A method for quickly verifying user data on a smart packaging interactive platform

Abstract

The present invention relates to the technical field of user data verification, and specifically to a method for quickly verifying user data of a smart application interactive platform. The present invention first obtains the application data of the current user and verified historical users, and obtains the electricity consumption data of historical users; further analyzes the similarity characteristics of the power equipment information, and obtains the first abnormality degree from the similarity angle of the power equipment information of the current user and the adjacent historical users; further obtains the second abnormality degree from the distribution and aggregation angle of the current user and similar historical users; finally, comprehensively combines the first abnormality degree and the second abnormality degree to quickly verify the application data of the current user. The present invention performs abnormal analysis on the application data of the current user with the help of historical data, evaluates the abnormal characteristics of the current user's application data from the similarity angle of the power equipment information and the distribution and aggregation angle of similar users, quickly verifies the application data of the current user, reduces the difficulty of data verification and improves the verification efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of user data verification, and in particular to a method for quickly verifying user data of a smart application interaction platform. Background Art

[0002] The power grid smart application interactive platform is a digitalized platform that aims to solve the problems of multiple submissions and complicated application procedures in the traditional electricity user application process. By allowing users to submit application materials online, it can effectively avoid the back and forth due to incomplete or incorrect information. The data verification submitted by users is a key link, which needs to ensure the accuracy, effectiveness and timeliness of the application information, thereby optimizing the service level and improving the user experience.

[0003] The existing verification of digital information submitted by users usually uses set input rules to complete preliminary verification, such as data format, range limit, etc. The process of setting the rules requires a lot of background research to determine the value range and format of different data, which makes the setting process cumbersome, complicated and time-consuming. Moreover, in the subsequent verification, a complete data character comparison is usually required to determine the verification result, resulting in low verification efficiency. And it is usually accompanied by manual review, which further reduces the efficiency of intelligent registration. Summary of the invention

[0004] In order to solve the technical problems of high difficulty and low efficiency of existing data verification, the purpose of the present invention is to provide a method for quickly verifying user data of a smart application interaction platform. The technical solution adopted is as follows:

[0005] A method for quickly verifying user data of a smart application interaction platform, the method comprising:

[0006] Obtain application data of the current user and verified historical users; the application data at least includes address information and power equipment information of the application; obtain power consumption data of verified historical users;

[0007] According to the similar features of the power equipment information of the current user and the power equipment information of the historical users, the device similarity parameters corresponding to the current user and each historical user are obtained; according to the address information of the current user and the address information of the historical users, the neighboring historical users corresponding to the current user when applying for installation are obtained; according to the similar features of the power usage data between the neighboring historical users, the degree of industrial agglomeration is obtained; according to the device similarity parameters corresponding to the current user and each of the neighboring historical users, combined with the degree of industrial agglomeration, the first abnormality degree of the application data of the current user is obtained;

[0008] Filter out similar historical users according to the device similarity parameters corresponding to the current user and each historical user; analyze the distribution and aggregation characteristics of the current user and the similar historical users according to the address information to obtain the second abnormality degree of the application data of the current user;

[0009] The application data of the current user is quickly verified according to the first abnormality degree and the second abnormality degree corresponding to the current user.

[0010] Furthermore, the method for obtaining the device similarity parameters includes:

[0011] The electric device information is segmented to obtain a similarity coefficient between a segmentation set of the electric device information of the current user and a segmentation set of the electric device information of a historical user as a device similarity parameter between the current user and the corresponding historical user.

[0012] Furthermore, the method for obtaining the degree of industrial agglomeration includes:

[0013] Obtaining the power consumption data of the preset time domain neighborhood of the neighboring historical users when the current user applies for the subscription, as the power consumption data to be analyzed of the neighboring historical users; segmenting each of the power consumption data to be analyzed to obtain segmented power consumption data;

[0014] According to the fluctuation similarity characteristics of the segmented power consumption data of all the same order of any two of the adjacent historical users, obtaining power consumption similarity parameters corresponding to the two adjacent historical users;

[0015] The degree of industrial agglomeration is obtained according to the electricity consumption similarity parameters among all the neighboring historical users; the electricity consumption similarity parameters are positively correlated with the degree of industrial agglomeration.

[0016] Furthermore, the method for obtaining the first abnormality degree includes:

[0017] According to the device similarity parameters corresponding to the current user and all the neighboring historical users, the abnormality degree of the device information of the current user is obtained; the device similarity parameters are negatively correlated with the abnormality degree of the device information;

[0018] The first abnormality degree of the current user is obtained according to the abnormality degree of the device information and the industrial concentration degree of the current user; the abnormality degree of the device information and the industrial concentration degree are both positively correlated with the first abnormality degree.

[0019] Furthermore, the method for obtaining similar historical users includes:

[0020] When the device similarity parameter corresponding to the historical user and the current user is greater than a preset similarity threshold, the corresponding historical user is determined as a similar historical user.

[0021] Furthermore, the method for obtaining the second abnormality degree includes:

[0022] Constructing a two-dimensional coordinate system according to the geographic horizontal plane, analyzing the address information based on a geographic information system, and mapping the address of the current user and the addresses of the similar historical users into the two-dimensional coordinate system;

[0023] In the two-dimensional coordinate system, the distribution and clustering characteristics of the current user and the similar historical users are analyzed to obtain the second abnormality degree of the application data of the current user.

[0024] Furthermore, the method of analyzing the distribution and aggregation characteristics of the current user and the similar historical users in the two-dimensional coordinate system to obtain the second abnormality degree of the application data of the current user includes:

[0025] The addresses of users in the two-dimensional coordinate system are clustered; the second abnormality degree is obtained according to the distance between the address of the current user and the cluster center of the cluster to which it belongs; the distance between the address of the current user and the cluster center of the cluster to which it belongs is positively correlated with the second abnormality degree.

[0026] Furthermore, the method for quickly verifying the application data of the current user according to the first abnormality degree and the second abnormality degree corresponding to the current user includes:

[0027] According to the similar features of the first abnormality degree and the second abnormality degree corresponding to the current user, the verification accuracy of the application data of the current user is obtained in combination with the first abnormality degree and the second abnormality degree; the similar features of the first abnormality degree and the second abnormality degree are positively correlated with the verification accuracy; the first abnormality degree and the second abnormality degree are both negatively correlated with the verification accuracy;

[0028] The application data also includes the user's ID number code; the verification result is obtained based on the verification accuracy of the application data of the current user and the accuracy of the ID number code.

[0029] Furthermore, the method for obtaining the verification result according to the verification accuracy of the application data of the current user and the certificate number code includes:

[0030] When the verification accuracy is greater than a preset verification threshold, the preliminary verification is determined to have passed; the ID number code of the current user is compared with the public network system data and the difference characters are extracted to obtain the proportion of the difference characters in the ID number code; when the proportion corresponding to the difference characters is less than a preset proportion threshold, the final verification is determined to have passed;

[0031] When the application data fails the preliminary verification or the final verification, the verification result is obtained through manual verification.

[0032] Furthermore, the method for obtaining neighboring historical users includes:

[0033] Analyze the address information based on the geographic information system to locate the addresses of the current user and historical users; take the address of the current user as the center of the circle and the preset base value as the radius, and take the historical users contained in the circle as neighboring historical users;

[0034] When the number of neighboring historical users corresponding to the current user is less than a preset neighboring number threshold, the preset base value is increased with a preset growth step until the number of historical users included in the circle for the first time is greater than or equal to the preset neighboring number threshold.

[0035] The present invention has the following beneficial effects:

[0036] The present invention first obtains the application data of the current user and the verified historical users, as well as the electricity consumption data of the historical users, to avoid the cumbersome and complicated setting process of the verification rules, and uses the historical data to analyze the abnormal characteristics of the application data of the current user; further obtains the device similarity parameters corresponding to the current user and each historical user, characterizes the similar characteristics of the current user's electricity consumption equipment information and the electricity consumption equipment information of the historical users, so as to facilitate the subsequent analysis of the similar characteristics of the current user and the neighboring historical users in the electricity consumption equipment information; further obtains the neighboring historical users corresponding to the current user's application for installation, so as to facilitate the subsequent analysis of the industrial cluster characteristics around the current user and ... The similar characteristics of electricity consumption data between historical users are used to obtain the degree of industrial agglomeration, and the first abnormal degree of the current user's application data is obtained by combining the equipment similarity parameters corresponding to the current user and each neighboring historical user, and the industrial agglomeration characteristics and the difference characteristics of the power consumption equipment information are combined to more accurately evaluate the abnormal situation of the current user's application data; further screen out similar historical users, analyze the distribution and aggregation characteristics of the current user and similar historical users according to the address information, obtain the second abnormal degree of the current user's application data, and obtain more evaluation basis from the distribution and aggregation angle of the current user and similar historical users to improve the accuracy of rapid verification; finally, according to the first abnormal degree and the second abnormal degree corresponding to the current user, the application data of the current user is quickly verified. The present invention uses historical data to perform abnormal analysis on the application data of the current user, evaluates the abnormal characteristics of the current user's application data from the similar angle of power consumption equipment information and the distribution and aggregation angle of similar users, and quickly verifies the application data of the current user, reducing the difficulty of data verification and improving the verification efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. 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 paying creative work.

[0038] Figure 1 A flowchart of a method for quickly verifying user data of a smart application interaction platform provided by an embodiment of the present invention;

[0039] Figure 2 A flowchart of a method for obtaining the degree of industrial agglomeration provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation method, structure, features and effects of a method for rapid verification of user data of a smart package interaction platform proposed by the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0041] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0042] The following is a detailed description of a method for quickly verifying user data on a smart application interaction platform provided by the present invention in conjunction with the accompanying drawings.

[0043] See also Figure 1 , which shows a flow chart of a method for quickly verifying user data of a smart application interaction platform provided by an embodiment of the present invention, specifically comprising:

[0044] Step S1: Obtain application data of the current user and verified historical users; the application data at least includes address information and power equipment information of the application; obtain power consumption data of verified historical users.

[0045] In an embodiment of the present invention, in order to avoid the cumbersome and complicated setting process of the verification rules, a database is constructed with the help of historical application data that has passed manual verification, and the abnormal characteristics of the current user's application data are analyzed with the help of historical data; taking into account regional planning and industrial clustering, similar power-consuming equipment exists in the same planning area. In order to utilize this feature, the application data at least includes the address information and power-consuming equipment information of the application, and the power consumption data of historical users is obtained at the same time to provide more data analysis angles; therefore, the application data of the current user and the verified historical users' applications are first obtained; the application data at least includes the address information and power-consuming equipment information of the application; the power consumption data of historical users is obtained to provide a basis for subsequent analysis.

[0046] It should be noted that the application data can be obtained through the application form and application materials entered by the user into the smart application interactive platform, and the application data of historical users can be obtained by scanning the application form and application materials submitted by historical users.

[0047] It should be noted that, in one embodiment of the present invention, taking into account that the same user may have multiple industries and multiple application records, the historical application data of this user can also be used as a basis for analyzing the current application data. Therefore, a unique application number is generated for each application by the user to represent the applicant user. Specifically, the application number can be generated by other methods such as the existing UUID (Universally Unique Identifier) ​​generation method.

[0048] Step S2: Based on the similar features of the current user's power usage equipment information and the power usage equipment information of historical users, obtain the equipment similarity parameters corresponding to the current user and each historical user; based on the current user's address information and the address information of historical users, obtain the neighboring historical users corresponding to the current user when applying for installation; based on the similar features of the power usage data between neighboring historical users, obtain the degree of industrial agglomeration; based on the equipment similarity parameters corresponding to the current user and each neighboring historical user, combined with the degree of industrial agglomeration, obtain the first abnormality degree of the current user's application data.

[0049] Considering that the more similar the current user's power usage equipment information is to that of historical users, the more normal the current user's power usage equipment information is, and the more conventional the power usage equipment reported by the current user is, the device similarity parameters corresponding to the current user and each historical user are obtained based on the similarity characteristics of the current user's power usage equipment information and the historical users' power usage equipment information, so as to provide a basis for subsequent analysis of the similarity characteristics of the current user and the neighboring historical users in power usage equipment information and obtaining the first abnormality degree.

[0050] Preferably, in one embodiment of the present invention, considering that the electric equipment information usually contains a large amount of complex information such as professional terms, models, specifications, etc., which cannot be directly recognized and processed by computers, it is necessary to first perform word segmentation processing on the electric equipment information, and continuous text can be cut into words or phrases with independent meanings, so as to better understand and process the information; considering the similarity coefficient between the word segmentation sets of two electric equipment information, the similarity features between the two electric equipment information can be concisely and accurately represented, so the similarity coefficient between the word segmentation set of the current user's electric equipment information and the word segmentation set of the historical user's electric equipment information is obtained as the equipment similarity parameter of the current user and the corresponding historical user.

[0051] As an example, word segmentation processing is performed using the LAC (Lexical Analysis of Chinese) algorithm, and the Jaccard similarity coefficient between the word segmentation set of the current user's power equipment information and the word segmentation set of the historical user's power equipment information is calculated as the device similarity parameter between the current user and the corresponding historical user.

[0052] It should be noted that the LAC algorithm and the Jaccard similarity coefficient are both existing technologies. In other embodiments of the present invention, the implementer may also use the existing Jieba word segmentation method to perform word segmentation and obtain device similarity parameters.

[0053] In an area with dense electricity consumption, the types of electricity consumption of users are basically the same. If the difference between the electricity equipment information of the current user and other users in the neighboring area is greater, it means that the user's electricity equipment information is more likely to be abnormal, and the possibility of data anomaly is higher. At the same time, it is also necessary to consider the concentration of industries in the neighboring area to determine the degree of influence of differences on the possibility of data anomaly. The higher the concentration of industries in the neighboring area, the higher the accuracy of differences in showing the possibility of data anomaly. In general, the more concentrated the industry is, the more similar the changes in user electricity data are. For example, the electricity consumption in ordinary commercial areas is generally higher in the afternoon and lower in the early morning. Therefore, according to the address information of the current user and the address information of historical users, the corresponding neighboring historical users when the current user applies for installation are obtained; according to the similar characteristics of the electricity data between neighboring historical users, the degree of industrial concentration is obtained, so as to prepare for the subsequent comprehensive industrial concentration characteristics and the difference characteristics of electricity equipment information, more accurately evaluate the abnormal situation of the current user's application data, and conduct rapid verification.

[0054] Preferably, in one embodiment of the present invention, address information is analyzed based on a Geographic Information System (GIS) to locate the addresses of the current user and historical users; the address of the current user is taken as the center of a circle and a preset base value is taken as the radius, and the historical users included in the circle are taken as neighboring historical users;

[0055] Considering that when the sample size of neighboring historical users is too small, it is not conducive to highlighting the abnormal characteristics of the current user, so when the number of neighboring historical users corresponding to the current user is less than the preset neighboring number threshold, the preset basic value is increased with a preset growth step until the number of historical users included in the circle for the first time is greater than or equal to the preset neighboring number threshold.

[0056] As an example, the preset base value is 100 meters, the preset growth step is 10 meters, the preset neighbor quantity threshold is 10, the current user's address is used as the center of the circle, and the preset base value is used as the radius. The preset base value is gradually increased, that is, the radius is gradually expanded until the number of historical users in the circle reaches or exceeds 10 for the first time; if the circle with the preset base value as the radius already contains 10 or more historical users, there is no need to increase the preset base value.

[0057] In other embodiments of the present invention, the implementer may set other shapes such as a square to obtain neighboring historical users, and may also set other preset basic values, preset growth steps, and preset neighbor quantity thresholds.

[0058] It should be noted that geographic information system is already an existing technology. In other embodiments of the present invention, the implementer can also use other positioning systems such as Beidou positioning system to analyze address information and locate the addresses of current users and historical users.

[0059] Preferably, in one embodiment of the present invention, the method for obtaining the degree of industrial agglomeration includes: Figure 2 , which shows a flow chart of a method for obtaining the degree of industrial agglomeration provided by an embodiment of the present invention, specifically comprising:

[0060] Step S201: obtaining electricity consumption data of a preset time domain neighborhood of neighboring historical users when the current user applies for subscription, as the electricity consumption data to be analyzed of the neighboring historical users; segmenting each electricity consumption data to be analyzed in the same way to obtain segmented electricity consumption data.

[0061] In order to limit the analysis scope of electricity consumption data, the electricity consumption data of the preset time domain neighborhood of the neighboring historical users when the current user applies for the subscription is obtained as the electricity consumption data to be analyzed of the neighboring historical users. As an example, the preset time domain neighborhood ends at the time point when the current user applies for the subscription and has a length of 24 hours, that is, the electricity consumption data of the neighboring historical users in the last 24 hours when the current user applies for the subscription is obtained as the electricity consumption data to be analyzed;

[0062] Considering that segmenting the electricity consumption data is more conducive to capturing the local fluctuation characteristics of the electricity consumption data and more conducive to analyzing the similar characteristics between the electricity consumption data of different users, each electricity consumption data to be analyzed is segmented to obtain segmented electricity consumption data.

[0063] As an example, the 24-hour electricity consumption data to be analyzed is equally divided into 24 segments, and the length of each segment of electricity consumption data is 1 hour; the electricity consumption data is specifically electricity power data, and the collection frequency is once per second.

[0064] In other embodiments of the present invention, the implementer may set other preset time domain neighborhood lengths, set other segmentation schemes and collection frequencies; and may also collect current, voltage and other electricity consumption data, and classify and compare them in subsequent comparative analysis.

[0065] Step S202: according to the fluctuation similarity characteristics of all the segmented power consumption data of the same order of any two adjacent historical users, obtain the power consumption similarity parameters corresponding to the two adjacent historical users.

[0066] Considering that the more similar the fluctuations of all segmented electricity consumption data of the same order of two neighboring historical users are, the more similar the electricity consumption characteristics of the corresponding two neighboring historical users are, so based on the fluctuation similarity characteristics of all segmented electricity consumption data of the same order of any two neighboring historical users, the electricity consumption similarity parameters of the corresponding two neighboring historical users are obtained.

[0067] As an example, considering the different sizes of different users, the numerical range of power consumption of electrical equipment varies. In order to analyze the similarity of power consumption data changes, the power consumption data to be analyzed for each adjacent historical user is normalized to the maximum and minimum values, and the power consumption data is preprocessed. Considering that the more similar the change amplitudes between segmented power consumption data are, the more similar the fluctuations of segmented power consumption data are, so the calculation formula of power consumption similarity parameters is constructed:

[0068] ;

[0069] in, and is the sequence number of the neighboring historical user, ; Indicates neighboring historical users and Similar electricity consumption parameters corresponding to adjacent historical users; It is the serial number of the segmented power consumption data; is the number of segmented electricity consumption data; Expressed as a natural constant The exponential function with base ; Indicates neighboring historical users The variation range of the segment power consumption data is the data range of the segment power consumption data; Indicates neighboring historical users The variation range of the segment-by-segment electricity consumption data; Indicates taking the absolute value.

[0070] In the calculation formula of electrical similarity parameters, The range of the segmented power consumption data is used to represent the variation of the segmented power consumption data. The absolute value of the difference between the segmented power consumption data is used to represent the difference between the segmented power consumption data. Then, negative correlation mapping is performed to represent the similarity of the fluctuation characteristics of the variation between the segmented power consumption data. The smaller it is, the smaller the difference in the amplitude of change between the segmented electricity consumption data is, the greater the fluctuation similarity feature is, and the larger the electricity consumption similarity parameter is.

[0071] It should be noted that the segmented power consumption data is sorted according to the collection time of the first power consumption data in the segment. In other embodiments of the present invention, the implementer may also normalize the segmented power consumption data, fit the curve of the segmented power consumption data, and analyze the similarity between the segmented power consumption data curves, such as obtaining the DTW distance between two segmented power consumption data curves through the Dynamic Time Warping (DTW) algorithm. The smaller the DTW distance, the more similar the fluctuations of the two segmented power consumption data curves, and then obtain power consumption similarity parameters, such as , Indicates neighboring historical users and The neighboring historical user DTW distance between segment power consumption data.

[0072] Step S203: Obtain the degree of industrial agglomeration based on the electricity consumption similarity parameters between all neighboring historical users; the electricity consumption similarity parameters are positively correlated with the degree of industrial agglomeration.

[0073] Considering that the larger the electricity consumption similarity parameter between neighboring historical users, the more consistent the electricity consumption behavior of the historical users around the current user, reflecting a higher degree of industrial agglomeration, the degree of industrial agglomeration is obtained based on the electricity consumption similarity parameters between all neighboring historical users; the electricity consumption similarity parameters are positively correlated with the degree of industrial agglomeration.

[0074] As an example, the average value of the electricity consumption similarity parameters among all neighboring historical users of the current user is taken as the industrial agglomeration degree corresponding to the current user.

[0075] After evaluating the degree of industrial agglomeration around the current user, we can obtain the first degree of abnormality of the current user's application data based on the equipment similarity parameters corresponding to the current user and each neighboring historical user, combined with the degree of industrial agglomeration. By combining the characteristics of industrial agglomeration and the difference characteristics of power equipment information, we can more accurately evaluate the abnormality of the current user's application data and prepare for the final rapid verification.

[0076] Preferably, in one embodiment of the present invention, the current user is compared with a single historical user, resulting in the unity of the comparison result. The abnormality degree of the device information of the current user is obtained according to the device similarity parameters corresponding to the current user and all adjacent historical users, thereby improving the accuracy and persuasiveness of the abnormal analysis of the current user. Considering that the larger the device similarity parameters corresponding to the current user and the adjacent historical users are, the more normal the electrical device information of the current user is, so the device similarity parameters are negatively correlated with the abnormality degree of the device information;

[0077] Taking into account that the higher the degree of industrial agglomeration, the higher the credibility of the device similarity parameters compared between the current user and the neighboring historical users, the higher the credibility of the device information anomaly degree, and the more it can reflect the abnormal situation of the current user. Therefore, the first anomaly degree of the current user is obtained according to the device information anomaly degree and the industrial agglomeration degree of the current user; the device information anomaly degree and the industrial agglomeration degree are positively correlated with the first anomaly degree.

[0078] As an example, the calculation formula of the first abnormality degree includes:

[0079] ;

[0080] in, Indicates the serial number of the current user; Indicates the sequence number of the historical users adjacent to the current user; Indicates the current user The first abnormality level of the application data; Indicates the current user The degree of industrial agglomeration; Indicates the current user The number of neighboring historical users; Indicates the current user and Similarity parameters of devices corresponding to neighboring historical users; Indicates the preset division by zero positive parameter, ; represents the linear normalization function; Indicates the current user The abnormality degree of device information.

[0081] In the calculation formula of the first abnormality degree, the average value of the device similarity parameters corresponding to the current user and all neighboring historical users is expressed as the normality of the current user's device information by taking the mean, and then a negative correlation mapping is performed by taking the inverse, and with the help of a preset positive division by zero parameter, the denominator is prevented from being zero, and the abnormality degree of the device information is obtained; the smaller the average value of the device similarity parameters corresponding to the current user and all neighboring historical users, the more abnormal the current user's device information is, the higher the abnormality degree is, and the greater the first abnormality degree; at the same time, the greater the degree of industrial agglomeration, the more concentrated the industry around the current user is, and the higher the credibility of the abnormality degree of the device information is.

[0082] In other embodiments of the present invention, the implementer may also use a negative correlation mapping function, such as Perform negative correlation mapping, such as ; Expressed as a natural constant The exponential function with base ; Represents the independent variable.

[0083] Step S3: Filter out similar historical users based on device similarity parameters corresponding to the current user and each historical user; analyze the distribution and aggregation characteristics of the current user and similar historical users based on address information to obtain the second abnormality degree of the current user's application data.

[0084] Taking into account the clustering characteristics of industries and the planning layout of urban areas, similar users are usually located in a clustered area, such as a commercial street, industrial park, industrial zone, etc.; therefore, more evaluation basis can be obtained from the distribution and clustering angle of the current user and similar historical users to improve the accuracy of rapid verification. Therefore, similar historical users are screened out based on the device similarity parameters corresponding to the current user and each historical user; based on the address information, the distribution and clustering characteristics of the current user and similar historical users are analyzed to obtain the second abnormality degree of the current user's application data.

[0085] Preferably, in one embodiment of the present invention, considering that the larger the device similarity parameter corresponding to the historical user and the current user is, the more similar the historical user and the current user are, so when the device similarity parameter corresponding to the historical user and the current user is greater than a preset similarity threshold, the corresponding historical user is determined as a similar historical user.

[0086] As an example, since the value range of the Jaccard similarity coefficient is 0 to 1, when two word segmentation sets are completely dissimilar, the Jaccard similarity coefficient is 0; the more similar the two word segmentation sets are, the closer the Jaccard similarity coefficient is to 1, that is, the device similarity parameter is between 0 and 1, so the preset similarity threshold is set to 0.8. When the device similarity parameter corresponding to the historical user and the current user is greater than 0.8, the corresponding historical user is determined as a similar historical user.

[0087] In other embodiments of the present invention, the implementer may also set other preset similarity thresholds, such as selecting a suitable preset similarity threshold in [0.75, 1].

[0088] Preferably, in one embodiment of the present invention, in order to facilitate the analysis of the distribution and aggregation characteristics of the current user and similar historical users, a two-dimensional coordinate system is constructed according to the geographic horizontal plane, and the address information is analyzed based on the geographic information system, and the address of the current user and the addresses of similar historical users are mapped to the two-dimensional coordinate system;

[0089] In a two-dimensional coordinate system, the distribution and clustering characteristics of the current user and similar historical users are analyzed to obtain the second abnormality degree of the current user's application data.

[0090] As an example, the longitude and latitude of the user's address are obtained as the user's two-dimensional coordinates, and the current user's address and the addresses of similar historical users are mapped into the two-dimensional coordinate system.

[0091] Preferably, in one embodiment of the present invention, considering that clustering can quickly and effectively identify user groups that are distributed and clustered in geographic space, the farther the distance between the current user and the cluster center is, the more isolated the current user is, and the more likely an abnormality is to occur, so the addresses of users in the two-dimensional coordinate system are clustered; the second abnormality degree is obtained based on the distance between the current user's address and the cluster center of the cluster to which it belongs; the distance between the current user's address and the cluster center of the cluster to which it belongs is positively correlated with the second abnormality degree.

[0092] As an example, the k-means algorithm is used for clustering, and the k value is determined according to the number of regional divisions of the city, such as the number of districts divided in a province or city. After the distance between the current user's address and the cluster center of the cluster to which it belongs is linearly normalized, the second abnormality degree of the current user is taken as the same level as the first abnormality degree.

[0093] It should be noted that, in one embodiment of the present invention, in order to limit the size of the geographic space analyzed by the two-dimensional coordinate system, the current user address is used as the center, and only similar historical users within 50 km of the user address are analyzed to narrow the clustering range and improve data verification efficiency.

[0094] Step S4: quickly verify the application data of the current user according to the first abnormality degree and the second abnormality degree corresponding to the current user.

[0095] The first abnormality degree obtained in step S2 is used to evaluate the abnormal characteristics of the current user's application data from the perspective of the similarity of the power equipment information of the current user and the neighboring historical users. The second abnormality degree obtained in step S3 is used to evaluate the abnormal characteristics of the current user's application data from the perspective of the distribution and aggregation of the current user and similar historical users. Therefore, the first abnormality degree and the second abnormality degree are finally integrated, and the first abnormality degree and the second abnormality degree are used to verify each other. According to the first abnormality degree and the second abnormality degree corresponding to the current user, the application data of the current user is quickly verified.

[0096] Preferably, in one embodiment of the present invention, considering that the more similar the first abnormality degree and the second abnormality degree are, the more consistent the abnormal characteristics of the current user's application data obtained from different angles are, and the more accurate the abnormality assessment of the current user's application data is; at the same time, the greater the first abnormality degree and the second abnormality degree are, the more abnormal the application data is, and the lower the verification accuracy is; considering that the user's ID number code is an important identification information of the user, it is also necessary to combine the accuracy of the ID number code to obtain the verification result;

[0097] Based on this, according to the similar features of the first abnormality degree and the second abnormality degree corresponding to the current user, the verification accuracy of the application data of the current user is obtained by combining the first abnormality degree and the second abnormality degree; the similar features of the first abnormality degree and the second abnormality degree are positively correlated with the verification accuracy; the first abnormality degree and the second abnormality degree are both negatively correlated with the verification accuracy;

[0098] The application data also includes the user's ID number code; the verification result is obtained based on the verification accuracy of the current user's application data and the accuracy of the ID number code.

[0099] As an example, the calculation formula for the verification accuracy includes:

[0100] ;

[0101] in, Indicates the serial number of the current user; Indicates the current user Verification accuracy of application data; Indicates the current user The first abnormality level of the application data; Indicates the current user The second abnormality level of the application data; Indicates the current user The average value of the first abnormality degree and the second abnormality degree of the application data; Indicates the preset division by zero positive parameter, ; Indicates taking the absolute value.

[0102] In the calculation formula of the verification accuracy, the difference characteristics of the first abnormality degree and the second abnormality degree are expressed by the absolute value of the difference between the first abnormality degree and the second abnormality degree, and then the similar characteristics of the first abnormality degree and the second abnormality degree are expressed by taking the inverse method. The more similar the first abnormality degree and the second abnormality degree are, the more consistent the abnormal characteristics of the current user's application data obtained from different angles are. The higher the credibility, the smaller the first abnormality and the second abnormality. The smaller the first abnormality and the second abnormality, the smaller the corresponding average value, and the smaller the abnormality of the user's application data. The smaller it is, the more consistent the abnormal characteristics of the current user's application data analyzed from different angles are, and the higher the verification accuracy is.

[0103] In other embodiments of the present invention, the implementer may also use a negative correlation mapping function, such as Perform negative correlation mapping, such as .

[0104] Preferably, in one embodiment of the present invention, considering that the greater the verification accuracy, the more likely the application data of the current user is normal and the lower the possibility of abnormality, when the verification accuracy is greater than a preset verification threshold, it is determined that the preliminary verification has passed;

[0105] Considering that the fewer the difference characters in the ID number code of the current user, the more accurate the ID number code is, so when the preliminary verification is passed, the ID number code of the current user is compared with the public network system data and the difference characters are extracted to obtain the proportion of the difference characters in the ID number code. When the proportion corresponding to the difference characters is less than the preset proportion threshold, it is determined that the final verification has passed;

[0106] In order to avoid system anomalies that may cause user application data to be abnormally rejected and cause losses to users, when application data fails the preliminary verification or final verification, the verification results will be obtained through manual verification.

[0107] As an example, the preset verification threshold is 0.86; the preset ratio threshold is 0.03; comparing the current user's ID number code with the public network system data and extracting the difference characters is already an existing technology and will not be described in detail here.

[0108] In summary, the present invention aims at the technical problems of high difficulty and low efficiency of existing data verification, and proposes a method for rapid verification of user data of a smart application interaction platform. The present invention first obtains the application data of the current user and the verified historical users, and obtains the electricity consumption data of the historical users; further analyzes the similar characteristics of the power equipment information, and obtains the similar parameters of the equipment corresponding to the current user and each historical user; further with the help of the similar characteristics of the power consumption data, analyzes and obtains the degree of industrial agglomeration, and obtains the first abnormality degree from the similarity of the power equipment information of the current user and the neighboring historical users; further from the distribution and aggregation perspective of the current user and similar historical users, evaluates the abnormal characteristics of the current user's application data, and obtains the second abnormality degree; finally, the first abnormality degree and the second abnormality degree are combined to quickly verify the application data of the current user. The present invention uses historical data to perform abnormal analysis on the application data of the current user, evaluates the abnormal characteristics of the current user's application data from the similarity perspective of the power equipment information and the distribution and aggregation perspective of similar users, and quickly verifies the application data of the current user, thereby reducing the difficulty of data verification and improving the verification efficiency.

[0109] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0110] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for quickly verifying user data of a smart application interaction platform, characterized in that: The method comprises: Obtain application data of the current user and verified historical users; the application data at least includes address information and power equipment information of the application; obtain power consumption data of verified historical users; According to the similar features of the power equipment information of the current user and the power equipment information of the historical users, the device similarity parameters corresponding to the current user and each historical user are obtained; according to the address information of the current user and the address information of the historical users, the neighboring historical users corresponding to the current user when applying for installation are obtained; according to the similar features of the power usage data between the neighboring historical users, the degree of industrial agglomeration is obtained; according to the device similarity parameters corresponding to the current user and each of the neighboring historical users, combined with the degree of industrial agglomeration, the first abnormality degree of the application data of the current user is obtained; Filter out similar historical users according to the device similarity parameters corresponding to the current user and each historical user; analyze the distribution and aggregation characteristics of the current user and the similar historical users according to the address information to obtain the second abnormality degree of the application data of the current user; According to the first abnormality degree and the second abnormality degree corresponding to the current user, quickly verify the application data of the current user; The method for obtaining the device similarity parameters includes: Perform word segmentation processing on the electric device information, and obtain a similarity coefficient between a word segmentation set of the electric device information of the current user and a word segmentation set of the electric device information of a historical user as a device similarity parameter between the current user and the corresponding historical user; The method for obtaining the degree of industrial agglomeration includes: Obtaining the power consumption data of the preset time domain neighborhood of the neighboring historical users when the current user applies for the subscription, as the power consumption data to be analyzed of the neighboring historical users; segmenting each of the power consumption data to be analyzed to obtain segmented power consumption data; According to the fluctuation similarity characteristics of the segmented power consumption data of all the same order of any two of the adjacent historical users, obtaining power consumption similarity parameters corresponding to the two adjacent historical users; According to the electricity consumption similarity parameters between all the adjacent historical users, the degree of industrial agglomeration is obtained; the electricity consumption similarity parameters are positively correlated with the degree of industrial agglomeration; The method for obtaining similar historical users includes: When the device similarity parameter corresponding to the historical user and the current user is greater than a preset similarity threshold, the corresponding historical user is determined as a similar historical user; The method for obtaining the second abnormality degree includes: Constructing a two-dimensional coordinate system according to the geographic horizontal plane, analyzing the address information based on a geographic information system, and mapping the address of the current user and the addresses of the similar historical users into the two-dimensional coordinate system; In the two-dimensional coordinate system, analyzing the distribution and aggregation characteristics of the current user and the similar historical users to obtain a second abnormality degree of the application data of the current user; The method for obtaining neighboring historical users includes: Analyze the address information based on the geographic information system to locate the addresses of the current user and historical users; take the address of the current user as the center of the circle and the preset base value as the radius, and take the historical users contained in the circle as neighboring historical users; When the number of neighboring historical users corresponding to the current user is less than a preset neighboring number threshold, the preset base value is increased with a preset growth step until the number of historical users included in the circle for the first time is greater than or equal to the preset neighboring number threshold.

2. According to claim 1, a method for quickly verifying user data of a smart application interactive platform is characterized in that: The method for obtaining the first abnormality degree includes: According to the device similarity parameters corresponding to the current user and all the neighboring historical users, the abnormality degree of the device information of the current user is obtained; the device similarity parameters are negatively correlated with the abnormality degree of the device information; The first abnormality degree of the current user is obtained according to the abnormality degree of the device information and the industrial concentration degree of the current user; the abnormality degree of the device information and the industrial concentration degree are both positively correlated with the first abnormality degree.

3. According to claim 1, a method for quickly verifying user data of a smart application interactive platform is characterized in that: The method of analyzing the distribution and aggregation characteristics of the current user and the similar historical users in the two-dimensional coordinate system to obtain the second abnormality degree of the application data of the current user includes: The addresses of users in the two-dimensional coordinate system are clustered; the second abnormality degree is obtained according to the distance between the address of the current user and the cluster center of the cluster to which it belongs; the distance between the address of the current user and the cluster center of the cluster to which it belongs is positively correlated with the second abnormality degree.

4. According to claim 1, a method for quickly verifying user data of a smart application interactive platform is characterized in that: The method for quickly verifying the application data of the current user according to the first abnormality degree and the second abnormality degree corresponding to the current user includes: According to the similar features of the first abnormality degree and the second abnormality degree corresponding to the current user, the verification accuracy of the application data of the current user is obtained in combination with the first abnormality degree and the second abnormality degree; the similar features of the first abnormality degree and the second abnormality degree are positively correlated with the verification accuracy; the first abnormality degree and the second abnormality degree are both negatively correlated with the verification accuracy; The application data also includes the user's ID number code; the verification result is obtained based on the verification accuracy of the application data of the current user and the accuracy of the ID number code.

5. According to claim 4, a method for quickly verifying user data of a smart application interactive platform is characterized in that: The method for obtaining the verification result according to the verification accuracy rate of the application data of the current user and the certificate number code includes: When the verification accuracy is greater than a preset verification threshold, the preliminary verification is determined to have passed; the ID number code of the current user is compared with the public network system data and the difference characters are extracted to obtain the proportion of the difference characters in the ID number code; when the proportion corresponding to the difference characters is less than a preset proportion threshold, the final verification is determined to have passed; When the application data fails the preliminary verification or the final verification, the verification result is obtained through manual verification.

Images