A method and system for analyzing intelligent campus information data

Abstract

The present invention discloses a method and system for analyzing intelligent campus information data, belonging to the technical field of data processing. By obtaining the device status monitoring data sets corresponding to each pre-screened IoT device monitoring behavior event in the campus IoT operation status log, determining the target status monitoring data set from several device status monitoring data sets, and then combining a series of technical means such as state vector mining, energy consumption quantification and combined analysis, the present invention can achieve precise management of campus IoT devices, effective operation status analysis and energy-saving optimization, thereby improving the overall operation efficiency and energy utilization efficiency of the campus IoT system.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and particularly relates to a method and system for analyzing intelligent campus information data. Background Art

[0002] With the continuous development of campus informatization construction, the number and types of campus Internet of Things (IoT) devices are increasing day by day, such as various devices in smart classrooms (projectors, intelligent lighting systems, air conditioners, etc.) and environmental sensors (temperature, humidity, light sensors, etc.). These devices play an important role in improving the level of campus teaching, management, and service, but at the same time, they also bring a series of technical problems.

[0003] In terms of the management of campus IoT devices, traditional management methods often lack accurate judgment of device status and priority differentiation. In terms of the analysis of device operation status, existing technical means usually simply collect device operation data and lack the ability to deeply mine and focus on analyzing the data. In terms of campus energy consumption management, due to the lack of in-depth understanding of the relationship between device operation status and energy consumption, existing energy consumption management methods are relatively extensive.

[0004] It can be seen that the existing campus IoT device management technologies are difficult to ensure the overall operation efficiency and energy utilization efficiency of the campus IoT system. Summary of the Invention

[0005] The present invention provides a method and system for analyzing intelligent campus information data, which can solve or partially solve the technical problems involved in the above background art.

[0006] The present invention provides a method for analyzing smart campus information data. The execution subject of the method for analyzing smart campus information data is a data analysis system. The method for analyzing smart campus information data includes: obtaining a device status monitoring data set corresponding to each pre-screened IoT device monitoring behavior event in the campus IoT operation status log, and determining a target status monitoring data set from several device status monitoring data sets, where the target status monitoring data set is used to indicate the target IoT device monitoring behavior event with the highest priority among several pre-screened IoT device monitoring behavior events; performing status vector mining on the campus IoT operation status log respectively according to the target status monitoring data set and each device status monitoring data set to obtain several IoT operation status vectors, and refining the status monitoring attention vectors corresponding to the target status monitoring data set and each device status monitoring data set; combining each IoT operation status vector with the corresponding status monitoring attention vector to obtain several global status monitoring vectors; performing operation energy consumption identification on the campus IoT operation status log to obtain a first operation energy consumption quantization vector, and combining the first operation energy consumption quantization vector and several global status monitoring vectors to obtain energy consumption adjustment auxiliary information; performing energy consumption adjustment analysis according to the energy consumption adjustment auxiliary information to generate a target energy consumption adjustment optimization strategy for the target IoT device monitoring behavior event.

[0007] The present invention provides a data analysis system, including at least one processor and a memory; the memory stores computer execution instructions; the at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the above method.

[0008] The present invention provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the above method are implemented.

[0009] By obtaining the device status monitoring data set corresponding to each pre-screened IoT device monitoring behavior event in the campus IoT operation status log, determining the target status monitoring data set from several device status monitoring data sets, and then combining a series of technical means such as status vector mining, energy consumption quantization and combination analysis, the present invention can achieve precise management, effective operation status analysis and energy-saving optimization of campus IoT devices, thereby improving the overall operation efficiency and energy utilization efficiency of the campus IoT system. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a flowchart of a method for analyzing smart campus information data provided by the present invention.

[0011] Figure 2 It is a schematic structural diagram of a data analysis system provided by the present invention. Detailed implementation manners

[0012] The following will clearly and completely describe the technical solutions in the present invention with reference to the accompanying drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0013] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such used data may be interchanged under appropriate circumstances so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same category, and the number of objects is not limited. For example, the first object may be one or multiple. In addition, "and / or" in the present invention represents at least one of the connected objects, and the character " / " generally represents an "or" relationship between the associated objects before and after.

[0014] Figure 1 Disclosed is a method for analyzing intelligent campus information data, which is applied to a data analysis system. The method includes the following steps 110 to 130.

[0015] Step 110: The data analysis system obtains the device status monitoring data sets corresponding to each preliminary screening IoT device monitoring behavior event in the campus IoT operation status log, and determines a target status monitoring data set from several of the device status monitoring data sets, where the target status monitoring data set is used to indicate the target IoT device monitoring behavior event with the highest priority among several of the preliminary screening IoT device monitoring behavior events.

[0016] In step 110, the campus IoT operation status log is a comprehensive record of the operation status of IoT devices on campus. It contains the device status monitoring data sets corresponding to each preliminary screening IoT device monitoring behavior event. For example, there are IoT devices such as smart classroom devices (such as projectors, smart lighting systems, air conditioners, etc.), environmental sensors (temperature, humidity, light sensors, etc.) on campus. Each monitoring behavior event of each IoT device will generate a corresponding device status monitoring data set.

[0017] Taking the intelligent lighting system as an example, its device status monitoring data set may contain the following data: the brightness value of the light (the value range can be 0 - 1000 lux, for example, the current brightness value is 300 lux), the duration of being turned on (in minutes, for example, the current duration of being turned on is 60 minutes), the number of switch operations (for example, it is 3 times), etc. For the temperature sensor in the environmental sensor, the device status monitoring data set may include the collected temperature value (for example, it is 25 degrees Celsius), the collection time interval (for example, it is 10 minutes), etc.

[0018] Among numerous device status monitoring data sets, it is necessary to determine the target status monitoring data set. The target status monitoring data set is used to indicate the target IoT device monitoring behavior event with the highest priority among several initially screened IoT device monitoring behavior events. Determining the priority can be based on multiple factors. For example, it can be achieved based on the device importance weight and the urgency level.

[0019] 1) Device importance weight

[0020] For example, for devices that ensure the normal progress of teaching, such as projectors and teaching computers in an intelligent classroom, relatively high weights can be assigned. For example, the weight of the projector is 0.8, the weight of the teaching computer is 0.7, while the weight of the temperature sensor in the environmental sensor is 0.5 (relatively speaking, projectors and teaching computers have a greater direct impact on teaching).

[0021] 2) Urgency level

[0022] If a certain device fails or is in an abnormal state, which may lead to serious consequences, its urgency level is high. For example, if the air - conditioning system fails (temperature out of control), it may seriously affect the teaching environment in the hot summer, then the priority of the monitoring behavior event related to the air - conditioning system failure will be increased. For example, when the air - conditioning system is operating normally, the priority of its device status monitoring data set is 0.6. When there is an abnormal temperature fluctuation (such as more than 5 degrees Celsius above the normal range), the priority is increased to 0.9.

[0023] By comprehensively considering these factors, the target status monitoring data set can be determined among several device status monitoring data sets. For example, at a certain moment, if there is a warning that the projector's bulb is about to be damaged (the comprehensive priority of this event is the highest after calculation), then the device status monitoring data set related to the projector will be determined as the target status monitoring data set.

[0024] Step 120: The data analysis system performs state vector mining on the campus Internet of Things operation status logs respectively according to the target status monitoring dataset and each device status monitoring dataset to obtain a number of Internet of Things operation state vectors, and extracts the status monitoring attention vectors corresponding to the target status monitoring dataset and each device status monitoring dataset; combines each of the Internet of Things operation state vectors with the corresponding status monitoring attention vector to obtain a number of global status monitoring vectors.

[0025] In the present invention, Step 120 involves three sub-steps: state vector mining, extracting status monitoring attention vectors, and combining to obtain global status monitoring vectors.

[0026] (I) State vector mining

[0027] 1) State vector mining according to the target status monitoring dataset: The data analysis system performs state vector mining on the campus Internet of Things operation status logs according to the target status monitoring dataset. Taking the previously determined projector as an example, if its target status monitoring dataset includes data such as bulb life (for example, the remaining life is 500 hours and the full life is 1000 hours), usage frequency (used 10 times a week), etc. These data can be quantified and normalized to form a state vector. For example, the bulb life can be quantified as 0.5 (the ratio of the remaining life to the full life), and the usage frequency can be quantified as 0.5 (for example, the maximum usage times per week is 20 times), then an exemplary state vector of the projector can be [0.5, 0.5].

[0028] 2) State vector mining according to each device status monitoring dataset: Similarly, the same operation is performed for other devices. For example, for a temperature sensor, if the temperature value it collects is 25 degrees Celsius and the normal comfortable temperature range is 22 - 26 degrees Celsius. The temperature value can be converted into a value between 0 and 1, and the calculation method is: (25 - 22) / (26 - 22) = 0.75 (for example). If its collection time interval is 10 minutes and the set maximum acceptable time interval is 15 minutes, then this factor is quantified as 0.67 (10 / 15). The state vector of the temperature sensor can be [0.75, 0.67].

[0029] (II) Extracting status monitoring attention vectors

[0030] For the target status monitoring data set: For the target status monitoring data set (related to projectors), according to its importance and current status in the entire campus Internet of Things system, extract the status monitoring attention vector. For example, if the projector is very critical in the current teaching activity (such as an important teaching demonstration is in progress), and the situation that its bulb is about to be damaged needs high attention, then its status monitoring attention vector can be [0.9, 0.8] (the first value represents the attention weight for the bulb life, and the second value represents the attention weight for the usage frequency). The weights in the present invention are determined according to the current status and importance of the device. For example, if the bulb life is close to the critical value, the attention weight for it will be relatively high.

[0031] For each device status monitoring data set: For the temperature sensor, considering that the temperature has a certain impact on the teaching environment but is not the most urgent situation, its status monitoring attention vector can be [0.6, 0.5] (the first value represents the attention weight for the temperature value, and the second value represents the attention weight for the acquisition time interval).

[0032] (III) Combine to obtain the global status monitoring vector

[0033] Combination process:

[0034] Combine each Internet of Things operation status vector with the corresponding status monitoring attention vector respectively. For the projector, its global status monitoring vector is calculated as follows: The status vector is [0.5, 0.5], and the status monitoring attention vector is [0.9, 0.8]. The combined global status monitoring vector is [0.5 * 0.9, 0.5 * 0.8] = [0.45, 0.4]. For the temperature sensor, the status vector is [0.75, 0.67], and the status monitoring attention vector is [0.6, 0.5]. The combined global status monitoring vector is [0.75 * 0.6, 0.67 * 0.5] = [0.45, 0.335].

[0035] Step 130: The data analysis system performs running energy consumption identification on the campus Internet of Things operation status log to obtain the first running energy consumption quantization vector, combines the first running energy consumption quantization vector and several of the global status monitoring vectors to obtain energy consumption adjustment auxiliary information; performs energy consumption adjustment analysis based on the energy consumption adjustment auxiliary information to generate the target energy consumption adjustment optimization strategy for the target Internet of Things device monitoring behavior event.

[0036] Specifically, step 130 involves three sections: running energy consumption identification, combining to obtain energy consumption adjustment auxiliary information, and generating the target energy consumption adjustment optimization strategy.

[0037] (1) Identification of operating energy consumption: The data analysis system identifies the operating energy consumption from the operation status logs of the campus Internet of Things. Taking the intelligent lighting system as an example, its energy consumption is related to factors such as the brightness of the lights and the duration of operation. For example, if the power of the intelligent lighting system is 100 watts and the duration of operation is 60 minutes (1 hour), according to the formula: energy consumption = power × time, its energy consumption is 100 watts × 1 hour = 0.1 kWh. If there are multiple lighting areas, the energy consumption of each area is added to obtain the total energy consumption of the lighting system. For the air conditioning system, for example, its power is 1500 watts and the operation time is 30 minutes (0.5 hours), and the energy consumption is 1500 watts × 0.5 hours = 0.75 kWh. The energy consumption of all Internet of Things devices on campus is arranged in a certain order (such as according to device type or area) to obtain the first operating energy consumption quantization vector. For example, in the campus, there are an intelligent lighting system, an air conditioning system, and a projector (the power of the projector is 300 watts, it operates for 1 hour, and the energy consumption is 0.3 kWh), and the first operating energy consumption quantization vector can be [0.1, 0.75, 0.3].

[0038] (2) Combining to obtain auxiliary information for energy consumption adjustment: Combine the first operating energy consumption quantization vector and several global status monitoring vectors. For example, in addition to the vectors related to the intelligent lighting system, air conditioning system, and projector mentioned above, there are other devices (such as a humidity sensor, and its global status monitoring vector is [0.3, 0.2]). The combined auxiliary information for energy consumption adjustment may be a matrix or a vector group. For example: [[0.1, 0.75, 0.3], [0.45, 0.4], [0.45, 0.335], [0.3, 0.2]] (the first row is the first operating energy consumption quantization vector, and the following rows are the global status monitoring vectors of each device).

[0039] (3) Energy consumption adjustment analysis and generation of target energy consumption adjustment optimization strategy

[0040] Example of energy consumption adjustment analysis algorithm - linear regression model: A linear regression model can be used for energy consumption adjustment analysis. For example, there is a linear relationship between energy consumption (Y) and the status factors of the device (such as the brightness of the intelligent lighting system, the temperature setting of the air conditioning system, etc., represented by X1, X2, etc.), that is, Y = a1X1 + a2X2 + … + b (where a1, a2, etc. are coefficients and b is a constant). Taking the intelligent lighting system as an example, the relationship between brightness (X1) and energy consumption (Y) may be Y = 0.01X1 + 0.05 (the coefficients obtained by fitting historical data, for example). According to the data in the auxiliary information for energy consumption adjustment, substitute the status factors of each device into the linear regression model to analyze the impact of different device statuses on energy consumption. For example, for the intelligent lighting system, if the current brightness is 300 lux, calculate the current energy consumption and the predicted energy consumption at different brightness levels according to the model.

[0041] Generate the target energy consumption regulation optimization strategy: According to the above analysis, generate the target energy consumption regulation optimization strategy for the target IoT device monitoring behavior event (such as the use of a projector). If the energy consumption of the projector is related to the usage duration and brightness (for example, the projector also has a brightness adjustment function), through analysis, it is found that reducing the usage duration of the projector or lowering its brightness can reduce energy consumption without affecting the teaching effect. For example, reducing the brightness of the projector from the current 800 lumens to 600 lumens (according to the analysis of the visibility of teaching content, 600 lumens can still meet the viewing requirements), and at the same time shortening the usage duration per time from 2 hours to 1.5 hours can effectively reduce energy consumption. Then the target energy consumption regulation optimization strategy can be: adjust the projector brightness to 600 lumens and control the usage duration per time not to exceed 1.5 hours. For other devices, corresponding energy consumption regulation optimization strategies can also be generated according to similar analyses, such as the intelligent lighting system adjusts the brightness and turning-on time according to the natural light intensity and classroom usage, and the air conditioning system adjusts the temperature setting according to the classroom temperature and personnel density, etc.

[0042] In the above technical solution, the IoT operation state vector, the state monitoring attention vector, the global state monitoring vector, the first operation energy consumption quantization vector, and the energy consumption regulation auxiliary information are the key technical features involved in the generation process of the target energy consumption regulation optimization strategy. The following are exemplary introductions and explanations of these technical features respectively.

[0043] The IoT operation state vector is a quantitative representation of the operation state of campus IoT devices, and reflects various operation state characteristics of the devices in the form of feature vectors. It is mined from the device state monitoring dataset.

[0044] Taking the air conditioning device in an intelligent classroom as an example, its IoT operation state vector may include multiple features. For example, the operation mode of the air conditioner (cooling, heating, ventilation, which can be represented by 0, 1, 2 respectively), the set temperature (for example, the value range is 16 - 30 degrees Celsius, the actual set temperature is 22 degrees Celsius, which can be normalized to the [0, 1] interval, in this invention it is (22 - 16) / (30 - 16) ≈ 0.43), the current power (for example, the air conditioner power range is 500 - 2000 watts, the current power is 1000 watts, and after normalization it is (1000 - 500) / (2000 - 500) = 0.33), the fan speed (for example, the speed range is 500 - 1500 revolutions per minute, the current speed is 800 revolutions per minute, and after normalization it is (800 - 500) / (1500 - 500) = 0.3), etc.

[0045] Then the IoT operation state vector of the air conditioning device can be expressed as [vec{v}_{run}=[0, 0.43, 0.33, 0.3]]. Each element in this invention is a feature, jointly describing the current operation state of the air conditioning device.

[0046] The Internet of Things operation status vector can comprehensively reflect the operation status of the device, which helps with subsequent analysis. For example, in energy management, by analyzing the power characteristics in the Internet of Things operation status vector, the current energy consumption level of the device can be understood; in device fault diagnosis, the combination of the operation mode and other characteristics can help determine whether the device is in an abnormal state. If the air conditioner is in the cooling mode (the first characteristic is 0), but the set temperature is very high and the power is very low, it may imply a fault in the cooling system.

[0047] The status monitoring attention vector is a quantitative representation of the degree of attention to different characteristics in device status monitoring. It reflects which device status characteristics require more attention under specific circumstances.

[0048] For the above air conditioner device, the status monitoring attention vector will be different in different scenarios. For example, in the energy management scenario, the set temperature and power may be the key characteristics to focus on, while the fan speed is relatively less important. For example, the attention weight for the set temperature is 0.8, the attention weight for the power is 0.7, the attention weight for the fan speed is 0.3, and the attention weight for the operation mode is 0.2 (because in energy management, the operation mode is relatively fixed and has less impact on energy consumption), then the status monitoring attention vector is [vec{v}_{attn}=[0.2, 0.8, 0.7, 0.3]].

[0049] The status monitoring attention vector is used to guide the analysis of the device status. When conducting data analysis, by combining the Internet of Things operation status vector with the status monitoring attention vector (for example, multiplying the corresponding elements), the influence of important characteristics on the overall analysis can be highlighted. In energy management, through this combination, the status related to device energy consumption can be evaluated more accurately, so as to take effective energy consumption adjustment measures.

[0050] The global status monitoring vector is the result obtained by combining the Internet of Things operation status vector and the status monitoring attention vector. It synthesizes the operation status of the device and the degree of attention to each status characteristic.

[0051] For the air conditioner device, the calculation of the global status monitoring vector is as follows:

[0052] [vec{v}_{global}=vec{v}_{run}odotvec{v}_{attn}];

[0053] where (odot) represents the element-wise multiplication operation.

[0054] That is, [vec{v}_{global}

[0055] =[0*0.2, 0.43*0.8, 0.33*0.7, 0.3*0.3]

[0056] =[0, 0.344, 0.231, 0.09]]。

[0057] The global status monitoring vector provides a more comprehensive and focused description of the device status. It can be used for the comprehensive evaluation of the device status at the level of the entire campus Internet of Things system. For example, in the comparison of the status of multiple devices, through the global status monitoring vector, it can be determined which devices require more attention or adjustment in terms of energy consumption, and which devices are operating relatively normally and meet the expectations.

[0058] The first operating energy consumption quantization vector is a quantitative representation of the operating energy consumption of campus Internet of Things devices. It contains the energy consumption information of each device or device group.

[0059] For example, there are three main energy-consuming devices in the campus: an intelligent lighting system, air conditioning equipment, and a projector. The energy consumption of the intelligent lighting system is 0.2 kWh, the energy consumption of the air conditioning equipment is 1.5 kWh, and the energy consumption of the projector is 0.3 kWh. Then the first operating energy consumption quantization vector is [vec{v}_{energy}=[0.2, 1.5, 0.3]]. Each element in the present invention corresponds to the energy consumption of a device.

[0060] The first operating energy consumption quantization vector is an important basis for campus energy consumption management. By analyzing the first operating energy consumption quantization vector, it is possible to intuitively understand the contribution of different devices in terms of energy consumption. For example, it can be found that the air conditioning equipment is a major energy consumer, so optimization measures for the air conditioning equipment, such as adjusting the temperature setting and optimizing the operating time, are key considerations in the energy consumption adjustment strategy.

[0061] The energy consumption adjustment auxiliary information is an information set that combines the first operating energy consumption quantization vector with the global status monitoring vector (of multiple devices).

[0062] For example, in addition to the above-mentioned air conditioning equipment, there are also relevant vectors for the intelligent lighting system and the projector.

[0063] The global status monitoring vector of the intelligent lighting system is:

[0064] [vec{v}_{global - light}=[0.1, 0.2, 0.15, 0.05]]。

[0065] The global status monitoring vector of the projector is:

[0066] [vec{v}_{global - proj}=[0.3, 0.1, 0.2, 0.1]]. Then the energy consumption adjustment auxiliary information can be expressed in a matrix form:

[0068] begin{bmatrix}

[0069] 0.2&1.5&0.3

[0070] 0&0.344&0.231&0.09

[0071] 0.1&0.2&0.15&0.05

[0072] 0.3&0.1&0.2&0.1

[0073] end{bmatrix}

[0075] The first row in the above matrix form is the first running energy consumption quantization vector, and the subsequent rows are the global state monitoring vectors of the air conditioner, intelligent lighting system, and projector respectively.

[0076] The energy consumption regulation auxiliary information provides a comprehensive data basis for energy consumption regulation analysis. It combines energy consumption information with the comprehensive state information of devices, and can use various data analysis methods (such as data mining, machine learning algorithms) to explore the relationship between device energy consumption and state, thereby generating effective energy consumption regulation optimization strategies. For example, clustering analysis can be used to classify devices according to energy consumption and state characteristics, and different energy consumption regulation strategies can be formulated for different categories of devices.

[0077] The present invention first determines a target state monitoring data set to indicate the target IoT device monitoring behavior event with the highest priority, and can accurately focus on the most critical or urgent device conditions in the campus IoT system. This helps to quickly locate the part that has the greatest impact on the overall campus IoT operation among numerous device monitoring events, avoiding the indiscriminate treatment of all device states, thereby improving the pertinence and efficiency of campus IoT device management. For example, during teaching activities, it is possible to give priority to ensuring the normal operation of core teaching devices (such as projectors, teaching computers, etc.) in smart classrooms, reducing the risk of teaching interruption caused by device failures or abnormalities.

[0078] ​​Secondly, the process of mining the state vector, refining the state monitoring attention vector, and then combining them to obtain the global state monitoring vector realizes a more comprehensive, detailed, and focused quantitative description of the device operation state. On the one hand, state vector mining can deeply explore the hidden information in the device operation state data, convert complex device state data into a quantifiable and analyzable vector form, and provide a unified mathematical model basis for subsequent analysis. On the other hand, the refinement of the state monitoring attention vector enables different attention weights to be given to different device state characteristics according to actual needs during the analysis process, such as the importance of the device, current task requirements, or key points of energy consumption management. The combined global state monitoring vector synthesizes the device state and the focus of attention, which can not only more accurately reflect the actual operation status of the device but also make more reasonable comparisons and evaluations between different devices, providing a more reliable basis for the optimized management of the overall campus Internet of Things system.

[0079] Furthermore, the identification of operating energy consumption obtains the first operating energy consumption quantization vector, and combining it with the global state monitoring vector to obtain the energy consumption adjustment auxiliary information. This process provides comprehensive and effective data support for the energy consumption management of campus Internet of Things devices. The first operating energy consumption quantization vector intuitively reflects the energy consumption of each device, enabling targeted energy consumption management. After combining it with the global state monitoring vector, the energy consumption adjustment auxiliary information can closely link the device operation state with energy consumption, fully considering the impact of various device operation state characteristics on energy consumption. This helps to discover the potential relationship between device energy consumption and operation state, such as the energy consumption change law of the device under different power, operation duration, working modes, etc.

[0080] Finally, based on the energy consumption adjustment auxiliary information, energy consumption adjustment analysis is carried out and the target energy consumption adjustment optimization strategy is generated, which can achieve precise energy consumption control of campus Internet of Things devices. Through comprehensive analysis of a large amount of data, the generated target energy consumption adjustment optimization strategy can formulate personalized and precise energy-saving measures according to the actual operation state and energy consumption of different devices. This not only helps to reduce the energy consumption of the campus and operating costs but also improves the energy utilization efficiency on the premise of ensuring the normal operation of campus Internet of Things devices, achieving the goal of energy conservation and emission reduction, which meets the pursuit of green and sustainable development in modern campuses.

[0081] In a possible embodiment, the combination of the first running energy consumption quantization vector and several of the global state monitoring vectors to obtain energy consumption regulation auxiliary information includes: respectively determining the data involvement weights of each of the device state monitoring data sets, and using the data involvement weights to combine the global state monitoring vectors corresponding to each of the device state monitoring data sets to obtain a first state monitoring combined vector; combining the first running energy consumption quantization vector, the first state monitoring combined vector, and the global state monitoring vector corresponding to the target state monitoring data set to obtain energy consumption regulation auxiliary information.

[0082] Further, if the target energy consumption regulation optimization strategy is generated by a first energy consumption regulation decision algorithm, then the combination of the first running energy consumption quantization vector, the first state monitoring combined vector, and the global state monitoring vector corresponding to the target state monitoring data set to obtain energy consumption regulation auxiliary information includes: obtaining regulation requirement information for guiding the first energy consumption regulation decision algorithm to generate an energy consumption regulation optimization strategy; refining a regulation requirement vector of the regulation requirement information, and combining the first running energy consumption quantization vector, the regulation requirement vector, the first state monitoring combined vector, and the global state monitoring vector corresponding to the target state monitoring data set to obtain energy consumption regulation auxiliary information.

[0083] In a campus Internet of Things system, the influence degrees of different device state monitoring data sets on overall energy consumption regulation are different. For example, for an intelligent lighting system, the two data features of its brightness value and on-time may have a relatively large impact on energy consumption, while for a temperature sensor, although the temperature data collected by it is somewhat related to energy consumption, the degree of association is relatively small. Therefore, it is necessary to determine the data involvement weights of each device state monitoring data set.

[0084] Taking the intelligent lighting system as an example, for instance, it includes three data features: brightness value (ranging from 0 to 1000 lux), on-time (in hours), and number of switchings. Through the analysis of historical energy consumption data and device operation data, it is found that the brightness value has a linear relationship with energy consumption, with a coefficient of 0.6 (that is, for every 100 lux increase in the brightness value, the energy consumption increases by 0.6 kWh, and this relationship in the present invention is obtained by fitting a large amount of data); the on-time has an exemplary proportional relationship with energy consumption, with a coefficient of 1 (that is, for every 1 hour of operation, the energy consumption increases by 1 kWh); the number of switchings has a relatively small impact on energy consumption, with a coefficient of 0.1 (each switching consumes an additional 0.1 kWh). In order to convert these coefficients into weights, normalization processing is required. For example, through calculation, the data involvement weight of the brightness value is 0.4, the data involvement weight of the on-time is 0.5, and the data involvement weight of the number of switchings is 0.1.

[0085] For other devices, such as air conditioning systems, data characteristics such as their set temperature (ranging from 16 to 30 degrees Celsius), operating power (ranging from 500 to 2000 watts), and fan speed (ranging from 500 to 1500 revolutions per minute) also have their respective data involvement weights. The set temperature has a greater impact on energy consumption. Through analyzing historical data, its coefficient is 0.5 (for example, for every 1-degree Celsius decrease in temperature, the energy consumption decreases by 0.5 kWh). The operating power has a direct proportional relationship with energy consumption, with a coefficient of 1 (operating at 1000 watts for 1 hour consumes 1 kWh). The fan speed has a relatively small impact on energy consumption, with a coefficient of 0.1 (for every 100 revolutions per minute increase in speed, the energy consumption increases by 0.1 kWh). After normalization, the data involvement weight of the set temperature is 0.45, the data involvement weight of the operating power is 0.5, and the data involvement weight of the fan speed is 0.05.

[0086] For example, the global state monitoring vector of the intelligent lighting system is (\(\vec{v}_{global - light}=[0.3, 0.2, 0.1]\)) (the elements of the present invention respectively correspond to the state values after processing the brightness value, the on - time duration, and the number of switch - on times). According to the data involvement weights determined above, the combined calculation method is as follows:

[0087] New combined value:

[0088] (\(v_{new - light}=0.4*0.3 + 0.5*0.2+0.1*0.1 = 0.23\))

[0089] For the air conditioning system, its global state monitoring vector is:

[0090] (\(\vec{v}_{global - air}=[0.2, 0.3, 0.1]\)) (the elements of the present invention respectively correspond to the state values after processing the set temperature, the operating power, and the fan speed). The combined calculation is:

[0091] (\(v_{new - air}=0.45*0.2 + 0.5*0.3+0.05*0.1 = 0.245\))

[0092] After combining all devices in this way, the first - stage state monitoring combined vector is obtained. For example, if there are only an intelligent lighting system and an air conditioning system in a campus, the first - stage state monitoring combined vector may be ([0.23, 0.245]).

[0093] During the energy consumption regulation process, there are different regulation requirements. For example, from the perspective of energy cost control, it may be desired to reduce the overall energy consumption by 30% without affecting the basic teaching needs; from the perspective of the service life of the equipment, it may be desired to reduce the high - power operating time of the equipment. These regulation requirement information needs to be quantified.

[0094] For example, the adjustment demand information from the perspective of energy cost control is to reduce the overall energy consumption by 30%, and the adjustment demand information from the perspective of equipment service life is to reduce the operation time of high-power operating equipment (such as air conditioners) by 20%. For the energy cost control demand, it can be quantified as a vector element. For example, if the set reduction ratio of energy consumption is between 0 and 1 (1 represents a 100% reduction), then this element is 0.3. For the demand of reducing the equipment operation time, a similar quantification is also carried out. For example, the reduction ratio of the operation time of high-power operating equipment is between 0 and 1, and in the present invention, it is 0.2. Combining them, the adjustment demand vector is (\(\vec{v}_{req} = [0.3, 0.2]\)).

[0095] Another example is that the first running energy consumption quantification vector (\(\vec{v}_{energy} = [0.2, 1.5]\)) has been obtained (in the present invention, for example, the energy consumption of the intelligent lighting system is 0.2 degrees of electricity, and the energy consumption of the air conditioning system is 1.5 degrees of electricity), the first state monitoring combined vector (\(\vec{v}_{first - comb} = [0.23, 0.245]\)), and the global state monitoring vector corresponding to the target state monitoring data set (for example, the target device is the air conditioning system, and its global state monitoring vector is:

[0096] (\(\vec{v}_{global - air - target} = [0.2, 0.3, 0.1]\))). And, the adjustment demand vector is (\(\vec{v}_{req} = [0.3, 0.2]\)).

[0097] The combination method of the energy consumption adjustment auxiliary information can be to arrange these vectors in a certain order to form a new vector or matrix. For example, form a matrix (\(M\)):

[0099] \(M=\begin{bmatrix}

[0100] 0.2&1.5

[0101] 0.23&0.245

[0102] 0.2&0.3&0.1

[0103] 0.3&0.2

[0104] \end{bmatrix}

[0106] ​​This matrix (M) is the auxiliary information for energy consumption regulation. Each row represents different information (the first row is the first operating energy consumption quantization vector, the second row is the first state monitoring combined vector, the third row is the global state monitoring vector corresponding to the target state monitoring data set, and the fourth row is the regulation demand vector). Through this combination method, energy consumption-related information, equipment state information, and regulation demand information are integrated together, providing a comprehensive data basis for subsequent energy consumption regulation analysis.

[0107] Furthermore, the first energy consumption regulation decision algorithm can be based on the linear programming algorithm. For example, the goal is to optimize the operating parameters of the equipment (such as the brightness and on-time of the intelligent lighting system, the set temperature and operating power of the air conditioning system) on the premise of meeting the requirements in the regulation demand vector (such as a 30% reduction in energy consumption and a 20% reduction in the high-power operating time of the equipment).

[0108] Let the brightness of the intelligent lighting system be (x_1) (the value range is 0 - 1000 lux), and the on-time be (x_2) (in hours); the set temperature of the air conditioning system be (y_1) (the value range is 16 - 30 °C), and the operating power be (y_2) (the value range is 500 - 2000 W).

[0109] According to the energy consumption relationship, the energy consumption function of the intelligent lighting system is:

[0110] (E_{light}=a_1x_1+b_1x_2); ((a_1) and (b_1) are coefficients obtained from the previous analysis. For example, (a_1 = 0.006) kWh / lux, (b_1 = 1) kWh / hour), and the energy consumption function of the air conditioning system is (E_{air}=a_2y_1+b_2y_2) (for example, (a_2=-0.5) kWh / °C, (b_2 = 0.001) kWh / W. The positive and negative signs of the coefficients in the present invention indicate the relationship with the increase and decrease of energy consumption).

[0111] The regulation demand constraint conditions include: the overall energy consumption (E = E_{light}+E_{air}) should satisfy (Eleqslant(1 - 0.3)(E_{light - original}+E_{air - original})) (where (E_{light - original}) and (E_{air - original}) are the original energy consumptions), and the high-power operating time of the air conditioning system (T_{air - high}) should satisfy (T_{air - high}leqslant(1 - 0.2)T_{air - high - original}).

[0112] Meanwhile, there are also constraint conditions for the operating status of the devices. For example, the brightness (x_1) of the intelligent lighting system should meet the teaching visibility requirements (e.g., the minimum brightness is 300 lux), and the set temperature (y_1) of the air conditioning system should meet the human comfort requirements (e.g., 18 - 26 degrees Celsius), etc.

[0113] By solving this linear programming problem, the optimal operating parameters of the intelligent lighting system and the air conditioning system can be obtained. For example, (x_1 = 400) lux, (x_2 = 1.5) hours, (y_1 = 22) degrees Celsius, (y_2 = 1000) watts. These parameter combinations are the target energy consumption regulation optimization strategies.

[0114] Designed in this way, first, by determining the data - involved weights to combine the global status monitoring vectors to obtain the first - stage status monitoring combined vector, it can more reasonably synthesize the impact of the status of each device on energy consumption, avoid equal treatment of the status characteristics of different devices, and make the integration of device status information and energy consumption relationship more in line with the actual situation. For example, by accurately quantifying the weights of the status characteristics of the intelligent lighting system and the air conditioning system, it can accurately reflect their different contributions to energy consumption. Secondly, by combining the adjustment demand information to obtain the energy consumption regulation auxiliary information, it comprehensively integrates energy - consumption - related, device status, and adjustment demand, providing rich and targeted data basis for energy consumption regulation decision - making. Finally, using the first - stage energy consumption regulation decision - making algorithm to generate the target energy consumption regulation optimization strategy, such as based on the linear programming algorithm, it can accurately optimize the device operating parameters under various constraint conditions (energy consumption reduction, equipment service life protection, etc.), effectively reduce energy consumption, improve the equipment operating efficiency, and achieve intelligent and precise energy consumption management of campus Internet - of - Things devices.

[0115] Under some preferred design ideas, the state vector mining of the campus Internet - of - Things operation status log is respectively carried out according to the target status monitoring data set and each device status monitoring data set to obtain several Internet - of - Things operation status vectors, including: performing pyramid state vector mining on the campus Internet - of - Things operation status log to obtain the pyramid operation status vector of the campus Internet - of - Things operation status log; respectively performing feature down - sampling on the pyramid operation status vector according to the target status monitoring data set and each device status monitoring data set to obtain several pyramid down - sampling vectors; respectively performing interaction on each pyramid down - sampling vector to obtain several Internet - of - Things operation status vectors.

[0116] In the next possible specific steps, interact with each of the pyramid downsampling vectors to obtain a number of IoT operation state vectors, including: for any one of the pyramid downsampling vectors, adjust the local state vectors of each feature depth in the pyramid downsampling vector to obtain a number of hidden state vectors with the same size, interact the hidden state vectors to obtain an interaction state vector; perform feature fully connected on each of the interaction state vectors to obtain a number of IoT operation state vectors.

[0117] To facilitate the understanding of the above technical solution, first introduce the pyramid state vector mining principle. When processing the campus IoT operation state log, pyramid state vector mining is an effective data processing method. It is similar to the pyramid structure in image processing, and obtains comprehensive operation state information by analyzing data at different levels.

[0118] For example, the campus IoT operation state log contains the state data of multiple devices at different time points. For example, for the intelligent lighting system, there are data such as the brightness and switch state of each lamp, and for the air conditioning system, there are data such as temperature setting and operating power. These data are recorded in chronological order to form a large-scale data set.

[0119] Pyramid state vector mining first performs hierarchical processing on this large-scale data set. At the bottom layer, there is the most primitive and detailed device state data. As the level increases, the abstraction degree of the data gradually increases. For example, the bottom layer data may be the lighting brightness value per minute, the upper layer may be the average brightness value per ten minutes, and the further upper layer may be the brightness trend data per hour, etc.

[0120] Through this hierarchical processing, data at different levels can capture the device operation state characteristics at different time scales and abstraction degrees. For example, the bottom layer data can reflect the instantaneous changes in the device state, while the upper layer data can reflect the long-term trends of the device operation.

[0121] The finally obtained pyramid operation state vector is a vector that synthesizes information at different levels, and it can comprehensively describe the operation state of campus IoT devices. For example, this vector may contain different level information such as the long-term trend value of the brightness of the intelligent lighting system and the power fluctuation range of the air conditioning system, which is represented in numerical form, such as [0.3 (long-term trend value of lighting brightness), 0.5 (power fluctuation range of air conditioning),...].

[0122] Based on the above content, for the target state monitoring data set, for example, taking the air conditioning system as an example, if the target state monitoring data set focuses on the energy consumption related states of the air conditioning (such as operating power, operating duration, etc.), then perform feature downsampling on the pyramid operation state vector according to this data set.

[0123] Feature downsampling is a method of data dimensionality reduction. For example, the part related to the air conditioning system in the pyramid operating state vector contains 10 features (such as power values at different time scales, operating durations in different modes, etc.). Through feature downsampling, according to the requirements of the target state monitoring data set, the three most relevant features may be selected (such as average operating power, operating duration during peak hours, total operating duration), and these three features are resampled to make them more in line with the requirements of subsequent analysis in terms of numerical range and data density.

[0124] For other device state monitoring data sets, such as the data set of the intelligent lighting system, if the states related to the lighting usage efficiency are focused on (such as brightness utilization rate, relationship between switching frequency and energy consumption, etc.), a similar feature downsampling operation is also performed. For example, the intelligent lighting system has 8 relevant features in the pyramid operating state vector. After downsampling, 2 key features are selected (such as average brightness utilization rate, relationship value between switching frequency and energy consumption) and resampled.

[0125] In this way, several pyramid downsampled vectors are obtained respectively based on the target state monitoring data set and each device state monitoring data set. Each pyramid downsampled vector focuses on the key features concerned by the corresponding data set, and has undergone data dimensionality reduction and resampling for subsequent analysis.

[0126] Furthermore, for any pyramid downsampled vector, for example, taking the pyramid downsampled vector of the air conditioning system obtained before as an example, it contains features such as average operating power, operating duration during peak hours, total operating duration, etc. These features are at different feature depths in the vector.

[0127] For example, the position of the average operating power in the vector is represented as depth 1, the operating duration during peak hours is represented as depth 2, and the total operating duration is represented as depth 3. Adjust these local state vectors at different depths.

[0128] Taking the average operating power as an example, if its numerical range is 500 - 2000 watts, in order to better interact with other features, it may be adjusted to the numerical range of 0 - 1 through the formula (x'=(x - min) / (max - min)) (where (x) is the original value, (x') is the adjusted value, (min) is the minimum value, (max) is the maximum value). For example, if the average operating power is 1000 watts, then the adjusted value is ((1000 - 500) / (2000 - 500)=0.33).

[0129] Similar adjustments are also made to the operation duration during peak hours and the total operation duration to obtain several hidden state vectors with consistent sizes (the same numerical range and data type). For example, after adjustment, the value of the hidden state vector corresponding to the operation duration during peak hours is 0.4, and the value of the hidden state vector corresponding to the total operation duration is 0.5.

[0130] Next, the hidden state vectors are interacted with each other. An exemplary interaction method can be to connect them in a certain order. For example, the hidden state vectors corresponding to the adjusted average operation power, operation duration during peak hours, and total operation duration of the air conditioning system are connected to obtain an interaction state vector [0.33, 0.4, 0.5]. This interaction state vector synthesizes the information of different key features after downsampling of the air conditioning system, and through adjustment and connection, enables this information to be represented and analyzed in a unified vector.

[0131] Finally, full connection of features is performed on each interaction state vector. For example, for the interaction state vector [0.33, 0.4, 0.5] of the air conditioning system and the interaction state vector of the intelligent lighting system (for example, [0.2, 0.3]), there are multiple ways to perform full connection of features.

[0132] One way is to directly splice them into a new vector to obtain [0.33, 0.4, 0.5, 0.2, 0.3]. This new vector is the Internet of Things operation state vector. This vector comprehensively contains the key state information of different devices (in this invention, the air conditioning system and the intelligent lighting system) after operations such as pyramid downsampling, local state vector adjustment, and interaction, and can provide a comprehensive data basis for subsequent energy consumption analysis, equipment state assessment, etc.

[0133] Designed in this way, first, the pyramid operation state vector is obtained by mining the pyramid state vector, which can analyze the operation state of campus Internet of Things devices from different levels and capture various information from instantaneous changes to long-term trends, such as the brightness change level information of the intelligent lighting system and the power fluctuation level information of the air conditioning system. Secondly, the pyramid downsampling vector is obtained by performing feature downsampling based on different data sets. By focusing on key features and performing data dimensionality reduction and resampling, the data processing volume is reduced, and at the same time, the important information related to the specific device state is highlighted, improving the efficiency and accuracy of subsequent analysis. Finally, the interaction operations of the pyramid downsampling vector, including local state vector adjustment, hidden state vector interaction, and full connection of features to obtain the Internet of Things operation state vector, enable the effective integration of the key state information of different devices, which is comprehensively represented in a unified vector, facilitating operations such as energy consumption analysis and equipment state assessment, and contributing to the refined management and optimized operation of campus Internet of Things devices.

[0134] In some technical solutions, obtaining the device status monitoring data sets corresponding to each pre-screened IoT device monitoring behavior event in the campus IoT operation status log and determining the target status monitoring data set from several of the device status monitoring data sets includes: obtaining the campus IoT operation status log and the index information of the campus IoT operation status log, where the campus IoT operation status log includes several pre-screened IoT device monitoring behavior events, and the index information is used to indicate the target IoT device monitoring behavior event with the highest priority among the several pre-screened IoT device monitoring behavior events; disassembling the campus IoT operation status log to obtain the device status monitoring data sets corresponding to each of the pre-screened IoT device monitoring behavior events, and determining the target status monitoring data set from each of the device status monitoring data sets according to the index information.

[0135] Specifically, determining the target status monitoring data set from each of the device status monitoring data sets according to the index information includes: when the index information is the first type of index, determining the target status monitoring data set from each of the device status monitoring data sets according to the relative distribution characteristics between the first type of index and each of the device status monitoring data sets; or, when the index information is the second type of index, determining the target status monitoring data set from each of the device status monitoring data sets according to the relevance between the second type of index and the key value characteristics of each of the device status monitoring data sets; or, when the index information is the third type of index, determining the target status monitoring data set from each of the device status monitoring data sets according to the relevance between the third type of index and each of the device status monitoring data sets.

[0136] In the present invention, the detailed implementation steps of the above technical solution are as follows.

[0137] (1) Obtaining the campus IoT operation status log and index information and disassembling the log to obtain the device status monitoring data set

[0138] 1) Obtaining the campus IoT operation status log and index information

[0139] The campus IoT operation status log is a detailed record of the operation of the entire campus IoT devices. It contains numerous pre-screened IoT device monitoring behavior events. For example, in the campus IoT environment, the devices include those in smart classrooms (such as projectors, intelligent lighting systems, air conditioners, etc.), environmental sensors (temperature, humidity, light sensors, etc.). Various monitoring behavior events during the operation of these devices, such as the turning on and off of projectors, brightness adjustment, changes in the light brightness of the intelligent lighting system, switch operations, changes in the temperature setting of air conditioners, operation mode switching, etc., will be recorded in the campus IoT operation status log.

[0140] Meanwhile, there is also index information related to this log. This index information plays a crucial role as it can indicate the target IoT device monitoring behavior event with the highest priority among several preliminarily screened IoT device monitoring behavior events. For example, the index information may determine the priority based on factors such as the importance of the device and the current urgency. For teaching activities, events related to the projector during an important teaching demonstration may have a higher priority; in hot weather, events related to a refrigeration failure in the air conditioning system also have a high priority.

[0141] 2) Disassemble the campus IoT operation status log to obtain the device status monitoring dataset

[0142] Disassembling the campus IoT operation status log is to obtain the device status monitoring dataset corresponding to each preliminarily screened IoT device monitoring behavior event. Taking the intelligent lighting system as an example, its device status monitoring dataset may contain multiple data elements. For example, the light brightness value (the value range may be 0 - 1000 lux), the on duration (in minutes), the number of switch operations, etc. For example, within a certain time period, the light brightness value is 300 lux, the on duration is 60 minutes, and the number of switch operations is 3 times. Then the device status monitoring dataset of this intelligent lighting system during this time period is {brightness: 300 lux, duration: 60 minutes, number of switch operations: 3 times}.

[0143] For the air conditioning system, the device status monitoring dataset may include the set temperature (for example, the value range is 16 - 30 degrees Celsius), the operating power (for example, the value range is 500 - 2000 watts), the operating mode (cooling, heating, ventilation, etc., which can be represented by numerical values, such as 0 for cooling, 1 for heating, 2 for ventilation), etc. If the set temperature of the air conditioner is 22 degrees Celsius, the operating power is 1000 watts, and the operating mode is cooling, then its device status monitoring dataset is {temperature: 22 degrees Celsius, power: 1000 watts, mode: 0}.

[0144] (2) Determine the target status monitoring dataset according to different types of indexes

[0145] 1) When the index information is the first type of index

[0146] There is a relationship of relative distribution characteristics between the first type of index and each device status monitoring dataset. For example, the first type of index determines the priority based on the usage frequency of the device. For example, in the campus IoT, the usage frequency of the device can be determined by counting the number of usage times within a certain time range (such as one day, one week, or one month).

[0147] Taking the intelligent lighting system and the projector as examples, if the intelligent lighting system is used 100 times within a week and the projector is used 30 times. The usage times can be normalized. For example, the maximum usage times of all devices on campus is 200 times. Then the normalized usage frequency of the intelligent lighting system is 0.5, and the normalized usage frequency of the projector is 0.15.

[0148] Each device status monitoring data set has a relative distribution characteristic with this first type of index based on usage frequency. For example, some data elements in the device status monitoring data set may have a direct or indirect relationship with the usage frequency. For the intelligent lighting system, the on - duration and the number of switch - ons in its device status monitoring data set may have a strong correlation with the usage frequency. If the on - duration is long and the number of switch - ons is large, it usually means a high usage frequency.

[0149] Determine the target status monitoring data set according to this relative distribution characteristic. For example, there are device status monitoring data sets of multiple devices. Through analysis, it is found that the distribution characteristic of the data elements related to the usage frequency in the device status monitoring data set of the intelligent lighting system most conforms to the first type of index (priority based on usage frequency). Then the device status monitoring data set of the intelligent lighting system will be determined as the target status monitoring data set.

[0150] 2) When the index information is the second type of index

[0151] There is a correlation between the second type of index and the key - value characteristics of each device status monitoring data set. For example, the second type of index determines the priority based on the failure risk level of the device. The failure risk level may be determined according to factors such as the device's historical failure data and current operating status.

[0152] Taking the air - conditioning system and the environmental sensor as examples, the key - value characteristics of the device status monitoring data set of the air - conditioning system may include temperature setting, operating power, etc. The key - value characteristics of the device status monitoring data set of the environmental sensor may include the collected data values, collection frequency, etc.

[0153] For example, an air conditioning system is determined to have a high failure risk level based on its historical failure data and current operating status (such as large fluctuations in operating power, frequent adjustment of set temperature, etc.). The key-value features of its equipment status monitoring dataset (such as fluctuations in operating power, amplitude of temperature setting adjustment, etc.) are associated with the second type of index based on the failure risk level. If this association is the strongest among all devices, for example, the operating power fluctuation of the air conditioning system exceeds 30% of the normal range (e.g., the normal fluctuation range is 10%), and the amplitude of temperature setting adjustment exceeds 5 degrees Celsius within a short period (e.g., the normal adjustment amplitude is 1 - 2 degrees Celsius), while other devices do not have similar obvious changes in key-value features related to the failure risk level, then the equipment status monitoring dataset of the air conditioning system will be determined as the target status monitoring dataset based on this association.

[0154] 3) When the index information is the third type of index

[0155] There is an association between the third type of index and each equipment status monitoring dataset. For example, the third type of index determines the priority based on the degree of influence of the device on the overall operation of the campus Internet of Things.

[0156] Consider the intelligent lighting system, air conditioning system, and network server in the campus Internet of Things (the network server is also part of the Internet of Things devices and is responsible for functions such as data transmission). The intelligent lighting system mainly affects the lighting environment in the classroom, the air conditioning system affects the indoor temperature environment, and once there is a problem with the network server, it may affect the data transmission and interaction between all campus Internet of Things devices.

[0157] The equipment status monitoring dataset of the network server may include data elements such as network bandwidth utilization rate and data transmission delay. If the network bandwidth utilization rate of the network server reaches 90% (e.g., the normal utilization rate is 60% - 70%), and the data transmission delay increases by 50% (e.g., the normal delay fluctuation range is 10% - 20%), this indicates that its equipment status monitoring dataset has a strong association with the third type of index based on the degree of influence on the overall operation of the campus Internet of Things. In contrast, the influence of the intelligent lighting system and the air conditioning system on the overall operation of the Internet of Things is not as large as that of the network server in the current state, so the equipment status monitoring dataset of the network server will be determined as the target status monitoring dataset based on this association.

[0158] In this way, by obtaining the operation status logs of the campus Internet of Things and their index information, the priority of device monitoring behavior events can be determined, providing a basis for subsequent precise processing. For example, the priority is determined based on factors such as device usage frequency, failure risk level, or the degree of impact on the overall operation. For instance, the high priority of a network server is determined according to its network bandwidth utilization rate and data transmission latency. Secondly, by disassembling the logs to obtain the device status monitoring data set, the operation status of each device can be analyzed in detail, such as data elements like the brightness and duration of the intelligent lighting system. Finally, by determining the target status monitoring data set based on different types of indexes, the data set of key devices can be accurately found according to specific index types (usage frequency, failure risk, overall impact, etc.), which helps to concentrate resources on handling matters related to key devices and improve the efficiency and pertinence of campus Internet of Things device management.

[0159] In the actual application process, the target energy consumption regulation and optimization strategy can be generated by the first energy consumption regulation decision algorithm. Based on this, the debugging steps of the first energy consumption regulation decision algorithm include the following contents:

[0160] (1) Obtain the historical Internet of Things operation status logs and the second monitoring data set samples corresponding to the historical Internet of Things device monitoring behavior events in the historical Internet of Things operation status logs. Disassemble the historical Internet of Things operation status logs to obtain the first monitoring data set samples corresponding to each frequent Internet of Things device behavior event in the historical Internet of Things operation status logs, where the historical Internet of Things device monitoring behavior event is an Internet of Things device monitoring behavior event among several frequent Internet of Things device behavior events;

[0161] (2) Refine the second operation energy consumption quantization vector of the historical Internet of Things operation status logs. Conduct state vector mining on the historical Internet of Things operation status logs respectively based on the second monitoring data set samples and each of the first monitoring data set samples to obtain several historical operation state vectors, and refine the historical monitoring attention vectors corresponding to the second monitoring data set samples and each of the first monitoring data set samples;

[0162] (3) Combine the second operation energy consumption quantization vector, the historical operation state vectors, and the historical monitoring attention vectors and input them into the first energy consumption regulation decision algorithm for energy consumption regulation analysis to generate an energy consumption regulation heat map, where the energy consumption regulation heat map is used to determine the energy consumption regulation and optimization strategy for the historical Internet of Things device monitoring behavior event;

[0163] (4) Obtain the first energy consumption regulation optimization strategy for the historical energy consumption regulation tasks configured in the historical Internet of Things operation status log. Determine the algorithm training error based on the energy consumption regulation heat map and the first energy consumption regulation optimization strategy, and debug the first energy consumption regulation decision algorithm based on the algorithm training error, where the historical energy consumption regulation task is used to indicate the historical Internet of Things device monitoring behavior events.

[0164] Exemplarily, the implementation method of the debugging steps of the first energy consumption regulation decision algorithm is as follows.

[0165] (I) Obtain historical data and disassemble the log to obtain the monitoring data set samples

[0166] 1) Obtain the historical Internet of Things operation status log and the second monitoring data set samples and disassemble the log

[0167] The historical Internet of Things operation status log is a record of the operation status of campus Internet of Things devices over a period of time in the past. It contains rich information, such as various monitoring behavior events of the devices. For example, for the devices in a smart classroom, it includes the opening duration and brightness adjustment times of the projector, the brightness change and switch-on time of the intelligent lighting system, as well as the temperature setting and operating power of the air conditioning system, etc.

[0168] Obtain the second monitoring data set samples corresponding to the historical Internet of Things device monitoring behavior events from the historical Internet of Things operation status log. Taking the air conditioning system as an example, this sample may include a set of data within a specific time period, such as the set temperature (the value range is 16 - 30 degrees Celsius, for example, the set temperature value is 22 degrees Celsius within a certain period), the operating power (the value range is 500 - 2000 watts, for example, the power at a certain moment is 1000 watts), the operating mode (such as cooling, heating, ventilation, and in the present invention, it is the cooling mode), etc.

[0169] Disassemble the historical Internet of Things operation status log to obtain the first monitoring data set samples corresponding to each frequent Internet of Things device behavior event. Frequent Internet of Things device behavior events are device behavior events that often appear in historical records. For example, for the frequent switching behavior of the intelligent lighting system, its first monitoring data set samples may include the time interval between each switch (for example, it is 30 minutes) and the brightness value at each turn-on (for example, it is 500 lux), etc. The historical Internet of Things device monitoring behavior event is a specific event among several frequent Internet of Things device behavior events, for example, it is the monitoring event of the cooling behavior of the air conditioning system within a specific time period.

[0170] (II) Refine the operation energy consumption quantization vector and related vectors

[0171] 1) Refine the second operation energy consumption quantization vector

[0172] Extract the second operating energy consumption quantization vector from the historical IoT operation status log. Taking the intelligent lighting system, air conditioning system, and projector in the campus as examples, for instance, the power of the intelligent lighting system is 100 watts and the operating duration is 2 hours. According to the energy consumption calculation formula (E = P * t) ((E) is the energy consumption, (P) is the power, and (t) is the time), its energy consumption is 100 watts × 2 hours = 0.2 kWh; the power of the air conditioning system is 1500 watts and it operates for 1 hour, with an energy consumption of 1.5 kWh; the power of the projector is 300 watts and it operates for 1.5 hours, with an energy consumption of 0.45 kWh. Then the second operating energy consumption quantization vector is [0.2, 1.5, 0.45], and this vector represents the energy consumption of different devices during historical operation.

[0173] 2) State vector mining and extraction of historical monitoring attention vectors

[0174] Perform state vector mining on the historical IoT operation status log based on the second monitoring dataset samples and each first monitoring dataset sample respectively. Taking the second monitoring dataset sample of the air conditioning system as an example, if it contains three data elements: set temperature, operating power, and operating mode, these data can be quantized to form a state vector. For example, the set temperature is 22 degrees Celsius, which is quantized to 0.4 (by mapping the actual temperature value to the 0 - 1 interval, and the calculation method is ((22 - 16) / (30 - 16))), the operating power is 1000 watts, which is quantized to 0.33 (the calculation method is ((1000 - 500) / (2000 - 500))), and the operating mode is cooling, represented by 0. Then the state vector of the air conditioning system is [0.4, 0.33, 0].

[0175] Similar state vector mining is also performed for each first monitoring dataset sample. For example, for the first monitoring dataset sample corresponding to the frequent switching behavior of the intelligent lighting system, if it contains two data elements: switching time interval and on - brightness value, a state vector is obtained after quantization. For example, the switching time interval is 30 minutes, which is quantized to 0.5 (for example, the maximum time interval is 60 minutes, and the calculation method is (30 / 60)), and the on - brightness value is 500 lux, which is quantized to 0.5 (for example, the brightness value range is 0 - 1000 lux, and the calculation method is (500 / 1000)). Then the state vector of the intelligent lighting system is [0.5, 0.5].

[0176] Meanwhile, extract the second monitoring dataset samples and the historical monitoring attention vectors corresponding to each first monitoring dataset sample. For the second monitoring dataset samples of the air conditioning system, if the current focus is on the impact of operating power and set temperature on energy consumption, then the attention weight for operating power is 0.6, the attention weight for set temperature is 0.4, and the attention weight for operating mode is 0.1 (relatively small because the impact of operating mode is relatively weak in energy consumption analysis), so the historical monitoring attention vector is [0.4, 0.6, 0.1]. For the first monitoring dataset samples of the intelligent lighting system, if the focus on the impact of switch time interval on energy consumption is greater than the on-brightness value, for example, the attention weight for switch time interval is 0.7 and the attention weight for on-brightness value is 0.3, then the historical monitoring attention vector is [0.7, 0.3].

[0177] (III) Combine data input algorithm to generate energy consumption regulation heat map

[0178] 1) Combine data and input algorithm

[0179] Combine the second operating energy consumption quantization vector, historical operating state vector, and historical monitoring attention vector and input them into the first energy consumption regulation decision algorithm for energy consumption regulation analysis. For example, combine the previously obtained second operating energy consumption quantization vector [0.2, 1.5, 0.45], the historical operating state vector [0.4, 0.33, 0] and historical monitoring attention vector [0.4, 0.6, 0.1] of the air conditioning system, and the historical operating state vector [0.5, 0.5] and historical monitoring attention vector [0.7, 0.3] of the intelligent lighting system according to certain rules. One possible combination method is to splice them into a large vector or matrix.

[0180] For example, combine these data into a matrix (M):

[0182] M = begin{bmatrix}

[0183] 0.2 & 1.5 & 0.45

[0184] 0.4 & 0.33 & 0

[0185] 0.4 & 0.6 & 0.1

[0186] 0.5 & 0.5

[0187] 0.7 & 0.3

[0188] end{bmatrix}

[0190] ​​Input this matrix (M) into the first energy consumption regulation decision algorithm. The first energy consumption regulation decision algorithm can be a machine learning-based algorithm, such as a neural network algorithm. In the neural network, the input layer receives the combined matrix data, which is calculated and processed by the neurons in the hidden layer, and finally outputs the result for energy consumption regulation analysis.

[0191] 2) Generate an energy consumption regulation heat map

[0192] Through the calculation of the first energy consumption regulation decision algorithm, an energy consumption regulation heat map is generated. The energy consumption regulation heat map is a visual representation used to determine the energy consumption regulation optimization strategy for historical IoT device monitoring behavior events. For example, in the heat map, the abscissa may represent different device status parameters (such as the set temperature of the air conditioning system, the brightness of the intelligent lighting system, etc.), and the ordinate may represent different time intervals or device operation modes. The depth of color in the heat map indicates the level of energy consumption or the potential for energy consumption regulation. If, at a certain set temperature (such as the set temperature of the air conditioning system being 20 degrees Celsius), the color in the heat map is darker, it means that the energy consumption is higher or there is a greater potential for energy consumption regulation at this temperature; if, at a certain brightness value (such as the brightness of the intelligent lighting system being 300 lux), the color in the heat map is lighter, it means that the energy consumption is lower or the necessity for energy consumption regulation is smaller.

[0193] (4) Determine the algorithm training error and debug the algorithm

[0194] 1) Obtain the first energy consumption regulation optimization strategy for historical energy consumption regulation tasks

[0195] Obtain the first energy consumption regulation optimization strategy for the configured historical energy consumption regulation tasks from the historical IoT operation status log. For example, for the air conditioning system, the historical energy consumption regulation task may be to reduce energy consumption while meeting indoor comfort. The first energy consumption regulation optimization strategy adopted historically may be to adjust the set temperature from 22 degrees Celsius to 24 degrees Celsius (determined based on experience or previous analysis that this adjustment can reduce energy consumption), and at the same time adjust the operation mode of the air conditioner (such as from continuous cooling mode to intermittent cooling mode).

[0196] 2) Determine the algorithm training error

[0197] Determine the algorithm training error based on the energy consumption adjustment heat map and the first energy consumption adjustment optimization strategy. For example, obtain energy consumption adjustment suggestions under the same conditions (such as the same equipment status, environment, etc.) according to the energy consumption adjustment heat map. For example, according to the heat map suggestion, adjusting the set temperature of the air conditioner to 23 degrees Celsius is more energy-efficient than adjusting it to 24 degrees Celsius historically. Then, the algorithm training error can be determined by calculating the difference between the actual historical energy consumption (the energy consumption after executing the first energy consumption adjustment optimization strategy historically) and the energy consumption suggested by the energy consumption adjustment heat map. For example, if the actual historical energy consumption is 1.2 kWh and the energy consumption suggested by the heat map is 1.0 kWh, then the algorithm training error can be ((1.2 - 1.0) / 1.2 ≈ 0.167).

[0198] 3) Debug the first energy consumption adjustment decision algorithm

[0199] Debug the first energy consumption adjustment decision algorithm based on this algorithm training error. If the algorithm training error is large, it indicates that there is a large deviation between the prediction result of the algorithm and the actual optimal energy consumption adjustment strategy. The error can be reduced by adjusting the parameters in the algorithm. For example, if the first energy consumption adjustment decision algorithm is a neural network algorithm, the connection weights between neurons can be adjusted. If the error is caused by unreasonable weight allocation of equipment status parameters (such as the set temperature and operating power of the air conditioning system), the weights of these parameters in the algorithm can be increased or decreased. By continuously adjusting the parameters and re-inputting the data for calculation until the algorithm training error is reduced to an acceptable range.

[0200] Thus, by obtaining historical data and disassembling it to obtain the monitoring dataset samples, the equipment status information during historical operation can be deeply mined, such as various parameter situations of the air conditioning and lighting systems. Secondly, refining the operation energy consumption quantization vector and related vectors can accurately quantify the energy consumption and focus on key status factors, such as determining the energy consumption of different equipment and the attention weights for different parameters. Furthermore, combining the data and inputting it into the algorithm to generate an energy consumption adjustment heat map can visually present the energy consumption adjustment potential, facilitating the determination of the optimization strategy. Finally, determining the algorithm training error and debugging the algorithm can improve the accuracy of the first energy consumption adjustment decision algorithm, enabling it to more accurately give the energy consumption adjustment optimization strategy.

[0201] In some alternative embodiments, the historical IoT operation status log, the second monitoring data set sample, and the first energy consumption regulation optimization strategy are all obtained from a training sample pool. Before obtaining the historical IoT operation status log and the second monitoring data set sample corresponding to the historical IoT device monitoring behavior events in the historical IoT operation status log, the intelligent campus information data analysis method further includes: obtaining a plurality of IoT operation status training logs and the corresponding status monitoring training data sets for each of the IoT operation status training logs, and respectively determining the log mining results corresponding to each of the IoT operation status training logs according to each of the IoT operation status training logs and the corresponding status monitoring training data sets, where the status monitoring training data set is used to represent the selected IoT device monitoring behavior events mined from the corresponding IoT operation status training log; obtaining a plurality of preliminary screened energy consumption regulation tasks, and respectively determining the associated energy consumption regulation tasks corresponding to each of the IoT operation status training logs in the plurality of preliminary screened energy consumption regulation tasks according to each of the log mining results; respectively determining the prior state data sets corresponding to each of the IoT operation status training logs according to each of the IoT operation status training logs and the corresponding status monitoring training data sets, where the prior state data set is used to indicate the corresponding selected IoT device monitoring behavior events; synchronously importing each of the IoT operation status training logs, the corresponding prior state data set, and the corresponding associated energy consumption regulation task into the training sample pool, where the historical IoT operation status log is obtained from the plurality of IoT operation status training logs, the second monitoring data set sample is the prior state data set corresponding to the historical IoT operation status log, and the historical energy consumption regulation task is the associated energy consumption regulation task configured for the historical IoT operation status log.

[0202] In the actual application process, the exemplary implementation manners of the above embodiments are as follows.

[0203] (I) Obtaining IoT operation status training logs and related data sets and determining log mining results

[0204] 1) Obtaining IoT operation status training logs and status monitoring training data sets

[0205] In the IoT environment of an intelligent campus, there are numerous IoT operation status training logs. These logs record the operation status information of various IoT devices on campus. For example, for the devices in a smart classroom, the IoT operation status training log will include information such as the startup time, usage duration, and brightness adjustment of the projector, the light switch time and brightness change value of the intelligent lighting system, and the temperature setting and operating power fluctuation of the air conditioning system.

[0206] Simultaneously obtain the status monitoring training data sets corresponding to the training logs of each IoT operation status. Taking the air conditioning system as an example, the status monitoring training data set may include data used to characterize the monitored behavior events of the selected IoT devices mined from the training logs of this IoT operation status. For example, if the selected monitored behavior event is related to the cooling effect of the air conditioner, then the status monitoring training data set may include data elements such as the set temperature of the air conditioner (the value range is 16 - 30 degrees Celsius, such as the set temperature is 22 degrees Celsius), the temperature difference between indoor and outdoor (for example, the indoor temperature is 22 degrees Celsius, the outdoor temperature is 30 degrees Celsius, and the temperature difference is 8 degrees Celsius), and the evaporator temperature (for example, it is 10 degrees Celsius).

[0207] 2) Determine the log mining results

[0208] According to the training logs of each IoT operation status and the corresponding status monitoring training data sets, respectively determine the log mining results corresponding to the training logs of each IoT operation status. For example, for the training logs of the IoT operation status containing air conditioning system information, conduct mining and analysis on the temperature data, power data, etc. therein. If a mining algorithm based on statistical analysis is adopted, calculate statistical quantities such as the average value, standard deviation of the temperature, and the fluctuation range of the power. For example, within a certain period of time, the average value of the set temperature of the air conditioner is 22 degrees Celsius, the standard deviation is 1 degree Celsius, and the fluctuation range of the operating power is 500 - 1000 watts (the fluctuation range is 500 watts). These statistical quantities and the relevant data relationships constitute the log mining results of the training logs of this IoT operation status.

[0209] (2) Obtain the preliminary screening energy consumption adjustment tasks and determine the associated energy consumption adjustment tasks

[0210] 1) Obtain the preliminary screening energy consumption adjustment tasks

[0211] In the energy consumption management of campus IoT devices, there are several preliminary screening energy consumption adjustment tasks. These tasks may be set based on different goals, such as reducing the overall energy consumption, optimizing the energy consumption efficiency of specific devices, etc. For example, a preliminary screening energy consumption adjustment task may be to reduce the overall energy consumption of the smart classroom by 20% without affecting the comfort of the teaching environment; another preliminary screening energy consumption adjustment task may be to increase the energy consumption efficiency of the air conditioning system by 30% (the energy consumption efficiency can be measured by the ratio of the actual cooling capacity to the power consumption).

[0212] 2) Determine the associated energy consumption adjustment tasks

[0213] Based on the respective log mining results, the associated energy consumption adjustment tasks corresponding to each IoT operation status training log are determined among several preliminary screening energy consumption adjustment tasks. Taking the IoT operation status training log containing air conditioning system information as an example, if the log mining result shows that the operating power of the air conditioner fluctuates greatly and the set temperature is relatively high, then the associated energy consumption adjustment task may be to reduce the operating power of the air conditioner to improve energy consumption efficiency while meeting the indoor temperature comfort level (for example, the human comfort temperature range is 22 - 26 degrees Celsius). If another IoT operation status training log shows that the light brightness of the intelligent lighting system remains at a relatively high level for a long time and the switching frequency is low, its associated energy consumption adjustment task may be to adjust the light brightness according to the actual lighting requirements of the classroom to reduce energy consumption.

[0214] (III) Determine the prior state data set and import it into the training sample pool

[0215] 1) Determine the prior state data set

[0216] Based on each IoT operation status training log and the corresponding status monitoring training data set, the prior state data set of each IoT operation status training log is determined respectively. Taking the IoT operation status training log of the intelligent lighting system as an example, the prior state data set is used to indicate the corresponding selected IoT device monitoring behavior event. For example, if the selected monitoring behavior event is the relationship between the brightness adjustment and energy consumption of the lighting system, then the prior state data set may include data elements such as the initial brightness of the light (for example, 800 lux), the frequency of brightness adjustment (for example, adjusted once per hour), the brightness change amount per adjustment (for example, 100 lux), and the current energy consumption (for example, 0.5 kWh / hour).

[0217] 2) Import into the training sample pool

[0218] Synchronously import each IoT operation status training log, the corresponding prior state data set, and the corresponding associated energy consumption adjustment task into the training sample pool. For example, for a set of data containing air conditioning system information, import the IoT operation status training log (including various operation status data of the air conditioner), the corresponding prior state data set (such as the set temperature of the air conditioner, the indoor-outdoor temperature difference, etc.), and the associated energy consumption adjustment task (such as reducing the air conditioner energy consumption while meeting the comfort level) into the training sample pool together. Similarly, the relevant data of the intelligent lighting system is also imported in this way.

[0219] In this way, in subsequent operations, the historical IoT operation status log is obtained from several IoT operation status training logs. The second monitoring data set sample is the prior state data set corresponding to the historical IoT operation status log, and the historical energy consumption adjustment task is the associated energy consumption adjustment task configured for the historical IoT operation status log. For example, if a certain imported IoT operation status training log containing an air conditioning system is selected as the historical IoT operation status log, then the corresponding prior state data set becomes the second monitoring data set sample, and the associated energy consumption adjustment task becomes the historical energy consumption adjustment task.

[0220] In this way, by obtaining the IoT operation status training logs and related data sets and determining the log mining results, the operation status of the device can be deeply analyzed. For example, a comprehensive operation situation can be obtained by statistically analyzing the air conditioning temperature and power data. Obtaining the preliminary screened energy consumption adjustment tasks and determining the associated energy consumption adjustment tasks can accurately match the energy consumption adjustment tasks according to the actual operation status of the device. For example, a suitable energy consumption adjustment task can be determined according to the power fluctuation of the air conditioner operation. Determining the prior state data set and importing it into the training sample pool enables subsequent operations to obtain complete and relevant data from the training sample pool, providing an accurate data basis for operations such as energy consumption adjustment analysis, and improving the reliability and effectiveness of the intelligent campus information data analysis method.

[0221] In the next step, determining the prior state data set of each of the IoT operation status training logs according to each of the IoT operation status training logs and the corresponding state monitoring training data set respectively includes: inputting each of the state monitoring training data sets into the second energy consumption adjustment decision algorithm for energy consumption adjustment analysis to generate an optimization mode label corresponding to each of the IoT operation status training logs; respectively performing IoT device monitoring behavior event mining according to each of the IoT operation status training logs and the corresponding optimization mode label to generate an event location window label corresponding to each of the IoT operation status training logs, where the event location window label is used to indicate the corresponding selected IoT device monitoring behavior event; respectively inputting each of the IoT operation status training logs and the corresponding event location window label into the first state data recognition algorithm for processing to generate a prior state data set corresponding to each of the IoT operation status training logs.

[0222] In addition, after respectively inputting each of the IoT operation status training logs and the corresponding event location window labels into the first state data recognition algorithm for processing to generate a prior state data set corresponding to each of the IoT operation status training logs, the intelligent campus information data analysis method further includes: obtaining a benchmark energy consumption optimization expectation feature corresponding to each of the associated energy consumption adjustment tasks, where the benchmark energy consumption optimization expectation feature is used to indicate the energy consumption adjustment trend of the benchmark energy consumption adjustment task, and the feature depth of the benchmark energy consumption adjustment task in the semantic feature space is higher than the feature depth of the associated energy consumption adjustment task in the semantic feature space; respectively inputting each of the IoT operation status training logs and the corresponding benchmark energy consumption optimization expectation feature into the second state data recognition algorithm for processing to generate a benchmark state data set corresponding to each of the IoT operation status training logs; determining the relevance between each of the prior state data sets and the corresponding benchmark state data set to obtain a target correlation corresponding to each of the prior state data sets; and when the target correlation is less than a set correlation degree, filtering out the IoT operation status training log corresponding to the target correlation.

[0223] In the data processing of IoT devices in an intelligent campus, to determine the prior state data set of each IoT operation status training log, first, each state monitoring training data set is respectively input into the second energy consumption adjustment decision algorithm for energy consumption adjustment analysis. For example, for the intelligent lighting system on campus, its state monitoring training data set may include data such as light brightness (the value range is 0 - 1000 lux, for example, 500 lux), on - time duration (in hours, for example, 2 hours), number of switch operations (for example, 3 times), etc.

[0224] The second energy consumption adjustment decision algorithm can be a machine - learning - based algorithm, such as a decision tree algorithm. The decision tree analyzes based on the input state monitoring training data set. Taking the intelligent lighting system as an example, if the light brightness is high and the on - time duration is long, the decision tree may generate an optimization mode label of "high - energy - consumption mode"; if the light brightness is moderate and the number of switch operations is large, it may generate an optimization mode label of "medium - energy - consumption fluctuation mode". For the state monitoring training data set of the air - conditioning system, which includes data such as set temperature (for example, 22 degrees Celsius), operating power (for example, 1000 watts), operating mode (for example, cooling), etc., the decision tree may generate an optimization mode label of "normal cooling energy - consumption mode" based on these data.

[0225] After obtaining the optimization mode labels corresponding to each IoT operation status training log, IoT device monitoring behavior event mining is performed based on each IoT operation status training log and the corresponding optimization mode label respectively. For example, for an intelligent lighting system, if the optimization mode label is "high energy consumption mode", events related to high energy consumption are mined from the IoT operation status training log. For example, if it is found in the log that the lights remain at high brightness continuously during a certain period (such as 7-9 pm), this period can be used as the event location window label. For an air conditioning system, if the optimization mode label is "normal cooling energy consumption mode", events related to normal cooling energy consumption are mined from the IoT operation status training log. For example, if it is found that the air conditioner operates stably near the set temperature during certain periods of the day (such as 10-12 am), this period becomes the event location window label.

[0226] Furthermore, each IoT operation status training log and the corresponding event location window label are respectively input into the first state data recognition algorithm for processing to generate the prior state dataset corresponding to each IoT operation status training log. The first state data recognition algorithm can be an algorithm based on a neural network. Taking the intelligent lighting system as an example, the IoT operation status training log containing data such as light brightness, on duration, and switch times, as well as the corresponding event location window label (7-9 pm), is input into the neural network. The neural network learns the relationships between these data and outputs the prior state dataset. For example, it may output data such as the average brightness and average energy consumption within this event location window as elements of the prior state dataset. For the air conditioning system, the IoT operation status training log containing data such as set temperature, operating power, and operating mode, as well as the corresponding event location window label (10-12 am), is input, and the neural network may output data such as the average operating power and temperature fluctuation range within this period as the prior state dataset.

[0227] Next, after determining the prior state dataset, the benchmark energy consumption optimization expectation features corresponding to each associated energy consumption adjustment task are obtained. The benchmark energy consumption optimization expectation features are used to indicate the energy consumption adjustment trend of the benchmark energy consumption adjustment task, and the feature depth of the benchmark energy consumption adjustment task in the semantic feature space is higher than that of the associated energy consumption adjustment task in the semantic feature space. For example, for the associated energy consumption adjustment task of an intelligent lighting system, it may be to reduce energy consumption in a specific classroom, while the benchmark energy consumption adjustment task may be to optimize the energy efficiency of the lighting system across the entire campus.

[0228] For the benchmark energy consumption regulation task, if the goal is to reduce the overall energy consumption of the campus lighting system by 30%, this goal reflects the energy consumption regulation trend in the desired characteristics of benchmark energy consumption optimization. Specifically, it may involve comprehensively considering the energy consumption of the lighting system in different areas and at different times. For example, reducing lighting usage in well-lit areas of teaching buildings during the day and adjusting the lighting brightness according to the personnel flow in places such as libraries.

[0229] Then, input each IoT operation status training log and the corresponding desired characteristics of benchmark energy consumption optimization into the second state data recognition algorithm for processing to generate the benchmark state dataset corresponding to each IoT operation status training log. The second state data recognition algorithm can also be based on a certain machine learning algorithm, such as the support vector machine algorithm. Taking the intelligent lighting system as an example, input the IoT operation status training log (including data such as light brightness, on duration, and switch times) and the desired characteristics of benchmark energy consumption optimization (such as a 30% reduction in the overall campus lighting energy consumption) into the support vector machine. The support vector machine generates the benchmark state dataset based on these data, which may include data such as the ideal brightness value and maximum on duration in different areas under the condition of meeting the overall campus energy consumption reduction goal.

[0230] Furthermore, determine the relevance between each prior state dataset and the corresponding benchmark state dataset to obtain the target relevance corresponding to each prior state dataset. For example, a correlation coefficient calculation method can be used, such as the Pearson correlation coefficient. For the intelligent lighting system, calculate the Pearson correlation coefficient between the prior state dataset (such as data on the average brightness and average energy consumption of a specific classroom) and the benchmark state dataset (such as the ideal brightness value and maximum on duration under the overall campus energy consumption reduction goal).

[0231] When the target relevance is less than the set relevance degree, filter out the IoT operation status training log corresponding to the target relevance. For example, if the set relevance degree is 0.5 and the Pearson correlation coefficient between the prior state dataset of an intelligent lighting system in a certain classroom and the benchmark state dataset of the entire campus is 0.3, then the IoT operation status training log corresponding to this classroom will be filtered out. This helps to remove data with low relevance to the overall energy consumption optimization goal and improve the accuracy and effectiveness of subsequent data analysis.

[0232] It can be seen that by using the second energy consumption regulation decision algorithm, the mining of IoT device monitoring behavior events, and the first state data recognition algorithm to determine the prior state data set, the relationship between the device operation state and energy consumption can be deeply explored. For example, the intelligent lighting system can obtain energy consumption-related data for a specific period through multi-algorithm processing. Secondly, obtaining the benchmark energy consumption optimization expectation features and generating the benchmark state data set helps to examine the energy consumption regulation task from a more macroscopic perspective, such as the ideal state data under the overall campus lighting energy consumption optimization goal. Finally, determining the relevance and filtering the logs can remove data with low relevance to the overall goal, improve the data quality, provide a more accurate data basis for the intelligent campus information analysis, and enhance the accuracy of analyses such as energy consumption regulation.

[0233] In some independent embodiments, before synchronously importing each of the IoT operation state training logs, the corresponding prior state data set, and the corresponding associated energy consumption regulation task into the training sample pool, the intelligent campus information data analysis method further includes: determining the number of state-involved feature blocks in each of the prior state data sets to obtain the number of feature blocks corresponding to each of the prior state data sets; when the number of feature blocks is greater than the set number, filtering out the IoT operation state training logs corresponding to the number of feature blocks.

[0234] For the above independent embodiments, the detailed implementation steps are as follows.

[0235] (1) Determining the number of feature blocks in the prior state data set

[0236] 1) Composition of the prior state data set and concept of feature blocks

[0237] In the intelligent campus information data analysis, the prior state data set is obtained through a series of complex algorithm processes and contains important information related to IoT device monitoring behavior events. The prior state data set is composed of multiple different types of data elements, and these data elements can be divided into different feature blocks according to their internal logical relationships or data characteristics.

[0238] For example, for the prior state data set of the intelligent lighting system in the campus, it may include data such as light brightness, light-on duration, and switch frequency data for different time periods. Among them, the light brightness data can be regarded as a feature block because it is a relatively independent data set reflecting an important state feature of the lighting system; the light-on duration data can also be used as a separate feature block, which describes another aspect of the operation state of the lighting device; the switch frequency data for different time periods also constitutes a feature block, which reflects the time pattern feature of the lighting system usage.

[0239] 2) Process of determining the number of feature blocks

[0240] Determine the number of state-involved feature blocks in each prior state dataset to obtain the number of feature blocks corresponding to each prior state dataset. Taking the intelligent lighting system as an example, if its prior state dataset contains the three feature blocks mentioned above (brightness, duration, switch frequency), then the number of feature blocks corresponding to this prior state dataset is 3. For the air conditioning system on campus, its prior state dataset may include data such as set temperature, operating power, operating mode, and temperature fluctuation range. Among them, the set temperature and the temperature fluctuation range can be divided into one feature block according to the data relationship (because they are both related to temperature), the operating power is taken as one feature block, and the operating mode is taken as one feature block. In this way, the number of feature blocks corresponding to the prior state dataset of the air conditioning system is 3.

[0241] (2) Filter the IoT operation status training logs according to the number of feature blocks

[0242] 1) Basis for determining the set number

[0243] In this process, there is a set number. This set number is determined based on various factors such as the resource limitations of the system, the efficiency requirements of data processing, and the applicability of subsequent data analysis algorithms. For example, if the memory of the data processing system is limited, and the subsequent analysis algorithm will experience performance degradation or a sharp increase in computational complexity when processing data with a large number of feature blocks, then the set number may be set to a relatively small value to ensure the efficiency of data processing and the effectiveness of the algorithm.

[0244] For example, in a certain intelligent campus information data analysis system, according to the hardware configuration of the system (such as limited memory and processing power) and the commonly used data analysis algorithm (such as a certain matrix operation-based algorithm, whose computational complexity increases exponentially with the increase in the number of feature blocks), the set number is determined to be 5. This means that when the number of feature blocks corresponding to a prior state dataset exceeds 5, it may have an adverse impact on the processing efficiency of the system and the accuracy of the analysis results.

[0245] 2) Filtering operation

[0246] When the number of feature blocks is greater than the set number, filter out the IoT operation status training logs corresponding to the number of feature blocks. For example, for a prior state dataset of a new intelligent device containing a large amount of complex sensor data, if the number of its feature blocks is analyzed to be 6, which is greater than the set number 5, then the IoT operation status training logs related to this new intelligent device will be filtered out. This is because a prior state dataset with too many feature blocks may lead to problems such as excessive data processing time, memory overflow, or inaccurate analysis results during subsequent data analysis processes, such as the data analysis process after synchronously importing IoT operation status training logs, prior state datasets, and associated energy consumption adjustment tasks into the training sample pool. Through this filtering operation, it is possible to ensure that the data entering the training sample pool has an appropriate complexity and scale, thereby improving the effectiveness and reliability of the entire intelligent campus information data analysis method.

[0247] Based on the above embodiments, determining the number of feature blocks in the prior state dataset helps to deeply understand the data structure, such as distinguishing different state feature blocks in the prior state datasets of intelligent lighting systems and air conditioning systems. Filtering the IoT operation status training logs according to the set number can effectively control the complexity of the data and avoid problems such as low data processing efficiency and memory overflow caused by too many feature blocks, such as filtering out the data of new intelligent devices with an excessive number of feature blocks in a system with limited resources. The above filtering operation helps to improve the accuracy and reliability of the entire intelligent campus information data analysis method, ensure the effectiveness of subsequent data analysis, and thus provide a more accurate data basis for tasks such as energy consumption adjustment.

[0248] In some other independent embodiments, the first energy consumption adjustment optimization strategy for obtaining the historical energy consumption adjustment tasks configured in the historical IoT operation status logs includes: obtaining the historical energy consumption optimization expected features of the historical energy consumption adjustment tasks configured in the historical IoT operation status logs, and performing iterative downsampling on the historical energy consumption optimization expected features to obtain a number of first-stage expected downsampled features; determining the thermal weights of each of the first-stage expected downsampled features in the semantic feature space, and sorting the first-stage expected downsampled features according to the ascending order rule of each of the thermal weights, and determining the first G first-stage expected downsampled features as the second-stage expected downsampled features, where G is a positive integer; determining the first energy consumption adjustment optimization strategy for the historical energy consumption adjustment tasks based on each of the second-stage expected downsampled features.

[0249] In addition, within the scope of intelligent campus information data analysis, for the historical energy consumption adjustment tasks configured for the historical IoT operation status logs, it is first necessary to obtain their historical energy consumption optimization expectation features. The historical energy consumption optimization expectation features are a quantitative representation of the goals of historical energy consumption adjustment tasks, which cover various aspects of information. For example, for the intelligent lighting system on campus, the historical energy consumption optimization expectation features may include reducing the overall energy consumption by a certain percentage (such as 20%) within a specific time period (such as a semester), while ensuring the basic functional requirements of lighting (such as the minimum average brightness in classrooms is 300 lux). For the air conditioning system, it may be to reduce the operating energy consumption (such as by 30%) on the premise of meeting indoor comfort (such as the temperature is maintained at 22 - 26 degrees Celsius).

[0250] Then, perform iterative downsampling on the historical energy consumption optimization expectation features. Downsampling is a data processing technique that simplifies the data structure by reducing the data volume while retaining key information. For example, for the historical energy consumption optimization expectation features of the intelligent lighting system, if its original representation contains multiple data points (such as energy consumption targets and brightness requirements for different classrooms and different time periods), iterative downsampling may gradually reduce these data points according to certain rules. For example, the first downsampling combines the daily energy consumption target data points within a month into weekly energy consumption target data points, and the second downsampling combines the energy consumption target data points of different classrooms according to regions (such as Teaching Building A, Teaching Building B, etc.). After multiple iterations of downsampling, several first-stage expected downsampling features are obtained.

[0251] Taking the intelligent lighting system as an example, for instance, the original historical energy consumption optimization expectation features contain 30 data points (representing the energy consumption and brightness information of each classroom every day within a month). After the first downsampling, the daily data is combined into weekly data, and 4 data points (representing the information of four weeks) may be obtained. After the second downsampling, combining according to the teaching building area, 2 data points (representing the information of two teaching building areas) may be obtained, and these data points are the first-stage expected downsampling features.

[0252] The following technical solution involves determining the thermal weights of the first-stage expected downsampling features and sorting out the sequence relationship.

[0253] 1) Determine the thermal weights

[0254] Determine the thermal weights of each first-stage expected downsampled feature in the semantic feature space. The semantic feature space is an abstract conceptual space where each feature has its specific semantic meaning and relative importance. The thermal weight represents the degree of importance or influence of a feature in this semantic feature space. For the first-stage expected downsampled features of the intelligent lighting system, for example, one data point represents the weekly energy consumption target of Teaching Building A, and the determination of its thermal weight may be related to factors such as the usage frequency of this teaching building, the area size, and the power of the lighting equipment.

[0255] An algorithm based on the Analytic Hierarchy Process (AHP) can be used to determine the thermal weights. For example, for the first-stage expected downsampled feature of the weekly energy consumption target of Teaching Building A, through the Analytic Hierarchy Process, considering factors such as the usage frequency of Teaching Building A (for example, used 10 hours a day, with a weight of 0.4), the area size (for example, 5000 square meters, with a weight of 0.3), and the average power of the lighting equipment (for example, 100 watts, with a weight of 0.3), the calculated thermal weight is 0.3 (the specific value obtained according to the calculation rules of the present invention).

[0256] 2) Sort the order according to the thermal weights

[0257] Sort the order of each first-stage expected downsampled feature according to the ascending order rule of each thermal weight. For example, there are three first-stage expected downsampled features, and their thermal weights are 0.2, 0.3, and 0.4 respectively. According to the ascending order rule, first process the feature with a thermal weight of 0.2, then process the feature with 0.3, and finally process the feature with 0.4. Determine the first G (G is a positive integer) first-stage expected downsampled features as the second-stage expected downsampled features. For example, G = 2, then the two first-stage expected downsampled features with thermal weights of 0.2 and 0.3 will be determined as the second-stage expected downsampled features.

[0258] Finally, the first energy consumption adjustment and optimization strategy can be determined based on the second-stage expected downsampled features: Determine the first energy consumption adjustment and optimization strategy of the historical energy consumption adjustment task according to each second-stage expected downsampled feature. Taking the intelligent lighting system as an example, if the second-stage expected downsampled features include the energy consumption target of Teaching Building A (determined as a more important feature through the previous analysis) and the brightness requirement of Teaching Building A (also a more important feature), then the first energy consumption adjustment and optimization strategy may be to first adjust the control strategy of the lighting equipment in Teaching Building A.

[0259] For example, if the energy consumption target of Teaching Building A is to reduce by 15%, it can be achieved by reducing the brightness during non-teaching periods (such as reducing the brightness from 500 lux to 300 lux during break times), adjusting the switching time of lighting equipment (such as turning off some lighting equipment 10 minutes earlier), etc. At the same time, according to the brightness requirements of Teaching Building A, ensure that the brightness during teaching periods is not lower than 300 lux, and adopt intelligent dimming technology to optimize lighting energy consumption according to the actual lighting conditions in the classroom (for example, if the natural light near the window is stronger, the artificial lighting brightness can be appropriately reduced). For the air conditioning system, if the expected downsampled features in the second stage include the temperature range that meets indoor comfort and the goal of reducing energy consumption, the first energy consumption adjustment and optimization strategy may be to optimize the temperature setting strategy of the air conditioner, such as dynamically adjusting the temperature setting according to the indoor-outdoor temperature difference and the personnel density, and at the same time operating the air conditioner in an energy-saving mode to achieve the goal of reducing energy consumption.

[0260] In this way, by obtaining the historical energy consumption optimization expected features and performing iterative downsampling, the complex energy consumption adjustment target data can be simplified. For example, the intelligent lighting system simplifies the energy consumption data of each classroom every day to the energy consumption data of the teaching building area, reducing the data volume while retaining key information. Determining the thermal weights of the expected downsampled features in the first stage and sorting out the sequence relationship can reasonably arrange the processing order according to the importance of each feature, such as determining the importance order of the energy consumption target features according to various factors of the teaching building. Determining the first energy consumption adjustment and optimization strategy based on the expected downsampled features in the second stage can formulate a more targeted and practical energy consumption adjustment strategy, improving the energy consumption management efficiency of the smart campus.

[0261] Furthermore, Figure 2 FIG. is a schematic structural diagram of a data analysis system 200 provided by the present invention. As Figure 2 shown, the data analysis system 200 includes a processor 210, and the processor 210 can call and run a computer program from the memory to implement the method in the present invention.

[0262] Optionally, as Figure 2 shown, the data analysis system 200 may further include a memory 230. Among them, the processor 210 can call and run a computer program from the memory 230 to implement the method in the present invention.

[0263] Among them, the memory 230 can be an independent device separate from the processor 210, or can be integrated in the processor 210.

[0264] Optionally, as Figure 2As shown, the data analysis system 200 may further include a transceiver 220, and the processor 210 may control the transceiver 220 to interact with other devices. Specifically, it may send information or data to other devices, or receive information or data sent by other devices.

[0265] Optionally, the data analysis system 200 may implement the corresponding processes of the storage engine or components (such as processing modules) in the storage engine or the device deployed with the storage engine in each method of the present invention. For the sake of brevity, it will not be elaborated here.

[0266] It should be understood that the processor of the present invention may be an integrated circuit chip with signal processing capabilities.

[0267] It can be understood that the memory in the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, suitable types of memory.

[0268] On the above basis, a readable storage medium is provided, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the above method are implemented.

[0269] It should be noted that in this article, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including that element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present invention is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in a reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0270] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described example methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to enable a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0271] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the purpose of the present invention and the scope protected by the present invention, and all of them fall within the protection scope of the present invention.

Claims

1. A method for analyzing intelligent campus information data, characterized in that, The execution subject of the intelligent campus information data analysis method is a data analysis system, and the intelligent campus information data analysis method includes: Obtain the device status monitoring data sets corresponding to each preliminary screening IoT device monitoring behavior event in the campus IoT operation status log, and determine a target status monitoring data set from several of the device status monitoring data sets, where the target status monitoring data set is used to indicate the target IoT device monitoring behavior event with the highest priority among several of the preliminary screening IoT device monitoring behavior events; Perform state vector mining on the campus IoT operation status log respectively according to the target status monitoring data set and each of the device status monitoring data sets to obtain several IoT operation state vectors, and refine the state monitoring attention vectors corresponding to the target status monitoring data set and each of the device status monitoring data sets; Combine each of the IoT operation state vectors with the corresponding state monitoring attention vector to obtain several global state monitoring vectors; Perform operation energy consumption identification on the campus IoT operation status log to obtain a first operation energy consumption quantization vector, combine the first operation energy consumption quantization vector and several of the global state monitoring vectors to obtain energy consumption adjustment auxiliary information; Perform energy consumption adjustment analysis according to the energy consumption adjustment auxiliary information to generate a target energy consumption adjustment optimization strategy for the target IoT device monitoring behavior event; The performing state vector mining on the campus IoT operation status log respectively according to the target status monitoring data set and each of the device status monitoring data sets to obtain several IoT operation state vectors includes: Perform pyramid state vector mining on the campus IoT operation status log to obtain the pyramid operation state vector of the campus IoT operation status log; Respectively according to the target status monitoring data set and each of the device status monitoring data sets, perform feature downsampling on the pyramid operation state vector to obtain several pyramid downsampling vectors; Perform interaction on each of the pyramid downsampling vectors respectively to obtain several IoT operation state vectors: For any one of the pyramid downsampling vectors, adjust the local state vectors at each feature depth in the pyramid downsampling vector respectively to obtain several implicit state vectors with the same size, and perform interaction on each of the implicit state vectors to obtain an interaction state vector; Perform feature full connection on each of the interaction state vectors respectively to obtain several IoT operation state vectors.

2. The intelligent campus information data analysis method according to claim 1, characterized in that The combining the first operation energy consumption quantization vector and several of the global state monitoring vectors to obtain energy consumption adjustment auxiliary information includes: Respectively determine the data involvement weights of each of the device status monitoring data sets, and use the data involvement weights to combine the global state monitoring vectors corresponding to each of the device status monitoring data sets to obtain a first state monitoring combined vector; Combine the first operation energy consumption quantization vector, the first state monitoring combined vector, and the global state monitoring vector corresponding to the target status monitoring data set to obtain energy consumption adjustment auxiliary information.

3. The intelligent campus information data analysis method according to claim 2, wherein The target energy consumption regulation optimization strategy is generated by the first energy consumption regulation decision algorithm. Combining the first running energy consumption quantization vector, the first state monitoring combination vector, and the global state monitoring vector corresponding to the target state monitoring data set to obtain energy consumption regulation auxiliary information, including: Obtain the regulation requirement information for guiding the first energy consumption regulation decision algorithm to generate the energy consumption regulation optimization strategy; Refine the regulation requirement vector of the regulation requirement information, and combine the first running energy consumption quantization vector, the regulation requirement vector, the first state monitoring combination vector, and the global state monitoring vector corresponding to the target state monitoring data set to obtain energy consumption regulation auxiliary information.

4. The intelligent campus information data analysis method according to claim 1, wherein The obtaining of the device state monitoring data set corresponding to each pre-screened IoT device monitoring behavior event in the campus IoT operation status log, and determining the target state monitoring data set from several of the device state monitoring data sets, includes: Obtain the campus IoT operation status log and the index information of the campus IoT operation status log, where the campus IoT operation status log includes several pre-screened IoT device monitoring behavior events, and the index information is used to indicate the target IoT device monitoring behavior event with the highest priority among the several pre-screened IoT device monitoring behavior events; Decompose the campus IoT operation status log to obtain the device state monitoring data set corresponding to each pre-screened IoT device monitoring behavior event, and determine the target state monitoring data set from each of the device state monitoring data sets according to the index information.

5. The intelligent campus information data analysis method according to claim 4, wherein The determining of the target state monitoring data set from each of the device state monitoring data sets according to the index information includes: When the index information is the first type of index, determine the target state monitoring data set from each of the device state monitoring data sets according to the relative distribution characteristics between the first type of index and each of the device state monitoring data sets; Or, when the index information is the second type of index, determine the target state monitoring data set from each of the device state monitoring data sets according to the correlation between the second type of index and the key value characteristics of each of the device state monitoring data sets; Or, when the index information is the third type of index, determine the target state monitoring data set from each of the device state monitoring data sets according to the correlation between the third type of index and each of the device state monitoring data sets.

6. The intelligent campus information data analysis method according to claim 1, characterized in that The target energy consumption regulation optimization strategy is generated by the first energy consumption regulation decision algorithm, and the first energy consumption regulation decision algorithm is debugged through the following steps: Obtain the historical IoT operation status log and the second monitoring data set sample corresponding to the historical IoT device monitoring behavior event in the historical IoT operation status log, and decompose the historical IoT operation status log to obtain the first monitoring data set sample corresponding to each frequent IoT device behavior event in the historical IoT operation status log, where the historical IoT device monitoring behavior event is one IoT device monitoring behavior event among several of the frequent IoT device behavior events; Refine the second operating energy consumption quantization vector of the historical Internet of Things operating status log, perform state vector mining on the historical Internet of Things operating status log respectively based on the second monitoring data set sample and each of the first monitoring data set samples to obtain a number of historical operating state vectors, and refine the historical monitoring attention vectors corresponding to the second monitoring data set sample and each of the first monitoring data set samples; Combine the second operating energy consumption quantization vector, the historical operating state vectors, and the historical monitoring attention vectors and input them into the first energy consumption adjustment decision algorithm for energy consumption adjustment analysis to generate an energy consumption adjustment heat map, where the energy consumption adjustment heat map is used to determine the energy consumption adjustment optimization strategy for the historical Internet of Things device monitoring behavior events; Obtain the first energy consumption adjustment optimization strategy of the historical energy consumption adjustment task configured in the historical Internet of Things operating status log, determine the algorithm training error based on the energy consumption adjustment heat map and the first energy consumption adjustment optimization strategy, and debug the first energy consumption adjustment decision algorithm based on the algorithm training error, where the historical energy consumption adjustment task is used to indicate the historical Internet of Things device monitoring behavior events; 7. The intelligent campus information data analysis method according to claim 6, characterized in that, The historical Internet of Things operating status log, the second monitoring data set sample, and the first energy consumption adjustment optimization strategy are all obtained from the training sample pool. Before obtaining the historical Internet of Things operating status log and the second monitoring data set sample corresponding to the historical Internet of Things device monitoring behavior events in the historical Internet of Things operating status log, the intelligent campus information data analysis method further includes: Obtain a number of Internet of Things operating status training logs and the corresponding state monitoring training data sets for each of the Internet of Things operating status training logs, and respectively determine the log mining results corresponding to each of the Internet of Things operating status training logs according to each of the Internet of Things operating status training logs and the corresponding state monitoring training data sets, where the state monitoring training data set is used to represent the selected Internet of Things device monitoring behavior events mined in the corresponding Internet of Things operating status training log; Obtain a number of preliminary screening energy consumption adjustment tasks, and respectively determine the associated energy consumption adjustment tasks corresponding to each of the Internet of Things operating status training logs in the number of preliminary screening energy consumption adjustment tasks according to each of the log mining results; Respectively determine the prior state data sets corresponding to each of the Internet of Things operating status training logs according to each of the Internet of Things operating status training logs and the corresponding state monitoring training data sets, where the prior state data set is used to indicate the corresponding selected Internet of Things device monitoring behavior events; Synchronously import each of the Internet of Things operating status training logs, the corresponding prior state data set, and the corresponding associated energy consumption adjustment task into the training sample pool, where the historical Internet of Things operating status log is obtained from the number of Internet of Things operating status training logs, the second monitoring data set sample is the prior state data set corresponding to the historical Internet of Things operating status log, and the historical energy consumption adjustment task is the associated energy consumption adjustment task configured in the historical Internet of Things operating status log; Determining the prior state datasets of each of the IoT operation state training logs respectively according to each of the IoT operation state training logs and the corresponding state monitoring training datasets includes: Inputting each of the state monitoring training datasets into a second energy consumption regulation decision algorithm for energy consumption regulation analysis to generate an optimization mode label corresponding to each of the IoT operation state training logs; Mining IoT device monitoring behavior event for each of the IoT operation state training logs and the corresponding optimization mode label respectively to generate an event location window label corresponding to each of the IoT operation state training logs, where the event location window label is used to indicate the corresponding selected IoT device monitoring behavior event; Inputting each of the IoT operation state training logs and the corresponding event location window label into a first state data recognition algorithm for processing to generate a prior state dataset corresponding to each of the IoT operation state training logs; After inputting each of the IoT operation state training logs and the corresponding event location window label into a first state data recognition algorithm for processing to generate a prior state dataset corresponding to each of the IoT operation state training logs, the intelligent campus information data analysis method further includes: Obtaining the benchmark energy consumption optimization expectation feature corresponding to each of the associated energy consumption regulation tasks, where the benchmark energy consumption optimization expectation feature is used to indicate the energy consumption regulation trend of the benchmark energy consumption regulation task, and the feature depth of the benchmark energy consumption regulation task in the semantic feature space is higher than the feature depth of the associated energy consumption regulation task in the semantic feature space; Inputting each of the IoT operation state training logs and the corresponding benchmark energy consumption optimization expectation feature into a second state data recognition algorithm for processing to generate a benchmark state dataset corresponding to each of the IoT operation state training logs; Determining the relevance between each of the prior state datasets and the corresponding benchmark state dataset to obtain the target relevance corresponding to each of the prior state datasets; When the target relevance is less than the set relevance, filtering out the IoT operation state training log corresponding to the target relevance.

8. A data analysis system, characterized in that, Including at least one processor and a memory; the memory stores computer execution instructions; the at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the method according to any one of claims 1-7.

Images