Multi-device cooperative control method and device, electronic device and storage medium

Abstract

The invention discloses a multi-device cooperative control method and device, an electronic device and a storage medium, and the method comprises the steps: determining a historical comprehensive utility according to the historical operation data of at least two devices based on a utility evaluation model; determining a short board index according to the current operation data of each device, and determining a current comprehensive utility according to the current operation data of each device based on a utility evaluation model and the short board index; and determining an optimal control strategy according to the current comprehensive utility and the historical comprehensive utility. According to the invention, the cooperative control capability of multiple devices in a complex environment can be improved, and an efficient, intelligent and adaptive cooperative control process is realized.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a method, apparatus, electronic device, and storage medium for collaborative control of multiple devices. Background Technology

[0002] With the rapid development of artificial intelligence technology, automatic control is being applied more and more widely in various fields. Traditional single-device operation scheduling and control is essentially a passive response mode of "human brain + machine". It has structural shortcomings in scheduling real-time performance, data connectivity, safety and controllability, and energy efficiency management, and can no longer meet the needs of high-efficiency and large-scale control. To address this, multi-device collaborative control technology has emerged. Through the cooperation and division of labor among multiple devices, it can significantly improve control efficiency and operation coverage. However, in complex environments, such as multi-forklift control in intelligent warehousing environments, it still has significant drawbacks such as poor environmental adaptability, low system integration, and high control costs. Summary of the Invention

[0003] This invention provides a method, apparatus, electronic device, and storage medium for collaborative control of multiple devices, thereby improving the collaborative control capability of multiple devices in complex environments and realizing an efficient, intelligent, and adaptive collaborative control process.

[0004] In a first aspect, embodiments of the present invention provide a method for collaborative control of multiple devices, the method comprising:

[0005] Based on the utility assessment model, the historical comprehensive utility is determined according to the historical operating data of at least two devices;

[0006] Based on the current operating data of each piece of equipment, the bottleneck index is determined, and based on the utility evaluation model and the bottleneck index, the current comprehensive utility is determined according to the current operating data of each piece of equipment.

[0007] The optimal control strategy is determined based on the current overall utility and the historical overall utility.

[0008] Optionally, based on a utility evaluation model, the historical comprehensive utility is determined using historical operating data from at least two devices, including:

[0009] Based on the utility evaluation model, the historical comprehensive utility is determined by taking into account the historical operating coverage area, historical overlapping area area, historical energy consumption, and historical communication limitation data of at least two devices.

[0010] Optionally, a bottleneck index is determined based on the current operating data of each piece of equipment, including:

[0011] Based on the current operating coverage area, current overlapping area, current energy consumption, and current communication limitations of each device, the bottleneck data is determined;

[0012] The bottleneck data includes overlapping area bottleneck, energy consumption bottleneck, and communication bottleneck. The overlapping area bottleneck is calculated by the ratio of the current overlapping area to the current operation coverage area. The energy consumption bottleneck is calculated by the ratio of the current energy consumption to the maximum energy consumption of the equipment per unit time. The communication bottleneck is represented by the current communication bottleneck loss value, which is determined based on the current communication bottleneck data.

[0013] Based on the data on shortcomings, a shortcomings index is determined.

[0014] Optionally, based on the utility evaluation model and the aforementioned bottleneck index, the current overall utility is determined according to the current operating data of each piece of equipment, including:

[0015] Based on the utility assessment model and the aforementioned bottleneck index, the revised utility assessment model is determined.

[0016] Based on the revised utility assessment model, the current overall utility is determined according to the current operating data of each device.

[0017] Optionally, the optimal control strategy is determined based on the current comprehensive utility and historical comprehensive utility, including:

[0018] Determine the utility difference based on the current total utility and the historical total utility;

[0019] If the utility difference is determined to be greater than or equal to a preset utility threshold, then the current control strategy is taken as the optimal control strategy.

[0020] Otherwise, determine the optimal control strategy based on current operational data and the bottleneck index.

[0021] Optionally, based on current operational data and the weakest link index, the optimal control strategy is determined, including:

[0022] Based on the support vector machine model, and according to the current work data and the utility evaluation model corrected by the bottleneck index, the target dimension work data that needs to be optimized and adjusted is determined from the current work data in each dimension.

[0023] Based on reinforcement learning algorithms, the weight coefficients of the short board data corresponding to the target dimension operation data are increased when calculating the short board index, and at least two candidate control parameter combinations are determined with minimizing the short board index as the optimization objective.

[0024] The control parameters include at least one of the following: individual movement speed, sensing frequency, and communication interval;

[0025] Based on the genetic algorithm, with minimizing the target dimension of the operation data as the optimization objective, evolutionary calculations are performed on each candidate combination of control parameters to obtain the target control parameter combination.

[0026] The target control parameter combination is used as the optimal control strategy.

[0027] Optionally, the optimal control strategy is determined based on the current comprehensive utility and historical comprehensive utility, including:

[0028] Based on the current comprehensive utility and historical comprehensive utility, determine the optimal control strategy until the cumulative control time is greater than or equal to the preset time threshold, and / or the control coverage is greater than or equal to the preset coverage threshold;

[0029] The control coverage rate is calculated based on the current operation data.

[0030] Secondly, embodiments of the present invention also provide a multi-device collaborative control device, the device comprising:

[0031] The historical comprehensive utility determination module is used to determine the historical comprehensive utility based on the utility evaluation model and the historical operating data of at least two devices.

[0032] The current comprehensive utility determination module is used to determine the bottleneck index based on the current operating data of each device, and to determine the current comprehensive utility based on the utility evaluation model and the bottleneck index, according to the current operating data of each device.

[0033] The optimal control strategy determination module is used to determine the optimal control strategy based on the current comprehensive utility and historical comprehensive utility.

[0034] Thirdly, embodiments of the present invention also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a multi-device collaborative control method as described in any of the embodiments of the present invention.

[0035] Fourthly, embodiments of the present invention also provide a storage medium for storing computer-executable instructions, which, when executed by a computer processor, are used to perform a multi-device collaborative control method as described in any of the embodiments of the present invention.

[0036] The technical solution of this invention determines the historical comprehensive utility through historical operating data and a utility evaluation model for each device. It then determines the bottleneck index based on the current operating data of each device and modifies the utility evaluation model accordingly. Finally, it determines the current comprehensive utility using the current operating data and the modified utility evaluation model, and finally determines the optimal control strategy based on the current and historical comprehensive utility. This invention constructs a utility evaluation model based on multi-dimensional operating data, forming a systematic evaluation system that effectively quantifies and evaluates the control utility of each device. The bottleneck index, calculated based on current operating data, quantitatively evaluates control bottlenecks, reflecting not only the strengths and weaknesses of the current control strategy but also providing direction for optimization. Finally, based on the current and historical comprehensive utility, it achieves adaptive adjustment of the optimal control strategy, enabling timely response to environmental changes, improving control efficiency, and ensuring continuous improvement in control utility.

[0037] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is a flowchart of a multi-device collaborative control method provided in Embodiment 1 of the present invention;

[0040] Figure 2 This is a flowchart of a multi-device collaborative control method provided in Embodiment 2 of the present invention;

[0041] Figure 3 This is a schematic diagram of the structure of a multi-device collaborative control device provided in Embodiment 3 of the present invention;

[0042] Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0043] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0044] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices. In the embodiments of this application, certain software, components, models, and other existing industry solutions may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solutions of this application, and do not imply that the applicant has already used or necessarily used such solutions.

[0045] The acquisition, transmission, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0046] Example 1

[0047] Figure 1 The flowchart of a multi-device collaborative control method is provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where the method can be executed by a multi-device collaborative control device. The multi-device collaborative control device can be implemented in hardware and / or software and can be configured in a device or server.

[0048] like Figure 1 As shown, the method includes:

[0049] S110. Based on the utility assessment model, determine the historical comprehensive utility according to the historical operating data of at least two devices.

[0050] Among them, the utility evaluation model is used to integrate multi-source operational data. By analyzing and clarifying the impact of operational data in each dimension on the overall utility, and quantifying the operational data in each dimension, a systematic overall utility evaluation model is formed.

[0051] In this embodiment, the number of devices is at least two. This embodiment is applicable to scenarios where multiple devices coordinate and control each other, such as multi-device collaborative operation scenarios in smart warehousing. The devices can refer to forklifts, driverless vehicles, or artificial intelligence robots, etc.

[0052] It should be noted that this embodiment can be executed by a server, where each device sends its work data to the server, which then makes the decision on the optimal control strategy. Alternatively, it can be executed by each device separately, with communication established between the devices beforehand to transmit work data to each other, and each device making its own decision on the optimal control strategy.

[0053] Historical operation data refers to the operation data of each device when performing historical tasks. Historical comprehensive utility refers to the comprehensive utility of multiple devices working together, obtained by substituting historical operation data into a utility evaluation model. Historical operation data can be the operation data from the last historical task. Correspondingly, historical comprehensive utility is the comprehensive utility of the last historical task. Historical operation data can also be the operation data at the moment corresponding to the highest value of comprehensive utility calculated in real time during the execution of the last historical task, or the operation data corresponding to the historical task with the highest comprehensive utility among all historical tasks. Correspondingly, historical comprehensive utility is the highest value of comprehensive utility calculated in real time during the execution of the last historical task, or the highest value of comprehensive utility among all historical tasks.

[0054] It should be noted that when performing multi-device collaborative control tasks for the first time using this embodiment, the set values, standard values, or predicted values ​​of the operation data of each device in various dimensions can be substituted into the utility evaluation model as historical comprehensive utility, which can be used for subsequent comprehensive utility comparison and control strategy optimization.

[0055] Furthermore, S110 may include: determining the historical comprehensive utility based on a utility evaluation model, according to the historical operating coverage area, historical overlapping area area, historical energy consumption, and historical communication limitation data of at least two devices.

[0056] This embodiment uses the dimensions of operational data—operational coverage area, overlapping area, energy consumption, and communication-restricted data—as examples for illustration. The operational coverage area can be collected by sensors such as radar, cameras, and encoders deployed in the equipment. If a radar sensor is deployed, the operational coverage area can be represented by the area of ​​the radar sensor's detection area; if a camera is deployed, the operational coverage area can be represented by the area of ​​the camera's field of view; if an encoder is deployed, the encoder can collect the equipment's movement trajectory and travel distance, and combined with parameters such as the equipment's width and operational range, the operational coverage area can be calculated.

[0057] The overlapping area refers to the area of ​​the overlapping region between the work coverage areas of each device. Specifically, in this embodiment, when executed by the server, the server can obtain the location of the work coverage area uploaded by each device, and determine the overlapping area based on the work coverage areas of each device and the map of the total work area. In this embodiment, when executed by each device separately, each device can pre-download the total work area map to its local machine, obtain the work coverage area location of other devices through inter-device communication, and thus calculate the overlapping area.

[0058] Energy consumption can be calculated using data collected by current sensors deployed in the equipment. The energy consumption level of the control process can be calculated from the current consumed by the equipment. Communication constraints can be quantified by detecting signal strength using signal strength sensors or by periodically performing ping tests and calculating packet loss rates. For example, communication constraints can be quantitatively represented using values ​​from 0 to 1 based on different levels of signal strength and / or packet loss rates; higher values ​​indicate greater communication constraints.

[0059] Furthermore, the operational data from these different dimensions comes from diverse sources and takes various forms, requiring data preprocessing. Specifically, the first step is data cleaning: removing noisy data points, filling in missing data, and ensuring data quality. The second step is data normalization: eliminating the influence of different units of measurement and achieving data standardization. Finally, feature extraction: using data mining methods such as dimensionality reduction and frequency domain analysis to extract key feature values ​​from the data. Furthermore, the preprocessed data can be sorted according to the collection timestamp, organizing it into a structured dataset that is easy to analyze and utilize. Control effectiveness evaluation requires tracing back the entire control process and comparing data at different time points; time-series datasets can provide a data foundation for control effectiveness tracking.

[0060] In this embodiment, various sensors are the primary channels for the equipment to perceive the external environment. Sensor data contains rich information about the control process. By collecting and summarizing this data, the control effect can be quantitatively analyzed, control shortcomings identified, and optimization directions determined. The structured dataset generated based on sensor data makes data analysis standardized and efficient, laying a data foundation for subsequent control effectiveness modeling. Simultaneously, historical operation data from past tasks serves as valuable experiential knowledge. By comparing historical task data with current task data, influencing factors on control effectiveness can be identified, guiding the improvement and optimization of control strategies. Therefore, the collection and summarization of operation data in this embodiment is of great significance for achieving efficient collaborative control of multiple devices.

[0061] Specifically, the utility evaluation model can be expressed by the following formula: Where U represents overall utility, The weighting coefficient represents the utility value of the work coverage area, where A represents the utility value of the work coverage area, calculated as the proportion of the work coverage area to the total area, and k represents the power exponent. The weighting coefficient represents the area loss of the overlapping region, and R represents the area of ​​the overlapping region. This represents the area loss of the overlapping region, where m represents the nonlinear exponent of the area loss of the overlapping region. The weighting coefficients represent the energy consumption cost value. Indicates energy consumption. This indicates the maximum energy consumption of the equipment per unit time. The energy consumption cost is represented by n, where n is the nonlinear exponent of the energy consumption cost. The weighting coefficient represents the communication limitation loss value, C represents the communication limitation loss value, which is determined based on the communication limitation data, and p represents the nonlinear exponent of the communication limitation loss value.

[0062] Understandably, in the above utility assessment model formula, the impact of the work coverage area on the overall utility is... The power function form is expressed as follows: , , k is used to control the marginal rate of diminishing utility of the work coverage area; the utility of the work coverage area decreases as the area increases. When A approaches 1, The value approaches 1.

[0063] m determines the degree of impact of the overlapping area loss on the overall utility value, as... Increase, It will decrease rapidly, especially when m is large, the decrease will be more significant.

[0064] n describes the nonlinear negative impact of energy consumption costs on overall utility. The range of values ​​is In essence, it is the normalized value of energy consumption. The impact of energy consumption on overall utility is determined through... This indicates that when n>1, the negative impact of energy consumption costs accelerates with increasing energy consumption. Energy consumption E approaches its maximum value. At this point, the rate of decline in overall utility accelerates, reflecting that the impact of increased energy consumption on utility is non-linear; excessive energy consumption leads to a rapid decline in utility. When E reaches... hour, The value of will become 0, indicating that excessive energy consumption will lead to a complete loss of overall utility.

[0065] p represents the nonlinear exponent of the communication-limited loss value; the impact of communication-limited data on overall utility is expressed through... To express, When p>1, the negative impact of the communication limitation loss value C on the overall utility accelerates as C increases. That is, the higher the degree of communication limitation, the greater the negative impact on the overall utility, and the growth rate of this impact accelerates as C increases. This reflects that the impact of communication limitation on overall utility is non-linear, and the deterioration of communication quality will lead to a rapid decline in overall utility.

[0066] as well as This is used to balance the impact of operational data from different dimensions on overall utility. It can be flexibly adjusted based on the actual situation of the applicable scenario, so that the overall utility assessment results and the direction of control strategy optimization are closer to the operational task requirements of the current applicable scenario. For example, in search and rescue operations with high timeliness requirements, the weight of the operational coverage area... The weight of energy consumption should be appropriately increased; however, in long-term controlled scientific research operations, the weight of energy consumption should be... Then it should be improved.

[0067] Multiplying the above different dimensional terms yields a comprehensive utility function that takes into account the quantitative indicators of each dimension and reflects the complex synergistic relationships between them. Integrating this comprehensive utility function over the utility value A of the work coverage area yields the comprehensive utility value reflecting the overall comprehensive utility of the entire multi-device control process.

[0068] The utility evaluation model formula provided in this embodiment integrates operational data from multiple dimensions, making the evaluation of control utility more comprehensive and multi-dimensional. Furthermore, based on considering operational data from each dimension, it uses nonlinear functions such as power functions and exponential functions to characterize their impact on overall utility. This reflects complex characteristics such as the diminishing utility of shelf coverage area, the superlinear negative impact of overlap and energy consumption costs, and the nonlinear constraints of communication limitations. It also demonstrates the game-theoretic and synergistic relationships between operational data from different dimensions. The utility evaluation model formula is of significant value for optimizing control strategies to maximize overall utility.

[0069] The quantification process of historical operational data transforms abstract control strategies into measurable numerical values, enabling precise characterization of control effectiveness. Simultaneously, the various quantified values ​​are integrated into a comprehensive historical utility using a utility evaluation model formula. This comprehensive historical utility not only integrates multi-dimensional historical operational data such as operational coverage area, overlapping area, energy consumption, and communication limitations, but also precisely characterizes the impact of each dimension of operational data on the comprehensive utility through nonlinear functions. It effectively quantifies and evaluates the effectiveness of historical control strategies for historical operational tasks, providing a concise and intuitive reflection of the overall control level. This facilitates subsequent comparison and optimization of the utility of current and historical control strategies, thereby identifying key factors affecting control effectiveness and providing data support for analyzing control shortcomings and strategy optimization directions. Therefore, the construction of comprehensive utility values ​​makes control utility evaluation more scientific and systematic, providing a quantitative tool for adaptively adjusting control strategies.

[0070] S120. Based on the current operating data of each piece of equipment, determine the bottleneck index, and based on the utility evaluation model and the bottleneck index, determine the current comprehensive utility according to the current operating data of each piece of equipment.

[0071] Similarly, current operation data can also include the operation coverage area, overlapping area, energy consumption, and communication-restricted data dimensions. In this embodiment, when executed by the server, each device feeds back its current operation data to the server in real time or periodically. When executed by individual devices, current operation data from other devices is obtained through inter-device communication.

[0072] Furthermore, taking the example of each device executing its own control strategy, in addition to the various operational data used to calculate the overall utility as described in the above embodiments, each device also needs to actively perceive the environment using its own sensors and rationally schedule multiple sensors to work together: for example, using lidar, visual odometry, etc. to achieve positioning and mapping, using ranging sensors, contact sensors, etc. to perceive obstacles, and using inertial navigation, wheeled odometry, etc. to assist navigation. At the same time, it also needs to monitor its own status in real time, such as battery level and fault information, and while actively perceiving the environment, it also needs to introspect to maintain stable operation.

[0073] Furthermore, to optimize group behavior among devices, appropriate communication is necessary. Shared information primarily includes individual device location, controlled area, and detected targets, helping devices develop a sense of group collaboration and avoid conflict. However, communication frequency and data volume must be carefully designed to avoid excessive communication impacting control efficiency. The fusion of shared information and local sensing data is fundamental for individual devices to understand group behavior. For example, comparing a device's location with other devices can identify potential overlapping areas; combining its own energy consumption with the average energy consumption of other devices can infer the difference between individual control intensity and the overall group level. Individual devices integrate the collected sensing information with information shared by other devices to form a comprehensive understanding of the current control state, providing a basis for subsequent action decisions. This comprehensive understanding guides devices to adjust their control behavior and better integrate into group collaboration. Therefore, through autonomous sensing, appropriate communication, and information fusion, individual devices can establish connections with the group while maintaining independent control, which is crucial for achieving distributed collaboration among multiple devices.

[0074] The weakness index is used to reflect the degree of negative impact of controlling weaknesses on overall utility.

[0075] Furthermore, based on the current operating data of each piece of equipment, a bottleneck index is determined, including:

[0076] S121. Based on the current operating coverage area, current overlapping area, current energy consumption, and current communication limitation data of each device, determine the bottleneck data; wherein, the bottleneck data includes overlapping area bottleneck, energy consumption bottleneck, and communication limitation bottleneck. The overlapping area bottleneck is calculated by the ratio of the current overlapping area to the current operating coverage area. The energy consumption bottleneck is calculated by the ratio of the current energy consumption to the maximum energy consumption of the device per unit time. The communication limitation bottleneck is represented by the current communication limitation loss value, which is determined based on the current communication limitation data.

[0077] S122. Determine the short-board index based on the short-board data.

[0078] It is understandable that when the number of devices is fixed, the current operating coverage area of ​​each device will not change significantly in a short period of time. Therefore, this embodiment mainly calculates the bottleneck index based on the bottleneck of overlapping area, energy consumption, and communication limitation.

[0079] Specifically, the area short of the overlapping region is represented by the following formula: , Indicates the area of ​​the current overlapping region. This represents the current operational coverage area. Energy consumption shortcomings are represented by the following formula: , Indicates current energy consumption. This indicates the maximum energy consumption of the equipment per unit of time.

[0080] Furthermore, S122 may include: calculating the shortest-board index using the following formula: ;in, Indicating the weakness index, , as well as These represent the weighting coefficients for the overlapping area limitation, energy consumption limitation, and communication limitation, respectively. This indicates the area of ​​the overlapping region being the shortest. This indicates a weakness in energy consumption. This indicates a limitation in communication.

[0081] In this embodiment, the current operation data reflects the actual control performance of each device under the current control strategy. Based on the current operation data, the bottleneck factors of the control process of the current control strategy can be calculated. The overlap area bottleneck represents the degree of overlap of the operation coverage areas of different devices during the control process. The higher the overlap, the more redundant control there is and the lower the control efficiency. The energy consumption bottleneck reflects the energy consumption of individual devices during the control process. The higher the energy consumption, the less remaining energy, and the more limited the subsequent control capabilities will be. The larger the communication limitation bottleneck, the more severe the communication limitation, and the more hindered the information interaction and collaboration between individual devices during the control process will be. Based on the above three bottleneck data, the control bottleneck index ε can be further calculated. ε is a comprehensive index that integrates the three bottleneck data D1, D2, and D3 together in the form of an exponential function, while introducing three weighting coefficients. This is used to balance the impact intensity of different bottleneck factors. The value of ε ranges from [0,1]. The larger the value of ε, the more serious the bottleneck is, and the greater its impact on control efficiency. It can be determined in advance through calibration experiments.

[0082] Furthermore, based on the utility evaluation model and the bottleneck index, the current comprehensive utility is determined according to the current operating data of each device, including: determining the revised utility evaluation model based on the utility evaluation model and the bottleneck index; and determining the current comprehensive utility based on the revised utility evaluation model and the current operating data of each device.

[0083] In this embodiment, after obtaining the bottleneck index, the utility evaluation model needs to be modified based on the bottleneck index.

[0084] Furthermore, the revised utility evaluation model can be expressed by the following formula: Where U represents overall utility, The weighting coefficient represents the utility value of the work coverage area, where A represents the utility value of the work coverage area, calculated as the proportion of the work coverage area to the total area, and k represents the power exponent. The weighting coefficient represents the area loss of the overlapping region, and R represents the area of ​​the overlapping region. This represents the area loss of the overlapping region, where m represents the nonlinear exponent of the area loss of the overlapping region. The weighting coefficients represent the energy consumption cost value. Indicates energy consumption. This indicates the maximum energy consumption of the equipment per unit time. The energy consumption cost is represented by n, where n is the nonlinear exponent of the energy consumption cost. The weighting coefficient represents the communication limitation loss value, C represents the communication limitation loss value, which is determined based on the communication limitation data, and p represents the nonlinear exponent of the communication limitation loss value.

[0085] Based on the original utility assessment model, the revised utility assessment model incorporates... For this item, with other dimensions of operational data remaining constant, the larger the bottleneck index, the greater the decrease in overall utility after correction compared to before correction, reflecting the significant limiting effect of bottleneck factors on control efficiency. Introducing the control bottleneck index into the utility evaluation model allows it to consider practical problems such as overlapping control, excessive energy consumption, and limited communication, enabling a quantitative assessment of the control bottlenecks of the current control strategy. Real-time utility evaluation results will be closer to the actual control process, providing stronger guidance for optimizing the control strategy and offering a precise tool for adaptive adjustment of the control strategy.

[0086] In this embodiment, by collecting real-time current operational data, the equipment evaluates the overall effectiveness of the current control strategy and diagnoses existing bottlenecks. Simultaneously, a quantitative analysis of these bottlenecks is performed. Through three bottleneck data points and a comprehensive bottleneck index, the control effectiveness evaluation model comprehensively incorporates key influencing factors such as overlapping control, energy consumption constraints, and communication interference, significantly improving the relevance and practicality of the evaluation results. Bottleneck analysis not only clarifies the main contradictions in the current control but also quantitatively reflects the degree of bottlenecks, facilitating focused efforts. Furthermore, the bottleneck index's correction of the comprehensive effectiveness model ensures that the control efficiency evaluation remains closely aligned with the actual control situation, avoiding detachment from reality. Moreover, the bottleneck-driven strategy adjustment mechanism provides crucial support for adaptive optimization. Based on the bottleneck identification results, each device can purposefully improve its control strategy, specifically enhancing control performance. Control bottleneck analysis is a key step in the self-improvement and continuous evolution of multiple devices in actual tasks, holding milestone significance for achieving multi-device collaborative control.

[0087] S130. Determine the optimal control strategy based on the current comprehensive utility and historical comprehensive utility.

[0088] In this embodiment, the current comprehensive utility and the historical comprehensive utility can be compared, and then the control strategy can be adaptively adjusted.

[0089] Specifically, if the difference between the current comprehensive utility and the historical comprehensive utility is greater than or equal to a preset difference threshold, or if the duration for which the current comprehensive utility is greater than the historical comprehensive utility is greater than or equal to a preset time threshold, it indicates that the comprehensive utility under the current control strategy is better than the historical comprehensive utility, which means that the control effect of the current control strategy is good, and the current control strategy can be directly used as the optimal control strategy.

[0090] Otherwise, it indicates that the current control strategy is less effective than historically expected. Further analysis of the bottleneck factors based on current operational data and the bottleneck index can be conducted to optimize and adjust the control strategy. The specific process will be explained in detail in the next embodiment.

[0091] The technical solution of this invention determines the historical comprehensive utility through historical operating data and a utility evaluation model for each device. It then determines the bottleneck index based on the current operating data of each device and modifies the utility evaluation model accordingly. Finally, it determines the current comprehensive utility using the current operating data and the modified utility evaluation model, and finally determines the optimal control strategy based on the current and historical comprehensive utility. This invention constructs a utility evaluation model based on multi-dimensional operating data, forming a systematic evaluation system that effectively quantifies and evaluates the control utility of each device. The bottleneck index, calculated based on current operating data, quantitatively evaluates control bottlenecks, reflecting not only the strengths and weaknesses of the current control strategy but also providing direction for optimization. Finally, based on the current and historical comprehensive utility, it achieves adaptive adjustment of the optimal control strategy, enabling timely response to environmental changes, improving control efficiency, and ensuring continuous improvement in control utility.

[0092] Example 2

[0093] Figure 2 This is a flowchart of a multi-device collaborative control method provided in Embodiment 2 of the present invention. Based on the above embodiments, the present invention further specifies the process of determining the optimal control strategy.

[0094] like Figure 2 As shown, the method includes:

[0095] S210. Based on the utility evaluation model, determine the historical comprehensive utility according to the historical operating data of at least two devices.

[0096] S220. Based on the current operating data of each piece of equipment, determine the bottleneck index, and based on the utility evaluation model and the bottleneck index, determine the current comprehensive utility according to the current operating data of each piece of equipment.

[0097] S230. Determine the utility difference based on the current total utility and the historical total utility.

[0098] The specific process described above has been explained in the previous embodiment, and will not be repeated here.

[0099] S240. Determine whether the utility difference is greater than or equal to the preset utility threshold. If yes, execute S250; otherwise, execute S260.

[0100] This embodiment uses the determination of whether the utility difference is greater than or equal to a preset utility threshold as an example to illustrate the optimization and adjustment method of the control strategy.

[0101] S250, The current control strategy is adopted as the optimal control strategy.

[0102] When the utility difference is greater than or equal to the preset utility threshold, it indicates that the overall utility under the current control strategy is significantly better than the historical overall utility, indicating that the control effect of the current control strategy is superior to that of the historical control strategy, and the current control strategy can be directly regarded as the optimal control strategy.

[0103] Furthermore, after adopting the current control strategy as the optimal strategy, the current overall utility can be used as the historical overall utility as the basis for further optimization of the control strategy during subsequent operations. Each device continuously acquires the latest operational data, calculates the latest bottleneck index and overall utility, and compares it with the updated historical overall utility to optimize the control strategy. This achieves continuous improvement in control utility and continuous optimization of the control strategy.

[0104] S260. Determine the optimal control strategy based on current operational data and the bottleneck index.

[0105] Specifically, when the current control strategy's effectiveness falls short of historical expectations, it's necessary to extract key parameters from the current operational data to characterize control effectiveness. The operational coverage area reflects the size of the control range, the overlapping area reflects the redundancy in the control process, energy consumption represents control strength and equipment endurance, and limited communication reflects the quality of coordination between individual devices. These key parameters influence control effectiveness from different dimensions and need to be refined and quantified based on the current operational data.

[0106] The process of extracting key parameter features that affect control effectiveness is essentially a form of data dimensionality reduction. This involves mapping the original high-dimensional operational data to a relatively low-dimensional feature space to reveal the inherent patterns within the data. Common feature extraction methods include principal component analysis, independent component analysis, and factor analysis. These methods can remove redundancy and noise while preserving the core information of the data, making subsequent control effectiveness modeling and strategy optimization more efficient and reliable.

[0107] This embodiment provides a specific implementation method for determining the strategy adjustment method based on machine learning. Specifically, S260 may include:

[0108] S261. Based on the support vector machine model, and according to the current work data and the utility evaluation model corrected according to the short board index, determine the target dimension work data that needs to be optimized and adjusted in the current work data of each dimension.

[0109] S262. Based on reinforcement learning algorithm, improve the weight coefficient of the short board data corresponding to the target dimension operation data when calculating the short board index, and determine at least two candidate control parameter combinations with minimizing the short board index as the optimization objective.

[0110] The control parameters include at least one of the following: individual movement speed, sensing frequency, and communication interval;

[0111] S263. Based on the genetic algorithm, with minimizing the target dimension of the operation data as the optimization objective, evolutionary calculations are performed on each candidate control parameter combination to obtain the target control parameter combination.

[0112] S264. Use the combination of target control parameters as the optimal control strategy.

[0113] The control strategy may also include control parameters such as individual movement speed, sensing frequency, and communication interval. Individual movement speed determines the operational coverage area of ​​the equipment per unit time, but excessively high speeds may lead to insufficient observation and positioning drift. Sensing frequency affects the density and amount of data collected by the equipment; higher frequencies result in more data collection, but also greater computational burden and energy consumption. Communication interval controls the frequency of information interaction between individual devices; shorter intervals lead to more timely information interaction, which is beneficial for coordination between individuals, but frequent communication also brings more latency, energy consumption, and communication congestion. These parameters have complex coupling relationships; therefore, intelligent optimization algorithms are needed to adaptively fine-tune the control parameters of the control strategy.

[0114] Specifically, a Support Vector Machine (SVM) model is first used, taking the current task data in each dimension as input and the current overall utility as output, to learn the intrinsic relationship between the task data in each dimension and the overall utility value. Based on the trained SVM model, the overall utility under different task data is predicted, thereby obtaining the gradient information of the overall utility and outputting the direction for optimizing and adjusting the control strategy.

[0115] Then, based on reinforcement learning algorithms, with minimizing the bottleneck index ε as the optimization objective, the optimal control policy is learned through Q-learning. Q-learning uses the negative value of ε as an immediate reward, and converges to the optimal control policy through value iteration. Key parameters of the control policy can include individual movement speed, sensing frequency, and communication interval. The reinforcement learning phase can output multiple candidate control parameter combinations as candidate control policies.

[0116] Finally, the Genetic Algorithm (GA) is used to evolve the candidate control parameter combinations for each candidate control strategy. Each individual is encoded as a set of candidate control strategy parameters. Through selection, crossover, and mutation operations, the population evolves, continuously increasing the average fitness of the population (i.e., the negative value of the bottleneck index ε), ultimately yielding the optimized control strategy parameter combination. The Genetic Algorithm directly uses -ε as the fitness function, finding the parameter combination that minimizes ε through evolutionary calculation.

[0117] In this embodiment, reinforcement learning algorithm and genetic algorithm complement each other and jointly drive the adaptive adjustment of control strategy.

[0118] In a specific example, suppose that during the control process of multiple devices, the communication limitation bottleneck D3 remains consistently high, becoming a key bottleneck restricting the improvement of control effectiveness. First, SVM learns the significant impact of the communication limitation parameter on the overall utility value and outputs the adjustment direction to reduce D3. Further, reinforcement learning specifically increases the reward weight of the communication limitation bottleneck, guiding policy adjustments to focus more on improving communication quality. A genetic algorithm then selects the best individual with the smallest D3 from numerous candidate control parameter combinations, allowing it to reproduce in the population through genetic operations, ultimately evolving into the optimal control strategy with the lowest communication limitation. Driven by this bottleneck, the control strategy can quickly respond to real-time bottlenecks and adaptively optimize, enabling multiple devices to focus on key issues and continuously improve control effectiveness.

[0119] In this embodiment, machine learning is used to mine key parameter features of control utility from real-time operation data, establish a nonlinear mapping relationship between key parameter features and comprehensive utility values, and specifically optimize control weaknesses to achieve dynamic tuning of the control strategy and output the adjustment direction of the control strategy. This data-driven, weakness-oriented control concept opens up new avenues for improving the collaborative control efficiency of multiple devices. Combined with prior knowledge of the task scenario, it can achieve more efficient, flexible, and robust autonomous intelligent control of multiple devices.

[0120] Furthermore, S260 may include: determining the optimal control strategy based on the current comprehensive utility and historical comprehensive utility, until the cumulative control time is greater than or equal to a preset time threshold, and / or the control coverage rate is greater than or equal to a preset coverage rate threshold; wherein the control coverage rate is calculated based on the current operation data.

[0121] This embodiment also provides a mechanism for determining the termination conditions of a control task.

[0122] Specifically, the cumulative control time from the start of the multi-device collaborative control task to the current time is obtained by aggregating the timestamp data of each device. The time threshold is the maximum allowable control time set in advance based on factors such as task requirements and device capabilities. When the cumulative control time is greater than or equal to the preset time threshold, a time constraint is triggered. Time constraints prevent the control process from proceeding indefinitely, ensuring that the control task is completed within an acceptable time limit. It also helps balance control effectiveness and control costs. When the control time is too long, the accumulated energy consumption increases dramatically, while the rate of increase in control coverage may gradually slow down, or even experience diminishing marginal utility. Terminating control with a time constraint in this situation saves resources and prevents control from stagnating; this balance is beneficial for optimizing control efficiency.

[0123] Control coverage rate is a quantitative indicator describing the degree of control coverage, representing the proportion of the area covered by equipment operations to the total operating area. When the real-time statistical control coverage rate reaches a coverage threshold, it means that the desired level of control coverage has been achieved, reducing the necessity for continued control. This triggers coverage constraints, terminating the current control task. Setting the coverage threshold requires balancing environmental perception needs with control costs. If the threshold is set too low, the information from the control results will be insufficient to support subsequent tasks; if the threshold is too high, control will consume excessive time and resources, resulting in over-control. Real-time statistical analysis of control coverage rate and dynamic judgment of whether coverage constraints have been met allows control tasks to be completed automatically after meeting necessary coverage requirements, avoiding the lag of manual judgment. Simultaneously, this immediate feedback provides a basis for timely optimization and adjustment of control strategies. Effective coverage constraints can maximize the sufficiency of control results while timely termination of control to save control costs, achieving a balance between control performance and control costs, which will significantly improve the input-output efficiency of control activities.

[0124] By dynamically determining task termination conditions using time constraints and coverage constraints, the system fully considers time costs and control effects, and can intelligently balance the two to complete the control of multi-device collaborative operations at the optimal time. This enables control tasks to be carried out in a more economical and efficient manner, greatly improving the intelligence level of equipment control.

[0125] Once either the time constraint or the coverage constraint is triggered, the collaborative control of multiple devices ceases, and a control results report is generated. The control results report summarizes the control tasks performed and their effects. On one hand, it can include key data from the control process, such as control duration, energy consumption, and movement trajectory, leaving a complete data log for easy retrospective analysis. On the other hand, it can refine the control results into a structured dataset with high information density and standardized format. For example, a grid map or topology map can be used to represent the environment, with each cell or node labeled with its location, obstacles, and other attributes. This form of control results is easy to transmit and share, and can be directly used for subsequent tasks such as map building and path planning, significantly lowering the barrier to interpretation and application of control results. Timely output of control results reports accurately records the entire control process and highly summarizes the control results, making the management and utilization of control results more efficient and convenient.

[0126] In a specific application scenario, taking the collaborative control of multiple forklifts in a smart warehousing environment as an example, multiple forklifts need to control a building with an area of ​​approximately 1000 square meters. Based on the complexity of the building and the performance of the forklifts, the preset time threshold is 30 minutes, and the coverage threshold is 90%. After forklift control begins, real-time statistics show that at the 28th minute, the control coverage rate has reached 91%, at which point the coverage constraint is triggered, and the current control task automatically terminates. Simultaneously, a control results report is generated: the report shows that the control lasted 28 minutes, the five individual forklifts moved a total of 13,000 meters, and the cumulative energy consumption was 8 kWh; the control coverage rate was 91%, and the effective rack coverage area was 910 square meters; two impassable damaged areas were found during the control process and marked on the map. The control results are extracted into a raster map with a resolution of 5 centimeters, and each raster cell records environmental information such as access status, material, and elevation. This demonstrates that the dynamic application of time and coverage constraints, combined with the timely generation of control results reports, effectively ensures the successful completion of the control task. This demonstrates the important role of task termination conditions in improving control performance and saving the cost of ineffective control.

[0127] The technical solution of this embodiment, by constructing a utility evaluation model, can effectively quantify and evaluate the comprehensive control utility of multiple devices in collaborative operations. It provides a systematic index that comprehensively considers multiple dimensions of factors such as operation coverage area, energy consumption, overlapping areas, and communication limitations. The multi-dimensional quantitative evaluation can not only comprehensively reflect the advantages and disadvantages of the control strategy, but also provide a clear direction for strategy optimization. By optimizing the control strategy online, it can adaptively adjust according to the real-time collected current operation data, respond to environmental changes in a timely manner, and improve control efficiency. The introduction of the control bottleneck index enables the system to identify and quantify the bottlenecks in the current control strategy, and further optimize the control strategy through machine learning algorithms to ensure the continuous improvement of control utility. In addition, the mechanism for dynamically determining the termination conditions of the control task can effectively avoid resource waste and improve the overall efficiency and coverage of the task. This invention significantly improves the collaborative control capability of multiple devices in complex environments, reduces invalid driving paths and empty driving time, realizes an efficient and intelligent control process, further improves operation efficiency, and can effectively reduce the energy consumption of equipment.

[0128] Example 3

[0129] Figure 3 This is a schematic diagram of a multi-device collaborative control device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes:

[0130] The historical comprehensive utility determination module 310 is used to determine the historical comprehensive utility based on the utility evaluation model and the historical operating data of at least two devices.

[0131] The current comprehensive utility determination module 320 is used to determine the bottleneck index based on the current operating data of each device, and to determine the current comprehensive utility based on the utility evaluation model and the bottleneck index, according to the current operating data of each device.

[0132] The optimal control strategy determination module 330 is used to determine the optimal control strategy based on the current comprehensive utility and the historical comprehensive utility.

[0133] The technical solution of this invention determines the historical comprehensive utility through historical operating data and a utility evaluation model for each device. It then determines the bottleneck index based on the current operating data of each device and modifies the utility evaluation model accordingly. Finally, it determines the current comprehensive utility using the current operating data and the modified utility evaluation model, and finally determines the optimal control strategy based on the current and historical comprehensive utility. This invention constructs a utility evaluation model based on multi-dimensional operating data, forming a systematic evaluation system that effectively quantifies and evaluates the control utility of each device. The bottleneck index, calculated based on current operating data, quantitatively evaluates control bottlenecks, reflecting not only the strengths and weaknesses of the current control strategy but also providing direction for optimization. Finally, based on the current and historical comprehensive utility, it achieves adaptive adjustment of the optimal control strategy, enabling timely response to environmental changes, improving control efficiency, and ensuring continuous improvement in control utility.

[0134] Optionally, based on the above embodiments, the historical comprehensive utility determination module 310 includes:

[0135] The historical comprehensive utility determination unit is used to determine the historical comprehensive utility based on the utility evaluation model and according to the historical operating coverage area, historical overlapping area area, historical energy consumption, and historical communication limitation data of at least two devices.

[0136] Optionally, based on the above embodiments, the current comprehensive utility determination module 320 includes:

[0137] The bottleneck data determination unit is used to determine bottleneck data based on the current operating coverage area, current overlapping area, current energy consumption, and current communication limitation data of each device.

[0138] The bottleneck data includes overlapping area bottleneck, energy consumption bottleneck, and communication bottleneck. The overlapping area bottleneck is calculated by the ratio of the current overlapping area to the current operation coverage area. The energy consumption bottleneck is calculated by the ratio of the current energy consumption to the maximum energy consumption of the equipment per unit time. The communication bottleneck is represented by the current communication bottleneck loss value, which is determined based on the current communication bottleneck data.

[0139] The short-board index determination unit is used to determine the short-board index based on short-board data.

[0140] Optionally, based on the above embodiments, the current comprehensive utility determination module 320 includes:

[0141] The utility evaluation model correction unit is used to determine the corrected utility evaluation model based on the utility evaluation model and the bottleneck index.

[0142] The current comprehensive utility determination unit is used to determine the current comprehensive utility based on the modified utility evaluation model and the current operating data of each device.

[0143] Optionally, based on the above embodiments, the optimal control strategy determination module 330 includes:

[0144] The utility difference determination unit is used to determine the utility difference based on the current comprehensive utility and the historical comprehensive utility.

[0145] The first optimal control strategy determination unit is used to determine the current control strategy as the optimal control strategy if the utility difference is determined to be greater than or equal to a preset utility threshold.

[0146] The second optimal control strategy determination unit is used to determine the optimal control strategy based on the current operation data and the bottleneck index.

[0147] Optionally, based on the above embodiments, the second optimal control strategy determination unit is specifically used for:

[0148] Based on the support vector machine model, and according to the current work data and the utility evaluation model corrected by the bottleneck index, the target dimension work data that needs to be optimized and adjusted is determined from the current work data in each dimension.

[0149] Based on reinforcement learning algorithms, the weight coefficients of the short board data corresponding to the target dimension operation data are increased when calculating the short board index, and at least two candidate control parameter combinations are determined with minimizing the short board index as the optimization objective.

[0150] The control parameters include at least one of the following: individual movement speed, sensing frequency, and communication interval;

[0151] Based on the genetic algorithm, with minimizing the target dimension of the operation data as the optimization objective, evolutionary calculations are performed on each candidate combination of control parameters to obtain the target control parameter combination.

[0152] The target control parameter combination is used as the optimal control strategy.

[0153] Optionally, based on the above embodiments, the optimal control strategy determination module 330 includes:

[0154] The control stop condition judgment unit is used to determine the optimal control strategy based on the current comprehensive utility and the historical comprehensive utility, until the cumulative control time is greater than or equal to the preset time threshold, and / or the control coverage is greater than or equal to the preset coverage threshold.

[0155] The control coverage rate is calculated based on the current operation data.

[0156] The multi-device collaborative control device provided in the embodiments of the present invention can execute the multi-device collaborative control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0157] Example 4

[0158] Figure 4 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0159] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0160] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0161] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as multi-device collaborative control methods.

[0162] In some embodiments, the multi-device cooperative control method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the multi-device cooperative control method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the multi-device cooperative control method by any other suitable means (e.g., by means of firmware).

[0163] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0164] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable multi-device cooperative control device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0165] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0166] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0167] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0168] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0169] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0170] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for coordinated control of multiple devices, characterized in that, include: Based on the utility assessment model, the historical comprehensive utility is determined according to the historical operating data of at least two devices; Based on the current operating data of each piece of equipment, the bottleneck index is determined, and based on the utility evaluation model and the bottleneck index, the current comprehensive utility is determined according to the current operating data of each piece of equipment. The optimal control strategy is determined based on the current overall utility and the historical overall utility.

2. The method according to claim 1, characterized in that, Based on a utility assessment model, the historical overall utility is determined using historical operating data from at least two devices, including: Based on the utility evaluation model, the historical comprehensive utility is determined by taking into account the historical operating coverage area, historical overlapping area area, historical energy consumption, and historical communication limitation data of at least two devices.

3. The method according to claim 1, characterized in that, Based on the current operating data of each piece of equipment, determine the bottleneck index, including: Based on the current operating coverage area, current overlapping area, current energy consumption, and current communication limitations of each device, the bottleneck data is determined; The bottleneck data includes overlapping area bottleneck, energy consumption bottleneck, and communication bottleneck. The overlapping area bottleneck is calculated by the ratio of the current overlapping area to the current operation coverage area. The energy consumption bottleneck is calculated by the ratio of the current energy consumption to the maximum energy consumption of the equipment per unit time. The communication bottleneck is represented by the current communication bottleneck loss value, which is determined based on the current communication bottleneck data. Based on the data on shortcomings, a shortcomings index is determined.

4. The method according to claim 3, characterized in that, Based on the utility assessment model and the aforementioned bottleneck index, the current overall utility is determined according to the current operating data of each piece of equipment, including: Based on the utility assessment model and the aforementioned bottleneck index, the revised utility assessment model is determined. Based on the revised utility assessment model, the current overall utility is determined according to the current operating data of each device.

5. The method according to claim 1, characterized in that, Based on the current overall utility and historical overall utility, determine the optimal control strategy, including: Determine the utility difference based on the current total utility and the historical total utility; If the utility difference is determined to be greater than or equal to a preset utility threshold, then the current control strategy is taken as the optimal control strategy. Otherwise, determine the optimal control strategy based on current operational data and the bottleneck index.

6. The method according to claim 5, characterized in that, Based on current operational data and the bottleneck index, determine the optimal control strategy, including: Based on the support vector machine model, and according to the current work data and the utility evaluation model corrected by the bottleneck index, the target dimension work data that needs to be optimized and adjusted is determined from the current work data in each dimension. Based on reinforcement learning algorithms, the weight coefficients of the short board data corresponding to the target dimension operation data are increased when calculating the short board index, and at least two candidate control parameter combinations are determined with minimizing the short board index as the optimization objective. The control parameters include at least one of the following: individual movement speed, sensing frequency, and communication interval; Based on the genetic algorithm, with minimizing the target dimension of the operation data as the optimization objective, evolutionary calculations are performed on each candidate combination of control parameters to obtain the target control parameter combination. The target control parameter combination is used as the optimal control strategy.

7. The method according to claim 1, characterized in that, Based on the current overall utility and historical overall utility, determine the optimal control strategy, including: Based on the current comprehensive utility and historical comprehensive utility, determine the optimal control strategy until the cumulative control time is greater than or equal to the preset time threshold, and / or the control coverage is greater than or equal to the preset coverage threshold; The control coverage rate is calculated based on the current operation data.

8. A multi-device collaborative control device, characterized in that, include: The historical comprehensive utility determination module is used to determine the historical comprehensive utility based on the utility evaluation model and the historical operating data of at least two devices. The current comprehensive utility determination module is used to determine the bottleneck index based on the current operating data of each device, and to determine the current comprehensive utility based on the utility evaluation model and the bottleneck index, according to the current operating data of each device. The optimal control strategy determination module is used to determine the optimal control strategy based on the current comprehensive utility and historical comprehensive utility.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the multi-device collaborative control method as described in any one of claims 1-7.

10. A storage medium for storing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the multi-device collaborative control method as described in any one of claims 1-7.

Images