Regional governance method, device and equipment based on data elements

By obtaining governance topic information, performing data cleaning and feature dimensionality reduction processing, calculating similarity and dynamic matching, the problem of inefficient matching of governance executive subjects, resources and demands in the existing technology is solved, and the rapid and accurate matching results are achieved. Efficient governance.

CN119066406AInactive Publication Date: 2024-12-03TAIJI COMPUTER CORPORATION LIMITED
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202410903045.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-05
Publication Date
2024-12-03
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

In the existing technology, the matching between the governance executive body, the resources required for governance and the governance needs is inefficient, and it is difficult to cope with complex and changing governance needs, and it mainly relies on manual and simple machine learning.

Method used

By obtaining governance topic information, performing data cleaning and feature dimensionality reduction processing, extracting data elements, calculating similarity and dynamic matching, and outputting matching results for governance.

Benefits of technology

It improves the efficiency and accuracy of information processing, reduces manual operation costs, can obtain matching results quickly and accurately, give full play to the role of the execution entity and the required resources, and meet governance needs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066406A_ABST
    Figure CN119066406A_ABST
Patent Text Reader

Abstract

The invention provides a regional governance method, device and equipment based on data elements. The method comprises the following steps: acquiring governance execution subject information, governance required resource information and governance demand information corresponding to governance subject information of a to-be-governed region; performing data cleaning on the governance execution subject information, the governance required resource information and the governance demand information; extracting data element information in the target execution main body information, the target required resource information and the target demand information obtained after cleaning to obtain main body elements, resource elements and demand elements; performing feature dimension reduction processing on the main body element, the resource element and the demand element to obtain a target main body element, a target resource element and a target demand element; determining the similarity among the target main body element, the target resource element and the target demand element; based on the similarity, matching the target main body element, the target resource element and the target demand element to obtain a matching result; and outputting a matching result for governing the to-be-governed area.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of regional governance technology, and in particular to a regional governance method, device and equipment based on data elements. Background Art

[0002] When governing some areas (areas may include cities, industrial parks, government sectors, etc.) according to governance themes (governance themes may include environment, transportation, public facilities, etc.), it is necessary to collect a large amount of relevant data and determine the degree of match between the governance executor, the resources required for governance, and the governance needs based on the collected relevant data.

[0003] At present, the collection of relevant data is mainly done manually, and the matching between governance execution entities, governance resources and governance needs is achieved by relying on database queries or simple machine learning. The above solutions are time-consuming and labor-intensive, with low matching efficiency, and are difficult to cope with complex and changing governance needs. Summary of the invention

[0004] The present invention provides a regional governance method, device and equipment based on data elements, which are used to solve the technical problem in the prior art that it is impossible to efficiently match the governance execution subject, the resources required for governance and the governance needs.

[0005] In one aspect, the present invention provides a regional governance method based on data elements, comprising: Obtaining governance execution subject information, governance resource information and governance demand information corresponding to the governance subject information of the area to be governed; The governance execution subject information, the governance required resource information and the governance demand information are respectively cleansed to obtain the corresponding target execution subject information, target required resource information and target demand information; Extracting data element information from the target execution subject information, the target required resource information and the target demand information to obtain the corresponding subject elements, resource elements and demand elements; Performing feature dimensionality reduction processing on the subject element, the resource element and the demand element respectively to obtain the corresponding target subject element, target resource element and target demand element; Determining the similarity between the target subject element, the target resource element and the target demand element; Based on the similarity, matching the target subject element, the target resource element and the target demand element to obtain a matching result; The matching result is output for use in governing the area to be governed.

[0006] According to a regional governance method based on data elements provided by the present invention, the feature dimension reduction processing of the subject element, the resource element and the demand element respectively includes: Selecting key features whose weights are greater than preset weights from the original features of the subject element, the resource element, and the demand element respectively; The key features of the main element, the resource element and the demand element are respectively subjected to feature conversion processing; or, the key features of the main element, the resource element and the demand element are respectively subjected to projection processing.

[0007] According to a regional governance method based on data elements provided by the present invention, the key features of the subject element, the resource element and the demand element are respectively converted into features, including: Mapping the key features of the subject element, the resource element and the demand element from the original first dimensional space to the second dimensional space; wherein the dimension of the second dimensional space is smaller than the dimension of the first dimensional space; The step of converting the key features of the subject element, the resource element, and the demand element respectively includes: The key features of the subject element, the resource element and the demand element are respectively converted or combined to obtain new key features.

[0008] According to a regional governance method based on data elements provided by the present invention, the determining of the similarity between the target subject element, the target resource element and the target demand element includes: The target subject element, the target resource element and the target demand element are respectively vectorized to obtain the corresponding vector subject element, vector resource element and vector demand element; Determine the similarity between the vector subject element, the vector resource element, and the vector requirement element.

[0009] According to a regional governance method based on data elements provided by the present invention, the determining of the similarity between the vector main element, the vector resource element, and the vector demand element includes: Determine the distance between any two of the vector main elements, the vector resource elements, and the vector requirement elements by distance measurement, wherein the smaller the distance, the higher the similarity; or The cosine similarity between any two of the vector main elements, the vector resource elements, and the vector requirement elements is determined by similarity measurement, wherein the larger the cosine similarity, the higher the similarity.

[0010] According to a regional governance method based on data elements provided by the present invention, the data cleaning includes at least one of the following methods: Process outliers, remove duplicate data, fill in missing values, convert data formats, and convert data types.

[0011] According to a regional governance method based on data elements provided by the present invention, the extracting of data element information from the target execution subject information, the target required resource information and the target demand information includes: The data element information in each of the target execution subject information, the target required resource information and the target demand information is extracted respectively through a pre-trained natural language processing model.

[0012] According to a regional governance method based on data elements provided by the present invention, matching the target subject element, the target resource element and the target demand element based on the similarity includes: Based on the similarity, dynamic matching is used to match the target subject element, the target resource element and the target demand element.

[0013] On the other hand, the present invention also provides a regional governance device based on data elements, comprising: An information acquisition module is used to obtain governance execution subject information, governance required resource information and governance demand information corresponding to the governance subject information of the area to be governed; A data cleaning module is used to clean the governance execution subject information, the governance required resource information and the governance demand information respectively to obtain the corresponding target execution subject information, target required resource information and target demand information; An element extraction module is used to extract data element information from the target execution subject information, the target required resource information and the target demand information to obtain the corresponding subject elements, resource elements and demand elements; A dimension reduction processing module is used to perform feature dimension reduction processing on the subject element, the resource element and the demand element respectively to obtain the corresponding target subject element, target resource element and target demand element; A similarity determination module, used to determine the similarity between the target subject element, the target resource element and the target demand element; A matching module, used for matching the target subject element, the target resource element and the target demand element based on the similarity to obtain a matching result; The output module is used to output the matching result for use in governing the area to be governed.

[0014] On the other hand, the present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements any of the data element-based regional governance methods described above.

[0015] The regional governance method, device and equipment based on data elements provided by the present invention can improve the efficiency and accuracy of subsequent information processing by performing data cleaning on the governance execution subject information, the resource information required for governance and the governance demand information respectively, and obtaining the corresponding target execution subject information, the target required resource information and the target demand information. The subject elements, resource elements and demand elements are subjected to feature dimensionality reduction processing respectively, and the corresponding target subject elements, target resource elements and target demand elements are obtained, which can improve the generalization ability of the elements, reduce the overfitting situation, enhance the understanding between the features and the feature values, and improve the processing efficiency of the elements. Then, the similarity between the target subject elements, the target resource elements and the target demand elements is determined, and based on the similarity, the target subject elements, the target resource elements and the target demand elements are matched to obtain the matching results for the governance of the area to be governed. In summary, this embodiment reduces the cost of manual operation, can obtain matching results more quickly and accurately, has high processing efficiency, can give full play to the role of the execution subject and the required resources, and meet the governance needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flowchart of a regional governance method based on data elements provided by an embodiment of the present invention; Figure 2 is a schematic diagram of the structure of a regional governance device based on data elements provided in an embodiment of the present invention; Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0019] Figure 1 It is a flowchart of the regional governance method based on data elements provided in an embodiment of the present invention.

[0020] like Figure 1 As shown, the regional governance method based on data elements provided in the embodiment of the present invention can be executed by a computer, a mobile phone or a smart wearable device, and the method mainly includes the following steps: 101. Obtain the governance execution entity information, governance required resource information and governance demand information corresponding to the governance subject information of the area to be governed.

[0021] In this step, the governance execution subject information, governance required resource information and governance demand information corresponding to the governance subject information of the area to be governed can be obtained through web crawlers; relevant permissions can be obtained from data operators to obtain the above information from data operators; or application for disclosure of relevant data sets can be made to obtain the above information.

[0022] 102. Perform data cleansing on the governance execution subject information, the governance required resource information and the governance demand information respectively to obtain the corresponding target execution subject information, target required resource information and target demand information.

[0023] In this step, data cleaning may include at least one of the following methods: processing outliers, removing duplicate data, filling missing values, data format conversion, and data type conversion. Data cleaning can be performed multiple times until the quality of the cleaned data meets the preset standards.

[0024] Processing outliers mainly involves correcting outliers so that the corrected outliers are within a reasonable range, which is conducive to ensuring the accuracy of subsequent matching. Removing duplicate data can also reduce the deviations generated during data analysis. To fill missing values, appropriate methods need to be used, such as using the mean, median or mode, or estimating missing values ​​through a predictive model. Data format conversion ensures the consistency of data formats, such as unifying the date format or encoding categorical data into numeric data. Data type conversion is the process of converting data from one type to another to ensure the accuracy and consistency of the data, thereby improving the reliability of the data, for example, converting data to a string type. This is very useful when processing text data or when converting numeric values ​​to text format. Of course, data cleaning can also include logical error cleaning (such as the value of the age field cannot be negative), non-requirement data cleaning, and relevance verification. For text type information, you can also extract PDF file data through text processing, or recognize text data through optical character recognition (OCR).

[0025] 103. Extract data element information from target execution subject information, target required resource information and target demand information to obtain the corresponding subject elements, resource elements and demand elements.

[0026] In this step, the data element information in the target execution subject information, target required resource information and target demand information is extracted through the pre-trained natural language processing model. Generally, the natural language processing model can be trained with pre-collected sample data. The recognition rate of the trained natural language processing model for data elements can reach 90%-95%, or even higher.

[0027] 104. Perform feature dimensionality reduction processing on the subject factors, resource factors and demand factors respectively to obtain their corresponding target subject factors, target resource factors and target demand factors.

[0028] In this step, feature dimensionality reduction is performed on the main factors, resource factors, and demand factors respectively, that is, the number of features of the main factors, resource factors, and demand factors are reduced. This can improve generalization ability, reduce overfitting, enhance the understanding between features and feature values, and improve the processing efficiency of factors.

[0029] 105. Determine the similarity between the target subject elements, target resource elements and target demand elements.

[0030] In this step, specifically, the target main element, the target resource element and the target demand element are respectively vectorized to obtain the corresponding vector main element, vector resource element and vector demand element, and then the similarity between the vector main element, the vector resource element and the vector demand element is determined. The advantage of vectorization is that it can capture the semantic information of the element text, convert high-dimensional text data into low-dimensional numerical vectors, unify the metric standards of different types of data, make the comparison of similarity more consistent and standardized, reduce the computational complexity and improve the processing efficiency. For example, text data, image data and sound data can all be converted into numerical vectors, and then compared using the same similarity measurement method. Vectorized data can simplify the calculation process of similarity. For example, cosine similarity is determined by calculating the dot product of two vectors and the product of their respective moduli, which is easy to implement in vector form.

[0031] 106. Based on the similarity, the target subject elements, target resource elements and target demand elements are matched to obtain the matching results.

[0032] In this step, dynamic matching is used to match the target subject elements, target resource elements and target demand elements based on similarity, which can improve the matching efficiency to adapt to the rapidly changing governance environment and needs.

[0033] 107. Output the matching results for the governance of the area to be governed.

[0034] In this step, a communication connection can be established in advance with the governance-related departments or systems, and the matching results can be output to the relevant departments or systems.

[0035] In this embodiment, the governance execution subject information, the governance required resource information and the governance demand information are cleaned respectively to obtain the corresponding target execution subject information, target required resource information and target demand information, which can improve the efficiency and accuracy of subsequent information processing. The subject elements, resource elements and demand elements are processed with feature dimensionality reduction to obtain the corresponding target subject elements, target resource elements and target demand elements, which can improve the generalization ability of the elements, reduce the overfitting situation, enhance the understanding between features and feature values, and improve the processing efficiency of the elements. Then, the similarity between the target subject elements, target resource elements and target demand elements is determined, and based on the similarity, the target subject elements, target resource elements and target demand elements are matched to obtain matching results for the governance of the area to be governed. In summary, this embodiment reduces the cost of manual operation, can obtain matching results more quickly and accurately, has high processing efficiency, can give full play to the role of the execution subject and the required resources, and meet the governance needs.

[0036] In one embodiment of the present specification, feature dimension reduction processing is performed on the subject elements, resource elements and demand elements respectively, including: Select key features whose weights are greater than preset weights from the original features of the main elements, resource elements and demand elements respectively; The key features of the main elements, resource elements and demand elements are respectively converted; or, the key features of the main elements, resource elements and demand elements are respectively projected.

[0037] In this embodiment, feature engineering can be used to perform feature dimensionality reduction processing on the main elements, resource elements, and demand elements respectively. For example, feature selection can be used to select key features with weights greater than preset weights (which can also be understood as eliminating features with the smallest weights) from the original features of the main elements, resource elements, and demand elements. The methods of feature selection mainly include: filtering, wrapping, and embedding. Filtering method: Evaluate the importance of features based on statistical tests or correlation coefficients, and select those features that are most relevant to the target variable. Wrapping method: Evaluate the importance of features through the selectivity of the model, such as using a recursive feature elimination method. Embedding method: During the model training process, evaluate the importance of features through the parameters of the model, such as using the number of feature splits in a decision tree. Feature selection is the process of selecting more effective features from feature vectors to form new, simpler and more effective feature vectors. It is particularly important in high-dimensional data analysis and can improve predictive and generalization capabilities.

[0038] For another example, feature transformation can be used to transform the key features of the main elements, resource elements, and demand elements; or, the key features of the main elements, resource elements, and demand elements can be projected. Feature transformation is a data pre-processing operation that transforms a set of features into a new set of features. The number of new features is usually less than the number of original features. This transformation can be linear or nonlinear. The purpose is to retain the information of the original features while reducing the number of features, thereby reducing the complexity of the model and improving learning efficiency. Feature transformation and the above-mentioned feature selection can be used separately or in combination. When used separately, the two are in an or relationship.

[0039] In an embodiment of the present specification, the key features of the subject element, the resource element and the demand element are respectively converted into features, including: Mapping the key features of the subject elements, resource elements and demand elements from the original first-dimensional space to the second-dimensional space; wherein the dimension of the second-dimensional space is smaller than the dimension of the first-dimensional space; The key features of the subject elements, resource elements and demand elements are converted respectively, including: The key features of the main elements, resource elements and demand elements are transformed or combined respectively to obtain new key features.

[0040] In this embodiment, the first dimensional space can be regarded as a high-dimensional space, and the second dimensional space can be regarded as a low-dimensional space. The key features of the subject elements, resource elements, and demand elements are respectively mapped from the original first dimensional space to the second dimensional space, and the features of the original data are converted into a set of new, fewer features, which are some form of combination or transformation of the original features. This conversion is intended to retain the most important information in the data set while removing those unimportant or redundant features.

[0041] Mapping (projection) usually involves creating a transformation matrix that maps points in the original feature space to a lower-dimensional space. For example, in principal component analysis (PCA), the data is projected into a new coordinate system consisting of principal components through linear transformation, which are the directions in which the variance of the original data is the largest. Random Projection reduces the dimensionality of the data by randomly selecting a transformation matrix while preserving the structure of the original data as much as possible. In general, projection in feature dimensionality reduction means converting a data set from a high-dimensional feature space to a low-dimensional feature space through mathematical transformation, so as to simplify the data structure and reduce computational complexity, while preserving the important features of the data as much as possible. The key features of the subject factor, resource factor, and demand factor are transformed or combined to obtain new key features. For example, if there are two features, speed and distance, by multiplying these two features, we can get a new feature, the total distance traveled, which may be more useful for certain analysis or prediction tasks. Feature transformation may include operations such as logarithmic transformation, standardization, and normalization. These operations can help us deal with skew, different dimensions or scales in the original data, making the data more suitable for subsequent analysis or model training. Through feature transformation, the number of features can be reduced. In general, feature transformation aims to improve the expressiveness of data by creating new feature combinations, while reducing the number of features, which is beneficial to improving the efficiency and effectiveness of machine learning algorithms.

[0042] In an embodiment of the present specification, determining the similarity between the vector subject element, the vector resource element, and the vector requirement element includes: Determine the distance between any two vector main elements, vector resource elements, and vector demand elements through distance measurement, where the smaller the distance, the higher the similarity; or The cosine similarity between any two vector main elements, vector resource elements, and vector demand elements is determined through similarity measurement, wherein the larger the cosine similarity, the higher the similarity.

[0043] In this embodiment, the distance measurement method may include multiple methods, such as Euclidean distance, Manhattan distance, Minkowski distance, and Mahalanobis distance. The distances between the vector main elements, vector resource elements, and vector demand elements may be determined, such as the distance between the vector main element and the vector resource element, the distance between the vector resource element and the vector demand element, and the distance between the vector main element and the vector demand element. In general, when the above three distances are all less than the preset distance, it means that the three are similar.

[0044] When determining the cosine similarity, the cosine similarity between the vector main elements, the vector resource elements, and the vector requirement elements can be determined. For example, the cosine similarity between the vector main element and the vector resource element, the cosine similarity between the vector resource element and the vector requirement element, and the cosine similarity between the vector main element and the vector requirement element. In general, when the above three cosine similarities are all greater than the preset similarity, it means that the three are similar.

[0045] In some other embodiments of the present specification, the matching results are output for governance of the area to be governed. Specifically, the matching result is the correspondence between the target subject elements, target resource elements and target demand elements obtained based on the similarity. For example, assume that the target subject elements, target resource elements and target demand elements are matched based on cosine similarity. The cosine similarity between the target subject element and the target resource element is 0.9, the cosine similarity between the target resource element and the target demand element is 0.85, and the cosine similarity between the target subject element and the target demand element is 0.9. If the cosine similarities of the three are all greater than the preset similarity threshold (for example, 0.8), then the correspondence between the target subject element, the target resource element and the target demand element is established, that is, the matching result is obtained.

[0046] For example, suppose that the target subject element, target resource element, and target demand element are matched based on cosine similarity. The cosine similarity between the target subject element and the target resource element is 0.9, the cosine similarity between the target resource element and the target demand element is 0.9, and the cosine similarity between the target subject element and the target demand element is 0.95. If the cosine similarities of the three are all greater than the preset similarity threshold (for example, 0.8), then the correspondence between the target subject element, the target resource element, and the target demand element is established, that is, the matching result is obtained. For the above multiple matching results, the one with the greatest similarity can be selected as the usage plan, and the governance execution entity can prepare resources and conduct governance according to the target resource element corresponding to the target demand in the usage plan.

[0047] For example, suppose that the target subject element, target resource element, and target demand element are matched based on cosine similarity. The cosine similarity between the target subject element and the target resource element is 0.9, the cosine similarity between the target resource element and the target demand element is 0.75, and the cosine similarity between the target subject element and the target demand element is 0.8. If the cosine similarities of the three are not all greater than the preset similarity threshold (for example, 0.8), the corresponding relationship between the target subject element, the target resource element, and the target demand element cannot be established, and no matching result is obtained.

[0048] In some other embodiments of the present specification, after outputting the matching result, the method may further include: Obtain evaluation satisfaction of matching results; If the evaluation satisfaction does not reach the preset threshold, the solution of the present application can be optimized and adjusted based on the above steps 103 to 105. For example, the method of extracting data element information, the method of feature dimensionality reduction processing, the method of determining similarity, etc. can be adjusted.

[0049] The following is an introduction to this application using the environmental governance of an industrial park as an example. The industrial park represents the area to be governed, and the environmental governance represents the governance subject information.

[0050] Step 1: Collect data on the executive entities related to environmental governance in industrial park governance (such as the environmental department of the industrial park, the leadership organization of the industrial park, etc.), data on resources required for governance (such as the human, material and financial resources required for the governance of the industrial park, etc.) and data on governance needs (such as the standards for achieving environmental governance in the industrial park).

[0051] Step 2: Preprocess the data of the executing subject, the data of resources required for governance, and the data of governance demand (for example, data cleaning). Then, extract the key elements of the executing subject data, the data of resources required for governance, and the data of governance demand, and obtain the corresponding subject elements, resource elements, and demand elements. For example, the subject elements (key elements of the executing subject data) may include the scope of responsibilities of the environmental department of the industrial park and the professional capabilities of the leading organization of the industrial park; the resource elements (key elements of the resources required for governance) may include the quantity and quality of governance resources; the demand elements (key elements of the governance demand data) may include specific indicators after environmental governance, etc.

[0052] Step 3: Based on the similarity calculation model, calculate the matching degree between the subject elements, resource elements and demand elements. Generally speaking, the higher the similarity, the higher the matching degree.

[0053] Step 4: According to the matching degree, the dynamic matching algorithm is used to dynamically match the subject elements, resource elements and demand elements to obtain the matching result, which is also the matching solution.

[0054] Step 5: Output the matching plan to the relevant department or system for execution, and optimize the matching algorithm based on the actual effect received.

[0055] The following uses the traffic management of a city as an example to introduce this application. The city represents the area to be managed, and the traffic management represents the management subject information.

[0056] Step 1: Collect data on the executive entities related to traffic management in urban governance (such as the city’s government transportation department, highway management department, etc.), data on resources required for governance (such as human, material, financial resources, etc.) and data on governance needs (such as the standards for meeting the city’s traffic management standards).

[0057] Step 2: Preprocess the data of the executing subject, the data of resources required for governance, and the data of governance demand (for example, data cleaning). Then, extract the key elements of the executing subject data, the data of resources required for governance, and the data of governance demand, and obtain the corresponding subject elements, resource elements, and demand elements. For example, the subject elements (key elements of the executing subject data) may include the scope of responsibilities of the government transportation department and the highway management department; the resource elements (key elements of the resources required for governance) may include the quantity and quality of governance resources; the demand elements (key elements of the governance demand data) may include specific indicators after traffic governance, etc.

[0058] Step 3: Based on the similarity calculation model, calculate the matching degree between the subject elements, resource elements and demand elements. Generally speaking, the higher the similarity, the higher the matching degree.

[0059] Step 4: According to the matching degree, the dynamic matching algorithm is used to dynamically match the subject elements, resource elements and demand elements to obtain the matching result, which is also the matching solution.

[0060] Step 5: Output the matching plan to the relevant department or system for execution, and optimize the matching algorithm based on the actual effect received.

[0061] The above two examples are only used to illustrate the present application and do not impose any limitation on the present application. In addition to the above-mentioned environmental and traffic management, it can also include the management of public facilities, etc., which will not be listed here one by one.

[0062] In addition, some other solutions can be used to achieve regional governance. Example 1, regional governance method based on blockchain: distributed storage and sharing of governance data are achieved through blockchain to ensure the security and credibility of data, while using smart contracts to realize automated matching process. This method can improve the transparency and traceability of data, but may face the complexity and cost of technical implementation. Example 2, regional governance method based on expert system: using the knowledge and experience of domain experts, build an expert system to guide the matching process of governance subjects, governance resources and governance needs. This method can make full use of the wisdom of experts, but may be limited by the number and availability of experts. Example 3, regional governance method based on machine learning: use machine learning algorithms to model and predict governance subjects, governance resources and governance needs to achieve more accurate matching. This method requires rich data support and complex model training process.

[0063] Based on the same general inventive concept, the present invention also protects a regional governance device based on data elements. Figure 2 20 is a schematic diagram of the structure of the regional governance device based on data elements provided by an embodiment of the present invention. The regional governance device based on data elements provided by the present invention is described below. The regional governance device based on data elements described below and the regional governance method based on data elements described above can be referred to each other. The regional governance device based on data elements includes an information acquisition module 201, a data cleaning module 202, an element extraction module 203, a dimensionality reduction processing module 204, a similarity determination module 205, a matching module 206 and an output module 207.

[0064] The information acquisition module 201 is used to acquire the governance execution subject information, governance required resource information and governance demand information corresponding to the governance subject information of the area to be governed; The data cleaning module 202 is used to clean the governance execution subject information, the governance required resource information and the governance demand information respectively, and obtain the corresponding target execution subject information, target required resource information and target demand information; The element extraction module 203 is used to extract data element information from target execution subject information, target required resource information and target demand information to obtain the corresponding subject elements, resource elements and demand elements; The dimension reduction processing module 204 is used to perform feature dimension reduction processing on the subject elements, resource elements and demand elements respectively, and obtain the corresponding target subject elements, target resource elements and target demand elements; The similarity determination module 205 is used to determine the similarity between the target subject element, the target resource element and the target demand element; The matching module 206 is used to match the target subject element, the target resource element and the target demand element based on similarity to obtain a matching result; The output module 207 is used to output the matching results for use in managing the area to be managed.

[0065] Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0066] like Figure 3 As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the regional governance method based on data elements.

[0067] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0068] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the regional governance methods based on data elements provided by the above methods.

[0069] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the data element-based regional governance method provided by the above-mentioned methods.

[0070] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0071] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these 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.

Claims

1. A regional governance method based on data elements, characterized in that: include: Obtaining governance execution subject information, governance required resource information and governance demand information corresponding to the governance subject information of the area to be governed; The governance execution subject information, the governance required resource information and the governance demand information are respectively cleansed to obtain the corresponding target execution subject information, target required resource information and target demand information; Extracting data element information from the target execution subject information, the target required resource information and the target demand information to obtain the corresponding subject elements, resource elements and demand elements; Performing feature dimensionality reduction processing on the subject element, the resource element and the demand element respectively to obtain the corresponding target subject element, target resource element and target demand element; Determining the similarity between the target subject element, the target resource element and the target demand element; Based on the similarity, matching the target subject element, the target resource element and the target demand element to obtain a matching result; The matching result is output for use in governing the area to be governed.

2. The regional governance method based on data elements according to claim 1 is characterized in that: The performing feature dimensionality reduction processing on the subject element, the resource element and the demand element respectively includes: Selecting key features whose weights are greater than preset weights from the original features of the subject element, the resource element, and the demand element respectively; The key features of the main element, the resource element and the demand element are respectively subjected to feature conversion processing; or, the key features of the main element, the resource element and the demand element are respectively subjected to projection processing.

3. The regional governance method based on data elements according to claim 2 is characterized in that: The step of converting the key features of the subject element, the resource element, and the demand element respectively includes: Mapping the key features of the subject element, the resource element and the demand element from the original first dimensional space to the second dimensional space; wherein the dimension of the second dimensional space is smaller than the dimension of the first dimensional space; The step of converting the key features of the subject element, the resource element, and the demand element respectively includes: The key features of the subject element, the resource element and the demand element are respectively converted or combined to obtain new key features.

4. The regional governance method based on data elements according to claim 1 is characterized in that: The determining of the similarity between the target subject element, the target resource element and the target demand element includes: The target subject element, the target resource element and the target demand element are respectively vectorized to obtain the corresponding vector subject element, vector resource element and vector demand element; Determine the similarity between the vector subject element, the vector resource element, and the vector requirement element.

5. The regional governance method based on data elements according to claim 4 is characterized in that: The determining the similarity between the vector main element, the vector resource element, and the vector requirement element includes: Determine the distance between any two of the vector main elements, the vector resource elements, and the vector requirement elements by distance measurement, wherein the smaller the distance, the higher the similarity; or The cosine similarity between any two of the vector main elements, the vector resource elements, and the vector requirement elements is determined by similarity measurement, wherein the larger the cosine similarity, the higher the similarity.

6. The regional governance method based on data elements according to claim 1 is characterized in that: The data cleaning includes at least one of the following methods: Process outliers, remove duplicate data, fill in missing values, convert data formats, and convert data types.

7. The regional governance method based on data elements according to claim 1 is characterized in that: The extracting of the target execution subject information, the target required resource information and the data element information in the target demand information includes: The data element information in each of the target execution subject information, the target required resource information and the target demand information is extracted respectively through a pre-trained natural language processing model.

8. The regional governance method based on data elements according to claim 1 is characterized in that: The matching of the target subject element, the target resource element and the target demand element based on the similarity includes: Based on the similarity, dynamic matching is used to match the target subject element, the target resource element and the target demand element.

9. A regional governance device based on data elements, characterized in that: include: An information acquisition module is used to obtain governance execution subject information, governance required resource information and governance demand information corresponding to the governance subject information of the area to be governed; A data cleaning module is used to clean the governance execution subject information, the governance required resource information and the governance demand information respectively to obtain the corresponding target execution subject information, target required resource information and target demand information; An element extraction module is used to extract data element information from the target execution subject information, the target required resource information and the target demand information to obtain the corresponding subject elements, resource elements and demand elements; A dimension reduction processing module is used to perform feature dimension reduction processing on the subject element, the resource element and the demand element respectively to obtain the corresponding target subject element, target resource element and target demand element; A similarity determination module, used to determine the similarity between the target subject element, the target resource element and the target demand element; A matching module, used for matching the target subject element, the target resource element and the target demand element based on the similarity to obtain a matching result; The output module is used to output the matching result for use in governing the area to be governed.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, it implements the regional governance method based on data elements as described in any one of claims 1 to 8.

Citation Information

Patent Citations

  • Demand matching method and system

    CN114742067A

  • Integrated commanding and dispatching system for urban governance

    CN115034604A

  • Resource matching method and device based on grassroots governance, and medium

    CN118210980A