CN109815803B

CN109815803B - Face examination risk control method and device, computer equipment and storage medium

Info

Publication number: CN109815803B
Application number: CN201811552004.5A
Authority: CN
Inventors: 汪国栋
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2018-12-18
Filing date: 2018-12-18
Publication date: 2023-04-18
Anticipated expiration: 2038-12-18
Also published as: CN109815803A

Abstract

The application relates to a face examination risk control method and device, computer equipment and a storage medium. The method relates to a micro-expression recognition technology, which comprises the following steps: receiving a face examination request message sent by a terminal, and acquiring to-be-examined verification information corresponding to the face examination request message; acquiring verification question and answer data corresponding to the to-be-examined verification information from a preset verification question and answer database; performing face examination verification on the to-be-face examination and verification information through the verification question-answer data to obtain an information verification result; acquiring face examination video data, wherein the face examination video data is obtained by recording when face examination is carried out; respectively inputting the face examination video data into a preset micro-expression pneumatic control model and a face recognition model to obtain a micro-expression pneumatic control result and a face recognition result; and obtaining a face examination wind control result according to the information verification result, the micro-expression wind control result, the face recognition result and a preset wind control weight coefficient. By adopting the method, the effect of the face examination risk control can be improved.

Description

Face examination risk control method and device, computer equipment and storage medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for controlling a risk of a face examination, a computer device, and a storage medium.

Background

With the development of internet technology, more and more business systems provide business services through various application programs, such as social services provided by social applications and online shopping provided by online shopping platform applications, so that the life of people is greatly facilitated. Generally, when a terminal user requests a relevant service in each application program, a corresponding service form needs to be filled in to provide required user information, and a service system verifies and verifies the user information, so that service risk control is performed, and service safety is ensured.

However, most of the user information provided by the terminal user in the current business system is verified and verified offline by professional verification personnel, especially the business service related to large amount of money needs to be verified and verified online and offline, the credibility of the information verification in the face check process is greatly influenced by personal influence factors of the face check personnel, and the risk control effect in the face check process is limited.

Disclosure of Invention

In view of the above, it is necessary to provide a face examination risk control method, apparatus, computer device, and storage medium capable of improving the effect of face examination risk control.

A method of interview risk control, the method comprising:

receiving a face examination request message sent by a terminal, and acquiring to-be-examined verification information corresponding to the face examination request message;

acquiring verification question and answer data corresponding to the to-be-examined verification information from a preset verification question and answer database;

performing face examination verification on the to-be-face examination and verification information through the verification question-answering data to obtain an information verification result;

acquiring face examination video data, wherein the face examination video data is obtained by recording when face examination is carried out;

respectively inputting the face examination video data into a preset micro-expression pneumatic control model and a face recognition model to obtain a micro-expression pneumatic control result and a face recognition result, wherein the micro-expression pneumatic control model is obtained by training historical micro-expression pneumatic control data;

and obtaining a face examination wind control result according to the information verification result, the micro-expression wind control result, the face recognition result and a preset wind control weight coefficient.

In one embodiment, before receiving the face examination request message sent by the terminal, the method further includes:

receiving a service request message sent by a terminal, and determining the service type of the service request message;

inquiring a preset service template form corresponding to the service type from the service system, and issuing the service template form to the terminal;

receiving a service form returned by the terminal, wherein the service form is obtained by editing and updating the service template form by the terminal;

the acquiring of the to-be-faced audit verification information corresponding to the face audit request message comprises the following steps:

and inquiring a business form corresponding to the face examination request message, and extracting the to-be-faced examination and verification information from the business form.

In one embodiment, the obtaining of the validation question-answer data corresponding to the to-be-validated validation information from the preset validation question-answer database includes:

determining user identification information and service identification information corresponding to the to-be-examined and verified information;

determining a user authentication level corresponding to the user identification information and a service authentication level corresponding to the service identification information;

obtaining an information verification level according to the user verification level, the service verification level and a preset level weight factor;

and acquiring the verification question-answer data corresponding to the to-be-examined verification information from a preset verification question-answer database according to the information verification level.

In one embodiment, the verification question-answer data includes verification question data and verification answer data corresponding to the verification question data; performing face examination verification on the to-be-face examination and verification information through the verification question-answer data, and obtaining an information verification result, wherein the information verification result comprises the following steps:

issuing verification problem data to a terminal;

receiving verification response data returned by the terminal, wherein the verification response data is obtained by performing response processing on verification problem data through the terminal;

and carrying out verification comparison on the verification response data and the verification answer data to obtain an information verification result.

In one embodiment, before acquiring the face-examination video data, the method further includes:

generating a recording request message;

issuing a recording request message to the terminal, wherein the recording request message is used for indicating the terminal to record the video when the terminal is subjected to face examination verification;

acquiring the face examination video data comprises the following steps:

and receiving the face examination video data returned by the terminal.

In one embodiment, the step of inputting the face examination video data into a preset micro-expression pneumatic control model and a preset face recognition model respectively to obtain a micro-expression pneumatic control result and a face recognition result comprises:

respectively extracting micro-expression characteristic data and face recognition characteristic data from the face examination video data;

inquiring a preset micro expression pneumatic control model and a face recognition model;

inputting the micro-expression characteristic data into a micro-expression air control model to obtain a micro-expression air control result;

and inputting the face recognition characteristic data into the face recognition model to obtain a face recognition result.

In one embodiment, before querying the preset micro-expression profile model, the method further includes:

acquiring historical micro-expression wind control data from each service system, wherein the historical micro-expression wind control data comprises micro-expression data and wind control data corresponding to the micro-expression data;

extracting micro-expression characteristic parameters from the micro-expression data, and establishing mapping between the micro-expression characteristic parameters and the wind control data;

and training the micro-expression characteristic parameters and the wind control data to obtain a micro-expression wind control model.

An interview risk control device, the device comprising:

the face examination request receiving module is used for receiving a face examination request message sent by the terminal and acquiring the information to be examined and verified corresponding to the face examination request message;

the verification data acquisition module is used for acquiring verification question and answer data corresponding to the to-be-examined verification information from a preset verification question and answer database;

the face examination and verification processing module is used for carrying out face examination and verification on the face examination and verification information through the verification question and answer data to obtain an information verification result;

the face examination video acquisition module is used for acquiring face examination video data, and the face examination video data is obtained by recording during face examination and verification;

the system comprises a face examination video processing module, a face examination video processing module and a face recognition module, wherein the face examination video processing module is used for respectively inputting face examination video data into a preset micro-expression pneumatic control model and a preset face recognition model to obtain a micro-expression pneumatic control result and a face recognition result, and the micro-expression pneumatic control model is obtained by training historical micro-expression pneumatic control data;

and the face audit wind control processing module is used for obtaining a face audit wind control result according to the information verification result, the micro expression wind control result, the face recognition result and a preset wind control weight coefficient.

A computer device comprising a memory storing a computer program and a processor implementing the following steps when the computer program is executed:

A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:

acquiring face examination video data, wherein the face examination video data is obtained by recording during face examination and verification;

and obtaining a face audit wind control result according to the information verification result, the micro expression wind control result, the face recognition result and a preset wind control weight coefficient.

According to the face examination risk control method, the face examination risk control device, the computer equipment and the storage medium, face examination is carried out through the question and answer data corresponding to the to-be-examined information, an information examination result is obtained, face examination video data recorded during face examination are obtained, the face examination video data are respectively input into the preset micro-expression pneumatic control model and the preset face recognition model, the micro-expression pneumatic control result and the face recognition result are obtained, the face examination pneumatic control result is obtained by combining the information examination result, the micro-expression pneumatic control result and the face recognition result according to the preset pneumatic control weight coefficient, and the face examination pneumatic control result is used for face examination risk control. In the face examination risk control process, the face examination is verified through verifying the question and answer data, and comprehensive risk control is performed through face examination video data recorded during face examination, so that professional face examiners do not need to directly participate in face examination information verification, the influence of artificial factors is avoided, and the effect of face examination risk control is effectively improved.

Drawings

FIG. 1 is a diagram of an application scenario of a face review risk control method in one embodiment;

FIG. 2 is a schematic flow chart of a risk control method for interview in one embodiment;

FIG. 3 is a schematic flow chart diagram illustrating the validation of question-answer data acquisition in one embodiment;

FIG. 4 is a schematic flow chart of a risk control method for interview in another embodiment;

FIG. 5 is a block diagram of an embodiment of an audit risk control device;

FIG. 6 is a diagram of the internal structure of a computer device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The review risk control method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal device 102 communicates with the server 104 via a network. The terminal device 102 sends a face examination request message to the server 104, the server 104 obtains corresponding to-be-faced examination information according to the face examination request message, performs face examination through the verification question-answer data corresponding to the to-be-faced examination information to obtain an information verification result, obtains face examination video data recorded during face examination, inputs the face examination video data into a preset micro-expression wind control model and a preset face recognition model respectively to obtain a micro-expression wind control result and a face recognition result, obtains a face examination wind control result according to a preset wind control weight coefficient and combines the information verification result, the micro-expression wind control result and the face recognition result, and the face examination wind control result is used for face examination risk control. The terminal device 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.

In one embodiment, as shown in fig. 2, a method for controlling a risk of a face examination is provided, which is described by taking the method as an example applied to the server 104 in fig. 1, and includes the following steps:

step S201: and receiving a face examination request message sent by the terminal, and acquiring the to-be-examined verification information corresponding to the face examination request message.

Generally, a service request message is sent from a terminal to the server 104 to request a relevant service, and the server 104 issues a corresponding service template form according to the service type of the service request message, so as to obtain user information required by the service, such as user information such as name, identification number, region, income, mobile phone number, and academic information. After the user information returned by the terminal meets the face-examination requirement, such as the integrity requirement of the user information, the server 104 sends a face-examination notification message to the terminal to prompt the terminal to perform a subsequent face-examination verification process. In this embodiment, after the terminal receives the face examination notification message sent by the server 104, the service user of the terminal may select an appropriate time to perform the face examination request verification.

Specifically, a face examination request message is sent by the terminal to the server 104 to request the business system to perform face examination verification on the provided user information. After receiving the face-examination request message, the server 104 obtains corresponding to-be-face-examination information, which may be user information provided by the terminal. In specific implementation, user information provided by the terminal can be intensively stored in a preset database to be subjected to surface examination, and when a surface examination request message is received, corresponding verification information to be subjected to surface examination is extracted from the database to be subjected to surface examination so as to perform subsequent verification processing on the surface examination information.

Step S203: and acquiring the verification question-answer data corresponding to the to-be-examined verification information from a preset verification question-answer database.

The question and answer verification database is constructed in advance according to historical information verification data of the service system, and verification question and answer data corresponding to various to-be-examined verification information are stored in the question and answer verification database. In a specific application, the verification question-answer data may include verification question data and verification answer data corresponding to the verification question data, where the verification question data is question data for the to-be-examined verification information, and the verification answer data is a reference answer corresponding to the verification question data.

Specifically, after obtaining the to-be-examined verification information, querying a preset verification question-answer database, and obtaining corresponding verification question-answer data from the preset verification question-answer database. During specific implementation, the information verification level of the to-be-examined information can be further determined, and the verification question and answer data can be obtained from the verification question and answer database according to the information verification level. The information authentication level can embody the authentication strength of the to-be-examined authentication information, and the higher the information authentication level is, the higher the authentication strength is, i.e., deeper and more comprehensive verification and authentication are performed, such as a larger authentication range, more authentication items, and the like, so as to ensure the authenticity and reliability of the information authentication.

Step S205: and performing face examination verification on the to-be-face examination and verification information through the verification question-answer data to obtain an information verification result.

And after the verification question-answer data corresponding to the to-be-subjected examination information is obtained, performing surface examination verification on the to-be-subjected examination information through the verification question-answer data to obtain an information verification result. Specifically, when the verification question-answer data includes verification question data and verification answer data corresponding to the verification question data, the verification question data in the verification question-answer data may be issued to the terminal, and the terminal performs response processing on the verification question data. For example, when the to-be-examined verification information is address information, the verification problem data comprises verification problems such as weather, landmark buildings, landmark building distances, commute time and the like, the verification problems are issued to the terminal, a service user of the terminal performs response processing on the verification problems, verification response data returned by the terminal and verification answer data in the verification question-answer data are verified and compared to obtain an information verification result, and therefore manual direct participation is avoided to achieve verification and verification processing on user information.

Step S207: and acquiring the face examination video data, wherein the face examination video data is obtained by recording during face examination.

The video data of the face examination is obtained by recording when the face examination is verified, and the video data of the face examination can be obtained by recording a video through a front camera of the terminal. In this embodiment, when performing a face examination verification on the face examination verification information through the verification question and answer data, a front-facing camera of the terminal is used for performing a face examination video recording, and the recorded face examination video data records morphological data such as a mood, an expression, an action and the like of a service user of the terminal in the face examination verification process. Through the form data, risk control such as micro expression analysis and face recognition processing can be carried out, and therefore the effect of face examination wind control is improved.

Step S209: and respectively inputting the face examination video data into a preset micro-expression pneumatic control model and a face recognition model to obtain a micro-expression pneumatic control result and a face recognition result, wherein the micro-expression pneumatic control model is obtained by training historical micro-expression pneumatic control data.

And after the face examination video data are obtained, inputting the face examination video data into a preset micro-expression pneumatic control model and a preset face recognition model respectively to obtain a micro-expression pneumatic control result and a face recognition result. The micro-expression wind control model is obtained by training historical micro-expression wind control data; the face recognition model can be obtained by training various face data.

Specifically, the micro expression wind control model can identify micro expressions, such as happiness, fear, anger, disgust, surprise, slight and the like, of the business user in the face examination video data, analyze the micro expressions of the business user to obtain quantitative degrees, such as positive, calm, tension and the like, of each emotional state of the business user in the face examination verification process, and finally comprehensively output a micro expression wind control result. The micro-expression style control result can be used for anti-fraud reference to judge whether a service user has fraud behaviors, so that risk control is realized. In addition, the face recognition model can perform face recognition on the business user in the face audit video data so as to verify the identity of the business user, judge whether the business user operates or not and further ensure the face audit risk control effect.

Step S211: and obtaining a face examination wind control result according to the information verification result, the micro-expression wind control result, the face recognition result and a preset wind control weight coefficient.

After the information verification result, the micro-expression wind control result and the face recognition result are obtained, weighting processing can be carried out according to the actual business wind control requirement, and the face examination wind control result can be obtained. Specifically, a preset wind control weight coefficient may be obtained, and the wind control weight coefficient is set according to the actual service wind control requirement, and is used for performing weighting processing on the information verification result, the micro-expression wind control result, and the face recognition result, so as to reflect the importance degree of the information verification result, the micro-expression analysis, and the face recognition.

During specific implementation, the information verification result, the micro-expression wind control result and the face recognition result can be embodied by the risk value after quantitative processing, and the face audit wind control result is a face audit wind control score. If the information verification result is the information verification risk value, the micro-expression pneumatic control result is the micro-expression risk value, the face recognition result is the biological recognition risk value, and by combining the information verification result, the micro-expression pneumatic control result and the weight factor corresponding to the face recognition result which are included in the pneumatic control weight coefficient, the face examination pneumatic control score can be obtained after multiplication and addition calculation, and can be used for risk control in the face examination process. For example, in the case of percentile quantization, if the information verification risk value is 30, the corresponding information weight factor is 0.6; the microexpression risk value is 60, and the corresponding microexpression weight factor is 0.25; if the biometric risk value is 20 and the corresponding biometric weight factor is 0.15, an audit-related score of (30 × 0.6) + (60 × 0.25) + (20 × 0.15) =36 can be calculated, which may be referred to as a user risk control.

And after the wind control weight coefficient is obtained, combining the information verification result, the micro-expression wind control result and the face recognition result, calculating to obtain a face-examination wind control result, wherein the face-examination wind control result reflects the fraud degree of the service user of the terminal in the face-examination verification process and can be used as a risk control reference when the service request message of the service user of the terminal is approved. For example, if the face examination wind control result is the face examination wind control score, the risk judgment can be performed according to the numerical value of the face examination wind control score, and if the face examination wind control score is higher, the corresponding risk is higher, which indicates that a service user may have a fraud behavior in the face examination and verification process, so that the face examination risk control on the service is realized.

According to the face examination risk control method, face examination is carried out through the question and answer verification data corresponding to the face examination information to obtain an information verification result, face examination video data recorded during face examination are obtained, the face examination video data are respectively input into a preset micro-expression pneumatic control model and a face recognition model to obtain a micro-expression pneumatic control result and a face recognition result, then the face examination pneumatic control result is obtained by combining the information verification result, the micro-expression pneumatic control result and the face recognition result according to a preset pneumatic control weight coefficient, and the face examination pneumatic control result is used for face examination risk control. In the face examination risk control process, the face examination is verified through verifying the question and answer data, and comprehensive risk control is performed through face examination video data recorded during face examination, so that professional face examiners do not need to directly participate in face examination information verification, the influence of artificial factors is avoided, and the effect of face examination risk control is effectively improved.

In one embodiment, before receiving the face examination request message sent by the terminal, the method further includes: receiving a service request message sent by a terminal, and determining the service type of the service request message; inquiring a preset service template form corresponding to the service type from the service system, and issuing the service template form to the terminal; and receiving a service form returned by the terminal, wherein the service form is obtained by editing and updating the service template form by the terminal.

In this embodiment, before the terminal sends the review request message to the server 104, the method further includes a step of sending user information to the server 104. Specifically, the terminal sends a service request message to the server 104 to request a relevant service, and different service systems need to collect different user information, that is, the service systems obtain the required user information through different service forms.

After receiving the service request message sent by the terminal, the server 104 determines the service type of the service request message, and queries a preset service template form corresponding to the service type from the service system. The service template form is used for collecting user information, and each service field included in the service template form is set according to the actual requirement of the service type. For example, identity information, contact information, family information, work information, income information, credit information, and the like may be included. And after the service template form corresponding to the service request message is obtained, the service template form is issued to the terminal, the terminal edits and fills the service template form, the filled service template form is returned to the server 104, and the user information required by the service system can be extracted from the service template form.

Further, the obtaining of the to-be-subjected-surface-examination information corresponding to the surface-examination request message includes: and inquiring a business form corresponding to the face examination request message, and extracting the to-be-faced examination and verification information from the business form.

In this embodiment, when obtaining the to-be-examined verification information, the service form corresponding to the face-examined request message may be queried first, and then the corresponding to-be-examined verification information is extracted from the service form. In specific implementation, user information provided by a terminal can be intensively stored in a preset database to be subjected to surface examination and classified storage according to service users, when a surface examination request message is received, a service form corresponding to the service user is inquired from the database to be subjected to surface examination, and corresponding verification information to be subjected to surface examination is extracted from the service form so as to perform subsequent surface examination information verification processing.

In one embodiment, as shown in fig. 3, the step of obtaining the validation question-answer data, that is, obtaining the validation question-answer data corresponding to the to-be-fronted examination information from a preset validation question-answer database, includes:

step S301: and determining user identification information and service identification information corresponding to the to-be-examined and verified information.

In this embodiment, for the verification question and answer data corresponding to the to-be-verified information, different to-be-verified information is provided with different information verification levels, and the information verification levels may be related to the service users and the service types corresponding to the to-be-verified information, that is, different service users and different service types may be provided with different information verification levels, so that verification resources are fully utilized, verification effectiveness is ensured, and verification efficiency of the to-be-verified information is improved.

Specifically, after receiving the face examination request message, determining user identification information and service identification information corresponding to the information to be verified. The user identification information may be IDentity information that uniquely identifies a service user, and may include, but is not limited to, a name, an IDentity card number, a service ID (IDentity) number, and the like; the service identification information may include a service name, a service code, and identification data for distinguishing each service type. In specific application, the user identification information and the service identification information can be directly extracted from the to-be-examined and verified information.

Step S303: and determining a user authentication level corresponding to the user identification information and a service authentication level corresponding to the service identification information.

And after the user identification information and the service identification information are obtained, respectively determining a user verification level corresponding to the user identification information and a service verification level corresponding to the service identification information. The user authentication level can be determined according to the risk data of the corresponding service user, and the higher the risk of the service user is, the higher the user authentication level is. In specific application, a preset user risk database can be queried, the user risk database stores user risk data of each service user, and corresponding user risk data can be queried through user identification information of the service user. And inquiring user risk data corresponding to the user identification information from the user risk database, inquiring a preset user level table, and determining a user authentication level corresponding to the user risk data according to the user level table, namely the user authentication level corresponding to the user identification information.

The service verification level can be determined according to the wind control requirement of the corresponding service type, and the service verification level is higher for the service type with high wind control requirement. In specific application, firstly, the service type corresponding to the service identification information is determined, the corresponding service system is inquired according to the service type, and a preset service wind control form is obtained from the service system. The business wind control form records business verification levels corresponding to various business types, and the business verification levels are obtained according to the actual wind control requirements of various business systems. For example, for financial services related to large amounts of money, such as loan services, insurance services, and the like, the wind control requirement is high, and the corresponding service verification level is high; for social networking services, for example, where the wind demand is low, a lower level of business authentication may be set. And inquiring to obtain a service verification level corresponding to the service type from the service wind control form, namely the service verification level corresponding to the service identification information.

Step S305: and obtaining an information verification level according to the user verification level, the service verification level and a preset level weight factor.

And after the user authentication level and the service authentication level are determined, the user authentication level and the service authentication level are integrated to obtain an information authentication level corresponding to the to-be-authenticated information. Specifically, a preset level weight factor is queried, and the level weight factor can be set according to actual requirements to integrate importance degrees of service users and service types, so that a suitable information verification level is obtained. The information verification level is obtained through calculation according to the user verification level, the service verification level and the level weight factor, the risk data of the service user and the wind control requirements of the service type are integrated through the information verification level, the user angle and the service angle are subjected to weight adjustment according to actual requirements, and the information verification efficiency can be improved on the premise that the information verification effect is guaranteed.

Step S307: and acquiring the verification question and answer data corresponding to the to-be-examined verification information from a preset verification question and answer database according to the information verification level.

And after the information verification level corresponding to the to-be-examined verification information is obtained, querying a preset verification question-answer database, and acquiring corresponding verification question-answer data from the verification question-answer database according to the information verification level. During specific implementation, the to-be-examined and verified information of various information types can be provided with a corresponding verification question-answer database, and corresponding verification question-answer data are stored in the verification question-answer database.

When the verification question and answer data corresponding to the to-be-examined information is obtained, the information type corresponding to the to-be-examined information is determined, and different verification question and answer data are set in the to-be-examined information of different information types. For example, for address class information, academic calendar class information, work class information, contact information, and the like, different validation question and answer data are corresponded. And inquiring a corresponding verification question-answer database according to the information type, and acquiring verification question-answer data corresponding to the information verification level from the verification question-answer database, namely the verification question-answer data corresponding to the to-be-examined information.

In one embodiment, the validation question-answer data includes validation question data and validation answer data corresponding to the validation question data; performing face examination verification on the to-be-face examination and verification information through the verification question-answer data, and obtaining an information verification result, wherein the information verification result comprises the following steps: issuing verification problem data to a terminal; receiving verification response data returned by the terminal, wherein the verification response data is obtained by performing response processing on verification problem data through the terminal; and carrying out verification comparison on the verification response data and the verification answer data to obtain an information verification result.

In this embodiment, the verification question-answering data includes verification question data and verification answer data corresponding to the verification question data. The verification question data is question data for the information to be verified, and the verification answer data is a reference answer corresponding to the verification question data. For example, when the to-be-examined verification information is address information, the verification problem data may be a problem related to the address information, such as weather, landmark buildings, landmark building distance, commute time, and the like of the address information; and the verification answer data is a reference answer corresponding to the question, for example, the weather is clear, the name of the landmark building, the distance between the landmark buildings is 3 kilometers, the commute time is 45 minutes, and the like.

When performing the surface examination, the authentication question data in the authentication question-and-answer data may be issued to the terminal, the terminal may perform response processing on the authentication question data to obtain authentication response data, and the terminal may return the obtained authentication response data to the server 104. The server 104 compares the verification response data returned by the terminal with the verification answer data in the verification question-answer data, thereby obtaining an information verification result. Specifically, the verification answer data and the verification answer data may be compared one by one, and when the verification comparison result is within a preset error range, the verification may be considered to pass; otherwise, the verification is not passed.

In one embodiment, before acquiring the face-up video data, the method further comprises: generating a recording request message; and issuing a recording request message to the terminal, wherein the recording request message is used for indicating the terminal to record the video when the terminal is subjected to face examination verification.

In this embodiment, when the on-the-spot verification information is subjected to the on-the-spot verification through the verification question-answer data, a front camera of the terminal is used for video recording, so as to obtain the on-the-spot verification video data. Specifically, server 104 generates a recording request message that may be used to instruct the terminal to record a video upon review verification. In specific implementation, the recording request message can be generated and issued to the terminal when the review request message sent by the terminal is received, the terminal starts the front-facing camera according to the recording request message, and video recording is performed when the review is verified.

Further, acquiring the face examination video data comprises: and receiving the face examination video data returned by the terminal.

The server 104 sends the recording request message to instruct the terminal to record the video during the face examination verification, and then receives the face examination video data returned by the terminal in real time, wherein the face examination video data records the morphological data of the expression, the action and the like of the service user of the terminal during the face examination verification. Through the form data, risk control such as micro-expression analysis, face recognition processing and the like can be performed, and therefore the effect of face examination wind control is improved.

In one embodiment, the step of inputting the face examination video data into a preset micro-expression pneumatic control model and a preset face recognition model respectively to obtain a micro-expression pneumatic control result and a face recognition result comprises the following steps: respectively extracting micro-expression characteristic data and face recognition characteristic data from the face examination video data; inquiring a preset micro expression style control model and a face recognition model; inputting the micro-expression characteristic data into a micro-expression air control model to obtain a micro-expression air control result; and inputting the face recognition characteristic data into the face recognition model to obtain a face recognition result.

In this embodiment, when the facial examination video data is respectively input into the preset micro-expression pneumatic control model and the face recognition model and is subjected to micro-expression analysis and face recognition analysis, the facial examination video data may be preprocessed to remove useless redundant information, and corresponding micro-expression analysis and face recognition analysis are performed through the micro-expression characteristic data and the face recognition characteristic data.

Specifically, micro-expression feature data and face recognition feature data are respectively extracted from the face-examination video data. Wherein, the micro expression characteristic data is related to the micro expression of the service user and is used for micro expression analysis; the face recognition feature data is related to the face features of the service users and used for face recognition analysis. Then inquiring a preset micro-expression pneumatic control model and a face recognition model, wherein the micro-expression pneumatic control model is obtained by training historical micro-expression pneumatic control data; the face recognition model can be obtained by training various face data.

And inputting the micro-expression characteristic data into the micro-expression air control model to obtain a micro-expression air control result, wherein the micro-expression air control result reflects the intensity of various emotional states, such as the positive, calm and nervous degrees, of a service user of the terminal in the process of on-the-spot examination and verification. Generally, compared with the real situation expression, various emotional states of the service user are different during counterfeiting or fraud, and whether the service user has fraud behaviors or not can be analyzed according to the micro-expression and style control result, so that risk control is realized. On the other hand, the face recognition characteristic data is input into the face recognition model to obtain a face recognition result, the face recognition result reflects the identity verification result of the service user, and the risk control effect can be further improved by combining the face recognition result.

In one embodiment, before querying the preset micro-expression profile model, the method further includes: acquiring historical micro-expression wind control data from each service system, wherein the historical micro-expression wind control data comprises micro-expression data and wind control data corresponding to the micro-expression data; extracting micro-expression characteristic parameters from the micro-expression data, and establishing mapping between the micro-expression characteristic parameters and the wind control data; and training the micro-expression characteristic parameters and the wind control data to obtain a micro-expression wind control model.

The micro-expression wind control model can be obtained by training historical micro-expression wind control data based on an artificial neural network algorithm. Specifically, historical micro-expression air control data are obtained from each business system, and the historical micro-expression air control data comprise micro-expression data and air control data corresponding to the micro-expression data. For example, the micro-expression data may be form information of each service user when editing each service field in the service form, and the wind control data may be credibility of each service field after subsequent verification. And extracting micro-expression characteristic parameters from the micro-expression data so as to preprocess the micro-expression data, remove redundant useless information and establish mapping between the micro-expression characteristic parameters and the wind control data. And establishing a mapping relation between each micro-expression characteristic parameter and the wind control data, using the mapping relation and the wind control data as a model training data set, and obtaining a micro-expression wind control model by training the micro-expression characteristic parameters and the wind control data, wherein the micro-expression wind control model can output a corresponding micro-expression wind control result according to the input current video data, such as outputting a micro-expression wind control score.

In one embodiment, as shown in fig. 4, there is provided a method for controlling a risk of a face examination, including:

step S401: receiving a service request message sent by a terminal, and determining the service type of the service request message;

step S402: inquiring a preset service template form corresponding to the service type from the service system, and issuing the service template form to the terminal;

step S403: receiving a service form returned by the terminal, wherein the service form is obtained by editing and updating the service template form by the terminal;

step S404: receiving a face examination request message sent by a terminal;

step S405: and inquiring a business form corresponding to the face examination request message, and extracting the to-be-faced examination and verification information from the business form.

In this embodiment, the terminal sends a service request message to the server 104 to request a related service, and the server 104 issues a corresponding service template form according to the service type of the service request message, so as to obtain user information required by the service. When a face examination request message sent by a terminal is received, a business form corresponding to the face examination request message is inquired, and corresponding information to be verified is extracted from the business form.

Step S406: determining user identification information and service identification information corresponding to the to-be-examined and verified information;

step S407: determining a user authentication level corresponding to the user identification information and a service authentication level corresponding to the service identification information;

step S408: obtaining an information verification level according to the user verification level, the service verification level and a preset level weight factor;

step S409: acquiring verification question and answer data corresponding to the to-be-examined verification information from a preset verification question and answer database according to the information verification level; the verification question-answer data includes verification question data and verification answer data corresponding to the verification question data.

And the verification question-answer database is constructed in advance according to the historical information verification data of the service system. When the verification question and answer data corresponding to the to-be-examined information is obtained, the information type corresponding to the to-be-examined information is determined, and different verification question and answer data are set in the to-be-examined information of different information types. And inquiring a corresponding verification question-answer database according to the information type, and acquiring verification question-answer data corresponding to the information verification level from the verification question-answer database, namely the verification question-answer data corresponding to the to-be-examined verification information.

Step S410: issuing verification problem data to a terminal;

step S411: receiving verification response data returned by the terminal, wherein the verification response data is obtained by performing response processing on verification problem data through the terminal;

step S412: and carrying out verification comparison on the verification response data and the verification answer data to obtain an information verification result.

After the verification question-answer data is obtained, the verification question data in the verification question-answer data is issued to the terminal, the terminal performs response processing on the verification question data to obtain verification response data, and the terminal returns the obtained verification response data to the server 104. The server 104 compares the verification response data returned by the terminal with the verification answer data in the verification question-answer data, thereby obtaining an information verification result.

Step S413: respectively inputting the face examination video data into a preset micro-expression pneumatic control model and a face recognition model to obtain a micro-expression pneumatic control result and a face recognition result;

step S414: and obtaining a face examination wind control result according to the information verification result, the micro-expression wind control result, the face recognition result and a preset wind control weight coefficient.

And respectively extracting micro-expression characteristic data and face recognition characteristic data from the face examination video data. Wherein, the micro expression characteristic data is related to the micro expression of the service user and is used for micro expression analysis; the face recognition feature data is related to the face features of the service users and used for face recognition analysis. And inquiring a preset micro-expression pneumatic control model and a face recognition model, and inputting micro-expression characteristic data into the micro-expression pneumatic control model to obtain a micro-expression pneumatic control result, wherein the micro-expression pneumatic control result reflects the intensity of various emotional states of a service user of the terminal in the process of on-surface examination and verification. On the other hand, the face recognition characteristic data is input into the face recognition model to obtain a face recognition result, the face recognition result reflects the identity verification result of the service user, and the risk control effect can be further improved by combining the face recognition result.

And after the information verification result, the micro-expression pneumatic control result and the face recognition result are obtained, a preset pneumatic control weight coefficient is obtained, and a face examination pneumatic control result is obtained through calculation by combining the information verification result, the micro-expression pneumatic control result and the face recognition result, reflects the fraud degree of the service user of the terminal in the face examination and verification process, and can be used as a risk control reference when the service request message of the service user of the terminal is approved.

It should be understood that although the various steps in the flow charts of 2-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-4 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.

In one embodiment, as shown in fig. 5, there is provided an interview risk control device comprising: a face examination request receiving module 501, a verification data obtaining module 503, a face examination and verification processing module 505, a face examination video obtaining module 507, a face examination video processing module 509 and a face examination wind control processing module 511, wherein:

a face examination request receiving module 501, configured to receive a face examination request message sent by a terminal, and acquire to-be-examined verification information corresponding to the face examination request message;

the verification data acquisition module 503 is configured to acquire verification question and answer data corresponding to the to-be-faced examination and answer information from a preset verification question and answer database;

the face examination and verification processing module 505 is configured to perform face examination and verification on the face examination and verification information through the verification question and answer data to obtain an information verification result;

a surface examination video acquisition module 507, configured to acquire surface examination video data, where the surface examination video data is obtained by recording when performing surface examination;

the face examination video processing module 509 is configured to input the face examination video data into a preset micro-expression pneumatic control model and a preset face recognition model respectively to obtain a micro-expression pneumatic control result and a face recognition result, where the micro-expression pneumatic control model is obtained by training historical micro-expression pneumatic control data;

and the face audit wind control processing module 511 is used for obtaining a face audit wind control result according to the information verification result, the micro expression wind control result, the face recognition result and a preset wind control weight coefficient.

In one embodiment, the system further includes a service request receiving module, a template form querying module, and a template form issuing module, and the review request receiving module 501 includes a verification information extracting unit, where: the service request receiving module is used for receiving a service request message sent by the terminal and determining the service type of the service request message; the template form inquiry module is used for inquiring a preset service template form corresponding to the service type from the service system and issuing the service template form to the terminal; the template form issuing module is used for receiving a service form returned by the terminal, and the service form is obtained by editing and updating the service template form by the terminal; and the verification information extraction unit is used for inquiring the service form corresponding to the face examination request message and extracting the to-be-faced examination and verification information from the service form.

In one embodiment, the verification data acquisition module 503 includes an identification information determination unit, an identification level determination unit, a verification level determination unit, and a verification data acquisition unit, wherein: the identification information determining unit is used for determining user identification information and service identification information corresponding to the to-be-faced examination and verification information; an identification level determining unit, configured to determine a user authentication level corresponding to the user identification information and a service authentication level corresponding to the service identification information; the authentication level determining unit is used for obtaining an information authentication level according to the user authentication level, the service authentication level and a preset level weight factor; and the verification data acquisition unit is used for acquiring verification question and answer data corresponding to the to-be-examined verification information from a preset verification question and answer database according to the information verification level.

In one embodiment, the validation question-answer data includes validation question data and validation answer data corresponding to the validation question data; the surface-examination-verification processing module 505 includes a question data issuing unit, a response data receiving unit, and an information verification unit, wherein: the problem data issuing unit is used for issuing verification problem data to the terminal; the response data receiving unit is used for receiving verification response data returned by the terminal, and the verification response data is obtained by performing response processing on verification problem data through the terminal; and the information verification unit is used for verifying and comparing the verification response data and the verification answer data to obtain an information verification result.

In one embodiment, the system further includes a recording request generating module and a recording request issuing module, the review video acquiring module 507 includes a review data receiving unit, where: the recording request generating module is used for generating a recording request message; the recording request issuing module is used for issuing a recording request message to the terminal, and the recording request message is used for indicating the terminal to record the video when the face audit is verified; and the face examination data receiving unit is used for receiving the face examination video data returned by the terminal.

In one embodiment, the facial examination video processing module 509 comprises a feature data extraction unit, a model query unit, a micro-expression style control unit and a face recognition unit, wherein: the characteristic data extraction unit is used for respectively extracting micro-expression characteristic data and face recognition characteristic data from the face examination video data; the model query unit is used for querying a preset micro-expression pneumatic control model and a human face recognition model; the micro-expression wind control unit is used for inputting the micro-expression characteristic data into the micro-expression wind control model to obtain a micro-expression wind control result; and the face recognition unit is used for inputting the face recognition characteristic data into the face recognition model to obtain a face recognition result.

In one embodiment, the system further comprises a historical data acquisition module, a mapping relation establishment module and a micro expression model training module, wherein: the historical data acquisition module is used for acquiring historical micro-expression wind control data from each service system, and the historical micro-expression wind control data comprises micro-expression data and wind control data corresponding to the micro-expression data; the mapping relation establishing module is used for extracting micro-expression characteristic parameters from the micro-expression data and establishing mapping between the micro-expression characteristic parameters and the wind control data; and the micro-expression model training module is used for training micro-expression characteristic parameters and wind control data to obtain a micro-expression wind control model.

For specific limitations of the panel risk control device, reference may be made to the above limitations of the panel risk control method, which are not described herein again. The modules in the above-mentioned panel risk control device can be implemented wholly or partially by software, hardware and their combination. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of interview risk control.

Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program:

In one embodiment, the processor, when executing the computer program, further performs the steps of: receiving a service request message sent by a terminal, and determining the service type of the service request message; inquiring a preset service template form corresponding to the service type from the service system, and issuing the service template form to the terminal; receiving a service form returned by the terminal, wherein the service form is obtained by editing and updating the service template form by the terminal; and inquiring a business form corresponding to the face examination request message, and extracting the to-be-faced examination and verification information from the business form.

In one embodiment, the processor when executing the computer program further performs the steps of: determining user identification information and service identification information corresponding to the to-be-examined and verified information; determining a user authentication level corresponding to the user identification information and a service authentication level corresponding to the service identification information; obtaining an information verification level according to the user verification level, the service verification level and a preset level weight factor; and acquiring the verification question-answer data corresponding to the to-be-examined verification information from a preset verification question-answer database according to the information verification level.

In one embodiment, the validation question-answer data includes validation question data and validation answer data corresponding to the validation question data; the processor when executing the computer program further realizes the following steps: issuing verification problem data to a terminal; receiving verification response data returned by the terminal, wherein the verification response data is obtained by performing response processing on verification problem data through the terminal; and carrying out verification comparison on the verification response data and the verification answer data to obtain an information verification result.

In one embodiment, the processor when executing the computer program further performs the steps of: generating a recording request message; issuing a recording request message to the terminal, wherein the recording request message is used for indicating the terminal to record the video when the terminal is subjected to face examination verification; and receiving the face examination video data returned by the terminal.

In one embodiment, the processor, when executing the computer program, further performs the steps of: respectively extracting micro-expression characteristic data and face recognition characteristic data from the face examination video data; inquiring a preset micro expression pneumatic control model and a face recognition model; inputting the micro-expression characteristic data into a micro-expression air control model to obtain a micro-expression air control result; and inputting the face recognition characteristic data into a face recognition model to obtain a face recognition result.

In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring historical micro-expression wind control data from each service system, wherein the historical micro-expression wind control data comprises micro-expression data and wind control data corresponding to the micro-expression data; extracting micro-expression characteristic parameters from the micro-expression data, and establishing mapping between the micro-expression characteristic parameters and the wind control data; and training the micro-expression characteristic parameters and the wind control data to obtain a micro-expression wind control model.

In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:

In one embodiment, the computer program when executed by the processor further performs the steps of: receiving a service request message sent by a terminal, and determining the service type of the service request message; inquiring a preset service template form corresponding to the service type from the service system, and issuing the service template form to the terminal; receiving a service form returned by the terminal, wherein the service form is obtained by editing and updating the service template form by the terminal; and inquiring a business form corresponding to the face examination request message, and extracting the to-be-faced examination and verification information from the business form.

In one embodiment, the computer program when executed by the processor further performs the steps of: determining user identification information and service identification information corresponding to the to-be-examined and verified information; determining a user authentication level corresponding to the user identification information and a service authentication level corresponding to the service identification information; obtaining an information verification level according to the user verification level, the service verification level and a preset level weight factor; and acquiring the verification question-answer data corresponding to the to-be-examined verification information from a preset verification question-answer database according to the information verification level.

In one embodiment, the validation question-answer data includes validation question data and validation answer data corresponding to the validation question data; the computer program when executed by the processor further realizes the steps of: issuing verification problem data to a terminal; receiving verification response data returned by the terminal, wherein the verification response data is obtained by performing response processing on verification problem data through the terminal; and carrying out verification comparison on the verification response data and the verification answer data to obtain an information verification result.

In one embodiment, the computer program when executed by the processor further performs the steps of: generating a recording request message; issuing a recording request message to the terminal, wherein the recording request message is used for indicating the terminal to record the video when the terminal is subjected to face examination verification; and receiving the face examination video data returned by the terminal.

In one embodiment, the computer program when executed by the processor further performs the steps of: respectively extracting micro-expression characteristic data and face recognition characteristic data from the face examination video data; inquiring a preset micro expression pneumatic control model and a face recognition model; inputting the micro-expression characteristic data into a micro-expression air control model to obtain a micro-expression air control result; and inputting the face recognition characteristic data into a face recognition model to obtain a face recognition result.

In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring historical micro-expression wind control data from each service system, wherein the historical micro-expression wind control data comprises micro-expression data and wind control data corresponding to the micro-expression data; extracting micro-expression characteristic parameters from the micro-expression data, and establishing mapping between the micro-expression characteristic parameters and the wind control data; and training the micro-expression characteristic parameters and the wind control data to obtain a micro-expression wind control model.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

All possible combinations of the technical features in the above embodiments may not be described for the sake of brevity, but should be considered as being within the scope of the present disclosure as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is specific and detailed, but not to be understood as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A method of interview risk control, the method comprising:

acquiring verification question and answer data corresponding to the to-be-faced examination and answer information from a preset verification question and answer database;

performing face examination verification on the to-be-faced examination and verification information through the verification question-answering data to obtain an information verification result;

and obtaining an audit wind control result according to the information verification result, the micro-expression wind control result, the face identification result and a preset wind control weight coefficient, wherein the information verification result is an information verification risk value, the micro-expression wind control result is a micro-expression risk value, the face identification result is a biological identification risk value, the information verification risk value, the micro-expression risk value and the biological identification risk value are respectively multiplied and added with a weight factor corresponding to the information verification result, a weight factor corresponding to the micro-expression wind control result and a weight factor corresponding to the face identification result in the wind control weight coefficient to obtain an audit wind control score, and the audit wind control score is used as the audit wind control result.

2. The method according to claim 1, further comprising, before the receiving of the review request message sent by the terminal:

receiving a service request message sent by the terminal, and determining the service type of the service request message;

inquiring a preset service template form corresponding to the service type from a service system, and issuing the service template form to the terminal;

the acquiring the to-be-faced audit verification information corresponding to the face audit request message comprises the following steps:

and inquiring the business form corresponding to the face examination request message, and extracting the to-be-faced examination and verification information from the business form.

3. The method according to claim 1, wherein the obtaining of the validation question-answer data corresponding to the to-be-fronted examination information from a preset validation question-answer database comprises:

and acquiring the verification question and answer data corresponding to the to-be-faced examination and answer information from a preset verification question and answer database according to the information verification level.

4. The method according to claim 1, wherein the validation question-answer data includes validation question data and validation answer data corresponding to the validation question data; the performing face examination and verification on the to-be-faced examination and verification information through the verification question-answering data to obtain an information verification result comprises the following steps:

issuing the verification problem data to the terminal;

receiving verification response data returned by the terminal, wherein the verification response data is obtained by the terminal through response processing of the verification question data;

5. The method of claim 1, prior to said obtaining the panel video data, further comprising:

generating a recording request message;

the recording request message is issued to the terminal and used for indicating the terminal to record the video when the face examination is verified;

the acquiring of the face examination video data comprises:

and receiving the face examination video data returned by the terminal.

6. The method according to any one of claims 1 to 5, wherein the step of inputting the face examination video data into a preset micro-expression pneumatic control model and a preset face recognition model respectively to obtain a micro-expression pneumatic control result and a face recognition result comprises:

inputting the micro expression characteristic data into the micro expression wind control model to obtain a micro expression wind control result;

7. The method of claim 6, prior to said querying a pre-defined micro-expression profile model, further comprising:

and training the micro-expression characteristic parameters and the wind control data to obtain the micro-expression wind control model.

8. An interview risk control apparatus, comprising:

the system comprises a face examination request receiving module, a face examination processing module and a face examination processing module, wherein the face examination request receiving module is used for receiving a face examination request message sent by a terminal and acquiring to-be-examined verification information corresponding to the face examination request message;

the surface examination and verification processing module is used for carrying out surface examination and verification on the to-be-surface examination and verification information through the verification question-answer data to obtain an information verification result;

and the face examination wind control processing module is used for obtaining a face examination wind control result according to the information verification result, the micro-expression wind control result, the face recognition result and a preset wind control weight coefficient, wherein the information verification result is an information verification risk value, the micro-expression wind control result is a micro-expression risk value, the face recognition result is a biological recognition risk value, the information verification risk value, the micro-expression risk value and the biological recognition risk value are respectively multiplied and added with a weight factor corresponding to the information verification result, a weight factor corresponding to the micro-expression wind control result and a weight factor corresponding to the face recognition result which are included in the wind control weight coefficient to obtain a face examination wind control score, and the face examination wind control score is used as the face examination wind control result.

9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.