Laboratory resource efficient allocation method based on big data analysis

Abstract

The invention discloses a laboratory resource efficient allocation method based on big data analysis, and relates to the technical field of laboratory resource management.The method comprises the following specific steps that microenvironment parameters are monitored and collected, comprising a temperature and humidity sensor, an air quality sensor, an illumination intensity sensor and an electromagnetic interference intensity sensor, a dynamic association model of external environment and laboratory resource demands is established by using a big data analysis technology, so that a complex relationship between external environment change and laboratory resource demands is accurately analyzed; a powerful basis is provided for scientific and reasonable resource allocation, so that a laboratory can more accurately predict and judge the demand degree of each resource and the allocation priority under different external environment conditions, unreasonable allocation and waste of the resources are avoided, and the resource allocation efficiency is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of laboratory resource management, and in particular to an efficient laboratory resource allocation method based on big data analysis. Background Art

[0002] As an important place for scientific research and technological innovation, the laboratory's operational efficiency and resource management capabilities have a decisive impact on the output of scientific research results. The effective allocation of laboratory resources is not only the basis for ensuring the smooth progress of experiments, but also the key to improving overall scientific research efficiency. Laboratory resources cover reagents, equipment, venues, and microenvironment (such as temperature, humidity, air quality, etc.). The rational allocation of these resources is directly related to the accuracy of experimental results and the progress of scientific research projects. With the rapid development of technologies such as the Internet of Things and big data, how to use these advanced technologies to improve the management level of laboratory resources has become an important issue in current laboratory operation and management.

[0003] Traditional laboratory resource allocation methods mainly focus on the monitoring and regulation of internal laboratory environmental factors, such as monitoring and adjusting the temperature and humidity conditions in the laboratory through temperature and humidity sensors to ensure that the experiment is carried out in a suitable environment. However, this method ignores the important impact of external environmental factors on laboratory resource allocation. For example, extreme weather conditions may cause the temperature and humidity inside the laboratory to be out of control, thereby affecting the accuracy and safety of the experiment. At the same time, the idle resources of similar laboratories in the surrounding areas may also provide potential opportunities for resource supplementation for the current laboratory. Due to the lack of comprehensive integration and analysis of external environmental data, traditional methods often find it difficult to formulate efficient and adaptable resource allocation plans, which not only leads to waste of resources, but also delays the progress of experiments due to resource shortages, and even affects the output of scientific research results.

[0004] In view of the above problems, it is necessary to optimize the existing efficient allocation methods of laboratory resources. By integrating the laboratory microenvironment and external environment data, and using big data analysis technology to establish a dynamic correlation model between the external environment and laboratory resource requirements, flexible allocation of laboratory internal reagents, equipment, venues and other resources can be achieved. Therefore, it is of great significance to develop an efficient laboratory resource allocation method based on big data analysis that can comprehensively realize the above characteristics. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the prior art and provide a method for efficient allocation of laboratory resources based on big data analysis. It can integrate the internal and external environmental data of the laboratory and use big data analysis technology to establish a dynamic correlation model between the external environment and laboratory resource requirements, thereby realizing the intelligent and dynamic allocation of resources. In terms of technical implementation, the present invention not only deploys a variety of Internet of Things sensors to perform high-precision monitoring of the laboratory microenvironment, but also establishes an interface with external environmental data, realizes the comprehensive integration and analysis of internal and external environmental data, and accurately predicts the demand degree and allocation priority of various laboratory resources under different external environmental conditions through big data analysis algorithms, thereby formulating an adaptive resource allocation strategy that integrates the external environment. In addition, the present invention also introduces a feedback and optimization mechanism, which continuously optimizes and adjusts according to the actual parameters after allocation and changes in the external environment, thereby ensuring the accuracy and efficiency of the resource allocation strategy.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for efficient allocation of laboratory resources based on big data analysis, the method comprising the following specific steps:

[0007] Monitoring and collection of micro-environment parameters: Various IoT sensors are deployed in various areas and experimental benches in the laboratory, including temperature and humidity sensors, air quality sensors, light intensity sensors, and electromagnetic interference intensity sensors. The collected data are transmitted to the central data processing server in real time through wireless or wired communication. The server receives and adds timestamps and location information to the data according to the rules, and organizes and stores them as structured data sets.

[0008] External environment data acquisition and integration: Build a weather data acquisition interface with the meteorological department or service provider, request and process weather data regularly as required, establish a resource idleness collection network with surrounding laboratories, share and receive data as agreed, and integrate and store external weather and surrounding laboratory resource data with internal microenvironment data on the central data processing server;

[0009] Analysis of the correlation between internal and external environment and resource demand: Construct a corresponding database table structure on the central data processing server to store the standard requirement range data of various experiments on microenvironment parameters and resource demand under the influence of the external environment, and pre-process the integrated internal and external environment data and resource demand standard requirement range data, determine the weight of each environmental factor by using the entropy weight method, calculate the weight coefficient by formula, and calculate the resource demand correlation index based on it, consider the interaction of environmental factors, adjust the correlation index, and obtain the adjusted correlation index, so as to establish a dynamic correlation model between the external environment and laboratory resource demand, and evaluate the optimization model performance;

[0010] Adaptive resource allocation strategy formulation: Based on the analysis results of the dynamic correlation model, the temperature and humidity are adjusted according to the internal and external environment and equipment conditions. For experimental equipment, it is borrowed from the surrounding areas according to demand and priority, and transportation and use coordination are arranged. Reagent resource allocation takes into account the weather and surrounding surplus, and the storage site and parameters are adjusted or shared. Site resource allocation is flexibly arranged for internal use or coordinated transfer to the surrounding areas based on internal and external factors to ensure the smooth progress of the experiment and optimize resource utilization;

[0011] Feedback and optimization: Continuously collect actual feedback data on changes in the laboratory's internal microenvironment and external environment, organize and store them in a classified manner, compare and analyze them with the allocation target parameters, evaluate the allocation effect, and use optimization algorithms to optimize and adjust resource allocation strategies based on the analysis results.

[0012] Furthermore, in the step of acquiring and integrating the external environment data, the external weather and surrounding laboratory resource data are fused and stored with the internal microenvironment data in the central data processing server, and the fusion formula is: Among them, D fusiom represents the fused data set, D i represents different types of data subsets, where i = 1, 2, ..., n, n is the total number of data subsets, ω i It corresponds to D i The weight coefficient, Corr(D i , E j ) represents the data subset D i Factor E that affects experimental resource requirements j The correlation coefficient of , where i = 1, 2, ..., n, m is the total number of factors affecting resource demand.

[0013] Furthermore, in the step of analyzing the correlation between the internal and external environment and resource demand, the weight of each environmental factor is determined by using the entropy weight method, the weight coefficient is calculated by the formula, and the resource demand correlation index is calculated based on it, and the calculation formula is: Among them, R represents the comprehensive resource demand correlation index, p represents the number of environmental factors considered, and x k is the actual observed value of the kth environmental factor, w k is the weight coefficient of the kth environmental factor calculated by the entropy weight method, H k is the information entropy of the kth environmental factor.

[0014] Furthermore, in the step of analyzing the correlation between the internal and external environment and resource demand, the correlation index is adjusted by considering the interaction of environmental factors to obtain an adjusted correlation index, the calculation formula of which is: Among them, R adj is the adjusted resource demand correlation index, p represents the number of environmental factors, λij is the interaction coefficient between the i-th environmental factor and the j-th environmental factor, x i 、x j are the actual observed values ​​of the i-th and j-th environmental factors, respectively. are the means of the observed values ​​of the corresponding environmental factors.

[0015] Furthermore, in the step of analyzing the correlation between the internal and external environment and resource requirements, λ ij is the interaction coefficient between the i-th environmental factor and the j-th environmental factor, and its calculation formula is: Among them, x i 、x j are the actual observed values ​​of the i-th and j-th environmental factors, respectively. are the means of the observed values ​​of the corresponding environmental factors, is the actual observed resource demand correlation corresponding to the s-th sample, It is the predicted resource demand correlation corresponding to the sth sample calculated without considering the interaction. The interaction coefficient λ is calculated by combining the difference between the two and the deviation of environmental factors. ij , to achieve quantitative analysis of the impact of interaction and adjustment of correlation index, if λ ij A positive value indicates that the two factors promote each other and affect resource demand. A negative value indicates mutual inhibition.

[0016] Furthermore, in the step of formulating the adaptive resource allocation strategy, for temperature and humidity adjustment, according to the external weather conditions and the requirements of the experiment for temperature and humidity, combined with the quantitative indicators of resource demand and the allocation priority, the temperature and humidity adjustment equipment is allocated and the temperature and humidity are accurately adjusted in combination with the laboratory internal microenvironment monitoring data. The allocation formula is: Among them, A TH represents the comprehensive decision result of temperature and humidity adjustment resource allocation, R TH is the resource demand correlation index corresponding to the current temperature and humidity, T TH is the preset threshold for starting temperature and humidity adjustment, T cur and H cur are the actual temperature and humidity values ​​monitored in the current internal microenvironment, T obj and H obj are the temperature adjustment target value and humidity adjustment target value calculated respectively, T lo , T hi are the lower and upper limits of the suitable temperature range corresponding to the experimental requirements, H lo , H hi are the lower and upper limits of the suitable humidity range, λ THis the comprehensive judgment threshold, E represents the urgency of the experiment, C is the adjustment capacity coefficient of the temperature and humidity adjustment equipment, V is the rate of change of the external environment temperature and humidity, v TH Indicates the temperature and humidity adjustment rate.

[0017] Furthermore, in the step of formulating the adaptive resource allocation strategy, for experimental equipment resource allocation, according to the resource allocation priority, when there is idle experimental equipment in the surrounding laboratories that is currently in urgent need of experimental equipment, an equipment borrowing request is initiated and the corresponding transportation and use coordination work is coordinated. Specifically, for the idle experimental equipment e in the surrounding laboratories, the criticality weight of the equipment to the current experiment is set to W e , the device idle time is L e , the matching degree between equipment performance and experimental requirements is M e , transportation cost coefficient C e , the device allocation priority P pri Calculation formula:

[0018] Furthermore, in the step of formulating the adaptive resource allocation strategy, for reagent resource allocation, the influence of external weather conditions on reagent storage conditions and the remaining reagents that can be allocated in surrounding laboratories are considered, and a more suitable storage site is allocated, the operating parameters of the reagent storage equipment are adjusted, or reagent sharing is allocated. Specifically, for reagent r, a total of m sites inside and around the laboratory are considered. For site s, the compatibility of its temperature and humidity with the optimal storage temperature and humidity of the reagent is set to The ventilation condition suitability is The light condition suitability is The overall stability coefficient of the site is S rs , then the suitability score F of site s for reagent r scσre The calculation formula is: Among them, α τ , β r , γ r , δ r is the corresponding weight coefficient. At the same time, for the calculation of the reagent preparation amount, assume that the current remaining amount of reagents in this laboratory is Q r The expected amount required for the experiment is Q n The remaining amount of the reagent that can be prepared in the surrounding laboratories is Q e , then the amount of the reagent Q prepared from the surrounding laboratories t Calculation formula:

[0019] Furthermore, in the step of formulating the adaptive resource allocation strategy, for the allocation of site resources, according to the impact of external environmental factors on the demand for different experimental sites and the availability of sites in surrounding laboratories, the order and time of use of the internal sites in the laboratory are flexibly allocated, or the experiment is coordinated and arranged to be transferred to a suitable site in the surrounding laboratories, so as to achieve efficient use of site resources. Specifically, for experiment p, the existing site A 1 and surrounding laboratory vacant space A 2 , assuming that the external environment affects the existing site A 1 The influence coefficient is The strictness of the site environment required by the experiment is R p , vacant site A 2 The environmental adaptation coefficient required by the experiment p is Site resource allocation decision factor D factor The calculation formula is: Set the site allocation decision threshold T limit , if D factor >T limit , then consider moving the experiment p from site A 1 Deployed to Site A 2 .

[0020] Furthermore, in the feedback and optimization step, an optimization algorithm is used to optimize and adjust the resource allocation strategy according to the analysis results, and the algorithm formula is: C t+1 =C t +α×Δ t , where Δ t It represents the resource allocation deviation index at time t, taking into account the actual allocation effect of different resources P i，t Effect of coordination with target T i，t The difference between the two, as well as the influence of time factors, are calculated by weighting the deviation of each resource according to the weight β i Perform weighted summation and combine the time difference tt 0 , to measure the overall deviation of resource allocation over time, C t is the resource allocation control parameter vector at time t, α is the adjustment coefficient, C t+1 is the resource allocation control parameter vector at time t+1 after optimization and adjustment. t According to the resource allocation deviation Δ t Dynamic adjustments are made so that resource allocation strategies can be continuously optimized with feedback from actual allocation results.

[0021] Compared with the existing technology, this method of efficient allocation of laboratory resources based on big data analysis has the following beneficial effects:

[0022] 1. The present invention uses big data analysis technology to establish a dynamic correlation model between the external environment and laboratory resource requirements, thereby accurately analyzing the complex relationship between external environmental changes and laboratory resource requirements, providing a strong basis for scientific and reasonable resource allocation, enabling the laboratory to more accurately predict and judge the demand level and allocation priority of each resource under different external environmental conditions, which not only avoids the unreasonable allocation and waste of resources, but also significantly improves the efficiency of resource allocation.

[0023] 2. The present invention realizes a comprehensive consideration of the factors affecting laboratory resource allocation by comprehensively integrating the internal microenvironment parameters of the laboratory with the external environmental data, making the resource allocation plan more adaptable and comprehensive. When facing various emergencies caused by changes in the external environment, the present invention can adjust the resource allocation strategy in time to ensure the smooth progress of the experiment.

[0024] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 This is a process operation diagram for an efficient allocation method of laboratory resources based on big data analysis;

[0027] Figure 2 This is a flow chart of an efficient laboratory resource allocation method based on big data analysis. DETAILED DESCRIPTION

[0028] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation mode, structure, characteristics and effects of the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0029] Embodiment 1

[0030] A certain food testing laboratory is mainly responsible for ingredient analysis, microbial testing, and hazardous substance testing of various foods. The laboratory is located near an urban industrial area with a relatively complex surrounding environment. The air quality is greatly affected by emissions from surrounding factories. The area has four distinct seasons with significant changes in temperature and humidity. At the same time, there are several laboratories in the surrounding area that are also engaged in food-related testing. They are equipped with many testing instruments with different functions and a large number of reagents for different testing projects, which places high demands on the timeliness and accuracy of resource allocation.

[0031] Temperature and humidity sensors, air quality sensors, light intensity sensors, and electromagnetic interference intensity sensors are installed in key locations such as the sterile operating room for food microbiology testing, laboratory benches where precision component analysis instruments are located, and various reagent storage areas. For example, a group of sensors is installed every 0.8 meters around each operating table in the sterile operating room to ensure that environmental conditions can be monitored in detail.

[0032] Each sensor collects data at the set sampling frequency. The temperature and humidity sensor collects data every 2 minutes, and the air quality sensor collects data every 10 minutes. The data is transmitted to the central data processing server via wired RS485 communication. After the server receives the data, it adds a timestamp accurate to the second and the corresponding detailed location information to each piece of data, organizes it into a structured data set and stores it in the SQL Server database to facilitate subsequent data query, analysis and management.

[0033] By cooperating with local environmental protection departments and professional meteorological service agencies, we use the API interface they provide to obtain weather data in the area, including temperature, humidity, air pressure, wind direction, wind speed, air quality index and other information, as well as extreme weather warnings (such as severe haze, heavy rain, etc.). We parse the XML format data, verify its legality and convert its format, and then store it in the database. We establish a data sharing network with several surrounding food testing laboratories, and use the FTP protocol based on SSL / TLS encryption for data transmission. We collect the idle resource status of the other party's laboratory at a frequency of every half an hour, such as the models of idle high-precision component analysis instruments and the available time periods, the area of ​​​​idle microbial testing special sites and usage restrictions, and the remaining amount of various food testing reagents that can be deployed. After checking the data integrity and formatting, we use the weighted fusion formula based on data correlation. Different weights ω are set according to the importance of each data in the food testing experiment i For example, air quality-related data has a relatively higher weight in the microbial detection scenario, integrating and storing external environmental data with internal microenvironment data to prepare for subsequent analysis.

[0034] Corresponding database tables are constructed in the central data processing server to store in detail the standard range data of resource requirements for various types of food testing experiments under different internal and external environmental conditions. For example, microbiological testing experiments require that the temperature of the sterile operating room be maintained at 20℃-25℃ and the humidity be controlled at 40%-60%. When the air quality is poor, the demand for air purification equipment resources increases. In component analysis experiments, the demand for heat dissipation guarantee resources for instruments is more prominent in high temperature weather. The integrated internal and external environmental data and resource demand standard range data are preprocessed, continuous data (such as temperature and humidity, air quality index values, etc.) are normalized to the [0, 1] interval, and categorical data (such as extreme weather warning categories, testing experiment types, etc.) are encoded and converted. The entropy weight method is used to determine the weight of each environmental factor, that is, through the formula Calculate, where p is the number of environmental factors, x ik is the actual observed value of the kth environmental factor, and then according to the formula Calculate the resource demand correlation index R, then consider the interaction of environmental factors, using the formula Adjust, where q is the number of samples, x i 、x j is the actual observed value of the environmental factor, is the mean, λ ij is the interaction coefficient, and the adjusted R adj As the final correlation index, a dynamic correlation model between the external environment and laboratory resource demand is established. For example, the correlation R between the demand for air purification equipment resources in microbial detection experiments under severe haze weather is obtained. adj At the same time, the priority of the demand for backup power supply resources has also been increased accordingly, providing a basis for subsequent deployment decisions.

[0035] If continuous high temperature weather causes the temperature inside the laboratory to rise, the dynamic correlation model analysis shows that the temperature and humidity in the area where the microbial detection experiment is located will soon exceed the appropriate range (resource demand correlation index R adjThe temperature and humidity in the medium part exceed the preset start threshold), the deployment server determines the temperature adjustment target value of 23°C and the humidity adjustment target value of 50% according to the corresponding formula based on the difference between the current micro-environment temperature and humidity and the experimental requirements (the current temperature is 28°C, the target temperature is 20°C-25°C, the current humidity is 65%, and the target humidity is 40%-60%) and the equipment performance (such as the refrigeration and dehumidification capacity coefficient of the air conditioner). In addition, the temperature and humidity adjustment rate is calculated based on the urgency of the experiment (because the microbial detection samples are time-limited, the urgency is set to 0.7), the rate of change of the external environment temperature and humidity (according to the meteorological data, the rate of change is moderate, set to 0.5) and the equipment adjustment capacity (the air conditioning adjustment capacity coefficient is set to 0.6), and the temperature and humidity adjustment rate is sent to the temperature and humidity adjustment equipment (air conditioning) in the microbial detection room. , dehumidifiers, etc.) to automatically adjust the environment. If there are idle microbial testing sites in the surrounding laboratories with more precise temperature and humidity control (determined by analyzing the idle situation of surrounding laboratory resources and the historical temperature and humidity data of the site), the deployment server will arrange for some important microbial testing samples to be transferred according to the pre-set deployment rules, after communicating and coordinating with the other party, and formulate a detailed plan for sample transfer and experiment development in the new site to ensure that the experiment is not affected by temperature and humidity. When a key component analysis instrument of the laboratory itself fails to maintain maintenance, and there are many food component analysis tasks, the deployment server will query the idle situation of surrounding laboratory resources in real time, and find that there is an idle component analysis instrument of the same type in a laboratory. According to the equipment deployment priority calculation formula (Where the criticality weight of the instrument to the current experiment is W e Set to 0.8, idle time L e The performance is 8 hours, and the matching degree between the performance and the experimental requirements is M e is 0.9, and the transportation cost coefficient C e is 0.3, and the allocation priority P is calculated prri The deployment server automatically generates an equipment borrowing agreement document and sends it to the other laboratory for review and confirmation. At the same time, it contacts a professional transportation company to arrange equipment transportation and coordinates the laboratory technicians to install, debug, and maintain the equipment after its arrival, to ensure that the food ingredient analysis experiment can be carried out smoothly.

[0036] During the period of haze weather, it is monitored that the air quality in the area where some test reagents sensitive to air quality (such as colorimetric reagents for microbial detection) are stored has deteriorated. The deployment server calculates the suitability of the reagent storage site based on the formula (For this reagent, the temperature and humidity compatibility In the current general storage site, the ventilation conditions are moderate and suitable Lower, light conditions suitable for the straightness Generally, the overall stability coefficient of the site is S rsHigher, set α according to reagent characteristics r =0.3, β r =0.2,γ r =0.1,δ r =0.4, and the F of the dedicated storage area equipped with air purification equipment in the laboratory is calculated. scorre The deployment server transfers these reagents to a dedicated storage site, adjusts the operating parameters of the air purification equipment to enhance the purification effect, and increases the frequency of air quality monitoring. If there are excess color reagents of the same color development reagents in the surrounding laboratories, the amount of reagent deployment is calculated based on the amount of reagent deployment. (It is known that the remaining amount of this reagent in this laboratory is Q r 15 pieces, estimated amount required for experiment is Q n 30 pieces, the remaining quantity can be allocated by surrounding laboratories e For 20 sticks, calculate the mixing amount Q t For example, if the surrounding factories are carrying out large-scale construction, which will generate large noise and vibration and affect the ongoing food harmful substance detection experiment (this experiment requires a high degree of environmental quietness), the deployment server will make reasonable reagent sharing deployment after communicating with the other party to reduce the reagent procurement cost and avoid waste. For site resource deployment, if the surrounding factories are carrying out large-scale construction, which will generate large noise and vibration and affect the ongoing food harmful substance detection experiment (this experiment requires a high degree of environmental quietness), the deployment server will make reasonable decisions based on the site resource deployment decision-making general formula. (The analysis shows that the current site is affected by the external environment is 0.7, and the experiment has strict requirements on the site environment. p The environmental adaptation coefficient of the surrounding laboratory vacant space and the experimental requirements is 0.8. is 0.8, and D factor Greater than the preset site allocation decision threshold T limit ), the deployment server coordinates and arranges to transfer the experiment to a suitable idle and quiet venue in the surrounding laboratories to continue. At the same time, personnel are organized to properly move the experimental equipment, samples and reagents, and prepare for equipment debugging at the new venue to ensure that the progress of the experiment is not affected.

[0037] After resource allocation is implemented, the internal microenvironment parameter changes are continuously collected through various sensors and the external environment changes are tracked. The actual parameters are fed back to the central data processing server. The server extracts the actual parameters and compares and analyzes the allocation target parameters. For example, the difference between the actual temperature and humidity of the microbial testing room and the set target temperature and humidity, the actual operating status of the component analysis instrument and the expected status, etc., according to the dynamic deviation adjustment algorithm based on time series C t+1 =C t +α×Δ t , where Δ t It represents the resource allocation deviation index at time t, taking into account the actual allocation effect of different resources Pi，t Effect of coordination with target T i，t The difference between the two, as well as the influence of time factors, are calculated by weighting the deviation of each resource according to the weight β i Perform weighted summation and combine the time difference tt 0 , to measure the overall deviation of resource allocation over time, C t is the resource allocation control parameter vector at time t, α is the adjustment coefficient, C t+1 It is the resource allocation control parameter vector at time t+1 after optimization and adjustment. The resource allocation deviation index is calculated. If it is found that the temperature and humidity adjustment rate of the microbial testing room does not meet expectations, resulting in too long adjustment time, the allocation server dynamically adjusts the control instruction parameters sent to the temperature and humidity adjustment equipment (such as increasing the control parameter value corresponding to the adjustment rate), and continuously optimizes the resource allocation strategy to better adapt to changes in internal and external environments, improve resource allocation efficiency and experimental success rate.

[0038] Embodiment 2

[0039] A materials science laboratory is dedicated to the research and development of new materials, performance testing, material structure analysis and other scientific research. The laboratory is located in a mountainous area, where the temperature difference between day and night is large, the air humidity fluctuates significantly with the seasons, and is often affected by special meteorological factors such as valley winds. There are related laboratories of several universities and scientific research institutions distributed around it. It is equipped with many advanced and expensive material testing and processing equipment such as high-precision electron microscopes, tensile testing machines, high-temperature sintering furnaces, etc., and also stores a large number of chemical reagents used for material synthesis, processing and analysis. Different material experimental projects have strict and diverse requirements on environmental conditions (such as temperature, humidity, electromagnetic environment, etc.) and various resources (covering equipment, sites, reagents, etc.).

[0040] In key experimental areas, such as electron microscope rooms, material synthesis reactor spaces, material performance test benches, and storage repositories for special reagents, a variety of IoT sensors are rationally arranged. Among them, temperature and humidity sensors are selected with an accuracy of ±0.15°C (temperature) and ±1.5%RH (relative humidity) to accurately capture subtle changes in ambient temperature and humidity. Air quality sensors have functions such as detecting water vapor content, trace harmful gases, and tiny particles in the air. The minimum detection limit can reach the ppm level, ensuring that changes in air quality can be detected in a timely manner. The measurement range of the light intensity sensor is set to 0-12000lux to meet the needs of different indoor experiments for monitoring light conditions. The electromagnetic interference intensity sensor has a resolution of microtesla level, which can accurately monitor the electrical The tiny fluctuations of the magnetic environment, for example, in the electron microscope room, a group of sensors are installed every 0.6 meters around each electron microscope to ensure that the environmental parameter information of each key position can be accurately obtained. Each sensor collects data according to the preset sampling frequency. The temperature and humidity sensors collect data every 1.5 minutes. The light intensity sensor collects data every 8 seconds based on the consideration of the impact of light on the performance test of some materials. The collected data is transmitted to the central data processing server in real time through the wireless WiFi communication network. On the server side, the received data will be added with a timestamp accurate to the second and the corresponding detailed location information, and then organized into a structured data set and stored in the PostgreSQL database, which is convenient for subsequent efficient query, in-depth analysis and data management operations.

[0041] By actively cooperating with local meteorological departments and professional monitoring organizations focusing on mountain climate research, the provided API interface is used to obtain weather data in the area. The data obtained not only covers conventional information such as temperature, humidity, air pressure, wind speed, precipitation, etc., but also includes meteorological data unique to mountainous areas, such as the direction and intensity of valley winds, and special weather warnings (such as heavy rain, cold waves, heavy fog, etc.). After receiving the returned data in JSON format, the server side of the laboratory will perform data parsing, legitimacy verification, and format conversion to ensure that the data is accurate and stored in the corresponding table structure of the database.

[0042] A stable data sharing network has been established with material-related laboratories of several surrounding universities and research institutions. The two parties exchange data based on the HTTPS protocol encrypted by SSL / TLS, and collect information on the idle resources of the other party's laboratory at a frequency of every two hours. This information covers the specific models of idle high-precision electron microscopes and the time periods in which they can be used, the size of the idle material synthesis site and the details of the supporting facilities, the remaining amount of special reagents for various material experiments that can be allocated, and other key contents. After receiving the data returned by the other party, a data integrity check will be performed first, and the data that does not meet the requirements will be recorded and notified to resend. Then, the qualified data will be formatted to match the internal data format, and finally a weighted fusion formula based on data correlation will be used. Where D fusiom Represents the fused data set, which serves as the unified data source for subsequent big data analysis. i Represents different types of data subsets, such as internal microenvironment data subset, external weather data subset, peripheral laboratory resource idle situation data subset, etc., i It corresponds to D i The weight coefficient ranges from 0 to 1 and The weight of the internal microenvironment data subset related to temperature and humidity is relatively high for electron microscope experiments. i , E j ) represents the data subset D i Factor E that affects experimental resource requirements j The correlation coefficient, j = 1, 2, ..., m, is the total number of factors affecting resource demand. Indicators such as the degree of dependence of different experiments on temperature, humidity, electromagnetic environment and other conditions can be used as influencing factors) The external environment data and the internal microenvironment data are integrated and stored to lay a comprehensive data foundation for the subsequent big data analysis.

[0043] A database table structure is carefully constructed in the central data processing server to store the standard requirement range data for microenvironmental parameters of various material science experiments and resource requirements under the influence of the external environment. For example, for electron microscope experiments, detailed records are required that the ambient temperature must be stably maintained at 20℃-22℃, and the humidity must be strictly controlled within the range of 45%-55%. When the external electromagnetic interference is strong (monitored by electromagnetic interference intensity sensors and comprehensive judgment with external environmental data), additional electromagnetic shielding measures need to be enabled, and the corresponding resource requirements (such as the number of electromagnetic shielding equipment enabled, power adjustment, etc.) are accurately entered. For material synthesis experiments, it is clear that the demand for drying equipment resources will increase significantly in seasons with high humidity. Different material performance test experiments also have specific requirements for the lighting, ventilation and other conditions of the site according to their test principles and requirements. All this information must be fully stored in the database.

[0044] The integrated internal and external environmental data and resource demand standard requirement range data are comprehensively preprocessed. For continuous data (such as actual observation values ​​of temperature and humidity, wind speed, electromagnetic interference intensity, etc.), the normalization method is used to map them to the [0, 1] interval to facilitate unified processing and comparative analysis of subsequent algorithms. For classified data (such as extreme weather warning categories, different types of material experimental projects, etc.), encoding conversion is performed to convert them into digital form for algorithm operation. The entropy weight method is used to determine the weight of each environmental factor, which is calculated by the following formula: Among them, p represents the number of environmental factors considered, covering all aspects from the laboratory internal microenvironment parameters (such as temperature and humidity, light intensity, electromagnetic interference intensity, etc.) to external environmental factors (such as weather conditions, surrounding laboratory resource status, etc.), x ik is the ith actual observed value of the kth environmental factor. For example, if k corresponds to the internal temperature and humidity, x ik It is the result of appropriate conversion or standardization of the temperature and humidity values ​​collected at a specific time. The values ​​of different environmental factors are preprocessed accordingly according to their own characteristics and data processing methods to ensure effective analysis under the same calculation framework. k is the information entropy of the kth environmental factor, which measures the amount of information and the degree of uncertainty contained in the environmental factor data. By calculating the information entropy of each environmental factor, its weight coefficient w is further derived. k , to achieve reasonable weight allocation of each environmental factor in the resource demand correlation analysis, and then according to the formula Calculate the resource demand correlation index R, where x kis the actual observed value of the kth environmental factor. The resource demand correlation index R is used to measure the overall demand for laboratory resources under the current internal and external environment. Its value range can be set between 0 and 1 according to the actual situation. The higher the value, the more urgent the resource demand, which provides a key quantitative reference for the subsequent resource allocation strategy. Further considering the interaction between different environmental factors, the resource demand correlation index R calculated above is adjusted using the formula: Among them, R adj is the adjusted resource demand correlation index. Compared with the initially calculated R, it further considers the mutual influence of environmental factors and more accurately reflects the actual demand for resources under the actual internal and external environment, providing strong support for formulating resource allocation strategies that are more in line with the actual situation. ij is the interaction coefficient between the i-th environmental factor and the j-th environmental factor, which is calculated through historical data samples. It reflects the degree and direction of the interaction between these two environmental factors on the correlation of resource demand. If λ i If it is a positive value, it means that the two factors promote each other and affect resource demand. If it is a negative value, it means that they inhibit each other. i 、x j are the actual observed values ​​of the i-th and j-th environmental factors, respectively, which are consistent with the previous explanation. are the means of the observed values ​​of the corresponding environmental factors. The difference between the observed value and the mean is used to reflect the deviation of the current environmental factors from the average level, and then the impact of their interaction on the correlation of resource demand is analyzed. is the actual observed resource demand correlation corresponding to the s-th sample, It is the predicted resource demand correlation corresponding to the sth sample calculated according to the previous formula without considering the interaction. The interaction coefficient λ is calculated by combining the difference between the two and the deviation of environmental factors. ij , to achieve quantitative analysis of the impact of interactions and accurate adjustment of correlation indicators.

[0045] Finally, a dynamic correlation model between the external environment and laboratory resource demand is established based on the above calculation process. The model can output quantitative indicators of the demand for various laboratory resources (such as the operating power of temperature and humidity control equipment, allocation suggestions for experimental equipment, reagent storage strategies, site use arrangements, etc.) under different external environmental conditions according to the real-time input of internal and external environmental data, as well as key information such as the priority ranking of various resource allocation, so as to provide a scientific and powerful basis for subsequent resource allocation decisions. For example, through model analysis, it is known that after heavy rain in mountainous areas, when the air humidity increases sharply, the correlation between the demand for drying equipment resources in material synthesis experiments is greatly improved. At the same time, the demand priority for backup power supply guarantee resources (to prevent power failures caused by humidity from affecting the operation of experimental equipment) is also correspondingly increased. Based on this, the laboratory can make corresponding resource allocation preparations in advance.

[0046] If high temperature and high humidity weather occurs continuously, it is found through dynamic correlation model analysis that the temperature and humidity of the electron microscope room are about to exceed the appropriate range (the temperature and humidity part of the resource demand correlation index exceeds the preset startup threshold). The deployment server will determine the temperature adjustment target value of 21°C and the humidity adjustment target value of 50% according to the difference between the current microenvironment temperature and humidity and the experimental requirements (the current temperature is 23°C, the target temperature range is 20°C-22°C, the current humidity is 58%, and the target humidity range is 45%-55%) and the performance parameters of the temperature and humidity adjustment equipment (such as air conditioners, dehumidifiers, etc.) (such as the refrigeration and dehumidification capacity coefficients of air conditioners, etc.) according to the corresponding calculation rules. At the same time, combined with the urgency of the electron microscope experiment (because some experimental samples need to be observed and analyzed in time, the urgency is set to 0.8), the rate of change of the external environment temperature and humidity (the rate of change is fast according to meteorological data, set to 0.6) and the equipment adjustment capacity (the air conditioning adjustment capacity coefficient is set to 0.7) , calculate the temperature and humidity adjustment rate through relevant formulas, and then send control instructions containing target values ​​and adjustment rates to the temperature and humidity adjustment equipment in the electron microscope room, so that it can automatically adjust the environment to ensure that the indoor temperature and humidity are restored to a range suitable for electron microscope experiments as soon as possible. If a laboratory in a surrounding university has an idle electron microscope site with more precise and stable temperature and humidity control (judged by analyzing the idle resources of surrounding laboratories and the historical temperature and humidity data of the site), the deployment server will communicate and coordinate with the other laboratory in accordance with the pre-set deployment rules, and then arrange for some electron microscope observation experiments with strict environmental requirements to be transferred to the site, and formulate a detailed sample transfer plan (including sample packaging, temperature and humidity protection measures during transportation, etc.) and experimental arrangements at the new site (such as equipment debugging, data transmission docking with the original laboratory, etc.), so as to ensure that the electron microscope experiment is not affected by changes in the temperature and humidity environment and proceeds smoothly.

[0047] When a key high-temperature sintering furnace in the laboratory breaks down and needs to be repaired, and there are multiple sets of sintering experiments on new materials that need to be carried out urgently, the deployment server will query the idle resources of surrounding laboratories in real time. If it is found that a laboratory of a scientific research institution has an idle high-temperature sintering furnace of the same type, it will calculate the equipment deployment priority according to the formula To evaluate the priority of deployment, where the criticality weight W of the high temperature sintering furnace to the current experiment e is set to 0.9 (given its indispensability in material sintering experiments), and the idle time L e The performance is 6 hours, and the matching degree between the performance and the experimental requirements is M e is 0.85 (determined by comparing equipment performance parameters with current experimental requirements), and the transportation cost coefficient C e =0.2 (taking into account factors such as transportation distance and mode of transportation), the allocation priority P is calculated. pri Based on this, the deployment server will automatically generate a detailed equipment borrowing agreement document (including detailed information of the borrowed equipment, borrowing time range, equipment use requirements, acceptance criteria when the equipment is returned, and the responsibilities and obligations of both parties), and send it to the other laboratory for review and confirmation. At the same time, it will actively coordinate and arrange the corresponding transportation and convenience coordination work, such as contacting a professional equipment transportation company, planning a suitable transportation route, formulating protective measures during transportation (ensuring that the equipment is not damaged by vibration, collision, etc. during transportation), arranging laboratory technicians to install and debug the equipment after its arrival, and communicating with the other laboratory on technical support and maintenance during the use of the equipment, etc., to ensure that the borrowed high-temperature sintering furnace can be put into use smoothly and meet the equipment resource requirements of the new material sintering experiment.

[0048] If the humidity in the storage area where certain humidity-sensitive material synthesis reagents (such as specific polymer polymerization initiators) are stored is detected to be increasing, the deployment server will calculate the suitability of the reagent storage site based on the formula To evaluate the suitability of each available site for the reagent, the temperature and humidity compatibility The ventilation conditions in the current general storage sites have decreased. Generally, the suitability of light conditions The impact on it is small (set to a lower value), the overall stability coefficient of the site S rs Higher, set α according to the characteristics of the reagent and the importance of each factor in the experiment τ =0.4, β r =0.3,γ r =0.1,δ r =0.2. After calculation, it is found that the F of a dedicated storage area equipped with dehumidification equipment and good ventilation in the laboratory is scoreThe value is the highest, so the deployment server will transfer these humidity-sensitive reagents to the dedicated storage site, and adjust the operating parameters of the dehumidification equipment accordingly (such as increasing the dehumidification power, increasing the dehumidification time, etc.) to enhance the control effect of the storage environment humidity, and at the same time increase the frequency of humidity monitoring in the area to ensure that the reagents are always in a suitable storage environment.

[0049] After resource allocation is implemented, the internal microenvironment parameter changes are continuously collected through various sensors and the external environment changes are tracked. The actual parameters are fed back to the central data processing server. The server extracts the actual parameters and compares and analyzes the allocation target parameters. For example, the difference between the actual temperature and humidity of the microbial testing room and the set target temperature and humidity, the actual operating status of the component analysis instrument and the expected status, etc., according to the dynamic deviation adjustment algorithm based on time series C t+1 =C t +α×Δ t , where Δ t It represents the resource allocation deviation index at time t, taking into account the actual allocation effect of different resources P i，t Effect of coordination with target T i，t The difference between the two, as well as the influence of time factors, are calculated by weighting the deviation of each resource according to the weight β i Perform weighted summation and combine the time difference tt 0 , to measure the overall deviation of resource allocation over time, C t is the resource allocation control parameter vector at time t, α is the adjustment coefficient, C t+1 It is the resource allocation control parameter vector at time t+1 after optimization and adjustment. The resource allocation deviation index is calculated. If it is found that the temperature and humidity adjustment rate of the microbial testing room does not meet expectations, resulting in too long adjustment time, the allocation server dynamically adjusts the control instruction parameters sent to the temperature and humidity adjustment equipment (such as increasing the control parameter value corresponding to the adjustment rate), and continuously optimizes the resource allocation strategy to better adapt to changes in internal and external environments, improve resource allocation efficiency and experimental success rate.

[0050] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A method for efficient allocation of laboratory resources based on big data analysis, characterized in that: The method comprises the following specific steps: Monitoring and collection of micro-environment parameters: Various IoT sensors are deployed in various areas and experimental benches in the laboratory, including temperature and humidity sensors, air quality sensors, light intensity sensors, and electromagnetic interference intensity sensors. The collected data are transmitted to the central data processing server in real time through wireless or wired communication. The server receives and adds timestamps and location information to the data according to the rules, and organizes and stores them as structured data sets. External environment data acquisition and integration: Build a weather data acquisition interface with the meteorological department or service provider, request and process weather data regularly as required, establish a resource idleness collection network with surrounding laboratories, share and receive data as agreed, and integrate and store external weather and surrounding laboratory resource data with internal microenvironment data on the central data processing server; Analysis of the correlation between internal and external environment and resource demand: Construct a corresponding database table structure on the central data processing server to store the standard requirement range data of various experiments on microenvironment parameters and resource demand under the influence of the external environment, and pre-process the integrated internal and external environment data and resource demand standard requirement range data, determine the weight of each environmental factor by using the entropy weight method, calculate the weight coefficient by formula, and calculate the resource demand correlation index based on it, consider the interaction of environmental factors, adjust the correlation index, and obtain the adjusted correlation index, so as to establish a dynamic correlation model between the external environment and laboratory resource demand, and evaluate the optimization model performance; Adaptive resource allocation strategy formulation: Based on the analysis results of the dynamic correlation model, the temperature and humidity are adjusted according to the internal and external environment and equipment conditions. For experimental equipment, it is borrowed from the surrounding areas according to demand and priority, and transportation and use coordination are arranged. Reagent resource allocation takes into account the weather and surrounding surplus, and the storage site and parameters are adjusted or shared. Site resource allocation is flexibly arranged for internal use or coordinated transfer to the surrounding areas based on internal and external factors to ensure the smooth progress of the experiment and optimize resource utilization; Feedback and optimization: Continuously collect actual feedback data on changes in the laboratory's internal microenvironment and external environment, organize and store them in a classified manner, compare and analyze them with the allocation target parameters, evaluate the allocation effect, and use optimization algorithms to optimize and adjust resource allocation strategies based on the analysis results.

2. According to claim 1, a method for efficient allocation of laboratory resources based on big data analysis is characterized in that: In the step of acquiring and integrating the external environment data, the external weather and surrounding laboratory resource data are fused and stored with the internal microenvironment data in the central data processing server, and the fusion formula is: Among them, D fusiom represents the fused data set, D i represents different types of data subsets, where i = 1, 2, ..., n, n is the total number of data subsets, ω i It corresponds to D i The weight coefficient, Corr(D i , E j ) represents the data subset D i Factor E that affects experimental resource requirements j The correlation coefficient is j=1, 2,…, m, where m is the total number of factors affecting resource demand.

3. According to the method of efficient allocation of laboratory resources based on big data analysis according to claim 1, it is characterized in that: In the step of analyzing the correlation between the internal and external environment and resource demand, the weight of each environmental factor is determined by using the entropy weight method, the weight coefficient is calculated by the formula, and the resource demand correlation index is calculated based on it. The calculation formula is: Among them, R represents the comprehensive resource demand correlation index, p represents the number of environmental factors considered, and x k is the actual observed value of the kth environmental factor, w k is the weight coefficient of the kth environmental factor calculated by the entropy weight method, H k is the information entropy of the kth environmental factor.

4. According to claim 1, a method for efficient allocation of laboratory resources based on big data analysis is characterized in that: In the step of analyzing the correlation between the internal and external environment and resource demand, the correlation index is adjusted by considering the interaction of environmental factors to obtain the adjusted correlation index, which is calculated as follows: Among them, R adj is the adjusted resource demand correlation index, p represents the number of environmental factors, λ ij is the interaction coefficient between the i-th environmental factor and the j-th environmental factor, x i 、x j are the actual observed values ​​of the i-th and j-th environmental factors, respectively. are the means of the observed values ​​of the corresponding environmental factors.

5. According to the method of efficient allocation of laboratory resources based on big data analysis according to claim 4, it is characterized in that: In the step of analyzing the correlation between internal and external environment and resource demand, λ ij is the interaction coefficient between the i-th environmental factor and the j-th environmental factor, and its calculation formula is: Among them, x i 、x j are the actual observed values ​​of the i-th and j-th environmental factors, respectively. are the means of the observed values ​​of the corresponding environmental factors, is the actual observed resource demand correlation corresponding to the s-th sample, It is the predicted resource demand correlation corresponding to the sth sample calculated without considering the interaction. The interaction coefficient λ is calculated by combining the difference between the two and the deviation of environmental factors. ij , to achieve quantitative analysis of the impact of interaction and adjustment of correlation index, if λ ij A positive value indicates that the two factors promote each other and affect resource demand. A negative value indicates mutual inhibition.

6. According to the method of claim 1, which is characterized by: In the step of formulating the adaptive resource allocation strategy, for temperature and humidity adjustment, according to the external weather conditions and the requirements of the experiment for temperature and humidity, combined with the quantitative indicators of resource demand and the allocation priority, the temperature and humidity adjustment equipment is allocated and the temperature and humidity are accurately adjusted in combination with the laboratory internal microenvironment monitoring data. The allocation formula is: Among them, A TH represents the comprehensive decision result of temperature and humidity adjustment resource allocation, R TH is the resource demand correlation index corresponding to the current temperature and humidity, T TH is the preset threshold for starting temperature and humidity adjustment, T cur and H cur are the actual temperature and humidity values ​​monitored in the current internal microenvironment, T obj and H obj are the temperature adjustment target value and humidity adjustment target value calculated respectively, T lo , T hi are the lower and upper limits of the suitable temperature range corresponding to the experimental requirements, H lo , H hi are the lower and upper limits of the suitable humidity range, λ TH is the comprehensive judgment threshold, E represents the urgency of the experiment, C is the adjustment capacity coefficient of the temperature and humidity adjustment equipment, V is the rate of change of the external environment temperature and humidity, v TH Indicates the temperature and humidity adjustment rate.

7. According to claim 1, a method for efficient allocation of laboratory resources based on big data analysis is characterized in that: In the step of formulating the adaptive resource allocation strategy, for the allocation of experimental equipment resources, according to the resource allocation priority, when there are idle experimental equipment in the surrounding laboratories and the laboratory is in urgent need of experimental equipment, an equipment borrowing request is initiated and the corresponding transportation and use coordination work is coordinated. Specifically, for the idle experimental equipment e in the surrounding laboratories, the criticality weight of the experimental equipment to the current experiment is set to W e , the device idle time is L e , the matching degree between equipment performance and experimental requirements is M e , transportation cost coefficient C e , the device allocation priority P pri Calculation formula:

8. The method for efficient allocation of laboratory resources based on big data analysis according to claim 1 is characterized in that: In the step of formulating the adaptive resource allocation strategy, for reagent resource allocation, the influence of external weather conditions on reagent storage conditions and the remaining reagents that can be allocated in the surrounding laboratories are considered, and a more suitable storage site is allocated, the operating parameters of the reagent storage equipment are adjusted, or reagent sharing is allocated. Specifically, for reagent r, a total of m sites inside and around the laboratory are considered. For site s, the compatibility between its temperature and humidity and the optimal storage temperature and humidity of the reagent is set to The ventilation condition suitability is The light condition suitability is The overall stability coefficient of the site is S rs , then the suitability score F of site s for reagent r scσre The calculation formula is: Among them, α τ , β r , γ r , δ r is the corresponding weight coefficient. At the same time, for the calculation of the reagent preparation amount, assume that the current remaining amount of reagents in this laboratory is Q r The expected amount required for the experiment is Q n The remaining amount of the reagent that can be prepared in the surrounding laboratories is Q e , then the amount of the reagent Q prepared from the surrounding laboratories t Calculation formula:

9. The method for efficient allocation of laboratory resources based on big data analysis according to claim 1, characterized in that: In the step of formulating the adaptive resource allocation strategy, for site resource allocation, according to the impact of external environmental factors on the demand for different experimental sites and the availability of vacant sites in surrounding laboratories, the order and time of using the internal sites in the laboratory are flexibly allocated, or the experiment is coordinated and arranged to be transferred to a suitable site in the surrounding laboratory to achieve efficient utilization of site resources. Specifically, for experiment p, the existing site A1 and the vacant site A2 in the surrounding laboratory, the influence coefficient of the external environment on the existing site A1 is The strictness of the site environment required by the experiment is R p , the environmental adaptation coefficient between the idle site A2 and the experimental p requirement is Site resource allocation decision factor D factor The calculation formula is: Set the site allocation decision threshold T limit , if D factor >T limit , then consider transferring experiment p from site A1 to site A2.

10. The method for efficient allocation of laboratory resources based on big data analysis according to claim 1, characterized in that: In the feedback and optimization step, the optimization algorithm is used to optimize and adjust the resource allocation strategy according to the analysis results. The algorithm formula is: C t+1 =C t +α×Δ t , where Δ t It represents the resource allocation deviation index at time t, taking into account the actual allocation effect of different resources P i，t Effect of coordination with target T i，t The difference between the two, as well as the influence of time factors, are calculated by weighting the deviation of each resource according to the weight β i The weighted sum is taken and combined with the time difference t-t0 to measure the overall deviation of resource allocation over time, C t is the resource allocation control parameter vector at time t, α is the adjustment coefficient, C t+1 is the resource allocation control parameter vector at time t+1 after optimization and adjustment. t According to the resource allocation deviation Δ t Dynamic adjustments are made so that resource allocation strategies can be continuously optimized with feedback from actual allocation results.

Images