Cooperative control communication method for intelligent kitchen equipment

Abstract

The invention provides an intelligent kitchen equipment cooperative control communication method, and relates to the technical field of intelligent kitchen equipment cooperative control communication, and the method comprises the steps: calculating a basic node score of each piece of equipment through obtaining a resource configuration type, a resource configuration amount and historical work information of the equipment to be cooperatively controlled; the method comprises the steps of calculating a working stability coefficient of each device according to historical working information, calculating the communication quality between the devices according to the communication state between the devices in the historical working information, taking the communication quality as a node weight, constructing a task resource decomposition model, and obtaining a demand type, a demand quantity and a task instruction of each resource configuration distributed along with time. And calculating a node score according to the resource surplus, the basic node score, the node weight and the working stability coefficient of each device, determining a communication control node according to the node score and the duration of the node score, and sending a task control instruction according to the communication node.

Description

Technical Field

[0001] This invention relates to the field of collaborative control and communication technology for kitchen equipment, specifically to a collaborative control and communication method for intelligent kitchen equipment. Background Technology

[0002] Over the past few decades, with the rapid development and popularization of IoT and AI technologies, smart homes have gradually moved from concept to reality. Among these, the smart kitchen, as a scenario closely related to users' daily lives, is witnessing the emergence of an increasingly rich ecosystem of devices. A wide variety of smart kitchen devices have appeared on the market. These devices each have their own specific functions, aiming to improve the automation, intelligence, and convenience of kitchen work.

[0003] However, the proliferation of these devices has also brought new technological challenges. Currently, most smart kitchen devices remain isolated, and even those connected to the same network exhibit limited levels of collaborative control. Existing solutions often rely on simple scene linkages or fixed processes manually programmed by the user, such as "one-click cooking," which are essentially preset, static sequences of instructions. This approach lacks true intelligence and adaptability, and cannot cope with complex and dynamically changing real-world usage environments.

[0004] Specifically, existing technologies face several critical issues that urgently need to be addressed: First, the system lacks a unified understanding and dynamic management capability for heterogeneous device resources. Different smart kitchen devices exhibit significant resource differences, yet the system cannot quantify and evaluate these resources. Second, system decisions heavily rely on the static parameters of the devices. A device with excellent hardware configuration may experience stability degradation due to prolonged high-load operation, or experience connectivity issues with other nodes in the network due to communication module quality problems. The lack of consideration for actual operational quality makes the selected control nodes potentially unreliable. User natural language commands are complex, involving the scheduling and timing of multiple devices and resources. Existing systems struggle to accurately understand and decompose such abstract tasks, leading to a "semantic gap" between task requirements and the actual capabilities of the devices. Furthermore, if control node selection is based solely on instantaneous states, frequent switching of control due to network fluctuations or instantaneous loads can severely compromise system stability.

[0005] Therefore, there is an urgent need in this field for a collaborative control and communication method for intelligent kitchen equipment that can deeply integrate equipment resource status, actual working quality and user task intent, in order to achieve truly efficient, reliable and adaptive collaborative operation of intelligent kitchen equipment.

[0006] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0007] The purpose of this invention is to provide a collaborative control and communication method for intelligent kitchen equipment to solve the problems mentioned in the background art.

[0008] To achieve the above objectives, the present invention provides the following technical solution: A collaborative control communication method for intelligent kitchen equipment, comprising the following steps: Step 1: Obtain the resource configuration type, resource configuration quantity, and historical working information of the devices to be collaboratively controlled; calculate the resource allocation rate of each device based on the resource configuration type; and calculate the basic node score of each device based on the resource allocation rate and resource configuration quantity. Step 2: Based on historical work information, calculate the utilization rate and usage cycle coefficient of each resource configuration type of the equipment. Based on the utilization rate and usage cycle coefficient of each resource configuration type of the equipment, calculate the working stability coefficient of each equipment through the weight allocation method. Based on the communication status between the equipment in the historical work information, calculate the communication quality between each equipment as the node weight. Step 3: Build a task resource decomposition model, obtain the tasks published by users, input the tasks into the task resource decomposition model, and obtain the demand type, demand quantity, and task instructions for each resource configuration distributed over time. Step 4: Calculate the remaining resources of each device at each time. Calculate the node score based on the demand type, time distribution of demand, remaining resources of each device, basic node score, node weight, and working stability coefficient for each resource configuration. Determine the communication control node based on the node score and its duration. Send task control instructions based on the communication node.

[0009] Furthermore, the resource configuration types include communication, caching, and controller; The resource allocation includes communication bandwidth, cache capacity, and controller calculation frequency; Historical work information includes usage time, duration, and resource allocation data for each resource configuration type of the equipment; Furthermore, the method for calculating the resource allocation rate of each device is as follows: in, For the first The first device Resource allocation rate for each type of resource allocation For the first The equipment number of the device Resource allocation amount for each resource allocation type For the number of kitchen equipment, All are positive integers; The basic node score for each device is calculated based on the resource allocation rate and resource allocation amount. The specific calculation steps are as follows: The calculation method for the computing power of the equipment is as follows: An initial base calculation score is assigned based on the calculation frequency of the device's controller. The calculation efficiency is set in conjunction with the ambient temperature. The controller's calculation capacity is calculated based on the base calculation score, the calculation efficiency, and the resource allocation rate of the device controller. The method for calculating the communication capability of a device is as follows: A basic communication score is allocated based on the device's communication bandwidth, a security factor is allocated based on the communication method, a security communication index is calculated based on the security factor and the basic communication score, and the communication capacity is calculated based on the security communication index, the communication score, and the communication resource allocation rate. The method for calculating the device's cache capacity is as follows: A base cache score is assigned based on the cache capacity of each device, and the cache capacity is calculated based on cache speed, number of cache channels, and communication resource allocation rate. The initial basic node score is calculated by assigning weights to computing power, communication power, and caching power. The node fitness index is calculated based on the resource allocation of computing power, communication power, and caching power. The basic node score is then calculated based on the node fitness index and the initial basic node score.

[0010] Furthermore, the method for calculating the utilization rate of the resource configuration type is as follows: Obtain the usage time and usage amount of each device's resource configuration type in historical work information, calculate the average usage ratio, and set a baseline adjustment value and add it to the average usage ratio as the utilization rate of that resource configuration type; The method for calculating the period coefficient is as follows: Obtain the usage time of each device's resource configuration type from historical work information, calculate the ratio between the cumulative usage time of each resource and the device's working time, and set a baseline adjustment value and add it to the average usage ratio as the usage cycle coefficient.

[0011] Furthermore, the specific steps for calculating the communication quality between each device as the node weight are as follows: The basic communication volume is calculated by acquiring the communication duration, communication data volume, and communication frequency between devices. The basic communication quality is calculated by exponential fitting of the basic communication volume based on the number of communication interruptions and communication speed. The average of the basic communication quality between the device and all communicating devices is calculated as the communication quality of the device. The communication quality of all devices is then normalized to the maximum, and the normalized value is used as the node weight of the device.

[0012] Furthermore, the construction of the task resource decomposition model is based on natural language processing and knowledge graphs, specifically including: Text preprocessing structure: The raw text of the user-submitted task is transformed into structured information through word segmentation, part-of-speech tagging, and stop word removal; Named entity recognition structure: Identifies key entities in the task description, providing a data foundation for subsequent relation extraction and knowledge graph construction; Relationship extraction structure: Extract the specific relationships between entities to ensure that the constructed graph can correctly reflect the dependencies between tasks and resources; Knowledge graph node and edge structure: Elements such as tasks, resources, and time exist as nodes in the graph, and the relationships between entities are represented by edges, which are used for association reasoning between tasks and resources and decomposition of resource requirements.

[0013] Furthermore, the method for calculating the node score based on node demand, basic node score, node weight, and operational stability coefficient is as follows: Based on the needs for computing power, communication power, and caching power, calculate the remaining resource ratio with the remaining capacity of each resource configuration type of the device, and obtain the node demand by accumulating the remaining resource ratio between resource configuration types through weight allocation. The formula for calculating node scores is: in, Rate the nodes For node demand, Basic node scoring, For node weights, For job stability coefficient, The correction coefficient for the basic node score. This is the weighting adjustment factor. To serve as a stable base.

[0014] Furthermore, the method for determining the communication control node based on the duration of the node score and the node score is as follows: Set time intervals, obtain the highest node score at each time interval point, and the corresponding device. Use n time intervals as the length of the time window and set the step value to n / na, where na is the step size setting. Filter out node scores whose duration is less than n / nb, where nb is the node filtering coefficient. Calculate the average node score of each device within the time window, and select the communication control node with the highest average node score within the current time window. Here, n, na, and nb are all positive integers.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention obtains the resource configuration type, resource configuration quantity and historical working information of the devices to be coordinated and controlled, calculates the basic node score of each device, calculates the working stability coefficient of each device based on the historical working information, calculates the communication quality between each device based on the communication status between devices in the historical working information, and uses it as the node weight to construct a task resource decomposition model, obtains the demand type, demand quantity and task instructions of each resource configuration distributed over time, calculates the node score based on the remaining resource quantity, basic node score, node weight and working stability coefficient of each device, determines the communication control node based on the node score and the duration of the node score, and sends task control instructions based on the communication node; This invention establishes a comprehensive equipment capability evaluation system by introducing quantitative indicators such as resource allocation rate and basic node score. This enables the system to accurately "perceive" the resource endowment of each device from three core dimensions: computing, communication, and caching. Through the computing node adaptability index, the system can also effectively avoid the "weakest link" effect, prioritizing devices with a balanced resource structure, which greatly improves resource utilization efficiency and task execution reliability. This solution creatively incorporates the historical working information and real-time communication status of the equipment into the core of decision-making. By calculating the working stability coefficient and node weight, the system can identify high-quality equipment that has been verified over a long period of time, operates steadily, and occupies a communication hub position in the network. This significantly improves the reliability and coordination efficiency of the control nodes and effectively reduces the risk of the entire task failing due to a single point of failure or communication delay. The task resource decomposition model constructed in this solution successfully breaks down the barrier between user intent and machine execution by utilizing natural language processing and knowledge graph technologies. This model can deeply analyze complex user instructions, accurately decompose them into executable subtasks with clear resource requirements, time sequences, and dependencies, and generate matching resource scheduling schemes accordingly, greatly improving the system's intelligence level and user experience. Regarding the decision-making mechanism of control nodes, this solution introduces a continuous duration verification method based on time windows, which can effectively filter out the interference of instantaneous states and ensure that only those devices that can stably maintain a high score can be elected as control nodes. This avoids frequent fluctuations in control and ensures the smooth and coherent execution of the collaborative control process. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the overall method flow of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0018] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0019] Example: Please see Figure 1 The present invention provides a technical solution: A collaborative control communication method for intelligent kitchen equipment, comprising the following steps: Step 1: Obtain the resource configuration type, resource configuration quantity, and historical working information of the devices to be collaboratively controlled. Calculate the resource allocation rate of each device based on the resource configuration type, and calculate the basic node score of each device based on the resource allocation rate and resource configuration quantity.

[0020] This step comprehensively acquires the resource configuration types, resource quantities, and historical operating information of the kitchen equipment to be collaboratively controlled, and integrates the resource information of all equipment, providing a solid data foundation for the entire collaborative control system. The advantage of this step lies in its systematic collection and standardization of equipment resource data, ensuring the system has a comprehensive understanding of each device's hardware capabilities (such as communication bandwidth, cache capacity, and controller computation frequency) and historical performance, thus providing an objective basis for subsequent resource allocation and decision-making. By calculating the resource allocation rate of each device, the system can quantify the relative resource contribution of each device when acting as a communication node, identify resource-rich devices, and calculate a basic node score based on resource type. This score comprehensively evaluates the device's computing power, communication capabilities, and cache capacity, providing key indicators for subsequent node selection and task scheduling. This step significantly improves the efficiency and reliability of the overall intelligent kitchen equipment collaborative control communication method. It enables the system to dynamically adapt to changes in equipment resources, optimize resource utilization, avoid resource bottlenecks or waste, and lays the foundation for subsequent steps such as calculating the working stability coefficient, applying the task decomposition model, and selecting control nodes. This enhances the collaborative response speed, task execution accuracy, and overall stability of the entire system, ultimately achieving efficient and intelligent collaborative control between kitchen equipment.

[0021] In this embodiment, the resource configuration types include communication, caching, and controller; The resource allocation includes communication bandwidth, cache capacity, and controller calculation frequency; Historical work information includes usage time, duration, and resource allocation data for each resource configuration type of the equipment.

[0022] Furthermore, the method for calculating the resource allocation rate of each device is as follows: in, For the first The first device Resource allocation rate for each type of resource allocation For the first The equipment number of the device Resource allocation amount for each resource allocation type For the number of kitchen equipment, All are positive integers.

[0023] The method of calculating the resource allocation rate of each device aims to quantify the relative capabilities and contributions of each device in a specific resource configuration type. This provides a key resource assessment indicator for the collaborative control system, ensuring that task allocation and node selection are optimized based on the actual resource status of the devices. The resource allocation rate is calculated by comparing the number of resource configuration types for each device with the total number of all devices with the same resource configuration type, resulting in a ratio. This value reflects the device's share of global resources, helping the system identify devices with abundant or scarce resources, thereby achieving load balancing and efficient resource utilization. A low resource allocation rate for communication indicates a low proportion of communication resources, and the system may prioritize devices with higher allocation rates when allocating high-bandwidth tasks. This method ensures the objectivity and consistency of resource assessment, providing standardized input for subsequent basic node scoring, thus improving the decision-making accuracy and efficiency of the entire collaborative control system.

[0024] The basic node score for each device is calculated based on the resource allocation rate and resource allocation amount. The specific calculation steps are as follows: The calculation method for the computing power of the equipment is as follows: An initial base calculation score is assigned based on the calculation frequency of the device's controller. The calculation efficiency is set in conjunction with the ambient temperature. The controller's calculation capacity is calculated based on the base calculation score, the calculation efficiency, and the resource allocation rate of the device controller. The method for calculating the communication capability of a device is as follows: A basic communication score is allocated based on the device's communication bandwidth, a security factor is allocated based on the communication method, a security communication index is calculated based on the security factor and the basic communication score, and the communication capacity is calculated based on the security communication index, the communication score, and the communication resource allocation rate. The method for calculating the device's cache capacity is as follows: A base cache score is assigned based on the cache capacity of each device, and the cache capacity is calculated based on cache speed, number of cache channels, and communication resource allocation rate. The initial basic node score is calculated by assigning weights to computing power, communication power, and caching power. The node fitness index is calculated based on the resource allocation of computing power, communication power, and caching power. The basic node score is then calculated based on the node fitness index and the initial basic node score.

[0025] The purpose of calculating computing power, communication capability, and caching capability using this method is to establish a comprehensive quantitative evaluation system, ensuring that the performance characteristics of each device in the collaborative control system can be objectively measured and effectively compared. Computing power characterizes the core performance of a device in processing control commands and running algorithms; it reflects the device's stable computing ability under specific environmental conditions. Computing efficiency can be precisely set using a temperature-efficiency correspondence table, for example, efficiency is 1.0 for 10-30℃, and decreases by 0.1 for every 5℃ beyond this range.

[0026] Communication capability characterizes the overall performance of a device's data transmission, including transmission rate and security reliability. The security factor should be clearly defined according to the security level of the communication protocol. Caching capability characterizes the device's ability to temporarily store and process data. Caching efficiency can be calculated using a standardized formula that integrates caching speed and the number of channels. The node fitness index is calculated based on the resource allocation ratio of computing capability, communication capability, and caching capability. This is to assess the balance of the device's resource structure and avoid the "barrel effect" where some resources are excessively powerful while others are significantly insufficient. Its core idea is to identify devices with more coordinated overall performance by quantifying the matching degree of these three core resources. The node fitness index is calculated using the coefficient of variation method, specifically through the following steps: First, the three values ​​of computing capability, communication capability, and caching capability are standardized to make them comparable. Then, the ratio of the standard deviation to the mean of these three values ​​is calculated as the coefficient of variation. Finally, the node fitness index is defined as 1 minus this coefficient of variation, ensuring the result is between 0 and 1. For example, a device scores 80 in computing power, 75 in communication power, and 85 in caching power, with an average of 80, a standard deviation of approximately 5, a coefficient of variation of 5 / 80 = 0.0625, and a node fitness index of 1 - 0.0625 = 0.9375. Another device scores 30 in computing power, 85 in communication power, and 25 in caching power, with an average of approximately 46.7, a standard deviation of approximately 32.1, a coefficient of variation of approximately 0.687, and a node fitness index of only 0.313. This calculation method has significant advantages for the overall intelligent kitchen equipment collaborative control communication scheme. It can select devices with balanced resource structures as control nodes, ensuring that no device becomes a system bottleneck due to a weakness in any aspect when undertaking collaborative tasks. This improves the reliability and stability of task execution, and extends the lifespan of equipment by promoting balanced resource utilization, ultimately achieving efficient and stable operation of the entire kitchen equipment collaborative system.

[0027] The purpose of calculating the basic node score using this method is to establish a quantitative comprehensive equipment capability evaluation system. The basic node score represents the overall performance level of the equipment across three dimensions: computing, communication, and caching. A higher score indicates that the equipment is more suitable for collaborative control tasks. By quantifying and weighting the core resource capabilities of the equipment across multiple dimensions, the basic node score provides an objective basis for node selection in the system. Its value directly reflects the equipment's potential capability as a control node; a higher score indicates greater advantages in resource allocation, operational efficiency, and functional completeness.

[0028] Step 2: Based on historical work information, calculate the utilization rate and usage cycle coefficient of each resource configuration type of the equipment. Based on the utilization rate and usage cycle coefficient of each resource configuration type of the equipment, calculate the working stability coefficient of each equipment by weighting. Based on the communication status between the equipment in the historical work information, calculate the communication quality between each equipment as the node weight.

[0029] This step, through in-depth analysis of the equipment's historical operating information and communication status, achieves a comprehensive capability profile, from static resource assessment to dynamic operational performance. Its core advantage lies in incorporating the time dimension and inter-device collaboration relationships into the evaluation system, enabling the system to assess current and future performance based on the equipment's actual operational history. By calculating the utilization rate and usage cycle coefficient of resource configuration types, the system can identify devices that maintain stable operating status over long periods. For example, a smart oven, whose controller resource utilization rate consistently remains within a reasonable range of 60%-70% and has a high usage cycle coefficient, indicates its ability to withstand continuous workloads for extended periods. Such devices are more advantageous when allocated resources requiring sustained and stable computing power. Simultaneously, by analyzing the communication quality between devices and quantifying it as node weights, the system can establish a quantitative model of inter-device collaboration relationships. For instance, when a smart refrigerator maintains stable high-speed communication with multiple devices, its higher node weight value indicates its suitability as a communication control node, while a device with abundant resources but frequent communication interruptions will receive a lower weight. This dynamic evaluation based on historical data plays a key role in optimizing the overall intelligent kitchen equipment collaborative control communication scheme. It enables the system to avoid devices with high hardware configurations but unstable actual operation, and prioritize reliable nodes that have been verified over a long period of time, thereby significantly improving the stability and success rate of task execution. At the same time, by establishing a communication quality map between devices to optimize data transmission paths, it reduces communication delays and failure risks in the collaborative control process, ultimately forming an intelligent collaborative network that can learn and continuously optimize itself.

[0030] In this embodiment, the method for calculating the resource configuration type utilization rate is as follows: Obtain the usage time and usage amount of each device's resource configuration type in historical work information, calculate the average usage ratio, and set a baseline adjustment value and add it to the average usage ratio as the utilization rate of that resource configuration type; The method for calculating the period coefficient is as follows: Obtain the usage time of each device's resource configuration type from historical work information, calculate the ratio between the cumulative usage time of each resource and the device's working time, and set a baseline adjustment value and add it to the average usage ratio as the usage cycle coefficient.

[0031] The purpose of calculating resource configuration type utilization rate and usage cycle coefficient using this method is to establish a quantitative evaluation system for equipment resource usage patterns. Its core value lies in transforming historical equipment operating data into reliable indicators of current and predicted future stability. Resource configuration type utilization rate reflects the resource load characteristics of equipment during long-term operation, while the usage cycle coefficient reveals the equipment's durability and continuous working capability. Together, they constitute the data foundation for equipment reliability assessment.

[0032] Resource configuration type utilization rate is calculated using historical data within a specified time window, such as the resource usage records of the most recent 30 days, with hourly sampling points. For example, if the controller resource of a smart oven has an average utilization rate of 65% across 200 sampling points, this is directly used as the utilization rate indicator. For smart devices lacking historical data, calculations are based on baseline adjustment values. This refined calculation enables the overall smart kitchen equipment collaborative control and communication scheme to identify devices that maintain reasonable loads and stable operating cycles over long-term operation.

[0033] In this embodiment, the specific steps for calculating the communication quality between each device as the node weight are as follows: The basic communication volume is calculated by acquiring the communication duration, communication data volume, and communication frequency between devices. The basic communication quality is calculated by exponential fitting of the basic communication volume based on the number of communication interruptions and communication speed. The average of the basic communication quality between the device and all communicating devices is calculated as the communication quality of the device. The communication quality of all devices is then normalized to the maximum, and the normalized value is used as the node weight of the device.

[0034] The core purpose of calculating node weights using this method is to establish a quantitative evaluation system for the communication reliability of devices in a network. Its fundamental value lies in transforming abstract communication relationships into concrete numerical indicators, enabling the system to identify key devices that occupy core positions in the network and maintain stable communication. The level of node weight directly reflects the hub status and transmission reliability of a device in a collaborative communication network; devices with higher weights are more suitable for undertaking key roles in control command relay and collaborative scheduling.

[0035] The basic communication volume is a weighted product of communication duration, communication data volume, and number of communication attempts. In the exponential fitting, the number of interruptions is represented by an attenuation form of exp(-λ × number of interruptions), where λ represents the quality degradation coefficient for each interruption. The impact of communication speed is expressed as a relative value, normalized based on the fastest communication speed in the network. This refined weighting calculation plays a crucial optimization role in the overall intelligent kitchen equipment collaborative control communication scheme. It enables the system to construct a network topology based on actual communication performance, prioritizing devices with stable communication and wide connectivity as control hubs. For example, a smart refrigerator with a node weight of 0.9 is more suitable for handling multi-device coordination tasks than a smart oven with a weight of 0.3, thus significantly reducing communication latency and transmission failure rate, enhancing the system's real-time response capability, and simultaneously optimizing the network layout in advance by identifying communication bottlenecks, ultimately ensuring the efficiency and reliability of collaborative control between kitchen equipment.

[0036] Step 3: Build a task resource decomposition model, obtain the tasks published by users, input the tasks into the task resource decomposition model, and obtain the demand type, demand quantity, time distribution of resource demand, and task instructions for each type of resource.

[0037] This step transforms user-issued task commands in natural language into precise, structured descriptions of resource requirements by constructing a task resource decomposition model. Its core advantage lies in bridging the semantic gap between task requirements and equipment resources in smart kitchen systems, achieving a precise mapping from user intent to machine-executable instructions. Employing natural language processing and knowledge graph technologies, this step deeply understands the contextual semantics of user commands. For example, when a user issues a compound command like "Prepare dinner at 6 PM using the oven and steamer, keeping the kitchen air fresh," the model not only identifies target devices such as "oven," "steamer," and "range hood," but also precisely decomposes the specific requirements and execution time distribution for different resource configuration types, including computational resource requirements (oven temperature control algorithm), communication resource requirements (inter-device synchronization timing instructions), and caching resource requirements (temporary storage of recipe data). It then generates executable instruction sequences such as "Start the oven to 180 degrees at 18:00," "Start the steamer at 18:05," and "Turn on the range hood throughout." This intelligent task parsing plays a crucial pivotal role in the overall intelligent kitchen equipment collaborative control and communication scheme. It enables the system to transform abstract user needs into specific resource scheduling schemes, providing accurate input basis for subsequent node scoring calculations and control node selection. This ensures that task allocation meets both user intentions and the current state of equipment resources, thereby significantly improving the system's intelligence level and user experience. At the same time, it avoids equipment resource conflicts or excesses through accurate resource demand prediction, optimizing the energy efficiency management and collaborative efficiency of the entire kitchen system.

[0038] In this embodiment, the construction task resource decomposition model is based on natural language processing and knowledge graph, and specifically includes: Text preprocessing structure: The original text of the task published by the user is processed through word segmentation,词性标注 (positional tagging), and stop word removal to be converted into structured information; Named entity recognition structure: Identify the key entities in the task description to provide a data basis for subsequent relationship extraction and knowledge graph construction; Relationship extraction structure: Extract the specific relationships between entities to ensure that the constructed graph can correctly reflect the dependencies between tasks and resources; Knowledge graph node and edge structure: Elements such as tasks, resources, and time exist as nodes in the graph, and the relationships between entities are represented by edges between the nodes, which are used for association reasoning between tasks and resources and resource requirement decomposition.

[0039] In the text preprocessing structure stage, the original text of the task published by the user is initially processed to be converted into structured information. This process includes word segmentation, positional tagging, and stop word removal of the text. The purpose of word segmentation is to break the text into smaller units - words, which can be key elements in the task description. Positional tagging is used to indicate the grammatical roles of each word (such as nouns, verbs, etc.) to provide a grammatical basis for subsequent entity recognition and relationship extraction. Stop word removal is to remove common words that have no practical meaning for the task content (such as "的", "是", etc.), which can reduce redundant information and retain more important key information.

[0040] In the named entity recognition structure stage, key entities are identified from the task description text. Key entities can include information such as the task itself, the resources involved, time, location, participants, etc. Through the NER model, we can extract these key information from natural language text to lay a foundation for subsequent relationship extraction and knowledge graph construction. In this stage, the output of the model is a set containing multiple entities, and each entity has a clear semantic annotation and position index.

[0041] In the relationship extraction structure stage, the task of this stage is to extract the specific relationships between the already identified entities. The core goal of relationship extraction is to identify the dependency relationships between entities by analyzing the semantic associations in the task text, such as the relationship between tasks and resources, and the time constraints of tasks. Through relationship extraction, we can construct the interconnections between various elements in the task, and these connections will become the edges in the knowledge graph. To ensure the correctness and effectiveness of the graph, relationship extraction not only needs to identify the direct connections between entities, but also infer potential associations to ensure that the dependency relationships between task resources are comprehensively and accurately described.

[0042] In the knowledge graph node and edge structure stage, key elements of the task, such as the task itself, resources, and time, are represented as nodes in the graph. Each node represents a task or resource element. Edges represent the relationships between these elements, with edge types indicating different types of relationships, such as dependency or temporal order. In a knowledge graph, edges are not always unidirectional; bidirectional or multi-directional relationships are possible. These require proper modeling during the construction process. The graph's structure facilitates reasoning about the relationships between tasks and resources, providing an intuitive way to understand resource requirements and allocation during task execution. Through the graph's reasoning capabilities, resource allocation, scheduling, and task execution order can be further optimized, providing crucial decision support for task resource decomposition.

[0043] Step 4: Calculate the remaining resources of each device at each time. Calculate the node score based on the demand type, time distribution of demand, remaining resources of each device, basic node score, node weight, and working stability coefficient for each resource configuration. Determine the communication control node based on the node score and its duration. Send task control instructions based on the communication node.

[0044] This step establishes a dynamic, real-time equipment evaluation and selection mechanism. It precisely matches the static capability indicators and historical performance of the equipment obtained in previous steps—namely, basic node scores, node weights, and operational stability coefficients—with the actual needs of the current task. Its core advantage lies in achieving a closed-loop decision-making process from theoretical evaluation to actual execution. By quantitatively calculating the adaptability of each device to the current task at a specific moment and introducing a time-based verification mechanism, it ensures the accuracy and stability of control node selection. First, based on the resource demand types, quantities, and time distribution obtained from task decomposition, and combined with the real-time resource availability of the equipment, this step calculates the node demand of each device in the task time dimension. This indicator reflects the matching degree between equipment resources and task requirements. Then, it integrates the inherent performance of the equipment represented by the basic node score, the communication hub value reflected by the node weight, and the operational reliability characterized by the operational stability coefficient. Through multi-factor fusion calculation, it obtains a dynamically changing node score. Finally, by introducing a judgment condition based on the duration of the score, it avoids frequent switching of control nodes due to instantaneous fluctuations. Switching is only triggered when a device's node score is consistently better than the current node over a given period. This dynamic evaluation and stable decision-making mechanism plays a crucial role in optimizing the overall intelligent kitchen equipment collaborative control communication scheme. It ensures that the system can select the most suitable control node based on real-time task requirements and equipment status, making full use of the advantages of high-performance equipment while avoiding unreliable equipment from undertaking critical tasks through stability considerations. At the same time, it maintains the stability of the control structure through continuous judgment, thereby improving the overall success rate of task execution, reducing communication latency, and enhancing the system's robustness in the face of complex and ever-changing environments. Ultimately, it achieves efficient, stable, and reliable operation of intelligent kitchen equipment collaborative control.

[0045] In this embodiment, the method for calculating the node score based on the node demand, basic node score, node weight, and operational stability coefficient is as follows: Based on the needs for computing power, communication power, and caching power, the remaining resource ratio is calculated with the remaining capacity of each resource configuration type of the device. The node demand is then obtained by accumulating the remaining resource ratios between resource configuration types through weight allocation.

[0046] The resource surplus ratio is specifically the ratio of remaining resource capacity to resource demand. It requires separate calculations of the remaining computing capacity, communication capacity, and caching capacity. For example, the remaining computing capacity ratio = remaining device computing capacity / task computing capacity demand. This method calculates node demand to establish a dynamic matching mechanism between task requirements and device resources. Its core value lies in transforming the abstract collaborative control problem into a concrete resource optimization and allocation problem, enabling the system to select the most suitable device to execute tasks based on real-time resource conditions. The calculation of node demand, by comparing the degree of matching between the computing power, communication capacity, and caching capacity required by the task and the currently available resources of the device, provides the system with a precise basis for device selection. This method effectively avoids assigning tasks to devices with insufficient or excessive resources, thereby achieving optimal resource utilization.

[0047] The formula for calculating node scores is: in, Rate the nodes For node demand, Basic node scoring, For node weights, For job stability coefficient, The correction coefficient for the basic node score. This is the weighting adjustment factor. To serve as a stable base.

[0048] This node scoring formula achieves a precise quantitative assessment of the overall capabilities of equipment through a nonlinear combination of multi-level parameters. This represents the final node score; a higher score indicates that the device is more suitable to serve as a control node. This refers to the node demand, reflecting the degree of matching between equipment resources and task requirements. It is a basic node score, reflecting the inherent performance benchmark of the equipment. Node weights represent the value of a device as a communication hub in the network. It is the operational stability coefficient, which describes the long-term reliability of the equipment. As a basic node scoring correction coefficient, it is used to adjust the scoring benchmark to prevent... If the value is too low, it will affect the stability of the calculation. β is used as a weight correction coefficient to adjust the sensitivity of the node weights and avoid excessive fluctuations in the exponential part.

[0049] The index part This allows the equipment to achieve a scoring amplification effect, ultimately through... Stability adjustment is introduced to mitigate the impact on operational stability. This design achieves this through... Ensure that task requirements are prioritized and matched, through The basic node scoring establishes a performance benchmark threshold, through Node weights enhance network communication advantages, through The operational stability coefficient ensures long-term reliable operation, ultimately forming a scoring mechanism that responds to real-time demands while also considering historical performance. For intelligent kitchen collaborative control systems, this formula achieves dynamic optimization decisions through adjustable parameters. It prioritizes high-performance equipment under high load scenarios, favors reliable equipment when stability requirements are high, and emphasizes the value of hub equipment in complex communication tasks. This comprehensively improves the system's task execution success rate, resource utilization efficiency, and network communication quality, achieving truly adaptive intelligent collaborative control.

[0050] In this embodiment, the method for determining the communication control node based on the duration of the node score and the node score is as follows: Set time intervals, obtain the highest node score at each time interval point, and the corresponding device. Use n time intervals as the length of the time window and set the step value to n / na, where na is the step size setting. Filter out node scores whose duration is less than n / nb, where nb is the node filtering coefficient. Calculate the average node score of each device within the time window, and select the communication control node with the highest average node score within the current time window. Here, n, na, and nb are all positive integers.

[0051] The core advantage of this method in determining communication control nodes lies in establishing a stable decision-making mechanism based on time window statistical analysis. This method effectively solves the problem of frequent control switching caused by instantaneous fluctuations in node scores in traditional methods by introducing multi-parameter collaborative control of time window length, step size, and node selection coefficient. The technical implementation first sets a fixed time interval (e.g., 1 second) to collect the scores of each device node, identifying the highest-scoring device in each interval. Then, a sliding time window is constructed with n intervals (e.g., n=10 represents a 10-second window), and a step size of n / na (e.g., na=2, then the step size is 5 seconds) is set to update the window. Next, a node selection coefficient nb (e.g., nb=5) is used to filter out instantaneously high-scoring devices with a duration less than n / nb (i.e., 2 seconds), effectively eliminating interference from random score peaks. Finally, the average node score of each device within the time window is calculated, and the device with the highest average score is selected as the control node. The core value of this method for intelligent kitchen collaborative control systems lies in ensuring, through continuous stability verification in the time dimension, that the selected control node not only has high score characteristics but also possesses continuously stable performance, thereby significantly improving the stability and reliability of the system control structure.

[0052] All the above formulas use dimensionless numerical values ​​for calculation, and the numerical values ​​substituted into the formulas are all in the International System of Units (SI). The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0053] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0054] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0055] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A collaborative control and communication method for intelligent kitchen equipment, characterized in that, The specific steps include: Step 1: Obtain the resource configuration type, resource configuration quantity, and historical working information of the devices to be collaboratively controlled; calculate the resource allocation rate of each device based on the resource configuration type; and calculate the basic node score of each device based on the resource allocation rate and resource configuration quantity. Step 2: Based on historical work information, calculate the utilization rate and usage cycle coefficient of each resource configuration type of the equipment. Based on the utilization rate and usage cycle coefficient of each resource configuration type of the equipment, calculate the working stability coefficient of each equipment through the weight allocation method. Based on the communication status between the equipment in the historical work information, calculate the communication quality between each equipment as the node weight. Step 3: Build a task resource decomposition model, obtain the tasks published by users, input the tasks into the task resource decomposition model, and obtain the demand type, demand quantity, and task instructions for each resource configuration distributed over time. Step 4: Calculate the remaining resources of each device at each time. Calculate the node score based on the demand type, time distribution of demand, remaining resources of each device, basic node score, node weight, and working stability coefficient for each resource configuration. Determine the communication control node based on the node score and its duration. Send task control instructions based on the communication node.

2. The intelligent kitchen equipment collaborative control communication method according to claim 1, characterized in that: The resource configuration types include communication, caching, and controller; The resource allocation includes communication bandwidth, cache capacity, and controller calculation frequency; Historical work information includes usage time, duration, and resource allocation data for each resource configuration type of the equipment.

3. The intelligent kitchen equipment collaborative control communication method according to claim 1, characterized in that: The method for calculating the resource allocation rate of each device is as follows: in, For the first The first device Resource allocation rate for each type of resource allocation For the first The equipment number of the device Resource allocation amount for each resource allocation type For the number of kitchen equipment, All are positive integers; The basic node score for each device is calculated based on the resource allocation rate and resource allocation amount. The specific calculation steps are as follows: The calculation method for the computing power of the equipment is as follows: An initial base calculation score is assigned based on the calculation frequency of the device's controller. The calculation efficiency is set in conjunction with the ambient temperature. The controller's calculation capacity is calculated based on the base calculation score, the calculation efficiency, and the resource allocation rate of the device controller. The method for calculating the communication capability of a device is as follows: A basic communication score is allocated based on the device's communication bandwidth, a security factor is allocated based on the communication method, a security communication index is calculated based on the security factor and the basic communication score, and the communication capacity is calculated based on the security communication index, the communication score, and the communication resource allocation rate. The method for calculating the device's cache capacity is as follows: A base cache score is assigned based on the cache capacity of each device, and the cache capacity is calculated based on cache speed, number of cache channels, and communication resource allocation rate. The initial basic node score is calculated by assigning weights to computing power, communication power, and caching power. The node fitness index is calculated based on the resource allocation of computing power, communication power, and caching power. The basic node score is then calculated based on the node fitness index and the initial basic node score.

4. The intelligent kitchen equipment collaborative control communication method according to claim 1, characterized in that: The method for calculating the utilization rate of the aforementioned resource configuration type is as follows: Obtain the usage time and usage amount of each device's resource configuration type in historical work information, calculate the average usage ratio, and set a baseline adjustment value and add it to the average usage ratio as the utilization rate of that resource configuration type; The method for calculating the period coefficient is as follows: Obtain the usage time of each device's resource configuration type from historical work information, calculate the ratio between the cumulative usage time of each resource and the device's working time, and set a baseline adjustment value and add it to the average usage ratio as the usage cycle coefficient.

5. The intelligent kitchen equipment collaborative control communication method according to claim 1, characterized in that: The specific steps for calculating the communication quality between each device, as a node weight, are as follows: The basic communication volume is calculated by acquiring the communication duration, communication data volume, and communication frequency between devices. The basic communication quality is calculated by exponential fitting of the basic communication volume based on the number of communication interruptions and communication speed. The average of the basic communication quality between the device and all communicating devices is calculated as the communication quality of the device. The communication quality of all devices is then normalized to the maximum, and the normalized value is used as the node weight of the device.

6. The intelligent kitchen equipment collaborative control communication method according to claim 1, characterized in that: The constructed task resource decomposition model is based on natural language processing and knowledge graphs, and specifically includes: Text preprocessing structure: The raw text of the user-submitted task is transformed into structured information through word segmentation, part-of-speech tagging, and stop word removal; Named entity recognition structure: Identifies key entities in the task description, providing a data foundation for subsequent relation extraction and knowledge graph construction; Relationship extraction structure: Extract the specific relationships between entities to ensure that the constructed graph can correctly reflect the dependencies between tasks and resources; Knowledge graph node and edge structure: Elements such as tasks, resources, and time exist as nodes in the graph, and the relationships between entities are represented by edges, which are used for association reasoning between tasks and resources and decomposition of resource requirements.

7. The intelligent kitchen equipment collaborative control communication method according to claim 1, characterized in that: The method for calculating node scores based on node demand, basic node scores, node weights, and operational stability coefficients is as follows: Based on the needs for computing power, communication power, and caching power, calculate the remaining resource ratio with the remaining capacity of each resource configuration type of the device, and obtain the node demand by accumulating the remaining resource ratio between resource configuration types through weight allocation. The formula for calculating node scores is: in, Rate the nodes For node demand, Basic node scoring, For node weights, For job stability coefficient, The correction coefficient for the basic node score. This is the weighting adjustment factor. To serve as a stable base.

8. The intelligent kitchen equipment collaborative control communication method according to claim 1, characterized in that: The method for determining the communication control node based on the duration of the node score and the node score is as follows: Set time intervals, obtain the highest node score at each time interval point, and the corresponding device. Use n time intervals as the length of the time window and set the step value to n / na, where na is the step size setting. Filter out node scores whose duration is less than n / nb, where nb is the node filtering coefficient. Calculate the average node score of each device within the time window, and select the communication control node with the highest average node score within the current time window. Here, n, na, and nb are all positive integers.

Images