AI-based energy-saving management method, system, and chip for pharmaceutical warehouses based on hybrid communication

Abstract

This invention provides an AI-based energy-saving management method, system, and chip for pharmaceutical warehouses based on hybrid communication, belonging to the field of communication system technology. Specifically, it includes: determining a monitoring and analysis method for the communication links of the equipment group based on the distribution data of temperature monitoring devices in different energy-saving optimization zones within an equipment group, and considering the composition of these zones; determining the operating status of the temperature monitoring devices in the equipment group using the monitoring and analysis method; determining an energy-saving management method for the energy-saving optimization zones based on the analysis results of the AI ​​model's operating status and the monitoring and analysis method for the communication links of the equipment group; updating the energy-saving optimization zones using the energy-saving management method; and determining energy-saving optimization schemes for different zones based on the updated energy-saving optimization zones and the temperature monitoring device data within those zones, thereby improving the reliability of energy-saving management.

Description

Technical Field

[0001] This invention belongs to the field of communication system technology, and in particular relates to an AI-based energy-saving management method, system and chip for pharmaceutical warehouses based on hybrid communication. Background Technology

[0002] As a crucial node in drug distribution, pharmaceutical warehouses must strictly adhere to the requirements of the Good Supply Practice (GSP) for pharmaceutical products. Different drugs exhibit significantly different sensitivities to temperature and humidity. To achieve precise temperature control, pharmaceutical warehouses typically deploy numerous temperature and humidity sensors, refrigeration units, dehumidification equipment, etc., which constitute a warehouse temperature management system based on a hybrid communication network.

[0003] Existing warehouse temperature management systems often use fixed temperature thresholds for temperature control in pharmaceutical warehouses, but these solutions have the following technical problems: In temperature regulation, existing technologies neglect the communication strategies of temperature monitoring devices in different areas. When the communication strategies are complex, any abnormality in any one of them can lead to insufficient reliability of temperature control. Therefore, it is urgent to solve the technical problem of determining energy-saving control strategies for different areas based on the communication strategies of temperature monitoring devices in different areas, and to determine the monitoring and analysis methods for different communication strategies by utilizing the communication strategies of temperature monitoring devices in energy-optimized areas, thereby improving the reliability of temperature control.

[0004] Therefore, there is an urgent need for an AI-based energy-saving management method, system, and chip for pharmaceutical warehouses based on hybrid communication. Summary of the Invention

[0005] To achieve the objectives of this invention, the following technical solution is adopted: Specifically, this application provides an AI-based energy-saving management method for pharmaceutical warehouses based on hybrid communication, which includes: Based on the communication strategy of the temperature monitoring system, S1 divides the temperature monitoring equipment into different equipment groups. Based on the distribution of temperature monitoring equipment in different equipment groups in the region, the energy-saving optimization area in the region is determined. By utilizing the correspondence between the temperature regulation results of the temperature regulation equipment and the temperature monitoring equipment, the temperature regulation processing of the energy-saving optimization area is carried out with the goal of minimizing energy consumption. S2 determines the monitoring and analysis method for the communication link of the equipment group based on the distribution data of the temperature monitoring devices in different energy-saving optimization areas in the equipment group, and in combination with the composition of the energy-saving optimization areas in the area, and uses the monitoring and analysis method to determine the operating status of the temperature monitoring devices in the equipment group. S3 determines the energy-saving management method for the energy-saving optimization area based on the analysis and processing results of the AI ​​model's operating status and the monitoring and analysis method of the communication links of the device group; S4 uses the energy-saving management method to update the energy-saving optimization area, and determines the energy-saving optimization scheme for different areas based on the updated energy-saving optimization area and the temperature monitoring equipment data of the energy-saving optimization area.

[0006] The beneficial effects of this invention are as follows: Based on the proportion of temperature monitoring devices in different device groups in the region, the dispersion of the communication strategies of the temperature monitoring devices in the region is determined. The dispersion is then used to screen energy-saving optimization areas with lower dispersion in the region, that is, areas with lower impact from multiple types of communication strategies. This ensures the reliability of temperature control processing and avoids the technical problem of poor temperature control stability caused by the simultaneous influence of multiple types of communication strategies.

[0007] Based on the number of energy-saving optimization zones and the distribution of temperature monitoring devices in different energy-saving optimization zones, the assessment and analysis requirements for the operational stability of the communication links of the equipment group are determined. The monitoring and analysis methods for the communication links of the equipment group are then determined based on these assessment and analysis requirements. This reduces the difficulty of monitoring and analysis processing and also lays the foundation for updating and managing energy-saving optimization zones based on the stability of the communication links.

[0008] Furthermore, the temperature monitoring equipment is divided into different equipment groups, specifically including: Temperature monitoring devices that use the same communication strategy are grouped into the same device group.

[0009] Furthermore, the method for determining the energy-saving optimization area within the aforementioned region is as follows: S11 determines the proportion of temperature monitoring devices in different equipment groups in the region based on the distribution of temperature monitoring devices in different equipment groups in the region; S12 uses the proportion of temperature monitoring devices in different equipment groups to determine the correlation coefficient between the area and the monitoring devices in different equipment groups; S13 determines whether the area belongs to the energy-saving optimization area based on the correlation coefficient between the area and the monitoring equipment of different equipment groups.

[0010] Furthermore, the method for determining the energy-saving optimization scheme for the region is as follows: S41 determines the number of updated energy-saving optimization regions based on the updated energy-saving optimization region data; S42 determines the proportion of temperature monitoring devices in different equipment groups in the energy-saving optimization area based on the temperature monitoring device data of the energy-saving optimization area, and determines the monitoring matching coefficient by summing the proportions of temperature monitoring devices in different energy-saving optimization areas in the equipment groups; S43 uses the number of energy-saving optimization areas after the update process and the monitoring matching coefficients of different equipment groups to determine the energy-saving optimization scheme for the area.

[0011] In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the aforementioned AI energy-saving management method for pharmaceutical warehouses based on hybrid communication when running the computer program.

[0012] Other features and advantages will be set forth in the following description, and the objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0013] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0014] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0015] Figure 1 This is a flowchart of an AI-based energy-saving management method for pharmaceutical warehouses based on hybrid communication; Figure 2 This is a flowchart illustrating the method for determining energy-saving optimization zones within a given area. Figure 3 This is a flowchart illustrating the method for determining the monitoring and analysis of communication links within a device group. Detailed Implementation

[0016] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0017] Example 1 like Figure 1As shown, this application provides an AI-based energy-saving management method for pharmaceutical warehouses based on hybrid communication, specifically including: Based on the communication strategy of the temperature monitoring system, S1 divides the temperature monitoring equipment into different equipment groups. Based on the distribution of temperature monitoring equipment in different equipment groups in the region, the energy-saving optimization area in the region is determined. By utilizing the correspondence between the temperature regulation results of the temperature regulation equipment and the temperature monitoring equipment, the temperature regulation processing of the energy-saving optimization area is carried out with the goal of minimizing energy consumption. S2 determines the monitoring and analysis method for the communication link of the equipment group based on the distribution data of the temperature monitoring devices in different energy-saving optimization areas in the equipment group, and in combination with the composition of the energy-saving optimization areas in the area, and uses the monitoring and analysis method to determine the operating status of the temperature monitoring devices in the equipment group. S3 determines the energy-saving management method for the energy-saving optimization area based on the analysis and processing results of the AI ​​model's operating status and the monitoring and analysis method of the communication links of the device group; S4 uses the energy-saving management method to update the energy-saving optimization area, and determines the energy-saving optimization scheme for different areas based on the updated energy-saving optimization area and the temperature monitoring equipment data of the energy-saving optimization area.

[0018] Furthermore, the temperature monitoring equipment is divided into different equipment groups, specifically including: Temperature monitoring devices that use the same communication strategy are grouped into the same device group.

[0019] Furthermore, by utilizing the correlation between the temperature regulation results of the temperature regulation equipment and the temperature monitoring equipment, temperature regulation processing is carried out in the energy-saving optimization area with the goal of minimizing energy consumption. Specifically, this includes: When the area belongs to the energy-saving optimization area, the temperature change of the temperature monitoring equipment under different temperature adjustment values ​​is used to construct the correspondence between the temperature adjustment value and the temperature change value. Based on the correspondence, the temperature is adjusted under the constraint that the energy consumption is the lowest and the monitoring data of the temperature monitoring equipment in the energy-saving optimization area is within the qualified range.

[0020] If the area is not an energy-saving optimization area, then based on the correspondence, the temperature is adjusted with the constraint that the monitoring data of the temperature monitoring equipment in the energy-saving optimization area is within the target temperature range, wherein the target temperature range is within the qualified range.

[0021] It should be noted that the temperature monitoring device will exhibit corresponding changes under different operating power and for different durations. Based on these changes, the operating power requirement within a set duration can be obtained when the energy-saving optimization zone is adjusted to the target temperature, and temperature adjustment processing can be performed based on the operating power requirement.

[0022] Furthermore, a neural network-based temperature control model can be constructed based on the temperature change of the temperature monitoring device under different temperature adjustment values. This model establishes the relationship between the temperature adjustment value and the temperature change value. Using the current monitoring temperature and temperature adjustment duration as inputs, the model automatically determines the temperature adjustment value under the current adjustment requirements.

[0023] Specifically, such as Figure 2 As shown, the method for determining the energy-saving optimization area in the region is as follows: In this embodiment, based on the proportion of temperature monitoring devices in different device groups in the region, the dispersion of the communication strategies of the temperature monitoring devices in the region is determined, and the dispersion is used to screen energy-saving optimization regions with lower dispersion in the region. That is, regions that are less affected by the abnormality of multiple types of communication strategies are screened, which ensures the reliability of temperature control processing and avoids the technical problem of poor temperature control stability caused by the simultaneous influence of multiple types of communication strategies.

[0024] Step S11: Determine the percentage of temperature monitoring devices in different equipment groups within the region based on the distribution of temperature monitoring devices in those groups.

[0025] The percentage of temperature monitoring devices refers to the proportion of temperature monitoring devices in a certain equipment group to the total number of temperature monitoring devices in the area. The calculation formula is: Percentage of a certain equipment group = Number of temperature monitoring devices in the equipment group ÷ Total number of temperature monitoring devices in the area × 100%.

[0026] The reason for setting up this step is that by quantifying the distribution of different device groups in the region, we can objectively reflect the status and role of each type of device group in the region, providing basic data support for subsequent analysis of the dispersion of communication strategies, and avoiding the subjectivity and uncertainty of relying on experience-based judgment.

[0027] By using the intuitive and quantifiable indicator of quantity proportion, we can quickly identify the dominant position and balance of various equipment groups in the region. When the quantity proportion of a certain equipment group is high, it indicates that the region mainly relies on that equipment group for temperature monitoring and the communication strategy is relatively simple. Conversely, it indicates that the region uses a combination of multiple communication strategies, which lays a solid foundation for judging the simplicity of the communication strategy.

[0028] Suppose a cold storage area in a pharmaceutical warehouse contains two device groups: Group A, which uses ZigBee communication, and Group B, which uses LoRa communication. Statistical analysis reveals a total of several temperature monitoring devices in the area, with Group A containing a number of devices and Group B containing a number of devices. Using the formula for calculating the proportion of devices in each group, we can determine their respective proportions. A higher proportion for Group A indicates that the cold storage area primarily relies on devices using ZigBee communication, suggesting a relatively simple communication strategy and high reliability of temperature control. Conversely, a more similar proportion for both groups suggests a mixed use of multiple communication strategies, potentially leading to the combined impact of anomalies in these strategies and a possible compromise in temperature control stability.

[0029] Step S12: Determine the correlation coefficient between the area and the monitoring equipment of different equipment groups by using the proportion of temperature monitoring equipment in different equipment groups.

[0030] The correlation coefficient of monitoring equipment refers to the degree of correlation between a region and a specific group of equipment. This coefficient is directly represented by the proportion of the number of equipment groups, that is, the correlation coefficient of monitoring equipment = the proportion of the number of equipment groups. The value of the correlation coefficient ranges from 0% to 100%, and the larger the value, the higher the degree of correlation.

[0031] The reason for setting up this step is to transform the quantity proportion into a correlation indicator with clear physical meaning, so that the comparison between different regions has a unified standard and basis, and at the same time provides operable parameters for subsequent threshold judgment and classification processing. Its significance is that the correlation coefficient of monitoring equipment can intuitively and accurately reflect the degree of dependence of a region on a certain equipment group. The higher the correlation coefficient, the more the temperature monitoring of the region depends on the equipment group, the more important the status of the equipment group in the region, and the greater its impact on the temperature control of the region. Thus, it provides an important quantitative basis for subsequent judgment of the singularity of communication strategy and the reliability of temperature control.

[0032] Continuing with the previous example, based on the calculated proportions of equipment group A and equipment group B, we can directly obtain the correlation coefficients between the monitoring equipment in the cold storage area and equipment group A, as well as the correlation coefficients between the monitoring equipment in the cold storage area and equipment group B. When the correlation coefficient of the monitoring equipment in equipment group A is high, it indicates that the cold storage area is highly dependent on equipment group A. This area mainly consists of equipment using the ZigBee communication strategy, and temperature monitoring is mainly achieved through equipment group A. When the correlation coefficients of the monitoring equipment in the two equipment groups are relatively close and not very high, it indicates that the cold storage area's dependence on the two equipment groups is relatively balanced. This area involves the mixed use of multiple communication strategies, and temperature monitoring is shared by both equipment groups, which may be affected by the combined effects of abnormalities in the two communication strategies.

[0033] Step S13: Determine whether the area belongs to the energy-saving optimization area based on the correlation coefficient between the area and the monitoring equipment of different equipment groups.

[0034] Energy-saving optimization areas refer to regions with low dispersion in communication strategy distribution and low susceptibility to anomalies from various types of communication strategies. These areas are suitable for energy-saving optimization and can ensure the reliability of temperature control. The determination method is as follows: if there is a group of devices in the area with a correlation coefficient greater than a preset correlation coefficient threshold, then the area is determined to be an energy-saving optimization area; otherwise, it is not. The preset correlation coefficient threshold is set based on the actual application scenario and the diverse requirements of communication strategies, taking into account factors such as the size of the pharmaceutical warehouse, the number of devices, the communication environment, and the drug storage requirements.

[0035] The reason for setting this step is that by using a threshold to make judgments, areas with a single communication strategy can be objectively and consistently screened out, avoiding the subjectivity and inconsistency of manual judgment. At the same time, the threshold setting has a certain degree of flexibility, which can adapt to the needs of different application scenarios. Its significance lies in accurately identifying areas suitable for energy-saving optimization. These areas, due to their single communication strategy, are less likely to be affected by anomalies from multiple communication strategies. During energy-saving processing, the reliability and stability of temperature control can be guaranteed, avoiding temperature control anomalies caused by communication strategy conflicts, thus laying a solid foundation for subsequent energy-saving management.

[0036] Continuing the previous example, based on the preset correlation coefficient threshold, the correlation coefficients of the monitoring devices in device group A and device group B are compared with this threshold. When it is found that the correlation coefficient of the monitoring devices in a certain device group is greater than the preset correlation coefficient threshold, it indicates that the temperature monitoring devices in this cold storage area are mainly composed of devices with a single communication strategy. The communication strategy is relatively simple, the communication reliability is strong, and the possibility of being affected by anomalies in multiple communication strategies is low. Therefore, it is determined that this cold storage area belongs to the energy-saving optimization area, and energy-saving optimization can be carried out in this area. When it is found that the correlation coefficients of the monitoring devices in all device groups are not greater than the preset correlation coefficient threshold, it indicates that multiple communication strategies are used in combination in this cold storage area. It may be affected by the combined impact of anomalies in multiple communication strategies, and the stability of temperature control is poor. Therefore, it is determined that this cold storage area does not belong to the energy-saving optimization area and is not suitable for energy-saving optimization.

[0037] It is understandable that if there is a group of devices in the area whose correlation coefficient of monitoring devices is greater than the preset correlation coefficient threshold, then the temperature monitoring devices are mainly composed of temperature range devices with a certain communication strategy. Therefore, they are not affected by the stability of multiple communication strategies at the same time, and the communication reliability is relatively strong. Thus, the area is determined to be an energy-saving optimization area.

[0038] A pharmaceutical warehouse has 10 areas, designated as Area 1 to Area 10. There are three device groups within the warehouse: Group A (using ZigBee communication, 80 devices), Group B (using LoRa communication, 60 devices), and Group C (using NB-IoT communication, 40 devices).

[0039] For Area 1 (cold storage area), there are a total of 50 temperature monitoring devices, of which device group A contains 35 devices, device group B contains 15 devices, and device group C contains 0 devices. The proportion of devices in device group A is 35 ÷ 50 × 100% = 70%, and the correlation coefficient of the monitoring devices is 70%; the proportion of devices in device group B is 15 ÷ 50 × 100% = 30%, and the correlation coefficient of the monitoring devices is 30%; the proportion of devices in device group C is 0%, and the correlation coefficient of the monitoring devices is 0%. The preset correlation coefficient threshold is set to 60%. Since the correlation coefficient of monitoring devices in device group A (70%) is greater than 60%, Area 1 is determined to be an energy-saving optimization area.

[0040] This embodiment achieves intelligent identification of energy-saving optimization areas through three steps: S11, S12, and S13. By quantitative analysis of the proportion of areas and threshold judgment of correlation coefficients, it can accurately screen out areas with simple communication strategies and high reliability. Its core value lies in three aspects: First, quantitative analysis avoids the subjectivity of human judgment, improving the accuracy and consistency of identification results; second, the correlation coefficient threshold ensures the uniformity of screening standards, making the identification results of different areas comparable; and third, it lays the foundation for subsequent energy-saving management while ensuring the reliability of temperature control, avoiding abnormal temperature control problems that may result from energy-saving treatment in unsuitable areas.

[0041] Specifically, such as Figure 3 As shown, the method for determining the monitoring and analysis method of the communication links of the device group is as follows: In this embodiment, based on the number of energy-saving optimization zones and the distribution of temperature monitoring devices of the equipment group in different energy-saving optimization zones, the assessment and analysis requirements for the operational stability of the communication links of the equipment group are determined. The monitoring and analysis methods for the communication links of the equipment group are determined using the assessment and analysis requirements. This reduces the difficulty of monitoring and analysis processing and also lays the foundation for updating and managing energy-saving optimization zones based on the stability of the communication links.

[0042] S21: Using the distribution data of temperature monitoring devices in different energy-saving optimization zones within the equipment group, determine the correlation coefficient between the equipment group and the monitoring devices in different energy-saving optimization zones, and use the correlation coefficient of the monitoring devices to determine the associated optimization zones within the energy-saving optimization zones.

[0043] The correlation coefficient of monitoring equipment refers to the proportion of temperature monitoring equipment in a specific energy-saving optimization zone to the total number of equipment in the equipment group. The value ranges from 0% to 100%, with a higher value indicating a denser distribution of equipment within that energy-saving optimization zone. The correlation optimization zone refers to the energy-saving optimization zone where the correlation coefficient of monitoring equipment is the highest among all equipment groups; that is, the zone corresponding to the maximum value of the correlation coefficient of monitoring equipment in each equipment group within a certain energy-saving optimization zone. This step quantifies the degree of correlation between equipment groups and energy-saving optimization zones by calculating the correlation coefficient, providing a data foundation for subsequent identification of correlation optimization zones. Its significance lies in transforming the dispersion of equipment distribution into a measurable correlation indicator, thus providing an objective basis for determining monitoring and analysis methods.

[0044] By calculating the correlation coefficients of monitoring equipment, the distribution density of equipment in different energy-saving optimization zones can be accurately reflected. Identifying the correlation optimization zones determines the core monitoring areas for each equipment group, providing a basis for selecting subsequent monitoring and analysis methods. The significance of this approach lies in enabling the identification of key monitoring and analysis areas, ensuring that monitoring resources are preferentially allocated to densely populated equipment areas.

[0045] Example: Suppose a pharmaceutical warehouse has several areas, some of which are energy-saving optimization areas. A certain equipment group has a different number of temperature monitoring devices distributed in each energy-saving optimization area. Calculate the proportion of the number of devices in each energy-saving optimization area to the total number of devices in the equipment group, and obtain the correlation coefficient of the monitoring devices. By comparing the correlation coefficients of the monitoring devices of all equipment groups in each energy-saving optimization area, identify the area with the highest correlation coefficient for that equipment group, and determine it as the correlation optimization area for that equipment group.

[0046] It is understandable that the correlation optimization region is the energy-saving optimization region where the correlation coefficient of the monitored equipment is the largest among all equipment groups. This setting indicates that the correlation optimization region is the energy-saving optimization region where the equipment distribution of each equipment group is most concentrated. Identifying this region can clarify the core monitoring area of ​​each equipment group, and its significance lies in providing a regional-dimensional decision-making basis for the refinement of monitoring and analysis methods.

[0047] S22: Utilize the composition of energy-saving optimization areas in the region to determine the proportion of energy-saving optimization areas in the region, and use the proportion of energy-saving optimization areas in the region as the energy-saving optimization area ratio.

[0048] The energy-saving optimization area ratio refers to the ratio of the number of energy-saving optimization areas to the total number of areas in a region. The value ranges from 0 to 1, with a higher value indicating a higher overall level of energy-saving optimization coverage. This step quantifies the overall level of energy-saving optimization coverage by statistically analyzing the number of energy-saving optimization areas, providing a macro-level basis for determining subsequent monitoring and analysis methods. Its significance lies in transforming the overall coverage of energy-saving optimization into a measurable proportional indicator, ensuring that the selection of monitoring and analysis methods aligns with the overall energy-saving plan.

[0049] The proportion of energy-saving optimization areas reflects the overall coverage of energy-saving optimization. When this proportion is high, it indicates that most areas have been included in the energy-saving optimization scope. In this case, a full-coverage monitoring and analysis method should be adopted to ensure the overall stability of the system. When the proportion is moderate, differentiated monitoring and analysis methods can be adopted according to the correlation of equipment groups to reduce the workload of monitoring and analysis. The significance of this setting is that it achieves a match between the monitoring and analysis methods and the overall energy-saving coverage, ensuring the rationality of resource allocation.

[0050] Assuming a pharmaceutical warehouse comprises several areas, some of which are designated as energy-saving optimization areas, the proportion of these energy-saving optimization areas to the total number of areas is calculated. This percentage reflects the overall coverage of energy-saving optimization within the pharmaceutical warehouse, providing a basis for selecting subsequent monitoring and analysis methods.

[0051] S23: Based on the correlation coefficient between the equipment group and the monitoring equipment in different energy-saving optimization areas, the correlation optimization areas, and the proportion of energy-saving optimization areas, determine the monitoring and analysis method for the communication link of the equipment group.

[0052] It is understood that the correlation optimization region is the energy-saving optimization region where the correlation coefficient of the monitoring equipment is the largest among all equipment groups.

[0053] The communication link monitoring and analysis method refers to the approach of monitoring and analyzing the stability of the communication links of temperature monitoring devices in a group of devices. This includes different methods such as monitoring and analysis in all areas, monitoring and analysis in energy-saving optimization areas, and monitoring and analysis in areas where the correlation coefficient of the monitored devices is above the target correlation coefficient. This step, by comprehensively considering the correlation coefficient of the monitored devices, the proportion of correlation optimization areas, and energy-saving optimization areas, achieves intelligent determination of the monitoring and analysis method. Its significance lies in reducing the workload of monitoring and analysis while ensuring the effectiveness of communication link monitoring and analysis.

[0054] By identifying the correlation coefficients and optimized areas of monitoring equipment, the core monitoring areas of each equipment group can be determined; by evaluating the proportion of energy-saving optimized areas, the overall coverage of energy-saving optimization can be clarified; and by combining these factors, differentiated monitoring and analysis methods can be developed to optimize the allocation of monitoring and analysis resources. The significance of this approach is that it minimizes the workload of monitoring and analysis processing while ensuring the effectiveness of the analysis.

[0055] Suppose that the associated optimization area of ​​a certain device group is a certain energy-saving optimization area, and the proportion of energy-saving optimization areas is relatively high. Then, according to the subsequent judgment logic, the monitoring and analysis method of the communication link of this device group is determined to be to carry out monitoring and analysis processing in all areas.

[0056] Furthermore, if the proportion of energy-saving optimization areas is greater than the preset proportion threshold, then the monitoring and analysis method for the communication links of all equipment groups is to monitor and analyze the stability of the communication links of the temperature monitoring equipment in all areas.

[0057] The preset proportion threshold is a critical value for determining whether the energy-saving optimization coverage has reached a high level. When the proportion of the energy-saving optimization area is greater than this threshold, it indicates that most areas have been included in the energy-saving optimization scope. At this time, a comprehensive communication link monitoring and analysis should be performed on all equipment groups. The significance of this step is to ensure the overall stability of the system and the continuity of energy-saving effects through full-coverage monitoring and analysis in high-energy-saving coverage scenarios.

[0058] When the proportion of energy-saving optimized areas is high, it indicates that energy-saving optimization has covered most areas. At this point, the mutual influence between different device groups is significant, and instability in the communication link of any device group may affect the overall energy-saving effect. Therefore, comprehensive communication link monitoring and analysis of all device groups is required to identify potential communication link stability issues and ensure the continuity of energy-saving effects and the overall stability of the system. The significance of this setting is to prioritize the overall stability of the system in high-energy-saving coverage scenarios, avoiding a decrease in energy-saving effects due to local communication link problems.

[0059] Assuming that the proportion of energy-saving optimization areas is greater than the preset proportion threshold, the monitoring and analysis method for the communication links of all equipment groups is to monitor and analyze the stability of the communication links of the temperature monitoring equipment in all areas.

[0060] Additionally, it should be noted that if the proportion of the energy-saving optimization area is not greater than the preset proportion threshold, the following content is also included: Scenario 1: If there is no associated optimization area for the equipment group, then the monitoring and analysis method for the communication link of the equipment group is to only monitor and analyze the stability of the communication link of the temperature monitoring equipment in the equipment group within the energy-saving optimization area.

[0061] This situation applies when the correlation coefficients of monitoring devices in all energy-saving optimization zones for certain equipment groups are not at their maximum values, meaning there are no associated optimization zones. In this case, the correlation between this equipment group and the energy-saving optimization zones is low, so monitoring and analysis only need to be performed within the energy-saving optimization zones to reduce the workload of monitoring and analysis. The significance of this step is that for equipment groups with low correlation, targeted monitoring and analysis methods are adopted, achieving optimal resource allocation.

[0062] When a device group lacks associated optimization zones, it indicates that the device density of this group is not the highest across all energy-saving optimization zones, meaning the correlation between this group and each energy-saving optimization zone is relatively low. In this case, monitoring and analysis only need to be performed within the energy-saving optimization zones, which can cover the main monitoring needs of this device group while avoiding unnecessary monitoring and analysis work. The significance of this setup lies in achieving precise control over the workload of monitoring and analysis, thereby improving resource utilization efficiency.

[0063] Assuming that the correlation coefficients of monitoring devices in a certain equipment group are not the maximum values ​​of those in other equipment groups across all energy-saving optimization zones, then this equipment group does not have a correlation optimization zone. In this case, the monitoring and analysis method for determining the communication links of this equipment group only requires monitoring and analyzing the stability of the communication links of the temperature monitoring devices within the energy-saving optimization zones.

[0064] Scenario 2: If there are associated optimization areas in the device group, and if the number of associated optimization areas in the device group is greater than the preset threshold for the number of associated areas, then the monitoring and analysis method for the communication link of the device group is to monitor and analyze the stability of the communication link of the temperature monitoring device in all areas.

[0065] The preset threshold for the number of associated regions is a critical value used to determine whether the correlation between a device group and an energy-saving optimization region is high. When the number of associated optimization regions exceeds this threshold, it indicates that the device group has a high device distribution density in multiple energy-saving optimization regions. In this case, a comprehensive communication link monitoring and analysis should be performed on the device group. The significance of this step is to adopt a full-coverage monitoring and analysis method for device groups with a high degree of correlation, thereby ensuring the stability of their communication links.

[0066] When the number of associated optimization areas for a device group exceeds a preset threshold, it indicates that the device group has a high device distribution density across multiple energy-saving optimization areas, meaning the device group is highly correlated with these areas. In this case, monitoring and analysis only within the energy-saving optimization areas may not fully cover the communication link stability issues of the device group. Therefore, monitoring and analysis of all areas are necessary to ensure timely detection and resolution of communication link stability problems. This setting prioritizes comprehensive communication link monitoring and analysis for highly correlated device groups, avoiding omissions due to insufficient monitoring and analysis scope.

[0067] If the number of associated optimization areas of a certain device group is greater than the preset threshold for the number of associated areas, then the monitoring and analysis method for the communication link of the device group is to monitor and analyze the stability of the communication link of the temperature monitoring device in all areas.

[0068] Scenario 3: If the number of associated optimization areas of the equipment group is not greater than the preset threshold for the number of associated areas, the comprehensive association value of the equipment group is determined based on the association coefficient between the equipment group and the monitoring equipment in different energy-saving optimization areas and the proportion of the number of associated optimization areas of the equipment group in the energy-saving optimization areas. It is then determined whether the comprehensive association value of the equipment group is greater than the preset association threshold. If so, the monitoring and analysis method for the communication link of the equipment group is to monitor and analyze the stability of the communication link of the temperature monitoring equipment of the equipment group in all areas. If not, the monitoring and analysis method for the communication link of the equipment group is to monitor and analyze the stability of the communication link of the temperature monitoring equipment of the equipment group in areas where the association coefficient of the monitoring equipment is greater than the target association coefficient.

[0069] The comprehensive correlation value refers to a comprehensive score calculated based on the correlation coefficients between equipment groups and monitoring equipment in different energy-saving optimization areas, as well as the proportion of associated optimization areas. It is used to assess the overall correlation between equipment groups and energy-saving optimization areas. The preset correlation threshold is a critical value used to determine whether the comprehensive correlation of equipment groups has reached a high level. The target correlation coefficient is the lower limit for the correlation coefficients of monitoring equipment used to determine whether monitoring and analysis are necessary. This step, by comprehensively evaluating the correlation between equipment groups and energy-saving optimization areas, achieves a refined determination of the monitoring and analysis methods. Its significance lies in the fact that for equipment groups with moderate correlation, differentiated monitoring and analysis methods are adopted based on the comprehensive correlation value, achieving optimal resource allocation.

[0070] When the number of associated optimization areas for a device group is no greater than the preset threshold for the number of associated areas, it indicates that the association degree of the device group is moderate, and further evaluation of its comprehensive association value is needed. If the comprehensive association value is greater than the preset threshold, it indicates that the overall association degree between the device group and the energy-saving optimization area is high, and a full-coverage monitoring and analysis method should be adopted; if the comprehensive association value is no greater than the preset threshold, it indicates that the overall association degree between the device group and the energy-saving optimization area is average, and a targeted monitoring and analysis method can be adopted, monitoring and analysis only in areas where the association coefficient of the monitored devices is high. The significance of this setting is that it enables fine-tuning of the monitoring and analysis method, ensuring that resources can be rationally allocated according to actual needs.

[0071] Assuming the number of associated optimization areas for a certain device group is no greater than a preset threshold for the number of associated areas, the comprehensive association value of the device group is calculated, and it is determined whether the comprehensive association value is greater than the preset association threshold. If it is greater than the preset association threshold, the monitoring and analysis method for the communication links of the device group is determined to be to monitor and analyze the stability of the communication links of the temperature monitoring devices in all areas; if it is not greater than the preset association threshold, the monitoring and analysis method for the communication links of the device group is determined to be to monitor and analyze the stability of the communication links of the temperature monitoring devices in areas where the association coefficient of the monitored devices is above the target association coefficient.

[0072] This embodiment achieves intelligent determination of the monitoring and analysis method for the communication links of the device group through step S2. Its core value is reflected in three aspects: First, by calculating the correlation coefficient of the monitored devices, it realizes a quantitative assessment of the correlation between the device group and the energy-saving optimization area, thereby providing data support for the selection of the monitoring and analysis method; Second, by assessing the proportion of the energy-saving optimization area, it realizes overall control of the coverage of energy-saving optimization, thereby ensuring the matching of the monitoring and analysis method with the overall energy-saving plan; Third, through a multi-level judgment mechanism of preset proportion threshold, preset correlation area number threshold, preset correlation threshold and target correlation coefficient, it realizes the refined formulation of the monitoring and analysis method, thereby reducing the workload of monitoring and analysis processing while ensuring the monitoring and analysis effect.

[0073] This embodiment provides a communication link monitoring and analysis method for determining the AI ​​energy-saving management method for pharmaceutical warehouses. It is applied to the energy-saving management system for pharmaceutical warehouses, which includes 3 equipment groups and 10 areas. The comprehensive correlation value calculation formula is the sum of 0.4 times the proportion of the number of correlation optimization areas and 0.6 times the average correlation coefficient of the monitoring equipment.

[0074] First, step S21 is executed to determine the correlation optimization area for each equipment group based on the equipment distribution in each area. For area 1 (cold storage area), there are a total of 50 temperature monitoring devices, of which equipment group A contains 35 devices, equipment group B contains 15 devices, and equipment group C contains 0 devices. Equipment group A accounts for 70% of the total number of devices and has a correlation coefficient of 70%; equipment group B accounts for 30% of the total number of devices and has a correlation coefficient of 30%; equipment group C accounts for 0% of the total number of devices and has a correlation coefficient of 0%. Since the correlation coefficient of equipment group A (70%) is greater than the preset correlation coefficient threshold of 60%, area 1 is determined to be an energy-saving optimization area. Furthermore, the correlation coefficient of equipment group A (70%) is the maximum value in this area. Therefore, area 1 is designated as the correlation optimization area for equipment group A.

[0075] According to statistics, the energy-saving optimization areas are areas 1, 2, 3, 4, 5, 7, 8, 9, and 10, a total of 9 areas, and the proportion of energy-saving optimization areas is 9 ÷ 10 = 90%.

[0076] Next, step S23 is executed to determine whether the proportion of the energy-saving optimization area is greater than the preset proportion threshold of 70%. Since 90% > 70%, the condition is met. Therefore, it is determined that the monitoring and analysis method for the communication links of all equipment groups A, B, and C is to monitor and analyze the stability of the communication links of the temperature monitoring equipment of the equipment groups in all areas.

[0077] Additionally, it should be noted that if the proportion of the energy-saving optimization area is not greater than the preset proportion threshold, the following content is also included: If the preset ratio threshold is adjusted to 90%, then the energy-saving optimization area ratio of 90% is not greater than 90%, the condition is not met, and the subsequent situation is judged.

[0078] Example of Case 1: Assume that in this scenario, the correlation coefficients of the monitoring devices in device group C are not at their maximum values ​​in all energy-saving optimization zones, then device group C does not have any correlation optimization zones. Based on the logic of Case 1, the monitoring and analysis method for the communication links of device group C is to only monitor and analyze the stability of the communication links of the temperature monitoring devices in device group C within the energy-saving optimization zones.

[0079] Example of Scenario 2: Assume that in this scenario, the correlation coefficients of the monitoring devices in energy-saving optimization zones 1, 4, and 8 of device group A are all at their maximum values, and the number of correlation optimization zones is 3. Since 3 > the preset threshold of the number of correlation zones 2, according to the logic of Scenario 2, the monitoring and analysis method for the communication link of device group A is determined to be to monitor and analyze the stability of the communication link of the temperature monitoring devices of device group A in all zones.

[0080] Example of Scenario 3: Assume that in this scenario, the correlation coefficient of the monitoring devices in energy-saving optimization zones 2 and 5 of device group B is at its maximum, and the number of associated optimization zones is 2, which is equal to the preset threshold of 2 for the number of associated zones. Calculate the comprehensive correlation value: the proportion of associated optimization zones is 2 ÷ 5 = 40% (assuming device group B has 2 associated optimization zones out of 5 energy-saving optimization zones), the average monitoring device correlation coefficient is (70% + 64% + correlation coefficients of other zones) ÷ 5 = 58%, and the comprehensive correlation value is 40% × 0.4 + 58% × 0.6 = 50.8%. Since the comprehensive correlation value of 50.8% is greater than the preset correlation threshold of 50%, according to the logic of Scenario 3, the monitoring and analysis method for the communication link of device group B is determined to be to monitor and analyze the stability of the communication link of the temperature monitoring devices of device group B in all associated optimization zones.

[0081] The significance of this step lies in the fact that it enables the refined formulation of monitoring and analysis methods through a multi-level judgment mechanism. Its core value is reflected in three aspects: First, through full-coverage monitoring, it ensures the stability of the communication link between the energy-saving optimization area and the equipment group; second, through differentiated monitoring and analysis methods, it reduces the workload of monitoring and analysis processing; and third, through intelligent judgment logic, it achieves the optimization of resource allocation.

[0082] Furthermore, the method for determining the energy-saving management method of the energy-saving optimization area is as follows: In this embodiment, based on the monitoring and analysis method of the communication links of different equipment groups in the energy-saving optimization area and the correlation coefficient of the monitoring equipment between different equipment groups, the reliability of the monitoring and analysis processing of the communication links of different temperature monitoring devices in the energy-saving optimization area is determined, and the energy-saving management method of the energy-saving optimization area is determined by using the reliability. While ensuring the energy-saving effect, the reliability of temperature control processing is further improved.

[0083] S31: Based on the analysis and processing results of the operating status, identify the temperature monitoring devices in the device group that do not meet the requirements for offline times, and designate them as stable deviation devices. Use the stable deviation devices and AI models to determine the deviation weight values ​​in the device group.

[0084] Stable deviation devices refer to temperature monitoring devices that experience offline times, offline frequency, or offline duration exceeding preset requirements during operation, indicating poor communication link stability. Deviation weight values ​​are stability assessment indicators for device groups calculated by an AI model based on characteristics such as the number of stable deviation devices, offline frequency, and offline duration. The value ranges from 0 to 1, with lower values ​​indicating poorer stability of the device group. The AI ​​model is a predictive model built using machine learning algorithms, capable of learning the correlation between device stability and various characteristics based on historical data, thereby quantitatively assessing the stability of the device group. This step, by identifying stable deviation devices and calculating deviation weight values, quantifies the operational stability of the device group, providing foundational data for determining subsequent energy-saving management methods. Its significance lies in transforming the operational stability of the device group into a measurable indicator, giving objective evidence to the determination of energy-saving management methods.

[0085] By identifying devices with stability deviations, the system can accurately reflect the situation of devices with poor communication link stability within a device group. Calculating deviation weight values ​​using an AI model allows for a comprehensive assessment of the device group's stability, taking into account multiple stability-influencing factors. The quantified results of the deviation weight values ​​provide a basis for determining subsequent energy-saving management methods. The significance of this approach lies in achieving an objective assessment of device group stability, avoiding the limitations of subjective judgment, and improving the scientific rigor of energy-saving management method selection.

[0086] Suppose a group of devices contains several temperature monitoring devices. Through analysis of their operational status, it is found that several devices have exceeded preset requirements for the number of offline occurrences, offline frequency, and offline duration. Statistically, several devices exhibit at least one of these non-compliance issues; therefore, these devices are classified as stable deviation devices. The offline occurrences, offline frequency, and offline duration of these stable deviation devices are input into an AI model, which calculates the deviation weight value for the entire device group.

[0087] Understandably, determining the deviation weight value in a device group using stable deviation devices and an AI model involves: first, collecting characteristic data such as the number of times, frequency, and duration of offline events of stable deviation devices; second, inputting this characteristic data into the AI ​​model, which then outputs the deviation weight value through its prediction function; and finally, evaluating the stability level of the device group based on the magnitude of the deviation weight value. A smaller deviation weight value indicates a worse stability of the device group, while a larger deviation weight value indicates a better stability of the device group.

[0088] S32: Based on the monitoring and analysis method of the communication links of equipment groups in the energy-saving optimization area, determine the analysis area range of different equipment groups in the energy-saving optimization area.

[0089] The analysis area refers to the geographical area covered by the equipment group during communication link monitoring and analysis. This includes all areas, energy-saving optimization areas, and areas where the correlation coefficient of monitored equipment is above the target correlation coefficient. This step, by determining the analysis area for each equipment group, clarifies the monitoring and analysis coverage of each equipment group within the energy-saving optimization area. This provides a regional-level decision-making basis for determining subsequent energy-saving management methods. Its significance lies in transforming the monitoring and analysis coverage into a describable geographical area, making the determination of energy-saving management methods more precise.

[0090] By defining the analysis area for each equipment group, it becomes clear which equipment groups are monitored and analyzed in all areas, which are monitored and analyzed only in energy-optimized areas, and which are monitored and analyzed only in areas with high correlation coefficients between monitored devices. This differentiated analysis area reflects the importance and reliability level of each equipment group, providing an important reference for determining subsequent energy-saving management methods. The significance of this setup lies in achieving a quantitative assessment of monitoring and analysis coverage, making the determination of energy-saving management methods more accurate and scientific.

[0091] Assuming that, based on the judgment results of step S2, the analysis area of ​​some equipment groups is all areas, the analysis area of ​​some equipment groups is part of the energy-saving optimization area, and the analysis area of ​​some equipment groups is the area where the correlation coefficient of the monitoring equipment is above the target correlation coefficient.

[0092] S33: Determine the energy management method for the energy-saving optimization area based on the deviation weight values ​​of different equipment groups in the energy-saving optimization area and the analysis area range.

[0093] Energy-saving management methods refer to decision-making methods regarding whether to continue energy-saving treatment in energy-optimized areas, including two scenarios: energy-saving treatment cannot continue and energy-saving treatment continues. "Energy-saving treatment cannot continue" means that due to poor operational stability of the equipment group or insufficient monitoring and analysis coverage, energy-saving treatment in the energy-optimized area is suspended, prioritizing the reliability of temperature control. "Energy-saving treatment continues" means that, provided the operational stability of the equipment group and sufficient monitoring and analysis coverage are ensured, the energy-saving treatment strategy for the energy-optimized area continues. This step, by comprehensively considering the deviation weight values ​​of the equipment group and the scope of the analysis area, achieves intelligent determination of the energy-saving management method. Its significance lies in further improving the reliability of temperature control treatment while ensuring energy-saving effects.

[0094] By comprehensively considering the deviation weight values ​​of equipment groups, equipment groups with poor operational stability can be identified; by analyzing the assessment of the area scope, situations with insufficient monitoring and analysis coverage can be identified; combining these two factors, the overall reliability of the energy-saving optimization area can be judged, thereby determining whether energy-saving treatment should continue. The significance of this setup lies in achieving a balance between energy-saving effect and temperature control reliability, avoiding temperature control risks caused by unilaterally pursuing energy-saving effects.

[0095] Assuming there are several equipment groups in the energy-saving optimization area, each equipment group has a corresponding deviation weight value and analysis area range, the energy-saving management method for this energy-saving optimization area is determined based on the subsequent judgment logic.

[0096] It is understandable that, based on the deviation weight values ​​of different equipment groups within the energy-saving optimization area and the analysis area range, the energy-saving management method for the energy-saving optimization area is determined, specifically including: S331: Based on the analysis area range of different equipment groups in the energy-saving optimization area, determine whether there is an equipment group in the energy-saving optimization area that is monitored and analyzed in all areas. If yes, proceed to step S332. If no, determine that if there is any equipment group in the energy-saving optimization area with a deviation weight value greater than the preset deviation weight threshold, then determine that the energy-saving management method in the energy-saving optimization area cannot continue to carry out energy-saving processing.

[0097] The preset deviation weight threshold is a critical value used to determine whether the stability of a group of devices has reached a low level. This step first determines whether there are any groups of devices monitored and analyzed in all areas; these groups have high reliability and importance. If no such groups exist, and any group has a deviation weight value greater than the preset deviation weight threshold, it indicates that there are unstable groups of devices in the energy-saving optimization area, and therefore, energy-saving processing cannot continue. The significance of this step is to quickly identify energy-saving optimization areas with stability risks, avoiding temperature control problems caused by energy-saving processing.

[0098] When no equipment group is monitored and analyzed across all areas, it indicates the absence of highly reliable core equipment groups within the energy-saving optimization area. If, in this case, less stable equipment groups also exist, the overall reliability of the energy-saving optimization area is low, and continuing energy-saving efforts could lead to temperature control risks. Therefore, in this situation, it is determined that energy-saving efforts cannot continue, and priority is given to ensuring the reliability of temperature control. The significance of this setting lies in achieving a balance between energy-saving effects and temperature control reliability, avoiding temperature control risks caused by unilaterally pursuing energy-saving effects.

[0099] If there is no equipment group in the energy-saving optimization area that is monitored and analyzed in all areas, and there is a equipment group whose deviation weight value is greater than the preset deviation weight threshold, then the energy-saving management method for this energy-saving optimization area is determined to be unable to continue energy-saving processing.

[0100] S332: The equipment groups that are monitored and analyzed in all areas are designated as reliable analysis equipment groups. It is determined whether the proportion of reliable analysis equipment groups in the equipment groups in the energy-saving optimization area is greater than the preset reliable analysis group proportion threshold. If so, the energy-saving management method in the energy-saving optimization area is determined to be unable to continue energy-saving processing only when there are a target number of equipment groups with deviation weight values ​​greater than the preset deviation weight threshold. Otherwise, proceed to step S333.

[0101] A reliable analysis equipment group refers to the equipment group that performs monitoring and analysis in all areas. This type of equipment group has high reliability and importance. The preset reliable analysis group percentage threshold is a critical value for determining whether the percentage of reliable analysis equipment groups has reached a high level. The target number is a critical number for determining whether there are a large number of equipment groups with poor stability. This step assesses the overall reliability level of the energy-saving optimization area by judging the percentage of reliable analysis equipment groups, and then, combined with the determination of deviation weight values, determines whether to continue energy-saving treatment. The significance of this step lies in enabling the refined formulation of energy-saving management methods, ensuring that resources can be rationally allocated according to actual needs.

[0102] When the proportion of reliable analysis equipment groups exceeds the preset threshold, it indicates that the overall reliability of the energy-saving optimization area is high, and the stability requirements can be appropriately relaxed. However, if there are more than a target number of equipment groups with deviation weight values ​​exceeding the preset deviation weight threshold, it indicates that there are still a certain number of equipment groups with poor stability, and therefore, caution is required. In this case, only when there are more than a target number of equipment groups with poor stability will it be determined that energy-saving treatment cannot continue, in order to avoid temperature control risks. The significance of this setting lies in achieving a balance between reliability assessment and risk management, ensuring the scientific and rational nature of the energy-saving management method.

[0103] Assuming there are several reliable analysis device groups in the energy-saving optimization area, and the proportion of reliable analysis device groups is greater than a preset reliable analysis group proportion threshold, it is necessary to determine whether there are more than one target number of device groups with deviation weight values ​​greater than a preset deviation weight threshold. If so, the energy-saving management method for this energy-saving optimization area is determined to be unable to continue energy-saving processing; if not, proceed to step S333.

[0104] S333: Determine whether the reliable analysis equipment group belongs to the equipment group with the largest correlation coefficient of the monitoring equipment in the energy-saving optimization area. If so, only when there are equipment groups with a target number of deviation weight values ​​greater than the preset deviation weight threshold, it is determined that the energy-saving management method in the energy-saving optimization area cannot continue to carry out energy-saving processing. If not, proceed to step S334.

[0105] This step further assesses the importance of the reliable analysis equipment group by determining whether it is the group with the highest correlation coefficient among the monitored equipment. If the reliable analysis equipment group is the group with the highest correlation coefficient, it indicates that this equipment group is a core equipment group in the energy-saving optimization area, and its stability has a significant impact on overall reliability, thus requiring more cautious handling. In this case, energy-saving processing is only deemed impossible to continue if there are more than a target number of equipment groups with deviation weight values ​​exceeding the preset deviation weight threshold. If the reliable analysis equipment group is not the group with the highest correlation coefficient among the monitored equipment, further evaluation of other factors is required. The significance of this step lies in achieving a refined assessment of equipment importance, ensuring that energy-saving management methods are more accurate and scientific.

[0106] When the reliable analysis equipment group has the highest correlation coefficient among the monitored equipment groups, it indicates that this equipment group is a core equipment group in the energy-saving optimization area, and its stability has a significant impact on overall reliability. In this case, if there are more than one target number of equipment groups with deviation weight values ​​greater than the preset deviation weight threshold, it indicates that there are still a certain number of equipment groups with poor stability, and therefore, careful handling is required. If the reliable analysis equipment group does not have the highest correlation coefficient among the monitored equipment groups, it indicates that the importance of this equipment group is relatively low, and further evaluation of other factors, such as the degree of correlation between the reliable analysis equipment group and the energy-saving optimization area, is needed. The significance of this setting is to achieve differentiated assessment of equipment importance, ensuring that energy-saving management methods are more accurate and scientific.

[0107] If the proportion of reliable analysis equipment groups is greater than the preset reliable analysis equipment group proportion threshold, and there are no target number of equipment groups with deviation weight values ​​greater than the preset deviation weight threshold, then proceed to step S333. Determine whether the reliable analysis equipment group is the equipment group with the largest correlation coefficient among the monitored equipment. If so, it is necessary to further determine whether there are target number of equipment groups with deviation weight values ​​greater than the preset deviation weight threshold; otherwise, proceed to step S334.

[0108] S334: Based on the sum of the correlation coefficients between the reliable analysis equipment group and the monitoring equipment in the energy-saving optimization area, and the monitoring and analysis method of the communication link of the equipment group with the largest correlation coefficient in the energy-saving optimization area, determine the analysis matching coefficient of the energy-saving optimization area, and determine whether the analysis matching coefficient of the energy-saving optimization area is greater than the preset matching coefficient threshold. If yes, then only when there are a target number of equipment groups with deviation weight values ​​greater than the preset deviation weight threshold, the energy-saving management method of the energy-saving optimization area is determined to be unable to continue energy-saving processing. If no, then only when there are a target number of equipment groups with deviation weight values ​​greater than the preset deviation weight threshold, or when the number of stable deviation equipment in the equipment group with the largest correlation coefficient does not meet the requirements, the energy-saving management method of the energy-saving optimization area is determined to be unable to continue energy-saving processing.

[0109] The analysis matching coefficient is a comprehensive index calculated using the sum of the correlation coefficients between the reliable analysis equipment group and the monitoring equipment in the energy-saving optimization area, as well as the monitoring analysis method of the communication link of the equipment group with the largest correlation coefficient. It is used to evaluate the degree of monitoring analysis matching in the energy-saving optimization area. The preset matching coefficient threshold is a critical value for determining whether the monitoring analysis matching degree of the energy-saving optimization area has reached a high level. This step calculates the analysis matching coefficient to evaluate the degree of monitoring analysis matching in the energy-saving optimization area, and then, combined with the determination of the deviation weight value, determines whether to continue energy-saving treatment. The significance of this step lies in achieving a quantitative assessment of the monitoring analysis matching degree, making the determination of energy-saving management methods more accurate and scientific.

[0110] By calculating and analyzing the matching coefficient, the degree of monitoring and analysis matching in the energy-saving optimization area can be accurately reflected. If the matching coefficient is greater than the preset matching coefficient threshold, it indicates a high degree of monitoring and analysis matching in the energy-saving optimization area, and the stability requirements can be appropriately relaxed. In this case, energy-saving processing can only be considered impossible if there are more than a target number of equipment groups with deviation weight values ​​greater than the preset deviation weight threshold. If the matching coefficient is not greater than the preset matching coefficient threshold, it indicates a moderate degree of monitoring and analysis matching in the energy-saving optimization area, requiring more cautious handling. In this case, energy-saving processing can only be considered impossible if there are more than a target number of equipment groups with deviation weight values ​​greater than the preset deviation weight threshold, or if the number of stable deviation equipment in the equipment group with the highest correlation coefficient of the monitored equipment does not meet the requirements, to avoid temperature control risks. The significance of this setting is that it achieves a comprehensive assessment of the degree of monitoring and analysis matching and stability, ensuring the scientific and rational nature of the energy-saving management method.

[0111] Assuming the proportion of reliable analysis equipment groups exceeds a preset reliable analysis equipment group proportion threshold, and there are no equipment groups with a target number or more deviation weight values ​​exceeding a preset deviation weight threshold, and the reliable analysis equipment group is not the equipment group with the largest correlation coefficient among the monitored equipment, then proceed to step S334. Calculate the sum of the correlation coefficients between the reliable analysis equipment group and the monitored equipment in the energy-saving optimization area, and the monitoring and analysis method for the communication link of the equipment group with the largest correlation coefficient, to obtain the analysis matching coefficient for the energy-saving optimization area. Determine whether the analysis matching coefficient is greater than a preset matching coefficient threshold. If it is, further determine whether there are equipment groups with a target number or more deviation weight values ​​exceeding a preset deviation weight threshold; if not, determine whether there are equipment groups with a target number or more deviation weight values ​​exceeding a preset deviation weight threshold, or whether the number of stable deviation equipment in the equipment group with the largest correlation coefficient among the monitored equipment does not meet the requirements.

[0112] This embodiment achieves intelligent determination of energy-saving management methods for energy-optimized areas through step S3. Its core value lies in three aspects: First, through comprehensive evaluation of stable deviation equipment and AI models, it achieves quantitative assessment of the operational stability of equipment groups, thus providing data support for determining energy-saving management methods. Second, through the evaluation of the analysis area and reliable analysis equipment groups, it achieves quantitative assessment of the monitoring and analysis coverage, thereby ensuring the matching of energy-saving management methods with actual monitoring conditions. Third, through a multi-level judgment mechanism that presets deviation weight thresholds, preset reliable analysis group proportion thresholds, target quantity, and preset matching coefficient thresholds, it achieves refined formulation of energy-saving management methods, thereby further improving the reliability of temperature control processing while ensuring energy-saving effects.

[0113] This embodiment provides a method for determining an energy-saving management method for AI-based energy-saving management in pharmaceutical warehouses. Applied to an energy-saving management system for pharmaceutical warehouses, the formula for calculating the matching coefficient is the sum of the correlation coefficients of the monitoring devices in the reliable analysis device group multiplied by the proportion of the reliable analysis device group, plus the correlation coefficient of the device group with the largest correlation coefficient.

[0114] Based on the monitoring and analysis method of S2, the monitoring and analysis method for the communication links of equipment group A and equipment group B is to perform monitoring and analysis processing in all areas, while the monitoring and analysis method for the communication links of equipment group C is to perform monitoring and analysis processing only in the energy-saving optimization area.

[0115] The energy-saving management method for Energy-Saving Optimization Area 1 is determined as follows: For Energy-Saving Optimization Area 1, the correlation coefficient of monitoring equipment in Equipment Group A is 70%, which is the maximum value and greater than 60%; the correlation coefficient of monitoring equipment in Equipment Group B is 20%; and the correlation coefficient of monitoring equipment in Equipment Group C is 0%. The analysis area for Equipment Group A is all 10 areas, the analysis area for Equipment Group B is all 10 areas, and the analysis area for Equipment Group C is the energy-saving optimization area (areas 1, 2, 3, 4, 5, 7, 8, 9, 10). Therefore, the reliable analysis equipment groups are Equipment Groups A and B, and the proportion of reliable analysis equipment groups is 100%, which is greater than the preset reliable analysis group proportion threshold of 60%. Only when there are a target number (e.g., not less than 2) of equipment groups with deviation weight values ​​greater than the preset deviation weight threshold (e.g., 5%), is the energy-saving management method for the energy-saving optimization area determined to be unable to continue energy-saving processing.

[0116] The significance of this step lies in the fact that it enables the refined formulation of energy-saving management methods through a multi-level judgment mechanism, ensuring that the reliability of temperature control is further improved while guaranteeing energy-saving effects. The core value is reflected in three aspects: First, through the comprehensive evaluation of stable deviation equipment and AI models, the operational stability of equipment groups is quantitatively evaluated; second, through the evaluation of the analysis area and reliable analysis equipment groups, the coverage of monitoring and analysis is quantitatively evaluated; and third, through a multi-level judgment mechanism with preset deviation weight thresholds, preset reliable analysis group proportion thresholds, target quantity, and preset matching coefficient thresholds, the refined formulation of energy-saving management methods is achieved.

[0117] Furthermore, the method for determining the energy-saving optimization scheme for the region is as follows: In this embodiment, based on the updated number of energy-saving optimization areas and the monitoring matching coefficients of different equipment groups, a comprehensive evaluation of the updated energy-saving effect and the monitoring matching degree of the equipment groups is performed. Using the comprehensive evaluation results, a differentiated new energy-saving optimization area identification strategy is generated, thereby improving the energy-saving effect while also ensuring a reliable evaluation of the monitoring matching degree of different equipment groups.

[0118] S41: Based on the updated energy-saving optimization area data, determine the number of updated energy-saving optimization areas.

[0119] The number of energy-saving optimization areas after the update refers to the total number of energy-saving optimization areas after the update process. This step quantifies the coverage of energy-saving optimization areas by statistically analyzing the number of updated energy-saving optimization areas, providing basic data for determining subsequent energy-saving optimization schemes. Its significance lies in converting the coverage of energy-saving optimization areas into measurable values, thus providing an objective basis for determining energy-saving optimization schemes.

[0120] By statistically analyzing the number of updated energy-saving optimization areas, the current coverage of energy-saving optimization can be accurately reflected. A high number indicates broad coverage, allowing for a slower update speed; conversely, a low number indicates narrow coverage, necessitating a faster update speed. This approach enables a quantitative assessment of energy-saving optimization coverage, leading to more precise and scientific determination of energy-saving optimization strategies.

[0121] Assuming that after the update process, there are several energy-saving optimization areas, this number reflects the current coverage of energy-saving optimization and provides a basis for determining subsequent energy-saving optimization schemes.

[0122] S42: Based on the temperature monitoring equipment data of the energy-saving optimization area, determine the proportion of temperature monitoring equipment in different equipment groups in the energy-saving optimization area, and sum the proportions of temperature monitoring equipment in different energy-saving optimization areas in the equipment groups to determine the monitoring matching coefficient.

[0123] The monitoring matching coefficient refers to the sum of the proportions of temperature monitoring devices in an equipment group within the energy-saving optimization zone, ranging from 0% to 100%. A higher value indicates a higher degree of monitoring matching for that equipment group within the energy-saving optimization zone. This step quantifies the monitoring matching degree of each equipment group within the energy-saving optimization zone by calculating the monitoring matching coefficient, providing an important reference for determining subsequent energy-saving optimization schemes. Its significance lies in transforming the matching status of equipment groups with the energy-saving optimization zone into a measurable indicator, making the determination of energy-saving optimization schemes more accurate.

[0124] By calculating the monitoring matching coefficient, the degree of monitoring matching for each equipment group within the energy-saving optimization area can be accurately reflected. A higher monitoring matching coefficient for a particular equipment group indicates higher monitoring coverage within the energy-saving optimization area, and its stability has a significant impact on the overall energy-saving effect. Conversely, a lower monitoring matching coefficient for a particular equipment group indicates lower monitoring coverage within the energy-saving optimization area, and its stability has a smaller impact on the overall energy-saving effect. The significance of this setup lies in enabling differentiated assessment of the importance of equipment groups, making the determination of energy-saving optimization schemes more accurate and scientific.

[0125] Suppose that a certain equipment group has different numbers of temperature monitoring devices distributed in several energy-saving optimization zones. Calculate the proportion of the number of devices in each energy-saving optimization zone to the total number of devices in the equipment group, and add these proportions together to obtain the monitoring matching coefficient of the equipment group.

[0126] S43: Determine the energy-saving optimization scheme for a region by using the number of updated energy-saving optimization areas and the monitoring matching coefficients of different equipment groups.

[0127] The energy-saving optimization scheme refers to decision-making methods regarding whether to continue updating the energy-saving optimization area and how to identify new energy-saving optimization areas. These include different schemes such as: no need to update the energy-saving optimization area; designating a new energy-saving optimization area as long as there exists a monitoring equipment matching coefficient above the first matching coefficient threshold and no equipment group with a deviation weight value greater than the preset deviation weight threshold; and designating a new energy-saving optimization area as long as there exists another equipment group with a monitoring equipment matching coefficient above the first matching coefficient threshold, and the sum of the monitoring equipment matching coefficients of this group with other different equipment groups is greater than the preset matching coefficient value and no equipment group with a deviation weight value greater than the preset deviation weight threshold. This step, by comprehensively considering the number of energy-saving optimization areas after the update process and the monitoring matching coefficients of each equipment group, achieves intelligent determination of the energy-saving optimization scheme. Its significance lies in ensuring a reliable assessment of the monitoring matching degree of different equipment groups while improving energy-saving effects.

[0128] By comprehensively considering the number of updated energy-saving optimization zones, the current level of energy-saving optimization coverage can be accurately reflected; by comprehensively considering the monitoring matching coefficients of each equipment group, the monitoring matching degree of each equipment group within the energy-saving optimization zones can be accurately reflected. Combining these two factors allows for determining whether to continue updating energy-saving optimization zones and how to identify new energy-saving optimization zones, ultimately achieving a balance between energy-saving effects and monitoring matching degree. The significance of this setup lies in enabling the refined formulation of energy-saving optimization schemes, ensuring that resources can be rationally allocated according to actual needs.

[0129] Assuming there are several energy-saving optimization areas after the update process, and each equipment group has a corresponding monitoring matching coefficient, the energy-saving optimization scheme for that area is determined based on the subsequent judgment logic.

[0130] Furthermore, if the number of updated energy-saving optimization areas is less than the preset threshold for the number of energy-saving optimization areas, then the energy-saving optimization scheme for a region is determined as follows: if there is a group of devices in the region whose monitoring equipment matching coefficient is above the first matching coefficient threshold, and there is no group of devices whose deviation weight value is greater than the preset deviation weight threshold, then it is taken as a new energy-saving optimization region.

[0131] The preset threshold for the number of energy-saving optimization zones is a critical value for determining whether the coverage of these zones has reached a high level. The first matching coefficient threshold is a critical value for determining whether the monitoring matching degree of equipment groups within the energy-saving optimization zones has reached a high level. When the number of updated energy-saving optimization zones is less than this threshold, it indicates that the energy-saving optimization coverage is narrow, and the update speed of the energy-saving optimization zones needs to be accelerated. At this time, as long as there are equipment groups with high monitoring matching coefficients and good stability in the area, it can be used as a new energy-saving optimization zone to expand the energy-saving optimization coverage. The significance of this step is that it enables the rapid expansion of energy-saving optimization zones, ensuring that the energy-saving effect can be continuously improved.

[0132] When the number of updated energy-saving optimization zones is less than the preset threshold, it indicates that the energy-saving optimization coverage is too narrow, and the update speed of the energy-saving optimization zones needs to be accelerated. In this case, by identifying areas where equipment groups with high monitoring matching coefficients and good stability are located, and designating them as new energy-saving optimization zones, the coverage of energy-saving optimization can be rapidly expanded while ensuring the reliability of temperature control. The significance of this setting lies in achieving a balance between energy-saving effect and temperature control reliability, avoiding temperature control risks caused by unilaterally pursuing expanded energy-saving effects.

[0133] Furthermore, if the number of energy-saving optimized regions after the update process is not less than a preset threshold for the number of energy-saving optimized regions, the following situations also apply: Case 1: The device group that does not perform communication link monitoring and analysis in all areas is designated as other device groups. If there are no other device groups whose monitoring matching coefficient is less than the preset matching coefficient threshold, then the energy-saving optimization scheme for the area is determined to be that no energy-saving optimization area update processing is required.

[0134] Other device groups refer to device groups that are not monitored and analyzed for communication links in all areas; that is, device groups that are monitored and analyzed only in energy-saving optimization areas or areas with high correlation coefficients between monitored devices. This applies when the number of updated energy-saving optimization areas is not less than the preset threshold for the number of energy-saving optimization areas, and there are no other device groups with low monitoring matching coefficients. This indicates that the coverage of energy-saving optimization areas is high, and the monitoring matching degree of all other device groups is good; therefore, there is no need to continue updating the energy-saving optimization areas. The significance of this step is to avoid excessive updates to energy-saving optimization areas and ensure that resources are allocated rationally.

[0135] When the number of updated energy-saving optimized areas is not less than the preset threshold for the number of energy-saving optimized areas, it indicates that the energy-saving optimization coverage has reached a high level. When there are no other device groups with a monitoring matching coefficient lower than the preset threshold, it indicates that the monitoring matching degree of all other device groups is good. In this case, continuing to update the energy-saving optimized areas may lead to a waste of system resources, so there is no need to update the energy-saving optimized areas. The significance of this setting is that it optimizes resource allocation and avoids over-investment.

[0136] Assuming that the number of energy-saving optimization areas after the update is not less than the preset threshold for the number of energy-saving optimization areas, and the monitoring matching coefficients of all other equipment groups are not less than the preset matching coefficient threshold, then the energy-saving optimization scheme for the determined area is one that does not require updating the energy-saving optimization areas.

[0137] Scenario 2: If there are other equipment groups whose monitoring matching coefficient is less than the preset matching coefficient threshold, the monitoring deviation value of the other equipment groups is determined based on the number of other equipment groups and the average value of their monitoring matching coefficients. It is then determined whether the monitoring deviation value is greater than the preset deviation threshold. If so, the energy-saving optimization scheme for the region is determined as follows: if there are other equipment groups in the region whose monitoring equipment matching coefficient is above the first matching coefficient threshold, and there are no equipment groups whose deviation weight value is greater than the preset deviation weight threshold, then that region is designated as a new energy-saving optimization region. If not, the energy-saving optimization scheme for the region is determined as follows: if there are other equipment groups in the region whose monitoring equipment matching coefficient is above the first matching coefficient threshold, and the sum of their monitoring equipment matching coefficients with those of different other equipment groups is greater than the preset matching coefficient value, and there are no equipment groups whose deviation weight value is greater than the preset deviation weight threshold, then that region is designated as a new energy-saving optimization region.

[0138] The monitoring deviation value of other equipment groups refers to a comprehensive index calculated based on the number of other equipment groups with monitoring matching coefficients lower than the preset matching coefficient threshold and the average of their monitoring matching coefficients. This index is used to assess the overall monitoring matching deviation of other equipment groups. The preset deviation threshold is the critical value for determining whether the monitoring matching deviation of other equipment groups has reached a high level. The preset matching coefficient value is the critical value for determining whether the cumulative sum of the monitoring matching coefficients of other equipment groups has reached a high level. This situation applies when the number of updated energy-saving optimization areas is not less than the preset energy-saving optimization area number threshold, and there are other equipment groups with monitoring matching coefficients lower than the preset matching coefficient threshold. In this case, it is necessary to further evaluate the monitoring deviation value of other equipment groups to determine whether energy-saving optimization area updates are needed. The significance of this step is that for situations with insufficient monitoring matching, differentiated energy-saving optimization schemes are adopted, achieving precise resource allocation.

[0139] When other equipment groups have monitoring matching coefficients lower than the preset matching coefficient threshold, it indicates that the monitoring matching degree of these equipment groups is insufficient, which may affect the energy-saving optimization effect. In this case, it is necessary to further evaluate the overall monitoring matching degree of these equipment groups. If the monitoring deviation value of other equipment groups is greater than the preset deviation threshold, it indicates that the overall monitoring matching degree of these equipment groups has a large deviation, and the energy-saving optimization area needs to be updated first to improve the monitoring matching degree of these equipment groups. If the monitoring deviation value of other equipment groups is not greater than the preset deviation threshold, it indicates that the overall monitoring matching degree of these equipment groups has a small deviation, and more stringent conditions can be used to identify energy-saving optimization areas. That is, the cumulative sum of the monitoring equipment matching coefficients of other equipment groups must be greater than the preset matching coefficient value to ensure that the newly identified energy-saving optimization areas can significantly improve the monitoring matching degree of these equipment groups. The significance of this setting is that it enables fine-tuning of the energy-saving optimization scheme, ensuring that resources can be rationally allocated according to actual needs.

[0140] Assuming the number of updated energy-saving optimization areas is not less than a preset threshold, and that several other equipment groups have monitoring matching coefficients less than a preset matching coefficient threshold, the monitoring deviation values ​​of these other equipment groups are calculated to determine if they exceed a preset deviation threshold. If they do, the area is designated as a new energy-saving optimization area as long as there are other equipment groups in the area whose monitoring equipment matching coefficients are above the first matching coefficient threshold and whose deviation weight values ​​are not greater than a preset deviation weight threshold. If they do not exceed the threshold, the cumulative sum of the monitoring equipment matching coefficients of the other equipment groups must be greater than a preset matching coefficient value. Only when this condition is met and the deviation weight value is not greater than a preset deviation weight threshold is the area designated as a new energy-saving optimization area.

[0141] The significance of this step lies in the fact that, through differentiated energy-saving optimization schemes, it enables precise processing of other equipment groups with different monitoring deviations, ensuring that resources can be rationally allocated according to actual needs.

[0142] Based on the results determined by the S3 energy-saving management method, some energy-optimized areas will continue to implement energy-saving measures, while others cannot. For the energy-optimized areas that will continue to implement energy-saving measures, further determination of temperature control methods is needed.

[0143] The associated optimization areas for equipment group A are: Area 1, Area 2, Area 3, Area 6, Area 7, and Area 8 (6 in total, all with the maximum correlation coefficient). The associated optimization areas for equipment group B are: Area 4, Area 5, and Area 9 (3 in total, all with the maximum correlation coefficient). The associated optimization areas for equipment group C are: None (the correlation coefficient is not the maximum value in any of the energy-saving optimization areas). Monitoring methods determined: Equipment Group A: Performs monitoring, analysis, and processing in all areas; Equipment Group B: Performs monitoring, analysis, and processing in all areas; Equipment Group C: Monitoring and analysis are only performed in the energy-saving optimization area (other equipment groups); After the S3 judgment and processing, eight energy-saving optimization areas, namely Area 1, Area 2, Area 3, Area 4, Area 5, Area 6, Area 7, and Area 8, were determined to continue energy-saving processing, while Area 9 was determined to be unable to continue energy-saving processing.

[0144] The updated number of energy-saving optimized zones is 8.

[0145] Monitoring matching coefficient = Number of devices in the current effective energy-saving optimization area of ​​the equipment group ÷ Total number of devices in the equipment group; Monitoring matching coefficient for equipment group A: Equipment group A consists of 80 devices, distributed across the current 8 energy-saving optimization zones: Monitoring matching coefficient = 72 ÷ 80 = 90%; Monitoring matching coefficient for equipment group B: Equipment group B consists of 60 devices, with 48 different devices distributed across 8 energy-saving optimization zones. Therefore, the monitoring matching coefficient = 48 ÷ 60 = 80%. Monitoring matching coefficient of equipment group C (other equipment groups): Equipment group C has a total of 40 devices, and monitoring and analysis are only performed in the energy-saving optimization area. The total number of devices in the current 8 energy-saving optimization areas of equipment group C is 3+3+4+4+4+4+4+3 = 29. The monitoring matching coefficient is 29 ÷ 40 = 72.5%.

[0146] Identify other device groups: Other device groups refer to device groups that are not monitored and analyzed for communication links in all areas.

[0147] Equipment group C is only monitored and analyzed in the energy-saving optimization area, and is not monitored in area 10 (non-energy-saving optimization area). Therefore, equipment group C is another equipment group.

[0148] Determine if there are other device groups whose monitoring matching coefficient is less than the preset matching coefficient threshold: The preset matching coefficient threshold is 80%, and the monitoring matching coefficient for device group C (other device groups) is 72.5%. Judgment: 72.5% < 80%, indicating the existence of other device groups with monitoring matching coefficients lower than the preset matching coefficient threshold.

[0149] Calculate the monitoring deviation value: The number of other device groups with a monitoring matching coefficient less than the preset matching coefficient threshold is 1 (device group C). The average monitoring matching coefficient of these device groups is 72.5%. Monitoring deviation value = (1 - actual monitoring matching coefficient) average value × number of other equipment groups = (1 - 72.5%) × 1.0 = 27.5%. Preset deviation threshold = 0.3 Judgment: The monitoring deviation value is less than or equal to the preset deviation threshold.

[0150] Determine the energy-saving optimization plan: Based on the judgment result that the monitoring deviation value is less than or equal to the preset deviation threshold, the energy-saving optimization scheme is determined as follows: as long as the monitoring matching coefficient of other equipment groups in the area is above the first matching coefficient threshold, and the sum of the monitoring matching coefficients of other equipment groups is greater than the preset matching coefficient value, and there is no equipment group with a deviation weight value greater than the preset deviation weight threshold, then it is regarded as a new energy-saving optimization area.

[0151] Determine whether region 10 can be used as a new energy-saving optimization region: In region 10, there are 10 devices in device group C, meaning the monitoring matching coefficient is 25%, which is greater than the first matching coefficient threshold of 5%. The sum of the monitoring matching coefficients of other device groups is greater than the preset matching coefficient value. The sum of the monitoring matching coefficients of other device groups in region 10 is 25%, which is greater than 10%. Therefore, as long as there are no device groups in region 10 with a deviation weight value greater than the preset deviation weight threshold (e.g., 5%), region 10 will be designated as a new energy-saving optimization region.

[0152] The significance of this step lies in the fact that it enables the refined formulation of temperature control methods through a multi-level judgment mechanism, ensuring that the accuracy and stability of temperature control processing are further improved while guaranteeing energy-saving effects. The core value is reflected in three aspects: First, through the comprehensive evaluation of temperature control deviation and data matching coefficient, the quantitative evaluation of temperature control effect is achieved; second, through the evaluation of deviation weight value, the indirect evaluation of the operational stability of equipment groups is achieved; and third, through the multi-level judgment mechanism of preset temperature control deviation threshold, preset data matching coefficient threshold, and preset deviation weight threshold, the refined formulation of temperature control methods is achieved.

[0153] This embodiment fully implements the determination of communication link monitoring and analysis methods, energy-saving management methods, and energy-saving optimization schemes for AI-based energy-saving management in pharmaceutical warehouses. Its core value is reflected in three aspects: First, by conducting quantitative assessments across multiple dimensions, such as the correlation coefficient of monitoring equipment, the proportion of energy-saving optimization areas, and the comprehensive correlation value, a comprehensive grasp of the correlation between equipment groups and energy-saving optimization areas was achieved. This provided sufficient data support for determining the monitoring and analysis methods for communication links, ensuring a high degree of matching between the monitoring and analysis methods and the actual equipment distribution.

[0154] Secondly, by using evaluation indicators at multiple levels, such as stable deviation equipment, deviation weight value, analysis area range, and reliable analysis equipment group, a comprehensive assessment of the operational stability and monitoring and analysis coverage of the energy-saving optimization area was achieved. This provides a comprehensive and reliable basis for determining energy-saving management methods, ensuring that the reliability of temperature control is further improved on the basis of enhancing energy-saving effects.

[0155] Third, through comprehensive analysis of updated indicators such as the number of energy-saving optimization areas, monitoring matching coefficients, and monitoring deviation values, the energy-saving optimization plan was refined. This ensured that the identification of new energy-saving optimization areas was highly scientific and operable, while guaranteeing the rational allocation of resources. Ultimately, it achieved a continuous balance and optimization between energy-saving effect and temperature control reliability, providing a complete theoretical basis and practical guidance for energy-saving management of pharmaceutical warehouses.

[0156] Example 2 In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the aforementioned AI energy-saving management method for pharmaceutical warehouses based on hybrid communication when running the computer program.

[0157] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0158] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0159] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for AI-powered energy-saving management of pharmaceutical warehouses based on hybrid communication, characterized in that, Specifically, it includes: Based on the communication strategy of the temperature monitoring system, the temperature monitoring equipment is divided into different equipment groups. Based on the distribution of temperature monitoring equipment in different equipment groups in the region, the energy-saving optimization area in the region is determined. By utilizing the correspondence between the temperature regulation results of the temperature regulation equipment and the temperature monitoring equipment, the temperature regulation processing of the energy-saving optimization area is carried out with the goal of minimizing energy consumption. Based on the distribution data of temperature monitoring devices in different energy-saving optimization areas in the equipment group, and in combination with the composition of the energy-saving optimization areas in the area, the monitoring and analysis method of the communication link of the equipment group is determined, and the operating status of the temperature monitoring devices in the equipment group is determined using the monitoring and analysis method. Based on the analysis and processing results of the AI ​​model's operating status and the monitoring and analysis method of the communication links of the device group, the energy-saving management method for the energy-saving optimization area is determined. The energy-saving management method is used to update the energy-saving optimization area. Based on the updated energy-saving optimization area and the temperature monitoring equipment data of the energy-saving optimization area, energy-saving optimization schemes for different areas are determined.

2. The AI-powered energy-saving management method for pharmaceutical warehouses based on hybrid communication as described in claim 1, characterized in that, Temperature monitoring equipment is divided into different equipment groups, specifically including: Temperature monitoring devices that use the same communication strategy are grouped into the same device group.

3. The AI-powered energy-saving management method for pharmaceutical warehouses based on hybrid communication as described in claim 1, characterized in that, By utilizing the correlation between the temperature control results of temperature control equipment and temperature monitoring equipment, temperature control in energy-saving optimized areas is carried out with the goal of minimizing energy consumption. Specifically, this includes: When the area belongs to the energy-saving optimization area, the temperature change of the temperature monitoring equipment under different temperature adjustment values ​​is used to construct the correspondence between the temperature adjustment value and the temperature change value. Based on the correspondence, the temperature is adjusted under the constraint that the energy consumption is the lowest and the monitoring data of the temperature monitoring equipment in the energy-saving optimization area is within the qualified range.

4. The AI-powered energy-saving management method for pharmaceutical warehouses based on hybrid communication as described in claim 1, characterized in that, The method for determining the energy-saving optimization zone in the aforementioned region is as follows: Based on the distribution of temperature monitoring devices in different equipment groups within a region, determine the proportion of temperature monitoring devices in different equipment groups within that region. By utilizing the proportion of temperature monitoring devices in different equipment groups, the correlation coefficient between the area and the monitoring devices in different equipment groups is determined; Based on the correlation coefficient between the area and the monitoring equipment of different equipment groups, it is determined whether the area belongs to the energy-saving optimization area.

5. The AI-powered energy-saving management method for pharmaceutical warehouses based on hybrid communication as described in claim 4, characterized in that, If there is a group of devices in the area whose correlation coefficient of monitoring devices is greater than the preset correlation coefficient threshold, then the temperature monitoring devices are mainly composed of temperature range devices with a certain communication strategy. Therefore, they are not affected by the stability of multiple communication strategies at the same time, and the communication reliability is relatively strong. Thus, the area is determined to be an energy-saving optimization area.

6. The AI-powered energy-saving management method for pharmaceutical warehouses based on hybrid communication as described in claim 1, characterized in that, The method for determining the monitoring and analysis method of the communication links of the device group is as follows: Based on the distribution data of temperature monitoring devices in the equipment group in different energy-saving optimization areas, the correlation coefficient between the equipment group and the monitoring devices in different energy-saving optimization areas is determined, and the correlation coefficient is used to determine the associated optimization areas in the energy-saving optimization areas. By utilizing the composition of energy-saving optimization areas in the region, the proportion of energy-saving optimization areas in the region is determined, and this proportion is taken as the energy-saving optimization area ratio. Based on the correlation coefficients between the monitoring equipment of the equipment group and the monitoring equipment of different energy-saving optimization areas, the associated optimization areas, and the proportion of the energy-saving optimization areas, the monitoring and analysis method of the communication link of the equipment group is determined.

7. The AI-powered energy-saving management method for pharmaceutical warehouses based on hybrid communication as described in claim 6, characterized in that, The correlation optimization region is the energy-saving optimization region where the correlation coefficient of the monitoring equipment is the largest among all equipment groups.

8. The AI-powered energy-saving management method for pharmaceutical warehouses based on hybrid communication as described in claim 6, characterized in that, If the proportion of the energy-saving optimization area is greater than the preset proportion threshold, then the monitoring and analysis method for the communication links of all equipment groups is to monitor and analyze the stability of the communication links of the temperature monitoring equipment of the equipment group in all areas.

9. The AI-powered energy-saving management method for pharmaceutical warehouses based on hybrid communication as described in claim 1, characterized in that, The method for determining the energy-saving optimization scheme for the area is as follows: Based on the updated energy-saving optimization area data, determine the number of updated energy-saving optimization areas; Based on the temperature monitoring equipment data of the energy-saving optimization area, determine the proportion of temperature monitoring equipment in different equipment groups in the energy-saving optimization area, and sum the proportions of temperature monitoring equipment in different energy-saving optimization areas in the equipment groups to determine the monitoring matching coefficient; By utilizing the number of energy-saving optimization areas after the update process and the monitoring matching coefficients of different equipment groups, the energy-saving optimization scheme for the area is determined.

10. A computer system, comprising: A memory and processor connected by communication, and a computer program stored on the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes the AI ​​energy-saving management method for pharmaceutical warehouses based on hybrid communication as described in any one of claims 1-9.

Images