Charging management method, device and storage medium for automatic guidance device

Abstract

The present application relates to the technical field of charging management, and provides a charging management method, device and storage medium for an automatic guidance device. The method includes: obtaining the remaining power of the automatic guidance device at the current moment; inputting multiple first power selected at the current moment and within the range from a preset lower limit value to the remaining power into a task prediction model; obtaining the first dispatch probability of the operation task corresponding to each first power that the automatic guidance device can perform at the current moment output by the task prediction model; determining the first potential benefit of the operation task that the automatic guidance device can perform at the current moment according to all the first dispatch probabilities; determining the second potential benefit of the automatic guidance device performing the charging task at the current moment according to the remaining power; determining the charging management operation for the automatic guidance device at the current moment according to the first potential benefit and the second potential benefit, so that the charging management for the automatic guidance device at the current moment is more reasonable.

Description

Technical Field

[0001] The present application relates to the field of charging management technology, and in particular to a charging management method, device and storage medium for an automatic guiding device. Background Art

[0002] In the machinery manufacturing industry, material handling is a common business requirement, and automatic guided vehicles are widely used in factories. During the production process, automatic guided vehicles can autonomously drive according to the preset path to complete tasks such as material handling, transportation, and automatic charging. However, the working time of automatic guided vehicles is generally long, and frequent charging is required to ensure continuous operation.

[0003] At present, the commonly used charging strategy for Automated Guided Vehicles (AGVs) is to set a scheduled charging task or set a unified charging threshold. Among them, the scheduled charging task needs to be set when the factory stops production, which relies too much on manual adjustment of the charging time, and the labor cost is too high. Set a unified charging threshold to charge the AGV. If the charging threshold of the AGV is set high, it will cause the AGV to frequently go back and forth to the charging pile, reducing the charging efficiency and affecting production efficiency. When the charging threshold is set low, the AGV may fail to return to the charging point normally and run out of power, affecting work efficiency.

[0004] Therefore, the charging management of the automatic guided device in the prior art is not reasonable enough, which easily causes waste of resources, reduces the operating efficiency of the automatic guided device, and affects the production efficiency of the factory. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a charging management method, device and storage medium for an automatic guiding device, so as to solve the problem of unreasonable charging management of the automatic guiding device in the prior art.

[0006] In order to achieve the above-mentioned object, the first aspect of the present application provides a charging management method for an automatic guiding device, comprising:

[0007] Obtain the remaining power of the automatic guidance device at the current moment;

[0008] Inputting the current moment and a plurality of first electric quantities selected from a range from a preset lower limit value to the remaining electric quantity into the task prediction model;

[0009] Obtain a first probability of issuing an operation task corresponding to each first electrical quantity that can be executed by the automatic guidance device at the current moment output by the task prediction model;

[0010] Determine, based on all first delivery probabilities, a first potential benefit of the automatic guided device performing the task that can be performed at the current moment;

[0011] Determine a second potential benefit of the automatic guidance device performing the charging task at the current moment according to the remaining power;

[0012] The charging management operation for the automatic guiding device at the current moment is determined according to the first potential benefit and the second potential benefit.

[0013] In an embodiment of the present application, determining the first potential benefit of the automatic guided device performing any work task at the current moment based on all the first delivery probabilities includes: weighting each first delivery probability to obtain the weighted first delivery probability; and determining the sum of the probabilities of the weighted first delivery probabilities as the first potential benefit.

[0014] In an embodiment of the present application, determining the second potential benefit of the automatic guiding device performing the charging task at the current moment based on the remaining power includes: determining the charging completion time of the automatic guiding device based on the remaining power; inputting the charging completion time and multiple second power levels within the range from a preset lower limit value to the maximum storage capacity of the automatic guiding device into the task prediction model; obtaining the second delivery probability of the work task corresponding to each second power level output by the task prediction model at the charging completion time; and determining the second potential benefit of the automatic guiding device performing the charging task from the current moment to the charging completion moment based on all the second delivery probabilities.

[0015] In an embodiment of the present application, determining the time when charging of the automatic guiding device is completed based on the remaining power includes: determining the power difference between the remaining power and the maximum storage power; determining the charging time required for the automatic guiding device to charge from the remaining power to the maximum storage power based on the power difference and the charging power and battery capacity of the automatic guiding device; determining the time when charging of the automatic guiding device is completed based on the current time and the charging time.

[0016] In an embodiment of the present application, determining the charging management operation for the automatic guiding device at the current moment based on the first potential benefit and the second potential benefit includes: when the first potential benefit is less than the second potential benefit, determining the charging management operation for the automatic guiding device at the current moment to be charging the automatic guiding device; when the first potential benefit is greater than or equal to the second potential benefit, determining the charging management operation for the automatic guiding device at the current moment to be not charging the automatic guiding device.

[0017] In an embodiment of the present application, the automatic guided device includes multiple ones, and the charging management method also includes: in the case where there are at least two automatic guided devices that need to be charged, determining the potential profit difference between the second potential profit and the first potential profit of each automatic guided device that needs to be charged; sorting all the automatic guided devices that need to be charged in order from large to small according to the potential profit difference, and obtaining a charging order for all the automatic guided devices that need to be charged; and sending corresponding charging instructions to each automatic guided device that needs to be charged in turn according to the charging order, so that each automatic guided device that needs to be charged performs the charging task in turn.

[0018] In an embodiment of the present application, sending corresponding charging instructions to each automatic guided device to be charged in sequence according to the charging order includes: obtaining the available number of charging devices in an idle state; determining the automatic guided devices to be charged that are arranged before the available number in the charging order as the automatic guided devices to be charged; and sending charging instructions to the automatic guided devices to be charged in sequence according to the charging order, so that the automatic guided devices to be charged perform the charging tasks in sequence.

[0019] In an embodiment of the present application, the charging management method also includes: obtaining multiple training samples, wherein each training sample includes the historical power consumption of executing any operation task and the historical issuance time of the operation task; inputting all the training samples into a preset timing prediction model so that the timing prediction model outputs the historical issuance probability of operation tasks with different historical power consumption at different historical issuance times; when the timing prediction model meets the training completion conditions, the timing prediction model that meets the training completion conditions is determined as the task prediction model.

[0020] A second aspect of the present application provides a charging management device for an automatic guiding device, comprising:

[0021] a memory configured to store instructions;

[0022] The processor is configured to call instructions from the memory and implement the above-mentioned charging management method for the automatic guidance device when executing the instructions.

[0023] A third aspect of the present application provides a machine-readable storage medium having instructions stored thereon, which, when executed by a processor, configures the processor to execute the above-mentioned charging management method for an automatic guided device.

[0024] Through the above technical scheme, the probability of task issuance is predicted based on the task prediction model, and whether to issue the charging task to the automatic guided device is selected according to the first potential benefit of the working task that the automatic guided device can perform at the current moment and the second potential benefit of performing the charging task, so that the charging management of the automatic guided device at the current moment is more reasonable, the waste of resources is reduced, and the operating efficiency of the automatic guided device and the production efficiency of the factory are improved.

[0025] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0027] Figure 1 A schematic diagram of a flow chart of a charging management method for an automatic guiding device according to an embodiment of the present application is schematically shown;

[0028] Figure 2 A schematic diagram of a time series prediction model according to an embodiment of the present application is schematically shown;

[0029] Figure 3 A schematic diagram of a flow chart of a charging management method for an automatic guiding device according to another embodiment of the present application is shown;

[0030] Figure 4 A schematic diagram of an AGV charging management system according to an embodiment of the present application is schematically shown;

[0031] Figure 5 The internal structure diagram of a computer device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0033] It should be noted that if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0034] Figure 1 The flowchart of the charging management method for an automatic guidance device according to an embodiment of the present application is schematically shown. Figure 1 As shown, in one embodiment of the present application, a charging management method for an automatic guiding device is provided, comprising the following steps:

[0035] Step 101: Obtain the remaining power of the automatic guidance device at the current moment.

[0036] An Automated Guided Vehicle (AGV) can travel along a preset guide path and is a transport vehicle or truck with safety protection and various transfer functions. In the production process of workshop products, it is necessary to use an AGV to continuously transport the materials required for product production to the corresponding processing location. In order to ensure the smooth progress of workshop production, the AGV can be charged and managed. When charging the AGV, the processor can first obtain the remaining power of the AGV at the current moment. Among them, the remaining power of the AGV can be maintained based on the Robot Control System (RCS). The Robot Control System can realize path planning, task allocation and real-time monitoring of the AGV, thereby improving logistics and production efficiency. The processor can obtain the remaining power corresponding to the AGV from the RCS system where the AGV is located. The remaining power can be presented in the form of a combination of numbers and / or percentages, or in other forms that can represent the remaining power.

[0037] Step 102: Input the current moment and a plurality of first power quantities selected from a range from a preset lower limit value to the remaining power into a task prediction model.

[0038] Step 103: Obtain the first probability of issuing the operation task corresponding to each first electrical quantity that the automatic guidance device can execute at the current moment output by the task prediction model.

[0039] Before inputting the selected multiple first electrical quantities into the task prediction model, the preset time series prediction model may be trained to obtain the task prediction model. The time series prediction model may include a Transformer model, which refers to a sequence-to-sequence model based on a self-attention mechanism.

[0040] In an embodiment of the present application, the charging management method also includes: obtaining multiple training samples, wherein each training sample includes the historical power consumption of executing any operation task and the historical issuance time of the operation task; inputting all the training samples into a preset timing prediction model so that the timing prediction model outputs the historical issuance probability of operation tasks with different historical power consumption at different historical issuance times; when the timing prediction model meets the training completion conditions, the timing prediction model that meets the training completion conditions is determined as the task prediction model.

[0041] When training to obtain the task prediction model, the processor may obtain multiple training samples. Each training sample includes the historical power consumption of executing any one operation task and the historical issuance time of the operation task. The operation task may include the task of handling and / or transporting by an automatic guided device. The processor may input all the training samples into a preset time series prediction model. The preset time series prediction model may output the historical issuance probability of operation tasks with different historical power consumption at different historical issuance times.

[0042] For example, if all training samples include: X1, X2, X3 and X4, where training sample X1={task A; 50%; 9:00}, training sample X2={task A; 50%; 9:00}, training sample X3={task B; 50%; 10:00}, and training sample X4={task C; 40%; 10:00}, then when the preset time series prediction model is output, the historical probability of a task with a historical power consumption of 50% at 9:00 is 1 / 2, the historical probability of a task with a historical power consumption of 50% at 10:00 is 1 / 4, the historical probability of a task with a historical power consumption of 40% at 10:00 is 1 / 4, and the historical probability of a task with a historical power consumption of 40% at 9:00 is 0.

[0043] The training completion condition may include the number of training iterations and / or the prediction accuracy and / or the prediction error. When it is determined that the time series prediction model meets the training completion condition, the processor may determine the time series prediction model that meets the training completion condition as the task prediction model. That is, the task prediction model can be used to predict the probability of a certain power consumption task being sent to the automatic guided device at a certain time.

[0044] In one embodiment, Figure 2As shown, a schematic diagram of a time series prediction model is provided.

[0045] As shown in the figure, the time series prediction model includes an attention distillation mechanism, a decoder, and a fully connected layer. During training, the training data can be input into the attention distillation mechanism so that the attention distillation mechanism outputs the corresponding probability coding sequence. The training data may include the historical power consumption of different tasks. And the historical release time of different tasks The probability coding sequence refers to the historical probability of job tasks with different historical power consumption being issued at different times. The corresponding sequence.

[0046] The attention distillation mechanism inputs the probability coding sequence into the decoder. The decoder can decode the probability coding sequence and output the probability of tasks with different power consumption being dispatched at different times through the fully connected layer. After the training is completed and the time series prediction model is obtained, the prediction data can be input into the decoder of the time series prediction model, so as to realize the prediction of the probability of issuing the operation task that the automatic guidance device can perform at the current moment. Among them, the prediction data may include the current moment, and the power within the range from the preset lower limit value to the remaining power of the automatic guidance device at the current moment.

[0047] After obtaining the remaining power of the automatic guidance device at the current moment, the processor may be based on the range from the preset lower limit value to the remaining power. Among them, the preset lower limit value is the minimum power of the automatic guidance device, and the preset lower limit value is less than or equal to the remaining power. For example, if the remaining power of the automatic guidance device is presented in the form of numbers and percentages, its preset lower limit value may be 1%. If the remaining power is 80%, the corresponding range is 1%~80%. It can be seen that at this time, the automatic guidance device can accept a task with a power consumption of less than 80% at the current moment. The processor can input multiple first powers selected at the current moment and in the range from the preset lower limit value to the remaining power into the task prediction model.

[0048] When selecting multiple first power levels, the processor may select them at certain intervals. For example, a first power level may be selected every 1% until the remaining power level is reached, thereby obtaining multiple first power levels. The processor may also randomly select first power levels from the range of a preset lower limit value to the remaining power level, thereby obtaining multiple first power levels. The processor may also set the number of first power levels input into the task prediction model as required, thereby evenly dividing the range from the preset lower limit value to the remaining power level based on the number, thereby obtaining multiple first power levels.

[0049] The task prediction model can output the first probability of sending the work task corresponding to each first power that the automatic guidance device can perform at the current moment based on the current moment and each first power, that is, the probability of sending the work task with power consumption of each first power to the automatic guidance device at the current moment. Taking the above training sample as an example, the task prediction model is obtained. When the current moment is 9:00 and the first power input to the task prediction model is 50%, it is necessary to predict the probability of sending the work task with power consumption of 50% to the automatic guidance device at 9:00. At this time, the probability output by the task prediction model can be 1 / 2.

[0050] Step 104: Determine the first potential benefit of the automatic guiding device performing the work task that can be performed at the current moment based on all the first sending probabilities.

[0051] After obtaining the probability of issuing each task with the first power, the processor can determine the first potential benefit of the task that the automatic guided device can perform at the current moment according to all the first issuance probabilities. Among them, the more remaining power the automatic guided device has, the more tasks it can accept, and the higher the corresponding potential benefit. The probability of issuing a task changes with time. If the production of products in the workshop is in a busy period, the probability of issuing a certain task at different times will be different. The first potential benefit can define the potential benefit that the automatic guided device brings to the production of the factory where the automatic guided device is located when it is waiting to execute the task at the current moment.

[0052] In an embodiment of the present application, determining the first potential benefit of the automatic guided device performing any work task at the current moment based on all the first delivery probabilities includes: weighting each first delivery probability to obtain the weighted first delivery probability; and determining the sum of the probabilities of the weighted first delivery probabilities as the first potential benefit.

[0053] The processor may perform weighted processing on each first delivery probability to obtain a weighted first delivery probability. Afterwards, the processor may sum all weighted first delivery probabilities to obtain a probability sum of the weighted first delivery probabilities, and determine the probability sum as the first potential benefit of the automatic guided device performing any operation task at the current moment.

[0054] When weighted processing is performed on each first delivery probability, the product between each first delivery probability and a preset benefit coefficient can be determined, and the product is determined as the first delivery probability after weighted processing. The preset benefit coefficient is a constant and can be set according to actual needs. For example, different benefit coefficients can be set for different types of automatic guided devices.

[0055] In one embodiment, when obtaining all the first delivery probabilities, the processor may determine the probability sum of all the first delivery probabilities, perform weighted processing on the probability sum of all the first delivery probabilities, and determine the weighted probability sum as the first potential benefit.

[0056] When weighted processing is performed on the probability sum of all first delivery probabilities, the product between the probability sum of all first delivery probabilities and a preset benefit coefficient can be determined, and the product is determined as the probability sum after weighted processing. The preset benefit coefficient is a constant and can be set according to actual needs. For example, different benefit coefficients can be set for different types of automatic guided devices.

[0057] Step 105: Determine a second potential benefit of the automatic guiding device performing the charging task at the current moment according to the remaining power.

[0058] The processor may determine the second potential benefit of the automatic guiding device performing the charging task at the current moment according to the remaining power of the automatic guiding device. The second potential benefit may define the potential benefit that the automatic guiding device brings to the production of the factory where the automatic guiding device is located when the automatic guiding device performs the charging task from the current moment.

[0059] In an embodiment of the present application, determining the second potential benefit of the automatic guiding device performing the charging task at the current moment based on the remaining power includes: determining the charging completion time of the automatic guiding device based on the remaining power; inputting the charging completion time and multiple second power levels within the range from a preset lower limit value to the maximum storage capacity of the automatic guiding device into the task prediction model; obtaining the second delivery probability of the work task corresponding to each second power level output by the task prediction model at the charging completion time; and determining the second potential benefit of the automatic guiding device performing the charging task from the current moment to the charging completion moment based on all the second delivery probabilities.

[0060] The processor may determine the charging completion time of the automatic guiding device according to the remaining power of the automatic guiding device. Specifically, the processor may obtain the charging power of the automatic guiding device, and may determine the charging completion time of the automatic guiding device according to the charging power and the remaining power of the automatic guiding device. The power of the automatic guiding device at the charging completion time is the maximum storage power.

[0061] In an embodiment of the present application, determining the time when charging of the automatic guiding device is completed based on the remaining power includes: determining the power difference between the remaining power and the maximum storage power; determining the charging time required for the automatic guiding device to charge from the remaining power to the maximum storage power based on the power difference and the charging power and battery capacity of the automatic guiding device; determining the time when charging of the automatic guiding device is completed based on the current time and the charging time.

[0062] The processor may determine the power difference between the remaining power and the maximum power storage, and may determine the charging time required for the automatic guiding device to charge from the remaining power to the maximum power storage according to the power difference, the charging power of the automatic guiding device, and the battery capacity. The processor may determine the charging completion time of the automatic guiding device according to the current time and the charging time. Specifically, the time obtained by summing the current time and the charging time may be determined as the charging completion time.

[0063] After determining the charging completion time of the automatic guiding device, the processor can select multiple second electric quantities from the range of the preset lower limit value to the maximum storage capacity of the automatic guiding device and input them into the task prediction model. The processor can obtain the second delivery probability of the operation task corresponding to each second electric quantity output by the task prediction model at the charging completion time, that is, the probability of delivering the operation task with a power consumption of each second electric quantity to the automatic guiding device at the charging completion time. The processor can determine the second potential benefit of the automatic guiding device performing the charging task from the current time to the charging completion time based on all the second delivery probabilities.

[0064] In one embodiment, the processor may perform weighted processing on each second delivery probability to obtain a weighted second delivery probability. Afterwards, the processor may sum all weighted second delivery probabilities to obtain a probability sum of the weighted second delivery probabilities, and determine the probability sum as the second potential benefit of the automatic guiding device performing the charging task at the time of charging completion.

[0065] When weighted processing is performed on each second probability of sending, the product between each second probability of sending and a preset benefit coefficient can be determined, and the product is determined as the second probability of sending after weighted processing. The preset benefit coefficient is a constant and can be set according to actual needs. For example, different benefit coefficients can be set for different types of automatic guided devices.

[0066] In one embodiment, when obtaining all the second delivery probabilities, the processor may determine the probability sum of all the second delivery probabilities, perform weighted processing on the probability sum of all the second delivery probabilities, and determine the weighted probability sum as the second potential benefit.

[0067] When weighted processing is performed on the probability sum of all second delivery probabilities, the product of the probability sum of all second delivery probabilities and a preset benefit coefficient can be determined, and the product is determined as the probability sum after weighted processing. The preset benefit coefficient is a constant and can be set according to actual needs. For example, different benefit coefficients can be set for different types of automatic guided devices.

[0068] Step 106: Determine a charging management operation for the automatic guiding device at the current moment according to the first potential benefit and the second potential benefit.

[0069] The processor may determine the charging management operation for the automatic guided device at the current moment according to the first potential benefit and the second potential benefit. The first potential benefit may define the potential benefit brought by the automatic guided device waiting to perform the operation task at the current moment for the production of the factory where the automatic guided device is located. The second potential benefit may define the potential benefit brought by the automatic guided device performing the charging task from the current moment for the production of the factory where the automatic guided device is located. The processor may determine whether the automatic guided device is suitable for performing the operation task or the charging task at the current moment according to the first potential benefit and the second potential benefit, thereby determining the charging management operation for the automatic guided device at the current moment.

[0070] The charging management operation includes charging the automatic guiding device and not charging the automatic guiding device. When the charging management operation is to charge the automatic guiding device, the automatic guiding device is controlled to perform the charging task. When the charging management operation is not to charge the automatic guiding device, the automatic guiding device is controlled to continue to perform the operation task.

[0071] In an embodiment of the present application, determining the charging management operation for the automatic guiding device at the current moment based on the first potential benefit and the second potential benefit includes: when the first potential benefit is less than the second potential benefit, determining the charging management operation for the automatic guiding device at the current moment to be charging the automatic guiding device; when the first potential benefit is greater than or equal to the second potential benefit, determining the charging management operation for the automatic guiding device at the current moment to be not charging the automatic guiding device.

[0072] When the first potential benefit is less than the second potential benefit, it can be explained that the automatic guided device is more suitable for performing the charging task at this time, that is, the automatic guided device can bring better benefits to the current production after performing the charging task. At this time, the processor can determine that the charging management operation for the automatic guided device at the current moment is to charge the automatic guided device.

[0073] When the first potential benefit is greater than or equal to the second potential benefit, it can be explained that the automatic guided device is more suitable for performing the operation task at this time, that is, the automatic guided device can bring better benefits to the current production after continuing to perform the operation task. At this time, the processor can determine that the charging management operation for the automatic guided device at the current moment is not to charge the automatic guided device.

[0074] In an embodiment of the present application, the automatic guided device includes multiple ones, and the charging management method also includes: in the case where there are at least two automatic guided devices that need to be charged, determining the potential profit difference between the second potential profit and the first potential profit of each automatic guided device that needs to be charged; sorting all the automatic guided devices that need to be charged in order from large to small according to the potential profit difference, and obtaining a charging order for all the automatic guided devices that need to be charged; and sending corresponding charging instructions to each automatic guided device that needs to be charged in turn according to the charging order, so that each automatic guided device that needs to be charged performs the charging task in turn.

[0075] In the case where there are at least two automatic guided vehicles that need to be charged, for each automatic guided vehicle that needs to be charged, the processor may determine the potential benefit difference between the second potential benefit and the first potential benefit of the automatic guided vehicle. The larger the potential benefit difference, the more urgent the corresponding automatic guided vehicle needs to be charged. At this time, the processor may sort all the automatic guided vehicles that need to be charged in order from large to small according to the potential benefit difference, and obtain the charging order for all the automatic guided vehicles that need to be charged. The processor may send the corresponding charging instructions to each automatic guided vehicle that needs to be charged in sequence according to the charging order, so that each automatic guided vehicle that needs to be charged performs the charging task in sequence.

[0076] In an embodiment of the present application, sending corresponding charging instructions to each automatic guided device to be charged in sequence according to the charging order includes: obtaining the available number of charging devices in an idle state; determining the automatic guided devices to be charged that are arranged before the available number in the charging order as the automatic guided devices to be charged; and sending charging instructions to the automatic guided devices to be charged in sequence according to the charging order, so that the automatic guided devices to be charged perform the charging tasks in sequence.

[0077] The processor may obtain the available number of charging devices in an idle state. The charging device may be used to charge the automatic guiding device. The charging device may be a device capable of providing electric energy, such as a charging pile. The processor may determine the automatic guiding device to be charged that is arranged before the available number in the charging sequence as the automatic guiding device to be charged. The processor may send charging instructions to the automatic guiding device to be charged in sequence according to the charging sequence, so that the automatic guiding device to be charged performs the charging task in sequence.

[0078] In one embodiment, the automatic guided devices that need to be charged and are arranged after the available number in the charging sequence can be controlled to continue to perform the working task.

[0079] In one embodiment, when all the automatic guided devices to be charged are performing charging tasks, the operating status of the charging devices can be continuously or in real time detected. If a charging device in an idle state is detected, it is possible that the automatic guided devices to be charged have been charged. A charging instruction can be sent to the automatic guided devices to be charged that are arranged after the available number until all the automatic guided devices to be charged are charged.

[0080] In one embodiment, Figure 3 As shown, a flow chart of another charging management method for an automatic guiding device is provided.

[0081] When charging each AGV, a data set can be used to train a time series prediction model. Specifically, the task data such as the time, frequency, and power consumption of the AGV handling task are passed into the deep learning model, and the potential profit function R (t, b) is constructed. After that, the current power of each AGV is obtained, and the potential profit of each AGV waiting to perform the task at the current moment and the potential profit of starting to perform the charging task at this moment are calculated through the trained time series prediction model. Then, it can be determined whether the potential profit of performing the task is greater than the potential profit of performing the charging task. If the potential profit of performing the task is less than the potential profit of performing the charging task, it is determined that the corresponding AGV meets the conditions, and the corresponding AGV can be added to the AGV queue to be charged. The AGVs can be sorted according to the potential profit increased after charging, and the charging instructions can be issued according to the number of charging piles. Among them, the potential profit increased after charging is the difference between the potential profit of performing the charging task and the potential profit of performing the task. The greater the potential profit increased after charging, the higher the charging order of the corresponding AGV can be arranged.

[0082] Through the above technical scheme, the probability of task issuance is predicted based on the task prediction model, and whether to issue the charging task to the automatic guided device is selected according to the first potential benefit of the working task that the automatic guided device can perform at the current moment and the second potential benefit of performing the charging task, so that the charging management of the automatic guided device at the current moment is more reasonable, the waste of resources is reduced, and the operating efficiency of the automatic guided device and the production efficiency of the factory are improved.

[0083] Figure 1 and 3 FIG. 1 is a flow chart of a charging management method for an automatic guiding device in one embodiment. It should be understood that although Figure 1 and 3 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 and 3 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0084] In one embodiment, a charging management device for an automatic guiding device is provided, comprising:

[0085] a memory configured to store instructions;

[0086] The processor is configured to call instructions from the memory and implement the above-mentioned charging management method for the automatic guidance device when executing the instructions.

[0087] In one embodiment, Figure 4 As shown, a schematic diagram of an AGV charging management system is provided. The AGV charging management system includes a handling task prediction module, a status monitoring module, a charging decision module and a charging control module.

[0088] The handling task prediction module includes a time series prediction model. Before charging management is performed, the time series prediction model can be trained. The input for the time series prediction model training is the power consumption of different handling tasks. And the time of issuing different handling tasks The output of the time series prediction model training is the probability of dispatching handling tasks with different power consumption at different times. The trained time series prediction model can predict the probability of dispatching handling tasks with different power consumption at different times. The more power the AGV has left, the more handling tasks it can accept, and the higher its potential profit from performing handling tasks. At the same time, the probability of task dispatching will change over time. During the busy period of the factory, the probability of task dispatching will be significantly higher than during the factory rest time.

[0089] The status monitoring module can be used to monitor whether there are idle charging piles. If there are idle charging piles, the status monitoring module can obtain the remaining power of each AGV in the current RCS and send the remaining power of each AGV to the charging decision module. The charging decision module can be used to calculate the potential benefits of each AGV continuing to wait for the task at the current moment, as well as the potential benefits of charging from the current moment until the charging task is completed.

[0090] Specifically, the charging decision module can calculate based on the following formula: The potential profit of the Kth AGV continuing to wait for the task at the next moment is:

[0091] =

[0092] in, means The potential profit of the Kth AGV continuing to wait for the task at the next moment, is the remaining power of the AGV, , Refers to the preset profit coefficient.

[0093] The charging decision module can calculate the following formula: Start charging at any time until Potential benefits after completing the charging task at all times:

[0094] =

[0095] in, It means that AGV Start charging at any time until The potential benefits after completing the charging task at any time, is the maximum storage capacity of AGV, , It refers to the preset profit coefficient. It refers to the time when the AGV is fully charged, which can be determined based on the charging power of the AGV. ,in, is the battery capacity of the AGV, The charging power of the AGV.

[0096] The charging decision module can be used to determine the potential benefits of the AGV waiting task Is it less than the potential benefit of performing the charging task? If the potential revenue of the Kth AGV currently waiting for the task is less than the revenue after charging, then the AGV is added to the set of AGVs waiting for charging. The charging decision module can also The AGV queue waiting for charging is sorted from large to small. The charging control module can send charging instructions to the first m AGVs in the queue waiting for charging according to the number of charging piles currently available, and the remaining AGVs will continue to perform the handling task.

[0097] The above technical solution learns and predicts the task issuance rules and attributes based on the deep learning model, and then judges the benefits of the vehicle waiting for the task and executing charging according to the vehicle's current power and current time. When the benefit of executing charging is greater than the potential benefit of continuing to wait for the task, the AGV will execute the charging task, making the AGV's charging task arrangement more reasonable, and charging can be carried out during the idle time period when the task is issued, reducing the waste of logistics resources and improving production efficiency.

[0098] In one embodiment, a storage medium is provided, on which a program is stored, and when the program is executed by a processor, the above-mentioned charging management method for an automatic guiding device is implemented.

[0099] In one embodiment, a processor is provided, and the processor is used to run a program, wherein the program executes the above-mentioned charging management method for an automatic guiding device when it is run.

[0100] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor A01, a network interface A02, a memory (not shown in the figure) and a database (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02 and a database (not shown in the figure). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The database of the computer device is used to store data such as the first potential benefit of the automatic guidance device performing the task that can be performed at the current moment and the second potential benefit of performing the charging task. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program B02 is executed by the processor A01, a charging management method for an automatic guidance device is implemented.

[0101] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0102] An embodiment of the present application provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: obtaining the remaining power of the automatic guiding device at the current moment; inputting multiple first power levels selected at the current moment and within the range from a preset lower limit value to the remaining power level into a task prediction model; obtaining a first dispatch probability of an operation task corresponding to each first power level that the automatic guiding device can perform at the current moment output by the task prediction model; determining a first potential benefit of the operation task that the automatic guiding device can perform at the current moment based on all the first dispatch probabilities; determining a second potential benefit of the automatic guiding device performing a charging task at the current moment based on the remaining power; and determining a charging management operation for the automatic guiding device at the current moment based on the first potential benefit and the second potential benefit.

[0103] In one embodiment, determining the first potential benefit of the automatic guided device performing any work task at the current moment based on all the first delivery probabilities includes: weighting each first delivery probability to obtain the weighted first delivery probability; and determining the sum of the probabilities of the weighted first delivery probabilities as the first potential benefit.

[0104] In one embodiment, determining the second potential benefit of the automatic guiding device performing the charging task at the current moment based on the remaining power includes: determining the charging completion time of the automatic guiding device based on the remaining power; inputting the charging completion time and multiple second power levels within the range from a preset lower limit value to the maximum storage capacity of the automatic guiding device into a task prediction model; obtaining the second delivery probability of the work task corresponding to each second power level output by the task prediction model at the charging completion time; and determining the second potential benefit of the automatic guiding device performing the charging task from the current moment to the charging completion moment based on all the second delivery probabilities.

[0105] In one embodiment, determining the charging completion time of the automatic guiding device based on the remaining power includes: determining the power difference between the remaining power and the maximum storage power; determining the charging time required for the automatic guiding device to charge from the remaining power to the maximum storage power based on the power difference and the charging power and battery capacity of the automatic guiding device; and determining the charging completion time of the automatic guiding device based on the current time and the charging time.

[0106] In one embodiment, determining the charging management operation for the automatic guiding device at the current moment based on the first potential benefit and the second potential benefit includes: when the first potential benefit is less than the second potential benefit, determining the charging management operation for the automatic guiding device at the current moment to be charging the automatic guiding device; when the first potential benefit is greater than or equal to the second potential benefit, determining the charging management operation for the automatic guiding device at the current moment to be not charging the automatic guiding device.

[0107] In one embodiment, the automatic guided device includes a plurality of devices, and the charging management method further includes: in the case where there are at least two automatic guided devices that need to be charged, determining the potential benefit difference between the second potential benefit and the first potential benefit of each automatic guided device that needs to be charged; sorting all the automatic guided devices that need to be charged in order from large to small according to the potential benefit difference, and obtaining a charging order for all the automatic guided devices that need to be charged; and sending corresponding charging instructions to each automatic guided device that needs to be charged in sequence according to the charging order, so that each automatic guided device that needs to be charged performs the charging task in sequence.

[0108] In one embodiment, sending corresponding charging instructions to each automatic guided device to be charged in sequence according to the charging order includes: obtaining the available number of charging devices in an idle state; determining the automatic guided devices to be charged that are arranged before the available number in the charging order as the automatic guided devices to be charged; and sending charging instructions to the automatic guided devices to be charged in sequence according to the charging order, so that the automatic guided devices to be charged perform the charging tasks in sequence.

[0109] In one embodiment, the charging management method also includes: obtaining multiple training samples, wherein each training sample includes the historical power consumption of executing any job task and the historical issuance time of the job task; inputting all the training samples into a preset timing prediction model so that the timing prediction model outputs the historical issuance probability of job tasks with different historical power consumption at different historical issuance times; when the timing prediction model meets the training completion condition, the timing prediction model that meets the training completion condition is determined as the task prediction model.

[0110] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the steps of a charging management method for an automatic guiding device.

[0111] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0112] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0113] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0114] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0115] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0116] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0117] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0118] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0119] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A charging management method for an automatic guiding device, characterized in that: The charging management method comprises: Obtain the remaining power of the automatic guidance device at the current moment; Inputting the current moment and a plurality of first electric quantities selected from a range from a preset lower limit value to the remaining electric quantity into a task prediction model; Obtain a first probability of issuing an operation task corresponding to each first electrical quantity that can be performed by the automatic guiding device at the current moment, output by the task prediction model; Determine, based on all first delivery probabilities, a first potential benefit of the automatic guided device performing the task that can be performed at the current moment; Determining a second potential benefit of the automatic guiding device performing the charging task at the current moment according to the remaining power; Determine a charging management operation for the automatic guiding device at the current moment according to the first potential benefit and the second potential benefit; Wherein, determining the first potential benefit of the automatic guided device performing any operation task at the current moment according to all the first sending probabilities includes: Performing weighted processing on each first delivery probability to obtain a weighted first delivery probability; The sum of the probabilities of the weighted first sending probabilities is determined as the first potential benefit.

2. The charging management method for an automatic guided vehicle according to claim 1, characterized in that: The second potential benefit of determining, according to the remaining power, that the automatic guiding device performs the charging task at the current moment includes: Determining the charging completion time of the automatic guiding device according to the remaining power; The charging completion time and a plurality of second electric quantities selected from the range from the preset lower limit value to the maximum storage capacity of the automatic guiding device are input into the task prediction model; Obtain a second delivery probability of the operation task corresponding to each second electric quantity output by the task prediction model at the charging completion time; The second potential benefit of the automatic guiding device performing the charging task from the current moment to the charging completion moment is determined according to all the second sending probabilities.

3. The charging management method for an automatic guided vehicle according to claim 2, characterized in that: Determining the charging completion time of the automatic guiding device according to the remaining power includes: Determining a power difference between the remaining power and the maximum power storage capacity; Determine the charging time required for the automatic guiding device to charge from the remaining power to the maximum storage power according to the power difference and the charging power and battery capacity of the automatic guiding device; The charging completion time of the automatic guiding device is determined according to the current time and the charging duration.

4. The charging management method for an automatic guided vehicle according to claim 1, characterized in that: The determining of the charging management operation for the automatic guiding device at the current moment according to the first potential benefit and the second potential benefit includes: In a case where the first potential benefit is less than the second potential benefit, determining that the charging management operation for the automatic guiding device at the current moment is to charge the automatic guiding device; When the first potential benefit is greater than or equal to the second potential benefit, determining the charging management operation for the automatic guiding device at the current moment is not to charge the automatic guiding device.

5. The charging management method for an automatic guided vehicle according to claim 4, characterized in that: The automatic guiding device includes a plurality of devices, and the charging management method further includes: In the case where there are at least two automatic guided devices to be charged, determining a potential profit difference between a second potential profit and a first potential profit of each automatic guided device to be charged; Sort all the automatic guiding devices that need to be charged according to the potential revenue difference from large to small, to obtain a charging sequence for all the automatic guiding devices that need to be charged; The corresponding charging instructions are sent to each automatic guiding device that needs to be charged in sequence according to the charging sequence, so that each automatic guiding device that needs to be charged performs the charging task in sequence.

6. The charging management method for an automatic guided vehicle according to claim 5, characterized in that: The sending of corresponding charging instructions to each automatic guiding device to be charged in sequence according to the charging sequence comprises: Get the available number of charging devices in idle state; Determine the automatic guided devices that need to be charged and are arranged before the available number in the charging sequence as the automatic guided devices to be charged; Charging instructions are sent to the automatic guiding devices to be charged in sequence according to the charging sequence, so that the automatic guiding devices to be charged perform charging tasks in sequence.

7. The charging management method for an automatic guided vehicle according to claim 1, characterized in that: The charging management method further includes: Acquire multiple training samples, wherein each training sample includes the historical power consumption of executing any job task and the historical issuing time of the job task; Input all training samples into a preset time series prediction model, so that the time series prediction model outputs the historical delivery probabilities of the job tasks with different historical power consumption at different historical delivery times; In the case where the time series prediction model meets the training completion condition, the time series prediction model that meets the training completion condition is determined as the task prediction model.

8. A charging management device for an automatic guiding device, characterized in that: The charging management device comprises: a memory configured to store instructions; A processor is configured to call the instructions from the memory and implement the charging management method for an automatic guided device according to any one of claims 1 to 7 when executing the instructions.

9. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions, which are used to enable a machine to execute the charging management method for an automatic guided device according to any one of claims 1 to 7.

Images