Identity recognition method for electricity selling system

Abstract

The invention belongs to the field of identity recognition, and discloses an identity recognition method for an electricity selling system, which comprises the following steps: S1, a client sends login verification information to a server; s2, the server judges whether the first round of login verification is passed or not according to the login verification information, and sends a result of the first round of login verification to the client; s3, the client side judges whether the result of the first round of login verification is passed or not, and if yes, a face image of the user is obtained and uploaded to the server; s4, the server calculates a verification coefficient of the second round of login verification of the client, and obtains image features of the obtained face image uploaded by the client based on the verification coefficient; and S5, the server judges whether the second round of login verification is passed based on the image features, and sends a result of the second round of login verification to the client. According to the method and the device, the security and the login verification efficiency can be comprehensively considered in the login verification process, and the probability of occurrence of the situation that a user needs to wait for a long time can be reduced while the security is ensured.

Description

Technical Field

[0001] The present invention relates to the field of identity recognition, and particularly to an identity recognition method for an electricity sales system. Background Art

[0002] An electricity sales system is a system used to manage electricity customers and electricity transactions, etc. The management of electricity customers includes customer portrait construction (power consumption habits, credit ratings), full life cycle management (from potential customer development to contract customer maintenance, etc.). The management of electricity transactions includes medium- and long-term contract decomposition, spot auction declaration, purchase cost prediction, and transaction review analysis, etc.

[0003] In order to ensure security, the electricity sales system usually adopts a multi-verification identity recognition method to identify the client. For example, first, identity recognition based on an account and password is performed. After the recognition passes, face recognition is performed to ensure the security of the system. During the face recognition process, it is usually necessary to upload a face image to the server for recognition. By extracting the image features of the newly uploaded face image and comparing the similarity with the features of the pre-stored face image in the server, the result of face recognition is determined. However, the prior art usually uses a fixed feature extraction algorithm to extract features, which brings a problem. If an algorithm with good feature extraction effect (high matching accuracy) is used to extract features, it will take a relatively long time to obtain the result of face recognition, so that the user needs to wait for a long time; if an algorithm with general feature extraction effect is used to extract features, although the efficiency of feature extraction can be guaranteed, the security will be reduced. Summary of the Invention

[0004] The purpose of the present invention is to disclose an identity recognition method for an electricity sales system to solve the technical problems pointed out in the background art.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions:

[0006] The present invention provides an identity recognition method for an electricity sales system, including:

[0007] S1, the client sends login verification information to the server;

[0008] S2, the server determines whether the first round of login verification is passed according to the login verification information, and sends the result of the first round of login verification to the client;

[0009] S3, the client determines whether the result of the first round of login verification is passed. If so, the client obtains the user's face image and uploads it to the server;

[0010] S4, the server calculates the verification coefficient for the second-round login verification of the client, and obtains the image features of the face image uploaded by the client based on the verification coefficient;

[0011] S5, the server determines whether the second-round login verification is passed based on the image features, and sends the result of the second-round login verification to the client;

[0012] Among them, obtaining the image features of the face image uploaded by the client based on the verification coefficient includes:

[0013] Obtain the numerical range corresponding to the verification coefficient;

[0014] Use the feature extraction algorithm corresponding to the numerical range to obtain the image features of the face image uploaded by the client.

[0015] Preferably, the login verification information includes an account and a password or the login verification information includes a verification code.

[0016] Preferably, determining whether the first-round login verification is passed according to the login verification information includes:

[0017] If the login verification information includes an account and a password, compare the account and password in the login verification information with the account and password pre-stored in the server to determine whether the first-round login verification is passed;

[0018] If the login verification information includes a verification code, compare the verification code with the verification code generated in the server to determine whether the first-round login verification is passed.

[0019] Preferably, in S3, it further includes:

[0020] If the result of the first-round login verification is not passed, display the result of the first-round login verification to the user in a page display manner.

[0021] Preferably, the login verification information further includes the IP address of the client.

[0022] Preferably, calculating the verification coefficient for the second-round login verification of the client includes:

[0023] Obtain the device score, network score and historical record score of the client;

[0024] Calculate the verification coefficient for the second-round login verification based on the device score, network score and historical record score.

[0025] Preferably, the process of obtaining the device score includes:

[0026] Obtain the login activity coefficient, registration coefficient and location coefficient of the client;

[0027] Calculate the device score based on the login activity coefficient, registration coefficient, and location coefficient.

[0028] Preferably, the process of obtaining the network score includes:

[0029] Obtain the network type coefficient and encryption protocol coefficient of the client;

[0030] Calculate the network score based on the network type coefficient and encryption protocol coefficient.

[0031] Preferably, the process of obtaining the historical record score includes:

[0032] Obtain the failure event coefficient and information modification coefficient;

[0033] Calculate the historical record score based on the failure event coefficient and information modification coefficient.

[0034] Preferably, the numerical range includes 4, the first numerical range is [0, T1); the second numerical range is [T1, T2); the third numerical range is [T2, T3); the fourth numerical range is (T3, 1];

[0035] T1, T2, and T3 are respectively the preset first interval parameter, second interval parameter, and third interval parameter.

[0036] Beneficial effects:

[0037] Different from the prior art, in the process of logging in and verifying the client, the electricity selling coefficient of the present invention does not use a fixed feature extraction algorithm to identify the client's identity, but obtains the image features of the face image uploaded by the client by calculating the verification coefficient. Therefore, in the process of login verification, the security and the efficiency of login verification can be comprehensively considered. While ensuring security, the probability of the situation where the user needs to wait for a long time can be reduced, so that the users of the electricity selling system can obtain a better user experience. Description of the Drawings

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0039] Figure 1 It is a schematic diagram of an identity recognition method for an electricity selling system of the present invention. Detailed Embodiments

[0040] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Usually, the components of the embodiments of the present invention described and illustrated herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0041] As Figure 1 shown in an embodiment, the present invention provides an identity recognition method for an electricity sales system, including:

[0042] S1, the client sends login verification information to the server.

[0043] Preferably, the login verification information includes an account number and a password or the login verification information includes a verification code.

[0044] In the present invention, if the user selects a verification code as the login verification information, then before S1, it further includes:

[0045] The client obtains the mobile phone number input by the user and sends it to the server, and this mobile phone number is the mobile phone number bound to the account;

[0046] After receiving the mobile phone number, the server generates a dynamic verification code and sends it to the device (such as a tablet, a smart phone, etc.) where the mobile phone number is located.

[0047] Specifically, when generating the verification code, a random generation algorithm can be used:

[0048] Principle: Use a random number generator to generate a random digital sequence as the verification code.

[0049] Steps: First, define the available digital set, etc.; then select characters from the character set through the random number generator to form a verification code with a specified length; finally, store the generated verification code for subsequent comparison and verification with the verification code transmitted by the client.

[0050] In the present invention, the electricity sales system can adopt a B / S architecture, so the client can be used on various types of devices.

[0051] S2, the server determines whether the first round of login verification is passed according to the login verification information, and sends the result of the first round of login verification to the client.

[0052] Specifically, if the user selects the verification code as the login verification information, the verification code generated has been pre-stored in the server, and only needs to compare the verification code sent by the client with the verification code stored in the server later to determine whether the first round of login verification is passed.

[0053] Preferably, judging whether the first round of login verification is passed according to the login verification information includes:

[0054] If the login verification information includes the account number and password, then compare the account number and password in the login verification information with the account number and password pre-stored in the server to determine whether the first round of login verification is passed;

[0055] If the login verification information includes the verification code, then compare the verification code with the verification code generated in the server to determine whether the first round of login verification is passed.

[0056] Specifically, if the account number in the login verification information is stored in the server and the password corresponding to the account number stored in the server is consistent with the password included in the login verification information, it means that the first round of login verification is passed.

[0057] If the verification code in the login verification information is the same as the verification code stored in the server, it means that the first round of login verification is passed.

[0058] In addition, after the server generates the verification code, it starts a countdown for a preset duration (such as 5 minutes), and after the countdown ends, the verification code is deleted.

[0059] Performing the countdown can prevent the verification code from being reused and improve the security of login verification.

[0060] Preferably, the account number stored in the server is the account number that has been pre-stored in the server when the user registers the account, and the password is the password that has been pre-stored in the server when the user registers the account. If the user has the behavior of modifying the password, the password is the password stored in the server after the user modifies it.

[0061] The first round of login verification of the present invention is a verification with a very low verification difficulty, so as to avoid the server from performing invalid processing on a large number of invalid login data sent by the client. The server only needs to compare the account password or the verification code to obtain the verification result, so that the server can process a large-scale first round of login verification at the same time.

[0062] S3. The client judges whether the result of the first round of login verification is passed. If so, it obtains the user's face image and uploads it to the server.

[0063] Specifically, when the result of the first-round login verification is passed, the face image of the user can be obtained through the camera of the device where the client is located.

[0064] Preferably, S3 further includes:

[0065] If the result of the first-round login verification is not passed, the result of the first-round login verification is displayed to the user in a page display manner.

[0066] Specifically, if the first-round verification fails, a pop-up prompt can be made on the login page, and the prompt text can be "The account or password is incorrect" or "The verification code is incorrect".

[0067] If the user selects the verification code as the login verification information, the prompt text is "The verification code is incorrect", otherwise the prompt text is "The account or password is incorrect".

[0068] S4, the server calculates the verification coefficient of the second-round login verification of the client, and obtains the image features of the face image uploaded by the client based on the verification coefficient.

[0069] The second-round login verification of the present invention is a verification method that requires a certain calculation time. By performing two rounds of login verification, the security of the electricity sales coefficient of the present invention is greatly improved.

[0070] Preferably, the login verification information further includes the IP address of the client.

[0071] Through the IP address, the server can distinguish different clients.

[0072] Preferably, calculating the verification coefficient of the second-round login verification of the client includes:

[0073] Obtain the device score, network score and historical record score of the client;

[0074] Calculate the verification coefficient of the second-round login verification based on the device score, network score and historical record score.

[0075] By calculating the verification coefficient through multiple different types of scores, the present invention represents the credibility of the current client's login through the verification coefficient, so that different feature extraction algorithms can be used based on different credibility levels to obtain the image features of the face image to achieve the balance between the accuracy of the extracted features and the efficiency of feature extraction.

[0076] Preferably, calculating the verification coefficient of the second-round login verification based on the device score, network score and historical record score includes:

[0077] Let A1, A2, and A3 represent the device score, network score, and historical record score respectively. Then the calculation formula for the verification coefficient of the second-round login verification is:

[0078] score = D1×A1 + D2×A2 + D3×A3

[0079] score represents the verification coefficient of the second-round login verification, and D1, D2, and D3 are the weight values of A1, A2, and A3 respectively.

[0080] The verification coefficient of the present invention is calculated based on three different types of scores. Therefore, when the values of A1, A2, and A3 are smaller, the value of the verification coefficient is smaller, indicating that the credibility of the client's current login is lower.

[0081] Specifically, the values of D1, D2, and D3 can be 0.4, 0.4, and 0.2 respectively.

[0082] Preferably, the process of obtaining the device score includes:

[0083] Obtain the login activity coefficient, registration coefficient, and location coefficient of the client;

[0084] Calculate the device score based on the login activity coefficient, registration coefficient, and location coefficient.

[0085] Preferably, the login activity coefficient is based on the number of logins mons on the currently logged-in device within a variable time range, and the historical login times mon ave to obtain:

[0086]

[0087] C1 represents the login activity coefficient.

[0088] In the present invention, the historical login times can be the number of logins of the account currently undergoing login verification in the most recent year.

[0089] The present invention is calculated by the ratio of the number of logins within a variable time range to the historical login times, so that the more the number of logins on the current device within the variable time range, the higher the credibility.

[0090] Specifically, the device can be identified through browser fingerprints, client identifiers, etc.

[0091] Browser fingerprint: Utilize the characteristic information of the browser, such as browser type, version, user agent string (User-Agent), screen resolution, installed font list, plugin list, time zone, language settings, etc. These pieces of information combined can form a relatively unique identifier. For example, if the browser fingerprints of two devices are exactly the same, including the same font and plugin combination, it may be that one device is logged in.

[0092] Client identifier (such as Cookie): When a user first visits a website, the server can send a Cookie to the client, which contains a unique identifier. If the browser sends the same Cookie when the user logs in again, the server can determine that it is the same device (provided that the user has not cleared the Cookie).

[0093] Preferably, the process of obtaining the variable time range includes:

[0094] Calculate the time length:

[0095]

[0096] tml represents the time length; Tb and Tc respectively represent the preset first time length and second time length;

[0097] K represents the time when the server receives the login verification information during this login, and N1 and N2 are respectively the number of logins on the currently logged-in device in the time ranges [K - Tc, K] and [K - 2Tc, K - Tc];

[0098] Then the variable time range is [K - tml, K].

[0099] In the process of calculating the login activity coefficient of the present invention, a variable time range is used as the time range for counting mons instead of a fixed time range, so that the calculated login activity coefficient can more sensitively and accurately represent the activity degree of the most recent login. If a fixed-length time range is used, it is easy to fail to capture this feature in a timely manner when the change trend of the login frequency of the same device is increasing, resulting in a smaller value of the calculated login activity coefficient, and thus a smaller calculated verification coefficient, affecting the calculation efficiency.

[0100] Preferably, the preset first time length and second time length are 2 months and 1 month respectively.

[0101] Preferably, the calculation formula for the registration coefficient is:

[0102]

[0103] C2 is the registration coefficient, datelen is the cumulative time length from the last password modification to the current login (in days); datebir is the cumulative time length from the account registration to the current login (in days).

[0104] The registration coefficient is mainly calculated based on the time length from the last password modification to the current time. If the current password has been used for a longer time, the registration coefficient is smaller, indicating a lower credibility of the current login.

[0105] Preferably, the calculation formula for the location coefficient is as follows:

[0106]

[0107] C3 is the location coefficient, dist1 is the distance between the IP address of the client at the current login and the client's commonly used login address; distpre is the preset distance.

[0108] The location coefficient is calculated based on the degree of change in the login location. When the degree of change in the login location is greater, the value of the location coefficient is smaller, indicating a lower credibility of the current login.

[0109] Specifically, the preset distance can be 1000km.

[0110] Preferably, calculating the device score based on the login activity coefficient, registration coefficient, and location coefficient includes:

[0111] Use the following formula to calculate the device score:

[0112] A1 = E1×C1 + E2×C2 + E3×C3

[0113] E1, E2, and E3 are the weight values of C1, C2, and C3 respectively.

[0114] The device score is comprehensively considered from three different directions, which can make the calculation result more comprehensively represent the credibility of the current login.

[0115] Preferably, E1, E2, and E3 can be 0.2, 0.3, and 0.5 respectively.

[0116] Preferably, the process of obtaining the network score includes:

[0117] Obtain the network type coefficient and encryption protocol coefficient of the client;

[0118] Calculate the network score based on the network type coefficient and encryption protocol coefficient.

[0119] Preferably, obtaining the network type coefficient of the client includes:

[0120] The network types include public WiFi, cellular network, proxy network, home WiFi, and other networks;

[0121] Let F1 represent the network type coefficient. When the network type of the client is public WiFi, F1 is 0.2; when the network type of the client is cellular network, F1 is 0.5;

[0122] When the network type of the client is proxy network, F1 is 0.5;

[0123] When the network type of the client is home WiFi, F1 is 0.7;

[0124] When the network type of the client is other networks, F1 is 0.4.

[0125] By judging the network type, the risk of this login can be determined to a certain extent, and the risk of public networks is the highest.

[0126] The network type can be judged by the client and then sent to the server together with the login verification information.

[0127] The public WiFi name (SSID) often contains location identifiers (such as "Starbucks_WiFi") and requires a login page or open encryption (such as WPA2). View the details in the device WiFi settings. Unencrypted or weakly encrypted (such as WEP) has a higher risk.

[0128] The IP of the cellular network is dynamically assigned by the operator, mostly public IP or specific private segments (such as 10.x.x.x), and the operator information can be displayed through an IP query tool (such as IP2Location).

[0129] Proxy requests will add specific header fields (such as X-Forwarded-For, Via, or Proxy-Connection), and the server can identify the proxy by analyzing these fields.

[0130] The name of the home WiFi is usually a random and irregular name or a room number (such as 1602), etc., and basically requires a password to log in. Therefore, it can be judged by the WiFi name.

[0131] If the network type of the client does not conform to the above 4 types, it is classified into other networks.

[0132] Preferably, obtaining the encryption protocol coefficient of the client includes:

[0133] Let F2 represent the encryption protocol coefficient;

[0134] If the secure communication protocol used for communication between the client and the server is TLS1.2, then F2 is 0.5;

[0135] If the secure communication protocol used for communication between the client and the server is TLS1.3, then F2 is 0.7;

[0136] If there is no secure communication protocol used for communication between the client and the server, then F2 is 0.1.

[0137] TLS1.2 supports multiple encryption algorithms, which are used to protect the confidentiality and integrity of data. For example, it supports the Advanced Encryption Standard (AES) for data encryption, which is a symmetric encryption algorithm with multiple key lengths (such as 128 bits, 192 bits, and 256 bits), and can provide high-strength data protection.

[0138] In the present invention, if the effect of the encryption algorithm adopted is better, then the value of F2 is larger.

[0139] Preferably, calculating the network score based on the network type coefficient and the encryption protocol coefficient includes:

[0140] A2 = α1 × F1 + α2 × F2

[0141] α1 and α2 are the weight values of F1 and F2 respectively.

[0142] Preferably, α1 and α2 are 0.5 and 0.5 respectively.

[0143] Preferably, the process of obtaining the historical record score includes:

[0144] Obtaining the failure event coefficient and the information modification coefficient;

[0145] Calculating the historical record score based on the failure event coefficient and the information modification coefficient.

[0146] Preferably, obtaining the failure event coefficient includes:

[0147] Obtaining the number of times Ftc that the account login fails in the most recent half month;

[0148] Obtaining the total number of times tc of account login in the most recent half month;

[0149] Then the login failure event coefficient

[0150] When the number of login failures is more, it indicates that the risk of the account is greater. Therefore, the value of G1 is smaller, and it can also make the value of A3 smaller.

[0151] Preferably, obtaining the information modification coefficient includes:

[0152] Obtain the total number of times Ch that information has been modified from the start of account registration to the current login;

[0153] Obtain the number of times Dh that password modification belongs to among the Ch times of information modification;

[0154] Then the information modification coefficient

[0155] The number of times of password modification is not the more the better. Modifying the password too frequently indicates a higher risk of account theft.

[0156] Preferably, calculate the historical record score based on the failure event coefficient and the information modification coefficient, including:

[0157] A3 = β1×G1 + β2×G2

[0158] β1 and β2 are the weight values of G1 and G2 respectively.

[0159] Preferably, β1 and β2 are 0.6 and 0.4 respectively.

[0160] Preferably, obtain the image features of the face image uploaded by the client based on the verification coefficient, including:

[0161] Obtain the numerical interval corresponding to the verification coefficient;

[0162] Use the feature extraction algorithm corresponding to the numerical interval to obtain the image features of the face image uploaded by the client.

[0163] In the present invention, different numerical intervals correspond to different account login risks, so that different image feature extraction algorithms can be selected based on the risk level, realizing the verification efficiency of multiple different clients to log in on the premise of ensuring account login security.

[0164] Preferably, the numerical interval includes 4, the first numerical interval is [0, T1); the second numerical interval is [T1, T2); the third numerical interval is [T2, T3); the fourth numerical interval is (T3, 1];

[0165] T1, T2 and T3 are the preset first interval parameter, second interval parameter and third interval parameter respectively.

[0166] Furthermore, T1, T2 and T3 can be 0.25, 0.5 and 0.75 respectively.

[0167] Preferably, the feature extraction algorithms corresponding to the first numerical interval, the second numerical interval, the third numerical interval and the fourth numerical interval are SIFT, SUFR, HOG and ORB respectively.

[0168] The computing time consumption of ORB, HOG, SUFR, and SIFT increases successively, while the matching accuracy increases successively.

[0169] SIFT (Scale-Invariant Feature Transform) performs excellently under scale, rotation, and illumination changes, with high matching accuracy (especially in image registration and 3D reconstruction).

[0170] The accuracy of SUFR is close to the stability of SIFT, but it is faster; it is robust to affine transformation, and the matching accuracy rate is slightly lower than that of SIFT.

[0171] HOG (Histogram of Oriented Gradients) performs outstandingly in pedestrian detection, but is sensitive to geometric deformation and occlusion.

[0172] ORB is fast but the descriptor has low distinctiveness, and the matching accuracy is weaker than that of SIFT, SURF, and HOG.

[0173] S5, the server determines whether to pass the second-round login verification based on the image features and sends the result of the second-round login verification to the client.

[0174] Preferably, determining whether to pass the second-round login verification based on the image features includes:

[0175] If the similarity between the image features of the face image obtained by the client uploaded based on the verification coefficient and the pre-stored image features in the server is less than the set threshold, the result of the second-round login verification is verification failed;

[0176] If the similarity between the image features of the face image obtained by the client uploaded based on the verification coefficient and the pre-stored image features in the server is greater than or equal to the set threshold, the result of the second-round login verification is verification passed.

[0177] In the present invention, the server can use ORB, HOG, SUFR, and SIFT in advance to extract the image features of the face image reserved during account registration, thereby improving the efficiency of subsequent face recognition.

[0178] During the subsequent face recognition process, according to the type of the algorithm for extracting features from the face image obtained by the client uploaded, the corresponding image features obtained using the same type of feature extraction algorithm can be obtained from the server, and then the similarity between the two can be calculated.

[0179] Specifically, the set threshold can be 0.8.

[0180] Different from the prior art, during the process of logging in and verifying the client, the electricity selling coefficient of the present invention does not use a fixed feature extraction algorithm to identify the identity of the client, but calculates the verification coefficient to obtain the image features of the face image uploaded by the client, so that during the process of logging in and verifying, the security and the efficiency of logging in and verifying can be comprehensively considered, and while ensuring security, the probability of the situation where the user needs to wait for a long time can be reduced, enabling the users of the electricity selling system to obtain a better user experience.

[0181] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. An identity recognition method for an electricity sales system, which is applied to an electricity sales system including a client and a server, characterized in that Including: S1, the client sends login verification information to the server; S2, the server determines whether the first-round login verification is passed according to the login verification information, and sends the result of the first-round login verification to the client; S3, the client determines whether the result of the first-round login verification is passed. If so, it acquires the user's face image and uploads it to the server; S4, the server calculates the verification coefficient of the second-round login verification of the client, and acquires the image features of the face image uploaded by the client based on the verification coefficient; S5, the server determines whether the second-round login verification is passed based on the image features, and sends the result of the second-round login verification to the client; Among them, acquiring the image features of the face image uploaded by the client based on the verification coefficient includes: Acquiring the numerical interval corresponding to the verification coefficient; Adopting the feature extraction algorithm corresponding to the numerical interval to acquire the image features of the face image uploaded by the client.

2. The identity recognition method for an electricity sales system according to claim 1, characterized in that, The login verification information includes an account and a password or the login verification information includes a verification code.

3. The identity recognition method for an electricity sales system according to claim 2, characterized in that, Determining whether the first-round login verification is passed according to the login verification information includes: If the login verification information includes an account and a password, the account and password in the login verification information are respectively compared with the account and password pre-stored in the server to determine whether the first-round login verification is passed; If the login verification information includes a verification code, the verification code is compared with the verification code generated in the server to determine whether the first-round login verification is passed.

4. The identity recognition method for an electricity sales system according to claim 1, characterized in that In S3, it further includes: If the result of the first-round login verification is not passed, the result of the first-round login verification is displayed to the user in a page display manner.

5. The identity recognition method for an electricity selling system according to claim 1, characterized in that, The login verification information further includes the IP address of the client.

6. The identity recognition method for an electricity sales system according to claim 5, wherein Calculating the verification coefficient of the second-round login verification of the client includes: Acquiring the device score, network score and historical record score of the client; Calculating the verification coefficient of the second-round login verification based on the device score, network score and historical record score.

7. An identity recognition method for an electricity sales system according to claim 6, characterized in that, The process of acquiring the device score includes: Acquiring the login activity coefficient, registration coefficient and location coefficient of the client; Calculating the device score based on the login activity coefficient, registration coefficient and location coefficient.

8. The identity recognition method for an electricity sales system according to claim 6, characterized in that, The process of acquiring the network score includes: Acquiring the network type coefficient and encryption protocol coefficient of the client; Calculating the network score based on the network type coefficient and encryption protocol coefficient.

9. The identity recognition method for an electricity sales system according to claim 6, characterized in that The process of acquiring the historical record score includes: Acquiring the failure event coefficient and information modification coefficient; Calculating the historical record score based on the failure event coefficient and information modification coefficient.

10. The identity recognition method for an electricity sales system according to claim 1, characterized in that There are 4 numerical intervals. The first numerical interval is [0, T1); the second numerical interval is [T1, T2); the third numerical interval is [T2, T3); the fourth numerical interval is (T3, 1]; T1, T2 and T3 are respectively the preset first interval parameter, second interval parameter and third interval parameter.

Images