WO2021217944A1 - Method and apparatus for verifying electronic signature, and computer device and storage medium - Google Patents

Abstract

A method for verifying an electronic signature, which method relates to the technical field of artificial intelligence, and can be applied to an intelligent security and protection scenario. The method comprises: collecting time series data of an electronic signature on a touch-screen input device, wherein the time series data of the electronic signature carries a signature identifier of the electronic signature; acquiring time series data of an authentication electronic signature of the signature identifier; according to the time series data of the electronic signature and the time series data of the authentication electronic signature, determining the feature similarity between the electronic signature and the authentication electronic signature; and according to the feature similarity between the electronic signature and the authentication electronic signature, determining a verification result for the electronic signature.

Description

Electronic signature verification method, device, computer equipment and storage medium

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on April 27, 2020. The application number is 2020103445591, and the application name is "Verification Method, Device, Computer Equipment and Storage Medium of Electronic Signature". The reference is incorporated in this application.

Technical field

This application relates to the field of artificial intelligence technology, in particular to an electronic signature verification method, device, computer equipment and storage medium.

Background technique

With the rapid development of Internet technology, electronic signatures have been widely used in many fields, such as online banking, physical banking, e-government, and the signing of electronic contracts. In order to ensure the security of electronic signatures, electronic signatures need to be verified.

At present, the authentication method for electronic signatures is generally to collect the picture information of the electronic signature, extract the characteristics from the picture information of the electronic signature, and then analyze these characteristics to obtain the verification result of the electronic signature. However, the inventor realizes that the picture information of the electronic signature only involves the static information of the electronic signature, which can easily cause misidentification or omission of the electronic signature, which in turn leads to a lower verification accuracy rate of the electronic signature.

Summary of the invention

According to various embodiments disclosed in the present application, an electronic signature verification method, device, computer equipment, and storage medium are provided.

An electronic signature verification method includes:

Collecting the time series data of the electronic signature on the touch screen input device; the time series data of the electronic signature carries the signature identification of the electronic signature;

Acquiring the time series data of the authenticated electronic signature of the signature identification;

Determine the feature similarity between the electronic signature and the certified electronic signature according to the time series data of the electronic signature and the time series data of the certified electronic signature; and

According to the feature similarity between the electronic signature and the certified electronic signature, the verification result of the electronic signature is determined.

An electronic signature verification device includes:

The data collection module is used to collect the time series data of the electronic signature on the touch screen input device; the time series data of the electronic signature carries the signature identification of the electronic signature;

A data acquisition module for acquiring the time series data of the certified electronic signature of the signature identification;

The similarity determination module is configured to determine the feature similarity between the electronic signature and the certified electronic signature according to the time series data of the electronic signature and the time series data of the certified electronic signature; and

The verification result determination module is configured to determine the verification result of the electronic signature according to the feature similarity between the electronic signature and the certified electronic signature.

A computer device, including a memory and one or more processors, the memory stores computer readable instructions, and when the computer readable instructions are executed by the processor, the one or more processors execute The following steps:

Collecting the time series data of the electronic signature on the touch screen input device; the time series data of the electronic signature carries the signature identification of the electronic signature;

Acquiring the time series data of the authenticated electronic signature of the signature identification;

Determine the feature similarity between the electronic signature and the certified electronic signature according to the time series data of the electronic signature and the time series data of the certified electronic signature; and

According to the feature similarity between the electronic signature and the certified electronic signature, the verification result of the electronic signature is determined.

One or more computer-readable storage media storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors perform the following steps:

Collecting the time series data of the electronic signature on the touch screen input device; the time series data of the electronic signature carries the signature identification of the electronic signature;

Acquiring the time series data of the authenticated electronic signature of the signature identification;

Determine the feature similarity between the electronic signature and the certified electronic signature according to the time series data of the electronic signature and the time series data of the certified electronic signature; and

According to the feature similarity between the electronic signature and the certified electronic signature, the verification result of the electronic signature is determined.

The above-mentioned verification method, device, computer equipment and storage medium of the electronic signature, the time series data of the electronic signature identified by the same signature on the touch screen input device and the time series data of the certified electronic signature are used to determine the distance between the electronic signature and the certified electronic signature. According to the feature similarity between the electronic signature and the certified electronic signature, the verification result of the electronic signature is determined; it is realized that the electronic signature is determined in real time according to the time series data of the electronic signature and the time series data of the certified electronic signature. The purpose of the verification result of the signature is to comprehensively consider the time series data of the electronic signature and the time series data of the authentication electronic signature, which is conducive to obtaining the dynamic information of the electronic signature in the time dimension, thereby making the verification of the electronic signature more accurate and avoiding just considering The static information of the electronic signature leads to the defect that the verification accuracy of the electronic signature is low, which further improves the verification accuracy of the electronic signature. At the same time, through the feature similarity between the electronic signature and the certified electronic signature, the verification result of the electronic signature is determined, which is conducive to the accurate verification of the electronic signature, thereby improving the verification accuracy of the electronic signature.

The details of one or more embodiments of the present application are set forth in the following drawings and description. Other features and advantages of this application will become apparent from the description, drawings and claims.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. A person of ordinary skill in the art can obtain other drawings based on these drawings without creative work.

Fig. 1 is an application environment diagram of an electronic signature verification method according to one or more embodiments;

Fig. 2 is a schematic flow chart of a verification method for an electronic signature according to one or more embodiments;

Fig. 3 is a schematic diagram of an electronic pen and a touch screen input device according to one or more embodiments;

4 is a schematic flowchart of the steps of determining the feature similarity between an electronic signature and a certified electronic signature according to one or more embodiments;

FIG. 5 is a schematic diagram of the feature similarity between the output electronic signature and the certified electronic signature according to one or more embodiments;

FIG. 6 is a schematic flowchart of a method for verifying an electronic signature in another embodiment;

Fig. 7 is a block diagram of an electronic signature verification device according to one or more embodiments;

Figure 8 is a block diagram of a computer device according to one or more embodiments.

Detailed ways

In order to make the technical solutions and advantages of the present application clearer, the following further describes the present application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

The electronic signature verification method provided in this application can be applied to the application environment as shown in FIG. 1. Wherein, the touch screen input device 110 communicates with the server 120 through a network. The touch screen input device 110 collects the time series data of the electronic signature of the current signer, and sends the time series data of the electronic signature to the server 120, and the time series data of the electronic signature carries the signature identifier. The server 120 obtains the time series data of the corresponding certified electronic signature according to the signature identifier of the electronic signature; determines the feature similarity between the electronic signature and the certified electronic signature according to the time series data of the electronic signature and the time series data of the certified electronic signature; According to the feature similarity between the electronic signature and the certified electronic signature, the verification result of the electronic signature is determined. Among them, the touch screen input device 110 refers to a touch screen device with an electronic signature function, which can be, but is not limited to, various smart phones, tablets, and electronic signature devices. The server 120 can be an independent server or a server composed of multiple servers. Cluster to achieve.

It should be noted that the electronic signature verification method provided in this application can also be applied to touch screen input devices, and can also be applied to a server, which is not specifically limited by this application.

In one of the embodiments, as shown in FIG. 2, an electronic signature verification method is provided. Taking the method applied to the server in FIG. 1 as an example for description, the method includes the following steps:

Step S201: Collect the time series data of the electronic signature on the touch screen input device; the time series data of the electronic signature carries the signature identifier of the electronic signature.

In this step, the touch screen input device refers to the device with electronic signature function, such as Apple iPad, which can allow users to perform electronic signatures and collect the time series data of electronic signatures; electronic signatures refer to the electronic pen (such as Apple Pencil). ) The name written on a touch screen input device (such as Apple iPad).

In this step, the time series data of the electronic signature refers to the data of multiple dimensions of the electronic pen collected under different timestamps in chronological order, which can characterize the signature characteristics of the user; for example, under different timestamps, the electronic pen’s The position coordinates of the pen tip on the touch screen input device (including the horizontal and vertical coordinates), the pressure value of the electronic pen on the touch screen input device, and the projection line of the electronic pen on the surface of the touch screen input device and the horizontal line of the surface of the touch screen input device The radian (as shown in Figure 3a), the arc between the height of the electronic pen and the surface of the touch screen input device (as shown in Figure 3b), and so on. In this step, the signature identification of the electronic signature refers to the unique identification of the electronic signature, such as the name corresponding to the electronic signature, the electronic signature number, etc.; for example, if the electronic signature is "Li San", the signature identification of the electronic signature is also As "Li San".

In specific implementation, the touch screen input device responds to the current electronic signature operation, obtains the time series data of the electronic signature, and sends the time series data of the electronic signature to the corresponding server; the server reads the time series data of the electronic signature The signature identifier of the electronic signature carried in it is convenient to subsequently obtain the corresponding time-series data of the authenticated electronic signature based on the signature identifier.

For example, a user writes an electronic signature on a touch screen input device through an electronic pen to trigger the electronic signature operation; the touch screen input device responds to the electronic signature operation and collects data of multiple dimensions of the electronic pen under different time stamps in chronological order , As the time series data of the corresponding electronic signature, and send the time series data of the electronic signature to the corresponding server. Among them, the touch screen input device can also take the data of multiple dimensions of the electronic pen collected under each time stamp as a row of data and write it into a pre-established form (such as a CSV form) as the time sequence of the corresponding electronic signature Data table (as shown in Table 1), and send the entire electronic signature time series data table to the corresponding server.

ID	X	Y	Force	Altitude	Azimuth	Timestamp
S0-0	212.9297	218.7813	0.424479	1.10815	0.508911	311881.499
S0-1	212.8477	218.7813	0.337049	1.10815	0.508911	311881.507
S0-2	212.4375	218.7813	0.209896	1.10815	0.508911	311881.512
S0-3	212.1094	218.7813	0.248417	1.10815	0.508911	311881.515
S0-4	211.7813	218.8594	0.312618	1.10815	0.508911	311881.520
S0-5	211.6172	219.0313	0.327137	1.10815	0.508911	311881.524
S0-6	211.4531	219.3594	0.337137	1.10815	0.508911	311881.528
S0-7	211.3711	219.5938	0.33904	1.10815	0.508911	311881.532
S0-8	211.3711	219.9219	0.341744	1.10815	0.508911	311881.537
S0-9	211.3711	220.4219	0.346929	1.10815	0.508911	311881.540

Table 1

Among them, ID represents the number corresponding to each row of time series data, X represents the abscissa of the pen tip of the electronic pen on the touch screen input device, Y represents the ordinate of the pen tip of the electronic pen on the touch screen input device, and Force represents the electronic pen pair The pressure value of the touch screen input device, Altitude represents the arc between the height of the electronic pen and the surface of the touch screen input device, and Azimuth represents the arc between the projection line of the electronic pen on the surface of the touch screen input device and the horizontal line of the touch screen input device. Timestamp stands for timestamp. It should be noted that due to the system of the touch screen input device, the interval between different timestamps is different, and the approximate range is between 0.005 and 0.013.

Further, the server can also receive the electronic signature verification request of the touch screen input device, analyze the electronic signature verification request, and obtain the time series data of the electronic signature and the signature identification corresponding to the electronic signature; for example, the touch screen input device responds to the current The electronic signature operation obtains the time series data of the electronic signature, generates an electronic signature verification request according to the time series data of the electronic signature, and sends the electronic signature verification request to the corresponding server to request the server to verify the electronic signature.

Step S202: Obtain the time series data of the authenticated electronic signature identified by the signature.

In this step, the authenticated electronic signature refers to the name written by the user on the touch screen input device through the electronic pen in the real-name authentication link. The time-series data for authenticating electronic signatures also refers to the data of multiple dimensions of the electronic pen collected under different timestamps in chronological order, such as the position of the pen tip of the electronic pen on the touch screen input device under different timestamps Coordinates, the pressure value of the electronic pen on the touch screen input device, etc.

In specific implementation, the server queries the local database storing the time series data of the certified electronic signatures corresponding to multiple signatures according to the signature identification, and obtains the time series data of the certified electronic signatures corresponding to the signature identification from the local database, so as to facilitate the follow-up according to The time series data of the electronic signature and the time series data of the authentication electronic signature can accurately identify the electronic signature, thereby improving the verification accuracy of the electronic signature.

Further, before querying the local database storing the time series data of the certified electronic signatures corresponding to the multiple signature identities according to the signature identification, the server collects the time series of the certified electronic signatures on the multiple touch screen input devices based on the big data technology in advance. Data, so as to obtain the time series data of multiple certified electronic signatures; store the time series data of multiple certified electronic signatures in the local database according to the signature identification classification of the certified electronic signature, so as to store the certification of multiple signature identifications through the local database The time series data of the electronic signature; in this way, it is helpful to query the local database later to obtain the time series data of the certified electronic signature identified by the signature.

In one of the embodiments, the server may also query the correspondence between the preset signature identifier and the time-series data of the certified electronic signature based on the signature identifier to obtain the time-series data of the certified electronic signature corresponding to the signature identifier.

Step S203: Determine the feature similarity between the electronic signature and the certified electronic signature according to the time series data of the electronic signature and the time series data of the certified electronic signature.

Among them, the feature similarity between the electronic signature and the certified electronic signature is used to measure the degree of similarity between the signature feature corresponding to the electronic signature and the signature feature corresponding to the certified electronic signature; the higher the feature similarity, the greater the electronic signature and the certified electronic signature. The more similar the signature, it means that the electronic signature is a true signature, and the lower the feature similarity is, the less similar the electronic signature and the certified electronic signature are, indicating that the electronic signature is a fake signature.

Specifically, the server determines the feature code of the electronic signature and the feature code of the certification electronic signature according to the time series data of the electronic signature and the time series data of the certification electronic signature; according to the feature code of the electronic signature and the feature code of the certification electronic signature, count the electronic The feature similarity between the signature and the certified electronic signature; in this way, it is helpful to determine the verification result of the electronic signature according to the feature similarity between the electronic signature and the certified electronic signature, so as to achieve the accurate verification of the electronic signature, thereby improving The verification accuracy rate of the electronic signature. Among them, the feature code of an electronic signature refers to the low-dimensional feature vector used to represent the low-level semantics of the electronic signature after compression encoding, and the feature code of the certified electronic signature also refers to the low-level semantics of the certified electronic signature after compression encoding. The low-dimensional feature vector of.

For example, the server inputs the time series data of the electronic signature and the time series data of the authentication electronic signature into the feature extraction network, and extracts the time series features in the time series data of the electronic signature and the time series data of the authentication electronic signature through the feature extraction network. Time sequence features, and determine the feature code of the electronic signature and the feature code of the authenticated electronic signature according to the time sequence feature in the time series data of the electronic signature and the time sequence feature in the time series data of the certified electronic signature; count the feature code and certification of the electronic signature The feature distance between the feature codes of the electronic signature, and the feature similarity between the electronic signature and the certified electronic signature is determined according to the feature distance.

Further, before determining the feature similarity between the electronic signature and the certified electronic signature according to the time series data of the electronic signature and the time series data of the certified electronic signature, the server may also obtain a preset data preprocessing instruction, and according to the preset The data preprocessing instruction of the electronic signature preprocesses the time series data of the electronic signature and the time series data of the certified electronic signature to obtain the preprocessed time series data of the electronic signature and the preprocessed time series data of the certified electronic signature. In this way, by preprocessing the time series data of the electronic signature and the time series data of the authentication electronic signature, the subsequent determination is made based on the time series data of the preprocessed electronic signature and the time series data of the authentication electronic signature after preprocessing. The feature similarity between the electronic signature and the certified electronic signature is more accurate.

For example, referring to Table 1, for the time series data of the electronic signature, the server calculates the difference between the abscissa X and the ordinate Y corresponding to each time stamp and the abscissa X and the ordinate Y corresponding to the previous time stamp to obtain The difference between the abscissa dX and the ordinate dY; then keep the two decimal places of each timestamp, for example, 311881.499 becomes 31188149; in this way, the time series data corresponding to each timestamp becomes dX, dY , Force, Altitude, and Azimuth; then, merge the time series data with the same timestamp, and calculate the average values of dX, dY, Force, Altitude, and Azimuth respectively; in this way, the time series data corresponding to each timestamp becomes dX', dY', Force', Altitude' and Azimuth', as shown in Table 2. It should be noted that the time series data for authenticating electronic signatures is also preprocessed in the above-mentioned manner, and the details are not repeated in this application.

Timestamp	Force’	Altitude’	Azimuth’	dX’	dY’
31188149	0.424479	1.10815	0.508911	0	0
31188150	0.337049	1.10815	0.508911	-0.08203	0
31188151	0.229156	1.10815	0.508911	-0.36914	0
31188152	0.32563	1.10815	0.508911	-0.21875	0.192708

31188153	0.340392	1.10815	0.508911	-0.04102	0.28125
31188154	0.351754	1.10815	0.508911	0	0.411458
31188155	0.356407	1.10815	0.508911	0.246094	0.367188
31188156	0.363395	1.10815	0.508911	0.369141	0.242188
31188157	0.390325	1.10815	0.508911	0.328125	0.109375
31188158	0.447672	1.10815	0.508911	0.205078	0

Table 2

Step S204: Determine the verification result of the electronic signature according to the feature similarity between the electronic signature and the certified electronic signature.

Among them, the verification result of the electronic signature means that the electronic signature verification passes or the electronic signature verification fails.

Specifically, the server compares the feature similarity between the electronic signature and the certified electronic signature with the preset similarity to obtain a comparison result; according to the comparison result, it determines whether the electronic signature and the certified electronic signature belong to the same user's true signature, and then obtains The verification result of the electronic signature. For example, if the electronic signature and the certified electronic signature belong to the true signature of the same user, the electronic signature verification passed; if the electronic signature and the certified electronic signature do not belong to the true signature of the same user, the electronic signature verification failed. In this way, through the feature similarity between the electronic signature and the certified electronic signature, the verification result of the electronic signature is determined, which is conducive to the accurate verification of the electronic signature, and avoids only considering the static information of the electronic signature, resulting in the verification accuracy of the electronic signature Lower defects further improve the verification accuracy of electronic signatures.

In the verification method of the above electronic signature, the time series data of the electronic signature identified by the same signature on the touch screen input device and the time series data of the certified electronic signature are used to determine the feature similarity between the electronic signature and the certified electronic signature; The feature similarity between the electronic signature and the certified electronic signature determines the verification result of the electronic signature; realizes the purpose of determining the verification result of the electronic signature in real time based on the time series data of the electronic signature and the time series data of the certified electronic signature. Comprehensive consideration of the time series data of the electronic signature and the time series data of the authentication electronic signature is conducive to obtaining the dynamic information of the electronic signature in the time dimension, thus making the verification of the electronic signature more accurate, avoiding only considering the static information of the electronic signature, resulting in The shortcoming of low verification accuracy of electronic signatures further improves the verification accuracy of electronic signatures. At the same time, through the feature similarity between the electronic signature and the certified electronic signature, the verification result of the electronic signature is determined, which is conducive to the accurate verification of the electronic signature, thereby improving the verification accuracy of the electronic signature. The proposed solution can be applied to scenarios such as smart security, such as security monitoring, so as to promote the construction of smart cities.

In one of the embodiments, as shown in FIG. 4, the above step S203, according to the time series data of the electronic signature and the time series data of the certified electronic signature, determine the feature similarity between the electronic signature and the certified electronic signature, which specifically includes the following step:

Step S401: According to the time series data of the electronic signature and the time series data of the authentication electronic signature, the characteristic code of the electronic signature and the characteristic code of the authentication electronic signature are determined.

Specifically, the server extracts the time series characteristics in the time series data of the electronic signature and the time series characteristics in the time series data of the authentication electronic signature, and according to the time series characteristics in the time series data of the electronic signature and the time series data in the time series data of the authentication electronic signature Time sequence feature, determine the feature code of the electronic signature and the feature code of the authenticated electronic signature,

Step S402: Determine the characteristic distance between the characteristic code of the electronic signature and the characteristic code of the authenticated electronic signature.

Among them, the feature distance between the feature code of the electronic signature and the feature code of the certified electronic signature refers to the Euclidean distance between the feature code of the electronic signature and the feature code of the certified electronic signature, which is used to measure the difference between the electronic signature and the certified electronic signature. The feature similarity between the two; the larger the feature distance, the greater the feature similarity between the electronic signature and the certified electronic signature; the smaller the feature distance, the smaller the feature similarity between the electronic signature and the certified electronic signature.

Specifically, the server uses the Euclidean distance algorithm to calculate the Euclidean distance between the feature code of the electronic signature and the feature code of the authentication electronic signature as the feature distance between the feature code of the electronic signature and the feature code of the authentication electronic signature.

For example, if the feature code of the electronic signature is X(x ₁ , x ₂ , x ₃ …x _n ), and the feature code of the certified electronic signature is Y(y ₁ , y ₂ , y ₃ …y _n ), then the electronic signature The feature distance between the feature code of and the feature code of the certified electronic signature is:

In step S403, the feature distance is subjected to a mapping process, and the feature distance after the mapping process is obtained as the feature similarity between the electronic signature and the authenticated electronic signature.

Specifically, the server maps the characteristic distance to a value belonging to [0, 1], and uses the value as the characteristic similarity between the electronic signature and the authenticated electronic signature.

For example, the server uses the sigmoid function to map the feature distance. For example, the feature distance is used as the input of the sigmoid function, and the feature distance after the mapping process is output through the sigmoid function as the feature similarity between the electronic signature and the authenticated electronic signature.

Further, the server may also determine the feature similarity corresponding to the obtained feature distance according to the preset correspondence between the feature distance and the feature similarity, as the feature similarity between the electronic signature and the authenticated electronic signature.

In this embodiment, comprehensively considering the time series data of the electronic signature and the time series data of the authentication electronic signature, it is beneficial to obtain the dynamic information of the electronic signature and the authentication electronic signature in the time dimension, so that the determined electronic signature and the authentication electronic The feature similarity between the signatures is more accurate, which in turn makes the verification of the electronic signature more accurate, avoiding the defect that only the static information of the electronic signature is considered, which leads to the low accuracy of the verification of the electronic signature.

In one of the embodiments, the above step S401, according to the time series data of the electronic signature and the time series data of the authentication electronic signature, determine the characteristic code of the electronic signature and the characteristic code of the authentication electronic signature, which specifically includes: Serial data and certified electronic signature time series data undergo batch standardization processing to obtain electronic signature standard time series data and certified electronic signature standard time series data; extract the time series features and certified electronic signatures of electronic signature standard time series data respectively According to the time series characteristics in the standard time series data of the electronic signature and the time series characteristics in the standard time series data of the certified electronic signature, the signature code of the electronic signature and the signature code of the certified electronic signature are determined.

Among them, the standard time series data of the electronic signature and the time series data of the certified electronic signature both refer to the time series data whose data distribution is normally distributed; the time series characteristics refer to the characteristics of the electronic signature in the time dimension.

Specifically, the server performs batch standardization processing on the time series data of the electronic signature and the time series data of the certified electronic signature respectively, and obtains the time series data of the electronic signature whose data distribution is a normal distribution and the certified electronic signature whose data distribution is a normal distribution. The time series data corresponding to the standard time series data of the electronic signature and the standard time series data of the certified electronic signature; respectively input the time series data of the electronic signature and the time series data of the certified electronic signature into the feature extraction network, and pass the feature extraction network Extract the time series features in the time series data of the electronic signature and the time series features in the time series data of the authenticated electronic signature; respectively characterize the time series features in the time series data of the electronic signature and the time series data of the authenticated electronic signature The encoding process obtains the feature code of the electronic signature and the feature code of the authenticated electronic signature.

In this embodiment, according to the time series data of the electronic signature and the time series data of the authentication electronic signature, the characteristic code of the electronic signature and the characteristic code of the authentication electronic signature are determined, which is beneficial to follow-up according to the characteristics between the electronic signature and the authentication electronic signature. The similarity determines the verification result of the electronic signature, so as to realize the accurate verification of the electronic signature, thereby improving the verification accuracy of the electronic signature.

In one of the embodiments, the above step S203, determining the feature similarity between the electronic signature and the certified electronic signature according to the time series data of the electronic signature and the time series data of the certified electronic signature, further includes: The sequence data and the time-series data of the certified electronic signature are input into the pre-trained signature verification model to obtain the feature similarity between the electronic signature and the certified electronic signature; the pre-trained signature verification model is used according to the time-series data of the electronic signature and the certified electronic signature. Signature time series data, determine the feature code of the electronic signature and the feature code of the certified electronic signature; determine the feature distance between the feature code of the electronic signature and the feature code of the certified electronic signature; map the feature distance to obtain the mapping process The feature distance of is used as the feature similarity between the electronic signature and the certified electronic signature.

Among them, the pre-trained signature verification model refers to a neural network model that can verify whether two electronic signatures belong to the true signature of the same user. LSTM (Long Short-Term Memory) layer, feature coding layer, feature comparison layer, logistic regression layer.

Specifically, referring to Figure 5, the server inputs the time series data of the electronic signature and the time series data of the authentication electronic signature into the BN layer in the twin deep network model, and the input time series data of the electronic signature and the authentication electronic The signed time series data is processed for batch standardization, and the output data distribution is normally distributed electronic signature time series data, as the standard time series data of electronic signature, and the output data distribution is normal distribution certified electronic signature time series data , As the standard time series data for authenticating electronic signatures; respectively input the standard time series data for electronic signatures and the standard time series data for authenticating electronic signatures into the corresponding double-layer two-way LSTM layer, and extract the time series of electronic signatures through the double-layer two-way LSTM layer The time series characteristics in the data and the time series characteristics in the time series data of the authentication electronic signature, and the time series characteristics in the time series data of the electronic signature and the time series characteristics in the time series data of the authentication electronic signature are respectively input into the corresponding feature encoding layer; The feature encoding layer performs feature encoding processing on the timing features in the time series data of the input electronic signature and the timing features in the time series data for authenticating the electronic signature to obtain a multi-dimensional (such as 64-dimensional) electronic signature feature encoding and A multi-dimensional (such as 64-dimensional) authentication electronic signature feature code, and input the feature code of the electronic signature and the feature code of the authentication electronic signature to the feature comparison layer; calculate the feature code of the electronic signature and the authentication electronic through the feature comparison layer The Euclidean distance between the feature codes of the signature is used as the feature distance between the feature code of the electronic signature and the feature code of the certified electronic signature, and the feature distance is input to the logistic regression layer; the logistic regression layer is based on the sigmoid function, and the feature The distance is mapped to a value belonging to [0,1] as the feature similarity between the electronic signature and the certified electronic signature, and the feature similarity between the electronic signature and the certified electronic signature is output.

In this embodiment, through the pre-trained signature verification model, combined with the time series data of the electronic signature and the time series data of the certified electronic signature, it is beneficial to improve the accuracy of the feature similarity between the obtained electronic signature and the certified electronic signature. Therefore, the subsequent electronic signature verification is more accurate, and the verification accuracy rate of the electronic signature is further improved.

In one of the embodiments, the pre-trained signature verification model is obtained by training in the following way: collecting the time series data of two sample electronic signatures of the same signature and the actual feature similarity of the two sample electronic signatures; The sample time series data of the two sample electronic signatures identified by the signature are input into the signature verification model to be trained, and the feature similarity of the two sample electronic signatures is obtained; the feature similarity of the two sample electronic signatures and the corresponding actual feature similarity are calculated When the error is greater than or equal to the preset threshold, the network parameters of the signature verification model to be trained are adjusted according to the error to obtain the adjusted signature verification model, and the adjusted signature verification model is repeatedly trained until it is trained according to the The error obtained by the subsequent signature verification model is less than the preset threshold.

Among them, the error between the feature similarity of the two sample electronic signatures and the corresponding actual feature similarity is used to measure that the feature similarity of the two sample electronic signatures output by the signature verification model to be trained is similar to the corresponding actual feature The degree of deviation between degrees.

Specifically, based on big data technology, the server collects the time series data of two sample electronic signatures corresponding to multiple identical signatures and the actual feature similarity of the two sample electronic signatures, and identifies the two samples corresponding to multiple identical signatures The time series data of electronic signatures are trained on the signature verification model to be trained, and the trained signature verification model is obtained, and the feature similarity of the two sample electronic signatures output by the trained signature verification model is calculated between the feature similarity of the two samples and the corresponding actual feature similarity. When the error is greater than or equal to the preset threshold, the network parameters in the signature verification model are continuously adjusted, and the signature verification model is repeatedly trained until the error obtained according to the trained signature verification model is less than the preset threshold. The current signature verification model is used as a pre-trained signature verification model.

In this embodiment, the server repeatedly trains the signature verification model through the time series data of two sample electronic signatures identified by the same signature, which can improve the feature similarity between the electronic signature output by the signature verification model and the certified electronic signature. The accuracy rate further improves the verification accuracy rate of the electronic signature.

In one of the embodiments, the above step S204, determining the verification result of the electronic signature according to the feature similarity between the electronic signature and the certified electronic signature, includes: if the feature similarity between the electronic signature and the certified electronic signature is greater than or If it is equal to the preset similarity, it is confirmed that the electronic signature verification is passed; if the feature similarity between the electronic signature and the certified electronic signature is less than the preset similarity, it is confirmed that the electronic signature verification fails.

For example, if the feature similarity between the electronic signature and the certified electronic signature is greater than or equal to 0.7, it means that the electronic signature and the certified electronic signature belong to the same user's true signature, and the electronic signature verification is confirmed; if the electronic signature and the certified electronic signature are both The feature similarity between the two is less than 0.7, indicating that the electronic signature and the certified electronic signature do not belong to the true signature of the same user, and the verification of the electronic signature is confirmed to fail.

In this embodiment, the verification result of the electronic signature is determined based on the feature similarity between the electronic signature and the certified electronic signature, which is conducive to the accurate verification of the electronic signature, and avoids only considering the static information of the electronic signature, which leads to the electronic signature. The shortcomings of low verification accuracy rate further improve the verification accuracy rate of the electronic signature; at the same time, by verifying the electronic signature, it is beneficial to improve the security of the electronic signature process.

In one of the embodiments, if the feature similarity between the electronic signature and the certified electronic signature is greater than or equal to the preset similarity, after confirming that the electronic signature verification is passed, the method further includes: generating an electronic signature verification passed message; The verification is sent to the touch screen input device via a message.

Specifically, after confirming that the electronic signature verification is passed, the server generates an electronic signature verification passed message according to the preset message template, and sends the electronic signature verification passed message to the corresponding touch screen input device, and then the signature interface of the touch screen input device Display the electronic signature verification passed message to remind the user that the signature is successful without repeating the signature.

In another embodiment, if the feature similarity between the electronic signature and the certified electronic signature is less than the preset similarity, after confirming that the electronic signature verification fails, the method further includes: generating an electronic signature verification failure message, and adding the electronic signature The verification failure message is sent to the touch screen input device, and the electronic signature verification failure message is displayed through the signature interface of the touch screen input device to remind the user that the signature is successful; at this time, the user can re-enter the signature.

In one of the embodiments, as shown in FIG. 6, another method for verifying an electronic signature is provided. Taking the method applied to the server in FIG. 1 as an example for description, the method includes the following steps:

Step S601: Collect the time series data of the electronic signature on the touch screen input device; the time series data of the electronic signature carries the signature identifier of the electronic signature.

Step S602: Obtain the time series data of the authenticated electronic signature identified by the signature.

Step S603: Perform batch standardization processing on the time series data of the electronic signature and the time series data of the certified electronic signature, respectively, to obtain the standard time series data of the electronic signature and the standard time series data of the certified electronic signature.

Step S604, extracting the time series features in the standard time series data of the electronic signature and the time series features in the standard time series data of the authentication electronic signature respectively.

Step S605: Determine the feature code of the electronic signature and the feature code of the certification electronic signature according to the time sequence feature in the standard time series data of the electronic signature and the time sequence feature in the standard time series data of the certified electronic signature.

Step S606: Determine the characteristic distance between the characteristic code of the electronic signature and the characteristic code of the authenticated electronic signature.

In step S607, the feature distance is subjected to a mapping process, and the feature distance after the mapping process is obtained as the feature similarity between the electronic signature and the authenticated electronic signature.

In step S608, if the feature similarity between the electronic signature and the certified electronic signature is greater than or equal to the preset similarity, it is confirmed that the electronic signature has passed the verification. In step S609, an electronic signature verification passed message is generated, and the electronic signature verification passed message is uploaded to the blockchain.

Based on the electronic signature verification, the corresponding digest information is obtained through the message. Specifically, the digest information is obtained by the electronic signature verification through the hash processing of the message, for example, obtained by the sha256s algorithm. Uploading summary information to the blockchain can ensure its security and fairness and transparency to users. The user equipment can download the summary information from the blockchain in order to verify whether the electronic signature verification information has been tampered with.

In one of the embodiments, the electronic signature verification can be sent to the touch screen input device through a message.

In this embodiment, comprehensive consideration of the time series data of the electronic signature and the time series data of the authentication electronic signature is conducive to obtaining the dynamic information of the electronic signature in the time dimension, thereby making the verification of the electronic signature more accurate and avoiding only considering the electronic signature. The static information of the signature leads to the defect that the verification accuracy rate of the electronic signature is low, and the verification accuracy rate of the electronic signature is further improved.

It should be understood that although the various steps in the flowcharts of FIGS. 2, 4, and 6 are displayed in sequence as indicated by the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless specifically stated in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least part of the steps in Figures 2, 4, and 6 may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. These steps or stages The execution order of is not necessarily performed sequentially, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.

In one of the embodiments, as shown in FIG. 7, an electronic signature verification device is provided, which includes: a data acquisition module, a data acquisition module, a similarity determination module, and a verification result determination module, wherein:

The data collection module 710 is used to collect the time series data of the electronic signature on the touch screen input device; the time series data of the electronic signature carries the signature identification of the electronic signature.

The data acquisition module 720 is configured to acquire the time series data of the authenticated electronic signature of the signature identification.

The similarity determination module 730 is configured to determine the feature similarity between the electronic signature and the certified electronic signature according to the time series data of the electronic signature and the time series data of the certified electronic signature.

The verification result determination module 740 is configured to determine the verification result of the electronic signature according to the feature similarity between the electronic signature and the certified electronic signature.

In one of the embodiments, the similarity determination module 730 is also used to determine the feature code of the electronic signature and the feature code of the certification electronic signature according to the time series data of the electronic signature and the time series data of the certification electronic signature; determine the characteristics of the electronic signature The feature distance between the code and the feature code of the authenticated electronic signature; the feature distance is mapped to obtain the feature distance after the mapping process, which is used as the feature similarity between the electronic signature and the authenticated electronic signature.

In one of the embodiments, the similarity determination module 730 is further configured to perform batch standardization processing on the time series data of the electronic signature and the time series data of the authentication electronic signature, respectively, to obtain the standard time series data of the electronic signature and the standard time series of the authentication electronic signature. Time series data; respectively extract the time series features in the standard time series data of the electronic signature and the time series features in the standard time series data of the authentication electronic signature; according to the time series characteristics in the standard time series data of the electronic signature and the standard time of the authentication electronic signature The sequence features in the sequence data determine the feature code of the electronic signature and the feature code of the authenticated electronic signature.

In one of the embodiments, the similarity determination module 730 is also used to separately input the time series data of the electronic signature and the time series data of the authentication electronic signature into the pre-trained signature verification model to obtain the characteristics between the electronic signature and the authentication electronic signature. Similarity; the pre-trained signature verification model is used to determine the feature code of the electronic signature and the feature code of the authentication electronic signature according to the time series data of the electronic signature and the time series data of the authentication electronic signature; determine the feature code of the electronic signature and the authentication electronic The feature distance between the feature codes of the signature; the feature distance is mapped to obtain the feature distance after the mapping process, which is used as the feature similarity between the electronic signature and the authenticated electronic signature.

In one of the embodiments, the electronic signature verification device further includes a model training module, which is used to collect the time series data of the two sample electronic signatures of the same signature and the actual feature similarity of the two sample electronic signatures; The sample time series data of the two sample electronic signatures identified by the signature are input into the signature verification model to be trained, and the feature similarity of the two sample electronic signatures is obtained; the feature similarity of the two sample electronic signatures and the corresponding actual feature similarity are calculated When the error is greater than or equal to the preset threshold, the network parameters of the signature verification model to be trained are adjusted according to the error to obtain the adjusted signature verification model, and the adjusted signature verification model is repeatedly trained until it is trained according to the The error obtained by the subsequent signature verification model is less than the preset threshold.

In one of the embodiments, the verification result determination module 740 is further configured to confirm that the electronic signature verification has passed if the feature similarity between the electronic signature and the certified electronic signature is greater than or equal to the preset similarity; If the feature similarity between the two is less than the preset similarity, it is confirmed that the electronic signature verification fails.

In one of the embodiments, the electronic signature verification device further includes a message sending module for generating an electronic signature verification pass message after the verification result determination module 740 confirms that the electronic signature verification is passed; sending the electronic signature verification passed message to the touch screen input equipment.

In each of the above embodiments, the electronic signature verification device realizes the purpose of determining the verification result of the electronic signature in real time according to the time series data of the electronic signature and the time series data of the authentication electronic signature, and comprehensively considers the time series data and the time series data of the electronic signature. Authenticating the time series data of an electronic signature is conducive to obtaining the dynamic information of the electronic signature in the time dimension, thereby making the verification of the electronic signature more accurate, avoiding only considering the static information of the electronic signature, resulting in a lower verification accuracy rate of the electronic signature The defect further improves the verification accuracy of the electronic signature.

Regarding the specific limitation of the verification device of the electronic signature, please refer to the above limitation of the verification method of the electronic signature, which will not be repeated here. Each module in the above-mentioned electronic signature verification device can be implemented in whole or in part by software, hardware, and a combination thereof. The above-mentioned modules may be embedded in the form of hardware or independent of the processor in the computer equipment, or may be stored in the memory of the computer equipment in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

In one of the embodiments, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. 8. The computer equipment includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile or volatile storage medium and internal memory. The non-volatile or volatile storage medium stores an operating system, computer readable instructions, and a database. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in the non-volatile or volatile storage medium. The database of the computer equipment is used to store the time series data of the electronic signature, the time series data of the authentication electronic signature, and so on. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer-readable instruction is executed by the processor to realize an electronic signature verification method.

Those skilled in the art can understand that the structure shown in FIG. 8 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may Including more or fewer parts than shown in the figure, or combining some parts, or having a different arrangement of parts.

A computer device including a memory and one or more processors, and computer-readable instructions are stored in the memory. When the computer-readable instructions are executed by the processor, the steps of the method for verifying an electronic signature provided in any one of the embodiments of the present application are implemented .

One or more computer-readable storage media storing computer-readable instructions. The computer-readable storage media may be non-volatile or volatile. When the computer-readable instructions are executed by one or more processors , Enabling one or more processors to implement the steps of the electronic signature verification method provided in any embodiment of the present application.

The blockchain referred to in this application is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Blockchain, essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information for verification. The validity of the information (anti-counterfeiting) and the generation of the next block. The blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing relevant hardware through computer-readable instructions, which can be stored in a computer-readable storage medium. Here, when the computer-readable instructions are executed, they may include the processes of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, or optical storage. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not a limitation, RAM may be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc.

The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be It is considered as the range described in this specification.

The above-mentioned embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can be made, and these all fall within the protection scope of this application. Therefore, the scope of protection of the patent of this application shall be subject to the appended claims.

Claims (20)

1. An electronic signature verification method, including:

   Collecting the time series data of the electronic signature on the touch screen input device; the time series data of the electronic signature carries the signature identification of the electronic signature;

   Acquiring the time series data of the authenticated electronic signature of the signature identification;

   Determine the feature similarity between the electronic signature and the certified electronic signature according to the time series data of the electronic signature and the time series data of the certified electronic signature; and

   According to the feature similarity between the electronic signature and the certified electronic signature, the verification result of the electronic signature is determined.
2. The method according to claim 1, wherein said determining the feature similarity between said electronic signature and said certified electronic signature based on the time series data of the electronic signature and the time series data of the certified electronic signature ,include:

   Determining the feature code of the electronic signature and the feature code of the certification electronic signature according to the time series data of the electronic signature and the time series data of the certification electronic signature;

   Determining the characteristic distance between the characteristic code of the electronic signature and the characteristic code of the authentication electronic signature; and

   The feature distance is subjected to a mapping process, and the feature distance after the mapping process is obtained as the feature similarity between the electronic signature and the authenticated electronic signature.
3. The method according to claim 2, wherein said determining the feature code of the electronic signature and the feature code of the certification electronic signature based on the time series data of the electronic signature and the time series data of the certification electronic signature ,include:

   Performing batch standardization processing on the time series data of the electronic signature and the time series data of the authentication electronic signature respectively to obtain the standard time series data of the electronic signature and the standard time series data of the authentication electronic signature;

   Extracting the time series features in the standard time series data of the electronic signature and the time series features in the standard time series data of the authentication electronic signature respectively; and

   Determine the feature code of the electronic signature and the feature code of the certified electronic signature according to the time sequence feature in the standard time series data of the electronic signature and the time sequence feature in the standard time series data of the certified electronic signature.
4. The method according to claim 1, wherein said determining the feature similarity between said electronic signature and said certified electronic signature based on the time series data of the electronic signature and the time series data of the certified electronic signature ,Also includes:

   Respectively input the time series data of the electronic signature and the time series data of the certified electronic signature into a pre-trained signature verification model to obtain the feature similarity between the electronic signature and the certified electronic signature;

   Wherein, the pre-trained signature verification model is used to determine the feature code of the electronic signature and the feature code of the certification electronic signature according to the time series data of the electronic signature and the time series data of the certification electronic signature; Determine the feature distance between the feature code of the electronic signature and the feature code of the authentication electronic signature; perform a mapping process on the feature distance to obtain the feature distance after the mapping process, as the electronic signature and the authentication electronic signature The feature similarity between signatures.
5. The method according to claim 4, wherein the pre-trained signature verification model is obtained by training in the following manner:

   Collecting the time series data of the two sample electronic signatures with the same signature and the similarity of the actual features of the two sample electronic signatures;

   Input the sample time series data of the two sample electronic signatures identified by the same signature into the signature verification model to be trained to obtain the feature similarity of the two sample electronic signatures;

   Count the error between the feature similarity of the two sample electronic signatures and the corresponding actual feature similarity; and

   When the error is greater than or equal to a preset threshold, adjust the network parameters of the signature verification model to be trained according to the error to obtain an adjusted signature verification model, and perform repeated training on the adjusted signature verification model , Until the error obtained according to the trained signature verification model is less than the preset threshold.
6. The method according to any one of claims 1 to 5, wherein the determining the verification result of the electronic signature according to the feature similarity between the electronic signature and the certified electronic signature comprises:

   If the feature similarity between the electronic signature and the certified electronic signature is greater than or equal to the preset similarity, confirm that the electronic signature has passed the verification; and

   If the feature similarity between the electronic signature and the certified electronic signature is less than the preset similarity, it is confirmed that the electronic signature verification fails.
7. The method according to claim 6, wherein if the feature similarity between the electronic signature and the certified electronic signature is greater than or equal to a preset similarity, then it is confirmed that the electronic signature verification is passed, The method also includes:

   An electronic signature verification passed message is generated, and the electronic signature verification passed message is uploaded to the blockchain.
8. An electronic signature verification device, including:

   The data collection module is used to collect the time series data of the electronic signature on the touch screen input device; the time series data of the electronic signature carries the signature identification of the electronic signature;

   A data acquisition module for acquiring the time series data of the certified electronic signature of the signature identification;

   The similarity determination module is configured to determine the feature similarity between the electronic signature and the certified electronic signature according to the time series data of the electronic signature and the time series data of the certified electronic signature; and

   The verification result determination module is configured to determine the verification result of the electronic signature according to the feature similarity between the electronic signature and the certified electronic signature.
9. A computer device includes a memory and one or more processors. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the one or more processors, the one or more Each processor performs the following steps:

   Collect the time series data of the electronic signature on the touch screen input device; the time series data of the electronic signature carries the signature identification of the electronic signature;

   Acquiring the time series data of the authenticated electronic signature of the signature identification;

   Determine the feature similarity between the electronic signature and the certified electronic signature according to the time series data of the electronic signature and the time series data of the certified electronic signature; and

   According to the feature similarity between the electronic signature and the certified electronic signature, the verification result of the electronic signature is determined.
10. The computer device according to claim 9, wherein the processor further executes the following steps when executing the computer readable instruction:

    Determining the feature code of the electronic signature and the feature code of the certification electronic signature according to the time series data of the electronic signature and the time series data of the certification electronic signature;

    Determining the characteristic distance between the characteristic code of the electronic signature and the characteristic code of the authentication electronic signature; and

    The feature distance is subjected to a mapping process, and the feature distance after the mapping process is obtained as the feature similarity between the electronic signature and the authenticated electronic signature.
11. The computer device according to claim 10, wherein the processor further executes the following steps when executing the computer-readable instructions:

    Performing batch standardization processing on the time series data of the electronic signature and the time series data of the authentication electronic signature respectively to obtain the standard time series data of the electronic signature and the standard time series data of the authentication electronic signature;

    Extracting the time series features in the standard time series data of the electronic signature and the time series features in the standard time series data of the authentication electronic signature respectively; and

    Determine the feature code of the electronic signature and the feature code of the certified electronic signature according to the time sequence feature in the standard time series data of the electronic signature and the time sequence feature in the standard time series data of the certified electronic signature.
12. The computer device according to claim 9, wherein the processor further executes the following steps when executing the computer readable instruction:

    Respectively input the time series data of the electronic signature and the time series data of the certified electronic signature into a pre-trained signature verification model to obtain the feature similarity between the electronic signature and the certified electronic signature;

    Wherein, the pre-trained signature verification model is used to determine the feature code of the electronic signature and the feature code of the certification electronic signature according to the time series data of the electronic signature and the time series data of the certification electronic signature; Determine the feature distance between the feature code of the electronic signature and the feature code of the authentication electronic signature; perform a mapping process on the feature distance to obtain the feature distance after the mapping process, as the electronic signature and the authentication electronic signature The feature similarity between signatures.
13. The computer device according to claim 12, wherein the processor further executes the following steps when executing the computer readable instruction:

    Collecting the time series data of the two sample electronic signatures with the same signature mark and the similarity of the actual features of the two sample electronic signatures;

    Input the sample time series data of the two sample electronic signatures identified by the same signature into the signature verification model to be trained to obtain the feature similarity of the two sample electronic signatures;

    Count the error between the feature similarity of the two sample electronic signatures and the corresponding actual feature similarity; and

    When the error is greater than or equal to a preset threshold, adjust the network parameters of the signature verification model to be trained according to the error to obtain an adjusted signature verification model, and perform repeated training on the adjusted signature verification model , Until the error obtained according to the trained signature verification model is less than the preset threshold.
14. The computer device according to any one of claims 9 to 13, wherein the processor further executes the following steps when executing the computer readable instruction:

    If the feature similarity between the electronic signature and the certified electronic signature is greater than or equal to the preset similarity, confirm that the electronic signature has passed the verification; and

    If the feature similarity between the electronic signature and the certified electronic signature is less than the preset similarity, it is confirmed that the electronic signature verification fails.
15. One or more computer-readable storage media storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to perform the following steps:

    Collecting the time series data of the electronic signature on the touch screen input device; the time series data of the electronic signature carries the signature identification of the electronic signature;

    Acquiring the time series data of the authenticated electronic signature of the signature identification;

    Determine the feature similarity between the electronic signature and the certified electronic signature according to the time series data of the electronic signature and the time series data of the certified electronic signature; and

    According to the feature similarity between the electronic signature and the certified electronic signature, the verification result of the electronic signature is determined.
16. The storage medium according to claim 15, wherein the following steps are further performed when the computer-readable instructions are executed by the processor:

    Determining the feature code of the electronic signature and the feature code of the certification electronic signature according to the time series data of the electronic signature and the time series data of the certification electronic signature;

    Determining the characteristic distance between the characteristic code of the electronic signature and the characteristic code of the authentication electronic signature; and

    The feature distance is subjected to a mapping process, and the feature distance after the mapping process is obtained as the feature similarity between the electronic signature and the authenticated electronic signature.
17. The storage medium according to claim 16, wherein the following steps are further performed when the computer-readable instructions are executed by the processor:

    Performing batch standardization processing on the time series data of the electronic signature and the time series data of the authentication electronic signature respectively to obtain the standard time series data of the electronic signature and the standard time series data of the authentication electronic signature;

    Extracting the time series features in the standard time series data of the electronic signature and the time series features in the standard time series data of the authentication electronic signature respectively; and

    Determine the feature code of the electronic signature and the feature code of the certified electronic signature according to the time sequence feature in the standard time series data of the electronic signature and the time sequence feature in the standard time series data of the certified electronic signature.
18. The storage medium according to claim 15, wherein the following steps are further performed when the computer-readable instructions are executed by the processor:

    Respectively input the time series data of the electronic signature and the time series data of the certified electronic signature into a pre-trained signature verification model to obtain the feature similarity between the electronic signature and the certified electronic signature;

    Wherein, the pre-trained signature verification model is used to determine the feature code of the electronic signature and the feature code of the certification electronic signature according to the time series data of the electronic signature and the time series data of the certification electronic signature; Determine the feature distance between the feature code of the electronic signature and the feature code of the authentication electronic signature; perform a mapping process on the feature distance to obtain the feature distance after the mapping process, which is used as the electronic signature and the authentication electronic signature The feature similarity between signatures.
19. The storage medium according to claim 18, wherein the following steps are further performed when the computer-readable instructions are executed by the processor:

    Collecting the time series data of the two sample electronic signatures with the same signature and the similarity of the actual features of the two sample electronic signatures;

    Input the sample time series data of the two sample electronic signatures identified by the same signature into the signature verification model to be trained to obtain the feature similarity of the two sample electronic signatures;

    Count the error between the feature similarity of the two sample electronic signatures and the corresponding actual feature similarity; and

    When the error is greater than or equal to a preset threshold, adjust the network parameters of the signature verification model to be trained according to the error to obtain an adjusted signature verification model, and perform repeated training on the adjusted signature verification model , Until the error obtained according to the trained signature verification model is less than the preset threshold.
20. The storage medium according to any one of claims 15 to 19, wherein the following steps are further executed when the computer-readable instructions are executed by the processor:

    If the feature similarity between the electronic signature and the certified electronic signature is greater than or equal to the preset similarity, confirm that the electronic signature has passed the verification; and

    If the feature similarity between the electronic signature and the certified electronic signature is less than the preset similarity, it is confirmed that the electronic signature verification fails.

Images