Village-level power grid reconstruction project data association method and device

Abstract

The invention provides a village-level power grid reconstruction project data association method and device, and belongs to the technical field of electric power. The method comprises the following steps: acquiring electric power data of a village-level power grid in a target area, position data of each village and reconstruction data of a reconstruction project of each village; determining a power feature vector corresponding to the attribute of each type of data in the power data, a position feature vector corresponding to the attribute of each type of data in the position data, and a transformation feature vector corresponding to the attribute of each type of data in the transformation data; according to the electric power feature vector, the position feature vector and the transformation feature vector, establishing a corresponding relation among the electric power data, the position data and the transformation data; and matching the electric power data and the position data as well as the transformation data and the position data according to the corresponding relation to obtain village-level power grid data of each village in the target area. According to the invention, various data of the village-level power grid corresponding to the reconstruction project can be accurately obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of power grids, and particularly to a method and device for associating data of a rural power grid transformation project. Background Art

[0002] With the continuous development of power grid technology, it is necessary to transform and upgrade the rural power grid in order to obtain various power data of the rural power grid in a timely and accurate manner, and improve the safety and stability of power transmission.

[0003] When carrying out the transformation project of the rural power grid, it is necessary to collect and sort out the basic situation of the rural power grid. In the related art, mainly the power data such as power grid lines and power equipment in the power grid are sorted out. However, the inventor found that when transforming the rural power grid, the relevant data is numerous and complex, and it is difficult to accurately obtain the power data corresponding to the rural power grid transformation only by using the method of sorting out the power data in the related art. Summary of the Invention

[0004] Embodiments of the present invention provide a method and device for associating data of a rural power grid transformation project, so as to correspond the power data of the rural power grid to the transformation project and accurately obtain various data of the rural power grid corresponding to the transformation project.

[0005] In a first aspect, embodiments of the present invention provide a method for associating data of a rural power grid transformation project, including:

[0006] Obtaining power data of a rural power grid in a target area, location data of each village, and transformation data of the transformation project of each village;

[0007] Determining a power feature vector corresponding to the attribute of each type of data in the power data, a location feature vector corresponding to the attribute of each type of data in the location data, and a transformation feature vector corresponding to the attribute of each type of data in the transformation data;

[0008] Establishing a matching correspondence relationship among the power data, the location data, and the transformation data according to the power feature vector, the location feature vector, and the transformation feature vector;

[0009] Matching the power data and the location data, and the transformation data and the location data according to the matching correspondence relationship to obtain the rural power grid data of each village in the target area.

[0010] In a possible implementation manner, determining a power feature vector corresponding to the attribute of each type of data in the power data, a location feature vector corresponding to the attribute of each type of data in the location data, and a transformation feature vector corresponding to the attribute of each type of data in the transformation data includes:

[0011] Determine multiple attributes of each type of data in the power data, multiple attributes of each type of data in the location data, and multiple attributes of each type of data in the renovation data;

[0012] Perform feature vectorization processing on the multiple attributes corresponding to the power data respectively to obtain power feature vectors of the multiple attributes corresponding to the power data;

[0013] Perform feature vectorization processing on the multiple attributes corresponding to the location data respectively to obtain location feature vectors of the multiple attributes corresponding to the location data;

[0014] Perform feature vectorization processing on the multiple attributes corresponding to the renovation data respectively to obtain renovation feature vectors of the multiple attributes corresponding to the renovation data.

[0015] In a possible implementation manner, according to the power feature vectors, the location feature vectors, and the renovation feature vectors, establish a matching correspondence relationship among the power data, the location data, and the renovation data, including:

[0016] Calculate the first attribute similarity between the power feature vector of each attribute corresponding to the power data and the location feature vector of each attribute corresponding to the location data respectively;

[0017] According to the power feature vectors and location feature vectors corresponding to the first attribute similarity greater than the first preset threshold, establish a first correspondence relationship between the power data and the location data;

[0018] Calculate the second attribute similarity between the location feature vector of each attribute corresponding to the location data and the renovation feature vector of each attribute corresponding to the renovation data respectively;

[0019] According to the location feature vectors and renovation feature vectors corresponding to the second attribute similarity greater than the second preset threshold, establish a second correspondence relationship between the location data and the renovation data;

[0020] Based on the first correspondence relationship and the second correspondence relationship, establish a matching correspondence relationship among the power data, the location data, and the renovation data.

[0021] In a possible implementation manner, according to the matching correspondence relationship, match the power data and the location data, and the renovation data and the location data to obtain the village-level power grid data of each village in the target area, including:

[0022] According to the attributes corresponding to the power data and the location data in the matching correspondence relationship, calculate multiple first data similarities between the power data and the location data;

[0023] Match the power data and the location data based on the first data similarity;

[0024] Calculate multiple second data similarities between the location data and the renovation data according to the attributes corresponding to the location data and the renovation data in the matching correspondence;

[0025] Match the location data and the renovation data based on the second data similarity;

[0026] Based on the matching results of the power data and the location data, and the matching results of the renovation data and the location data, obtain the village-level power grid data of each village in the target area.

[0027] In a possible implementation manner, calculating multiple first data similarities between the power data and the location data according to the attributes corresponding to the power data and the location data in the matching correspondence includes:

[0028] According to the expression: Calculate multiple first data similarities between the power data and the location data;

[0029] In the formula, α ij represents the first data similarity between the i-th data of a type of data in the power data and the j-th data of a type of data in the location data, n represents the set of attributes corresponding between the power data and the location data, k represents the k-th attribute corresponding between the power data and the location data, A ik represents the value of the k-th corresponding attribute in the i-th data of the power data, and B jk represents the value of the k-th corresponding attribute in the j-th data of the location data.

[0030] In a possible implementation manner, after matching the power data and the location data, and the renovation data and the location data according to the matching correspondence to obtain the village-level power grid data of each village in the target area, it further includes:

[0031] Input the renovation data and the target power data corresponding to the target time period into a preset renovation progress determination model to obtain the renovation progress situation output by the renovation progress determination model; wherein, the renovation progress determination model is trained according to the renovation data and the power data corresponding to different renovation progress situations;

[0032] Based on the renovation progress situation and the renovation progress data corresponding to the target time period in the renovation data, determine the actual renovation progress and the actual power data corresponding to the target time period.

[0033] In a possible implementation, based on the renovation progress situation and the renovation progress data corresponding to the target period in the renovation data, determining the actual renovation progress and actual power data corresponding to the target period includes:

[0034] Determining whether a first difference between the renovation progress situation and the renovation progress data corresponding to the target period in the renovation data is less than a third preset threshold;

[0035] If the first difference is less than the third preset threshold, determining the target power data corresponding to the target period as the actual power data, and determining the actual renovation progress corresponding to the target period according to the renovation progress data corresponding to the target period in the renovation progress.

[0036] In a possible implementation, after determining whether the first difference between the renovation progress situation and the renovation progress data corresponding to the target period in the renovation progress is less than the third preset threshold, it further includes:

[0037] If the first difference is greater than or equal to the third preset threshold, updating the target power data corresponding to the target period;

[0038] Based on the updated target power data and the renovation data, re-determining the new renovation progress situation corresponding to the target period;

[0039] Re-determining whether a second difference between the newly determined renovation progress situation and the renovation progress data corresponding to the target period in the renovation progress is less than the third preset threshold;

[0040] If the second difference is less than the third preset threshold, determining the updated target power data corresponding to the target period as the actual power data, and determining the actual renovation progress corresponding to the target period according to the renovation progress data corresponding to the target period in the renovation progress.

[0041] In a possible implementation, after re-determining whether the second difference between the newly determined renovation progress situation and the renovation progress data corresponding to the target period in the renovation progress is less than the third preset threshold, it further includes:

[0042] If the second difference is greater than or equal to the third preset threshold, determining the updated target power data corresponding to the target period as the actual power data, and determining the new renovation progress situation corresponding to the updated target power data as the actual renovation progress corresponding to the target period.

[0043] In a second aspect, an embodiment of the present invention provides a device for associating data of a village-level power grid renovation project, including:

[0044] An acquisition module, configured to acquire power data of the village-level power grid, location data of each village, and renovation data of the renovation projects of each village within a target area;

[0045] A determination module, configured to determine a power feature vector corresponding to the attribute of each type of data in the power data, a location feature vector corresponding to the attribute of each type of data in the location data, and a renovation feature vector corresponding to the attribute of each type of data in the renovation data;

[0046] A corresponding module, configured to establish a corresponding relationship among the power data, the location data, and the renovation data according to the power feature vector, the location feature vector, and the renovation feature vector;

[0047] A matching module, configured to match the power data and the location data, and the renovation data and the location data according to the corresponding relationship, so as to obtain the village-level power grid data of each village within the target area.

[0048] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows:

[0049] In the embodiments of the present invention, by determining the power feature vector corresponding to the attribute of each type of data in the power data, the location feature vector corresponding to the attribute of each type of data in the location data, and the renovation feature vector corresponding to the attribute of each type of data in the renovation data, the attributes in the power data, the attributes in the location data, and the attributes in the renovation data can be vectorized; then, through the power feature vector, the location feature vector, and the renovation feature vector, a matching corresponding relationship among the power data, the location data, and the renovation data is established, and the attributes in the power data, the attributes in the location data, and the attributes in the renovation data can be compared and matched by using the power feature vector, the location feature vector, and the renovation feature vector, so that a preliminary matching corresponding relationship can be established among the power data, the location data, and the renovation data; then, according to the corresponding relationship, the power data and the location data, and the renovation data and the location data are matched to obtain the village-level power grid data of each village within the target area, and an association relationship between the power data and the renovation data can be established based on the location data of each village, so that the power data required for the village-level power grid renovation project can be accurately obtained. Description of the Drawings

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0051] Figure 1It is an application scenario diagram of the data association method for the rural power grid transformation project provided by the embodiments of the present invention;

[0052] Figure 2 It is a flowchart of the implementation of a data association method for the rural power grid transformation project provided by the embodiments of the present invention;

[0053] Figure 3 It is a flowchart of the implementation of another data association method for the rural power grid transformation project provided by the embodiments of the present invention;

[0054] Figure 4 It is a schematic structural diagram of the data association device for the rural power grid transformation project provided by the embodiments of the present invention. Detailed implementation manners

[0055] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. However, those skilled in the art should clearly understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present invention.

[0056] The inventor of the present invention found that in the related art, the sorting of power data mainly focuses on the association and sorting of power data such as power lines and power equipment in the power grid, and does not associate power data with transformation data, making it difficult to accurately obtain the power data corresponding to the rural power grid transformation. Therefore, it is necessary to consider a method for associating the data of the rural power grid transformation project.

[0057] With the idea of accurately obtaining various data of the rural power grid corresponding to the transformation project, in the implementation manner of the present application, the power data of the rural power grid, the location data of each village, and the transformation data of the transformation project are obtained, and the power feature vectors corresponding to the attributes of each type of data in the power data, the location feature vectors corresponding to the attributes of each type of data in the location data, and the transformation feature vectors corresponding to the attributes of each type of data in the transformation data are matched, so as to establish a preliminary matching correspondence relationship among the power data, the location data, and the transformation data; then, according to the established matching correspondence relationship, the power data and the location data, as well as the transformation data and the location data, are matched, so that the power data is associated with the location data, and the transformation data is associated with the location data, that is, based on the location data of each village, an association relationship between the power data and the transformation data is established, thereby accurately obtaining the power data required for the rural power grid transformation project.

[0058] In order to make the purpose, technical solution, and advantages of the present invention clearer, the following will be described through specific embodiments with reference to the accompanying drawings.

[0059] Figure 1 This is an application scenario diagram of the data association method for the rural power grid transformation project provided by the embodiments of the present invention. When performing data association for the rural power grid transformation project, it is mainly to associate power data, location data, and transformation data. As Figure 1 shown, the power data may include line information and power equipment information, etc. The line information includes data values of various attributes, such as line basic information, line parameters, and line topology data, etc. Among them, the line basic information may include basic information such as the name, number, affiliated substation, start and end nodes of the line, etc. The line parameters may include electrical parameters of the line, such as line length, resistance, reactance, capacitance, etc. The line topology data may include connection relationships of the lines, nodes between the lines, etc.

[0060] The location data may include geographical locations and village information of each village, etc. The location information also includes data values of various attributes, such as administrative regions and line data of each village, etc. Among them, the administrative region may include the county, town, etc. to which each village belongs, and the line data may include information such as whether each village is adjacent to the main road, the affiliated power supply grid, and power supply unit, etc. The village information may include village type and the number of households in the village. Among them, the village type may include that each village belongs to a mountain village, a plain industrial village, or a plain agricultural village, and the number of households in the village may include the total number of households, the number of households with low electricity consumption, and the number of power households, etc.

[0061] The transformation data may include transformation planning data and power transformation data, etc. The transformation planning data also includes data values of various attributes, such as transformation plans and transformation times, etc. Among them, the transformation plan may include specific transformation contents, transformation progress, and transformation goals of each village, etc. The transformation time may include the time when the transformation plan is issued, the time planned for future transformation, the time when the overall transformation is completed, etc. The power transformation data may include distribution transformer information and user power information planned for each village, and may include power data under different transformation progress.

[0062] Figure 2 This is a flowchart of the implementation of a data association method for the rural power grid transformation project provided by the embodiments of the present invention, which is described in detail as follows:

[0063] Step S201, obtain the power data of the rural power grid in the target area, the location data of each village, and the transformation data of the transformation projects of each village.

[0064] In this embodiment, if there is a transformation plan for the rural power grid or the transformation is in progress, the transformation data may be the specific content of the corresponding transformation plan. If there is no transformation plan set for the rural power grid temporarily, the transformation data may be a preset transformation data determined according to the type and scale of the village. In addition, if there is no transformation plan set for the rural power grid temporarily, the transformation data may also be empty.

[0065] Step S202: Determine the power feature vectors corresponding to the attributes of each type of data in the power data, the location feature vectors corresponding to the attributes of each type of data in the location data, and the transformation feature vectors corresponding to the attributes of each type of data in the transformation data.

[0066] In this embodiment, encoding or feature vectorization processing can be performed for each attribute to obtain corresponding feature vectors, that is, the power feature vectors of the attributes corresponding to the power data, the location feature vectors of the attributes corresponding to the location data, and the transformation feature vectors of the attributes corresponding to the transformation data.

[0067] Optionally, to determine the power feature vectors corresponding to the attributes of each type of data in the power data, the location feature vectors corresponding to the attributes of each type of data in the location data, and the transformation feature vectors corresponding to the attributes of each type of data in the transformation data, first determine multiple attributes of each type of data in the power data, multiple attributes of each type of data in the location data, and multiple attributes of each type of data in the transformation data; then, perform feature vectorization processing on the multiple attributes corresponding to the power data respectively to obtain the power feature vectors of the multiple attributes corresponding to the power data; perform feature vectorization processing on the multiple attributes corresponding to the location data respectively to obtain the location feature vectors of the multiple attributes corresponding to the location data; and perform feature vectorization processing on the multiple attributes corresponding to the transformation data respectively to obtain the transformation feature vectors of the multiple attributes corresponding to the transformation data.

[0068] In this embodiment, the power data includes multiple types of data, and each type of data includes multiple attributes; the location data includes multiple types of data, and each type of data also includes multiple attributes; similarly, the transformation data includes multiple types of data, and each type of data also includes multiple attributes.

[0069] Therefore, feature vectorization processing can be performed for each attribute in the power data, each attribute in the location data, and each attribute in the transformation data respectively to obtain corresponding feature vectors, that is, the power feature vectors of each attribute corresponding to the power data, the location feature vectors of each attribute corresponding to the location data, and the transformation feature vectors of each attribute corresponding to the transformation data.

[0070] Here, to determine the feature vector of each attribute, it can also be to perform feature extraction from the data values corresponding to the attribute for each attribute, and based on multiple data values of the attribute, obtain the feature vector of the attribute.

[0071] Step S203: Establish a matching correspondence relationship among the power data, the location data, and the transformation data according to the power feature vectors, the location feature vectors, and the transformation feature vectors.

[0072] In this embodiment, matching is performed based on the power feature vector, location feature vector, and renovation feature vector. Preliminary matching can be carried out using the attributes of each type of data in the power data, the attributes of each type of data in the location data, and the attributes of each type of data in the renovation data to find similar features among the power data, location data, and renovation data for further subsequent matching.

[0073] Here, the matching correspondence relationship refers to the correspondence relationship among the attributes in the power data, the attributes in the location data, and the attributes in the renovation data.

[0074] Step S204: According to the matching correspondence relationship, match the power data and the location data, as well as the renovation data and the location data, to obtain the village-level power grid data of each village in the target area.

[0075] In this embodiment, both the power data and the renovation data are matched with the location data. The location data can be used as a bridge and a reference to extract the village-level power grid data corresponding to each village from the power data for the renovation and tracking of each village.

[0076] Here, when performing the matching according to the matching correspondence relationship, the matching can be carried out through the data values of the corresponding attributes between the power data and the location data, as well as the data values of the corresponding attributes between the location data and the renovation data in the matching correspondence relationship.

[0077] In the embodiment of the present invention, by determining the power feature vector corresponding to the attribute of each type of data in the power data, the location feature vector corresponding to the attribute of each type of data in the location data, and the renovation feature vector corresponding to the attribute of each type of data in the renovation data, the attributes in the power data, the attributes in the location data, and the attributes in the renovation data can be vectorized. Then, through the power feature vector, location feature vector, and renovation feature vector, a matching correspondence relationship is established among the power data, location data, and renovation data. The comparison and matching of the attributes in the power data, location data, and renovation data can be carried out using the power feature vector, location feature vector, and renovation feature vector, so as to establish a preliminary matching correspondence relationship among the power data, location data, and renovation data. Then, according to the matching correspondence relationship, the power data and the location data, as well as the renovation data and the location data are matched to obtain the village-level power grid data of each village in the target area. An association relationship can be established between the power data and the renovation data based on the location data of each village, so that the power data required for the village-level power grid renovation project can be accurately obtained.

[0078] In some embodiments, establishing a matching correspondence relationship among the power data, location data, and renovation data according to the power feature vector, location feature vector, and renovation feature vector may be:

[0079] Step 1: Calculate the first-attribute similarity between the power feature vectors of each attribute corresponding to the power data and the location feature vectors of each attribute corresponding to the location data respectively.

[0080] In this embodiment, by calculating the similarity between each power feature vector and each location feature vector respectively, the matching situation between every two attributes can be determined.

[0081] For example, if one type of power data includes four attributes A, B, C, and D, and one type of location data includes four attributes a, b, c, and d, then calculate the first-attribute similarity between A and a, between A and b, between A and c, between A and d, between B and a, between B and b, between B and c, between B and d, between C and a, between C and b, between C and c, between C and d, between D and a, between D and b, between D and c, and between D and d respectively, so as to obtain all the first-attribute similarities.

[0082] Step 2: Based on the power feature vectors and location feature vectors corresponding to the first-attribute similarities greater than the first preset threshold, establish the first correspondence between the power data and the location data.

[0083] Here, the first correspondence is the correspondence between the attributes in the power data and the attributes in the location data.

[0084] For example, for the line information in the power data, the attributes of the line information include line basic information, line parameters, line topology data, etc. For the geographical location in the location data, the attributes of the geographical location include administrative regions and line data, etc. Among them, if the first-attribute similarity between the line basic information and the line data is greater than the first preset threshold, then establish the first correspondence between the power data and the location data based on the line basic information and the line data.

[0085] If the first-attribute similarity between the line basic information and the administrative region is greater than the first preset threshold, and the first-attribute similarity between the line topology data and the line data is greater than the first preset threshold, then establish the first correspondence between the power data and the location data based on the correspondence between the line basic information and the administrative region, and the correspondence between the line topology data and the line data.

[0086] Step 3: Calculate the second-attribute similarity between the location feature vectors of each attribute corresponding to the location data and the transformation feature vectors of each attribute corresponding to the transformation data respectively.

[0087] Step 4: Based on the position feature vectors and transformation feature vectors corresponding to the second attribute similarity greater than the second preset threshold, establish a second correspondence between the position data and the transformation data.

[0088] Here, the specific implementation processes of Step 3 and Step 4 can refer to the above-mentioned Step 1 and Step 2, except that here each position feature vector and each transformation feature vector are processed.

[0089] Step 5: Based on the first correspondence and the second correspondence, establish a matching correspondence between the power data, the position data, and the transformation data.

[0090] In this embodiment, based on the relationship between the attributes in the power data and the attributes in the position data, and the relationship between the attributes in the position data and the attributes in the transformation data, a correspondence between the three is established.

[0091] Here, taking the execution of Step 1 and Step 2 first, and then Step 3 and Step 4 as an example for illustration. However, in actual implementation, it is not limited to this. It is possible to execute Step 3 and Step 4 first, and then Step 1 and Step 2, or it is also possible to execute Step 1 and Step 2, and Step 3 and Step 4 simultaneously.

[0092] In some embodiments, according to the matching correspondence, the power data and the position data, as well as the transformation data and the position data, are matched to obtain the village-level power grid data of each village in the target area. It can be to first calculate multiple first data similarities between the power data and the position data according to the corresponding attributes in the matching correspondence; then, based on the first data similarities, match the power data and the position data. And, first calculate multiple second data similarities between the position data and the transformation data according to the corresponding attributes in the matching correspondence; then, based on the second data similarities, match the position data and the transformation data. Finally, based on the matching results of the power data and the position data, and the matching results of the transformation data and the position data, the village-level power grid data of each village in the target area is obtained.

[0093] In this embodiment, according to the corresponding attributes in the matching correspondence, the calculation of the first data similarity between the power data and the position data, and the calculation of the second data similarity between the position data and the transformation data can accurately find the similarity between the two types of data based on the corresponding attributes, so as to perform the matching.

[0094] Among them, based on the first data similarity, matching the power data and the position data can be to determine, for each position data, the power data with the largest first data similarity corresponding to the position data, and match the position data with the power data.

[0095] Similarly, based on the second data similarity, the location data and the retrofit data are matched. For each piece of location data, the retrofit data with the largest second data similarity corresponding to the location data can be determined, and the location data is matched with the retrofit data.

[0096] Alternatively, it can also be matched for each piece of power data or each piece of retrofit data.

[0097] Here, there is no restriction on the order of calculating the first data similarity and the second data similarity. The first data similarity can be calculated first, the second data similarity can be calculated first, or the first data similarity and the second data similarity can be calculated simultaneously.

[0098] Optionally, according to the attributes corresponding to the power data and the location data in the matching correspondence, multiple first data similarities between the power data and the location data can be calculated. It can be according to the expression: Calculate multiple first data similarities between the power data and the location data; in the formula, α ij represents the first data similarity between the i-th data of a certain type of data in the power data and the j-th data of a certain type of data in the location data. n represents the set of corresponding attributes between the power data and the location data, k represents the k-th corresponding attribute between the power data and the location data, A ik represents the value of the k-th corresponding attribute in the i-th data of the power data, and B jk represents the value of the k-th corresponding attribute in the j-th data of the location data.

[0099] Correspondingly, according to the attributes corresponding to the location data and the retrofit data in the matching correspondence, multiple second data similarities between the location data and the retrofit data can be calculated according to the expression: Calculate multiple second data similarities between the location data and the retrofit data; in the formula, β pq represents the second data similarity between the p-th data of a certain type of data in the location data and the q-th data of a certain type of data in the retrofit data. m represents the set of corresponding attributes between the retrofit data and the location data, r represents the r-th corresponding attribute between the retrofit data and the location data, B pr represents the value of the r-th corresponding attribute in the p-th data of the location data, and C qr represents the value of the q-th corresponding attribute in the i-th data of the retrofit data.

[0100] Here, when calculating the similarity between data, for a piece of power data and a piece of location data, or for a piece of location data and a piece of renovation data, the values corresponding to all matching attributes between the two are calculated separately, so as to obtain the similarity between the two pieces of data, accurately calculate the similarity between the data, accurately match the data, reduce the situation of misalignment matching, and reduce the situation where a piece of power data matches multiple location data and there are conflicts among the multiple location data, or a piece of location data matches multiple power data and there are conflicts among the multiple power data, etc., which can improve the accuracy of data matching.

[0101] In some embodiments, Figure 3 The following is a flowchart for implementing another method for associating data of a rural power grid renovation project provided by an embodiment of the present invention:

[0102] Step S301, obtain the power data of the rural power grid in the target area, the location data of each village, and the renovation data of the renovation projects of each village.

[0103] Step S302, determine the power feature vectors corresponding to the attributes of each type of data in the power data, the location feature vectors corresponding to the attributes of each type of data in the location data, and the renovation feature vectors corresponding to the attributes of each type of data in the renovation data.

[0104] Step S303, establish a matching correspondence relationship among the power data, the location data, and the renovation data according to the power feature vectors, the location feature vectors, and the renovation feature vectors.

[0105] Step S304, match the power data and the location data, and the renovation data and the location data according to the matching correspondence relationship to obtain the rural power grid data of each village in the target area.

[0106] Here, the implementation manners of steps S301 to S304 can be referred to Figure 2 the relevant descriptions in the embodiments, which will not be elaborated here.

[0107] Step S305, input the renovation data and the target power data corresponding to the target time period into a preset renovation progress determination model to obtain the renovation progress situation output by the renovation progress determination model; wherein, the renovation progress determination model is trained according to the renovation data and the power data corresponding to different renovation progress situations.

[0108] In this embodiment, through the renovation data and the target power data corresponding to the target time period, the renovation progress situation of the target time period can be determined, so as to timely master the renovation progress of the rural power grid and reduce the complexity of obtaining data related to the power grid renovation project.

[0109] Here, the renovation progress determination model can be a neural network model. By comparing and classifying the target power data of the target time period with the renovation power data corresponding to different renovation progress in the renovation data, the renovation progress situation of the target time period can be determined.

[0110] Step S306: Based on the renovation progress situation and the renovation progress data corresponding to the target time period in the renovation data, determine the actual renovation progress and actual power data corresponding to the target time period.

[0111] In this embodiment, by comparing the renovation progress situation with the renovation progress data corresponding to the target time period, it can be determined whether the renovation within the target time period has reached the expected renovation progress, so as to accurately obtain the actual renovation progress and actual power data of the renovation project, and timely and accurately grasp the power grid renovation situation.

[0112] Optionally, in this embodiment, based on the renovation progress situation and the renovation progress data corresponding to the target time period in the renovation data, determining the actual renovation progress and actual power data corresponding to the target time period may include determining whether the first difference between the renovation progress situation and the renovation progress data corresponding to the target time period in the renovation data is less than a third preset threshold; if the first difference is less than the third preset threshold, then determine the target power data corresponding to the target time period as the actual power data, and determine the actual renovation progress corresponding to the target time period according to the renovation progress data corresponding to the target time period in the renovation progress.

[0113] In this embodiment, the renovation progress situation can be compared with the renovation progress data corresponding to the target time period in the renovation data, and the first difference between the two can be calculated. If the first difference is less than the third preset threshold, it indicates that the renovation progress situation is close to the renovation progress data corresponding to the target time period in the renovation data, and the expected renovation progress has been achieved. Correspondingly, the target power data of the target time period is also the data updated according to the renovation progress. Therefore, the target power data can be directly determined as the actual power data and recorded.

[0114] In some embodiments, after determining whether the first difference between the renovation progress situation and the renovation progress data corresponding to the target time period in the renovation progress is less than the third preset threshold, it may further include: if the first difference is greater than or equal to the third preset threshold, then update the target power data corresponding to the target time period; based on the updated target power data and the renovation data, re-determine the new renovation progress situation corresponding to the target time period; re-determine whether the second difference between the new renovation progress situation and the renovation progress data corresponding to the target time period in the renovation progress is less than the third preset threshold; if the second difference is less than the third preset threshold, then determine the updated target power data corresponding to the target time period as the actual power data, and determine the actual renovation progress corresponding to the target time period according to the renovation progress data corresponding to the target time period in the renovation progress.

[0115] In this embodiment, if the first difference is greater than or equal to the third preset threshold, it indicates that there is a significant difference between the renovation progress and the renovation progress data corresponding to the target time period in the renovation data. It may be that the expected renovation progress has not been achieved or exceeded, or it may be that the target power data for the target time period has not been updated.

[0116] Therefore, the target power data for the target time period can be retrieved again from the corresponding data source to update the target power data, and then recalculated based on the updated target power data to reduce the probability of not obtaining power data in a timely manner, so as to accurately grasp the renovation progress of the renovation project.

[0117] Here, if the second difference obtained from the recalculation is less than the third preset threshold, it indicates that the renovation progress of the target time period actually meets the expected renovation progress, but the power data has not been updated in a timely manner. Therefore, the updated target power data can be used as the actual power data.

[0118] Optionally, after re-determining whether the second difference between the newly determined renovation progress and the renovation progress data corresponding to the target time period in the renovation progress is less than the third preset threshold in this embodiment, it may further include: if the second difference is greater than or equal to the third preset threshold, the updated target power data corresponding to the target time period is determined as the actual power data, and the new renovation progress corresponding to the updated target power data is determined as the actual renovation progress corresponding to the target time period.

[0119] In this embodiment, if the second difference is still greater than or equal to the third preset threshold, it indicates that there is indeed a significant difference between the renovation progress and the renovation progress data corresponding to the target time period in the renovation data. At this time, the updated target power data can be determined as the actual power data, and the new renovation progress corresponding to the updated target power data can be determined as the actual renovation progress corresponding to the target time period for the reference of relevant staff to timely adjust the plan of the renovation project.

[0120] In the embodiments of the present invention, by determining the power feature vectors corresponding to the attributes of each type of data in the power data, the location feature vectors corresponding to the attributes of each type of data in the location data, and the renovation feature vectors corresponding to the attributes of each type of data in the renovation data, the attributes in the power data, the attributes in the location data, and the attributes in the renovation data can be vectorized; then, through the power feature vectors, location feature vectors, and renovation feature vectors, a matching correspondence relationship between the power data, location data, and renovation data can be established, and the power feature vectors, location feature vectors, and renovation feature vectors can be used to compare and match the attributes in the power data, the attributes in the location data, and the attributes in the renovation data, so as to establish a preliminary matching correspondence relationship between the power data, location data, and renovation data; then, according to the matching correspondence relationship, the power data and location data, as well as the renovation data and location data, are matched to obtain the village-level power grid data of each village in the target area, and an association relationship between the power data and the renovation data can be established based on the location data of each village, so as to accurately obtain the power data required for the village-level power grid renovation project. Among them, according to the matching correspondence relationship, multiple first data similarities between the power data and the location data, and multiple second data similarities between the renovation data and the location data are calculated, and all the data can be matched to find the two most matching data for establishing the association relationship. Then, through the location data as a bridge, the power data and the renovation data are associated, and the corresponding village-level power grid data can be accurately obtained for the renovation project; moreover, by calculating the similarity between the two data through all the matching attributes, the attribute matching situation between the two data can be comprehensively considered, and the matching data can be accurately found for associating the data. In addition, during the project renovation process, the target power data in the target time period can be obtained, and the target power data is compared with the renovation progress data in the target time period in the renovation data to detect whether the renovation progress of the power grid renovation project reaches the expected renovation progress, and the situation of the village-level power grid renovation can be timely grasped to adjust the plan of the renovation project

[0121] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention

[0122] The following are the device embodiments of the present invention. For the details not described in detail, reference can be made to the corresponding method embodiments above

[0123] Figure 4 The structural schematic diagram of the village-level power grid renovation project data association device provided by the embodiments of the present invention is shown. For the convenience of description, only the parts related to the embodiments of the present invention are shown and are described in detail as follows

[0124] As Figure 4As shown, the data association device 40 for the village-level power grid transformation project includes:

[0125] An acquisition module 41, configured to acquire power data of the village-level power grid in the target area, location data of each village, and transformation data of the transformation projects of each village;

[0126] A determination module 42, configured to determine a power feature vector corresponding to the attribute of each type of data in the power data, a location feature vector corresponding to the attribute of each type of data in the location data, and a transformation feature vector corresponding to the attribute of each type of data in the transformation data;

[0127] A corresponding module 43, configured to establish a corresponding relationship among the power data, the location data, and the transformation data according to the power feature vector, the location feature vector, and the transformation feature vector;

[0128] A matching module 44, configured to match the power data and the location data, and the transformation data and the location data according to the corresponding relationship, so as to obtain the village-level power grid data of each village in the target area.

[0129] In a possible implementation manner, the determination module 42 is specifically configured to:

[0130] Determine multiple attributes of each type of data in the power data, multiple attributes of each type of data in the location data, and multiple attributes of each type of data in the transformation data;

[0131] Perform feature vectorization processing on the multiple attributes corresponding to the power data respectively to obtain power feature vectors of the multiple attributes corresponding to the power data;

[0132] Perform feature vectorization processing on the multiple attributes corresponding to the location data respectively to obtain location feature vectors of the multiple attributes corresponding to the location data;

[0133] Perform feature vectorization processing on the multiple attributes corresponding to the transformation data respectively to obtain transformation feature vectors of the multiple attributes corresponding to the transformation data.

[0134] In a possible implementation manner, the corresponding module 43 is specifically configured to:

[0135] Calculate the first attribute similarity between the power feature vector of each attribute corresponding to the power data and the location feature vector of each attribute corresponding to the location data respectively;

[0136] Establish a first corresponding relationship between the power data and the location data according to the power feature vector and the location feature vector corresponding to the first attribute similarity greater than the first preset threshold;

[0137] Calculate the second attribute similarity between the location feature vector of each attribute corresponding to the location data and the transformation feature vector of each attribute corresponding to the transformation data respectively;

[0138] Establish a second correspondence between the location data and the retrofit data according to the location feature vector and the retrofit feature vector corresponding to the second attribute similarity greater than the second preset threshold;

[0139] Based on the first correspondence and the second correspondence, establish a matching correspondence between the power data, the location data, and the retrofit data.

[0140] In a possible implementation, the matching module 44 is specifically configured to:

[0141] Calculate multiple first data similarities between the power data and the location data according to the attributes corresponding to the power data and the location data in the matching correspondence;

[0142] Match the power data and the location data based on the first data similarity;

[0143] Calculate multiple second data similarities between the location data and the retrofit data according to the attributes corresponding to the location data and the retrofit data in the matching correspondence;

[0144] Match the location data and the retrofit data based on the second data similarity;

[0145] Based on the matching results of the power data and the location data, and the matching results of the retrofit data and the location data, obtain the village-level power grid data of each village in the target area.

[0146] In a possible implementation, the matching module 44 is specifically configured to:

[0147] According to the expression: Calculate multiple first data similarities between the power data and the location data;

[0148] In the formula, α ij represents the first data similarity between the i-th data of a type of data in the power data and the j-th data of a type of data in the location data, n represents the set of corresponding attributes between the power data and the location data, k represents the k-th attribute corresponding between the power data and the location data, A ik represents the value of the corresponding attribute in the i-th data of the power data, and B jk represents the value of the corresponding attribute in the j-th data of the location data.

[0149] In a possible implementation, the matching module 44 is further configured to:

[0150] Input the transformed data and the target power data corresponding to the target time period into a preset transformation progress determination model to obtain the transformation progress determined by the model; wherein, the transformation progress determination model is trained based on the transformed data and the power data corresponding to different transformation progress situations.

[0151] Based on the transformation progress situation and the transformation progress data corresponding to the target time period in the transformed data, determine the actual transformation progress and the actual power data corresponding to the target time period.

[0152] In a possible implementation, the matching module 44 is specifically configured to:

[0153] Determine whether the first difference between the transformation progress situation and the transformation progress data corresponding to the target time period in the transformed data is less than a third preset threshold;

[0154] If the first difference is less than the third preset threshold, determine the target power data corresponding to the target time period as the actual power data, and determine the actual transformation progress corresponding to the target time period according to the transformation progress data corresponding to the target time period in the transformation progress.

[0155] In a possible implementation, the matching module 44 is further configured to:

[0156] If the first difference is greater than or equal to the third preset threshold, update the target power data corresponding to the target time period;

[0157] Based on the updated target power data and the transformed data, re-determine the new transformation progress situation corresponding to the target time period;

[0158] Re-determine whether the second difference between the new transformation progress situation and the transformation progress data corresponding to the target time period in the transformation progress is less than the third preset threshold;

[0159] If the second difference is less than the third preset threshold, determine the updated target power data corresponding to the target time period as the actual power data, and determine the actual transformation progress corresponding to the target time period according to the transformation progress data corresponding to the target time period in the transformation progress.

[0160] In a possible implementation, the matching module 44 is further configured to:

[0161] If the second difference is greater than or equal to the third preset threshold, determine the updated target power data corresponding to the target time period as the actual power data, and determine the new transformation progress situation corresponding to the updated target power data as the actual transformation progress corresponding to the target time period.

[0162] In the above embodiments, the descriptions of the various embodiments have their own focuses. For parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0163] Those of ordinary skill in the art can realize that the templates, units, and algorithm steps of the various examples described in combination with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0164] If a module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0165] 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 foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for associating data of a village-level power grid transformation project, characterized in that: include: Obtain power data of village-level power grids in the target area, location data of each village, and renovation data of renovation projects in each village; Determine a power feature vector corresponding to an attribute of each data in the power data, a position feature vector corresponding to an attribute of each data in the position data, and a transformation feature vector corresponding to an attribute of each data in the transformation data; According to the power feature vector, the position feature vector and the transformation feature vector, a matching correspondence relationship is established between the power data, the position data and the transformation data; According to the matching correspondence, the power data and the location data, as well as the transformation data and the location data are matched to obtain the village-level power grid data of each village in the target area.

2. The method for associating data of a village-level power grid transformation project according to claim 1, characterized in that: Determining a power feature vector corresponding to an attribute of each data in the power data, a position feature vector corresponding to an attribute of each data in the position data, and a transformation feature vector corresponding to an attribute of each data in the transformation data, comprises: Determining a plurality of attributes of each type of data in the power data, a plurality of attributes of each type of data in the location data, and a plurality of attributes of each type of data in the transformation data; Performing feature vectorization processing on multiple attributes corresponding to the power data respectively to obtain power feature vectors of the multiple attributes corresponding to the power data; Performing feature vectorization processing on multiple attributes corresponding to the position data respectively to obtain position feature vectors of the multiple attributes corresponding to the position data; Feature vectorization processing is performed on multiple attributes corresponding to the transformed data respectively to obtain transformed feature vectors of the multiple attributes corresponding to the transformed data.

3. The method for associating data of a village-level power grid transformation project according to claim 1, characterized in that: According to the power feature vector, the position feature vector and the transformation feature vector, a matching correspondence relationship is established between the power data, the position data and the transformation data, including: respectively calculating a first attribute similarity between the power feature vector of each attribute corresponding to the power data and the position feature vector of each attribute corresponding to the position data; Establishing a first corresponding relationship between the power data and the position data according to a power feature vector and a position feature vector corresponding to a first attribute similarity greater than a first preset threshold; respectively calculating a second attribute similarity between the position feature vector of each attribute corresponding to the position data and the transformation feature vector of each attribute corresponding to the transformation data; Establishing a second corresponding relationship between the position data and the transformed data according to the position feature vector and the transformed feature vector corresponding to the second attribute similarity greater than a second preset threshold; Based on the first corresponding relationship and the second corresponding relationship, a matching corresponding relationship among the power data, the position data and the transformation data is established.

4. The method for associating data of a village-level power grid transformation project according to claim 3 is characterized in that: According to the matching correspondence, the power data and the location data, as well as the transformation data and the location data are matched to obtain village-level power grid data of each village in the target area, including: Calculating a plurality of first data similarities between the power data and the position data according to the attributes corresponding to the power data and the position data in the matching correspondence; matching the power data and the location data based on the first data similarity; Calculating a plurality of second data similarities between the position data and the transformed data according to the attributes corresponding to the position data and the transformed data in the matching correspondence; matching the location data with the transformation data based on the second data similarity; Based on the matching results of the power data and the location data, and the matching results of the transformation data and the location data, the village-level power grid data of each village in the target area is obtained.

5. The method for associating data of a village-level power grid transformation project according to claim 4 is characterized in that: Calculating a plurality of first data similarities between the power data and the position data according to the attributes corresponding to the power data and the position data in the matching correspondence relationship includes: According to the expression: calculating a plurality of first data similarities between the power data and the location data; In the formula, α ij represents the first data similarity between the i-th data of one type of data in the power data and the j-th data of one type of data in the location data, n represents the set of corresponding attributes between the power data and the location data, k represents the k-th attribute corresponding between the power data and the location data, A ik represents the value of the kth corresponding attribute in the i-th data in the power data, B jk Represents the value of the kth corresponding attribute in the jth data in the position data.

6. The method for associating data of a village power grid transformation project according to any one of claims 1 to 5, characterized in that: After matching the power data and the location data, and the transformation data and the location data according to the matching correspondence to obtain the village-level power grid data of each village in the target area, the method further includes: Input the transformation data and the target power data corresponding to the target period into a preset transformation progress determination model to obtain the transformation progress output by the transformation progress determination model; wherein the transformation progress determination model is trained based on the transformation data and the power data corresponding to different transformation progress conditions; Based on the transformation progress and the transformation progress data corresponding to the target time period in the transformation data, the actual transformation progress and actual power data corresponding to the target time period are determined.

7. The method for associating data of a village-level power grid transformation project according to claim 6 is characterized in that: Based on the transformation progress and the transformation progress data corresponding to the target period in the transformation data, determining the actual transformation progress and actual power data corresponding to the target period, including: Determine whether a first difference between the transformation progress status and the transformation progress data corresponding to the target period in the transformation data is less than a third preset threshold; If the first difference is less than a third preset threshold, the target power data corresponding to the target period is determined as the actual power data, and the actual transformation progress corresponding to the target period is determined according to the transformation progress data corresponding to the target period in the transformation progress.

8. The method for associating data of a village-level power grid transformation project according to claim 7, characterized in that: After determining whether a first difference between the transformation progress status and the transformation progress data corresponding to the target period in the transformation progress is less than a third preset threshold, the method further includes: If the first difference is greater than or equal to a third preset threshold, updating the target power data corresponding to the target time period; Based on the updated target power data and the transformation data, re-determine a new transformation progress corresponding to the target period; Re-determining whether a second difference between the new transformation progress and the transformation progress data corresponding to the target period in the transformation progress is less than the third preset threshold; If the second difference is less than the third preset threshold, the updated target power data corresponding to the target period is determined as the actual power data, and the actual transformation progress corresponding to the target period is determined according to the transformation progress data corresponding to the target period in the transformation progress.

9. The method for associating data of a village-level power grid transformation project according to claim 8, characterized in that: After re-determining whether the second difference between the new transformation progress and the transformation progress data corresponding to the target period in the transformation progress is less than the third preset threshold, the method further includes: If the second difference is greater than or equal to the third preset threshold, the updated target power data corresponding to the target time period is determined as the actual power data, and the new transformation progress corresponding to the updated target power data is determined as the actual transformation progress corresponding to the target time period.

10. A data association device for a village-level power grid transformation project, characterized in that: include: An acquisition module is used to acquire power data of village-level power grids in the target area, location data of each village, and transformation data of transformation projects of each village; A determination module, used to determine a power feature vector corresponding to an attribute of each data in the power data, a position feature vector corresponding to an attribute of each data in the position data, and a transformation feature vector corresponding to an attribute of each data in the transformation data; a corresponding module, configured to establish a corresponding relationship between the power data, the position data and the transformation data according to the power feature vector, the position feature vector and the transformation feature vector; A matching module is used to match the power data and the location data, as well as the transformation data and the location data according to the corresponding relationship, to obtain the village-level power grid data of each village in the target area.

Images