WO2023078115A1

WO2023078115A1 - Information verification method, and server and storage medium

Info

Publication number: WO2023078115A1
Application number: PCT/CN2022/127061
Authority: WO
Inventors: 白雪
Original assignee: 中兴通讯股份有限公司
Priority date: 2021-11-04
Filing date: 2022-10-24
Publication date: 2023-05-11
Also published as: CN116074033A

Abstract

The embodiments of the present disclosure belong to the technical field of communications. Provided are an information verification method, and a server and a storage medium. The method comprises: reading identity verification information and biological feature information of a person to be subjected to verification; and verifying health risk information of said person according to the identity verification information and the biological feature information.

Description

Information verification method, server and storage medium

Cross References to Related Applications

This disclosure claims the priority of the Chinese patent application CN202111302427.3 filed on November 04, 2021, entitled "Information Verification Method, Server and Storage Medium", the entire content of which is incorporated into this disclosure by reference.

technical field

The present disclosure relates to the field of communication technologies, and in particular, to an information verification method, a server and a storage medium.

Background technique

In recent years, as the new crown epidemic has raged around the world, normalized, intelligent and convenient epidemic prevention is very important. The user's health risk level is a key indicator of epidemic prevention. At present, the health risk level is displayed by the health code. The health code is based on real data. The user declares online by himself, and after being reviewed by the relevant department, the generated health code belongs to the user. Personal QR code. The health code serves as an electronic certificate for the user when entering and exiting. When epidemic diseases are widely spread in society, the efficient management of mobile personnel can be realized through the health code, for example, in office buildings, shopping malls, subways, and railway stations. In places with dense crowds, check the health code to improve the efficiency of inspections and avoid excessive contact and gathering of people. However, the current health code verification used for epidemic prevention has the problems of low security and low verification efficiency, which increases the difficulty of epidemic prevention work.

Contents of the invention

Embodiments of the present disclosure provide an information verification method, a server, and a storage medium, aiming at improving the efficiency and accuracy of verifying the health risk level of personnel to be verified.

An embodiment of the present disclosure provides an information verification method, including: reading identity verification information and biometric information of a person to be verified; and verifying health risk information of the person to be verified according to the identity verification information and biometric information.

An embodiment of the present disclosure provides a server, the server includes a processor, a memory, a computer program stored on the memory and executed by the processor, and a data bus for realizing connection and communication between the processor and the memory, wherein the computer program is processed When the device is executed, it realizes the steps of any one of the information verification methods provided in the present disclosure.

An embodiment of the present disclosure provides a storage medium for computer-readable storage. The storage medium stores one or more programs. When the one or more programs are executed by one or more processors, any of the functions provided in the present disclosure can be realized. Steps in a health code verification method.

Description of drawings

FIG. 1 is a schematic flowchart of an information verification method provided by an embodiment of the present disclosure;

Fig. 2 is a schematic flow chart of the sub-steps of the information verification method in Fig. 1;

FIG. 3 is another schematic flowchart of an information verification method provided by an embodiment of the present disclosure;

FIG. 4 is a schematic diagram of a scenario of an information verification method provided by an embodiment of the present disclosure;

FIG. 5 is another schematic flowchart of an information verification method provided by an embodiment of the present disclosure;

FIG. 6 is another schematic flowchart of an information verification method provided by an embodiment of the present disclosure;

Fig. 7 is a schematic structural block diagram of a server provided by an embodiment of the present disclosure.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present disclosure with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are part of the embodiments of the present disclosure, not all of them. Based on the embodiments in the present disclosure, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present disclosure.

The flow charts shown in the drawings are just illustrations, and do not necessarily include all contents and operations/steps, nor must they be performed in the order described. For example, some operations/steps can be decomposed, combined or partly combined, so the actual order of execution may be changed according to the actual situation.

It should be understood that the terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the present disclosure. As used in this disclosure and the appended claims, the singular forms "a", "an" and "the" are intended to include plural referents unless the context clearly dictates otherwise.

Embodiments of the present disclosure provide an information verification method, a server, and a storage medium. Wherein, the information verification method can be applied to a server, and the server can be a single server, or a server cluster composed of multiple single servers. For example, the server obtains the identity verification information and biometric information of the person to be verified; and then verifies the health risk level of the person to be verified according to the identity verification information and biometric information.

Some embodiments of the present disclosure will be described in detail below in conjunction with the accompanying drawings. In the case of no conflict, the following embodiments and features in the embodiments can be combined with each other.

Please refer to FIG. 1 . FIG. 1 is a schematic flowchart of an information verification method provided by an embodiment of the present disclosure.

As shown in FIG. 1 , the method for verifying information includes steps S101 to S102.

Step S101, reading the identity verification information and biometric information of the person to be verified.

Obtain the identity verification information and biometric information of the person to be verified transmitted by the terminal device, wherein the identity verification information includes at least one of the first password information of the person to be verified and the device ID of the terminal device, and the biometric information includes at least one of the following : Voiceprint feature information, iris feature information, face feature information and fingerprint feature information. Wherein, the terminal device can be selected according to the actual situation, which is not specifically limited in this embodiment. For example, the terminal device can be a gate, an access control device, a mobile phone and other devices. The communication mode between the terminal device and the server can be selected according to the actual situation, which is not specifically limited in this embodiment, for example, identity verification information and biometric information are sent through 5G messages.

Exemplarily, the terminal device is a gate, and the gate collects the identity verification information and biometric information of the person to be verified, and sends the identity verification information and biometric information of the person to be verified to the server through a 5G message, so that the server reads the The identity verification information and biometric information of the person to be verified. Sending identity verification information and biometric information through 5G messages does not require the installation of additional applications on the terminal device, and can be completed using the native interface of the terminal device, which greatly improves the convenience, efficiency and security of transmission.

Step 102, verifying the health risk information of the person to be verified according to the identity verification information and biometric information.

Wherein, the health risk information may include a health risk level, and the health risk level may include a first health risk level and a second health risk level, the first health risk level may be low risk, and the second health risk level may be high risk.

In one embodiment, as shown in FIG. 2, step 102 includes sub-steps S1021 to sub-steps S1022.

Sub-step S1021. Obtain the biometric information database that matches the first password information.

Wherein, the first password information includes at least one of the following: voice password information, gesture action information, facial action information, for example, the first password information is preset voice password information, and the voice password information can be set according to the actual situation , which is not specifically limited in this embodiment, for example, the voice password information may be "Open Sesame".

In one embodiment, the second password information corresponding to each biometric information database is obtained, and the matching degree between the first password information and each second password information is determined; the matching degree is greater than or equal to the preset matching degree The biometric information database is determined to be the biometric information database that matches the first password information. Wherein, the preset matching degree may be set according to actual conditions, which is not specifically limited in this embodiment. By matching the first secret code information with a plurality of second secret code information, the biological feature information library whose matching degree is greater than or equal to the preset matching degree is determined as the biological feature information database matching the first secret code information, thereby improving the biological feature information. Accuracy of library matching.

In one embodiment, the second code information corresponding to each biometric information database is obtained, and the matching degree between the first code information and each second code information is determined to obtain multiple matching degrees; according to the matching degree Sorting the multiple matching degrees, and when the largest matching degree is greater than or equal to the preset matching degree, determining the biometric information database corresponding to the largest matching degree as the biometric information database matching the first password information. Wherein, the sorting of the matching degree may be performed according to the matching degree from small to large, or may be sorted according to the matching degree from large to small, which is not specifically limited in this embodiment. The efficiency of determining the biometric information base can be improved by sorting multiple matching degrees. Of course, it is also possible to select the matching degree according to the needs among the various matching degrees greater than or equal to the preset matching degree, and determine the biometric information database corresponding to the selected matching degree as the biometric information database matching the first password information. The embodiment does not specifically limit this.

In an embodiment, the manner of determining the matching degree between the first encrypted information and each second encrypted information may be as follows: performing Euclidean distance calculation on the first encrypted information and each second encrypted information to obtain the first The Euclidean distance between the first cipher information and each second cipher information, obtain the preset mapping relationship table between the Euclidean distance and the matching degree, and according to the mapping relationship table and the Euclidean distance, A degree of matching between the first encrypted message and each second encrypted message is determined. Wherein, the mapping relationship table may be established in advance according to the Euclidean distance and matching degree, or may be established according to actual conditions, which is not specifically limited in this embodiment.

Exemplarily, there are biometric information database 1, biological characteristic information database 2, biological characteristic information database 3, biological characteristic information database 4 and biological characteristic information database 5, and the biological characteristic information database 1 corresponds to the second password information as A, biological characteristic The information database 2 corresponds to the second password information as B, the biological characteristic information database 3 corresponds to the second password information as C, the biological characteristic information database 4 corresponds to the second password information as D, and the biological characteristic information database 5 corresponds to the second password information as E, The first encrypted information is a, and the Euclidean distance calculation is performed on the first encrypted information a and the second encrypted information A to obtain the Euclidean distance A; the first encrypted information a and the second encrypted information B are Euclidean Calculate the Euclidean distance to obtain the Euclidean distance B; calculate the Euclidean distance between the first encrypted message a and the second encrypted message C to obtain the Euclidean distance C; combine the first encrypted message a with the second The Euclidean distance calculation is performed on the encrypted information D to obtain the Euclidean distance D; the Euclidean distance calculation is performed on the first encrypted information a and the second encrypted information E to obtain the Euclidean distance E. Obtain the preset mapping relationship table between Euclidean distance and matching degree, query from the mapping relationship table to obtain the matching degree corresponding to Euclidean distance A is 95%, and the matching degree corresponding to Euclidean distance B The matching degree corresponding to the Euclidean distance C is 60%, the matching degree corresponding to the Euclidean distance D is 20%, and the matching degree corresponding to the Euclidean distance E is 25%. Among them, the preset matching degree is 90%, and the matching degree is sorted according to the matching degree from large to small as matching degree 95%, matching degree 60%, matching degree 40%, matching degree 25% and matching degree 20%, and the maximum matching degree is matching degree of 95%, and the matching degree of 95% is greater than the preset matching degree of 90%, the biometric information library 1 corresponding to the matching degree of 95% is used as the biometric information library matching the first password information.

In an embodiment, when no biometric information database matching the first password information is obtained according to the first password information, the identity verification information of the person to be verified is acquired again. The accuracy of health risk level verification can be improved by reacquiring the identity verification information of the person to be verified.

Sub-step S1022, verifying the health risk information of the person to be verified according to the biometric information database and the biometric information.

In an embodiment, the biometric information includes voiceprint feature information, the biometric information library includes a first voiceprint model library, and the first voiceprint model library includes a plurality of first voiceprint models. Determine the first matching score between the voiceprint feature information and each first voiceprint model; determine the target first voiceprint model according to multiple first matching scores, and use the health risk level corresponding to the target first voiceprint model as the target The health risk level of the inspector. By determining the target first voiceprint model according to multiple first matching scores, and accurately determining the health risk level of the person to be verified according to the health risk level corresponding to the first voiceprint model, the determined health risk of the person to be verified is improved level of accuracy.

In an embodiment, the manner of determining the first matching score between the voiceprint feature information and each first voiceprint model may be: input the voiceprint feature information into each first voiceprint model for processing to obtain the voiceprint The first matching probability between the feature information and each first voiceprint model; input the voiceprint feature information into the first voiceprint background model corresponding to the first voiceprint model library for processing, and obtain the voiceprint feature information and the first voiceprint model The second matching probability between the fingerprint background models; according to the first matching probability and the second matching probability, determine the first matching score between the voiceprint feature information and each first voiceprint model. By determining the first matching probability between the voiceprint feature information and each first voiceprint model, determine the second matching probability between the voiceprint feature information and the first voiceprint background model, according to the first matching probability and the second The matching probability can accurately determine the first matching score between the voiceprint feature information and each first voiceprint model.

In an embodiment, according to the first matching probability and the second matching probability, the method of determining the first matching score between the voiceprint feature information and each first voiceprint model may be: taking the logarithm of the first matching probability , to obtain the third matching probability; take the logarithm of the second matching probability to obtain the fourth matching probability; subtract the fourth matching probability from the third matching probability to obtain the first matching probability between the voiceprint feature information and the first voiceprint model match score.

In an embodiment, the method of using the health risk level corresponding to the first voiceprint model as the health risk level of the person to be verified may be: determine the target person corresponding to the first voiceprint model, obtain the health risk level of the target person, The health risk level of the target person is used as the health risk level of the person to be verified.

Exemplarily, the first matching score formula is obtained, wherein the first matching score formula is S ₁ =logP ₁ -logP ₂ , S ₁ is the first matching score, P ₁ is the difference between the voiceprint feature information and the first voiceprint model _P2 is the second matching probability between the voiceprint feature information and the first voiceprint background model. Based on the first matching score formula, the voiceprint is generated according to the first matching probability and the second matching probability. The first matching score between the fingerprint feature information and the first voiceprint model.

In an embodiment, the method of determining the target first voiceprint model according to the multiple first matching scores may be as follows: selecting the first matching score greater than or equal to the first threshold from the multiple first matching scores to obtain multiple candidate voiceprint models. The first matching score: sort multiple candidate first matching scores according to the size of the matching scores to obtain a candidate first matching score queue, and select the largest candidate first matching score from the candidate first matching score queue as the target first matching score , taking the first voiceprint model corresponding to the target first matching score as the target first voiceprint model. Wherein, the first threshold can be set according to the actual situation, which is not specifically limited in this embodiment; the sorting of multiple candidate first matching scores can be sorted according to the matching scores from large to small, or can be sorted according to the matching scores from small to small. Sort to large. Certainly, in some implementation manners, candidate first matching scores other than the largest candidate first matching score may also be selected as the target first matching score.

In one embodiment, the identity verification information includes the device ID of the terminal device, and the first voiceprint model matching the device ID is acquired; the second matching score between the voiceprint feature information and the first voiceprint model is determined; When the matching score is greater than or equal to the second threshold, the health risk level corresponding to the first voiceprint model is used as the health risk level of the person to be verified. Wherein, the second threshold may be set according to actual conditions, which is not specifically limited in this embodiment. The device ID is used to determine whether the health risk level of the person to be verified has passed the verification, which can improve the efficiency of the verification of the health risk level of the person to be verified.

In an embodiment, the method of obtaining the first voiceprint model matching the device ID may be: obtaining the pre-stored device ID corresponding to each first voiceprint model, and the first voiceprint corresponding to the pre-stored device ID matching the device ID The fingerprint model is used as the first voiceprint model matched with the device ID. Wherein, the first voiceprint model has one or more corresponding pre-stored device IDs, the correspondence between the first voiceprint model and the pre-stored device IDs may be preset, and the first voiceprint model and the pre-stored device IDs may be based on actual It is set according to the situation, which is not specifically limited in this embodiment. In one embodiment, the method of calculating the second matching score between the voiceprint feature information and the first voiceprint model may be the same as the way of calculating the first matching score between the voiceprint feature information and each first voiceprint model Same, therefore, the method of calculating the second matching score between the voiceprint feature information and the first voiceprint model can refer to the way of calculating the first matching score between the voiceprint feature information and each first voiceprint model.

In one embodiment, when no biometric information library matching the first password information is obtained, or when each first matching score is less than the first threshold, or the second matching score is less than the second threshold, the second The voiceprint model library, the second voiceprint model library includes a plurality of second voiceprint models; determine the third matching score between the voiceprint feature information and each first voiceprint model, and determine the voiceprint feature information and each The fourth matching score between the second voiceprint models; when each third matching score is less than the third threshold, and each fourth matching score is less than the fourth threshold, it is determined that the health risk information of the person to be verified is normal ; When there is a third matching score greater than or equal to the third threshold and/or a fourth matching score greater than or equal to the fourth threshold, it is determined that the health risk information of the person to be verified is abnormal. Wherein, the third threshold and the fourth threshold may be set according to actual conditions, which is not specifically limited in this embodiment. By determining the third matching score and the fourth matching score, and according to the third matching score and the fourth matching score, it can be accurately determined whether the person to be verified has passed the verification.

In an embodiment, the manner of determining the third matching score between the voiceprint feature information and each first voiceprint model may be: input the voiceprint feature information into each first voiceprint model for processing to obtain the voiceprint The fifth matching probability between the feature information and each first voiceprint model; input the voiceprint feature information into the first voiceprint background model corresponding to the first voiceprint model library for processing, and obtain the voiceprint feature information and the first voiceprint model The sixth matching probability between the fingerprint background models; according to the fifth matching probability and the sixth matching probability, determine the third matching score between the voiceprint feature information and each first voiceprint model. By determining the fifth matching probability between the voiceprint feature information and each first voiceprint model, determine the sixth matching probability between the voiceprint feature information and the first voiceprint background model, according to the fifth matching probability and the sixth The matching probability can accurately determine the third matching score between the voiceprint feature information and each first voiceprint model.

In an embodiment, according to the fifth matching probability and the sixth matching probability, the manner of determining the third matching score between the voiceprint feature information and each first voiceprint model may be: take the logarithm of the fifth matching probability , to obtain the seventh matching probability; take the logarithm of the sixth matching probability to obtain the eighth matching probability; subtract the eighth matching probability from the seventh matching probability to obtain the third matching probability between the voiceprint feature information and the first voiceprint model match score.

Exemplarily, the third matching score formula is obtained, wherein the third matching score formula is S ₂ =logP ₃ -logP ₄ , S ₂ is the third matching score, P ₃ is the difference between the voiceprint feature information and the first voiceprint model is the fifth matching probability between the voiceprint feature information and the first voiceprint background model, _{and P4} is the sixth matching probability between the voiceprint feature information and the first voiceprint background model. Based on the third matching score formula, the voice The third matching score between the fingerprint feature information and the first voiceprint model.

In an embodiment, the method of determining the fourth matching score between the voiceprint feature information and each second voiceprint model may be: input the voiceprint feature information into each second voiceprint model for processing to obtain the voiceprint The ninth matching probability between the feature information and each second voiceprint model; input the voiceprint feature information into the second voiceprint background model corresponding to the second voiceprint model library for processing, and obtain the voiceprint feature information and the second voiceprint model. The tenth matching probability between the fingerprint background models; according to the ninth matching probability and the tenth matching probability, a fourth matching score between the voiceprint feature information and each second voiceprint model is determined. By determining the ninth matching probability between the voiceprint feature information and each second voiceprint model, determine the tenth matching probability between the voiceprint feature information and the second voiceprint background model, according to the ninth matching probability and the tenth matching probability The matching probability can accurately determine the fourth matching score between the voiceprint feature information and each second voiceprint model.

In an embodiment, according to the ninth matching probability and the tenth matching probability, the method of determining the fourth matching score between the voiceprint feature information and each second voiceprint model may be: taking the logarithm of the ninth matching probability , to obtain the eleventh matching probability; take the logarithm of the tenth matching probability, and obtain the twelfth matching probability; subtract the eleventh matching probability from the twelfth matching probability, and obtain the difference between the voiceprint feature information and the second voiceprint model The fourth match score between.

Exemplarily, the fourth matching score formula is obtained, wherein the fourth matching score formula is S ₃ =logP ₅ −logP ₆ , S ₃ is the fourth matching score, and P ₅ is the difference between the voiceprint feature information and the second voiceprint model. is the ninth matching probability between the voiceprint feature information and the second voiceprint background model, _{and P6} is the tenth matching probability between the voiceprint feature information and the second voiceprint background model. Based on the fourth matching score formula, according to the ninth matching probability and the tenth matching probability, a voice The fourth matching score between the fingerprint feature information and the second voiceprint model.

Exemplarily, as shown in Figure 3, the identity verification information is the device ID, and the biometric information is voiceprint feature information. The method includes step S201, obtaining the device ID and biometric information of the person to be verified, and step S202, judging whether there is The pre-stored device ID matching the device ID, step S203, when there is a pre-stored device ID matching the device ID, obtain the first voiceprint model corresponding to the pre-stored device ID, and determine the relationship between the voiceprint feature information and the first voiceprint model The second matching score, step S204, judging whether the second matching score is greater than or equal to the second threshold, step S205, when the second matching score is greater than or equal to the second threshold, taking the health risk level corresponding to the first voiceprint model as the level to be verified The health risk level of the person, step S206, if there is no pre-stored device ID matching the device ID and/or the second matching score is less than the second threshold, obtain the second voiceprint model library, and according to the first voiceprint model library, the second 2. The voiceprint model library and the voiceprint feature information determine whether the person to be verified has passed the verification.

In an embodiment, after verifying the health risk level of the person to be verified, the health risk level of the person to be verified is sent to the terminal device, so that the terminal device performs the next operation. Wherein, the next step of operation of the terminal device can be set according to the actual situation, which is not specifically limited in this embodiment. For example, when the terminal device is an access control device, when the health risk level of the person to be verified is the first risk level, the The door is opened to allow the person to be checked to pass through, and when the health risk level of the person to be checked is the second risk level, the door is not opened and an alarm is sounded.

Exemplarily, as shown in Figure 4, the access control device A collects the first password information and voiceprint feature information of the person to be verified, and the access control device A sends the first password information and voiceprint feature information to the server B, and the server B according to the first password information and voiceprint feature information A password information and voiceprint feature information, verify that the health risk level of the person to be verified is the first risk level, then the health risk level of the person to be verified passes the verification, generate an access control command, and send the command to the access control Device A, so that the access control device A opens the access control, so that the personnel to be verified can pass.

In one embodiment, the biometric model is iris feature information, and the target iris feature information that matches the iris feature information is screened out from the iris feature information database, and the health risk level corresponding to the target iris feature information is used as the health risk of the person to be verified. grade. Wherein, the iris characteristic information database is established in advance according to the health risk level and iris characteristic information, and the iris characteristic information database can also be established according to the actual situation, which is not specifically limited in this embodiment.

In one embodiment, as shown in FIG. 5 , the method further includes step S301 to step S305.

Step S301. Obtain a health code generation request, wherein the health code generation request includes the password information, voiceprint feature information and health risk level of the target person applying for the health code.

Wherein, the password information includes at least one of the following: voice password information, gesture action information, and facial action information. For example, when the password information is voice password information, the voice password information can be "Hello" and/or "Open Sesame", etc. Password, the health risk level is the risk level of the target person, for example, the health risk level includes a first risk level and a second risk level, the first risk level may correspond to a low risk, and the second risk level may correspond to a high risk.

In one embodiment, the mobile terminal used by the target person obtains the target person's password information, voiceprint feature information and health risk level, and generates a health code generation request according to the password information, voiceprint feature information and health risk level. The mobile terminal sends the health code generation request to the server, so that the server receives the target person's health code generation request. Wherein, the mobile terminal can be selected according to actual conditions, which is not specifically limited in this embodiment. For example, the mobile terminal can be electronic devices such as mobile phones, tablets, and smart watches.

The communication mode between the mobile terminal and the server can be selected according to the actual situation, which is not specifically limited in this embodiment, for example, the health code generation request is sent through a 5G message. Sending the health code generation request through 5G messages has the following advantages: the phone number of the target person can be used as the identity information of the target person, and no additional identity authentication is required when the mobile terminal interacts with the server. Therefore, the mobile terminal does not need to install additional application programs, and can obtain location information and complete information interaction in real time.

In one embodiment, the mobile terminal collects voice password information sent by the target person, performs voice-to-text conversion on the voice password information, and obtains password information of the verification personnel. The voiceprint feature extraction is performed on the voice password information to obtain the voiceprint feature information. The feature information of the voiceprint can be obtained accurately by extracting the voice password information.

The voice-to-text conversion of the voice-to-text information is performed to obtain the password information of the target personnel, which can be selected according to the actual situation. This embodiment does not specifically limit this. Perform voice-to-text conversion to obtain cipher information. The speech-to-text conversion model and the speech recognition model may be neural network models or other recognition models, which are not specifically limited in this embodiment.

In one embodiment, the voiceprint feature extraction is performed on the voice password information to obtain the voiceprint feature information may be: the voiceprint feature information includes Mel frequency cepstral coefficients, and the voice password information is pre-emphasized and framed and windowing, perform fast Fourier transform on each short-time analysis window to obtain the frequency spectrum corresponding to each short-time analysis window, and filter each frequency spectrum through the preset filter bank to obtain multiple Mel frequency spectrums. Cepstrum analysis is performed on multiple mel spectra to obtain mel frequency cepstral coefficients. Among them, the cepstrum analysis includes processing such as logarithm and inverse transformation of the mel spectrum. The voiceprint feature information can be obtained accurately by performing voiceprint feature extraction on the voice password information. In one embodiment, before voiceprint feature extraction is performed on the voice password information, preprocessing may be performed on the voice password information. The preprocessing includes noise suppression, blind separation, endpoint detection, and AI noise reduction processing. Through the above preprocessing The accuracy and efficiency of extracting voiceprint feature information from voice password information can be improved.

In an embodiment, the way to obtain the health risk level of the target person may be: to obtain the target person's identity information, location information, physical health status information, collection time stamp and related health risk level of the associated person, according to the target person's The identity information, location information, physical health status information, collection time stamp and the health risk level of related associated personnel are used to generate the health risk level of the target person. Wherein, the identity information may include the target person's name, mobile phone number, ID number and device ID (Identity Document, identity identification number) of the mobile terminal, and the health status information may include body temperature information and/or whether the target person has a cough, etc. For information on abnormal physical conditions, the associated person is a person related to the target person, and the associated person can be set according to the actual situation. For example, the associated person can be a person who lives with the target person. According to the target person's identity information, location information, physical health status information, collection time stamp and the health risk level of related related personnel, the health risk level of the target person can be accurately generated.

In an embodiment, the health risk level of the target person is generated according to the target person's identity information, physical health status information, location information, collection time stamp and the health risk level of related associated persons. The method of generating the health risk level of the target person can be as follows: obtain the preset identity weight coefficient, physical health status weight coefficient, positioning and collection time weight coefficient, and the health risk level weight coefficient of related associated personnel, and combine the identity information with the identity Multiplication of weight coefficient, multiplication of physical health status information and weight coefficient of physical health status, multiplication of positioning information and collection time stamp by weight coefficient of positioning and collection time, health risk level of relevant associated personnel and health risk of relevant associated personnel Multiply the grade weight coefficients to obtain the first weight value, the second weight value, the third weight value and the fourth weight value respectively, and add the first weight value, the second weight value, the third weight value and the fourth weight value Calculate the health risk score of the target person. The health risk level of the target person is determined according to the health risk score. Wherein, the preset identity weight coefficient, physical health weight coefficient, positioning and collection time weight coefficient, and the health risk level weight coefficient of relevant associated personnel can be set according to the actual situation, which is not specifically limited in this embodiment. Identity information may also include occupational information of the target person. By determining the health risk score of the target person, the health risk level of the target person can be accurately obtained according to the health risk score.

In an embodiment, the method of determining the health risk level of the target person according to the health risk score may be: obtain a mapping relationship table between the preset health risk score and the health risk level, and query the health risk level from the mapping relationship table. The health risk level corresponding to the risk score is used to obtain the health risk level of the target person. Wherein, the mapping relationship table is established in advance according to the health risk score and the health risk level, and the mapping relationship table can also be established according to the actual situation, which is not specifically limited in this embodiment. The health risk level of the target personnel can be accurately determined through the mapping relationship table.

Step S302, adding the voiceprint feature information into the first voiceprint feature information library corresponding to the password information.

The password information is matched with the standard password information corresponding to the first voiceprint feature information base of each of the first risk levels, and the voiceprint feature information is added to the first voiceprint feature information base with the highest matching degree.

In an embodiment, the manner of matching the secret code information with the standard secret code information corresponding to the first voiceprint feature information database of each of the first risk levels may be: Euclidean Euclidean analysis of the secret code information and each standard secret code information Calculate the distance to obtain the Euclidean distance between the cipher information and each standard cipher information, and obtain the preset mapping relationship table between the Euclidean distance and the matching degree. According to the mapping relationship table and the Euclidean The distance determines how well the cipher message matches each standard cipher message. Wherein, the mapping relationship table may be established in advance according to the Euclidean distance and the matching degree, or may be established according to actual conditions, which is not specifically limited in this embodiment.

Step S303, generating a first voiceprint background model corresponding to the password information according to the first voiceprint feature information library.

Based on the preset first algorithm, the first voiceprint feature information library is processed to obtain the first voiceprint background model corresponding to the password information. Wherein, the preset first algorithm may be selected according to the situation, which is not specifically limited in this embodiment, for example, the preset first algorithm may be an expectation maximization algorithm (Expectation Maximization Algorithm, EM algorithm). The first voiceprint background model corresponding to the password information can be accurately obtained by performing calculation processing on the first voiceprint feature information library through the preset first algorithm.

Exemplarily, the predetermined first algorithm is the EM algorithm, and the first voiceprint feature information database is processed by the EM algorithm to obtain the first voiceprint background model θ _μ = (μ _μ , σ _μ , α _μ ), θ _μ is the model parameter of the first voiceprint background model, μ _μ is the expectation of the model parameter, σ _μ is the variance of the model parameter, and α _μ is the weight of the model parameter.

Step S304, generating a first voiceprint model according to the first voiceprint background model and voiceprint feature information.

Based on the preset second algorithm, the first voiceprint background model and the voiceprint feature information are processed to obtain the first voiceprint model corresponding to the voiceprint feature information. Wherein, the preset second algorithm can be selected according to the actual situation, which is not specifically limited in this embodiment. For example, the preset second algorithm can be a maximum a posteriori probability (Maximum a Posteriori Probability, MAP algorithm). Through the preset second algorithm, the first voiceprint background model and the voiceprint feature information can be calculated and processed, and the first voiceprint model corresponding to the voiceprint feature information can be accurately obtained.

Exemplarily, the preset second algorithm is the MAP algorithm. Based on the MAP algorithm, the model parameters of the first voiceprint background model are adjusted according to the voiceprint feature information to obtain the first voiceprint model θ ₁ =(μ ₁ , σ ₁ , α ₁ ), where θ ₁ is the model parameter of the first voiceprint model, μ ₁ is the expectation of the model parameter, σ ₁ is the variance of the model parameter, and α ₁ is the weight of the model parameter.

Step S305, storing the first voiceprint model into the first voiceprint model library corresponding to the password information, and adding the first voiceprint model and health risk level into the health code file of the target person.

After obtaining the first voiceprint model of the target person, store the first voiceprint model in the first voiceprint model library corresponding to the password information, and add the first voiceprint model and the first risk level to the health of the target person Code files to complete the establishment of the target personnel's health code.

In one embodiment, as shown in FIG. 6 , after step S301 , step S306 to step S308 are further included.

Step S306, when the health risk level is the second risk level, add the voiceprint feature information to the second voiceprint feature information database.

Exemplarily, there are target person 1, target person 2, target person 3, target person 4 and target person 5, wherein the health risk level of target person 1 and target person 4 is the second risk level, and the sound of target person 1 The fingerprint feature information 1 and the voiceprint feature information 4 of the target person 4 are added to the second voiceprint feature information database.

Step S307, generating a second voiceprint background model according to the second voiceprint feature information library, and generating a second voiceprint model according to the second voiceprint background model and the voiceprint feature information.

Based on the preset first algorithm, the second voiceprint feature information library is processed to obtain the second voiceprint background model. Wherein, the preset first algorithm may be selected according to the situation, which is not specifically limited in this embodiment, for example, the preset first algorithm may be an expectation maximization algorithm (Expectation Maximization Algorithm, EM algorithm). The second voiceprint background model can be accurately obtained by performing calculation processing on the second voiceprint feature information library through the preset first algorithm.

Exemplarily, the predetermined first algorithm is the EM algorithm, and the second voiceprint feature information library is processed by the EM algorithm to obtain the second voiceprint background model θ _h = (μ _h , σ _h , α _h ), θ _h is the model parameter of the second voiceprint background model, μ _h is the expectation of the model parameter, σ _h is the variance of the model parameter, and α _h is the weight of the model parameter.

In an embodiment, based on a preset second algorithm, the second voiceprint background model and the voiceprint feature information are processed to obtain the second voiceprint model corresponding to the voiceprint feature information. Wherein, the preset second algorithm can be selected according to the actual situation, which is not specifically limited in this embodiment. For example, the preset second algorithm can be a maximum a posteriori probability (Maximum a Posteriori Probability, MAP algorithm). Through the preset second algorithm, the second voiceprint background model and the voiceprint feature information are processed to accurately obtain the second voiceprint model corresponding to the voiceprint feature information.

Exemplarily, the preset second algorithm is the MAP algorithm. Based on the MAP algorithm, the model parameters of the second voiceprint background model are adjusted according to the voiceprint feature information to obtain the second voiceprint model θ ₂ =(μ ₂ , σ ₂ , α ₂ ), where θ ₂ is the model parameter of the second voiceprint model, μ ₂ is the expectation of the model parameter, σ ₂ is the variance of the model parameter, and α ₂ is the weight of the model parameter.

Step S308, storing the second voiceprint model into the second voiceprint model database, and adding the second voiceprint model into the health code file of the target person.

After obtaining the second voiceprint model of the target person, store the second voiceprint model in the second voiceprint model library, and add the second voiceprint model and the second risk level to the health code file of the target person, so as to Complete the establishment of the health code of the target person.

In one embodiment, when the health risk level of the target person changes from the first risk level to the second risk level, the voiceprint feature information of the target person is added to the second voiceprint feature information library corresponding to the second risk level, and A second voiceprint background model and a second voiceprint model corresponding to the voiceprint feature information are generated. Store the second voiceprint model of the target person in the second voiceprint model library, add the second voiceprint model to the health code file of the target person, and adjust the voiceprint model of the target person, which can improve the accuracy of subsequent health checks. Real-time performance of risk level verification.

In one embodiment, when the health risk level of the target person is changed from the first risk level to the second risk level, related persons related to the target person are obtained; and the health risk level and the voiceprint model of the related person are updated. By updating the health risk level and voiceprint model of associated personnel, the accuracy and efficiency of epidemic prevention management can be improved.

In one embodiment, the location information of the target person is acquired at preset intervals, and the health risk level of the target person is determined according to the location information and collection time. When the health risk level of the target person changes, the voiceprint model of the target person is updated. , and update the health risk level and voiceprint model of the associated person.

The information verification method in the above embodiment reads the identity verification information and biometric information of the person to be verified; and then verifies the health risk information of the person to be verified according to the identity verification information and biometric information. According to the identity verification information and biometric information, this solution will check the health risk level of the inspectors, which can avoid cheating in manual verification and reduce the risk of personal information leakage caused by the release of flow transfer, and improve the accuracy of health risk level verification. Efficiency and safety.

Please refer to FIG. 7 . FIG. 7 is a schematic structural block diagram of a server provided by an embodiment of the present disclosure.

As shown in FIG. 7, the server 400 includes a processor 401 and a memory 402, and the processor 401 and the memory 402 are connected through a bus 403, such as an I2C (Inter-integrated Circuit) bus.

In one embodiment, the processor 401 is used to provide computing and control capabilities to support the operation of the entire server. The processor 401 can be a central processing unit (Central Processing Unit, CPU), and the processor 401 can also be other general processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC) ), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Wherein, the general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

In one embodiment, the memory 402 may be a Flash chip, a read-only memory (ROM, Read-Only Memory) disk, an optical disk, a U disk, or a mobile hard disk.

The structure shown in FIG. 7 is only a block diagram of a part of the structure related to the disclosed solution, and does not constitute a limitation to the server on which the disclosed solution is applied. The server may include more or less than shown in the figure. components, or combine certain components, or have a different arrangement of components.

Wherein, the processor is configured to run a computer program stored in the memory, and implement any one of the information verification methods provided by the embodiments of the present disclosure when executing the computer program.

In one embodiment, the processor is used to run a computer program stored in the memory, and implement the following steps when executing the computer program: read the identity verification information and biometric information of the person to be verified; , verify the health risk information of the person to be verified.

In an embodiment, when the processor realizes that the identity verification information includes the first password information of the person to be verified, and verifies the health risk information of the person to be verified according to the identity verification information and biometric information, the processor is used to realize: acquiring and first The biometric information database matching the password information; verify the health risk information of the person to be verified according to the biometric information database and biometric information.

In an embodiment, when the processor obtains the biometric information library matching the first password information, it is configured to: acquire the second password information corresponding to each biometric information library, and determine the first password information and The degree of matching between each second code information: determining the biometric information database whose matching degree is greater than or equal to the preset matching degree as the biometric information database matching the first cryptographic information.

In one embodiment, the processor implements that the biometric information includes voiceprint feature information, the biometric information library includes a first voiceprint model library, and the first voiceprint model library includes a plurality of first voiceprint models. library and biometric information, when verifying the health risk information of the person to be verified, it is used to: determine the first matching score between the voiceprint feature information and each first voiceprint model; determine the target according to multiple first matching scores The first voiceprint model, using the health risk level corresponding to the target first voiceprint model as the health risk level of the person to be verified.

In an embodiment, when determining the first matching score between the voiceprint feature information and each first voiceprint model, the processor is configured to: input the voiceprint feature information into each first voiceprint model for Processing to obtain the first matching probability between the voiceprint feature information and each first voiceprint model; input the voiceprint feature information into the first voiceprint background model corresponding to the first voiceprint model library for processing to obtain the voiceprint feature A second matching probability between the information and the first voiceprint background model; according to the first matching probability and the second matching probability, a first matching score between the voiceprint feature information and each first voiceprint model is determined.

In an embodiment, when the processor realizes that the identity verification information includes the device ID of the terminal device; and when verifying the health risk information of the person to be verified according to the biometric information database and the biometric information, the processor is used to realize: obtaining the information that matches the device ID The first voiceprint model; determine the second matching score between the voiceprint feature information and the first voiceprint model; when the second matching score is greater than or equal to the second threshold, use the health risk level corresponding to the first voiceprint model as The health risk level of the personnel to be verified.

In an embodiment, the processor is further configured to implement: when no biometric information library matching the first password information is obtained, or when each first matching score is less than the first threshold, or the second matching score When it is less than the second threshold, obtain a second voiceprint model library, the second voiceprint model library includes a plurality of second voiceprint models; determine the third matching score between the voiceprint feature information and each first voiceprint model, And determine the fourth matching score between the voiceprint feature information and each second voiceprint model; when each third matching score is less than the third threshold, and each fourth matching score is less than the fourth threshold, determine The health risk information of the person to be verified is normal; when there is a third matching score greater than or equal to the third threshold and/or a fourth matching score greater than or equal to the fourth threshold, it is determined that the health risk information of the person to be verified is abnormal.

In an embodiment, the processor is also used to: obtain a health code generation request, wherein the health code generation request includes the password information, voiceprint feature information and health risk level of the target person applying for the health code; The feature information is added to the first voiceprint feature information library corresponding to the password information; the first voiceprint background model corresponding to the password information is generated according to the first voiceprint feature information library; the first voiceprint background model is generated according to the first voiceprint background model and the voiceprint feature information. Voiceprint model: store the first voiceprint model in the first voiceprint model library corresponding to the password information, and add the first voiceprint model and health risk level to the health code file of the target person.

In an embodiment, the processor is further configured to implement: when the health risk level is the second risk level, add the voiceprint feature information to the second voiceprint feature information library; generate the first voiceprint feature information library according to the second voiceprint feature information library. Two voiceprint background models, and generate a second voiceprint model according to the second voiceprint background model and voiceprint feature information; store the second voiceprint model in the second voiceprint model library, and add the second voiceprint model In the health code file of the target person.

Those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the server described above can refer to the corresponding process in the foregoing embodiment of the information verification method, which will not be repeated here.

An embodiment of the present disclosure also provides a storage medium for computer-readable storage. The storage medium stores one or more programs, and one or more programs can be executed by one or more processors, so as to implement the information provided in this disclosure specification. The steps of any one of the health code verification methods.

Wherein, the storage medium may be an internal storage unit of the server in the foregoing embodiments, such as a hard disk or memory of the server. The storage medium can also be an external storage device of the server, such as a plug-in hard disk equipped on the server, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash memory card (Flash Card) and the like.

Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, the functional modules/units in the system, and the device can be implemented as software, firmware, hardware, and an appropriate combination thereof. In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be composed of several physical components. Components cooperate to execute. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). As known to those of ordinary skill in the art, the term computer storage media includes both volatile and nonvolatile media implemented in any method or technology for storage of information, such as computer readable instructions, data structures, program modules, or other data. permanent, removable and non-removable media. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD), or optical disk storage, magnetic cartridges, tape, magnetic disk storage, or other magnetic storage devices, or can Any other medium used to store desired information and which can be accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal transported by such as a carrier wave or other transport mechanism and may include any information delivery media.

The term "and/or" used in the present disclosure and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations. In this disclosure, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or system comprising a set of elements includes not only those elements explicitly listed, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or system. Without further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical or different elements in the process, method, article or system comprising the element.

The serial numbers of the above-mentioned embodiments of the present disclosure are for description only, and do not represent the advantages and disadvantages of the embodiments. The above is only a specific embodiment of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person familiar with the technical field can easily think of various equivalents within the technical scope of the present disclosure. Modifications or replacements should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be determined by the protection scope of the claims.

Claims

A method for verifying information, including:

Read the identity verification information and biometric information of the person to be verified;

Verifying the health risk information of the person to be verified according to the identity verification information and the biometric information.
The information verification method according to claim 1, wherein the identity verification information includes the first password information of the person to be verified, and the verification of the person to be verified is based on the identity verification information and the biometric information. Health risk information for verifiers, including:

Obtaining a biometric information library that matches the first password information;

Verifying the health risk information of the person to be verified according to the biometric information database and the biometric information.
The information verification method according to claim 2, wherein said obtaining the biometric information library matching the first password information comprises:

Acquiring the second password information corresponding to each biometric information database, and determining the matching degree between the first password information and each of the second password information;

Determining the biometric information database whose matching degree is greater than or equal to the preset matching degree as the biological characteristic information database matching the first password information.
The information verification method according to claim 2, wherein the biometric information includes voiceprint feature information, the biometric information library includes a first voiceprint model library, and the first voiceprint model library includes a plurality of The first voiceprint model, the verification of the health risk information of the person to be verified according to the biometric information database and the biometric information includes:

determining a first matching score between the voiceprint feature information and each of the first voiceprint models;

The target first voiceprint model is determined according to the plurality of first matching scores, and the health risk level corresponding to the target first voiceprint model is used as the health risk level of the person to be verified.
The information verification method according to claim 4, wherein said determining the first matching score between said voiceprint feature information and each of said first voiceprint models comprises:

inputting the voiceprint feature information into each of the first voiceprint models for processing to obtain a first matching probability between the voiceprint feature information and each of the first voiceprint models;

inputting the voiceprint feature information into a first voiceprint background model corresponding to the first voiceprint model library for processing, and obtaining a second matching probability between the voiceprint feature information and the first voiceprint background model ;

A first matching score between the voiceprint feature information and each of the first voiceprint models is determined according to the first matching probability and the second matching probability.
The information verification method according to claim 4, wherein the identity verification information includes the device ID of the terminal device; and the health of the person to be verified is verified according to the biometric information database and the biometric information Risk information, including:

Obtain the first voiceprint model matching the device ID;

determining a second matching score between the voiceprint feature information and the first voiceprint model;

When the second matching score is greater than or equal to a second threshold, the health risk level corresponding to the first voiceprint model is used as the health risk level of the person to be verified.
The information verification method according to claim 4, wherein the method further comprises:

Acquire the second voiceprint when no biometric information library matching the first password information is obtained, or when each of the first matching scores is less than the first threshold, or the second matching score is less than the second threshold A model library, the second voiceprint model library includes a plurality of second voiceprint models;

determining a third matching score between the voiceprint feature information and each of the first voiceprint models, and determining a fourth matching score between the voiceprint feature information and each of the second voiceprint models ;

When each of the third matching scores is less than a third threshold, and each of the fourth matching scores is less than a fourth threshold, determining that the health risk information of the person to be verified is normal;

When one of the third matching scores is greater than or equal to a third threshold and/or one of the fourth matching scores is greater than or equal to a fourth threshold, it is determined that the health risk information of the person to be verified is abnormal.
The information verification method according to any one of claims 1-7, wherein the method further comprises:

Obtain a health code generation request, wherein the health code generation request includes the password information, voiceprint feature information and health risk level of the target person applying for the health code;

Adding the voiceprint feature information to the first voiceprint feature information database corresponding to the password information;

generating a first voiceprint background model corresponding to the cipher information according to the first voiceprint feature information library;

generating a first voiceprint model according to the first voiceprint background model and the voiceprint feature information;

The first voiceprint model is stored in the first voiceprint model library corresponding to the password information, and the first voiceprint model and the health risk level are added to the health code file of the target person.
The information verification method according to claim 8, wherein the method further comprises:

When the health risk level is the second risk level, adding the voiceprint feature information to a second voiceprint feature information database;

generating a second voiceprint background model according to the second voiceprint feature information library, and generating a second voiceprint model according to the second voiceprint background model and the voiceprint feature information;

The second voiceprint model is stored in a second voiceprint model library, and the second voiceprint model is added to the health code file of the target person.
A server, wherein the server includes a processor, a memory, a computer program stored on the memory and executed by the processor, and data for realizing connection communication between the processor and the memory bus, wherein when the computer program is executed by the processor, the steps of the information verification method according to any one of claims 1 to 9 are realized.
A storage medium for computer-readable storage, wherein the storage medium stores one or more programs, and when the one or more programs are executed by one or more processors, the claims 1 to 9 are implemented The steps of the information verification method described in any one.