Multi-source data processing method, device, equipment and medium for power Internet of Things

Abstract

The present invention discloses a multi-source data processing method, device, equipment and medium of an electric power Internet of Things, and relates to the technical field of data processing of the electric power Internet of Things. The method is applied to the policy layer of the electric power Internet of Things including the platform side and the edge side, and the method includes: receiving the business data of at least one source node to be distributed through a data distribution node; determining the priority of each source node to be distributed based on the business data of each source node to be distributed through the data distribution node, determining the target source node set to be distributed according to the priority, and sending the target business data set composed of the business data of each target source node to be distributed to the platform side; using the preset neural network on the platform side to extract the semantic feature set of the target business data set, mapping the semantic features to corresponding code words and sending them to the corresponding target nodes, wherein when the correlation between any two semantic features meets the preset conditions, they are mapped to the same code word. Effectively improve the data processing efficiency.

Description

Technical Field

[0001] Embodiments of the present invention relate to the technical field of power Internet of Things data processing, and in particular, to a multi-source data processing method, device, equipment and medium for power Internet of Things. Background Art

[0002] As the demand for electricity supply in modern society continues to grow, the power Internet of Things system has become increasingly complex. The power Internet of Things must cope with the diversity of energy, the integration of renewable energy, the increase in distributed energy resources, and the changing load demand. In order to effectively manage and maintain the power Internet of Things, various sensors, monitoring devices, and data sources have been deployed at all levels of the power Internet of Things to collect data, such as power equipment status, energy production conditions, and grid topology. These data are crucial for the operation and maintenance of the power Internet of Things. They help decision makers understand the real-time status of the power Internet of Things and take necessary measures to ensure the reliability and security of power supply.

[0003] Semantic communication refers to the inclusion of information about the meaning and context of data in communication. This means not only delivering raw data, but also delivering semantic information about the data, enabling the recipient to better understand and process the data. In power IoT applications, the goal of semantic communication is to promote in-depth and meaningful exchanges between devices to support intelligent decision-making and automated operations.

[0004] However, faced with such a large and diverse data source, the existing data processing methods of the power Internet of Things have the problem of low processing efficiency. Summary of the invention

[0005] The present invention provides a multi-source data processing method, device, equipment and medium for an electric power Internet of Things to solve the problem of low processing efficiency in existing data processing methods for the electric power Internet of Things.

[0006] According to one aspect of the present invention, a multi-source data processing method of an electric power Internet of Things is provided, which is applied to a strategy layer of the electric power Internet of Things, wherein the strategy layer includes a platform side and an edge side, wherein the edge side includes a data distribution node, at least one source node and at least one target node, and the method includes:

[0007] Receiving, through the data distribution node, service data of at least one source node to be distributed;

[0008] Determine the priority of each source node to be distributed based on the business data of each source node to be distributed by the data distribution node, determine the target source node set to be distributed according to the priority of each source node to be distributed, and send the target business data set composed of the business data of each target source node to be distributed in the target source node set to the platform side;

[0009] The preset neural network on the platform side is used to extract the semantic feature set of the target business data set, the semantic features in the semantic feature set are mapped to corresponding codewords, and the codewords are sent to the corresponding target nodes, wherein when the correlation between any two semantic features in the semantic feature set meets a preset condition, the two semantic features are mapped to the same codeword.

[0010] According to another aspect of the present invention, a multi-source data processing device of an electric power Internet of Things is provided, which is applied to a strategy layer of the electric power Internet of Things, wherein the strategy layer includes a platform side and an edge side, wherein the edge side includes a data distribution node, at least one source node and at least one target node, and the device includes:

[0011] A data receiving module, used for receiving business data of at least one source node to be distributed through the data distribution node;

[0012] A first sending module, configured to determine the priority of each source node to be distributed based on the business data of each source node to be distributed through the data distribution node, determine a target source node set to be distributed according to the priority of each source node to be distributed, and send a target business data set consisting of the business data of each target source node to be distributed in the target source node set to the platform side;

[0013] The second sending module is used to extract the semantic feature set of the target business data set by using the preset neural network on the platform side, map the semantic features in the semantic feature set to corresponding code words, and send the code words to the corresponding target node, wherein when the correlation between any two semantic features in the semantic feature set meets a preset condition, the two semantic features are mapped to the same code word.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] at least one processor; and a memory in communication with the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the multi-source data processing method of the electric power Internet of Things described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the multi-source data processing method of the electric power Internet of Things described in any embodiment of the present invention when executed.

[0018] The technical solution provided by the embodiment of the present invention is applied to the strategy layer of the electric power Internet of Things, the strategy layer includes a platform side and an edge side, the edge side includes a data distribution node, at least one source node and at least one target node, the method includes: receiving business data of at least one source node to be distributed through the data distribution node; determining the priority of each source node to be distributed based on the business data of each source node to be distributed through the data distribution node, determining a target source node set to be distributed according to the priority of each source node to be distributed, and sending a target business data set consisting of the business data of each target source node to be distributed in the target source node set to the platform side; extracting a semantic feature set of the target business data set using a preset neural network on the platform side, mapping the semantic features in the semantic feature set to corresponding codewords, and sending the codewords to the corresponding target nodes, wherein, when the correlation between any two semantic features in the semantic feature set meets a preset condition, the two semantic features are mapped to the same codeword. Through the above technical scheme, the data distribution node is used to determine the target set of source nodes to be distributed according to the priority of each source node to be distributed, and the preset neural network on the platform side is used to extract the semantic feature set of the target business data set. The semantic features in the semantic feature set are mapped to corresponding codewords and sent to the corresponding target nodes. In particular, the semantic features whose correlation meets the preset conditions are mapped to the same codeword, which effectively improves the data processing efficiency.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 This is a flowchart of a multi-source data processing method of the electric power Internet of Things provided by the first embodiment of the present invention;

[0022] Figure 2 This is a schematic diagram of the structure of a multi-source data processing device for an electric power Internet of Things provided by Embodiment 2 of the present invention;

[0023] Figure 3 It is a structural schematic diagram of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations of these terms are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] Embodiment 1

[0027] Figure 1 This is a flowchart of a multi-source data processing method of an electric power Internet of Things provided in the first embodiment of the present invention. This embodiment is applicable to the case of processing multi-source data of the electric power Internet of Things. The method can be executed by a multi-source data processing device of the electric power Internet of Things. The multi-source data processing device of the electric power Internet of Things can be implemented in the form of hardware and / or software. The multi-source data processing device of the electric power Internet of Things can be configured in an electronic device integrating the strategy layer of the electric power Internet of Things, wherein the strategy layer of the electric power Internet of Things includes a platform side and an edge side, and the edge side includes a data distribution node, at least one source node and at least one target node. Figure 1 As shown, the method includes:

[0028] S110. Receive, through the data distribution node, business data of at least one source node to be distributed.

[0029] In this embodiment, the source node to be distributed can be understood as a source node for generating business data. For example, the source node to be distributed can be various sensors and various monitoring devices in the power Internet of Things. Business data is the data generated by the power Internet of Things during daily operation. These data can be structured data or unstructured data, such as video, text or voice. In the power Internet of Things, there are many categories of business data, such as warnings (abnormal information), logs (event records) or instructions (operation instructions). The data distribution node can be used to cache and manage the data of the source node to be distributed, such as distributing, transmitting, discarding and destroying the business data of the source node to be distributed.

[0030] Specifically, a strategy layer is preset in the electric power Internet of Things, and the strategy layer includes a platform side and an edge side. The edge side includes a plurality of pre-divided member groups, each of which includes a data distribution node, at least one source node, and at least one target node. Among them, the target node can be understood as a node for receiving the business data of the source node to be distributed. This embodiment is described by taking the business data processing of a single member group as an example.

[0031] During the operation of the power Internet of Things, the source node to be distributed will generate business data and send the business data to the data distribution node.

[0032] S120. Determine the priority of each source node to be distributed based on the business data of each source node to be distributed through the data distribution node, determine the target source node set to be distributed according to the priority of each source node to be distributed, and send the target business data set composed of the business data of each target source node to be distributed in the target source node set to the platform side.

[0033] Specifically, after the data distribution node receives the business data of each source node to be distributed, based on the business data of each source node to be distributed, a preset priority algorithm can be used to determine the priority of each source node to be distributed; then, a target source node set to be distributed is determined according to the priority of each source node to be distributed, and the business data of each target source node to be distributed in the target source node set to be distributed is aggregated into a target business data set, and then the target business data set is sent to the platform side. This embodiment does not limit the specific preset priority algorithm.

[0034] S130. Utilize the preset neural network on the platform side to extract the semantic feature set of the target business data set, map the semantic features in the semantic feature set to corresponding codewords, and send the codewords to the corresponding target nodes, wherein when the correlation between any two semantic features in the semantic feature set meets a preset condition, the two semantic features are mapped to the same codeword.

[0035] In this embodiment, the preset neural network can be understood as a deep neural network model pre-trained on a large number of data sets. For example, the preset neural network in this embodiment can be a Deep Learning Based Semantic Communication (DL-SC) network based on deep learning. A codeword is a sequence of several code elements used to represent specific data or information. For example, in ASCII encoding, an English character can be represented by one byte (8 code elements). A code element is the smallest unit in a coding system, usually represented in binary form, that is, 0 or 1. A semantic feature can be understood as an element that can express the meaning of the original data. A semantic feature can be a phrase, a phrase, or a sentence. The relevance of a semantic feature can be understood as the similarity between different semantic features, which can be used to measure the semantic proximity of a phrase, a phrase, or a sentence. The higher the similarity, the higher the relevance of two semantic features. The preset condition can be understood as a pre-set condition. For example, the preset condition indicates that the relevance is greater than a preset threshold.

[0036] Specifically, after receiving the target business data set, the platform first uses a preset neural network to extract the semantic feature set of the target business data set. The calculation process can be expressed as follows:

[0037]

[0038] in, Represents a set of semantic features; Represents the target business data set; Represents the parameters of the preset neural network; It is the function representation of the preset neural network.

[0039] In order to further improve the efficiency of data processing, the correlation between any two semantic features in the semantic feature set is calculated by a preset correlation algorithm, and the semantic features are mapped to corresponding code words based on the correlation, and then the code words are sent to the corresponding target nodes. In particular, if the correlation meets the preset conditions, the two semantic features are mapped to the same code word, thereby reducing data redundancy, thereby effectively improving the output efficiency of data. This embodiment does not limit the specific preset correlation algorithm.

[0040] For example, the two semantic features "You" and "Yours" appear in the semantic feature set. The correlation between the two words calculated by the preset correlation algorithm meets the preset conditions. In this case, the two words can be mapped to the same code word. If the two semantic features correspond to the same target node, the platform side can only send one code word when sending data to the target node, thereby effectively reducing redundancy and improving data transmission efficiency.

[0041] The technical solution provided in the first embodiment of the present invention is applied to the strategy layer of the electric power Internet of Things, the strategy layer includes a platform side and an edge side, the edge side includes a data distribution node, at least one source node and at least one target node, the method includes: receiving business data of at least one source node to be distributed through the data distribution node; determining the priority of each source node to be distributed based on the business data of each source node to be distributed through the data distribution node, determining a target source node set to be distributed according to the priority of each source node to be distributed, and sending a target business data set consisting of the business data of each target source node to be distributed in the target source node set to the platform side; extracting a semantic feature set of the target business data set using a preset neural network on the platform side, mapping the semantic features in the semantic feature set to corresponding codewords, and sending the codewords to the corresponding target nodes, wherein, when the correlation between any two semantic features in the semantic feature set meets a preset condition, the two semantic features are mapped to the same codeword. Through the above technical scheme, the data distribution node is used to determine the target set of source nodes to be distributed according to the priority of each source node to be distributed, and the preset neural network on the platform side is used to extract the semantic feature set of the target business data set. The semantic features in the semantic feature set are mapped to corresponding codewords and sent to the corresponding target nodes. In particular, semantic features with high correlation are mapped to the same codeword, which effectively improves the data processing efficiency.

[0042] Optionally, all source nodes to be distributed can be sorted in descending order of priority of each source node to be distributed, and all sorted source nodes to be distributed can be aggregated into a target source node to be distributed set, and then the business data of each target source node to be distributed in the target source node to be distributed set can be aggregated into a target business data set and sent to the platform side, so as to be sent to the corresponding target node through the platform side.

[0043] Optionally, all source nodes to be distributed can be sorted in descending order of priority of each source node to be distributed, and from the sorted results, a preset number of source nodes to be distributed with the highest rankings are selected to be aggregated into a target source node to be distributed set, and the source nodes to be distributed that are not selected are aggregated into a candidate source node to be distributed set; then, the business data of each target source node to be distributed in the target source node to be distributed set is aggregated into a target business data set and sent to the platform side, so as to be sent to the corresponding target node through the platform side; after the target business data set is distributed on the platform side, the above steps are repeated according to the priority of each source node to be distributed in the candidate source node to be distributed set until the business data distribution of all source nodes to be distributed is completed. In this way, the efficiency and timeliness of data distribution are ensured.

[0044] Optionally, an information table may be pre-set in the data distribution node, and the information table is used to determine whether the business data in the source node to be distributed is correct and to determine the target node to which it needs to be distributed. The information table may include a basic information table of pre-distributed data and a subscription information table of this member group. Among them, the basic information table of pre-distributed data is used to determine whether the business data of the source node to be distributed is correct, and the basic information table of pre-distributed data contains basic information of the business data of the source node to be distributed, such as data content, quality of service (Quality of Service, QoS) requirements, etc.; the subscription information table of this member group is used to determine the target node to which the business data in the source node to be distributed needs to be distributed, and the subscription information table of this member group includes subscription information of all nodes in this node group.

[0045] In some embodiments, the priority of each source node to be distributed is determined based on the business data of each source node to be distributed, including: for each source node to be distributed, determining the bandwidth and maximum delay of the transmission link between the current source node to be distributed and the corresponding target node based on the business data of the current source node to be distributed; calculating the sensitivity of the business data of the current source node to be distributed based on the bandwidth, maximum delay, total number of source nodes to be distributed and the data volume of the business data of the current source node to be distributed; determining the priority of each source node to be distributed according to the sensitivity of the business data of each source node to be distributed, wherein the sensitivity is positively correlated with the priority.

[0046] In this embodiment, the bandwidth of the transmission link can be understood as the amount of data that can be transmitted through the link per unit time. The size of the bandwidth directly affects the rate and efficiency of data transmission. The maximum delay of the transmission link can be understood as the maximum time required from the source node to send data to the target node to completely receive the data. The amount of business data can be understood as the size of the business data that the current source node to be distributed needs to transmit. The length of the maximum delay is related to the real-time and reliability of data transmission.

[0047] Specifically, in order to ensure the efficiency and security of data transmission, for each source node to be distributed, the business data characteristics of the current source node to be distributed, such as the data volume, type and real-time requirements of the business data, can be comprehensively considered to determine the bandwidth and maximum delay of the transmission link between the current source node to be distributed and the corresponding target node; then, the bandwidth, maximum delay, total number of source nodes to be distributed and the data volume of the business data of the current source node to be distributed of the transmission link are comprehensively considered, and the sensitivity of the business data of the current source node to be distributed is calculated using a preset sensitivity algorithm; then, according to the sensitivity of the business data of each source node to be distributed, the priority of each source node to be distributed is determined, and the source node to be distributed with higher sensitivity will be assigned a higher priority, that is, the sensitivity is positively correlated with the priority. The preset sensitivity algorithm is not limited in this embodiment. Through the above technical solution, the efficiency of data transmission and the security of data transmission are effectively ensured.

[0048] In some embodiments, based on the bandwidth of the transmission link, the maximum delay, the total number of source nodes to be distributed, and the data volume of the business data of the current source node to be distributed, the sensitivity of the business data of the current source node to be distributed is calculated, including: subtracting a preset value from the total number of source nodes to be distributed to obtain a target difference; multiplying the bandwidth of the transmission link, the maximum delay, and the target difference to obtain a target product; and determining the ratio of the data volume of the business data of the current source node to be distributed to the target product as the sensitivity of the business data of the current source node to be distributed.

[0049] In this embodiment, the preset value can be set according to actual conditions.

[0050] Specifically, the sensitivity of the service data of the current source node to be distributed can be calculated by the following formula:

[0051]

[0052] in, Indicates the current source node to be distributed the sensitivity of your business data; Indicates the current source node to be distributed and the corresponding target node The transmission link between Indicates bandwidth; Indicates the maximum delay; Indicates the total number of source nodes to be distributed, represents the target difference, where 1 is the preset value; represents the target product; Indicates the amount of business data of the current source node to be distributed. Through the above technical method, the sensitivity of the business data of each source node to be distributed is calculated, laying an effective foundation for more flexible and efficient processing of large amounts of data distribution.

[0053] In some embodiments, the target set of source nodes to be distributed is determined according to the priority of each of the source nodes to be distributed, including: according to the priority of each of the source nodes to be distributed, a preset number of source nodes to be distributed are selected as first candidate source nodes to be distributed to obtain a first candidate node set, and the source nodes to be distributed that are not selected are used as second candidate source nodes to be distributed to obtain a second candidate node set; the first candidate source node to be distributed with the lowest priority in the first candidate node set and the second candidate source node to be distributed with the highest priority in the second candidate node set are exchanged to obtain an updated first candidate node set and a second candidate node set; the updated first candidate node set is determined as the target set of source nodes to be distributed.

[0054] In this embodiment, the preset number can be understood as a pre-set number.

[0055] Specifically, the source nodes to be distributed are sorted in order from high to low according to the priority of each source node to be distributed, and a preset number of source nodes to be distributed with the highest ranking are selected as the first candidate source nodes to be distributed, so as to obtain a first candidate node set; the source nodes to be distributed that are not selected are selected as the second candidate source nodes to be distributed, so as to obtain a second candidate node set. In order to ensure the fairness of the distribution of business data of each source node to be distributed, the first candidate source node to be distributed with the lowest priority in the first candidate node set and the second candidate source node to be distributed with the highest priority in the second candidate node set are exchanged to obtain the updated first candidate node set and the second candidate node set, while ensuring the priority of the source nodes to be distributed with high priority, providing opportunities for source nodes that do not meet the candidate standards, and then determining the updated first candidate node set as the target source node set to be distributed. Through the above technical solution, the priority of important business data is effectively highlighted, and while effectively improving the efficiency of data distribution, the fairness and flexibility of data processing are also enhanced.

[0056] Exemplarily, the source nodes to be distributed are sorted in descending order of priority, and the top P source nodes to be distributed are selected to form the first candidate node set. , unselected source nodes to be distributed , forming the second candidate node set , and then The first candidate source node to be distributed has the lowest priority, that is The source node to be distributed with the smallest sensitivity in The second candidate source node with the highest priority is The source nodes to be distributed with the greatest sensitivity are exchanged to obtain an updated first candidate node set and a second candidate node set; and the updated first candidate node set is determined as the target source node set to be distributed.

[0057] Then, the target business data set consisting of the business data of each target source node to be distributed in the target source node set to be distributed is sent to the platform side, and the platform side processes the target business data set and sends it to the corresponding target node. After the platform side completes the distribution of the target business data set, the above process is repeated according to the priority of the second candidate source node to be distributed in the updated second candidate node set until the business data of all source nodes to be distributed are distributed.

[0058] In some embodiments, when the correlation between any two semantic features in the semantic feature set does not satisfy the preset condition, the two semantic features are mapped to different codewords.

[0059] Specifically, to ensure the accuracy of business data, when it is determined that the correlation between any two semantic features in the semantic feature set does not meet the preset condition, the two semantic features are mapped to different codewords. Through the above technical solution, the accuracy of data is effectively guaranteed while ensuring efficient data transmission.

[0060] For example, if the calculated correlation between the two semantic features "car" and "candy" in the semantic feature set does not satisfy a preset condition, the two semantic features are mapped to different code words.

[0061] In some embodiments, the association degree between any two semantic features in the semantic feature set is determined in the following manner: calculating a first total number of characters in the first semantic feature, a second total number of characters in the second semantic feature, and the number of characters in the intersection of the first semantic feature and the second semantic feature; based on the first total number, the second total number, and the number of characters in the intersection, determining the association degree between the first semantic feature and the second semantic feature.

[0062] In this embodiment, a character can be understood as a basic element in a text, such as a word or a Chinese character.

[0063] Specifically, a preset statistical algorithm is used to calculate the first total number of characters in the first semantic feature, the second total number of characters in the second semantic feature, and the number of characters in the intersection of the first semantic feature and the second semantic feature, respectively. Then, based on the first total number, the second total number, and the number of characters in the intersection, a preset correlation algorithm is used to determine the correlation between the first semantic feature and the second semantic feature. The specific preset statistical algorithm is not limited in this embodiment. Through the above technical solution, the calculation of the correlation of semantic features is realized, laying a foundation for further improving the efficiency of data processing.

[0064] In some embodiments, the association between a first semantic feature and a second semantic feature is determined based on the first total number, the second total number, and the number of characters in the intersection, including: determining the maximum value of the first total number and the second total number; and determining the ratio of the number of characters in the intersection to the maximum value as the association between the first semantic feature and the second semantic feature.

[0065] Specifically, the correlation between the first semantic feature and the second semantic feature is calculated in the following manner:

[0066]

[0067] in, represents the correlation between the first semantic feature and the second semantic feature; Represents a set of semantic features; express The first semantic feature of any two semantic features in ; express The second semantic feature of any two semantic features; Represents the number of characters in the intersection of two semantic features; represents the first total quantity; represents the second total quantity; The maximum value of the first total number and the second total number is represented. Through the above technical solution, a quantitative correlation index is provided, which is helpful to evaluate and understand the correlation between the first semantic feature and the second semantic feature.

[0068] Embodiment 2

[0069] Figure 2 1 is a schematic diagram of the structure of a multi-source data processing device of the power Internet of Things provided in the second embodiment of the present invention. The device is applied to an electronic device integrating the strategy layer of the power Internet of Things, wherein the strategy layer of the power Internet of Things includes a platform side and an edge side, and the edge side includes a data distribution node, at least one source node and at least one target node. Figure 2 As shown, the device comprises:

[0070] A data receiving module 21, configured to receive service data of at least one source node to be distributed through the data distribution node;

[0071] A first sending module 22 is used to determine the priority of each source node to be distributed based on the business data of each source node to be distributed through the data distribution node, determine a target source node set to be distributed according to the priority of each source node to be distributed, and send a target business data set composed of the business data of each target source node to be distributed in the target source node set to the platform side;

[0072] The second sending module 23 is used to extract the semantic feature set of the target business data set using the preset neural network on the platform side, map the semantic features in the semantic feature set to corresponding code words, and send the code words to the corresponding target node, wherein when the correlation between any two semantic features in the semantic feature set meets a preset condition, the two semantic features are mapped to the same code word.

[0073] The technical solution provided by the second embodiment of the present invention effectively improves the data processing efficiency.

[0074] Optionally, the first sending module 22 includes:

[0075] A sensitivity calculation unit is used to determine, for each of the source nodes to be distributed, the bandwidth and maximum delay of the transmission link between the current source node to be distributed and the corresponding target node based on the service data of the current source node to be distributed; based on the bandwidth and maximum delay of the transmission link, the total number of source nodes to be distributed and the data volume of the service data of the current source node to be distributed, calculate the sensitivity of the service data of the current source node to be distributed;

[0076] The priority determination unit is used to determine the priority of each source node to be distributed according to the sensitivity of the business data of each source node to be distributed, wherein the sensitivity is positively correlated with the priority.

[0077] Optionally, the first sending module 22 further includes:

[0078] A candidate set determination unit is used to select a preset number of source nodes to be distributed as first candidate source nodes to be distributed according to the priority of each source node to be distributed, to obtain a first candidate node set, and to use unselected source nodes to be distributed as second candidate source nodes to be distributed, to obtain a second candidate node set;

[0079] A set updating unit, configured to exchange a first candidate source node to be distributed with the lowest priority in the first candidate node set with a second candidate source node to be distributed with the highest priority in the second candidate node set, to obtain an updated first candidate node set and a second candidate node set;

[0080] The target set determining unit is used to determine the updated first candidate node set as the target source node set to be distributed.

[0081] Optionally, the sensitivity calculation unit includes:

[0082] The difference determination subunit is used to subtract a preset value from the total number of source nodes to be distributed to obtain a target difference;

[0083] A product determination subunit, configured to multiply the bandwidth of the transmission link, the maximum delay, and the target difference to obtain a target product;

[0084] The sensitivity determination subunit is used to determine the ratio of the data volume of the business data of the current source node to be distributed and the target product as the sensitivity of the business data of the current source node to be distributed.

[0085] Optionally, when the correlation between any two semantic features in the semantic feature set does not satisfy the preset condition, the two semantic features are mapped to different codewords.

[0086] Optionally, the correlation between any two semantic features in the semantic feature set is determined in the following manner:

[0087] Calculating a first total number of characters in a first semantic feature, a second total number of characters in a second semantic feature, and a number of characters in an intersection of the first semantic feature and the second semantic feature;

[0088] A degree of association between the first semantic feature and the second semantic feature is determined based on the first total number, the second total number, and the number of characters in the intersection.

[0089] Optionally, determining the correlation between the first semantic feature and the second semantic feature based on the first total number, the second total number, and the number of characters in the intersection includes:

[0090] determining a maximum value of the first total number and the second total number;

[0091] The ratio of the number of characters in the intersection to the maximum value is determined as the correlation between the first semantic feature and the second semantic feature.

[0092] The multi-source data processing device of the electric power Internet of Things provided in the embodiment of the present invention can execute the multi-source data processing method of the electric power Internet of Things provided in any embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method.

[0093] Embodiment 3

[0094] Figure 3 : is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. The electronic device may be an electronic device intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0095] like Figure 3 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0096] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0097] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the multi-source data processing method of the power Internet of Things.

[0098] In some embodiments, the multi-source data processing method of the electric power Internet of Things can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the multi-source data processing method of the electric power Internet of Things described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the multi-source data processing method of the electric power Internet of Things in any other appropriate manner (for example, by means of firmware).

[0099] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0100] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0101] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0102] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0103] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0104] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0105] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0106] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A multi-source data processing method for power Internet of Things, characterized in that: A strategy layer applied to an electric power Internet of Things, the strategy layer comprising a platform side and an edge side, the edge side comprising a data distribution node, at least one source node and at least one target node, the method comprising: Receiving, through the data distribution node, service data of at least one source node to be distributed, wherein the source node to be distributed is used to generate service data; Determine the priority of each source node to be distributed based on the business data of each source node to be distributed by the data distribution node, determine the target source node set to be distributed according to the priority of each source node to be distributed, and send the target business data set composed of the business data of each target source node to be distributed in the target source node set to the platform side; Extracting a semantic feature set of the target business data set using a preset neural network on the platform side, mapping semantic features in the semantic feature set to corresponding codewords, and sending the codewords to corresponding target nodes, wherein when the correlation between any two semantic features in the semantic feature set meets a preset condition, the two semantic features are mapped to the same codeword; Wherein, determining the target set of source nodes to be distributed according to the priority of each source node to be distributed includes: According to the priority of each of the source nodes to be distributed, a preset number of source nodes to be distributed are selected as first candidate source nodes to be distributed to obtain a first candidate node set, and unselected source nodes to be distributed are used as second candidate source nodes to be distributed to obtain a second candidate node set; The first candidate source node to be distributed with the lowest priority in the first candidate node set is exchanged with the second candidate source node to be distributed with the highest priority in the second candidate node set to obtain an updated first candidate node set and a second candidate node set; The updated first candidate node set is determined as the target source node set to be distributed.

2. The method according to claim 1, characterized in that Determining the priority of each of the source nodes to be distributed based on the service data of each of the source nodes to be distributed includes: For each of the source nodes to be distributed, determine the bandwidth and maximum delay of the transmission link between the current source node to be distributed and the corresponding target node based on the service data of the current source node to be distributed; calculate the sensitivity of the service data of the current source node to be distributed based on the bandwidth, maximum delay, total number of source nodes to be distributed and data volume of the service data of the current source node to be distributed; The priority of each source node to be distributed is determined according to the sensitivity of the service data of each source node to be distributed, wherein the sensitivity is positively correlated with the priority.

3. The method according to claim 2, characterized in that Calculating the sensitivity of the service data of the current source node to be distributed based on the bandwidth of the transmission link, the maximum delay, the total number of source nodes to be distributed, and the data volume of the service data of the current source node to be distributed, including: Subtract the preset value from the total number of source nodes to be distributed to obtain the target difference; Multiplying the bandwidth of the transmission link, the maximum delay, and the target difference to obtain a target product; The ratio of the data volume of the service data of the current source node to be distributed and the target product is determined as the sensitivity of the service data of the current source node to be distributed.

4. The method according to claim 1, characterized in that: When the correlation between any two semantic features in the semantic feature set does not satisfy the preset condition, the two semantic features are mapped to different codewords.

5. The method according to claim 1, characterized in that The correlation between any two semantic features in the semantic feature set is determined in the following manner: Calculating a first total number of characters in a first semantic feature, a second total number of characters in a second semantic feature, and a number of characters in an intersection of the first semantic feature and the second semantic feature; A degree of association between the first semantic feature and the second semantic feature is determined based on the first total number, the second total number, and the number of characters in the intersection.

6. The method according to claim 5, characterized in that Determining a correlation between the first semantic feature and the second semantic feature based on the first total number, the second total number, and the number of characters in the intersection includes: determining a maximum value of the first total number and the second total number; The ratio of the number of characters in the intersection to the maximum value is determined as the correlation between the first semantic feature and the second semantic feature.

7. A multi-source data processing device for electric power Internet of Things, characterized in that: A strategy layer applied to the electric power Internet of Things, the strategy layer includes a platform side and an edge side, the edge side includes a data distribution node, at least one source node and at least one target node, and the device includes: A data receiving module, used for receiving business data of at least one source node to be distributed through the data distribution node, wherein the source node to be distributed is used for generating business data; A first sending module, configured to determine the priority of each source node to be distributed based on the business data of each source node to be distributed through the data distribution node, determine a target source node set to be distributed according to the priority of each source node to be distributed, and send a target business data set consisting of the business data of each target source node to be distributed in the target source node set to the platform side; A second sending module is used to extract a semantic feature set of the target business data set by using a preset neural network on the platform side, map the semantic features in the semantic feature set to corresponding codewords, and send the codewords to the corresponding target nodes, wherein when the correlation between any two semantic features in the semantic feature set meets a preset condition, the two semantic features are mapped to the same codeword; Wherein, the first sending module also includes: A candidate set determination unit is used to select a preset number of source nodes to be distributed as first candidate source nodes to be distributed according to the priority of each source node to be distributed, to obtain a first candidate node set, and to use unselected source nodes to be distributed as second candidate source nodes to be distributed, to obtain a second candidate node set; A set updating unit, configured to exchange a first candidate source node to be distributed with the lowest priority in the first candidate node set with a second candidate source node to be distributed with the highest priority in the second candidate node set, to obtain an updated first candidate node set and a second candidate node set; The target set determining unit is used to determine the updated first candidate node set as the target source node set to be distributed.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory in communication with the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the multi-source data processing method of the electric power Internet of Things as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the multi-source data processing method of the electric power Internet of Things as described in any one of claims 1-6 is implemented.

Images