of a method for executing a task of a smart device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0035] Figure 1 is a flowchart of a method for executing a task of a smart device according to an embodiment of the present application, as shown in Figure 1 The method can include the following steps:

[0036] In step S102, the priority of at least one target task to be executed is obtained, and based on the priority, an initial task allocation strategy of the target task is determined.

[0037] In the technical solution provided in step S102 of the present application, the priority can be used to represent the order of triggering the target task to be executed by the at least one smart device, and the initial task allocation strategy is used to represent the rule of allocating the target task to the at least one smart device according to the priority. The smart device can be a drone, an automated guided vehicle (AGV), a robot cluster, etc., which are only used as examples and are not limited specifically herein.

[0038] In this embodiment, the priority is a key indicator for measuring the urgency and importance of the target task execution. In the scenario of a logistics warehouse, the target task can be a picking task, a transportation task, a loading and unloading task, a packaging task, etc., which are only used as examples and are not limited specifically herein.

[0039] Optionally, the initial task allocation strategy is a smart device allocation rule formulated for each target task according to the priority of the target task currently obtained. Since the priority of the target task is considered, the initial task allocation strategy can ensure that tasks with high priority can be processed first, and the resources of the smart device can be utilized reasonably.

[0040] Optionally, the priority of the target task can be determined by a pre-set rule. For example, in a picking task, if the picking task is to meet a specific delivery time window, especially for those orders with a tight time window, such picking tasks can be assigned a higher priority. For example, in a transportation task, if the energy of the smart device (such as an AGV) is about to run out, and the destination of the transportation task is close to a charging station, the task can be allocated preferentially to ensure that the smart device can be timely replenished with energy after completing the task, avoiding interruption of the target task due to insufficient energy of the smart device.

[0041] Optionally, the priority of the target job can also be predicted by a machine learning algorithm. For example, data such as the urgency of historical tasks, out-of-stock situations, and production delays are analyzed to train a model to predict the priority of the target job, achieving more accurate scheduling.

[0042] It should be noted that the above-mentioned manner of obtaining the priority of the target job and the content are only illustrative, and are not specifically limited herein. As long as the manner can be used to obtain the priority of the at least one target job to be executed and determine the initial task allocation strategy of the target job based on the priority, it is within the protection scope of the embodiments of the present application, and will not be illustrated one by one herein.

[0043] In step S104, the initial task allocation strategy is adjusted based on at least the state information of the at least one smart device to obtain a target job allocation strategy.

[0044] In the technical solution provided in the above step S104 of the present application, the state information is used to represent the idle degree of the smart device, the target job allocation strategy is used to represent the rule of allocating the target job to a target smart device in the at least one smart device, and the state information of the target smart device satisfies a state information threshold. The state information is the working state data of the smart device at a certain moment, which can be the working state, the load state, or the power state of the smart device. The working state can be used to represent that the smart device is in a busy state or an idle state. For example, whether the smart device is currently executing a task (busy state) or waiting for a new task (idle state).

[0045] In this embodiment, after obtaining the priority of the at least one target job to be executed and determining the initial task allocation strategy of the target job based on the priority, the initial task allocation strategy can be adjusted based on at least the state information of the at least one smart device to obtain a target job allocation strategy, thereby ensuring that the task can be properly assigned to the smart device suitable for executing the task, while considering the working state data of the smart device at a certain moment, the target job efficiency and resource utilization can be maximized. The target job allocation strategy can be referred to as a task dispatching strategy.

[0046] Optionally, the setting of the state information threshold can depend on the technical specifications of the smart device, the requirements of the target job environment, etc. For example, a power threshold is set, and if the remaining power of the smart device is lower than the power threshold, the smart device will no longer be allocated a new task, but will be guided to a charging station. For another example, a load threshold is set, and if the load of the smart device exceeds the load threshold, the smart device will no longer accept a new task.

[0047] For example, the initial task allocation strategy can be dynamically adjusted to optimize the use of the smart device and the completion of the task, if the state information of the smart device meets the state information threshold. For example, if it is found that the smart device has low power or is full of load, and the smart device is assigned a new task, the initial task allocation strategy can be adjusted, and the target task allocation strategy obtained can be to reassign the task to another smart device that meets the conditions.

[0048] For example, in the case where multiple smart devices meet the state information threshold condition, a smart device in an idle state can be preferentially selected to perform a task to reduce the idle time of the smart device and improve overall efficiency.

[0049] In the embodiments of the present application, through the dynamic adjustment of the initial task allocation strategy, a more reasonable and efficient target task allocation strategy can be developed under the premise that the state information of the target smart device meets the device state information threshold, thereby improving the overall performance of the smart device.

[0050] In step S106, based on the first position of the target smart device and the second position corresponding to the target task, a target path to be moved by the target smart device is determined.

[0051] In the technical solution provided in step S106 of the present application, the second position is used to represent the position of the work site where the target smart device performs the target task.

[0052] In this embodiment, after adjusting the initial task allocation strategy based on at least the state information of at least one smart device to obtain a target task allocation strategy, path planning can be performed based on the first position (such as the starting position) of the target smart device and the second position (such as the target position) corresponding to the target task to determine the target path to be moved by the target smart device.

[0053] Optionally, the goal of path planning is to find a shorter, faster or safer target path from the first position to the second position, while considering the priority of the target task and the state information of the smart device. The path planning method can be A* algorithm, which finds a suitable target path from the starting position to the target position by combining heuristic search strategies (such as shortest distance estimation).

[0054] Optionally, the path planning needs to consider the current position of the intelligent device, ensuring that the path planning starts from the correct starting point. The work position needs to be considered, that is, the starting position and the ending position of the target work, to determine the destination of the path planning. Environmental constraints, such as the layout of the logistics warehouse, the positions of other intelligent devices or obstacles, and possible dynamic changes (such as movement of other intelligent devices, appearance of temporary obstacles, etc.), need to be considered to ensure the feasibility of the target path.

[0055] Optionally, the path planning is not only performed at the time of task allocation, but can also be adjusted in real time as the state of the intelligent device and the environment changes. For example, if a temporary obstacle or another intelligent device is encountered during the execution of the task by the intelligent device, the path can be re-planned to avoid collision and delay, ensuring the smooth progress of the target work.

[0056] Step S108, according to the target path, control the target intelligent device to move to the work position to execute the target work.

[0057] In the technical solution provided by step S108 of the present application described above, the target intelligent device to be moved can be determined according to the target work allocation strategy previously formulated and the target path determined through path planning, and the specified intelligent device (target intelligent device) can be accurately controlled to move to the work position to execute the allocated target work, thereby ensuring the efficiency of the execution of the target work.

[0058] In this embodiment, after the target intelligent device reaches the specified work position, the accuracy of the position can be confirmed through the sensors or communication interfaces of the target intelligent device, and the target work execution program on the target intelligent device can be started. For example, in a picking task, the intelligent device identifies and carries specific materials to a specified position, and in a transportation task, the intelligent device can automatically load or unload materials and move to the next work position or destination to complete the execution of the target work.

[0059] Optionally, according to the target path, the target intelligent device is controlled to move to the work position, and the intelligent device can quickly respond and execute the task according to the target path, reducing the time for material handling, picking and other work. By ensuring that the intelligent device can accurately reach the specified work position according to the previously planned target path, and then execute the allocated task, the problem of ineffective execution of the task by the intelligent device is solved.

[0060] The above steps S102 to S108 of the embodiment of the present application can be used to solve the problem of task allocation for intelligent devices. According to the priority order of the to-be-executed task, an initial task allocation strategy can be formulated to allocate tasks to intelligent devices. The initial task allocation strategy can be dynamically adjusted according to real-time state information of the intelligent devices to obtain a target task allocation strategy, so as to ensure that the task can be allocated to a target intelligent device suitable for execution. After the target intelligent device and the target task are determined, the target path of the target intelligent device moving to the task location can be calculated according to the current location (corresponding to the first location) of the target intelligent device and the location (corresponding to the second location) of the target task, so that the target intelligent device can be controlled to move to the task location according to the planned target path to execute the target task. The above method overcomes the task execution mode relying on a fixed order in the related art, which may cause high-priority tasks to be delayed and the intelligent device to be idle for a long time when executing tasks. The above method achieves the technical effect of effectively executing tasks for intelligent devices and solves the technical problem of being unable to effectively execute tasks for intelligent devices.

[0061] The above method of the embodiment will be further described below.

[0062] As an optional embodiment, in step S102, the initial task allocation strategy of the target task is determined based on the priority, including: determining a first initial task allocation strategy, a second initial task allocation strategy and / or a third initial task allocation strategy of the target task based on the priority, wherein the first initial task allocation strategy is used to represent a rule of allocating the target task to at least one intelligent device according to the order of the creation time of the target task, the second initial task allocation strategy is used to represent a rule of allocating the target task to at least one intelligent device according to the arrangement order of the importance of the target task, and the third initial task allocation strategy is used to represent a rule of allocating the target task to at least one intelligent device according to the arrangement order of the proximity between the second location and the first location of at least one intelligent device; and the initial task allocation strategy is determined from the first initial task allocation strategy, the second initial task allocation strategy and / or the third initial task allocation strategy.

[0063] In this embodiment, in the process of determining the initial task allocation strategy of the target job based on the priority, the priority of the target job can be analyzed, and three different initial task allocation strategies of the target job can be determined based on the priority: a first initial task allocation strategy, a second initial task allocation strategy, and a third initial task allocation strategy; the initial task allocation strategy can be determined from the first initial task allocation strategy, the second initial task allocation strategy, and / or the third initial task allocation strategy. The first initial task allocation strategy can be used to represent a rule for allocating the target job to at least one smart device according to the order of creation time of the target job. The second initial task allocation strategy can be used to represent a rule for allocating the target job to at least one smart device according to the order of importance of the target job. The third initial task allocation strategy can be used to represent a rule for allocating the target job to at least one smart device according to the order of proximity between the second position and the first position of the at least one smart device.

[0064] Optionally, the first initial task allocation strategy can allocate the target job to the available smart device according to the principle of first created first executed according to the creation time of the target job. This allocation method is simple and direct, easy to implement, and suitable for scenarios where the priority of the target job is not clear or the target jobs are equally important.

[0065] Optionally, the second initial task allocation strategy can prioritize the target job according to the importance of the target job, and allocate the target job with higher priority to the smart device first. The basis for judging the importance can include the urgency of the target job, the value of the involved materials, the impact on the production line, etc., to ensure that the target job can be executed in time and reduce the loss caused by the delay of the target job.

[0066] Optionally, the third initial task allocation strategy can allocate the job to the smart device closest to the job site to reduce the time and distance of the smart device traveling empty, and improve the utilization rate of the smart device.

[0067] As an optional embodiment, the first initial task allocation strategy of the target job is determined based on the priority, which includes: in response to the number of target jobs being multiple, generating a first priority according to the order of creation time of the multiple target jobs; generating a first initial task allocation strategy according to the first priority, wherein the target job with a first priority greater than a priority threshold has a first initial task allocation strategy with an allocation time earlier than the target job with a first priority less than the priority threshold.

[0068] In the embodiment, in the process of determining the first initial task allocation strategy of the target job based on the priority, when the number of target jobs is multiple, the first priority can be generated according to the chronological order of the creation time of the multiple target jobs; and the first initial task allocation strategy can be generated according to the first priority. Wherein, the target job with the first priority greater than the priority threshold value corresponds to the allocation time of the first initial task allocation strategy earlier than the allocation time of the first initial task allocation strategy corresponding to the target job with the first priority less than the priority threshold value. The generation of the first initial task allocation strategy based on the chronological order of the job creation time and the priority threshold value ensures that more urgent tasks are processed first, thereby improving the overall job efficiency.

[0069] Optionally, when it is detected that the number of target jobs to be processed is multiple, the first priority can be generated according to the chronological order of the creation time of the target jobs to be processed. For example, the earlier the creation time of a target job, the higher the first priority, which means that the target job can be allocated to the intelligent device earlier.

[0070] Optionally, the priority threshold value can be used to distinguish the urgency of the job. If the priority of the target job is greater than the priority threshold value, the corresponding target job has higher urgency and needs to be processed first, and the intelligent device is assigned with an earlier allocation time; otherwise, if the priority of the target job is less than the priority threshold value, the corresponding target job will be regarded as a secondary or regular task, and the intelligent device will be arranged to execute the task after more urgent tasks are processed.

[0071] As an optional embodiment, determining the second initial task allocation strategy of the target job based on the priority includes: in response to the number of target jobs being multiple, generating a second priority according to the importance of the target job, wherein the importance is used to represent the importance of the target job; and generating the second initial task allocation strategy according to the second priority, wherein the target job with the second priority greater than the priority threshold value corresponds to the allocation time of the second initial task allocation strategy earlier than the allocation time of the second initial task allocation strategy corresponding to the target job with the second priority less than the priority threshold value.

[0072] In the embodiment, in the process of determining the second initial task allocation strategy of the target job based on the priority, the second priority can be generated according to the importance of the target job when the number of target jobs is multiple; and the second initial task allocation strategy can be generated according to the second priority. The importance can be used to represent the importance of the target job. The target job with the second priority greater than the priority threshold has an allocation time of the corresponding second initial task allocation strategy earlier than the target job with the second priority less than the priority threshold.

[0073] Optionally, when the second priority of the target job is greater than the priority threshold, the target job belongs to a high importance category and needs to be processed in priority; on the contrary, the target job with the second priority less than the priority threshold is considered to be of lower importance and can be arranged to be processed at a later time. The second initial task allocation strategy generated based on the second priority ensures that the priority of the high importance job is reflected in the time of task allocation. Specifically, for the target job with the second priority greater than the priority threshold, the time of allocation to the smart device will be earlier than the target job with the second priority less than the priority threshold. Therefore, by reasonably controlling the execution order of the task, it can be ensured that the task will not be affected by waiting, and at the same time, non-urgent tasks can also be arranged in time to fully utilize the job gap of the smart device.

[0074] In the embodiment of the application, the second initial task allocation strategy provides a more fine and targeted task scheduling scheme by introducing the importance of the target job and the setting of the priority threshold, and flexibly adjusts the order and time of task execution according to the actual working state of the smart device and the priority demand, so that the smart device scheduling is more efficient and intelligent.

[0075] As an optional embodiment, determining the third initial task allocation strategy of the target job based on the priority includes: obtaining a first position of at least one smart device in an idle state; in response to the number of target jobs being multiple, generating a third priority according to the proximity degree of the distance between the second position of the multiple target jobs and the first position; and generating a third initial task allocation strategy according to the third priority, wherein the target job with the third priority greater than the priority threshold has an allocation time of the corresponding third initial task allocation strategy earlier than the target job with the third priority less than the priority threshold.

[0076] In the embodiment, in the process of determining the third initial task allocation strategy of the target job based on the priority, the first position of at least one smart device in an idle state can be acquired; in the case that the number of target jobs is multiple, the third priority can be generated according to the distance between the second position of the multiple target jobs and the first position; and the third initial task allocation strategy can be generated according to the third priority. The target job with the third priority greater than the priority threshold has an allocation time of the corresponding third initial task allocation strategy earlier than the target job with the third priority less than the priority threshold.

[0077] Optionally, based on the distance between the target job and the smart device in an idle state, the third initial task allocation strategy can be generated by greedy allocation, which not only considers the creation time or importance of the task, but also integrates the position information to improve the response speed of the smart device and reduce the empty load cost. The greedy allocation is to generate the third initial task allocation strategy based on the proximity principle and short empty load time.

[0078] Optionally, the position information (the first position) of the smart device in an idle state can be acquired by a global positioning system (GPS) module, a laser radar, a radio frequency identification (RFID) tag or an indoor positioning system built in the smart device, which is only an example and is not limited specifically.

[0079] Optionally, based on the distance between the target job and the smart device, the third priority can be generated. The closer the distance between the target job and the smart device, the higher the third priority, which means that the corresponding target job will be assigned to the nearby idle smart device in priority. On the contrary, the target job with a longer distance has a lower priority and can be delayed until a more suitable smart device appears. According to the third priority, the third initial task allocation strategy can be generated for each target job. For example, if the third priority of the target job is greater than the priority threshold, the target job can be arranged with an earlier allocation time, that is, the smart device will move to the job position for processing in priority. On the contrary, the target job with the third priority less than the priority threshold has a relatively late allocation time, which is arranged after the target job with a high priority is processed according to the dynamic idle time of the smart device.

[0080] In the embodiment of the present application, by combining distance priority and greedy allocation, tasks closer to the intelligent device can be quickly responded and prioritized, while maintaining high utilization of the intelligent device and balanced allocation of target jobs, effectively improving the overall performance and response speed of intelligent logistics.

[0081] As an optional embodiment, the method further comprises: determining a job scene of the target job to be executed, and determining an adjustment strategy of the initial task allocation strategy based on the job scene, wherein the adjustment strategy is used to represent a rule for adjusting the initial task allocation strategy; and adjusting the initial task allocation strategy based on at least the state information of the intelligent device to obtain the target job allocation strategy, comprising: adjusting the initial task allocation strategy based on at least the state information of the at least one intelligent device according to the adjustment strategy to obtain the target job allocation strategy.

[0082] In this embodiment, the job scene of the target job to be executed can be determined, and the adjustment strategy of the initial task allocation strategy can be determined based on the job scene; in the process of adjusting the initial task allocation strategy based on at least the state information of the intelligent device to obtain the target job allocation strategy, the initial task allocation strategy can be adjusted based on at least the state information of the at least one intelligent device according to the adjustment strategy to obtain the target job allocation strategy. The adjustment strategy can be used to represent a rule for adjusting the initial task allocation strategy.

[0083] Optionally, the determination of the job scene is based on the nature of the task and the execution environment, for example, the job scene can be high-density cargo handling, cross-departmental material distribution, equipment maintenance and inspection, which are only examples and are not limited specifically here. For different job scenes, corresponding adjustment strategies are formulated to adapt to the specific requirements of the scene. For example, in the high-density cargo handling scene, the adjustment strategy focuses on minimizing the collision risk between intelligent devices, by increasing the safety distance between intelligent devices or adjusting the travel speed of intelligent devices, to ensure the safety of target job execution.

[0084] Optionally, after determining the adjustment strategy, the initial task allocation strategy can be adjusted to obtain the target job allocation strategy by monitoring the state information of the intelligent device in real time, such as the power, load condition, maintenance state and current position of the intelligent device, so as to more flexibly cope with complex and variable working environment, and ensure the effective execution of the target job and the efficient utilization of the intelligent device.

[0085] As an optional embodiment, the job scene includes a first job scene, the first job scene is used to represent that the target job is assigned to the smart device corresponding to the first position, and the distance between the first position and the second position is less than the distance threshold, and the initial task allocation strategy is adjusted based on at least the state information of the at least one smart device according to the adjustment strategy to obtain the target job allocation strategy, including: in response to the job scene being the first job scene and the target job to be executed being detected, obtaining the distance difference between the first position and the second position of the at least one smart device in the idle state; in response to the distance difference being less than or equal to the distance threshold, determining that the target job allocation strategy is a first target job allocation strategy, wherein the first target job allocation strategy is used to represent the rule of assigning the target job to the smart device in the idle state with the distance difference less than the distance threshold.

[0086] In this embodiment, in the process of adjusting the initial task allocation strategy based on at least the state information of the at least one smart device according to the adjustment strategy to obtain the target job allocation strategy, the distance difference between the first position and the second position of the at least one smart device in the idle state can be obtained when the job scene is the first job scene and the target job to be executed is detected; the target job allocation strategy can be determined as the first target job allocation strategy when the distance difference is less than or equal to the distance threshold. The first target job allocation strategy can be used to represent the rule of assigning the target job to the smart device in the idle state with the distance difference less than the distance threshold.

[0087] Optionally, the first job scene refers to a task scene that requires short-distance movement between the smart device and the job target position. For example, in a logistics storage environment, when the smart device is in an idle state and located at or adjacent to the position of some to-be-processed materials, the scene can be the first job scene.

[0088] Optionally, in the first job scene, the state information of the smart device can be detected to ensure that the smart device is in an idle state, and then for each target job to be executed, the distance difference between the first position of the at least one smart device in the idle state and the second position of the job is calculated. If the distance difference is less than the distance threshold, the first target job allocation strategy can be to preferentially assign the target job to the smart device, that is, to preferentially assign the target job to the idle smart device with a small distance difference.

[0089] Optionally, the above task dispatching by the nearest smart device can ensure that the task is completely executed according to the task list priority, that is, the task dispatching according to the proximity principle, and the first target job allocation strategy preferentially considers the job with a small distance difference to reduce the idle running time of the smart device and improve the job efficiency.

[0090] As an optional embodiment, the job scene includes a second job scene, the second job scene is used to indicate that the target job with a priority higher than the priority threshold is assigned to the intelligent device in the idle state, and the initial task allocation strategy is adjusted according to the adjustment strategy based on at least the state information of the at least one intelligent device to obtain a target job allocation strategy, including: in response to the job scene being the second job scene and the idle state of the intelligent device being detected, obtaining a target job set to be executed in a target area of the intelligent device, wherein the target area is a region centered on the intelligent device in the idle state; based on the target job set, determining that the target job allocation strategy is a second target job allocation strategy, wherein the second target job allocation strategy is used to indicate that the target job is assigned to the intelligent device in the idle state according to the priority of at least one target job to be executed in the target job set.

[0091] In this embodiment, in the process of adjusting the initial task allocation strategy according to the adjustment strategy based on at least the state information of the at least one intelligent device to obtain the target job allocation strategy, the target job set to be executed in the target area of the intelligent device can be obtained in the case that the job scene is the second job scene and the idle state of the intelligent device is detected; the target job allocation strategy can be determined to be the second target job allocation strategy based on the target job set. The target area can be a region centered on the intelligent device in the idle state. The second target job allocation strategy can be used to indicate that the target job is assigned to the intelligent device in the idle state according to the priority of at least one target job to be executed in the target job set.

[0092] Optionally, the second job scene refers to that the intelligent device in the idle state gives priority to task allocation in the surrounding target area. The target area is a certain range centered on the idle intelligent device, for example, a distance from the current position of the intelligent device or a preset area that the intelligent device can quickly reach. In this scene, the tasks in the area near the intelligent device can be processed preferentially to reduce the idle running time of the intelligent device and improve the resource utilization efficiency.

[0093] Optionally, when the intelligent device is detected to be in the idle state, the target area around the intelligent device is automatically searched to discover and collect the target job to be executed in the area to form a target job set, the target job with a priority higher than the priority threshold can be selected from the target job set, and the target job allocation strategy is determined to be the second target job allocation strategy based on the target job set to perform the target job allocation.

[0094] Optionally, the above-mentioned task sequence with the shortest idle time is to reduce the idle time of the intelligent device, and when the second target task allocation strategy is generated, the task sequence that can make the idle time of the intelligent device shortest is given priority, which means that after the intelligent device finishes processing the current task, the starting position of the next task should be as close as possible to the current or expected ending position of the intelligent device, so as to reduce the idle time of the intelligent device during moving between two tasks.

[0095] As an optional embodiment, the method further comprises: obtaining the remaining power of the intelligent device and the remaining mileage of the intelligent device; in response to the remaining power being less than or equal to a remaining power threshold and the remaining mileage satisfying the distance between the intelligent device and the corresponding charging device, determining a charging travel path of the intelligent device; and controlling the intelligent device to move to the position of the charging device according to the charging travel path to charge.

[0096] In this embodiment, the remaining power and the remaining mileage of the intelligent device can be monitored. The remaining power reflects the storage energy of the current battery of the intelligent device, and the remaining mileage is the maximum distance that the intelligent device can travel according to the current power. A remaining power threshold can be set, and when the remaining power of the intelligent device is less than or equal to the remaining power threshold, the charging travel path planning process is automatically started. According to the planned charging travel path, a control command is sent to the intelligent device to move the intelligent device to the position of the charging device according to the planned path to charge.

[0097] As an optional embodiment, the method further comprises: obtaining the number of executed tasks and / or the execution time of the task of at least one intelligent device in the target period; in response to the number of executed tasks being less than or equal to a number threshold and / or the execution time of the task being less than or equal to a time threshold, adjusting the priority of the at least one intelligent device in the next period of the target period, wherein the adjusted priority of the at least one intelligent device is greater than the priority of the at least one intelligent device before adjustment; in response to the number of executed tasks being greater than the number threshold and / or the execution time of the task being greater than the time threshold, adjusting the task allocation priority of the at least one intelligent device in the next period, wherein the adjusted priority of the at least one intelligent device is greater than the priority of the at least one intelligent device before adjustment.

[0098] In this embodiment, the scheduling and task allocation of the smart devices need to consider the usage efficiency and health status of the smart devices to avoid the phenomenon of "overwork" or "starvation" of the smart devices, and ensure the balanced use and long-term sustainability of the resources of the smart devices. Therefore, the number of tasks executed by at least one smart device in a target period and / or the execution time of the job can be obtained, and in the case that the number of tasks executed is less than or equal to a number threshold and / or the execution time of the job is less than or equal to a time threshold, the priority of the at least one smart device is adjusted in the next period of the target period. In the case that the number of tasks executed is greater than the number threshold and / or the execution time of the job is greater than the time threshold, the task allocation priority of the at least one smart device is adjusted in the next period. The target period can be one day, which is only an example and is not specifically limited here.

[0099] Optionally, taking a day as the target period, the number of tasks executed by each smart device in the day and the execution time of the job in the day can be recorded, and the smart device with a shorter number of tasks executed can be preferentially assigned tasks. In order to distinguish the usage state of the smart device, a number threshold and a time threshold can be set. The setting of the above two thresholds can be determined based on the average working capacity, the maximum working load of the smart device, and the maintenance and maintenance of the smart device.

[0100] Optionally, if the number of tasks executed is less than or equal to the number threshold or the execution time of the job is less than or equal to the time threshold, it means that the smart device can continue to work, and at the beginning of the next target period (such as the next day), the priority of the smart device satisfying the above condition can be adjusted, and the adjusted priority will be greater than the priority before adjustment, which means that the above smart device can be preferentially considered for task allocation to fully utilize the working potential of the smart device. If the number of tasks executed is greater than the number threshold or the execution time of the job is greater than the time threshold, it means that the smart device needs to stop using or maintaining, and at the beginning of the next period, the task allocation priority of the overloaded smart device can be adjusted, and for the smart device whose workload has been overloaded, its priority in task allocation can be reduced to ensure that the smart device can rest or perform necessary maintenance and inspection, and avoid overwork of the smart device.

[0101] As an optional embodiment, in step S106, based on the first position where the target smart device is located and the second position corresponding to the target job, a target path to be moved by the target smart device is determined, including: determining a candidate path set based on the first position and the second position, wherein the candidate path set includes at least one candidate path; and determining the target path from the candidate path set.

[0102] In this embodiment, in the process of determining the target path to be moved by the target intelligent device based on the first position where the target intelligent device is located and the second position corresponding to the target job, the candidate path set can be determined based on the first position and the second position, and the target path can be determined from the candidate path set. The candidate path set includes at least one candidate path.

[0103] Optionally, when the target intelligent device is assigned one or more target jobs, the candidate path set can be generated based on the current position (the first position) of the intelligent device and the target position (the second position) of the job. The candidate path set is not limited to one candidate path, but includes multiple possible candidate path options, and each candidate path can be generated based on different optimization targets, such as the shortest time, the shortest distance, or the minimum energy consumption. After the candidate path set is determined, the target path can be determined from the candidate path set.

[0104] As an optional embodiment, determining the target path from the candidate path set includes: in response to the number of at least one intelligent device in an idle state at the current time being multiple, deleting the target path of at least one intelligent device other than the current intelligent device from the candidate path set to obtain a target candidate path set of the current intelligent device; and determining the candidate path with the shortest execution time of the target job in the target candidate path set as the target path of the current intelligent device.

[0105] In this embodiment, in the process of determining the target path from the candidate path set, in the case where the number of at least one intelligent device in an idle state at the current time is multiple, the target path of at least one intelligent device other than the current intelligent device can be deleted from the candidate path set to obtain a target candidate path set of the current intelligent device; and the candidate path with the shortest execution time of the target job in the target candidate path set can be determined as the target path of the current intelligent device.

[0106] Optionally, when it is detected that multiple intelligent devices are in an idle state, the path set related to the current intelligent device, i.e., the target candidate path set, can be selected from the candidate path set to remove the candidate paths irrelevant to the current intelligent device, so as to ensure that the candidate path selection is only for the current intelligent device, thereby simplifying the complexity of the candidate path selection. In the target candidate path set, the execution time of each candidate path can be further analyzed to determine the candidate path with the shortest execution time of the target job, thereby obtaining the target path of the current intelligent device.

[0107] Optionally, when it is detected that two candidate paths may meet or overlap at a certain point, the two paths can be marked as conflicting paths, and when determining the target path of the current intelligent device, the marked conflicting paths can be excluded to ensure the safety and feasibility of the selected target path.

[0108] Optionally, the conflicting paths cannot be selected at the same time, and the constraint condition can be:

[0109]

[0110] wherein i can be used to represent an intelligent device, h(i) can be used to represent that the ith path is selected, and C can be used to represent a conflicting path pair.

[0111] In the embodiments of the present application, for the problem of task allocation of intelligent devices, an initial task allocation strategy can be formulated according to the priority order of the to-be-executed task, the task is allocated to the intelligent device, and the initial task allocation strategy is dynamically adjusted according to the real-time state information of the intelligent device to obtain a target task allocation strategy, so as to ensure that the task can be allocated to the target intelligent device suitable for execution. After the target intelligent device and the target task are determined, the target path of the target intelligent device moving to the task position can be calculated according to the current position (corresponding to the first position) of the target intelligent device and the position (corresponding to the second position) of the target task, so as to control the target intelligent device to move to the task position according to the planned target path to execute the target task. The above method overcomes the task execution mode depending on a fixed order in the related art, which leads to the delay of high-priority tasks and the long idle time of the intelligent device when executing the task, realizes the technical effect of effectively executing the task of the intelligent device, and solves the technical problem that the task of the intelligent device cannot be effectively executed.

[0112] The technical solutions of the embodiments of the present application will be described below in conjunction with preferred embodiments.

[0113] At present, due to the low efficiency and error-prone of human task execution, in order to improve the efficiency of on-site picking operation, it is usually considered to invest intelligent devices, and the comprehensive improvement of software combined with hardware helps to effectively improve the accuracy and work efficiency of on-site operation. However, the complexity of warehouse logistics tasks determines that in most cases, multiple intelligent devices will be used in collaborative operation mode, and therefore the following problems will arise: how to reasonably assign tasks, which tasks have the highest priority, how to promote the execution order of the task, and how to make the task not have a starvation phenomenon. After specifying the task, which device is selected to execute the task, how many intelligent devices are needed in the workshop to achieve the highest efficiency, etc. Therefore, there is still the technical problem that the task of the intelligent device cannot be effectively executed.

[0114] The application provides a smart device task allocation and path optimization method, which processes and calculates task information, station information, appliance information, delivery site information, arrival site information, smart device state information and the like, forms a smart device task allocation scheme meeting a task time requirement under a predetermined constraint condition, and outputs relevant scheduling information according to a predetermined rule, so as to realize multi-smart device scheduling and timely delivery to a destination, thereby realizing reasonable allocation of smart devices, unified and efficient management of smart devices, and achieving the technical effect of effectively performing a job by the smart device, and solving the technical problem that the smart device cannot effectively perform a job.

[0115] The application embodiment is further introduced below.

[0116] Figure 2 It is a flowchart of a smart device task allocation and path optimization method according to the application embodiment, and the method comprises the following steps:

[0117] In step S202, the smart device is in a low power state or a sudden failure state.

[0118] In this embodiment, the working state of the smart device (device) can be idle state, busy state, charging state and failure state. The smart device in the failure state and the charging state cannot perform task allocation.

[0119] Optionally, in the logistics warehouse scenario, the working state of the smart device in the warehouse can be monitored, and only the smart device in the idle state can accept the allocation of a new task group; the smart device in the busy state can accept a newly created task in the nearest time neighborhood when performing the combined task, and meet the nearest allocation principle and other constraint conditions of task combination.

[0120] Optionally, the remaining power of the device is considered when allocating the task, whether the remaining power can support the transportation work of the entire task group, for the device with the remaining power lower than the power threshold, the target point is automatically set to the charging area, and the path command is sent to the corresponding device. For example, the number of tasks executed by each device and the work duration of each device are recorded in a day, and the smart device with fewer times and shorter work duration is preferentially allocated the task. According to the comparison relationship between the battery remaining power and the mileage, the task group is allocated, so that the vehicle has excess power to drive to the nearby charging area after completing the task group, and the vehicle is prevented from running out of power and stopping at the cargo site to cause traffic congestion.

[0121] Optionally, in order to reduce the no-load time of the smart device, the nearest allocation principle should be used when allocating the task. In order to balance the degree of wear of each device, the task allocation is balanced as much as possible when allocating the task, so as to avoid the phenomenon that some devices are overworked and some devices are starved.

[0122] Step S204, determining whether the AGV is carrying a load.

[0123] In this embodiment, it can be determined whether the AGV is in a load state. If the AGV is in a load state, step S206 is performed, otherwise, step S208 is performed.

[0124] Step S206, reassigning tasks.

[0125] In this embodiment, if the AGV is in a load state, i.e., the vehicle is transporting materials or in the process of performing tasks, the subsequent tasks can be reassigned according to the real-time task requirements and the current position, remaining power, running efficiency, and other information of the AGV.

[0126] Step S208, scheduling charging or maintenance for the AGV.

[0127] In this embodiment, if the AGV is not in a load state, i.e., the device is idle or has completed the current task, other states of the AGV, such as power level, running health status, etc., can be evaluated to determine whether charging or maintenance needs to be scheduled.

[0128] Step S210, generating tasks to be assigned.

[0129] In this embodiment, the tasks to be assigned can be generated according to the task state, task start time, loading and unloading points, and priority queue. The priority queue can be determined by high-priority insertion queue and medium-priority insertion queue.

[0130] Optionally, if the tasks are reassigned, the high-priority insertion queue corresponds; if charging or maintenance is scheduled, the medium-priority insertion queue corresponds. According to the high-priority insertion queue and the medium-priority insertion queue, the final priority queue can be determined, so that the tasks to be assigned can be generated according to the task state, task start time, loading and unloading points, and priority queue.

[0131] In the embodiment of the present application, in the logistics warehouse scenario, the randomly generated task dispatching mechanism has three kinds of first creation first execution, task priority, and greedy allocation. First creation first execution, that is, the execution order of the task is completely according to the time sequence of task generation, without considering other factors. When there is an idle device in the warehouse, the task at the top of the list is randomly dispatched to the idle device. According to the priority of the task to be transported, the execution order of the task is determined, and the priority can be judged according to the importance of the task itself. The priority can be added again according to certain constraints after the task is created. For tasks with the same priority, the tasks can be executed in the time sequence of task generation. Greedy allocation is based on the principle of proximity and the shortest empty time to design a task dispatching scheme. It includes the following two dispatching scenarios: the intelligent device closest to the top task can be selected for task dispatching, which can ensure that the task is completely executed according to the priority of the task list; for the idle transport vehicle, the position of the vehicle is taken as the center to search for tasks within a certain range, and the tasks are dispatched in the priority of the task list according to the searched tasks. Based on the priority allocation, the present application balances the demand satisfaction rate and the resource utilization rate of the same priority to achieve the minimum handling time efficiency.

[0132] Figure 3 Figure is a schematic diagram of an intelligent device executing a target task according to an embodiment of the present application, as shown in Figure 3 Figure is a layout diagram of a logistics warehouse, the upper half is a two-dimensional layout diagram of a logistics warehouse, which can include a target task, an intelligent device, and a task position. The lower half is a three-dimensional layout diagram of a logistics warehouse, which can include a target task, an intelligent device, and a task position. The following will be further described taking a handling task as an example.

[0133] Before the handling task is performed, a task allocation model and conflict recognition can be modeled by a map.

[0134] Figure 4 Figure is a schematic diagram of a topological map according to an embodiment of the present application, as shown in Figure 4 The environment can be abstracted as a network representation of nodes and edges, which emphasizes the connection relationship between positions, and has low requirements for the storage space and computing time of the computer.

[0135] In addition to the topological map, a grid map can also be used for modeling. The grid map is a method of discretely representing the environment, which divides the environment into small squares (grids), and each square represents a discrete spatial unit. The size of the square determines the simulation effect, and the smaller the square, the more accurate the simulation effect, and the larger the amount of calculation.

[0136] Optionally, when the path conflicts, the conflict type can be divided into node conflict, opposite conflict, and overtaking conflict.

[0137] Figure 5 is a schematic diagram of node conflict according to an embodiment of the present application, as shown in Figure 5 , node conflict is the case that two or more intelligent devices arrive at a node at the same time point and have different driving directions.

[0138] Figure 6 is a schematic diagram of opposite conflict according to an embodiment of the present application, as shown in Figure 6 , opposite conflict is divided into two categories, the left side can solve the conflict by waiting, and the right side needs one of the intelligent devices to change the path planning.

[0139] Figure 7 is a schematic diagram of overtaking conflict according to an embodiment of the present application, as shown in Figure 7 , overtaking conflict is caused by different driving speeds of different intelligent devices, and the same type of intelligent device should be used as much as possible for the same task.

[0140] The optimization goal of the intelligent device task allocation model can be determined by the following formula:

[0141]

[0142] Wherein, x t,i may be used to represent the decision variable, indicating whether the task t is allocated to the intelligent device i, x t,i is 1, indicating allocation, and x t,i is 0, indicating no allocation; t i,t may be used to represent the expected time of intelligent device i to arrive at task t; T may be used to represent the set of tasks to be allocated; E may be used to represent the set of intelligent devices waiting for allocation; T may be used to represent the set of tasks to be executed; p i may be used to represent the expected remaining time of the current task of intelligent device i; M may be used to represent a large constant, used to "punish" the case of exceeding the time window or not meeting the constraint condition, usually combined with t max ; t max may be used to represent the maximum time; γ i may be used to represent the cumulative load time of intelligent device i on the same day; penalty may be used to represent the penalty value when the task cannot be executed in time or the device is not selected properly.

[0143] Optionally, the intelligent device can only be allocated to 1 task at a certain time, that is, at this time, the intelligent device must be allocated, wherein F may be used to represent the set of intelligent devices that must be allocated. The intelligent device is allocated to 0 tasks, that is, at this time, the intelligent device can be selected, wherein G may be used to represent the set of intelligent devices that can be allocated. The intelligent device is allocated to 0 tasks, that is, At this time, the intelligent device is not selected, wherein H can be used to represent a set of intelligent devices not assigned with tasks.

[0144] Optionally, if the task of the device is successfully assigned, one intelligent device is assigned, which can be represented by the following formula:

[0145]

[0146] wherein y t can be used to represent a decision variable, indicating whether the task t is successfully assigned to the intelligent device, y t = 1 indicates success, and y t = 0 indicates failure.

[0147] Optionally, in the case of mandatory task constraints, y t = 1, t ∈ I, wherein I can be used to represent a set of mandatory tasks.

[0148] Optionally, in the case of optional task constraints, y t ≤ 1, t ∈ J, wherein J can be used to represent a set of optional tasks.

[0149] Optionally, in the case of non-optional task constraints, y t = 0, t ∈ K, wherein K can be used to represent a set of non-optional tasks.

[0150] Optionally, the task assignment quantity constraint, i.e., the number of tasks assigned to the device reaches the specified total number to be assigned, can be represented by the following formula:

[0151]

[0152] wherein N can be used to represent the task assignment quantity.

[0153] The maximum number of assigned tasks constraint can be represented by the following formula:

[0154]

[0155] wherein ρ i can be used to represent the number of tasks assigned to the workstation i; and R i can be used to represent a set of tasks corresponding to the workstation i.

[0156] In the embodiments of the present application, each intelligent device moves from a starting position to a target position in a given road network, and needs to plan a path to meet the target and constraints.

[0157] Optionally, the smart device moves, which can be a single step to a neighboring node or remains in place (waits), and each movement consumes a certain amount of time. Each potential path (candidate path) can contain a sequence of code points and a corresponding waiting time. Based on this data, the time at which the device reaches each node and the time at which the device leaves each node can be calculated in advance by configuring parameters of the smart device (including acceleration, deceleration, turning time, and the like, which approximate the variable speed conditions in the real physical world).

[0158] Optionally, if the optimization goal is to minimize the length of the emergency task carrying, the following formula can be used to represent it:

[0159]

[0160] wherein L(j) can be used to represent the time at which the jth path reaches the destination; r(i,j) can be used to represent whether the ith smart device selects the jth path; P(i) can be used to represent the potential path code corresponding to the ith smart device, such as {1, 2, 3}; and S can be used to represent a set of smart devices that have emergency tasks.

[0161] If the optimization goal is to minimize the length of the ordinary task carrying, the following formula can be used to represent it:

[0162]

[0163] Optionally, conflicting routes cannot be selected at the same time, and the constraint condition is:

[0164]

[0165] Optionally, if each smart device must select a route, the constraint condition is:

[0166]

[0167] wherein T can be used to represent a set of all smart devices.

[0168] Optionally, the selected route is necessarily selected by a smart device, and the constraint condition is:

[0169]

[0170] wherein h(j) can be used to represent that the jth path is selected.

[0171] Optionally, the smart device must reach the destination before the latest time, and the constraint condition is:

[0172]

[0173] wherein t i can be used to represent the latest time at which the ith smart device reaches the destination.

[0174] In this embodiment, the path optimization algorithm can be solved by using a windowed hierarchical cooperative A* algorithm (WHCA*), and the specific algorithm process is as follows:

[0175] Initialization: a window is created for each agent (Agent), and the window size is w;

[0176] An initial abstract search is performed from the initial position O of each agent to the target position G using a rollback horizon A* (RRA*) algorithm. The search result is stored in the node to be searched (Open) list of each Agent, and the Closed list records the searched nodes (Closed) list;

[0177] The following steps are executed in a loop until all intelligent devices reach the target position:

[0178] Perform a window search for each agent;

[0179] If the agent has reached the target position, its target becomes to complete the window through the terminal edge;

[0180] Perform a cooperative search within the window, considering the reserved positions of other agents within the window;

[0181] Use the abstract distance as the heuristic function to guide the search to quickly find the target position;

[0182] If the search depth reaches the window size w, use the abstract distance to calculate the cost from the current node to the target position, and add a special terminal edge;

[0183] The agent moves along the calculated partial path;

[0184] When the agent reaches the midpoint of its partial path:

[0185] Move the window forward;

[0186] Continue to perform the abstract search using the previously stored RRA* search result to consider the newly encountered nodes;

[0187] When all agents reach the target position and complete their windows, the algorithm terminates.

[0188] According to an embodiment of the present application, an intelligent device job execution device is also provided. It should be noted that the intelligent device job execution device can be used to execute the intelligent device job execution method in the above embodiment.

[0189] Figure 8 is a schematic diagram of an intelligent device job execution device according to an embodiment of the present application, as Figure 8As shown, the job execution device 800 of the intelligent device can include an acquisition unit 802, an adjustment unit 804, a determination unit 806, and a control unit 808.

[0190] The acquisition unit 802 is configured to acquire a priority of at least one target job to be executed, and determine an initial task allocation strategy of the target job based on the priority, where the priority is used to indicate a sequence of triggering the at least one intelligent device to execute the target job, and the initial task allocation strategy is used to indicate a rule of allocating the target job to the at least one intelligent device according to the priority.

[0191] The adjustment unit 804 is configured to adjust the initial task allocation strategy based on at least state information of the at least one intelligent device, to obtain a target job allocation strategy, where the state information is used to indicate an idle degree of the intelligent device, the target job allocation strategy is used to indicate a rule of allocating the target job to a target intelligent device in the at least one intelligent device, and the state information of the target intelligent device satisfies a state information threshold.

[0192] The determination unit 806 is configured to determine a target path to be moved by the target intelligent device based on a first position where the target intelligent device is located and a second position corresponding to the target job, where the second position is used to indicate a position of a job site where the target intelligent device executes the target job.

[0193] The control unit 808 is configured to control the target intelligent device to move to the job site according to the target path, to execute the target job.

[0194] In the embodiments of the present application, the acquisition unit 802 is configured to acquire a priority of at least one target job to be executed, and determine an initial task allocation strategy of the target job based on the priority, where the priority is used to indicate a sequence of triggering the at least one intelligent device to execute the target job, and the initial task allocation strategy is used to indicate a rule of allocating the target job to the at least one intelligent device according to the priority; the adjustment unit 804 is configured to adjust the initial task allocation strategy based on at least state information of the at least one intelligent device, to obtain a target job allocation strategy, where the state information is used to indicate an idle degree of the intelligent device, the target job allocation strategy is used to indicate a rule of allocating the target job to a target intelligent device in the at least one intelligent device, and the state information of the target intelligent device satisfies a state information threshold; the determination unit 806 is configured to determine a target path to be moved by the target intelligent device based on a first position where the target intelligent device is located and a second position corresponding to the target job, where the second position is used to indicate a position of a job site where the target intelligent device executes the target job; and the control unit 808 is configured to control the target intelligent device to move to the job site according to the target path, to execute the target job, thereby solving the technical problem that the intelligent device cannot effectively execute the job, and achieving the technical effect that the intelligent device effectively executes the job.

[0195] According to the embodiments of the present application, a computer readable storage medium is further provided, which includes a stored program. The program performs the job execution method of the smart device in the above embodiments when executed by a processor.

[0196] According to the embodiments of the present application, a processor is further provided, which is used to execute a program. The program performs the job execution method of the smart device in the above embodiments when executed.

[0197] The embodiments of the present application further provide a computer program product. Optionally, in the embodiments, the computer program product can include a computer program, which, when executed by a processor, implements the job execution method of the smart device in the embodiments of the present application.

[0198] According to the embodiments of the present application, a vehicle is further provided, which is used to perform the job execution method of the smart device in the embodiments of the present application.

[0199] In the above embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0200] In the several embodiments provided by the present application, it should be understood that the disclosed technology can be implemented in other ways. Of course, the unit described as the division is only a logical function division, and there can be another division manner in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, and can be electrical or other forms.

[0201] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0202] In addition, each functional unit in the embodiments of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be in the form of hardware or software functional unit.

[0203] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to make a computer device (which can be a personal computer, a server or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0204] The above only describes the preferred embodiments of the present application. It should be noted that, for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A method for executing a job on an intelligent device, characterized in that: include: Obtaining a priority of at least one target job to be executed, and determining an initial task allocation strategy for the target job based on the priority, wherein the priority is used to indicate a sequence in which at least one intelligent device is triggered to execute the target job, and the initial task allocation strategy is used to indicate a rule for allocating the target job to the at least one intelligent device according to the priority; Adjusting the initial task allocation policy based at least on the status information of the at least one intelligent device to obtain a target job allocation policy, wherein the status information is used to indicate the idleness of the intelligent device, the target job allocation policy is used to indicate a rule for allocating the target job to a target intelligent device among the at least one intelligent device, and the status information of the target intelligent device satisfies a status information threshold; Determining a target path for the target intelligent device to move based on a first position of the target intelligent device and a second position corresponding to the target operation, wherein the second position is used to represent a position of the target intelligent device when performing the target operation; According to the target path, the target intelligent device is controlled to move to the operation position to perform the target operation.

2. The method according to claim 1, characterized in that Determining an initial task allocation strategy for the target job based on the priority includes: Based on the priority, a first initial task allocation strategy, a second initial task allocation strategy and / or a third initial task allocation strategy for the target job are determined, wherein the first initial task allocation strategy is used to represent a rule for allocating the target job to the at least one intelligent device in the order of creation time of the target job, the second initial task allocation strategy is used to represent a rule for allocating the target job to the at least one intelligent device in the order of importance of the target job, and the third initial task allocation strategy is used to represent a rule for allocating the target job to the at least one intelligent device in the order of distance between the second location and the first location of the at least one intelligent device; The initial task allocation strategy is determined from the first initial task allocation strategy, the second initial task allocation strategy and / or the third initial task allocation strategy.

3. The method according to claim 2, characterized in that Determining a first initial task allocation strategy for the target job based on the priority includes: In response to the number of the target jobs being multiple, generating a first priority according to the order of creation time of the multiple target jobs; According to the first priority, the first initial task allocation strategy is generated, wherein the allocation time of the first initial task allocation strategy corresponding to the target job whose first priority is greater than the priority threshold is earlier than the allocation time of the first initial task allocation strategy corresponding to the target job whose first priority is less than the priority threshold.

4. The method according to claim 2, characterized in that Determining a second initial task allocation strategy for the target job based on the priority includes: In response to the number of the target jobs being multiple, generating a second priority level according to the importance of the target jobs, wherein the importance is used to indicate the degree of importance of the target jobs; According to the second priority, the second initial task allocation strategy is generated, wherein the allocation time of the second initial task allocation strategy corresponding to the target job whose second priority is greater than the priority threshold is earlier than the allocation time of the second initial task allocation strategy corresponding to the target job whose second priority is less than the priority threshold.

5. The method according to claim 2, characterized in that Determining a third initial task allocation strategy for the target job based on the priority includes: Acquire a first location of the at least one smart device in an idle state; In response to the number of the target jobs being multiple, generating a third priority level according to the distance between the second locations and the first location of the multiple target jobs; According to the third priority, the third initial task allocation strategy is generated, wherein the allocation time of the third initial task allocation strategy corresponding to the target job whose third priority is greater than the priority threshold is earlier than the allocation time of the third initial task allocation strategy corresponding to the target job whose third priority is less than the priority threshold.

6. The method according to claim 1, characterized in that The method further comprises: Determining a job scenario for the target job to be executed, and determining an adjustment strategy for the initial task allocation strategy based on the job scenario, wherein the adjustment strategy is used to represent a rule for adjusting the initial task allocation strategy; Adjusting the initial task allocation strategy based at least on the state information of the smart device to obtain a target task allocation strategy includes: According to the adjustment strategy, the initial task allocation strategy is adjusted based at least on the status information of the at least one intelligent device to obtain the target task allocation strategy.

7. The method according to claim 6, characterized in that The operation scenario includes a first operation scenario, the first operation scenario being used to indicate that the target operation is assigned to the smart device corresponding to the first position whose distance from the second position is less than a distance threshold, and adjusting the initial task allocation strategy according to the adjustment strategy based at least on status information of the at least one smart device to obtain the target operation allocation strategy, including: In response to the operation scene being the first operation scene and the target operation to be performed being detected, obtaining a distance difference between the first position and the second position of the at least one smart device in an idle state; In response to the distance difference being less than or equal to the distance threshold, the target job allocation strategy is determined to be a first target job allocation strategy, wherein the first target job allocation strategy is used to represent a rule for allocating the target job to the smart device in the idle state whose distance difference is less than the distance threshold.

8. The method according to claim 6, characterized in that The operation scenario includes a second operation scenario, where the second operation scenario is used to indicate that the target operation with a priority higher than a priority threshold is assigned to the smart device in the idle state, and the initial task allocation strategy is adjusted according to the adjustment strategy based at least on the state information of the at least one smart device to obtain the target operation allocation strategy, including: In response to the operation scene being the second operation scene and the smart device being in the idle state being detected, obtaining a set of target operations to be executed that are within a target area of ​​the smart device, wherein the target area is an area centered around the smart device in the idle state; Based on the target job set, the target job allocation strategy is determined to be a second target job allocation strategy, wherein the second target job allocation strategy is used to represent a rule for allocating the target job to the smart device in the idle state according to the priority of at least one target job to be executed in the target job set.

9. The method according to claim 1, characterized in that The method further comprises: Obtaining the remaining power of the smart device and the remaining mileage of the smart device; In response to the remaining power being less than or equal to a remaining power threshold and the remaining mileage satisfying a distance between the smart device and a corresponding charging device, determining a charging driving route for the smart device; According to the charging driving path, the smart device is controlled to move to the location of the charging device for charging.

10. The method according to claim 9, characterized in that The method further comprises: Obtaining the number of tasks executed and / or the execution duration of the at least one intelligent device in a target period; In response to the number of executed tasks being less than or equal to a number threshold, and / or the execution duration being less than or equal to a duration threshold, adjusting the priority of the at least one smart device in a period next to the target period, wherein the priority of the at least one smart device after the adjustment is greater than the priority of the at least one smart device before the adjustment; In response to the number of executed tasks being greater than the number threshold, and / or the execution time of the job being greater than the time threshold, in the next cycle, the task allocation priority of the at least one smart device is adjusted, wherein the priority of the at least one smart device after adjustment is greater than the priority of the at least one smart device before adjustment.

11. The method according to any one of claims 1 to 10, characterized in that Determining a target path for the target smart device to move based on a first position of the target smart device and a second position corresponding to the target job includes: Determine a candidate path set based on the first position and the second position, wherein the candidate path set includes at least one candidate path; The target path is determined from the candidate path set.

12. The method according to claim 11, characterized in that Determining the target path from the candidate path set includes: In response to the number of the at least one smart device currently in an idle state being multiple, deleting the target path of at least one smart device other than the current smart device from the candidate path set to obtain a target candidate path set for the current smart device; The target candidate paths are concentrated, and the candidate path with the shortest time required to execute the target job is determined as the target path of the current smart device.

13. A job execution device for an intelligent device, characterized in that: include: an acquisition unit, configured to acquire a priority of at least one target job to be executed, and determine an initial task allocation strategy for the target job based on the priority, wherein the priority is used to indicate a sequence in which at least one intelligent device is triggered to execute the target job, and the initial task allocation strategy is used to indicate a rule for allocating the target job to the at least one intelligent device according to the priority; an adjusting unit, configured to adjust the initial task allocation policy based at least on status information of the at least one intelligent device to obtain a target job allocation policy, wherein the status information is used to indicate an idleness level of the intelligent device, the target job allocation policy is used to indicate a rule for allocating the target job to a target intelligent device among the at least one intelligent device, and the status information of the target intelligent device satisfies a status information threshold; a determining unit, configured to determine a target path for the target intelligent device to move based on a first position of the target intelligent device and a second position corresponding to the target operation, wherein the second position is used to represent a position of an operating position of the target intelligent device when performing the target operation; The control unit is used to control the target intelligent device to move to the operation position according to the target path to perform the target operation.

14. A processor, characterized in that: The processor is configured to run a program, wherein the program, when run by the processor, performs the method according to any one of claims 1 to 12.

15. A vehicle, characterized in that: Used to perform the method according to any one of claims 1 to 12.

Images