Device data modeling method, device, and medium based on data deduction

Abstract

The application discloses a device data modeling method and device based on data deduction, and a medium. The method comprises the following steps: acquiring carrier sensing data corresponding to historical electric energy flow, historical information flow and historical service flow of a target low-voltage area; performing data knowledge extraction on each kind of carrier sensing data to respectively establish a sparse data matrix; performing element completion on the sparse data matrix to obtain a target sparse data matrix, thereby solving the problem of missing carrier sensing data, and the data knowledge extraction is beneficial to ensuring the relevance and accuracy of data; based on the target sparse data matrix, an electric energy interaction model, an information interaction model and a service interaction model of multi-service electrical equipment are respectively established; and model fusion is performed on the electric energy interaction model, the information interaction model and the service interaction model to obtain an integrated data model of multi-service electrical equipment of the target low-voltage area, so as to realize integrated processing of electrical equipment data among electric energy flow, information flow and service flow.

Description

Technical Field

[0001] This application relates to the field of energy security technology, and in particular to a method, apparatus, equipment and medium for equipment data modeling based on data extrapolation. Background Technology

[0002] Carrier sensing based on power flow, information flow, and service flow offers advantages such as reduced transmission noise, frequency division multiplexing, and long propagation distance. However, the large-scale integration of multiple energy sources, including high-proportion renewable energy sources, flexible and controllable loads, and distributed energy storage, in low-voltage distribution areas leads to severe channel interference. Power line carrier sensing data is unstable and may be affected by interference or noise, resulting in data loss and poor data quality, rendering it unusable for modeling. Furthermore, carrier sensing primarily collects data near commonly used frequencies, limiting its acquisition capabilities. Frequent switching of some devices, sudden pulse interference and noise, and the impact of unexpected emergencies can also affect carrier sensing data acquisition. Therefore, it is necessary to supplement the sparse data of power flow, information flow, and service flow to support device data modeling. Summary of the Invention

[0003] This application provides a method, apparatus, device, and medium for device data modeling based on data extrapolation, in order to solve the technical problem of data scarcity caused by interference with current device data.

[0004] To address the aforementioned technical problems, in a first aspect, this application provides a device data modeling method based on data extrapolation, comprising:

[0005] Acquire carrier sensing data corresponding to the historical power flow, historical information flow, and historical service flow of the target low-voltage distribution area;

[0006] Data knowledge is extracted for each type of carrier sensing data to establish a sparse data matrix respectively;

[0007] The sparse data matrix is ​​padded with elements to obtain the target sparse data matrix;

[0008] Based on the target sparse data matrix, power interaction model, information interaction model and business interaction model of multi-service electrical equipment are established respectively.

[0009] The power interaction model, information interaction model, and business interaction model are fused to obtain an integrated data model of multi-business electrical equipment in the target low-voltage distribution area.

[0010] In some implementations, the step of extracting data knowledge for each type of carrier sensing data to establish a sparse data matrix includes:

[0011] For each type of carrier sensing data, data structure identification, data feature identification, and data relationship extraction are performed on the carrier sensing data to obtain the data structure, data features, and data relationships of the carrier sensing data;

[0012] Based on the data structure, data features, and data relationships, a sparse data matrix is ​​established for each type of carrier sensing data. The sparse data matrix includes a power flow carrier sensing data matrix, an information flow carrier sensing data matrix, a service flow carrier sensing data matrix, an extracted knowledge matrix, and a data relationship matrix.

[0013] In some implementations, the step of padding the sparse data matrix to obtain the target sparse data matrix includes:

[0014] Using a preset data completion strategy, based on the preset weight coefficients of each influencing factor, element completion is performed on each of the sparse data matrices to obtain the corresponding target sparse data matrix. The expression for the preset data completion strategy is as follows:

[0015]

[0016] Among them, a * (a 1 a 2 a 3 ) represents the power flow carrier sensing data matrix, b * (b 1 b 2 b 3 ) represents the information flow carrier sensing data matrix, c * (c 1 c 2 c 3 ) represents the service flow carrier sensing data matrix, d * (d 1 d 2 d 3 ) represents the extracted knowledge matrix, e * (e 1 e 2 e 3 ) represents a data relationship matrix, a 1 a 2 and a 3 δ1, δ2, and δ3 represent the weighting coefficients corresponding to current, voltage, and power quality, respectively, G represents the total number of elements in the power flow carrier sensing data matrix, and b represents the weighting coefficients corresponding to current, voltage, and power quality, respectively. 1 b 2 and b 3ε1, ε2, and ε3 represent the information arrival time, information effect, and information quality, respectively; H represents the total number of elements in the information flow carrier sensing data matrix; and c represents the information arrival time, information effect, and information quality, respectively. 1 c 2 and c 3 φ1, φ2, and φ3 represent the service completion time, service difficulty, and service quantity, respectively; φ3 represents the weighting coefficients corresponding to the service completion time, service difficulty, and service quantity, respectively; J represents the total number of elements in the service flow carrier sensing data matrix; and d represents the total number of elements in the service flow carrier sensing data matrix. 1 d 2 and d 3 These represent the amount of knowledge extracted, the speed of knowledge extraction, and the method of knowledge extraction, respectively. and These represent the weight coefficients corresponding to the amount of knowledge extracted, the speed of knowledge extraction, and the method of knowledge extraction, respectively. K represents the total number of elements in the knowledge extraction matrix, and e 1 e 2 and e 3 γ1, γ2, and γ3 represent the learning correlation degree, learning correlation effect, and learning correlation method, respectively. γ1, γ2, and γ3 represent the weight coefficients corresponding to the learning correlation degree, learning correlation effect, and learning correlation method, respectively. L represents the total number of elements in the data relationship matrix.

[0017] In some implementations, the step of establishing power interaction models, information interaction models, and service interaction models for multi-service electrical equipment based on the target sparse data matrix includes:

[0018] Based on the target sparse data matrix, an energy flow adjacency matrix is ​​constructed, and a first adjacency graph of the energy flow direction is constructed based on the energy flow adjacency matrix, and the energy interaction model is established based on the first adjacency graph.

[0019] Based on the target sparse data matrix, an information flow adjacency matrix is ​​constructed, and a second adjacency graph of the information flow direction is constructed based on the information flow adjacency matrix, and the information interaction model is established based on the second adjacency graph;

[0020] Based on the business nodes in the business flow, an association topology graph of the business nodes is established according to the target sparse data matrix, and the business interaction model is established based on the association topology graph.

[0021] In some implementations, the process of fusing the power interaction model, information interaction model, and service interaction model to obtain an integrated data model of multi-service electrical equipment for the target low-voltage distribution area includes:

[0022] Based on the service nodes, power flow direction, and information transmission direction of the target low-voltage distribution area, establish the correlation between power flow, information flow, and service flow;

[0023] Based on the aforementioned relationships, the power interaction model, the information interaction model, and the business interaction model are fused together to obtain the integrated data model for multi-business electrical equipment.

[0024] Secondly, this application also provides a device data modeling apparatus based on data extrapolation, comprising:

[0025] The acquisition module is used to acquire carrier sensing data corresponding to the historical power flow, historical information flow and historical service flow of the target low-voltage distribution area.

[0026] An extraction module is used to extract data knowledge from each type of carrier sensing data to establish a sparse data matrix respectively.

[0027] The completion module is used to complete the elements of the sparse data matrix to obtain the target sparse data matrix.

[0028] A module is established to build, based on the target sparse data matrix, a power interaction model, an information interaction model, and a business interaction model for multi-service electrical equipment, respectively.

[0029] The fusion module is used to fuse the power interaction model, information interaction model and business interaction model to obtain an integrated data model of multi-business electrical equipment in the target low-voltage distribution area.

[0030] In some implementations, the completion module is specifically used for:

[0031] Using a preset data completion strategy, based on the preset weight coefficients of each influencing factor, element completion is performed on each of the sparse data matrices to obtain the corresponding target sparse data matrix. The expression for the preset data completion strategy is as follows:

[0032]

[0033] Among them, a * (a 1 a 2 a 3 ) represents the power flow carrier sensing data matrix, b * (b 1 b 2 b 3 ) represents the information flow carrier sensing data matrix, c * (c 1 c 2 c 3 ) represents the service flow carrier sensing data matrix, d* (d 1 d 2 d 3 ) represents the extracted knowledge matrix, e * (e 1 e 2 e 3 ) represents a data relationship matrix, a 1 a 2 and a 3 δ1, δ2, and δ3 represent the weighting coefficients corresponding to current, voltage, and power quality, respectively, G represents the total number of elements in the power flow carrier sensing data matrix, and b represents the weighting coefficients corresponding to current, voltage, and power quality, respectively. 1 b 2 and b 3 ε1, ε2, and ε3 represent the information arrival time, information effect, and information quality, respectively; H represents the total number of elements in the information flow carrier sensing data matrix; and c represents the information arrival time, information effect, and information quality, respectively. 1 c 2 and c 3 φ1, φ2, and φ3 represent the service completion time, service difficulty, and service quantity, respectively; φ3 represents the weighting coefficients corresponding to the service completion time, service difficulty, and service quantity, respectively; J represents the total number of elements in the service flow carrier sensing data matrix; and d represents the total number of elements in the service flow carrier sensing data matrix. 1 d 2 and d 3 These represent the amount of knowledge extracted, the speed of knowledge extraction, and the method of knowledge extraction, respectively. and These represent the weight coefficients corresponding to the amount of knowledge extracted, the speed of knowledge extraction, and the method of knowledge extraction, respectively. K represents the total number of elements in the knowledge extraction matrix, and e 1 e 2 and e 3 γ1, γ2, and γ3 represent the learning correlation degree, learning correlation effect, and learning correlation method, respectively. γ1, γ2, and γ3 represent the weight coefficients corresponding to the learning correlation degree, learning correlation effect, and learning correlation method, respectively. L represents the total number of elements in the data relationship matrix.

[0034] In some implementations, the establishment module is specifically used for:

[0035] Based on the target sparse data matrix, an energy flow adjacency matrix is ​​constructed, and a first adjacency graph of the energy flow direction is constructed based on the energy flow adjacency matrix, and the energy interaction model is established based on the first adjacency graph.

[0036] Based on the target sparse data matrix, an information flow adjacency matrix is ​​constructed, and a second adjacency graph of the information flow direction is constructed based on the information flow adjacency matrix, and the information interaction model is established based on the second adjacency graph;

[0037] Based on the business nodes in the business flow, an association topology graph of the business nodes is established according to the target sparse data matrix, and the business interaction model is established based on the association topology graph.

[0038] Thirdly, this application also provides a computer device, including a processor and a memory, wherein the memory is used to store a computer program, and the computer program, when executed by the processor, implements the device data modeling method based on data extrapolation as described in the first aspect.

[0039] Fourthly, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the device data modeling method based on data extrapolation as described in the first aspect.

[0040] Compared with the prior art, this application has at least the following beneficial effects:

[0041] By acquiring carrier sensor data corresponding to historical power flow, historical information flow, and historical service flow of the target low-voltage distribution area, data knowledge is extracted for each type of carrier sensor data to establish a sparse data matrix. The sparse data matrix is ​​then filled with elements to obtain the target sparse data matrix, thereby solving the problem of missing carrier sensor data. Simultaneously, data knowledge extraction helps ensure the correlation and accuracy of the data. Based on the target sparse data matrix, power interaction models, information interaction models, and service interaction models for multi-service electrical equipment are established. These models are then fused to obtain an integrated data model for multi-service electrical equipment in the target low-voltage distribution area, enabling integrated processing of electrical equipment data among power flow, information flow, and service flow. Attached Figure Description

[0042] Figure 1 This is a schematic flowchart illustrating a device data modeling method based on data extrapolation, as shown in an embodiment of this application.

[0043] Figure 2 This is a schematic diagram of the structure of a device data modeling apparatus based on data extrapolation, as shown in an embodiment of this application.

[0044] Figure 3 This is a schematic diagram of the structure of a computer device shown in an embodiment of this application. Detailed Implementation

[0045] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0046] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a device data modeling method based on data extrapolation, provided as an embodiment of this application. The device data modeling method based on data extrapolation in this application can be applied to computer devices, including but not limited to smartphones, laptops, tablets, desktop computers, physical servers, and cloud servers. Figure 1 As shown, the device data modeling method based on data extrapolation in this embodiment includes steps S101 to S105, which are detailed below:

[0047] Step S101: Obtain carrier sensing data corresponding to the historical power flow, historical information flow, and historical service flow of the target low-voltage distribution area.

[0048] In this step, data is collected from the following areas: low-voltage distribution area electrical equipment marketing business, low-voltage distribution area electrical equipment power distribution business, and low-voltage distribution area electrical equipment control business. This includes energy flow carrier sensing data generated by energy flow, information flow carrier sensing data generated by information transmission, and business flow carrier sensing data generated by business operation processes. Specifically, low-voltage distribution area electrical equipment marketing business includes equipment change services, marketing electricity fee management, marketing electricity management, and equipment marketing business expansion; low-voltage distribution area electrical equipment power distribution business includes providing equipment power, installing equipment power metering devices, and equipment voltage adjustment; and low-voltage distribution area electrical equipment control business includes equipment power outage management, equipment operation management, equipment periodic work management, and handling of equipment anomalies and accidents.

[0049] Step S102: Extract data knowledge for each type of carrier sensing data to establish a sparse data matrix respectively.

[0050] In this step, data knowledge extraction includes data structure identification, data feature identification, and data relationship extraction.

[0051] In some embodiments, step S102 includes:

[0052] For each type of carrier sensing data, data structure identification, data feature identification, and data relationship extraction are performed on the carrier sensing data to obtain the data structure, data features, and data relationships of the carrier sensing data;

[0053] Based on the data structure, data features, and data relationships, a sparse data matrix is ​​established for each type of carrier sensing data. The sparse data matrix includes a power flow carrier sensing data matrix, an information flow carrier sensing data matrix, a service flow carrier sensing data matrix, an extracted knowledge matrix, and a data relationship matrix.

[0054] In this embodiment, based on historical power flow, information flow, and service flow carrier sensing data, data knowledge extraction is achieved through data structure identification, data feature identification, and data relationship extraction. The data structure can be obtained by analyzing the data storage method; data feature identification calculates features such as data range and frequency by analyzing data values; data relationship extraction utilizes structured data such as encyclopedia databases to continuously supplement the relationships between power flow, information flow, and service flow. Simultaneously, a learning algorithm is introduced, initializing the learning algorithm model with encyclopedia database data, and then outputting the relationships between each flow by inputting data from each flow. Through learning and fusion, the efficiency of relationship extraction is improved. A knowledge graph F(A, B, C, D, E) is constructed based on the extracted data structure, data features, and data relationships, where A represents the historical power flow carrier sensing data matrix; B represents the historical information flow carrier sensing data matrix; C represents the historical service flow carrier sensing data matrix; D represents the extracted knowledge matrix; and E represents the data relationship matrix.

[0055] Step S103: Fill in the elements of the sparse data matrix to obtain the target sparse data matrix.

[0056] In this embodiment, elements of the sparse data matrix are added based on its characteristics. Specifically, the elements in the historical power flow carrier sensing data matrix are all related to the current a. 1 Voltage a 2 Power quality a 3 That is, the element in the g-th historical power flow carrier sensing data matrix can be represented as a g (a 1 a 2 a 3 ); The elements in the historical information stream carrier sensing data matrix are all related to the information arrival time b. 1 Information effect b 2 Information quality b 3 That is, the element in the h-th historical information stream carrier sensing data matrix can be represented as b h (b 1 b 2 b 3 The elements in the historical service flow carrier sensing data matrix are all related to the service completion time c. 1 Business difficulty c 2 Number of business items c 3That is, the elements in the j-th historical service flow carrier sensing data matrix can be represented as c j (c 1 c 2 c 3 The elements in the extracted knowledge matrix are all related to the amount of knowledge extracted, d. 1 Knowledge extraction speed d 2 Knowledge extraction method d 3 That is, the elements in the k-th historical traffic flow carrier sensing data matrix can be represented as d k (d 1 d 2 d 3 ); All elements in the learning correlation matrix are related to the learning correlation degree e. 1 Learning association effect e 2 Learning association methods e 3 That is, the element in the l-th historical service flow carrier sensing data matrix can be represented as e l (e 1 e 2 e 3 ).

[0057] In some embodiments, step S103 includes:

[0058] Using a preset data completion strategy, based on the preset weight coefficients of each influencing factor, element completion is performed on each of the sparse data matrices to obtain the corresponding target sparse data matrix. The expression for the preset data completion strategy is as follows:

[0059]

[0060] Among them, a * (a 1 a 2 a 3 ) represents the power flow carrier sensing data matrix, b * (b 1 b 2 b 3 ) represents the information flow carrier sensing data matrix, c * (c 1 c 2 c 3 ) represents the service flow carrier sensing data matrix, d * (d 1 d 2 d 3 ) represents the extracted knowledge matrix, e * (e 1 e 2 e 3 ) represents a data relationship matrix, a 1a 2 and a 3 δ1, δ2, and δ3 represent the weighting coefficients corresponding to current, voltage, and power quality, respectively, G represents the total number of elements in the power flow carrier sensing data matrix, and b represents the weighting coefficients corresponding to current, voltage, and power quality, respectively. 1 b 2 and b 3 ε1, ε2, and ε3 represent the information arrival time, information effect, and information quality, respectively; H represents the total number of elements in the information flow carrier sensing data matrix; and c represents the information arrival time, information effect, and information quality, respectively. 1 c 2 and c 3 φ1, φ2, and φ3 represent the service completion time, service difficulty, and service quantity, respectively; φ3 represents the weighting coefficients corresponding to the service completion time, service difficulty, and service quantity, respectively; J represents the total number of elements in the service flow carrier sensing data matrix; and d represents the total number of elements in the service flow carrier sensing data matrix. 1 d 2 and d 3 These represent the amount of knowledge extracted, the speed of knowledge extraction, and the method of knowledge extraction, respectively. and These represent the weight coefficients corresponding to the amount of knowledge extracted, the speed of knowledge extraction, and the method of knowledge extraction, respectively. K represents the total number of elements in the knowledge extraction matrix, and e 1 e 2 and e 3 γ1, γ2, and γ3 represent the learning correlation degree, learning correlation effect, and learning correlation method, respectively. γ1, γ2, and γ3 represent the weight coefficients corresponding to the learning correlation degree, learning correlation effect, and learning correlation method, respectively. L represents the total number of elements in the data relationship matrix.

[0061] It should be noted that all weighting coefficients are used to measure the importance of different indicators. Specifically, for historical power flow, information flow, and service flow carrier sensor data matrices, the more known elements extracted from the knowledge matrix and learning correlation matrix, the more accurate the prediction of missing elements will be.

[0062] Step S104: Based on the target sparse data matrix, establish the power interaction model, information interaction model and business interaction model for multi-service electrical equipment respectively.

[0063] In this step, the target sparse data matrix includes the target sparse data matrices corresponding to the power flow, information flow, and business flow, respectively. Therefore, based on the corresponding target sparse data matrices, the power interaction model, information interaction model, and business interaction model are established.

[0064] In some embodiments, step S104 includes:

[0065] Based on the target sparse data matrix, an energy flow adjacency matrix is ​​constructed, and a first adjacency graph of the energy flow direction is constructed based on the energy flow adjacency matrix, and the energy interaction model is established based on the first adjacency graph.

[0066] Based on the target sparse data matrix, an information flow adjacency matrix is ​​constructed, and a second adjacency graph of the information flow direction is constructed based on the information flow adjacency matrix, and the information interaction model is established based on the second adjacency graph;

[0067] Based on the business nodes in the business flow, an association topology graph of the business nodes is established according to the target sparse data matrix, and the business interaction model is established based on the association topology graph.

[0068] In this embodiment, an adjacency matrix of power flow data features is constructed using the data features of a sparse data matrix, and an adjacency graph of power flow direction is constructed based on the adjacency matrix, thereby obtaining a power interaction model for multi-service electrical equipment; communication of various low-voltage distribution area electrical equipment is realized through differentiated multi-channel protocols, and an information interaction model for multi-service electrical equipment is obtained based on the information flow direction adjacency graph; by extracting service nodes in the service flow, a service node association topology graph is constructed, and a service interaction model for multi-service electrical equipment is established.

[0069] Step S105: The power interaction model, information interaction model and business interaction model are fused to obtain the integrated data model of multi-business electrical equipment in the target low-voltage distribution area.

[0070] In this step, based on the relationship between power flow, information flow, and business flow, the power interaction model, information interaction model, and business interaction model are integrated to establish an integrated data model.

[0071] In some embodiments, step S1050 includes:

[0072] Based on the service nodes, power flow direction, and information transmission direction of the target low-voltage distribution area, establish the correlation between power flow, information flow, and service flow;

[0073] Based on the aforementioned relationships, the power interaction model, the information interaction model, and the business interaction model are fused together to obtain the integrated data model for multi-business electrical equipment.

[0074] In this embodiment, the relationships between the power interaction model, information interaction model, and business interaction model of multi-service electrical equipment are constructed vertically. Specifically, by combining the characteristics of power flow and information transmission direction of business nodes, the deep correlation between the information flow under power flow and the power flow and information flow under business flow is obtained. The three types of models are fused through the deep relationship between power flow, information flow, and business flow to obtain an integrated data model of multi-service electrical equipment in low-voltage distribution area.

[0075] It should be noted that this application extracts knowledge and learns associations from historical power flow, information flow, and service flow carrier sensing data to construct a knowledge graph. Then, by analyzing various element indicators, it completes the prediction and completion of missing elements in the knowledge matrix and learning association matrix of historical power flow, information flow, and service flow carrier sensing data matrices, thereby realizing the deduction of sparse data of power flow, information flow, and service flow carrier sensing in the knowledge graph of the press area operation.

[0076] Meanwhile, based on the relevant table structure of business interaction, the graphical method of power interaction, and the information interaction of hardware and network cable communication, a business interaction, power interaction, and information interaction model of multi-service electrical equipment was constructed, and an integrated data model of multi-service electrical equipment in low-voltage distribution area was constructed through deep integration.

[0077] To implement the data-driven device data modeling method corresponding to the above method embodiments, and to achieve the corresponding functions and technical effects. See also Figure 2 , Figure 2 This diagram illustrates a structural block diagram of a data-based device data modeling apparatus according to an embodiment of this application. For ease of explanation, only the parts relevant to this embodiment are shown. The data-based device data modeling apparatus provided in this embodiment includes:

[0078] The acquisition module 201 is used to acquire carrier sensing data corresponding to the historical power flow, historical information flow and historical service flow of the target low-voltage distribution area.

[0079] Extraction module 202 is used to extract data knowledge for each type of carrier sensing data to establish a sparse data matrix respectively;

[0080] The completion module 203 is used to complete the elements of the sparse data matrix to obtain the target sparse data matrix.

[0081] Module 204 is used to establish, based on the target sparse data matrix, the power interaction model, information interaction model and business interaction model of the multi-service electrical equipment respectively;

[0082] The fusion module 205 is used to fuse the power interaction model, information interaction model and business interaction model to obtain an integrated data model of multi-business electrical equipment in the target low-voltage distribution area.

[0083] In some embodiments, the extraction module 202 is specifically used for:

[0084] For each type of carrier sensing data, data structure identification, data feature identification, and data relationship extraction are performed on the carrier sensing data to obtain the data structure, data features, and data relationships of the carrier sensing data;

[0085] Based on the data structure, data features, and data relationships, a sparse data matrix is ​​established for each type of carrier sensing data. The sparse data matrix includes a power flow carrier sensing data matrix, an information flow carrier sensing data matrix, a service flow carrier sensing data matrix, an extracted knowledge matrix, and a data relationship matrix.

[0086] In some embodiments, the completion module 203 is specifically used for:

[0087] Using a preset data completion strategy, based on the preset weight coefficients of each influencing factor, element completion is performed on each of the sparse data matrices to obtain the corresponding target sparse data matrix. The expression for the preset data completion strategy is as follows:

[0088]

[0089] Among them, a * (a 1 a 2 a 3 ) represents the power flow carrier sensing data matrix, b * (b 1 b 2 b 3 ) represents the information flow carrier sensing data matrix, c * (c 1 c 2 c 3 ) represents the service flow carrier sensing data matrix, d * (d 1 d 2 d 3 ) represents the extracted knowledge matrix, e * (e 1 e 2 e 3 ) represents a data relationship matrix, a 1 a 2 and a 3δ1, δ2, and δ3 represent the weighting coefficients corresponding to current, voltage, and power quality, respectively, G represents the total number of elements in the power flow carrier sensing data matrix, and b represents the weighting coefficients corresponding to current, voltage, and power quality, respectively. 1 b 2 and b 3 ε1, ε2, and ε3 represent the information arrival time, information effect, and information quality, respectively; H represents the total number of elements in the information flow carrier sensing data matrix; and c represents the information arrival time, information effect, and information quality, respectively. 1 c 2 and c 3 φ1, φ2, and φ3 represent the service completion time, service difficulty, and service quantity, respectively; φ3 represents the weighting coefficients corresponding to the service completion time, service difficulty, and service quantity, respectively; J represents the total number of elements in the service flow carrier sensing data matrix; and d represents the total number of elements in the service flow carrier sensing data matrix. 1 d 2 and d 3 These represent the amount of knowledge extracted, the speed of knowledge extraction, and the method of knowledge extraction, respectively. and These represent the weight coefficients corresponding to the amount of knowledge extracted, the speed of knowledge extraction, and the method of knowledge extraction, respectively. K represents the total number of elements in the knowledge extraction matrix, and e 1 e 2 and e 3 γ1, γ2, and γ3 represent the learning correlation degree, learning correlation effect, and learning correlation method, respectively. γ1, γ2, and γ3 represent the weight coefficients corresponding to the learning correlation degree, learning correlation effect, and learning correlation method, respectively. L represents the total number of elements in the data relationship matrix.

[0090] In some embodiments, the establishment module 204 is specifically used for:

[0091] Based on the target sparse data matrix, an energy flow adjacency matrix is ​​constructed, and a first adjacency graph of the energy flow direction is constructed based on the energy flow adjacency matrix, and the energy interaction model is established based on the first adjacency graph.

[0092] Based on the target sparse data matrix, an information flow adjacency matrix is ​​constructed, and a second adjacency graph of the information flow direction is constructed based on the information flow adjacency matrix, and the information interaction model is established based on the second adjacency graph;

[0093] Based on the business nodes in the business flow, an association topology graph of the business nodes is established according to the target sparse data matrix, and the business interaction model is established based on the association topology graph.

[0094] In some embodiments, the fusion module 205 is specifically used for:

[0095] Based on the service nodes, power flow direction, and information transmission direction of the target low-voltage distribution area, establish the correlation between power flow, information flow, and service flow;

[0096] Based on the aforementioned relationships, the power interaction model, the information interaction model, and the business interaction model are fused together to obtain the integrated data model for multi-business electrical equipment.

[0097] The aforementioned data-based device data modeling apparatus can implement the data-based device data modeling method of the above method embodiments. The options in the above method embodiments are also applicable to this embodiment, and will not be detailed here. The remaining content of this application's embodiments can be referred to the content of the above method embodiments, and will not be repeated in this embodiment.

[0098] Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Figure 3 As shown, the computer device 3 of this embodiment includes: at least one processor 30 ( Figure 3 (Only one is shown in the diagram), memory 31, and computer program 32 stored in said memory 31 and executable on said at least one processor 30, wherein said processor 30 executes said computer program 32 to implement the steps in any of the above method embodiments.

[0099] The computer device 3 can be a smartphone, tablet, desktop computer, cloud server, or other computing device. This computer device may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will understand that... Figure 3 The computer device 3 is merely an example and does not constitute a limitation on the computer device 3. It may include more or fewer components than shown in the figure, or combine certain components, or different components, such as input / output devices, network access devices, etc.

[0100] The processor 30 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0101] In some embodiments, the memory 31 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 31 may be an external storage device of the computer device 3, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 3. Furthermore, the memory 31 may include both internal and external storage units of the computer device 3. The memory 31 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory 31 can also be used to temporarily store data that has been output or will be output.

[0102] In addition, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in any of the above method embodiments.

[0103] This application provides a computer program product that, when run on a computer device, enables the computer device to execute the steps described in the various method embodiments above.

[0104] In the several embodiments provided in this application, it will be understood that each block in the flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the figures. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved.

[0105] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0106] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of this application. It should be understood that the above descriptions are merely specific embodiments of this application and are not intended to limit the scope of protection of this application. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application for those skilled in the art.

Claims

1. A device data modeling method based on data extrapolation, characterized in that, include: Acquire carrier sensing data corresponding to the historical power flow, historical information flow, and historical service flow of the target low-voltage distribution area; Data knowledge is extracted for each type of carrier sensing data to establish a sparse data matrix respectively; The sparse data matrix is ​​padded with elements to obtain a target sparse data matrix; wherein, the element-padded process of the sparse data matrix to obtain the target sparse data matrix includes: using a preset data padding strategy, based on a preset weight coefficient for each influencing factor, to pad each type of sparse data matrix with elements to obtain the corresponding target sparse data matrix, wherein the expression of the preset data padding strategy is: ； in, Represents the power flow carrier sensing data matrix. Represents the information flow carrier sensing data matrix. Represents the carrier sensing data matrix of the service flow. This represents the extracted knowledge matrix. Represents a data relationship matrix. , and These represent current, voltage, and power quality, respectively. , and These represent the weighting coefficients corresponding to current, voltage, and power quality, respectively. This represents the total number of elements in the power flow carrier sensing data matrix. , and These represent information arrival time, information effect, and information quality, respectively. , and These represent the weighting coefficients corresponding to information arrival time, information effect, and information quality, respectively. This represents the total number of elements in the information flow carrier sensing data matrix. , and These represent the time to complete the task, the difficulty of the task, and the number of tasks, respectively. , and These represent the weighting coefficients corresponding to the business completion time, business difficulty, and business quantity, respectively. This represents the total number of elements in the service flow carrier sensing data matrix. , and These represent the amount of knowledge extracted, the speed of knowledge extraction, and the method of knowledge extraction, respectively. , and These represent the weight coefficients corresponding to the amount of knowledge extracted, the speed of knowledge extraction, and the method of knowledge extraction, respectively. This represents the total number of elements in the extracted knowledge matrix. , and These represent the degree of learning relevance, the effect of learning relevance, and the method of learning relevance, respectively. , and These represent the weight coefficients corresponding to the degree of learning association, the effect of learning association, and the method of learning association, respectively. Represents the total number of elements in the data relationship matrix; Based on the target sparse data matrix, power interaction model, information interaction model and business interaction model of multi-service electrical equipment are established respectively. The power interaction model, information interaction model, and business interaction model are fused to obtain an integrated data model of multi-business electrical equipment in the target low-voltage distribution area.

2. The equipment data modeling method based on data extrapolation as described in claim 1, characterized in that, The step of extracting data knowledge for each type of carrier sensing data to establish a sparse data matrix includes: For each type of carrier sensing data, data structure identification, data feature identification, and data relationship extraction are performed on the carrier sensing data to obtain the data structure, data features, and data relationships of the carrier sensing data; Based on the data structure, data features, and data relationships, a sparse data matrix is ​​established for each type of carrier sensing data. The sparse data matrix includes a power flow carrier sensing data matrix, an information flow carrier sensing data matrix, a service flow carrier sensing data matrix, an extracted knowledge matrix, and a data relationship matrix.

3. The equipment data modeling method based on data extrapolation as described in claim 1, characterized in that, The step of establishing power interaction models, information interaction models, and service interaction models for multi-service electrical equipment based on the target sparse data matrix includes: Based on the target sparse data matrix, an energy flow adjacency matrix is ​​constructed, and a first adjacency graph of the energy flow direction is constructed based on the energy flow adjacency matrix, and the energy interaction model is established based on the first adjacency graph. Based on the target sparse data matrix, an information flow adjacency matrix is ​​constructed, and a second adjacency graph of the information flow direction is constructed based on the information flow adjacency matrix, and the information interaction model is established based on the second adjacency graph; Based on the business nodes in the business flow, an association topology graph of the business nodes is established according to the target sparse data matrix, and the business interaction model is established based on the association topology graph.

4. The equipment data modeling method based on data extrapolation as described in claim 1, characterized in that, The process of fusing the power interaction model, information interaction model, and service interaction model to obtain an integrated data model of multi-service electrical equipment in the target low-voltage distribution area includes: Based on the service nodes, power flow direction, and information transmission direction of the target low-voltage distribution area, establish the correlation between power flow, information flow, and service flow; Based on the aforementioned relationships, the power interaction model, the information interaction model, and the business interaction model are fused together to obtain the integrated data model for multi-business electrical equipment.

5. A device for equipment data modeling based on data extrapolation, characterized in that, include: The acquisition module is used to acquire carrier sensing data corresponding to the historical power flow, historical information flow and historical service flow of the target low-voltage distribution area. An extraction module is used to extract data knowledge from each type of carrier sensing data to establish a sparse data matrix respectively. The completion module is used to complete the elements of the sparse data matrix to obtain a target sparse data matrix; wherein, the step of completing the elements of the sparse data matrix to obtain the target sparse data matrix includes: using a preset data completion strategy, based on a preset weight coefficient for each influencing factor, to complete the elements of each sparse data matrix to obtain the corresponding target sparse data matrix, wherein the expression of the preset data completion strategy is: ； in, Represents the power flow carrier sensing data matrix. Represents the information flow carrier sensing data matrix. Represents the carrier sensing data matrix of the service flow. This represents the extracted knowledge matrix. Represents a data relationship matrix. , and These represent current, voltage, and power quality, respectively. , and These represent the weighting coefficients corresponding to current, voltage, and power quality, respectively. This represents the total number of elements in the power flow carrier sensing data matrix. , and These represent information arrival time, information effect, and information quality, respectively. , and These represent the weighting coefficients corresponding to information arrival time, information effect, and information quality, respectively. This represents the total number of elements in the information flow carrier sensing data matrix. , and These represent the time to complete the task, the difficulty of the task, and the number of tasks, respectively. , and These represent the weighting coefficients corresponding to the business completion time, business difficulty, and business quantity, respectively. This represents the total number of elements in the service flow carrier sensing data matrix. , and These represent the amount of knowledge extracted, the speed of knowledge extraction, and the method of knowledge extraction, respectively. , and These represent the weight coefficients corresponding to the amount of knowledge extracted, the speed of knowledge extraction, and the method of knowledge extraction, respectively. This represents the total number of elements in the extracted knowledge matrix. , and These represent the degree of learning relevance, the effect of learning relevance, and the method of learning relevance, respectively. , and These represent the weight coefficients corresponding to the degree of learning association, the effect of learning association, and the method of learning association, respectively. Represents the total number of elements in the data relationship matrix; A module is established to build, based on the target sparse data matrix, a power interaction model, an information interaction model, and a business interaction model for multi-service electrical equipment, respectively. The fusion module is used to fuse the power interaction model, information interaction model and business interaction model to obtain an integrated data model of multi-business electrical equipment in the target low-voltage distribution area.

6. The equipment data modeling device based on data extrapolation as described in claim 5, characterized in that, The establishment module is specifically used for: Based on the target sparse data matrix, an energy flow adjacency matrix is ​​constructed, and a first adjacency graph of the energy flow direction is constructed based on the energy flow adjacency matrix, and the energy interaction model is established based on the first adjacency graph. Based on the target sparse data matrix, an information flow adjacency matrix is ​​constructed, and a second adjacency graph of the information flow direction is constructed based on the information flow adjacency matrix, and the information interaction model is established based on the second adjacency graph; Based on the business nodes in the business flow, an association topology graph of the business nodes is established according to the target sparse data matrix, and the business interaction model is established based on the association topology graph.

7. A computer device, characterized in that, It includes a processor and a memory, the memory being used to store a computer program, which, when executed by the processor, implements the device data modeling method based on data extrapolation as described in any one of claims 1 to 4.

8. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the device data modeling method based on data extrapolation as described in any one of claims 1 to 4.

Images