Intelligent deployment analysis system and method based on big data

By grey analysis processing and area division optimization of the data of the intelligent allocation analysis system, the system's lack of generalization capabilities in different scenarios is solved, and more efficient resource allocation and management is achieved.

CN119005619AInactive Publication Date: 2024-11-22ANHUI POLYTECHNIC UNIV MECHANICAL & ELECTRICAL COLLEGE
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411125241.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-16
Publication Date
2024-11-22
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing intelligent provisioning analysis system performs excellently in specific scenarios, but lacks generalization capabilities in different scenarios, making it difficult to adapt to complex situations.

Method used

By determining the distribution of population ranges using, collecting historical data and correlation data, pre-processing and grey analysis methods, generating environmental correlation matrix and individual correlation matrix, dividing regions and calculating correlation degrees, and optimizing regional division standards to adapt to different scenarios.

Benefits of technology

It improves the accuracy and efficiency of resource allocation, can more accurately predict and meet the needs of users, adapt to changes in different regions, and enhances the flexibility and applicability of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119005619A_ABST
    Figure CN119005619A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent deployment analysis system and method based on big data, relates to the field of big data processing and the technical field of intelligent deployment, and solves the problems that part of current intelligent deployment systems are likely to be excellent in performance in specific scenes, but the generalization ability in different scenes is still poor, and the deployment efficiency is poor. The algorithm needs to be further optimized to adapt to more complex conditions; according to the method, the division standards of the four regions are optimized by determining the range distribution of the user crowd, collecting historical data and associated data of the user crowd, processing the data, analyzing an environment association matrix and an individual association matrix, dividing the distribution range of the user crowd into regions, and analyzing the relation between the actual demand and the estimated demand of each region; the requirements of users can be predicted and met more accurately, and the accuracy and efficiency of resource allocation are improved; and the distribution range of the used crowds is dynamically divided to adapt to the change of different regions, so that resource allocation and management are more flexibly carried out.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the fields of big data processing and intelligent allocation technology, and specifically to an intelligent allocation analysis system and method based on big data. Background Art

[0002] Intelligent allocation and analysis is a resource scheduling system based on big data, which aims to realize intelligent management and optimal allocation of resources. The intelligent allocation and analysis system automatically adjusts the task allocation plan by real-time monitoring and analysis of task requirements, resource status and other information, thereby improving resource utilization and work efficiency.

[0003] At present, some existing intelligent analysis systems only target a specific situation. If the environment is changed, the effect of intelligent allocation analysis will be greatly reduced. Based on the current situation, it is necessary to propose a method and system for intelligent allocation analysis based on big data, which can solve the problem that some current intelligent allocation systems may perform well in specific scenarios, but still lack the generalization ability in different scenarios, and the algorithm needs to be further optimized to adapt to more complex situations. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides an intelligent allocation analysis system and method based on big data to solve the problem that some current intelligent allocation systems may perform well in specific scenarios, but still lack the generalization ability in different scenarios, and the algorithm needs to be further optimized to adapt to more complex situations.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent allocation and analysis system and method based on big data, comprising the following steps:

[0006] S1. Determine the distribution of user groups, collect historical data and related data of user groups, pre-process the historical data and related data, and generate original data;

[0007] The historical data of the user population includes the total demand Q and the total individual demand Q within the distribution range over the years; the associated data includes the environmental information within the distribution range and the individual attributes of the user population;

[0008] Environmental information, including topography, climate, pollution level and socio-economics, is recorded as environmental series Hi = {H1, H2, H3, ...};

[0009] Among them, terrain factors include mountains, plains and basins, and climate factors include temperature, humidity and precipitation, which are coded separately to form an environmental matrix

[0010] Individual attributes, including age, gender, job type, marital status, and whether or not there are children, are recorded as individual sequence Gi = {G1, G2, G3, ...};

[0011] Among them, the age factor is divided into ten years, such as those born in the 1980s, 1990s, and so on. The work type factors include education, medical and health, and IT, which are coded separately to form an individual matrix

[0012] S2. Determine the distribution of user groups, collect historical data and related data of user groups, pre-process the historical data and related data, and generate original data;

[0013] The elements in the environment matrix and individual matrix of the original data are quantified, and the correlation coefficients are calculated to obtain the correlation coefficient environment matrix H and the correlation coefficient individual matrix G respectively.

[0014] By using the grey analysis method, the correlation coefficient environment matrix H and the correlation coefficient individual matrix G are used to calculate the correlation between each row of information factors and the total demand Q within the user population distribution. The specific steps are as follows:

[0015] First, determine the reference sequence:

[0016] Y=Y(k)|k=1,2,3,…;

[0017] Among them, Y(k) represents the total demand Q within the distribution range in a certain year, and k represents the year sequence;

[0018] Second, determine the comparison sequence:

[0019] H ij=H ij(k)|k=1,2,3,…;

[0020] G ij=G ij(k)|k=1,2,3,…;

[0021] II, j represent the row and column numbers respectively. For example, the number column H11 represents the factors in the first row and first column of the correlation coefficient environment matrix H, which is the data set over the years;

[0022] Initialize each Hij sequence and Gij sequence in previous years respectively:

[0023]

[0024] Calculate the mean h of Hij and the mean g of Gij over the years, and perform averaging on each Hij series and Gij series after update over the years:

[0025]

[0026] Calculate the correlation coefficient:

[0027]

[0028] In the formula, ξ(k) is the correlation coefficient of a single factor, ρ∈(0,∞), called the resolution coefficient. The smaller ρ is, the greater the resolution is. Generally, the value range of ρ is (0,1). The specific value can be determined according to the situation. When ρ≤0.5463, the resolution is the best, and ρ=0.5 is usually taken.

[0029] The correlation coefficient is the correlation degree between the comparison series and the reference series in each year, so it has more than one value, and the information is too scattered to be convenient for overall comparison. Therefore, it is necessary to concentrate the correlation coefficients of each year into one value, that is, to find its average value, as a quantitative representation of the correlation degree between the comparison series and the reference series. The correlation degree ri formula is as follows:

[0030]

[0031] Finally, sort the relevance:

[0032] In the environment matrix, take the first a in the correlation ranking 2 Position factors, which form an environmental correlation matrix of size a*a;

[0033] In the individual matrix, take the first a in the correlation ranking 2 factors, forming an individual association matrix of size a*a.

[0034] S3. Analyze the environmental association matrix and the individual association matrix, divide the user population distribution range into regions, calculate the estimated demand of each region, and analyze the relationship between the actual demand and the estimated demand of each region;

[0035] Analyze the environmental correlation matrix and the individual correlation matrix, calculate the ratio of the eigenvalues ​​of the environmental correlation matrix and the individual correlation matrix, record it as the weight coefficient, and quantitatively compare the influence of factors in different matrices on the estimated total amount based on this;

[0036] According to the sum of the correlations of the factors in the environmental correlation matrix and the individual correlation matrix in the region, several types of regions are defined. In the present invention, four types of regions are set: type I region, type II region, type III region and type IV region;

[0037] Among them: The sum of the correlation degrees of the factors in the environment correlation matrix and the individual correlation matrix occupied within the region is less than or equal to the set value v1, denoted as the four-category region; the sum of the correlation degrees of the factors in the environment correlation matrix and the individual correlation matrix occupied within the region is greater than the set value v1 and less than or equal to the set value v2, denoted as the three-category region; the sum of the correlation degrees of the factors in the environment correlation matrix and the individual correlation matrix occupied within the region is greater than the set value v2 and less than or equal to the set value v3, denoted as the two-category region; the sum of the correlation degrees of the factors in the environment correlation matrix and the individual correlation matrix occupied within the region is greater than the set value v3, denoted as the one-category region;

[0038] After dividing the four-category regions, different estimation criteria are adopted for each category of region. The difference lies in that among different categories of regions, the influence degrees of the factors in different matrices on the total estimated quantity are different; count the actual total demand of each region, which is the sum of individual demands within each region;

[0039] Among them, the set values v1, v2, and v3 are all set by the operator according to experience;

[0040] Using the weighted average method, calculate the estimated demand within the distribution range of the user population, and obtain the average value of the total estimated quantity within each region according to the ratio of the number of people in the four-category regions;

[0041] Calculate the variance between the average value of the total estimated quantity within the region and the estimated demand every year over the years:

[0042]

[0043] Among them, i is the year sequence, N is the total number of years, here N = 1, F is the average value of the total estimated quantity within the region, and f is the estimated demand within the region;

[0044] Draw a curve graph of the variance, count the slope changes of the lines in the curve graph, define the trend coefficient T, and mark it as the discrete interval and mark the region when the slope in the curve graph is greater than T and the total continuous duration is greater than or equal to t, denoted as the deviation region.

[0045] S4. Analyze the connection between the four-category regions and the deviation region, and optimize the division criteria for the four major regions;

[0046] Compare the total estimated demand quantity w within the deviation region and the total estimated demand quantity W within the overlapping region of the category region where the deviation region is located. If w >> W, then raise the overlapping region by one region. If the category region where the deviation region is located is the one-category region, return this region to step S2;

[0047] Compare the total estimated demand quantity w within the deviation region and the total estimated demand quantity W within the overlapping region of the category region where the deviation region is located. If w << W, then lower the baseline of the overlapping region, and the lowering amplitude depends on the difference between w and W.

[0048] A big data-based intelligent allocation and analysis system, which specifically adopts a big data-based intelligent allocation and analysis method to realize intelligent allocation and analysis.

[0049] Beneficial Effects

[0050] The present invention provides an intelligent allocation and analysis system and method based on big data. Compared with the prior art, it has the following beneficial effects:

[0051] The present invention determines the distribution of user population, collects historical data and associated data of user population, processes the data, analyzes the environmental association matrix and the individual association matrix, divides the user population distribution range into regions, analyzes the relationship between the actual demand and the estimated demand of each region, and optimizes the division criteria of the four major regions;

[0052] By utilizing big data, a large amount of historical data and related data can be collected and analyzed to more accurately predict and meet the needs of the user population, improve the accuracy and efficiency of resource allocation, dynamically divide the distribution range of the user population, adapt to changes in different regions, and allocate and manage resources more flexibly; for situations where the amount of data is limited, the gray analysis method can also perform effective analysis, which is applicable to linear or nonlinear problems and has no strict requirements on data distribution, thereby enhancing the applicability and reliability of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 is a flow chart of the method of the present invention;

[0054] Figure 2 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] Embodiment 1

[0057] See also Figure 1 , the present application provides an intelligent deployment analysis method based on big data, including:

[0058] S1. Determine the distribution of user groups, collect historical data and related data of user groups, pre-process the historical data and related data, and generate original data;

[0059] The historical data of the user population includes the total demand Q and the total individual demand Q within the distribution range over the years; the associated data includes the environmental information within the distribution range and the individual attributes of the user population;

[0060] Environmental information, including topography, climate, pollution level and socio-economics, is recorded as environmental series Hi = {H1, H2, H3, ...};

[0061] Among them, terrain factors include mountains, plains and basins, and climate factors include temperature, humidity and precipitation, which are coded separately to form an environmental matrix

[0062] Individual attributes, including age, gender, job type, marital status, and whether or not there are children, are recorded as individual sequence Gi = {G1, G2, G3, ...};

[0063] Among them, the age factor is divided into ten years, such as those born in the 1980s, 1990s, and so on. The work type factors include education, medical and health, and IT, which are coded separately to form an individual matrix

[0064] Arranging in a matrix, that is, using a factor analysis matrix, allows you to intuitively see the relationships and interactions between the various factors, which helps you better understand the complexity of the problem, makes it easier to compare the influence of different factors, and identifies which factors are independent of each other and which are interrelated; it helps to systematically understand and solve problems, breaking down complex problems into smaller, more manageable parts, and simplifying the problem.

[0065] When processing historical data and related data, you first need to clean the data; including deleting missing values, filling in gaps, smoothing outliers, and calculating the similarity between data to identify and process duplicate records; merging duplicate items, or selecting a more representative one and deleting the rest; standardizing and unifying the data format to ultimately form standardized original data.

[0066] S2. Process the original data, including the total demand Q within the distribution range, the total individual demand q, the environmental information within the distribution range, and the individual attributes of the user population;

[0067] The elements in the environment matrix and individual matrix of the original data are quantified, and the correlation coefficients are calculated to obtain the correlation coefficient environment matrix H and the correlation coefficient individual matrix G respectively.

[0068] By using the grey analysis method, the correlation coefficient environment matrix H and the correlation coefficient individual matrix G are used to calculate the correlation between each row of information factors and the total demand Q within the user population distribution. The specific steps are as follows:

[0069] First, determine the reference sequence:

[0070] Y=Y(k)|k=1,2,3,…;

[0071] Among them, Y(k) represents the total demand Q within the distribution range in a certain year, and k represents the year sequence;

[0072] Second, determine the comparison sequence:

[0073] H ij=H ij(k)|k=1,2,3,…;

[0074] G ij=G ij(k)|k=1,2,3,…;

[0075] III, j represent the row number and column number respectively. For example, the number column H11 represents the factors in the first row and first column of the correlation coefficient environment matrix H, which is the data set over the years;

[0076] Initialize each Hi j sequence and Gi j sequence in previous years respectively:

[0077]

[0078] Calculate the mean h of Hij and the mean g of Gij over the years, and perform averaging on each Hij series and Gij series after update over the years:

[0079]

[0080] Calculate the correlation coefficient:

[0081]

[0082]

[0083] In the formula, ξ(k) is the correlation coefficient of a single factor, ρ∈(0,∞), called the resolution coefficient. The smaller ρ is, the greater the resolution is. Generally, the value range of ρ is (0,1). The specific value can be determined according to the situation. When ρ≤0.5463, the resolution is the best, and ρ=0.5 is usually taken.

[0084] The correlation coefficient is the correlation degree between the comparison series and the reference series in each year, so it has more than one value, and the information is too scattered to be convenient for overall comparison. Therefore, it is necessary to concentrate the correlation coefficients of each year into one value, that is, to find its average value, as a quantitative representation of the correlation degree between the comparison series and the reference series. The correlation degree ri formula is as follows:

[0085]

[0086] Finally, sort the relevance:

[0087] In the environment matrix, take the first a in the correlation ranking 2 Position factors, which form an environmental correlation matrix of size a*a;

[0088] In the individual matrix, take the first a in the correlation ranking 2 The bit factors constitute an individual association matrix of size a*a;

[0089] The specific value of a is determined by the staff based on experience;

[0090] Grey analysis can also be used to conduct effective analysis even when the amount of data is limited, and it has strong applicability. It can handle both linear and nonlinear problems, and has no strict requirements on the distribution of data. The calculation process is relatively simple and easy to implement through programming. The quantitative relationship is clear, and the relationship between different factors is pointed out, which helps decision makers understand the relative importance of each factor. It can reflect the dynamic influence relationship between factors and is suitable for complex system analysis with multiple factors and multiple levels.

[0091] S3. Analyze the environmental association matrix and the individual association matrix, divide the user population distribution range into regions, calculate the estimated demand of each region, and analyze the relationship between the actual demand and the estimated demand of each region;

[0092] Analyze the environmental correlation matrix and the individual correlation matrix, calculate the ratio of the eigenvalues ​​of the environmental correlation matrix and the individual correlation matrix, record it as the weight coefficient, and quantitatively compare the influence of factors in different matrices on the estimated total amount based on this;

[0093] According to the sum of the correlations of the factors in the environmental correlation matrix and the individual correlation matrix in the region, several types of regions are defined. In the present invention, four types of regions are set: type I region, type II region, type III region and type IV region;

[0094] Among them: the sum of the correlation degrees of the factors in the environmental correlation matrix and the individual correlation matrix in the region is less than or equal to the set value v1, which is recorded as a fourth-category region; the sum of the correlation degrees of the factors in the environmental correlation matrix and the individual correlation matrix in the region is greater than the set value v1 and less than or equal to the set value v2, which is recorded as a third-category region; the sum of the correlation degrees of the factors in the environmental correlation matrix and the individual correlation matrix in the region is greater than the set value v2 and less than or equal to the set value v3, which is recorded as a second-category region; the sum of the correlation degrees of the factors in the environmental correlation matrix and the individual correlation matrix in the region is greater than the set value v3, which is recorded as a first-category region;

[0095] Four categories of regions are divided, and different estimation criteria are adopted for each category. The difference lies in that among different categories of regions, the influence degrees of factors in different matrices on the total estimated amount are different; the actual total demand of each region is counted, which is the sum of individual demands within each region;

[0096] Among them, the set values v1, v2, and v3 are all set by the operator according to experience;

[0097] Using the weighted average method, the estimated demand within the range of the user population distribution is calculated, and the average value of the total estimated amount within each region is obtained according to the ratio of the number of people in the four categories of regions;

[0098] Calculate the variance between the average value of the total estimated amount within the region and the estimated demand for each year over the years:

[0099]

[0100] Among them, i is the year sequence, N is the total number of years, here N = 1, F is the average value of the total estimated amount within the region, and f is the estimated demand within the region;

[0101] Draw a curve graph of the variance, count the slope changes of the lines in the curve graph, define the trend coefficient T, and mark it as a discrete interval and mark the region when the slope in the curve graph is greater than T and the total continuous duration is greater than or equal to t, and mark this region as the deviation region;

[0102] S4. Analyze the connection between the four categories of regions and the deviation region, and optimize the division criteria of the four major regions;

[0103] Compare the total estimated demand w within the deviation region with the total estimated demand W within the overlapping region of the category region where the deviation region is located. If w >> W, raise this overlapping region by one region. If the category region where the deviation region is located is a first-category region, return this region to step S2;

[0104] Compare the total estimated demand w within the deviation region with the total estimated demand W within the overlapping region of the category region where the deviation region is located. If w << W, lower the baseline of this overlapping region, and the adjustment range depends on the difference between w and W;

[0105] Embodiment 2

[0106] Please refer to Figure 2 , an intelligent allocation analysis system based on big data. This system uses the above-mentioned intelligent allocation analysis method based on big data to conduct intelligent allocation analysis. This system includes:

[0107] The data collection and preprocessing unit is used to collect historical data and related data of the user population, including total demand, total individual demand, environmental information (topography, climate, etc.), and individual attributes (age, gender, etc.); this unit is also responsible for data cleaning, missing value processing, outlier smoothing, duplicate record identification and processing, as well as data standardization and format unification;

[0108] The data analysis and processing unit is used to receive data from the data collection and preprocessing unit, quantify the environmental matrix and the individual matrix, calculate the correlation coefficient, and use the grey analysis method to calculate the correlation between each factor and the total demand. The core of this unit is to process mathematical operations on data and output the correlation ranking and correlation matrix.

[0109] The regional division and demand estimation unit uses the correlation matrix and correlation degree output by the data analysis and processing unit to divide the user population distribution range into regions according to the preset weight coefficient and regional classification standard, and calculates the estimated demand for each region; at the same time, it analyzes the relationship between the actual demand and the estimated demand, including calculating the variance and drawing the variance curve;

[0110] The optimization and adjustment unit analyzes the relationship between different types of regions and deviation areas based on the results of the regional division and demand estimation unit, and proposes optimization suggestions for regional division standards; based on the comparison results between estimated demand and actual demand, it decides whether the regional classification needs to be adjusted to more accurately reflect the actual situation;

[0111] The display unit is used to display the real-time total demand and the future estimated total demand within the distribution range of the user population; it also includes the division of regions and standards, and the real-time total demand and future estimated total demand in each region.

[0112] Some of the data in the above formulas are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0113] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An intelligent deployment analysis method based on big data, characterized in that: The following steps are involved: S1. Determine the distribution of user groups, collect historical data and related data of user groups, pre-process the historical data and related data, and generate original data; S2. Process the original data, including the total demand Q within the distribution range, the total individual demand q, the environmental information within the distribution range, and the individual attributes of the user population; S3. Analyze the environmental association matrix and the individual association matrix, divide the user population distribution range into regions, calculate the estimated demand of each region, and analyze the relationship between the actual demand and the estimated demand of each region; S4. Analyze the relationship between the four types of areas and the deviation areas, and optimize the division criteria of the four major areas.

2. According to the big data-based intelligent deployment analysis method of claim 1, it is characterized in that: Collecting historical data and associated data of user groups and preprocessing the historical data and associated data include the following steps: The historical data of the user population includes the total demand Q and the total individual demand Q within the distribution range over the years; the associated data includes the environmental information within the distribution range and the individual attributes of the user population; Environmental information, including topography, climate, pollution level and socio-economics, is recorded as environmental series Hi = {H1, H2, H3, ...}; Among them, terrain factors include mountains, plains and basins, and climate factors include temperature, humidity and precipitation, which are coded separately to form an environmental matrix Individual attributes, including age, gender, job type, marital status, and whether or not there are children, are recorded as the individual sequence Gi = {G1, G2, G3, ...}; Among them, the age factor is divided into ten years, such as those born in the 1980s, 1990s, and so on. The work type factors include education, medical and health, and IT, which are coded separately to form an individual matrix 3. According to the big data-based intelligent deployment analysis method of claim 1, it is characterized in that: Information processing of the original data includes the following steps: The elements in the environment matrix and individual matrix of the original data are quantified, and the correlation coefficients are calculated to obtain the correlation coefficient environment matrix H and the correlation coefficient individual matrix G respectively. Through the grey analysis method, the correlation between each row of information factors and the total demand Q within the distribution of the user population in the correlation coefficient environment matrix H and the correlation coefficient individual matrix G is calculated.

4. According to the big data-based intelligent deployment analysis method of claim 3, it is characterized in that: Calculating the correlation between each row of information factors and the total demand Q within the user population distribution includes the following steps: First, determine the reference sequence: Y=Y(k)|k=1,2,3,…; Among them, Y(k) represents the total demand Q within the distribution range in a certain year, and k represents the year sequence; Second, determine the comparison sequence: Hij=Hij(k)|k=1,2,3,…; Gij=Gij(k)|k=1,2,3,…; I, j represent the row and column numbers respectively; Initialize each Hij sequence and Gij sequence in previous years respectively: Calculate the mean value h of Hij and the mean value g of Gij over the years, and perform averaging on each updated Hij series and Gij series over the years: Calculate the correlation coefficient: In the formula, ξ(k) is the correlation coefficient of a single factor, ρ∈(0,∞), which is called the resolution coefficient; The formula of correlation degree ri is as follows: Finally, sort the relevance: In the environment matrix, take the first a in the correlation ranking 2 Position factors, which form an environmental correlation matrix of size a*a; In the individual matrix, take the first a in the correlation ranking 2 factors, forming an individual association matrix of size a*a.

5. According to the big data-based intelligent deployment analysis method of claim 1, it is characterized in that: Divide the user population distribution into regions and calculate the estimated demand in each region, including the following steps: Analyze the environmental correlation matrix and the individual correlation matrix, calculate the ratio of the eigenvalues ​​of the environmental correlation matrix and the individual correlation matrix, record it as the weight coefficient, and quantitatively compare the influence of factors in different matrices on the estimated total amount based on this; According to the sum of the correlation degrees of the factors in the environmental correlation matrix and the individual correlation matrix occupied within the region, several types of regions are defined. In the present invention, they are set as four types of regions: type I region, type II region, type III region, and type IV region; Among them: the sum of the correlation degrees of the factors in the environmental correlation matrix and the individual correlation matrix occupied within the region is less than or equal to the set value v1, denoted as the type IV region; The sum of the correlation degrees of the factors in the environmental correlation matrix and the individual correlation matrix occupied within the region is greater than the set value v1 and less than or equal to the set value v2, denoted as the type III region; The sum of the correlation degrees of the factors in the environmental correlation matrix and the individual correlation matrix occupied within the region is greater than the set value v2 and less than or equal to the set value v3, denoted as the type II region; The sum of the correlation degrees of the factors in the environmental correlation matrix and the individual correlation matrix occupied within the region is greater than the set value v3, denoted as the type I region; After the four types of regions are divided, the total actual demand of each region is counted, which is the sum of the individual demands within each region.

6. According to the big data-based intelligent deployment analysis method of claim 5, it is characterized in that: Analyze the relationship between the actual demand and the estimated demand in each region, including the following steps: Using the weighted average method, calculate the estimated demand within the range of the user population distribution, and obtain the average value of the estimated total within each region according to the ratio of the number of people in the four types of regions; Calculate the variance between the average value of the estimated total within the region each year and the estimated demand over the years: Among them, i is the year sequence, N is the total number of years, here N = 1, F is the average value of the estimated total within the region, and f is the estimated demand within the region; Draw a curve graph of the variance, count the slope changes of the lines in the curve graph, define the trend coefficient T, and mark it as a discrete interval and mark the region when the slope in the curve graph is greater than T and the total continuous duration is greater than or equal to t, denoted as the deviation region.

7. The intelligent allocation and analysis method based on big data according to claim 1 is characterized in that: Analyze the relationship between the four types of regions and the deviation region, and optimize the division criteria of the four major regions, including the following steps: Compare the total estimated demand w within the deviation region with the total estimated demand W within the overlapping region of the category region where the deviation region is located. If w >> W, raise the overlapping region by one region. If the category region where the deviation region is located is the type I region, return this region to step S2; Compare the total estimated demand w within the deviation region with the total estimated demand W within the overlapping region of the category region where the deviation region is located. If w << W, lower the bottom line of the overlapping region, and the lowering range depends on the difference between w and W.

8. An intelligent deployment and analysis system based on big data, characterized in that: This system specifically adopts the intelligent allocation analysis method based on big data described in any one of claims 1-7 to achieve intelligent allocation analysis.