Multi-dimensional data management system and method based on geographic information

Abstract

The invention relates to the field of data processing, in particular to a multi-dimensional data management system and method based on geographic information. Comprising the following steps: acquiring a geographic information data set, processing geographic information data in the geographic information data set through a geographic information data nonlinear mapping algorithm, and calculating to obtain a mapping value of a data point; the mapping values of the data points are subjected to dimension reduction to a low-dimensional space through an adaptive nonlinear dimension reduction and embedding algorithm, and embedded values of the data points after dimension reduction are obtained; on the basis of the embedded values of the data points after dimension reduction, index values of the data points are calculated through an index generation algorithm; and comparing the query point with the index value of each data point in the index by using a query responsivity calculation algorithm, and calculating to obtain the query responsivity. The technical problems that an original geographic information data set contains a large amount of high-dimensional geographic information, consequently, the calculation amount is huge, memory consumption is high, and data dimensions in the geographic information data processing process are diversified and complex are solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a multidimensional data management system and method based on geographic information. Background Art

[0002] With the rapid development of information technology, geographic information data, as a part of big data, plays an increasingly important role in all walks of life. Geographic information data not only includes location information in the geographic coordinate system, but also includes various attribute information associated with the location, such as environmental monitoring data, climate data, and traffic data. The multidimensionality and large scale of geographic information data have brought new challenges to data management and processing. Traditional data management methods are often difficult to effectively handle such complex and dynamically changing data, and often face problems of storage redundancy and low query efficiency when processing data. Especially when facing large amounts of data, the query response time and storage space requirements are growing exponentially, which is difficult for traditional systems to cope with. Therefore, a multidimensional data management system and method based on geographic information came into being. With the continuous advancement of technologies such as cloud computing, big data, and artificial intelligence, the multidimensional data management system based on geographic information will further enhance data processing capabilities, promote the application of geographic information data in intelligent decision-making, public services, urban management, and other aspects, and promote the development of social informatization.

[0003] However, existing multidimensional data management methods have at least the following technical problems: the original geographic information dataset contains a large amount of high-dimensional geographic information, which leads to huge computational complexity and high memory consumption, and the data dimensions in the process of processing new geographic information data are diverse and complex; traditional methods are difficult to accurately capture the periodic fluctuations of geographic information data, which can easily lead to distortion of the mapped data or loss of important features, affecting the accuracy and effectiveness of subsequent analysis; when faced with spatial location differences, existing methods are prone to errors, resulting in inaccurate data mapping; traditional index generation methods are difficult to efficiently support fast queries, especially when the data dimension is high or the number of data points is large, the query response time is too long and the query efficiency is low. Summary of the invention

[0004] The present invention provides a multidimensional data management system and method based on geographic information to solve the problems that the original geographic information data set contains a large amount of high-dimensional geographic information, resulting in huge calculation amount, high memory consumption, and diverse and complex data dimensions in the geographic information data processing process; traditional methods are difficult to accurately capture the periodic fluctuations of geographic information data, which easily leads to distortion of mapped data or loss of important features, affecting the accuracy and effectiveness of subsequent analysis; when faced with spatial position differences, existing methods are prone to errors, resulting in inaccurate data mapping; traditional index generation methods are difficult to efficiently support fast queries, especially when the data dimension is high or the number of data points is large, the query response time is too long and the query efficiency is low.

[0005] The present invention provides a multidimensional data management system and method based on geographic information, which specifically includes the following technical solutions: A multidimensional data management method based on geographic information comprises the following steps: S1: Obtain a geographic information data set, process the geographic information data in the geographic information data set by a geographic information data nonlinear mapping algorithm, and calculate the mapping value of the data point; S2: Reduce the dimension of the mapping value of the data point to a low-dimensional space through an adaptive nonlinear dimensionality reduction and embedding algorithm to obtain the embedding value of the data point after dimensionality reduction; S3: Based on the embedding value of the data point after dimensionality reduction, the index value of the data point is calculated by the index generation algorithm; S4: Use a query responsiveness calculation algorithm to compare the query point with the index value of each data point in the index, and calculate the query responsiveness.

[0006] Preferably, the S1 specifically includes: The nonlinear mapping algorithm for geographic information data adopts a sine function to capture the periodic fluctuations of geographic information data, and introduces a periodic adjustment item to correct the geographic information data; and introduces a spatial adjustment factor to adjust the spatial transformation of the geographic information data; the change of the geographic information data is adjusted through an exponential function, and combined with the adjustment factor, the mapping value of the data point is obtained.

[0007] Preferably, the S1 specifically includes: The calculation formula for the mapping value of a data point is: in, Indicates that in the new coordinate space The data point The mapping value of the dimension; Indicates The data point The value of the dimension, i.e., geographic information data; Indicates The data point The square of the value of the dimension; Indicates that for Periodic adjustment items of geographic information data; represents the sine function; represents the adjustment factor that controls the intensity of the influence of the index term; represents the exponential function; Indicates that for The spatial adjustment factor for each data point; represents the cosine function; Indicates normalization processing.

[0008] Preferably, the S2 specifically includes: The adaptive nonlinear dimensionality reduction and embedding algorithm normalizes the mapping values ​​of the data points by introducing a normalization term, processes the normalization term by a hyperbolic tangent function, and smoothes the mapping values ​​of the data points.

[0009] Preferably, the S2 specifically includes: In the process of dimensionality reduction, the adaptive nonlinear dimensionality reduction and embedding algorithm adjusts the mapping value of each dimension through modular operation to obtain the embedding value of the data point after dimensionality reduction. The specific implementation formula is: in, Represents the first Embedding value of data points; Indicates that in the new coordinate space The data point The mapping value of the dimension; represents the hyperbolic tangent function; Express The dimensions are summed; represents the normalization term; It means that the mapping values ​​of all dimensions are weighted and accumulated, and then nonlinearly adjusted through the exponential function; Represents the adjustment factor that controls the exponential decay degree of the mapping value in the dimensionality reduction formula; Represents a modular operation term; express Activation function in functional form; Represents the adjustment factor that controls the influence of each dimension in the dimensionality reduction process.

[0010] Preferably, the S3 specifically includes: The index generation algorithm generates the index value of each data point through a weighted calculation consisting of two parts. The first part is to generate a nonlinear weighted term by performing high-order power operations and tangent function transformation on the embedded value of each data point after dimensionality reduction; the second part is to introduce smoothing and adjustment terms, use exponential functions to perform nonlinear smoothing on the embedded values ​​of the data points after dimensionality reduction, and introduce adjustable hyperparameters to obtain the index value of the data point.

[0011] Preferably, the S3 specifically includes: The calculation formula for the index value of a data point is: in, Indicates The index value of the data point; Represents the first Embedding value of data points; represents the nonlinear weighting term; Represents the first The embedding value of the data point Power; It means that the tangent function is used to reduce the dimension of the The embedding values ​​of the data points are nonlinearly mapped; represents smoothing and adjustment terms; It means that the exponential function is used to reduce the dimension of the Nonlinear smoothing of the embedded values ​​of data points; represents an adjustable hyperparameter.

[0012] Preferably, the S4 specifically includes: When calculating the query responsiveness, the query responsiveness calculation algorithm performs weighting according to the spatial distance between the data point and the query point, combines the weighting mechanism and smoothing function of the power exponent and exponential function, introduces a weighting factor, and dynamically adjusts the query responsiveness.

[0013] Preferably, the S4 specifically includes: The calculation formula for query responsiveness is: in, Indicates Query responsiveness for data points; Indicates The index values ​​of the data points are exponentially calculated; The adjustment factor that represents the influence of the index value of the control data point; Indicates that the exponential function is used to smooth the data; Indicates The index value of the data point and the query point The similarity measurement function between them; represents the weighting factor; Indicates The index value of the data point and the query point The Euclidean distance between Indicates The index value of the data point and the query point The maximum Euclidean distance between .

[0014] A multidimensional data management system based on geographic information, including the following parts: Data acquisition module, geographic information data mapping module, nonlinear dimension reduction and embedding module, index generation module, query responsiveness calculation module; Data acquisition module: acquires geographic information data set, and outputs geographic information data in the geographic information data set to the geographic information data mapping module; Geographic information data mapping module: processes the geographic information data in the geographic information data set from the data acquisition module through a geographic information data nonlinear mapping algorithm, calculates the mapping value, and outputs the mapping value to the nonlinear dimensionality reduction and embedding module; Non-linear dimensionality reduction and embedding module: The mapping value from the geographic information data mapping module is reduced to a low-dimensional space through an adaptive non-linear dimensionality reduction and embedding algorithm to obtain the embedding value of the data point after dimensionality reduction, and the embedded value of the data point after dimensionality reduction is output to the index generation module; Index generation module: Based on the embedding value of the data point after dimensionality reduction by the nonlinear dimensionality reduction and embedding module, the index value is calculated by the index generation algorithm, and the index value is output to the query responsiveness calculation module; Query responsiveness calculation module: Based on the index value of the index generation module, the query point is compared with the index value of each data point in the index using the query responsiveness calculation algorithm to calculate the query responsiveness.

[0015] The beneficial effects of the technical solution of the present invention are: 1. Nonlinear mapping of geographic information data through nonlinear mapping algorithm can not only capture the periodic changes of geographic information data, but also eliminate the loss of original geographic information data caused by spatial transformation or periodic changes, thereby ensuring the accuracy and authenticity of geographic information data, effectively enhancing the availability of geographic information data in subsequent processing, and avoiding the loss of geographic information data. It is particularly suitable for complex analysis of large-scale geographic information data.

[0016] 2. By reducing the dimension of geographic information data to a low-dimensional space, the computational complexity and memory consumption caused by high-dimensional data calculations are effectively reduced, while avoiding the data sparsity problem caused by high-dimensional data. The reduced-dimensional data retains the core features of the original geographic information data in the low-dimensional space, while making the calculation more efficient. Through normalization and modular operation methods, it ensures that each dimension makes a balanced contribution to the embedded value of the reduced-dimensional data point during the dimensionality reduction process, avoiding bias caused by excessive numerical differences. When processing large-scale geographic information data, it can significantly improve the computational efficiency and maintain the structural consistency of the geographic information data.

[0017] 3. Through nonlinear weighting terms and exponential smoothing, each data point can form a unique and highly discriminative index value in the low-dimensional space after dimensionality reduction. Weighting and nonlinear adjustment enhance the discriminability of the index and improve the efficiency and accuracy of index query. By introducing smoothing and adjustment terms, the negative impact of excessive index values ​​on query responsiveness is avoided, ensuring the stability and accuracy of query responsiveness. It is particularly suitable for application scenarios that require efficient query and retrieval of large-scale multidimensional data sets.

[0018] 4. In the query process, local weighting, similarity measurement and adaptive adjustment of spatial distance are adopted to accurately quantify query responsiveness. The weighting mechanism of power index and exponential function is used to enhance the influence of index value on query responsiveness, and the interference of excessive value on query response is eliminated by smoothing function. By incorporating the distance relationship between data point and query point into the query responsiveness calculation, and adjusting the influence of each data point by distance normalization, it is ensured that the query can focus on the points with closer spatial position, thus ensuring the locality of the query process and avoiding the influence of data points far away from the query point on the result, so that the query responsiveness meets the actual needs. Especially in geographic information data, the correlation of spatial position is crucial to the query. The introduction of weighting factor enhances the flexibility of the query and can adapt to different query scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a structural diagram of a multidimensional data management system based on geographic information according to the present invention; Figure 2 This is a flow chart of a multidimensional data management method based on geographic information described in the present invention. DETAILED DESCRIPTION

[0020] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all 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.

[0021] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0022] The specific scheme of a multidimensional data management system and method based on geographic information provided by the present invention is described in detail below with reference to the accompanying drawings.

[0023] See attached Figure 1 , which shows a structure diagram of a multidimensional data management system based on geographic information provided by an embodiment of the present invention, the system includes the following parts: Data acquisition module, geographic information data mapping module, nonlinear dimension reduction and embedding module, index generation module, query responsiveness calculation module; Data acquisition module: acquires geographic information data set, and outputs geographic information data in the geographic information data set to the geographic information data mapping module; Geographic information data mapping module: processes the geographic information data in the geographic information data set from the data acquisition module through a geographic information data nonlinear mapping algorithm, calculates the mapping value, and outputs the mapping value to the nonlinear dimensionality reduction and embedding module; Non-linear dimensionality reduction and embedding module: The mapping value from the geographic information data mapping module is reduced to a low-dimensional space through an adaptive non-linear dimensionality reduction and embedding algorithm to obtain the embedding value of the data point after dimensionality reduction, and the embedded value of the data point after dimensionality reduction is output to the index generation module; Index generation module: Based on the embedding value of the data point after dimensionality reduction by the nonlinear dimensionality reduction and embedding module, the index value is calculated by the index generation algorithm, and the index value is output to the query responsiveness calculation module; Query responsiveness calculation module: Based on the index value of the index generation module, the query point is compared with the index value of each data point in the index using the query responsiveness calculation algorithm to calculate the query responsiveness.

[0024] See attached Figure 2 , which shows a flow chart of a multidimensional data management method based on geographic information provided by an embodiment of the present invention, the method comprising the following steps: S1. Obtain a geographic information data set, process the geographic information data in the geographic information data set by a geographic information data nonlinear mapping algorithm, and calculate the mapping value of the data point; Get geographic information dataset , Indicates The data point The numerical value of the dimension, i.e., the geographic information data; the geographic information data in the geographic information data set is processed by a geographic information data nonlinear mapping algorithm to calculate the mapping value of the data point; In order to capture the possible periodic changes in geographic information data, the nonlinear mapping algorithm of geographic information data adopts a sine function to capture the periodic fluctuations of geographic information data, and introduces a periodic adjustment item to correct the geographic information data to ensure that the periodic changes in the geographic information data can be accurately reflected, thereby avoiding the loss of periodic features in the geographic information data during the mapping process; The cosine function is used to simulate the spatial changes of geographic information data, and a spatial adjustment factor is introduced to adjust the spatial transformation of geographic information data to adapt to the spatial position differences of different data points. In order to carry out effective nonlinear mapping of geographic information data, the changes of geographic information data are adjusted by exponential function, and the influence intensity of exponential term is controlled by adjusting factor. The calculation formula for the mapping value of a data point is: in, Indicates that in the new coordinate space The data point The mapping value of the dimension; Indicates The data point The value of the dimension, i.e., geographic information data; Indicates The data point The square of the value of the dimension. The square operation is used to enhance the difference between the values; Indicates that for Periodic adjustment items of dimensional geographic information data, used to adjust Periodic factors related to dimensional geographic information data; Represents the sine function, which is used to capture the periodic changes that may exist in geographic information data; The adjustment factor representing the influence strength of the control index item can be set according to the specific implementation scenario and is not limited here; Represents an exponential function, which is used to introduce nonlinear features in the mapping process, "compress" geographic information data, and enhance the smoothness of geographic information data; Indicates that for The spatial adjustment factor of each data point is used to adjust the spatial transformation of geographic information data to adapt to the spatial position differences of different data points. It can be set according to the specific implementation scenario and is not limited here; Represents the cosine function, which is used to simulate the spatial changes of geographic information data; Represents normalization processing to ensure that the mapping value is not over-amplified; Nonlinear mapping can truly preserve the nonlinear relationship of geographic information data, so that the mapped data points can accurately reflect the actual spatial and temporal characteristics of geographic information data; S2, reducing the dimension of the mapping value of the data point to a low-dimensional space through an adaptive nonlinear dimensionality reduction and embedding algorithm, and obtaining the embedding value of the data point after dimensionality reduction; Since high-dimensional data will face the problem of extremely large amount of calculation and extremely high memory consumption during processing, the adaptive nonlinear dimensionality reduction and embedding algorithm can reduce the dimension of the mapping value to a low-dimensional space, which can significantly reduce the computational complexity, ensure that the structure of geographic information data can be effectively preserved, and improve the computational efficiency of subsequent operations; In order to ensure that each dimension contributes relatively evenly to the embedding value of the data point after dimensionality reduction, the adaptive nonlinear dimensionality reduction and embedding algorithm needs to normalize the mapping value and introduce a normalization term to adjust it according to the sum of the squares of all dimensions; The adaptive nonlinear dimensionality reduction and embedding algorithm processes the normalization term through the hyperbolic tangent function, which is used to smooth the mapping value in the dimensionality reduction formula to avoid excessive differences between data points that affect the results and ensure that no extreme values ​​appear in the dimensionality reduction process; The adaptive nonlinear dimensionality reduction and embedding algorithm uses modular operation in the dimensionality reduction process to adjust the mapping value of each dimension to avoid distortion of the embedding value of the data point after dimensionality reduction due to extreme values; The calculation formula for the embedding value of the data point after dimensionality reduction is: in, Represents the first Embedding value of data points; Indicates that in the new coordinate space The data point The mapping value of the dimension; Represents the hyperbolic tangent function. In the dimension reduction formula, it is used to smooth the mapping values ​​to avoid large differences between data points that affect the results and ensure that no extreme values ​​appear in the dimension reduction process. Express The dimensions are summed; represents the normalization term, which is used to balance the contribution of each dimension; It means that the mapping values ​​of all dimensions are weighted and accumulated, and then nonlinearly adjusted through an exponential function to control the nonlinear change of the mapping values ​​during the dimensionality reduction process; Represents the adjustment factor that controls the exponential decay degree of the mapping value in the dimensionality reduction formula; Represents the modulo operation term, which is used to adjust the influence of the mapping value to avoid distortion of the embedding value of the data point after dimensionality reduction due to extreme values; express The activation function in functional form is used to adjust the contribution of the mapping value of each data point in the low-dimensional space, so that the contribution of each dimension to the embedding value of the data point after the final dimensionality reduction is smooth and nonlinear; Represents the adjustment factor that controls the influence of each dimension in the dimensionality reduction process; S3, based on the embedding value of the data point after dimensionality reduction, the index value of the data point is calculated by an index generation algorithm; In order to build an accurate index structure to achieve fast multi-dimensional data query, the index value of each data point is calculated through the index generation algorithm based on the embedded value of the data point after dimensionality reduction; The index generation algorithm generates the index value of each data point through a weighted calculation consisting of two parts. The first part generates a nonlinear weighted term by performing high-order power operations and tangent function transformation on the embedded value of each data point after dimensionality reduction, thereby increasing the discrimination of each data point, so that the index difference between different data points is significant during the index generation process, thereby improving the query performance; the second part is to use an exponential function to achieve nonlinear smoothing of the embedded value of the data point after dimensionality reduction by introducing smoothing and adjustment terms. The role of the negative sign is to reduce the embedded value of the extremely large data point after dimensionality reduction, avoiding an over-expanded value range, and introducing an adjustable hyperparameter to control the sensitivity of the exponential part to the embedded value of the data point after dimensionality reduction; The index value is calculated as follows: in, Indicates The index value of the data point; Represents the first Embedding value of data points; Represents a nonlinear weighted term. Through the combination of power exponent and tangent function, the discrimination of data points is increased, so that the index difference between different data points is significant during the index generation process, thereby improving query performance. Represents the first The embedding value of the data point The power increases the difference between data points. , can be set according to the specific implementation scenario, and is not limited here; It means that the tangent function is used to reduce the dimension of the The embedded values ​​of the data points are nonlinearly mapped to make them periodic, and As a translation term, it is used to help adjust the periodic characteristics; represents the smoothing and adjustment term, which effectively reduces the large-scale variation; It means that the exponential function is used to reduce the dimension of the The nonlinear smoothing of the embedding value of the data point is used to reduce the dimension of the The embedding value of each data point is reduced, avoiding over-amplification of the value range; represents an adjustable hyperparameter used to control the exponential part of the first The sensitivity of the embedded value of each data point can be set according to the specific implementation scenario and is not limited here; S4, using a query responsiveness calculation algorithm to compare the query point with the index value of each data point in the index, and calculate the query responsiveness; When performing a query, a query point is received as input, and the query point is compared with the index value of each data point in the index using a query responsiveness calculation algorithm to calculate the query responsiveness; When calculating the query responsiveness, the query responsiveness calculation algorithm is not only affected by the similarity between the data point and the query point, but also weighted according to the spatial distance between the two. The closer the distance, the greater the contribution to the query responsiveness. The influence of index value on query responsiveness is enhanced through the weighting mechanism of power index and exponential function, and the interference of excessive value on query response is eliminated through smoothing function; In order to enhance the sensitivity of query responsiveness to local information, a weighting factor is introduced to adjust the weight of distance information in query responsiveness. For each query point, the query responsiveness is dynamically adjusted according to the relative distance and similarity between the query point and each data point. The calculation formula for query responsiveness is: in, Indicates Query responsiveness for data points; Indicates The index value of each data point is exponentially operated to enhance the influence of the index value of the data point on the query responsiveness; represents the adjustment factor that controls the degree of influence of the index value of the data point, and The larger the index value, the greater the impact on query responsiveness. It can be set according to the specific implementation scenario and is not limited here. Indicates that the exponential function is used to smooth the data; Indicates The index value of the data point and the query point The similarity measurement function between them reflects the correlation between the two. The larger the similarity measurement, the closer the relationship between the data point and the query point, and the higher the query responsiveness. The similarity measurement method is a technical means well known to those skilled in the art and will not be described in detail here. It means that spatial information is introduced, so that the query responsiveness depends not only on the index value and similarity, but also on the spatial distance between the data point and the query point. By normalizing the distance, it can avoid that the data points that are too far away have too much influence on the query responsiveness. At the same time, the weighting factor is introduced to adjust the importance of spatial information. represents a weighting factor, which is used to adjust the weight of distance information in query responsiveness; Indicates The index value of the data point and the query point The Euclidean distance between them reflects the difference in relative positions in space; Indicates The index value of the data point and the query point The maximum Euclidean distance between the data points is used to normalize the distance between the data points and the query points, ensuring that the index values ​​of all data points are compared with the query points at the same scale, to avoid the situation where the data points with too large Euclidean distance between the index values ​​of the data points and the query points dominate the query responsiveness; In summary, a multidimensional data management system and method based on geographic information has been completed.

[0025] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0026] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0027] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A multidimensional data management method based on geographic information, characterized in that: The following steps are involved: S1: Obtain a geographic information data set, process the geographic information data in the geographic information data set by a geographic information data nonlinear mapping algorithm, and calculate the mapping value of the data point; S2: Reduce the dimension of the mapping value of the data point to a low-dimensional space through an adaptive nonlinear dimensionality reduction and embedding algorithm to obtain the embedding value of the data point after dimensionality reduction; S3: Based on the embedding value of the data point after dimensionality reduction, the index value of the data point is calculated by the index generation algorithm; S4: Use a query responsiveness calculation algorithm to compare the query point with the index value of each data point in the index, and calculate the query responsiveness.

2. A multidimensional data management method based on geographic information according to claim 1, characterized in that: The S1 specifically includes: The nonlinear mapping algorithm for geographic information data adopts a sine function to capture the periodic fluctuations of geographic information data, and introduces a periodic adjustment item to correct the geographic information data; and introduces a spatial adjustment factor to adjust the spatial transformation of the geographic information data; the change of the geographic information data is adjusted through an exponential function, and combined with the adjustment factor, the mapping value of the data point is obtained.

3. The multidimensional data management method based on geographic information according to claim 1, characterized in that: The S1 specifically includes: The calculation formula for the mapping value of a data point is: in, Indicates that in the new coordinate space The data point The mapping value of the dimension; Indicates The data point The value of the dimension, i.e., geographic information data; Indicates The data point The square of the value of the dimension; Indicates that for Periodic adjustment items of geographic information data; represents the sine function; represents the adjustment factor that controls the intensity of the influence of the index term; represents the exponential function; Indicates that for The spatial adjustment factor for each data point; represents the cosine function; Indicates normalization processing.

4. The multidimensional data management method based on geographic information according to claim 1, characterized in that: The S2 specifically includes: The adaptive nonlinear dimensionality reduction and embedding algorithm normalizes the mapping values ​​of the data points by introducing a normalization term, processes the normalization term by a hyperbolic tangent function, and smoothes the mapping values ​​of the data points.

5. The multidimensional data management method based on geographic information according to claim 4, characterized in that: The S2 specifically includes: In the process of dimensionality reduction, the adaptive nonlinear dimensionality reduction and embedding algorithm adjusts the mapping value of each dimension through modular operation to obtain the embedding value of the data point after dimensionality reduction. The specific implementation formula is: in, Represents the first Embedding value of data points; Indicates that in the new coordinate space The data point The mapping value of the dimension; represents the hyperbolic tangent function; Express The dimensions are summed; represents the normalization term; It means that the mapping values ​​of all dimensions are weighted and accumulated, and then nonlinearly adjusted through the exponential function; Represents the adjustment factor that controls the exponential decay degree of the mapping value in the dimensionality reduction formula; Represents a modular operation term; express Activation function in functional form; Represents the adjustment factor that controls the influence of each dimension in the dimensionality reduction process.

6. The multidimensional data management method based on geographic information according to claim 1, characterized in that: The S3 specifically includes: The index generation algorithm generates the index value of each data point through a weighted calculation consisting of two parts. The first part is to generate a nonlinear weighted term by performing high-order power operations and tangent function transformation on the embedded value of each data point after dimensionality reduction; the second part is to introduce smoothing and adjustment terms, use exponential functions to perform nonlinear smoothing on the embedded values ​​of the data points after dimensionality reduction, and introduce adjustable hyperparameters to obtain the index value of the data point.

7. A multidimensional data management method based on geographic information according to claim 6, characterized in that: The S3 specifically includes: The calculation formula for the index value of a data point is: in, Indicates The index value of the data point; Represents the first Embedding value of data points; represents the nonlinear weighting term; Represents the first The embedding value of the data point Power; It means that the tangent function is used to reduce the dimension of the The embedding values ​​of the data points are nonlinearly mapped; represents smoothing and adjustment terms; It means that the exponential function is used to reduce the dimension of the Nonlinear smoothing of the embedded values ​​of data points; represents an adjustable hyperparameter.

8. The multidimensional data management method based on geographic information according to claim 1, characterized in that: The S4 specifically includes: When calculating the query responsiveness, the query responsiveness calculation algorithm performs weighting according to the spatial distance between the data point and the query point, combines the weighting mechanism and smoothing function of the power exponent and exponential function, introduces a weighting factor, and dynamically adjusts the query responsiveness.

9. The multidimensional data management method based on geographic information according to claim 8, characterized in that: The S4 specifically includes: The calculation formula for query responsiveness is: in, Indicates Query responsiveness for data points; Indicates The index values ​​of the data points are exponentially calculated; The adjustment factor that represents the influence of the index value of the control data point; Indicates that the exponential function is used to smooth the data; Indicates The index value of the data point and the query point The similarity measurement function between them; represents the weighting factor; Indicates The index value of the data point and the query point The Euclidean distance between Indicates The index value of the data point and the query point The maximum Euclidean distance between .

10. A multidimensional data management system based on geographic information, applied to the multidimensional data management method based on geographic information as claimed in claim 1, characterized in that: Includes the following parts: Data acquisition module, geographic information data mapping module, nonlinear dimension reduction and embedding module, index generation module, query responsiveness calculation module; Data acquisition module: acquires geographic information data set, and outputs geographic information data in the geographic information data set to the geographic information data mapping module; Geographic information data mapping module: processes the geographic information data in the geographic information data set from the data acquisition module through a geographic information data nonlinear mapping algorithm, calculates the mapping value, and outputs the mapping value to the nonlinear dimensionality reduction and embedding module; Non-linear dimensionality reduction and embedding module: The mapping value from the geographic information data mapping module is reduced to a low-dimensional space through an adaptive non-linear dimensionality reduction and embedding algorithm to obtain the embedding value of the data point after dimensionality reduction, and the embedded value of the data point after dimensionality reduction is output to the index generation module; Index generation module: Based on the embedding value of the data point after dimensionality reduction by the nonlinear dimensionality reduction and embedding module, the index value is calculated by the index generation algorithm, and the index value is output to the query responsiveness calculation module; Query responsiveness calculation module: Based on the index value of the index generation module, the query point is compared with the index value of each data point in the index using the query responsiveness calculation algorithm to calculate the query responsiveness.

Images