Intelligent labeling method, system and device for power sample data

Abstract

The embodiment of the invention provides an intelligent labeling method, system and device for electric power sample data. The method comprises the steps of obtaining a viewing demand of a user terminal in response to an access instruction of the user terminal; acquiring an image data set of the multi-source power sample; substituting the image data set of the multi-source power sample and a viewing demand of a user terminal into an image processing model, generating an encrypted image data set with a label, and storing the encrypted image data set with the label in a preset historical label database; performing identity verification on the user terminal to obtain an identity verification result; and based on an identity verification result, selectively decrypting the encrypted image data set with the label, and displaying a decrypted part in the image data set with the label on the user terminal. According to the invention, automatic annotation and automatic encryption of the image data are realized, and the security of the image data set is ensured while accurate annotation of the image data set is ensured.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of image processing, in particular to the technical field of image processing in the power industry, and more particularly to a power sample data intelligent labeling method, system and device. BACKGROUND

[0002] In the power industry, image sample data plays an important role in equipment monitoring, fault diagnosis, safety monitoring, etc. Especially in the monitoring of the operating state of the power system and fault diagnosis, intelligent labeling of power sample data is a very important link, which can help managers quickly and accurately identify the cause and location of the fault.

[0003] However, the labeling method in the prior art requires manual labeling of power sample images, which is time-consuming and laborious and prone to errors.

[0004] Therefore, how to realize automatic, intelligent and safe power sample data labeling has become an important research direction in the field. SUMMARY

[0005] The present disclosure provides a power sample data intelligent labeling method, system and device, which solves the technical problem of the labeling method in the prior art requiring manual labeling of power sample images, which is time-consuming and laborious and prone to errors.

[0006] According to a first aspect of the present disclosure, a power sample data intelligent labeling method is provided. The method comprises: in response to an access instruction of a user terminal, obtaining a viewing requirement of the user terminal;

[0007] obtaining an image data set of a multi-source power sample;

[0008] substituting the image data set of the multi-source power sample and the viewing requirement of the user terminal into an image processing model to generate an encrypted image data set with labels, and storing the encrypted image data set with labels in a preset historical labeling database;

[0009] verifying the identity of the user terminal to obtain an identity verification result;

[0010] Based on the identity verification result, the encrypted image data set with labels is selectively decrypted, and the decrypted part of the image data set with labels is displayed on the user terminal.

[0011] As described above, the aspect and any possible implementation, further provides an implementation, wherein the obtaining an image data set of a multi-source power sample comprises:

[0012] acquire power image data of different data sources, wherein the different data sources at least include a power generation side, a power transmission side, a power distribution side, and a user side;

[0013] pre-process the power image data of the different data sources to obtain pre-processed power image data of the different data sources;

[0014] based on the pre-processed power image data of the different data sources, selectively re-execute the acquiring of the power image data of the different data sources and subsequent steps, or, based on the pre-processed power image data of the different data sources, construct an image data set of multi-source power samples.

[0015] As described above, the aspect and any possible implementation manner, further provide an implementation manner, the based on the pre-processed power image data of the different data sources, selectively re-execute the acquiring of the power image data of the different data sources and subsequent steps, or, based on the pre-processed power image data of the different data sources, construct an image data set of multi-source power samples include:

[0016] acquire at least one preset image necessary feature corresponding to the different data sources;

[0017] extract features from the pre-processed power image data of the different data sources to obtain a plurality of image features corresponding to each data source;

[0018] if the plurality of image features corresponding to the data source lacks at least one preset image necessary feature corresponding to the data source, it is determined that the power image data of the data source is missing data, and the acquiring of the power image data of the different data sources and subsequent steps are re-executed;

[0019] otherwise, it is determined that the power image data of the data source is complete data;

[0020] if the data of the power image data of all data sources in the pre-processed power image data of the different data sources is determined to be complete data, the pre-processed power image data of the different data sources is used to construct an image data set of multi-source power samples.

[0021] As described above, the aspect and any possible implementation manner, further provide an implementation manner, the said multi-source power sample image data set and the user terminal viewing requirement are substituted into the image processing model, and the encrypted image data set with label is generated, and the encrypted image data set with label is stored in the preset historical label database include:

[0022] based on the viewing requirement of the user terminal, generate the label data set corresponding to the viewing requirement;

[0023] based on the labeled data set, image data in an image data set of the multi-source power sample is image segmented one by one, and segmented image data is obtained;

[0024] based on the labeled data set, the segmented image data is identified and labeled, and a labeled image data set is generated;

[0025] The labeled image data set is stored, and an encrypted labeled image data set is obtained and stored in a preset historical labeling database.

[0026] As described above, the aspect and any possible implementation, further provides an implementation, the labeled data set corresponding to the viewing requirement of the user terminal is generated based on the viewing requirement of the user terminal, and the implementation comprises:

[0027] based on the viewing requirement of the user terminal, the labeled necessary data set corresponding to the viewing requirement is generated, wherein the labeled necessary data set comprises at least one necessary data source and at least one labeled necessary feature corresponding to each necessary data source;

[0028] based on the viewing requirement of the user terminal, the user portrait corresponding to the user terminal is determined;

[0029] based on the user portrait corresponding to the user terminal, the labeled unnecessary data set corresponding to the user portrait is generated, wherein the labeled unnecessary data set comprises at least one unnecessary data source and at least one labeled unnecessary feature corresponding to each unnecessary data source;

[0030] based on the labeled unnecessary data set corresponding to the user portrait and the labeled necessary data set corresponding to the viewing requirement, data fusion is carried out, and the labeled data set corresponding to the viewing requirement is obtained.

[0031] As described above, the aspect and any possible implementation, further provides an implementation, the labeled data set corresponding to the viewing requirement of the user terminal is generated based on the viewing requirement of the user terminal, and the implementation comprises:

[0032] feature extraction is carried out on image data in the image data set of the multi-source power sample, and a plurality of data features in power image data of each data source in the image data set of the multi-source power sample are obtained;

[0033] based on the labeled data set, the plurality of data features in the power image data of each data source in the image data set of the multi-source power sample are screened, and the plurality of data features in the screened power image data of each data source are obtained;

[0034] Based on the labeled data set, a plurality of data features in the power image data of each data source after screening are preliminarily divided, to obtain the divided power image data of each data source;

[0035] Based on the divided power image data of each data source, the image data in the image data set of the multi-source power sample is sequentially subjected to image segmentation, to obtain the segmented image data;

[0036] The identification and labeling of the segmented image data based on the labeled data set to generate the image data set with labeling includes:

[0037] Based on the labeled data set, the segmented image data is identified, and the identified image of at least one of the segmented image data is framed, to obtain the framed image data;

[0038] The framed image data is labeled to obtain the labeled image data;

[0039] The labeled image data is reviewed, and the labeling content or the framing position in the labeled image data is selectively adjusted;

[0040] To obtain the image data set with labeling.

[0041] As described above, the aspect and any possible implementation, further provides an implementation, the encrypted storage of the image data set with labeling to obtain the encrypted image data set with labeling, and the encrypted image data set with labeling is stored in the preset historical labeling database includes:

[0042] Based on the image data set with labeling, the encryption mode corresponding to at least one of the labeling content or the framing position in the labeled image data in the image data set with labeling is determined;

[0043] Based on each encryption mode corresponding to the image data set with labeling, the image data set with labeling is encrypted to obtain the encrypted image data set with labeling corresponding to each encryption mode;

[0044] Based on the encrypted image data set with labeling corresponding to each encryption mode, the encryption security score corresponding to each encryption mode is obtained;

[0045] Based on each corresponding encryption security score, the encrypted image data set with labeling corresponding to the highest encryption security score of a group of encryption modes is selected as the encrypted image data set with labeling;

[0046] The encrypted image data set with labeling is stored in the preset historical labeling database.

[0047] In addition to the aspects and any possible implementations described above, a further implementation is provided, wherein obtaining the encryption security score corresponding to each encryption mode based on the encrypted and labeled image dataset corresponding to each encryption mode includes:

[0048] Based on the encrypted and labeled image dataset corresponding to each encryption mode, determine the scores of multiple sub-indicators corresponding to each encryption mode. Among them, the types of multiple sub-indicators include at least encryption efficiency, algorithm complexity, key management strength, security and data integrity.

[0049] Based on the scores of multiple sub-indicators corresponding to each encryption mode, an encryption security score is obtained for each encryption mode.

[0050] The encryption security score corresponding to the encryption mode is obtained by the following formula:

[0051]

[0052] Among them, S total This represents the encryption security score, where n represents the total number of sub-indicators (here, n = 5), and i represents the i-th sub-indicator. i W represents the score of the i-th sub-indicator. i This represents the weight of the sub-indicator corresponding to the i-th sub-indicator, where...

[0053] According to a second aspect of this disclosure, an intelligent annotation system for power sample data is provided, used to implement the intelligent annotation method for power sample data as described in the first aspect, comprising:

[0054] The response module is used to respond to the access commands from the user terminal and obtain the viewing requirements of the user terminal.

[0055] The acquisition module is used to acquire image datasets of multi-source power samples;

[0056] The generation module is used to input the image dataset of the multi-source power samples and the viewing requirements of the user terminal into the image processing model, generate an encrypted labeled image dataset, and store the encrypted labeled image dataset in a preset historical label database.

[0057] The verification module is used to authenticate the user terminal and obtain the authentication result;

[0058] The display module is used to selectively decrypt the encrypted labeled image dataset based on the authentication result, and display the decrypted portion of the labeled image dataset on the user terminal.

[0059] According to a third aspect of the present disclosure, an intelligent labeling device for power sample data is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein,

[0060] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of the first aspect.

[0061] The above one or more technical solutions of the present disclosure have at least one or more of the following beneficial effects:

[0062] By responding to the access instruction of the user terminal, the viewing demand of the user terminal is obtained, which realizes that the viewing demand of the user terminal is known according to the access instruction of the user terminal, so as to facilitate image data labeling according to the viewing demand, improve the matching degree of the image data labeling result and the viewing demand of the user terminal, and then obtain the image data set of the multi-source power sample, which realizes real-time acquisition of power image data of different data sources, and the acquired data is substituted into the image processing model to generate an encrypted image data set with labels, and the image data set with labels is stored in a preset historical labeling database, which realizes automatic labeling and automatic encryption of image data, ensures the security and privacy of the data, and then the identity authentication result is obtained by identity authentication of the user terminal, and according to the identity authentication result, the encrypted image data set with labels is selectively decrypted, and the decrypted part in the image data set with labels is displayed on the user terminal, so as to ensure accurate labeling of the image data set while ensuring the security of the image data set, avoiding the technical problems of manual labeling of power sample images in the prior art, which is time-consuming and laborious and prone to errors.

[0063] It should be understood that the content described in the summary section is not intended to limit the key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0064] The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by describing in detail the following embodiments with reference to the attached drawings. The accompanying drawings are used to better understand the present disclosure and do not limit the present disclosure. In the drawings, the same or similar reference numerals refer to the same or similar elements, and:

[0065] Figure 1 A flowchart of a power sample data intelligent labeling method according to an embodiment of the present disclosure is shown;

[0066] Figure 2A block diagram of a power sample data intelligent labeling system according to an embodiment of the present disclosure is shown.

[0067] Figure 3 A block diagram of a power sample data intelligent labeling apparatus according to an embodiment of the present disclosure is shown.

[0068] List of reference signs:

[0069] 200: power sample data intelligent labeling system; 201: response module; 202: acquisition module; 203: generation module; 204: verification module; 205: display module; 300: power sample data intelligent labeling apparatus; 301: calculation unit; 302: read-only memory (ROM); 303: random access memory (RAM); 304: bus; 305: I / O interface; 306: input unit; 307: output unit; 308: storage unit; 309: communication unit. DETAILED DESCRIPTION

[0070] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are some but not all of the embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present disclosure.

[0071] In addition, the term "and / or" herein is only to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, the character " / " herein generally represents an "or" relationship between the front and rear associated objects.

[0072] In the present disclosure, AES represents an advanced encryption standard algorithm; DES represents a data encryption standard algorithm; 3DES represents a triple DES algorithm; IDEA represents an international data encryption algorithm; RSA represents a large data decomposition algorithm; ECC represents an elliptic curve cryptography algorithm; DSA represents a digital signature algorithm; SHA-256 represents a 256-bit hash algorithm; Blum-Goldwasser represents a public key encryption algorithm; and CEILIDH represents a discrete logarithm algorithm.

[0073] Referring to the drawings Figure 1 , Figure 1 A flowchart of a power sample data intelligent labeling method according to an embodiment of the present disclosure is shown. As shown in FIG. 2, the power sample data intelligent labeling method according to an embodiment of the present disclosure includes the following steps. Figure 1As shown, the power sample data intelligent labeling method in the embodiment of the disclosure mainly includes the following steps S101-S105.

[0074] Step S101: In response to the access instruction of the user terminal, the viewing demand of the user terminal is acquired.

[0075] Step S102: The image data set of the multi-source power sample is acquired.

[0076] Specifically, the acquisition of the image data set of the multi-source power sample includes:

[0077] Acquiring power image data of different data sources, wherein the different data sources at least include the power generation side, the power transmission side, the power distribution side and the user side;

[0078] The power image data of the different data sources is preprocessed to obtain preprocessed power image data of the different data sources;

[0079] Based on the preprocessed power image data of the different data sources, selectively re-executing "acquiring power image data of different data sources" and subsequent steps, or using the preprocessed power image data of the different data sources to constitute the image data set of the multi-source power sample.

[0080] Specifically, the preprocessing method of the power image data of the different data sources can be a data preprocessing method in the prior art, wherein the flow of the preprocessing method can include data cleaning, data denoising, removing outliers and data format conversion processing in sequence, so as to ensure the integrity and accuracy of data collection, so that the preprocessed power image data of the different data sources can meet the image processing format requirements of the image processing model, thereby improving the image data processing efficiency of the image processing model. The selection of the preprocessing method here is only exemplary, and in actual testing, those skilled in the art can select according to actual needs, as long as the preprocessed power image data of the different data sources can meet the image processing format requirements of the image processing model, which will not be described here.

[0081] Specifically, the preprocessing method of the power image data of the different data sources can be a data preprocessing method in the prior art, wherein the flow of the preprocessing method can include data cleaning, data denoising, removing outliers and data format conversion processing in sequence, so as to ensure the integrity and accuracy of data collection, so that the preprocessed power image data of the different data sources can meet the image processing format requirements of the image processing model, thereby improving the image data processing efficiency of the image processing model. The selection of the preprocessing method here is only exemplary, and in actual testing, those skilled in the art can select according to actual needs, as long as the preprocessed power image data of the different data sources can meet the image processing format requirements of the image processing model, which will not be described here.

[0082] Acquiring at least one preset image necessary feature corresponding to the different data sources;

[0083] Feature extraction is performed on the preprocessed power image data of the different data sources to obtain a plurality of image features corresponding to each data source;

[0084] If the data source corresponding to the plurality of image features lacks the preset at least one image necessary feature corresponding to the data source, it is determined that the power image data of the data source has data missing, and the steps of "obtaining power image data of different data sources" and the subsequent steps are re-executed;

[0085] Otherwise, it is determined that the power image data of the data source is data complete;

[0086] If the data of the power image data of all data sources in the preprocessed power image data of different data sources is determined to be data complete, the preprocessed power image data of different data sources is used to constitute the image data set of the multi-source power sample.

[0087] Specifically, the feature extraction mode of the preprocessed power image data of different data sources can adopt the feature extraction mode in the prior art, or can extract features from the preprocessed power image data of different data sources through an intelligent learning model. Here, the selection of the feature extraction mode is only exemplary, and in actual testing, a person skilled in the art can select according to actual needs, as long as the feature extraction of the preprocessed power image data of different data sources can be realized, and the plurality of image features corresponding to each data source can be obtained. Here, no further description is given.

[0088] In the above embodiment, by obtaining the power image data of different data sources and preprocessing the same, obtaining the preset at least one image necessary feature corresponding to different data sources, and extracting features from the preprocessed power image data of different data sources, the integrity of the data source corresponding to the plurality of image features is determined, and the integrity of the power image data of the data source is ensured, thereby improving the flexibility and accuracy of subsequent labeling.

[0089] Step S103: The image data set of the multi-source power sample and the viewing requirement of the user terminal are substituted into the image processing model to generate an encrypted image data set with labeling, and the encrypted image data set with labeling is stored in a preset historical labeling database;

[0090] Specifically, the image data set of the multi-source power sample and the viewing requirement of the user terminal are substituted into the image processing model to generate an encrypted image data set with labeling, and the encrypted image data set with labeling is stored in a preset historical labeling database, which includes:

[0091] Based on the viewing requirement of the user terminal, the labeling data set corresponding to the viewing requirement is generated;

[0092] based on the annotation dataset, image data in an image dataset of the multi-source power sample is image segmented one by one to obtain segmented image data;

[0093] based on the annotation dataset, the segmented image data is recognized and annotated to generate an image dataset with annotations;

[0094] The image dataset with annotations is stored in an encrypted manner to obtain an encrypted image dataset with annotations, and the encrypted image dataset with annotations is stored in a preset historical annotation database.

[0095] Specifically, the generation of the annotation dataset corresponding to the viewing requirement of the user terminal based on the viewing requirement of the user terminal includes:

[0096] based on the viewing requirement of the user terminal, an annotation necessary dataset corresponding to the viewing requirement is generated, wherein the annotation necessary dataset includes at least one necessary data source and at least one annotation necessary feature corresponding to each necessary data source;

[0097] based on the viewing requirement of the user terminal, a user portrait corresponding to the user terminal is determined;

[0098] based on the user portrait corresponding to the user terminal, an annotation unnecessary dataset corresponding to the user portrait is generated, wherein the annotation unnecessary dataset includes at least one unnecessary data source and at least one annotation unnecessary feature corresponding to each unnecessary data source;

[0099] based on the annotation unnecessary dataset corresponding to the user portrait and the annotation necessary dataset corresponding to the viewing requirement, data fusion is performed to obtain the annotation dataset corresponding to the viewing requirement.

[0100] Specifically, the image data in the image dataset of the multi-source power sample is image segmented one by one based on the annotation dataset to obtain segmented image data, which includes:

[0101] feature extraction is performed on the image data in the image dataset of the multi-source power sample to obtain a plurality of data features in the power image data of each data source in the image dataset of the multi-source power sample;

[0102] based on the annotation dataset, a plurality of data features in the power image data of each data source in the image dataset of the multi-source power sample are screened to obtain a plurality of data features in the screened power image data of each data source;

[0103] Based on the labeled data set, a plurality of data features in the power image data of each screened data source are preliminarily divided to obtain the divided power image data of each data source;

[0104] Based on the divided power image data of each data source, the image data in the image data set of the multi-source power sample is sequentially subjected to image segmentation to obtain the segmented image data.

[0105] Specifically, the identification and labeling of the segmented image data based on the labeled data set to generate the labeled image data set comprises:

[0106] Based on the labeled data set, the segmented image data is identified, and the identified image of at least one of the segmented image data is framed to obtain the framed image data;

[0107] The framed image data is labeled to obtain the labeled image data;

[0108] The labeled image data is reviewed, and the labeled content or the framing position in the labeled image data is selectively adjusted;

[0109] to obtain the labeled image data set.

[0110] Specifically, the encrypted storage of the labeled image data set to obtain the encrypted labeled image data set, and the encrypted labeled image data set is stored in the preset historical labeling database comprises:

[0111] Based on the labeled image data set, at least one encryption mode corresponding to the labeled content or the framing position in the labeled image data in the labeled image data set is determined;

[0112] Based on each encryption mode corresponding to the labeled image data set, the labeled image data set is encrypted to obtain the encrypted labeled image data set corresponding to each encryption mode;

[0113] Based on the encrypted labeled image data set corresponding to each encryption mode, an encryption security score corresponding to each encryption mode is obtained;

[0114] Based on each corresponding encryption security score, the encrypted labeled image data set corresponding to the highest encryption security score of a group of encryption modes is selected as the encrypted labeled image data set;

[0115] The encrypted image data set with the label is stored in a preset historical label database, and the updated preset historical label database and the update time are synchronized to the cloud, so that the data can be quickly recovered in case of data loss or damage.

[0116] Specifically, the different encryption algorithms correspond to different encryption modes, and the encryption algorithms can include AES, DES, 3DES, IDEA, RSA, ECC, DSA, SHA-256, Blum-Goldwasser, and CEILIDH. The selection of the encryption algorithm is only an example, and the person skilled in the art can select according to the actual needs in the actual test. As long as the encryption mode corresponding to the label content or the frame selection position in the labeled image data set can be determined according to the labeled image data set, and the labeled image data set is encrypted according to the determined encryption mode, the encryption algorithm is not described here.

[0117] Specifically, the encrypted image data set corresponding to each encryption mode is obtained based on the encrypted image data set corresponding to each encryption mode.

[0118] Based on the encrypted image data set corresponding to each encryption mode, the sub-index score corresponding to each encryption mode is determined, and the types of the sub-indices include at least encryption efficiency, algorithm complexity, key management strength, security, and data integrity.

[0119] Based on the sub-index score corresponding to each encryption mode, the encryption security score corresponding to each encryption mode is obtained.

[0120] The encryption security score corresponding to the encryption mode is obtained by the following formula:

[0121]

[0122] S = ∑ i = 1 n W i * A i total represents the encryption security score, n represents the total number of sub-indices, here n = 5, i represents the i-th sub-index, A i represents the sub-index score of the i-th sub-index, W i represents the sub-index weight corresponding to the i-th sub-index, and

[0123] Specifically, the sub-index scores are obtained by the following formula:

[0124]

[0125] A1 represents the sub-index score of encryption efficiency, e j A1 represents the jth sub-index score of encryption efficiency, where j = 1, 2, …, m1, A1 represents the jth sub-index score of encryption efficiency, where j = 1, 2, …, m1,

[0126] A2 represents the sub-index score of algorithm complexity, c k A2 represents the kth sub-index score of algorithm complexity, where k = 1, 2, …, m2, f c A2 represents the kth sub-index score of algorithm complexity, where k = 1, 2, …, m2, f k A2 represents the kth sub-index score of algorithm complexity, where k = 1, 2, …, m2, f A2 represents the kth sub-index score of algorithm complexity, where k = 1, 2, …, m2, f

[0127] A3 represents the sub-index score of key management strength, k l A3 represents the lth sub-index score of key management strength, where l = 1, 2, …, m3.

[0128] A4 represents the sub-index score of security, S h A4 represents the hth sub-index score of security, where h = 1, 2, …, m4.

[0129] A5 represents the sub-index score of data integrity, d p A5 represents the two sub-index scores of data integrity. q A5 represents the two sub-index scores of data integrity.

[0130] In the above embodiment, in the model processing, the viewing demand of the user terminal is used to generate the corresponding annotation data set, thereby realizing the preliminary confirmation of the annotation demand. Then, the image data in the image data set of the multi-source power sample is sequentially segmented through the annotation data set, thereby obtaining the segmented image data, realizing the division of the image data in the image data set, and further improving the annotation accuracy. Then, the segmented image data is identified and annotated according to the annotation data set, thereby generating an image data set with annotations, improving the annotation precision and efficiency. Then, the annotated image data is rechecked, and the annotation content or the frame selection position in the annotated image data is selectively adjusted, thereby realizing the adaptive optimization of the annotation result, further improving the intelligent annotation capability of the model. Then, the image data set with annotations is encrypted to obtain an encrypted image data set with annotations, thereby improving the security of the image data set with annotations. Finally, the encrypted image data set with annotations is stored in a preset historical annotation database, so that the image data can be quickly recovered when the data is lost or damaged, thereby improving the intelligent processing capability of the model for image data annotation.

[0131] Step S104: authenticating the user terminal to obtain an authentication result;

[0132] Specifically, the authentication manner for authenticating the user terminal can adopt an authentication manner in the prior art. The selection of the authentication manner is only exemplary and illustrative. In actual tests, those skilled in the art can select according to actual needs, as long as the authentication of the user terminal can be implemented to obtain the authentication result. Details are not described herein.

[0133] Step S105: selectively decrypting the encrypted image data set with labels based on the authentication result, and displaying the decrypted part of the image data set with labels on the user terminal, so as to ensure accurate labeling of the image data set and security of the image data set.

[0134] Specifically, the selectively decrypting the encrypted image data set with labels based on the authentication result, and displaying the decrypted part of the image data set with labels on the user terminal comprises the following steps.

[0135] If the authentication result is passed, the encrypted image data set with labels is selectively decrypted based on the viewing permission of the user corresponding to the user terminal, and the decrypted part of the image data set with labels is displayed on the user terminal.

[0136] If the authentication result is failed, the user terminal is fed back the authentication result of authentication failure, and the record of the attempt to view the user terminal is recorded.

[0137] In the above embodiment, by authenticating the user terminal and selectively decrypting the encrypted image data set with labels based on the authentication result, the access and operation permission of the labeled data is limited, the data leakage and abuse are prevented, and the security of the image data set is improved.

[0138] According to the embodiments of the present disclosure, the following technical effects are achieved.

[0139] By responding to the access instruction of the user terminal, the viewing demand of the user terminal is obtained, the viewing demand of the user terminal is known according to the access instruction of the user terminal, so that the image data labeling is carried out according to the viewing demand, the matching degree of the image data labeling result and the viewing demand of the user terminal is improved, the image data set of the multi-source power sample is obtained, the real-time acquisition of the power image data of different data sources is realized, and the acquired data is substituted into the image processing model, the encrypted image data set with labeling is generated, and the encrypted image data set with labeling is stored in the preset historical labeling database, the automatic labeling of the image data and the automatic encryption of the image data are realized, the safety and privacy of the data are ensured, the identity authentication result is obtained by identity authentication of the user terminal, and the encrypted image data set with labeling is selectively decrypted according to the identity authentication result, and the decrypted part in the image data set with labeling is displayed on the user terminal, so that the image data set is accurately labeled, and the safety of the image data set is ensured.

[0140] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the present disclosure is not limited to the action sequence described, because according to the present disclosure, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0141] The above is the introduction of the method embodiment, and the scheme of the present disclosure will be further described through the system embodiment.

[0142] Figure 2 A block diagram of a power sample data intelligent labeling system according to an embodiment of the present disclosure is shown. As Figure 2 The power sample data intelligent labeling system 200 shown in the figure includes:

[0143] The response module 201 is configured to obtain the viewing demand of the user terminal in response to the access instruction of the user terminal.

[0144] The acquisition module 202 is configured to acquire the image data set of the multi-source power sample.

[0145] The generation module 203 is configured to substitute the image data set of the multi-source power sample and the viewing demand of the user terminal into an image processing model, generate an encrypted image data set with labeling, and store the encrypted image data set with labeling in a preset historical labeling database.

[0146] The verification module 204 is configured to perform identity authentication on the user terminal to obtain an identity authentication result.

[0147] The display module 205 is configured to selectively decrypt the encrypted image dataset with annotations based on the authentication result, and display the decrypted part of the image dataset with annotations to the user terminal.

[0148] Intelligent labeling device for power sample data

[0149] Intelligent labeling device for power sample data

[0150] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described modules can refer to the corresponding process in the foregoing method embodiments, which will not be described herein.

[0151] According to embodiments of the present disclosure, the present disclosure further provides an intelligent labeling device for power sample data and a readable storage medium.

[0152] Figure 3 A block diagram of an intelligent labeling device for power sample data according to embodiments of the present disclosure is shown. The intelligent labeling device for power sample data 300 is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The intelligent labeling device for power sample data 300 can also represent various forms of mobile devices such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present disclosure described and / or claimed in this document.

[0153] As shown in Figure 3 The intelligent labeling device for power sample data 300 includes a computing unit 301 that can perform various appropriate actions and processes according to computer programs stored in a read-only memory (ROM) 302 or loaded into a random access memory (RAM) 303 from a storage unit 308. Various programs and data required for the operation of the intelligent labeling device for power sample data 300 can also be stored in the RAM 303. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. An I / O interface 305 is also connected to the bus 304.

[0154] The plurality of components in the power sample data intelligent labeling apparatus 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a magnetic disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the power sample data intelligent labeling apparatus 300 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0155] The computing unit 301 can be various general and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 301 performs various methods and processes described above, such as a power sample data intelligent labeling method. For example, in some embodiments, a power sample data intelligent labeling method 100 can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed on the power sample data intelligent labeling apparatus 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of a power sample data intelligent labeling method described above can be performed. Alternatively, in other embodiments, the computing unit 301 can be configured to perform the power sample data intelligent labeling method by other any appropriate means, such as by means of firmware.

[0156] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0157] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or block diagrams. The program code can be embodied on one or more non-transitory computer readable media that can be read by a machine, such as a general purpose computer, a special purpose computer, or other programmable data processing apparatus. The program code can be executed by a machine, such as a general purpose computer, a special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the machine, produces the functions / operations specified in the flowcharts and / or block diagrams. The program code can execute directly on the machine, partially on the machine, partially on one or more other machines connected to the machine through a network, and / or entirely on one or more other machines.

[0158] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores program code for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0159] It should be noted that the present disclosure also provides a non-transitory computer readable storage medium storing computer instructions, wherein the computer instructions are used to make a computer execute an intelligent labeling method of power sample data, and achieve the corresponding technical effects of the method executed by the embodiments of the present disclosure. For brevity, the description will not be repeated here.

[0160] In addition, the present disclosure also provides a computer program product, which comprises a computer program, and the computer program, when executed by a processor, implements the above-mentioned intelligent labeling method of power sample data.

[0161] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0162] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can 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), and the Internet.

[0163] The computer system can include clients and servers. This relationship can be. The servers are typically remote from the clients with the interactions between them occurring over a communication network. The relationship between a client and a server is one of client-server. The server can be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

[0164] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be performed in parallel, in series, or in a different order, without departing from the desired results of the technology disclosed in the present disclosure, and are not limited herein.

[0165] The specific embodiments described above are not intended to be limiting. One of skill in the art will understand that various modifications, combinations, sub-combinations, and alternatives can be made to the specific embodiments described above without departing from the spirit and principles of this disclosure. Any further modifications, changes, or improvements that come within the spirit and principles of the disclosure are intended to fall within the scope of the disclosure.

Claims

1. An intelligent labeling method for power sample data, characterized in that, The method comprises the following steps: in response to an access instruction of a user terminal, obtaining a viewing requirement of the user terminal; obtaining an image data set of a multi-source power sample; substituting the image data set of the multi-source power sample and the viewing requirement of the user terminal into an image processing model to generate an encrypted image data set with labels, and storing the encrypted image data set with labels in a preset historical labeling database; verifying the identity of the user terminal to obtain an identity verification result; based on the identity verification result, selectively decrypting the encrypted image data set with labels, and displaying the decrypted part of the image data set with labels on the user terminal.

2. The method of claim 1, wherein, The method comprises the following steps: obtaining power image data of different data sources, wherein the different data sources at least include power generation side, power transmission side, power distribution side and user side; preprocessing the power image data of different data sources to obtain preprocessed power image data of different data sources; based on the preprocessed power image data of different data sources, selectively re-executing "obtaining power image data of different data sources" and subsequent steps, or using the preprocessed power image data of different data sources to constitute the image data set of the multi-source power sample.

3. The method of claim 2, wherein, The method comprises the following steps: obtaining at least one preset image necessary feature corresponding to each data source; extracting features from the preprocessed power image data of different data sources to obtain a plurality of image features corresponding to each data source; if the plurality of image features corresponding to the data source are missing the at least one preset image necessary feature corresponding to the data source, it is determined that the power image data of the data source is missing data, and the "obtaining power image data of different data sources" and subsequent steps are re-executed; otherwise, it is determined that the power image data of the data source is complete data; if the data of the power image data of all data sources in the preprocessed power image data of different data sources is determined to be complete data, the preprocessed power image data of different data sources is used to constitute the image data set of the multi-source power sample.

4. The method of claim 3, wherein, The method comprises the following steps: based on the viewing requirement of the user terminal, generating a labeling data set corresponding to the viewing requirement; based on the labeling data set, image segmentation is performed on the image data in the image data set of the multi-source power sample one by one to obtain segmented image data; based on the labeling data set, the segmented image data is identified and labeled to generate an image data set with labels; The image data set with annotations is stored in an encrypted manner to obtain an encrypted image data set with annotations, and the encrypted image data set with annotations is stored in a preset historical annotation database.

5. The method of claim 4, wherein, The annotation data set corresponding to the viewing requirement of the user terminal is generated based on the viewing requirement of the user terminal, and includes: The annotation necessary data set corresponding to the viewing requirement of the user terminal is generated based on the viewing requirement of the user terminal, wherein the annotation necessary data set at least includes at least one necessary data source and at least one annotation necessary feature corresponding to each necessary data source; The user portrait corresponding to the user terminal is determined based on the viewing requirement of the user terminal; The annotation unnecessary data set corresponding to the user portrait is generated based on the user portrait corresponding to the user terminal, wherein the annotation unnecessary data set at least includes at least one unnecessary data source and at least one annotation unnecessary feature corresponding to each unnecessary data source; The annotation data set corresponding to the viewing requirement is obtained by data fusion based on the annotation unnecessary data set corresponding to the user portrait and the annotation necessary data set corresponding to the viewing requirement.

6. The method of claim 5, wherein, The image data in the image data set of the multi-source power sample is segmented one by one based on the annotation data set to obtain segmented image data, and includes: The power image data of each data source in the image data set of the multi-source power sample is extracted based on the annotation data set to obtain a plurality of data features in the power image data of each data source in the image data set of the multi-source power sample; The plurality of data features in the power image data of each data source after screening are obtained by screening the plurality of data features in the power image data of each data source in the image data set of the multi-source power sample based on the annotation data set; The power image data of each data source after division is obtained by preliminarily dividing the plurality of data features in the power image data of each data source after screening based on the annotation data set; The image data in the image data set of the multi-source power sample is segmented one by one based on the power image data of each data source after division to obtain segmented image data; The segmented image data is recognized and annotated based on the annotation data set to generate an image data set with annotations, and includes: The segmented image data is recognized based on the annotation data set, and at least one recognized image in each segmented image data is framed to obtain framed image data; The framed image data is annotated to obtain annotated image data; The annotated image data is reviewed, and the annotation content or the framing position in the annotated image data is selectively adjusted; An image data set with annotations is obtained.

7. The method of claim 6, wherein, The image data set with annotations is stored in an encrypted manner to obtain an encrypted image data set with annotations, and the encrypted image data set with annotations is stored in a preset historical annotation database, and includes: determine, based on the annotated image dataset, at least one encryption mode corresponding to the annotation or the bounding box position in the annotated image data in the annotated image dataset; encrypt, based on each encryption mode corresponding to the annotated image dataset, the annotated image dataset to obtain an encrypted annotated image dataset corresponding to each encryption mode; obtain, based on the encrypted annotated image dataset corresponding to each encryption mode, an encryption security score corresponding to each encryption mode; select, based on each corresponding encryption security score, an encrypted annotated image dataset corresponding to a set of encryption modes with the highest encryption security score as the encrypted annotated image dataset; store the encrypted annotated image dataset in a preset historical annotation database.

8. The method of claim 7, wherein, The encryption security score corresponding to each encryption mode is obtained based on the encrypted annotated image dataset corresponding to each encryption mode, and includes: determine, based on the encrypted annotated image dataset corresponding to each encryption mode, a plurality of sub-index scores corresponding to each encryption mode, wherein the types of the plurality of sub-indices include at least encryption efficiency, algorithm complexity, key management strength, security, and data integrity; obtain, based on the plurality of sub-index scores corresponding to each encryption mode, an encryption security score corresponding to each encryption mode; wherein the encryption security score corresponding to the encryption mode is obtained by the following formula: wherein S total represents the encryption security score, n represents the total number of sub-indicators, n = 5 in this case, i represents the i-th sub-indicator, A i represents the sub-indicator score of the i-th sub-indicator, W i represents the sub-indicator weight corresponding to the i-th sub-indicator, wherein, 9. An intelligent labeling system for power sample data, used to implement the intelligent labeling method for power sample data according to any one of claims 1-8. includes: a response module configured to obtain a viewing requirement of a user terminal in response to an access instruction of the user terminal; an acquisition module configured to acquire an image dataset of a multi-source power sample; a generation module configured to substitute the image dataset of the multi-source power sample and the viewing requirement of the user terminal into an image processing model to generate an encrypted annotated image dataset, and store the encrypted annotated image dataset in a preset historical annotation database; a verification module configured to perform identity verification on the user terminal to obtain an identity verification result; a display module configured to selectively decrypt the encrypted annotated image dataset based on the identity verification result, and display the decrypted part of the annotated image dataset on the user terminal.

10. An intelligent annotation device for power sample data, comprising: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

Images