An AI Internet of Things Multi-Domain Data Sharing Method and System

Abstract

The present invention discloses an AI Internet of Things multi-domain data sharing method and system, specifically relating to the technical field of the Internet of Things, which includes the following steps: acquiring target domain data and calculating its correlation with data in different domains based on the relevance weight to generate a correlation vector, and further analyzing the degree of correlation, and judging whether to establish a data pairing relationship according to the result; after summarizing all pairing relationships, generating a pairing relationship form and setting the actual time threshold of the data sharing channel; then using the genetic algorithm to optimize the allocation of resources for channel establishment, finally obtaining the optimal resource allocation scheme and applying it to the data sharing of the multi-domain Internet of Things system to achieve efficient cross-domain data collaboration and sharing; the present invention supports data fusion between multiple different domains, automatically judges which domain data needs to be shared and collaborated through AI, provides a cross-domain and multi-dimensional intelligent data processing solution, and ensures the rapid establishment of the data sharing channel.

Description

Technical Field

[0001] The present invention relates to the technical field of the Internet of Things. More specifically, the present invention relates to an AI Internet of Things multi-domain data sharing method and system. Background Art

[0002] With the rapid development of the Internet of Things, more and more devices and systems are interconnected through the Internet, generating a huge amount of data. However, this data is often scattered in different fields and platforms, forming so-called data "islands", where data in each field is not interconnected, greatly limiting the effective utilization of data.

[0003] In practical applications, Internet of Things systems such as intelligent transportation, smart healthcare, and intelligent city management need to comprehensively analyze data from different fields. For example, a traffic management system needs to share data from a medical emergency system to quickly allocate resources in case of a car accident; similarly, the medical system may also need to access traffic data to optimize the dispatching and route planning of ambulances.

[0004] However, most existing Internet of Things systems can only perform data interaction within a single field and lack an intelligent sharing mechanism for cross-domain data. In particular, when data needs to be shared between multiple Internet of Things fields, there are no effective means for correlation judgment and resource allocation, resulting in low data sharing efficiency and being unable to meet the real-time data requirements in dynamic and complex scenarios. Therefore, an AI Internet of Things multi-domain data sharing method and system are proposed herein. Summary of the Invention

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An AI Internet of Things multi-domain data sharing method, comprising the following steps:

[0007] Obtain target domain data and calculate the correlation between data in different domains using a weight fusion method based on relevance to obtain a correlation vector after pre-matching the target domain data with data in multiple different domains respectively;

[0008] Continue to perform a correlation degree analysis based on the paired correlation vector, and make a correlation level judgment according to the result of the correlation degree analysis;

[0009] Decide whether to establish a pairing relationship between the target domain data and the different domain data according to the determined correlation level, and summarize all the established pairing relationships to obtain a pairing relationship form of the target domain data and data in multiple different domains;

[0010] Set the actual time threshold for establishing the data sharing channel corresponding to the target pairing relationship based on the pairing relationship form, and then use the genetic algorithm to allocate resources for channel establishment, obtain the final resource allocation plan and apply it.

[0011] In a preferred embodiment, calculating the correlation between data in different fields based on the weight fusion method of relevance means:

[0012] Obtain the correlation coefficient r between the target domain data and the target dissimilar domain data to be pre-paired x，vi ; i represents the number corresponding to the pre-pairing, yi represents the type of the target dissimilar domain corresponding to the pre-pairing number i, and x represents the type of the target domain;

[0013] Then allocate weights according to the importance of the fields:

[0014] N represents the total number of pre-pairings, and wi represents the allocation weight corresponding to the pre-pairing number i.

[0015] In a preferred embodiment, the correlation vector after pre-pairing refers to summing up the correlation coefficient r corresponding to the pre-pairing number i x，yi and the importance allocation weight wi to obtain the correlation vector Gi = [r x，yi , wi].

[0016] The correlation coefficient r x，yi Is measured by the Pearson correlation coefficient.

[0017] In a preferred embodiment, continuing the correlation degree analysis based on the correlation vector after pairing means:

[0018] Obtain the correlation vector Gi = [r x，yi , wi] after pairing, extract the correlation coefficient r x，yi And perform the following conversions:

[0019] R1i = |r x，yi | * C;

[0020] R2i = |r x，yi | α * C;

[0021] R3i = ln(1 + |r x，yi |) * C;

[0022] α is greater than 1, R1i represents the type-I conversion value corresponding to the correlation coefficient r x，yi , R2i represents the type-II conversion value corresponding to the correlation coefficient r x，yi , and R3i represents the correlation coefficient r x，yiThe corresponding type III conversion value, and then replace all types of conversion value pairs r x，yi to obtain the vector Fi = [R1i, R2i, R3i, wi] under the relevant degree analysis.

[0023] In a preferred embodiment, making a relevant level judgment according to the relevant degree analysis result means:

[0024] Taking the vector Fi = [R1i, R2i, R3i, wi] under the relevant degree analysis as the input variable, taking the relevant level of the pre-matched number i as the output variable, performing fuzzy processing on the input variable, converting the value of the input variable into a fuzzy set, performing fuzzy processing on the output variable, converting the output variable into a fuzzy set, formulating fuzzy rules to describe the relevant levels under different combinations of data types, and inferring the fuzzy input variable through the fuzzy rules to obtain the relevant level of the pre-matched number i.

[0025] In a preferred embodiment, deciding whether to establish a pairing relationship between the target domain data and the dissimilar domain data according to the judged relevant level means:

[0026] Obtain the relevant level of the pre-matched number i, compare it with the preset level threshold. If the relevant level of the pre-matched number i is greater than or equal to the preset level threshold, the pairing relationship of the pre-matched number i is retained. If the relevant level of the pre-matched number i is less than the preset level threshold, the pairing relationship of the pre-matched number i is deleted.

[0027] In a preferred embodiment, the acquisition logic of the actual time threshold for establishing the data sharing channel is:

[0028] Di represents the relevant level corresponding to the retained pairing relationship i, fi represents the preset urgency adjustment coefficient in the current scenario, T0 represents the preset basic duration, Zi represents the preset load index data of the data fusion module in the current scenario, ZB represents the standard value corresponding to the load index data of the data fusion module in the current scenario, and Si represents the actual time threshold for establishing the data sharing channel corresponding to the pairing relationship i.

[0029] In a preferred embodiment, using the genetic algorithm for resource allocation in channel establishment means:

[0030] Coding and initial population: Encoding the resource quantity allocation parameter group of the channel, that is, the decision variable, into the form of a chromosome and randomly generating m chromosomes as the initial population;

[0031] Fitness evaluation: Define the constraint that the establishment time of each data sharing channel cannot exceed its actual time threshold. At the same time, calculate the total establishment duration value of all data sharing channels. The total establishment duration value is the fitness value of the chromosome, and the goal is to minimize the total establishment duration value of all data sharing channels.

[0032] Selection operation: Use the roulette wheel selection method to screen the offspring as the new parents.

[0033] Crossover operation: Randomly exchange the data in different parental chromosomes.

[0034] Mutation operation: Randomly select and adjust the data of different offspring chromosomes.

[0035] Iteration and termination conditions: When the preset termination conditions are reached, select the chromosome with the highest fitness from the final population for decoding to obtain the optimal resource allocation scheme.

[0036] In a preferred embodiment, an AI Internet of Things multi-domain data sharing system includes:

[0037] Pre-pairing module, which obtains the target domain data and calculates the correlation between different domain data using a relevance-based weight fusion method to obtain the correlation vectors after pre-pairing the target domain data with multiple different domain data respectively.

[0038] Secondary pairing module, which continues to analyze the degree of correlation based on the paired correlation vectors, and makes a correlation level judgment according to the analysis results of the degree of correlation. According to the determined correlation level, it decides whether to establish a pairing relationship between the target domain data and the different domain data, and summarizes all the established pairing relationships to obtain the pairing relationship form of the target domain data and multiple different domain data.

[0039] Data sharing channel establishment module, which sets the actual time threshold for the establishment of the data sharing channel corresponding to the target pairing relationship based on the pairing relationship form, and then uses the genetic algorithm for resource allocation for channel establishment, obtains the final resource allocation scheme and applies it.

[0040] Technical effects and advantages of the present invention:

[0041] The present invention realizes intelligent data sharing among multiple domains of the Internet of Things through AI technology, breaks the data "island" problem in traditional systems, can dynamically analyze the correlation of data in different application scenarios (such as intelligent transportation, smart healthcare), ensures the efficient flow of valuable data between different domains, and improves data utilization.

[0042] By using a genetic algorithm to optimize the allocation of resources in the data sharing process, the present invention can automatically adjust the allocation schemes of network bandwidth, CPU, and memory according to the real-time changes in different scenarios and system loads. Compared with the traditional fixed resource allocation method, the present invention can reduce resource waste while ensuring the rapid establishment of a data sharing channel, improving the overall operating efficiency of the system.

[0043] The present invention is particularly applicable to emergency scenarios (such as car accidents, natural disasters, etc.). Through an intelligent emergency adjustment mechanism and the rapid establishment of a data channel, the delay in data transmission and processing can be significantly reduced. The system can quickly share high-priority data according to real-time needs, greatly enhancing the emergency response speed and providing effective support for on-site decision-making.

[0044] The present invention supports data fusion between multiple different fields. Through the correlation analysis of AI, the system can automatically determine which field data needs to be shared and collaborated, providing a cross-domain, multi-dimensional intelligent data processing solution, which is particularly applicable to complex scenarios such as smart city management, medical emergency, and intelligent transportation.

[0045] By strictly controlling the establishment time of the data sharing channel and resource allocation, the present invention ensures the stability of the system under high load. At the same time, through correlation analysis and an optimized resource allocation strategy, unnecessary data transmission is reduced, avoiding system overload or delay, and enhancing the security and reliability in the data sharing process. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] For the convenience of those skilled in the art to understand, the present invention will be further described below in conjunction with the accompanying drawings;

[0047] Figure 1 It is a schematic diagram of a method for sharing multi-domain data in an AI Internet of Things of the present invention.

[0048] Figure 2 It is a schematic diagram of a system for sharing multi-domain data in an AI Internet of Things of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0050] Refer to Figure 1 - Figure 2 The following embodiments are obtained:

[0051] Example 1: An AI Internet of Things multi-domain data sharing method, comprising the following steps:

[0052] Collect multi-dimensional data through Internet of Things devices in different domains (such as transportation, healthcare, industry, etc.), where the data includes structured and unstructured types. Clean, format, and standardize the collected data to ensure the comparability and consistency of data in different domains. Then obtain the target domain data and calculate the correlation between the data in different domains using a weight fusion method based on relevance, obtaining the correlation vectors after pre-pairing the target domain data with the data in multiple different domains respectively; the purpose of this step is to identify the degree of association between the target domain data and the data in other different domains. By calculating the relevance of the data in each domain, the potential connections between cross-domain data can be determined, providing a basis for subsequent data sharing. The weight fusion method further precise the calculation of the correlation of the data in different domains, ensuring accurate results.

[0053] A different domain refers to a data domain that is different from the target domain and has an independent data source. The data in different domains is usually related to the data in the target domain but comes from different systems or platforms. Different domains can cover multiple Internet of Things application scenarios, and by calculating the data correlation between these domains, it can be determined whether data sharing is required. The following are some typical examples of different domains:

[0054] In the field of intelligent transportation, the medical emergency system belongs to a different domain. For example, in the scenario of a traffic accident, data such as the arrival time of the ambulance and the availability of emergency resources (such as the number of medical staff and the availability of emergency equipment) belong to different domains. These data are associated with the target domain (such as traffic flow and accident location), helping to make quick decisions and resource scheduling.

[0055] In intelligent city management, the fire protection system can be regarded as a different domain. For example, in the scenario of a building fire, data such as the arrival time of the fire truck and the scheduling data of fire protection resources belong to different domains. These data are associated with the data of the intelligent city's traffic management system and monitoring system, and sharing these data can improve the rescue efficiency.

[0056] In the agricultural Internet of Things system, environmental monitoring data can be used as a different domain. For example, data such as the meteorological conditions and soil humidity of farmland come from the environmental monitoring system and are different from the data in the agricultural production system (such as crop growth and irrigation data). The data in these different domains can help the intelligent agricultural system optimize production decisions.

[0057] Continue the correlation degree analysis based on the paired correlation vectors, and make a correlation level judgment according to the results of the correlation degree analysis; the correlation degree analysis is used to evaluate the specific association strength between the target domain data and the data in different domains. Through further analysis, the correlation level judgment provides a decision basis for the adaptability of cross-domain data, helping to identify which domain data is most suitable for sharing and collaboration.

[0058] Decide whether to establish a pairing relationship between the target domain data and the data in the different domain according to the judged correlation level, summarize all the established pairing relationships, and obtain a pairing relationship form of the target domain data and the data in multiple different domains; when the correlation levels of some data in different domains meet the requirements, these data will establish a pairing relationship with the target domain data. By summarizing the established pairing relationship form, it can be clear which data will be used for sharing. This step realizes the transition from theoretical analysis to actual data sharing and prepares for the implementation of data sharing.

[0059] Set the actual time threshold for establishing the data sharing channel corresponding to the target pairing relationship based on the pairing relationship form. The setting of the time threshold is to optimize the process of establishing the sharing channel and ensure the efficiency of data sharing. According to the requirements and sharing time requirements of different data, setting a reasonable time threshold can maximize resource utilization and reduce latency. Then use the genetic algorithm for resource allocation in channel establishment, obtain the final resource allocation plan and apply it. The genetic algorithm is used to optimize resource allocation to ensure that when establishing a cross-domain data sharing channel, each resource can be allocated in an optimal way. The application of the genetic algorithm can effectively improve the sharing efficiency, reduce resource waste, and ensure the stability of the sharing channel. The finally obtained resource allocation plan is applied to ensure the smooth progress of data sharing.

[0060] Calculating the correlation between data in different domains based on the weight fusion method of relevance means:

[0061] Obtain the correlation coefficient r between the pre-paired target domain data and the target different domain data x，yi; i represents the number corresponding to the pre - pairing, yi represents the type of the target different field corresponding to the pre - pairing number i, and x represents the type of the target field; the correlation coefficient is used to measure the association strength between the data of the target field and the different fields. This coefficient usually takes values between - 1 and 1. The closer the value is to 1, the stronger the positive correlation between the two; the closer it is to - 1, the stronger the negative correlation; and being close to 0 indicates that the two are almost uncorrelated. The weight is assigned according to the importance of each field, reflecting the priority occupied by a certain field in the pairing process. Weight fusion will make the correlation calculation more accurate, taking into account the influence degree of data in different fields. Summarize the correlation vectors after pairing. Through the correlation vector Gi, the association degree between the data of each field can be comprehensively reflected. Combining with the weights can generate a more accurate association measure result for subsequent relevant level judgment.

[0062] The weight represents the weight assigned to each field in the pairing process, which is assigned according to the importance of the field. The larger the weight, the higher the priority of the field in the pairing, and vice versa. Assign weights according to the importance of the field:

[0063] N represents the total number of pre - pairings, and wi represents the assigned weight corresponding to the pre - pairing number i. The correlation vector after pre - pairing refers to summarizing the correlation coefficient r corresponding to the pre - pairing number i x，yi and the importance - assigned weight wi to obtain the correlation vector Gi = [r x，yi , wi]. The correlation vector is the result after synthesizing the correlation coefficient and the weight, reflecting the association strength and its importance between the data of the target field and the different fields.

[0064] The correlation coefficient r x，yi is measured through the Pearson correlation coefficient. For example, in the car accident scenario, the process of determining the correlation coefficient between the traffic management field and the medical and health field is as follows:

[0065] Define variables: First, it is necessary to clarify the key data variables between the traffic management field and the medical and health field to determine their association. For example: traffic flow (such as the number of vehicles passing through the accident location per unit time); vehicle speed at the accident location; road congestion level (which can be measured by the congestion index or speed distribution); traffic signal status (the proportion of red lights and green lights) at the time of the accident; arrival time of the ambulance; number of injured and the severity of their injuries; availability of hospital emergency resources (such as the number of beds, emergency equipment, and the number of medical staff); response time of ambulance dispatching.

[0066] By collecting historical data, key variables in the fields of traffic management and healthcare can be statistically analyzed. For example, the following information can be obtained from historical records of traffic accidents: traffic flow and congestion at the accident site, the time it takes for the ambulance to arrive at the scene after the alarm, the distribution of the arrival time of the ambulance under different congestion conditions or traffic flows, the use of medical resources in the hospital and the rescue response time. These data can be collected through the Internet of Things and other means to form a multidimensional data set.

[0067] It should be noted that the target domain data and multiple different domain data mentioned in the present invention are pre-paired, which means that in a certain application scenario such as a car accident scenario, the target domain data refers to the target data variable in the field such as traffic flow, and the different domain data refers to the arrival time of the ambulance and the number of medical staff. The correlation coefficient between the traffic flow and the arrival time of the ambulance is calculated, and the correlation coefficient between the traffic flow and the number of medical staff is calculated. Finally, the correlation strength of the relevant data can be judged in the current application scenario, providing a basis for whether data sharing is ultimately needed.

[0068] Continuing the correlation analysis based on the paired correlation vector means: obtaining the paired correlation vector Gi = [r x，yi , wi], extract the correlation coefficient r x，yi And do the following conversion:

[0069] R1i=|r x，yi |*C; R2i=|r x，yi | α *C; R3i = ln(1+|r x，yi |)*C;

[0070] α is greater than 1, C is a positive constant, and R1i represents the correlation coefficient r x，yi The corresponding type 1 conversion value is amplified by its absolute value. Here C is a constant factor and is a positive number, which is usually used to amplify or reduce the converted value. The role of the absolute value is to avoid the positive and negative signs affecting the conversion results and focus on the correlation strength itself. R2i represents the correlation coefficient r x，yi The corresponding type II transformation value is calculated by x，yi The value is further magnified or reduced by raising it to the αth power. The purpose of setting α greater than 1 is to enhance the sensitivity to high correlation coefficients, that is, the stronger the correlation, the greater the difference in the value obtained after the power amplification. For weak correlation, the difference will not be too obvious due to the effect of the αth power. R3i represents the correlation coefficient r x，yiThe corresponding type-III conversion value adopts a logarithmic conversion method. The characteristic of the logarithmic function is to expand smaller values and compress larger values. Therefore, this conversion can amplify the coefficients with relatively weak correlations, and at the same time play a certain inhibitory effect on extremely large or extremely small correlation values to prevent them from overly dominating the results. Then, all types of conversion values are replaced with r x，yi to obtain the vector Fi = [R1i, R2i, R3i, wi] under the correlation degree analysis. This comprehensive vector reflects the correlation calculation results under multiple conversion methods, making the data with high correlations more significantly amplified, which is convenient for more detailed correlation analysis and judgment.

[0071] Making a correlation level judgment based on the correlation degree analysis results means:

[0072] Taking the vector Fi = [R1i, R2i, R3i, wi] of the correlation degree analysis as the input variable and the correlation level of the pre-matched number i as the output variable, perform fuzzy processing on the input variable, convert the value of the input variable into a fuzzy set, perform fuzzy processing on the output variable, and convert the output variable into a fuzzy set. Formulate fuzzy rules to describe the correlation levels under different combinations of data types. Infer the correlation level of the pre-matched number i by passing the fuzzified input variable through the fuzzy rules. The correlation level is the final result judgment of the input variable, indicating that the correlation degree between the input data is divided into different levels. The goal of level division is to classify the correlations under different combinations for subsequent use or further analysis. The first step in the fuzzy logic process is to perform fuzzy processing on the input correlation vector. Convert the precise numerical data into linguistic fuzzy sets, such as "low correlation", "medium correlation", and "high correlation", etc. This step is to facilitate processing in the subsequent fuzzy inference. According to historical data or prior knowledge, formulate fuzzy rules to describe the corresponding correlation levels under different correlation combinations. For example, there can be the following rules: If the first-level conversion value is high, the second-level conversion value is high, and the third-level conversion value is medium, then the correlation level is high; If the first-level conversion value is low, the second-level conversion value is low, and the third-level conversion value is high, then the correlation level is low. Through these rules, different combinations of correlation vectors can be mapped to the corresponding levels. Logical inference based on the fuzzy rules and the fuzzified input variables. After each input variable is converted into a fuzzy set, it is matched through the fuzzy rule set to infer a corresponding correlation level. The result of the inference represents a comprehensive judgment of different correlations on multiple input dimensions. Finally, defuzzify the result of the fuzzy inference to obtain a clear output of the correlation level. For example, through inference, the correlation level of a certain data pair can be obtained as "high" or "medium". This process is the output from the fuzzy space back to the actual numerical value. Through the fuzzy logic system, the entire process converts multiple different correlation conversion values and weight inputs into linguistic fuzzy sets, and after the inference of the fuzzy rules, a specific correlation level is obtained. This level is used for the final evaluation and judgment of the correlation between the data in the target domain and the data in the different domain.

[0073] Determining whether to establish a pairing relationship between the target domain data and the dissimilar domain data based on the obtained relevance level means: obtaining the relevance level of the pre-pairing number i, comparing it with the preset level threshold. If the relevance level of the pre-pairing number i is greater than or equal to the preset level threshold, the pairing relationship of the pre-pairing number i is retained; if the relevance level of the pre-pairing number i is less than the preset level threshold, the pairing relationship of the pre-pairing number i is deleted. In the previous steps, the relevance level of each pre-pairing number was obtained through fuzzy logic reasoning. This level represents the association strength between the target domain data and the dissimilar domain data. By assigning a relevance level to each pairing number, we can evaluate the quality of each data pairing.

[0074] To ensure the quality and effectiveness of data sharing, there is a preset level threshold in the system. This threshold represents the minimum standard for establishing a data pairing relationship. Only when the relevance levels of two data are higher than or equal to this threshold will the system consider the association between these data to be strong enough to be worthy of retaining the pairing relationship. When the relevance level of a certain pre-pairing number is higher than or equal to the preset level threshold, it means that the association degree between the target domain data and the dissimilar domain data is relatively strong. At this time, the system believes that these data pairs are valuable for sharing, so it will retain their pairing relationships and allow continued data sharing or resource collaboration in subsequent processes. If the relevance level of a certain pre-pairing number is lower than the preset level threshold, it indicates that the association degree between the target domain data and the dissimilar domain data is relatively weak. At this time, the system believes that the sharing between these data has little practical significance or insufficient association value. Therefore, this pairing relationship will be deleted and these data will no longer be shared. This process helps to exclude unimportant data pairs, reducing resource waste and the burden of data processing.

[0075] By comparing the relevance level with the threshold, the system can screen out high-quality and strongly relevant data pairs for sharing, thereby improving the efficiency and reliability of data sharing. This avoids the exchange of unnecessary low-correlation data and ensures the reasonable allocation of system resources.

[0076] The acquisition logic for the actual time threshold for establishing the data sharing channel is as follows:

[0077] Di represents the relevant level corresponding to the remaining pairing relationship i. The higher the relevant level, the stronger the correlation between data pairs, and the greater the necessity of data sharing. Therefore, the impact on the actual time is reduced by 1 - Di * fi. The higher the relevant level, the shorter the time to establish the sharing channel. fi represents the preset emergency adjustment coefficient in the current scenario, which is used to adjust the time requirement in a specific scenario. For example, in an emergency scenario (such as disaster relief), time is particularly important, and the adjustment coefficient will affect the time to establish the data sharing channel according to the degree of emergency. The higher the emergency, the shorter the time. This reflects the flexibility of the system, which can adjust the response speed according to the actual scenario. T0 represents the preset basic duration, which is the basic time for establishing the data sharing channel, indicating the standard time required for channel establishment when there is no other factor affecting. Introducing the basic time can ensure that the system has a standardized time framework. Zi represents the preset load index data of the data fusion module in the current scenario, and ZB represents the standard value corresponding to the load index data of the data fusion module in the current scenario. These two indicators are used to measure the system load in the current scenario. The greater the system load, the longer the resource allocation time. Conversely, when the system load is smaller, the time to establish the channel can be shortened. Standardizing and comparing the load index data can dynamically adjust the time to establish the channel, so that the system can operate reasonably under different load conditions. The load index data is, for example, one of the parameters of various system performances and resource usages in this AI Internet of Things multi-domain data sharing system, specifically depending on the application scenario of the system. The following are some common examples of load index data. CPU usage rate is one of them: CPU usage rate represents the load level of the processor during system operation. If the CPU usage rate is close to 100%, it means the system is running at full load and the resources are close to the limit. By monitoring the CPU usage rate, the time to establish the data sharing channel can be dynamically adjusted, extending the time when the CPU load is high to avoid further overloading of the system. Memory usage rate reflects the RAM (Random Access Memory) resources consumed during system operation. If the memory usage rate is high (for example, exceeding 80%), the performance of the system may decline, especially when dealing with large-scale data processing. High memory load may affect the speed of data sharing, so it can also be used as a load index. Si represents the actual time threshold for establishing the data sharing channel corresponding to the pairing relationship i. The smaller the time threshold, the faster the data sharing channel should be established, reducing the waiting time. This indicates that under the current conditions, the system can establish the data sharing channel for this pairing relationship at a faster speed to ensure the timely transmission and use of data. If this data sharing pairing involves an emergency scenario (adjusted by the emergency adjustment coefficient fi), the system will accelerate the establishment of the channel to ensure the rapid transmission and use of data in the emergency scenario.This is crucial for the emergency response to unexpected events. For example, in the scenario of a traffic accident, urgent medical data and traffic data need to be shared as soon as possible.

[0078] Resource allocation for channel establishment using genetic algorithms refers to:

[0079] Coding and initial population: First, the problem of resource quantity allocation for data sharing channels needs to be transformed into a form that can be processed by genetic algorithms. Here, the resource allocation parameters of each channel (such as bandwidth, CPU allocation, memory, etc.) are encoded into chromosomes, that is, each chromosome represents a possible resource allocation scheme. By randomly generating multiple (such as m) different chromosomes, an initial population is formed. These chromosomes respectively represent the resource allocation combinations that the system may adopt. The main purpose of this step is to provide multiple possible solutions for the genetic algorithm to ensure a wide range of initial exploration of the algorithm.

[0080] Fitness evaluation: The fitness value is used to measure the quality of each chromosome (i.e., resource allocation scheme). Here, the fitness value is measured by the total establishment duration, that is, after the system allocates resources to all data sharing channels, the sum of the establishment times of each channel. The goal is to minimize this total time as much as possible to ensure that all channels are established as soon as possible. The total duration cannot exceed the actual time threshold of each channel (this threshold is calculated according to the formula discussed above). The purpose of fitness evaluation is to evaluate each resource allocation scheme to see if it is effective and how efficient it is. A lower total establishment duration means a higher fitness value, which indicates that this scheme can complete the establishment of all channels faster and the resource allocation is more reasonable.

[0081] Selection operation: The selection operation retains chromosomes with higher fitness by simulating the process of natural selection. Through the "roulette wheel selection method", that is, according to the fitness level of each chromosome, it is given the corresponding probability to enter the next generation. Chromosomes with higher fitness have a higher probability of being selected, thus increasing the chance of high-quality solutions continuing to evolve in subsequent iterations. This process ensures the retention of better resource allocation schemes while eliminating poorer ones, making the overall resource allocation scheme in the population gradually optimized.

[0082] Crossover operation: The crossover operation simulates the process of gene recombination by exchanging data (resource allocation parameters) in different parent chromosomes. In this way, the new chromosomes may inherit the excellent characteristics of the parent chromosomes and further explore new solution spaces to generate better resource allocation schemes. The crossover operation can generate more new possibilities by combining existing resource allocation schemes, thus increasing the chance of finding the optimal solution.

[0083] Mutation operation: The mutation operation in the genetic algorithm is used to prevent the population from falling into local optimal solutions. By randomly selecting and slightly adjusting some genes (resource allocation parameters) in the offspring chromosomes, more possible solutions can be explored, and the chance of finding the global optimal solution can be increased. For example, randomly increasing or decreasing the bandwidth allocation of a certain channel, or changing the proportion of CPU resource allocation. Ensuring that the population has sufficient diversity can avoid the algorithm from falling into local optima and guarantee the global search ability of the genetic algorithm.

[0084] Iteration and termination conditions: After completing the selection, crossover, and mutation operations in each generation, the algorithm will continuously iterate to generate new populations until the preset termination conditions are met (such as reaching the specified number of iterations, or the fitness value of the optimal solution found has not changed significantly in consecutive generations). When the termination conditions are satisfied, the chromosome with the highest fitness is selected from the final population, and this chromosome is the optimal resource allocation scheme. Through continuous iteration, the genetic algorithm can gradually optimize the population and finally find a resource allocation scheme that can minimize the total time for establishing data sharing channels.

[0085] Form of the final resource allocation scheme: The final resource allocation scheme is a combination of a set of parameters, representing the resources allocated to each data sharing channel. For example: Channel 1: Bandwidth 50Mbps, CPU 10%, Memory 500MB; Channel 2: Bandwidth 30Mbps, CPU 15%, Memory 600MB; Channel 3: Bandwidth 70Mbps, CPU 20%, Memory 700MB; This resource allocation scheme can minimize the total establishment time of all data sharing channels, ensure that each channel is established as soon as possible within the specified time threshold, and effectively utilize system resources.

[0086] Embodiment 2: An AI Internet of Things multi-domain data sharing system, comprising:

[0087] A pre-pairing module, which acquires target domain data and calculates the correlation between different domain data using a weight fusion method based on relevance, to obtain a correlation vector after pre-pairing the target domain data with multiple different domain data respectively;

[0088] A secondary pairing module, which continues to perform a correlation degree analysis based on the paired correlation vector, and makes a correlation level judgment according to the result of the correlation degree analysis. According to the determined correlation level, it decides whether to establish a pairing relationship between the target domain data and the different domain data, and summarizes all the established pairing relationships to obtain a pairing relationship form of the target domain data and multiple different domain data;

[0089] A data sharing channel establishment module, which sets the actual time threshold for establishing the data sharing channel corresponding to the target pairing relationship based on the pairing relationship form, and then uses the genetic algorithm to perform resource allocation for channel establishment, obtains the final resource allocation scheme and applies it.

[0090] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0091] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0092] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0093] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0094] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all of them should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An AI Internet of Things multi-domain data sharing method, characterized in that: The following steps are involved: Obtain target domain data and use a weight fusion method based on relevance to calculate the correlation between data in different domains, and obtain a correlation vector after the target domain data is pre-paired with multiple different domain data; Continue to perform correlation analysis based on the paired correlation vectors, and make correlation level judgment based on the correlation analysis results; Determine whether to establish a pairing relationship between the target domain data and the different domain data according to the correlation level obtained by judgment, summarize all established pairing relationships, and obtain a pairing relationship form between the target domain data and multiple different domain data; The actual time threshold for establishing the data sharing channel corresponding to the target pairing relationship is set based on the pairing relationship form, and then the genetic algorithm is used to allocate resources for channel establishment, and the final resource allocation plan is obtained and applied; Continuing the correlation analysis based on the paired correlation vector means: Get the paired correlation vector , extract the correlation coefficient And do the following conversion: ； ； ； greater than 1, is a normal number, Represents the correlation coefficient The corresponding type-one conversion value, Represents the correlation coefficient The corresponding type-two conversion value, Represents the correlation coefficient The corresponding three-type conversion value, and then all types of conversion value pairs Replace it and get the vector under the correlation analysis ; i represents the number corresponding to the pre-pairing, Indicates the type of target different field corresponding to pre-pairing number i, Indicates the type of the target domain; represents the allocation weight corresponding to the pre-pairing number i; Judging the relevance level based on the relevance analysis results means: Analyze the correlation degree into vector As input variables, the correlation level of pre-pairing number i is taken as output variable, the input variables are fuzzified, the values ​​of the input variables are converted into fuzzy sets, the output variables are fuzzified, the output variables are converted into fuzzy sets, fuzzy rules are formulated to describe the correlation levels under different data type combinations, the fuzzified input variables are inferred through fuzzy rules, and the correlation level of pre-pairing number i is obtained; The logic for obtaining the actual time threshold for establishing a data sharing channel is: ; represents the correlation level corresponding to the retained pairing relationship i, Indicates the preset urgency adjustment coefficient for the current scenario. Indicates the preset basic duration. Indicates the preset load indicator data of the data fusion module in the current scenario. Indicates the standard value corresponding to the load indicator data of the data fusion module in the current scenario. Indicates the actual time threshold for establishing the data sharing channel corresponding to pairing relationship i.

2. According to claim 1, the AI ​​Internet of Things multi-domain data sharing method is characterized in that: The weight fusion method based on correlation calculates the correlation between data in different fields, which means: Get the correlation coefficient between the pre-paired target domain data and the target different domain data ; Then assign weights based on the importance of the fields: ; N represents the total number of pre-paired pairs.

3. The AI ​​IoT multi-domain data sharing method according to claim 2 is characterized in that: The correlation vector after pre-pairing refers to the correlation coefficient corresponding to the pre-pairing number i and importance weights Summarize and get the correlation vector .

4. The AI ​​IoT multi-domain data sharing method according to claim 3 is characterized in that: Correlation coefficient It is measured by Pearson's correlation coefficient.

5. The AI ​​IoT multi-domain data sharing method according to claim 4 is characterized in that: Determining whether to establish a pairing relationship between the target domain data and the different domain data based on the correlation level obtained by judgment refers to: Obtain the relevant level of the pre-pairing number i, and compare it with the preset level threshold. If the relevant level of the pre-pairing number i is greater than or equal to the preset level threshold, the pairing relationship of the pre-pairing number i is retained; if the relevant level of the pre-pairing number i is less than the preset level threshold, the pairing relationship of the pre-pairing number i is deleted.

6. The AI ​​IoT multi-domain data sharing method according to claim 5, characterized in that: Resource allocation for channel establishment using genetic algorithms refers to: Encoding and initial population: Encode the channel resource allocation parameter group, i.e., the decision variable, into a chromosome form and randomly generate m chromosomes as the initial population; Fitness evaluation: The constraint condition is defined as the establishment time of each data sharing channel cannot exceed its actual time threshold. At the same time, the total establishment time of all data sharing channels is calculated. The total establishment time is the fitness value of the chromosome. The goal is to minimize the total establishment time of all data sharing channels. Selection operation: Use the roulette wheel selection method to select offspring as new parents; Crossover operation: randomly exchange data in chromosomes of different parents; Mutation operation: randomly select data of different offspring chromosomes for adjustment; Iteration and termination conditions: When the pre-set termination conditions are reached, the chromosome with the highest fitness is selected from the final population for decoding to obtain the optimal resource allocation plan.

7. An AI Internet of Things multi-domain data sharing system, implemented based on an AI Internet of Things multi-domain data sharing method according to any one of claims 1 to 6, characterized in that: include: The pre-pairing module obtains the target domain data and calculates the correlation between the data in different domains by using a weight fusion method based on relevance, and obtains the correlation vector after the target domain data is pre-paired with the data in multiple different domains; The secondary pairing module continues to perform correlation analysis based on the correlation vector after pairing, and performs correlation level judgment according to the correlation level analysis result, and determines whether to establish a pairing relationship between the target domain data and the different domain data according to the correlation level obtained by judgment, and summarizes all the established pairing relationships to obtain a pairing relationship table between the target domain data and multiple different domain data; The data sharing channel establishment module sets the actual time threshold for establishing the data sharing channel corresponding to the target pairing relationship based on the pairing relationship form, and then uses the genetic algorithm to allocate resources for channel establishment, obtains the final resource allocation plan and applies it.

Images