Identity data verification method, system and terminal

Abstract

The present application relates to a kind of identity data checking method, system and terminal, it is related to the field of identity recognition, it includes obtaining the trigger signal of preset call terminal;When based on trigger signal and preset call signal are consistent, the call content of call terminal is obtained;According to call content, identity keyword is matched from preset content database;According to identity keyword, the identity of call personnel is determined;According to the identity of call personnel, reference personnel voice is matched from preset voice database, and current personnel voice is obtained;When based on reference personnel voice and current personnel voice are inconsistent, identity abnormality prompt is reported.The present application has the effect of improving checking accuracy.

Description

Technical Field

[0001] This invention relates to the field of identity recognition, and in particular to an identity data verification method, system, and terminal. Background Technology

[0002] Effective identity data verification methods refer to a systematic set of means for auditing and checking the accuracy, completeness, compliance, and authenticity of identity data.

[0003] Currently, when making a call, the terminal usually verifies the identity of the caller. In this process, the identity of the caller is usually determined by analyzing the statistical data of the current caller beforehand, and then appropriate actions are taken accordingly.

[0004] If the statistical data of the current caller is insufficient to support identity verification, the call terminal will not perform any further operations, thereby reducing the accuracy of the verification, which needs to be improved. Summary of the Invention

[0005] To improve the accuracy of verification, this invention provides an identity data verification method, system, and terminal.

[0006] In a first aspect, the present invention provides an identity data verification method, which adopts the following technical solution:

[0007] An identity data verification method includes:

[0008] Obtain the trigger signal from the preset calling terminal;

[0009] When the trigger signal matches the preset call signal, the call content of the call terminal is obtained;

[0010] Based on the call content, identity keywords are matched from a preset content database;

[0011] Identify the caller based on identity keywords;

[0012] Based on the identity of the person making the call, the system matches the voice of a baseline person from a preset voice database and obtains the voice of the current person.

[0013] When the voice of the baseline personnel is inconsistent with the voice of the current personnel, an identity abnormality prompt will be reported.

[0014] By adopting the above technical solution, upon receiving a trigger signal from the calling terminal, if the signal matches the call signal, the call content is retrieved. Identification keywords are extracted from the content to identify the caller. Based on this identity, a baseline voice is retrieved from the voice database, while simultaneously capturing the current voice. If the two voices do not match, an identity anomaly alert is immediately reported, thereby improving verification accuracy.

[0015] Optionally, image recognition methods may also be included:

[0016] When the voice of the baseline person matches the voice of the current person, determine whether the conversation contains preset sensitive words;

[0017] When the call content contains sensitive words, obtain the recognition execution signal of the call terminal;

[0018] When the recognition execution signal matches the preset recognition start signal, the recognition image information is acquired;

[0019] When the recognized image information does not contain preset jewelry wearing characteristics, the current person's characteristics are determined based on the recognized image information and preset facial features;

[0020] Identify the current person based on their current characteristics;

[0021] If the current person's identity does not match the identity of the person in the call, an identity anomaly alert will be reported.

[0022] By employing the above technical solution, once the voice of the reference person matches the voice of the current person, the call content is further screened to determine if it contains sensitive words. If sensitive words are found, and the recognition execution signal matches the recognition activation signal, the recognition image information is acquired. If the image does not contain any jewelry features, the current person's characteristics are determined based on facial features, thus confirming their identity. If a discrepancy is found between the current person's identity and the identity of the person in the call, an identity anomaly alert is immediately reported. This effectively enhances the accuracy and reliability of identity verification and avoids potential risks.

[0023] Optionally, methods for identification after wearing jewelry may also be included:

[0024] When the image information contains preset jewelry wearing features, the jewelry wearing position is determined based on the image information, jewelry wearing features, and facial features.

[0025] Based on the identified image information and the location of the jewelry, the missing and remaining feature areas can be determined.

[0026] The detection angle value is matched from the preset verification database based on the missing feature area;

[0027] Based on the detected angle value, the call terminal prompts the caller corresponding to the caller's identity to adjust the angle.

[0028] Once the adjustment is complete, obtain the adjusted image information;

[0029] When the adjusted image information contains missing feature parts, the missing feature parts are determined based on the adjusted image information, the missing feature parts, and the detection angle value.

[0030] Determine complete facial features based on missing and remaining features;

[0031] Identifying the current person is based on complete facial features.

[0032] By employing the above technical solution, when recognizing the characteristics of jewelry wearing in image information, the first step is to accurately locate the position of the jewelry, thereby identifying any missing features due to occlusion and the remaining features. Next, based on the missing features, a suitable detection angle value is matched from the verification database, and the user is guided to adjust the angle via a communication terminal. After adjustment, the adjusted image information is acquired. If it contains the previously missing features, the missing features are determined by combining the adjusted image, the missing features, and the detection angle value. The remaining features are then integrated to form a complete facial profile, ultimately confirming the identity of the person and improving recognition efficiency.

[0033] Optional methods for identifying jewelry include:

[0034] When the adjusted image information does not contain missing feature parts, the range of jewelry occlusion is determined based on the recognized image information, jewelry wearing features, and facial features.

[0035] When the area obscured by the jewelry exceeds the preset area of ​​influence obscuration, the location to remove the jewelry is determined based on the area obscured by the jewelry, the area of ​​influence obscuration, and the position of the jewelry.

[0036] The system controls the communication terminal to report a notification of jewelry removal based on the location of the removed jewelry.

[0037] Once the jewelry is removed, obtain the image information after removal;

[0038] The characteristics of the removal site are determined based on post-removal image information, facial features, and the location of the removed jewelry;

[0039] The identity of the current person is determined based on the characteristics of the removed part and the characteristics of the remaining part.

[0040] By employing the above technical solution, when the adjusted image information does not contain any missing features, the range of jewelry occlusion is comprehensively determined based on the recognized image information, jewelry wearing characteristics, and facial features. Once this range exceeds the preset occlusion range, the location of jewelry removal can be accurately pinpointed by combining the jewelry occlusion range, the occlusion range, and the jewelry wearing position. The communication terminal then reports the removal prompt to the person on the other end of the call. After the jewelry is removed, the image information after removal is obtained. Using this information, facial features, and the location of the removed jewelry, the features of the removed part are determined. Furthermore, by integrating the features of the remaining parts, the identity of the current person can be accurately determined, further improving the accuracy of verification.

[0041] Optionally, face-swapping recognition methods are also included:

[0042] When the current person's identity matches the identity of the person making the call, the playback device preset on the call terminal is controlled to play a sway detection prompt and acquire head sway image information;

[0043] Determine whether the head-shaking image information contains preset face-swapping features;

[0044] When the head-shaking image information contains face-swapping features, an identity anomaly warning will be reported.

[0045] When the head-shaking image information does not contain face-swapping features, the face color and neck color are matched from the preset color database based on the head-shaking image information and preset face features.

[0046] Based on the face color and neck color, color difference values ​​are matched from a preset difference database;

[0047] When the color difference value exceeds the preset baseline difference value, the color difference position is determined based on the head-shaking image information, facial color, and neck color, and the difference image information of the color difference position is obtained.

[0048] When the difference image information contains face-swapping features, an identity anomaly warning will be reported.

[0049] By adopting the above technical solution, once the identity of the current person is confirmed to match that of the person making the call, to further investigate risks, the playback device on the call terminal is controlled to play a head-swaying detection prompt, simultaneously acquiring head-swaying image information. Next, it is determined whether the head-swaying image information contains face-swapping features. If it does, an identity anomaly warning is directly reported; if not, based on the head-swaying image information and facial features, the face color and neck color are matched from a color database, and then a color difference value is obtained from a difference database. When the color difference value exceeds a baseline difference value, the location of the color difference is determined by combining the head-swaying image information, etc., and the image information of that difference is acquired. If face-swapping features are found there, an identity anomaly warning is also reported, greatly improving the accuracy of face-swapping recognition.

[0050] Optional, light detection methods may also be included:

[0051] When the trigger signal and the call signal are consistent, the call image information of the call terminal is obtained;

[0052] Determine whether the call image information contains a preset close-up feature;

[0053] When the call image information contains close-fitting features, the location of light arrival is determined based on the call image information and the close-fitting features.

[0054] Control the light emitting device pre-installed on the call terminal to emit light at the location where the light arrives, and obtain the light length value;

[0055] When the light length value matches the preset baseline length value, an identity anomaly warning is reported.

[0056] By employing the above technical solution, when the trigger signal and the call signal are consistent, the call image information of the call terminal is acquired. When there are closely spaced features in the image information, the location of the light source is determined by analyzing the image and the closely spaced features. The light emitting device on the call terminal is then controlled to emit light towards that location, and the length value of the light source is obtained. If this length value is the same as a preset baseline length value, an identity anomaly alert is reported, thereby effectively improving the accuracy and reliability of identity verification.

[0057] Optionally, a method for obtaining the baseline length value may also be included:

[0058] Obtain camera image information from the calling terminal;

[0059] When the lens image information contains preset film features, the film thickness value is determined based on the lens image information, film features, and preset reference objects, and the terminal model information of the calling terminal is obtained.

[0060] Determine the terminal screen parameters based on the terminal model information;

[0061] The light impact value is determined based on the terminal screen parameters;

[0062] The screen thickness value is determined based on the terminal screen parameters and the film thickness value.

[0063] The reference length value is determined based on the light arrival location, light influence value, screen thickness value, and preset light emission location.

[0064] By employing the above technical solution, to accurately obtain the baseline length value, the camera image information of the calling terminal is first acquired. When a screen protector feature appears in the image information, the screen protector thickness value is determined based on the camera image information, the screen protector feature, and a reference object. Simultaneously, the terminal model information is acquired to clarify the terminal screen parameters. Then, the light influence value and screen thickness value are calculated using the terminal screen parameters. Finally, by comprehensively considering multiple factors such as the light arrival location, light influence value, screen thickness value, and preset light emission position, the baseline length value is determined, ensuring the accuracy of the verification results.

[0065] Optionally, it also includes an algorithmic formula for calculating the baseline length value:

[0066] L = L0 + (n * d * cosθ), where L is the reference length value, L0 is the light influence value, n is the refractive index of the film corresponding to the film feature, d is the film thickness value, and θ is the refraction angle of the light.

[0067] By adopting the above technical solution and using the above algorithm formula, the reference length value can be calculated more accurately, thereby improving the accuracy of the reference length value.

[0068] Secondly, this application provides an identity data verification system, which adopts the following technical solution:

[0069] An identity data verification system, comprising:

[0070] The acquisition module is used to acquire trigger signals, call content, current person's voice, recognition execution signals, recognition image information, adjusted image information, removed image information, head-shaking image information, difference image information, call image information, light length value, lens image information, and terminal model information;

[0071] A memory for storing programs for any of the aforementioned identity data verification methods;

[0072] A processor is used to load, execute, and implement programs stored in memory.

[0073] Thirdly, this application provides a smart terminal, which adopts the following technical solution:

[0074] A smart terminal includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed by any of the aforementioned identity data verification methods.

[0075] In summary, this application includes at least one of the following beneficial technical effects:

[0076] 1. Upon receiving a trigger signal from the calling terminal, if the signal matches the call signal, the call content is retrieved. Identification keywords are extracted from the content to identify the caller. Based on this identification, the voice of a baseline person is retrieved from the voice database, while the voice of the current person is also collected. If the two voices do not match, an identity anomaly alert is immediately reported to improve the accuracy of verification.

[0077] 2. When a preset close-fitting feature exists in the image information, the location where the light arrives is determined by analyzing the image and the close-fitting feature. The light emitting device on the communication terminal is then controlled to emit light towards that location, and the light length value is obtained. If this length value is the same as the reference length value, an identity anomaly alert is reported, thereby effectively improving the accuracy and reliability of identity verification.

[0078] 3. When a screen protector is visible in the image information, the screen protector thickness is determined based on the lens image information, the screen protector features, and a reference object. Simultaneously, the terminal model information is obtained to clarify the terminal screen parameters. Then, the light impact value and screen thickness value are calculated using the terminal screen parameters. Finally, by comprehensively considering factors such as the light arrival location, light impact value, screen thickness value, and preset light emission position, a baseline length value is determined to ensure the accuracy of the verification results. Attached Figure Description

[0079] Figure 1 This is a flowchart of an identity data verification method according to an embodiment of the present invention;

[0080] Figure 2 This is a flowchart of the image recognition method in an embodiment of the present invention;

[0081] Figure 3 This is the method flow of the identification method after wearing jewelry in the embodiments of the present invention. Figure 1 ;

[0082] Figure 4 This is the method flow of the identification method after wearing jewelry in the embodiments of the present invention. Figure 2 ;

[0083] Figure 5 This is a flowchart of the face-swapping recognition method in an embodiment of the present invention;

[0084] Figure 6 This is a flowchart of the light detection method in an embodiment of the present invention;

[0085] Figure 7 This is a flowchart of the method for obtaining the reference length value in an embodiment of the present invention. Detailed Implementation

[0086] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments.

[0087] This application discloses a method for verifying identity data.

[0088] Reference Figure 1 An identity data verification method includes the following steps:

[0089] Step 100: Obtain the trigger signal of the preset call terminal.

[0090] A calling terminal refers to a terminal used for online calls. In this embodiment, the calling terminal is a mobile phone. A trigger signal is a signal triggered when the calling terminal is being manually operated. The trigger signal is acquired through a signal sensor on the calling terminal.

[0091] Step 101: When the trigger signal matches the preset call signal, obtain the call content of the call terminal.

[0092] A call signal refers to the signal emitted when a call terminal is in the middle of a call. The call signal is preset by those skilled in the art and will not be elaborated upon here. The call content refers to the content of the call when the call terminal is in the middle of a call. The call content is obtained through a preset content recording app within the call terminal. When the trigger signal matches the call signal, it indicates that the call terminal is in the middle of a call, and the call content needs to be obtained for subsequent steps.

[0093] Step 102: Match identity keywords from the preset content database based on the call content.

[0094] Identity keywords are keywords used to help identify the caller's identity. The caller refers to the party initiating the call. A content database can be used to match corresponding identity keywords from the call content. This database contains the correspondence between the call content and the identity keywords. The content database is a manually configured database and will not be elaborated upon here.

[0095] Step 103: Identify the caller based on identity keywords.

[0096] Caller identity refers to the caller's specific identity relative to the receiver. A pre-set identity database can be used to match caller identities with identity keywords. This database contains the correspondence between identity keywords and caller identities. The identity database is manually configured and will not be elaborated upon here.

[0097] Step 104: Match the baseline voice from the preset voice database based on the identity of the person making the call, and obtain the voice of the current person.

[0098] The baseline voice refers to the voice characteristics that should correspond to the identity of the person making the call. The current voice refers to the voice characteristics of the current caller. The baseline voice, which corresponds to the identity of the person making the call, can be matched using a voice database. This database contains the correspondence between the identities of the people making the call and the baseline voice. This voice database is manually configured and will not be elaborated upon here. The current voice is obtained through a voice recognition app pre-installed on the call terminal. After the baseline voice is matched, the current voice needs to be obtained for subsequent steps.

[0099] Step 105: When the voice of the baseline personnel is inconsistent with the voice of the current personnel, report an identity abnormality prompt.

[0100] An identity discrepancy alert is a notification issued when the caller's identity does not match the identity of the person speaking to them. This alert is pre-set by those skilled in the art and will not be elaborated upon here. When the voice of the reference person differs from the voice of the current person speaking to them, it indicates that the caller's identity does not match the identity of the person speaking to them, and an identity discrepancy alert must be reported.

[0101] Reference Figure 2 The image recognition method includes the following steps:

[0102] Step 200: When the reference voice is consistent with the current voice, determine whether the call content contains preset sensitive words.

[0103] Sensitive words refer to words in the call that involve money or other sensitive information. These sensitive words are pre-defined by those skilled in the art and will not be elaborated upon here. When the voice of the baseline person matches the voice of the current person, it is necessary to further determine whether the call content contains sensitive words in order to determine whether further identity verification is required.

[0104] Step 201: When the call content contains sensitive words, obtain the recognition execution signal of the call terminal.

[0105] The identification execution signal is the signal emitted by the call terminal when it determines whether further facial recognition is required. This signal is obtained through the transceiver on the call terminal. When the call content contains sensitive words, it indicates that further identity verification is needed, requiring the acquisition of the call terminal's identification execution signal for subsequent steps.

[0106] Step 202: When the recognition execution signal is consistent with the preset recognition start signal, acquire the recognition image information.

[0107] The activation signal for facial recognition is the signal emitted by the call terminal when further facial recognition is required. This activation signal is pre-set by those skilled in the art and will not be elaborated upon here. The recognition image information refers to the image presented in front of the call terminal. This image information is acquired by taking a picture using a camera pre-installed on the call terminal.

[0108] When the recognition execution signal is consistent with the recognition start signal, it means that the call terminal needs to perform further facial recognition and needs to obtain recognition image information for subsequent steps.

[0109] Step 203: When the recognized image information does not contain the preset jewelry wearing features, determine the current person's characteristics based on the recognized image information and the preset facial features.

[0110] Jewelry wearing characteristics refer to the features of the caller's face when they are wearing jewelry. Facial features refer to various distinctive characteristics of a face that can be used to distinguish different individuals or for identification and analysis. Both jewelry wearing characteristics and facial features are preset by those skilled in the art and will not be elaborated upon here. Current person characteristics refer to the facial features of the caller. A preset feature database can be used to match the recognition image information with the corresponding current person characteristics, which includes the correspondence between the recognition image information, facial features, and current person characteristics. The feature database is a manually set database and will not be elaborated upon here.

[0111] When the image information does not contain the feature of wearing jewelry, it means that the caller is not wearing jewelry on their face, and the current person's features can be directly matched for subsequent steps.

[0112] Step 204: Determine the identity of the current person based on their current characteristics.

[0113] Current person identity refers to the caller's identity information. An identity database can be used to match the current person's characteristics with their corresponding current person identity; this database contains the correspondence between the current person's characteristics and their current person identity.

[0114] Step 205: If the current person's identity does not match the identity of the person in the call, report an identity anomaly.

[0115] If the identity of the caller does not match the identity of the person in the call, it indicates that the identity of the caller does not match the identity of the person in the call, and an identity anomaly alert should be reported.

[0116] Reference Figure 3 The identification method after wearing jewelry includes the following steps:

[0117] Step 300: When the image information contains preset jewelry wearing features, determine the jewelry wearing position based on the image information, jewelry wearing features, and facial features.

[0118] The placement of jewelry refers to the position of the jewelry on the caller's face. A pre-set jewelry database can match the identification image information, jewelry wearing characteristics, and facial features to the corresponding jewelry placement. This database includes the correspondence between the identification image information, jewelry wearing characteristics, facial features, and jewelry placement. The jewelry database is a manually set database and will not be elaborated upon here.

[0119] When the image information contains features indicating that the caller is wearing jewelry, it means that the caller is wearing jewelry on their face. The location of the jewelry needs to be matched for subsequent steps.

[0120] Step 301: Determine the missing and remaining feature parts based on the identified image information and the position of the jewelry.

[0121] Missing feature areas refer to facial features that are obscured by jewelry, making them unrecognizable. Remaining feature areas refer to those not obscured by jewelry. A feature database can be used to match the missing and remaining feature areas between the recognition image information and the jewelry's wearing position. This database contains the correspondence between the recognition image information, jewelry wearing position, missing feature areas, and remaining feature areas.

[0122] Step 302: Match the detection angle value from the preset verification database based on the missing feature parts.

[0123] The detection angle value refers to the angle between the mobile communication terminal and the missing feature area. By checking a database, the corresponding detection angle value for the missing feature area can be found. This database contains the correspondence between the missing feature area and the detection angle value. The database is manually set and will not be elaborated upon here.

[0124] Step 303: Based on the detected angle value, control the call terminal to prompt the caller corresponding to the caller's identity to adjust the angle.

[0125] The control terminal prompts the person whose identity corresponds to the caller to adjust the angle of the terminal according to the detected angle value for subsequent steps.

[0126] Step 304: After adjustment is completed, obtain the adjusted image information.

[0127] Post-adjustment image information refers to the image presented in front of the call terminal after the angle has been adjusted. This image information is acquired by taking a picture using the call terminal's camera. Once the call terminal's angle has been adjusted, the post-adjustment image information needs to be obtained for subsequent steps.

[0128] Step 305: When the adjusted image information contains missing feature parts, determine the missing feature parts based on the adjusted image information, the missing feature parts, and the detection angle value.

[0129] Missing feature refers to the appearance features of the missing parts. A feature database can be used to match the adjusted image information, the missing feature parts, and the corresponding missing feature values, containing the correspondence between the adjusted image information, the missing feature parts, the detection angle values, and the missing feature.

[0130] When the adjusted image information contains missing feature parts, it means that the missing feature parts can be further identified, and the missing feature parts can be matched for subsequent steps.

[0131] Step 306: Determine the complete facial features based on the missing and remaining features.

[0132] A complete facial feature refers to the complete facial features of the caller. A complete facial feature can be obtained by combining the missing features with the remaining features.

[0133] Step 307: Determine the identity of the current person based on complete facial features.

[0134] The current person's identity refers to the caller's identity information. An identity database can be used to match the complete facial features with the current person's identity, containing the correspondence between complete facial features and the current person's identity.

[0135] Reference Figure 4 The identification method after wearing jewelry also includes the following steps:

[0136] Step 400: When the adjusted image information does not contain missing feature parts, determine the occlusion range of the jewelry based on the recognized image information, jewelry wearing features, and facial features.

[0137] The area obscured by jewelry refers to the area of ​​the caller's face that is covered by jewelry worn on the caller's face. A pre-defined range database can be used to match the obscured area with the identified image information, jewelry wearing characteristics, and facial features. This database contains the correspondence between the identified image information, jewelry wearing characteristics, facial features, and the obscured area. The range database is a manually set database and will not be elaborated upon here.

[0138] When the adjusted image information does not contain the missing feature part, it means that even after angle adjustment, the missing feature part cannot be identified. The area covered by the ornament needs to be matched for subsequent steps.

[0139] Step 401: When the area covered by the jewelry exceeds the preset area of ​​influence coverage, determine the location to remove the jewelry based on the area covered by the jewelry, the area of ​​influence coverage, and the position of the jewelry.

[0140] The area of ​​obstruction refers to the smallest area of ​​obstruction that begins to have an impact during the process of identifying the caller. This area is predetermined by those skilled in the art and will not be elaborated upon here. The location of jewelry removal refers to the position of the jewelry that needs to be removed from the caller's face. A jewelry database can be used to match the area of ​​obstruction, the area of ​​obstruction, and the corresponding location of jewelry removal, encompassing the correspondence between these elements.

[0141] When the area obscured by jewelry exceeds the range of influence, it indicates that one or more pieces of jewelry on the caller's face are excessively obscuring their face. Some or all of the jewelry needs to be removed for identification purposes. Therefore, it is necessary to match the location of the removed jewelry for subsequent steps.

[0142] Step 402: Control the communication terminal to report a prompt to remove the jewelry based on the location of the removed jewelry.

[0143] A jewelry removal prompt is a notification indicating that one or all jewelry on the face needs to be removed. The jewelry removal prompt is pre-set by those skilled in the art and will not be elaborated upon here. The control communication terminal reports the jewelry removal prompt based on the location of the jewelry to be removed.

[0144] Step 403: After the jewelry is removed, obtain the image information after removal.

[0145] Post-removal image information refers to the image after the caller has removed the jewelry. This image information is obtained by taking a picture with a camera. It is necessary to obtain this image information after the jewelry is removed for subsequent steps.

[0146] Step 404: Determine the features of the removed area based on the post-removal image information, facial features, and the location of the removed jewelry.

[0147] The features of the removed area refer to the appearance characteristics of the area after the jewelry is removed. A feature database can be used to match post-removal image information, facial features, and the features of the removed area corresponding to the location of the removed jewelry. This includes the correspondence between post-removal image information, facial features, the location of the removed jewelry, and the features of the removed area.

[0148] Step 405: Determine the identity of the current person based on the characteristics of the removed part and the characteristics of the remaining part.

[0149] The identity database can be used to match the features of the removed parts with the features of the remaining parts, and it contains the correspondence between the features of the removed parts, the features of the remaining parts, and the current person's identity.

[0150] Reference Figure 5 The face-swapping recognition method includes the following steps:

[0151] Step 500: If the current person's identity matches the caller's identity, control the playback device preset on the call terminal to play the sway detection prompt and acquire head sway image information.

[0152] The playback device refers to the device on the call terminal used for voice prompts. The head-shaking detection prompt refers to a prompt used to detect facial head-shaking of the caller. In this embodiment, facial head-shaking detection refers to the detection of the caller's head shaking up and down, and left and right. The head-shaking detection prompt is preset by those skilled in the art and will not be described in detail here. The head-shaking image information refers to the image of the caller during facial head-shaking detection. The head-shaking image information is acquired by taking a picture with a camera.

[0153] When the current person's identity matches the identity of the person making the call, to avoid the possibility of a face mask, it is necessary to control the playback device on the call terminal to play a sway detection prompt and obtain head-swaying image information for subsequent steps.

[0154] Step 501: Determine whether the head-shaking image information contains preset face-swapping features.

[0155] Face-swapping features refer to the characteristics of a caller wearing a face-swapping mask. These features are pre-defined by those skilled in the art and will not be elaborated upon here. By determining whether the head-moving image information contains face-swapping features, it is possible to determine whether the caller's identity is imposter.

[0156] Step 502: When the head-shaking image information contains face-swapping features, report an identity anomaly warning.

[0157] When the head-shaking image information contains face-swapping features, it indicates that the caller's identity is fake, and an identity anomaly alert should be reported.

[0158] Step 503: When the head-shaking image information does not contain face-swapping features, match the face color and neck color from the preset color database based on the head-shaking image information and preset face features.

[0159] Facial features refer to the distinctive characteristics of a person's face that can be used to differentiate individuals or for identity verification and analysis. Facial features are pre-defined by those skilled in the art and will not be elaborated upon here. Facial color refers to the color of the caller's face. Neck color refers to the color of the caller's neck. A color database can be used to match head-shaking image information with the corresponding facial and neck colors. This database contains the correspondence between head-shaking image information, facial features, facial colors, and neck colors. The color database is a manually defined database and will not be elaborated upon here.

[0160] When the head-shaking image information does not contain face-swapping features, in order to further detect the identity of the caller, it is necessary to match the face color and neck color for subsequent steps.

[0161] Step 504: Match color difference values ​​from a preset difference database based on face color and neck color.

[0162] Color difference value refers to the quantified numerical value of the degree of difference between face color and neck color. A color difference database can be used to match the color difference values ​​corresponding to face and neck colors. This database contains the correspondence between face and neck colors and their color difference values. The color difference database is a manually created database and will not be elaborated upon here.

[0163] Step 505: When the color difference value exceeds the preset baseline difference value, determine the color difference location based on the head-shaking image information, facial color, and neck color, and obtain the difference image information of the color difference location.

[0164] The baseline difference value refers to the maximum allowable color difference value. This baseline difference value is predetermined by those skilled in the art and will not be elaborated upon here. The color difference location refers to the position where a difference occurs between the face color and the neck color. The colors of the face and neck are distinguished using head-movement image information to determine the specific location where the color difference exists, which is defined as the color difference location. The difference image information refers to the image of the color difference location. This difference image information is acquired through camera photography.

[0165] When the color difference value exceeds the baseline difference value, it indicates that the color difference between the face and neck is too large. It is necessary to first determine the location of the color difference and then obtain the difference image information for subsequent steps.

[0166] Step 506: When the difference image information contains face-swapping features, report an identity anomaly warning.

[0167] When the difference image information contains face-swapping features, it indicates that the caller's identity is fake, and an identity anomaly alert should be reported.

[0168] Reference Figure 6 The light detection method includes the following steps:

[0169] Step 600: When the trigger signal and the call signal are consistent, obtain the call image information of the call terminal.

[0170] Call image information refers to the image presented to the terminal during a call. Call image information is acquired by taking a picture with a camera. When the trigger signal matches the call signal, it indicates that the terminal is in a call and call image information needs to be acquired for subsequent steps.

[0171] Step 601: Determine whether the call image information contains a preset close-up feature.

[0172] The "close contact feature" refers to the characteristic of the calling terminal being pressed firmly against the face. This feature is pre-defined by those skilled in the art and will not be elaborated upon here. Whether the calling terminal is pressed firmly against the face is determined by judging whether the call image information contains this feature.

[0173] Step 602: When the call image information contains close-fitting features, determine the location where the light arrives based on the call image information and the close-fitting features.

[0174] The location of light arrival refers to the position where the light used to detect whether a face mask is being worn falls. A pre-defined light database can be used to match call image information with the corresponding light arrival locations of adjacent features. This database contains the correspondence between call image information, adjacent features, and light arrival locations. The light database is a manually configured database and will not be elaborated upon here.

[0175] When the call image information contains a close-fitting feature, it means that the call terminal is close to the face, and the location where the light arrives needs to be matched for subsequent steps.

[0176] Step 603: Control the light emitting device preset on the call terminal to emit light at the light arrival location and obtain the light length value.

[0177] A light emitting device is a device used to emit light to detect whether a face mask is being worn on a person's face. The light length value refers to the distance the emitted light travels to the face. The light length value is measured by a preset light sensor on the communication terminal. The device controls the light emitting device on the communication terminal to emit light to the location where it arrives and obtains the light length value for subsequent steps.

[0178] Step 604: When the light length value is consistent with the preset reference length value, report an identity abnormality prompt.

[0179] The baseline length value refers to the length of light that should exist when no other interfering factors are present. The method for obtaining the baseline length value is explained in detail in subsequent steps 700 to 705, and will not be repeated here. Since oil is produced on human faces, an oil film will form, which will cause the light length value to be inconsistent with the baseline length value. If the light length value is consistent with the baseline length value, it means that there is no oil on the currently identified face, which means that the currently identified face is a face mask, and an identity anomaly warning should be reported.

[0180] Reference Figure 7 The method for obtaining the baseline length value includes the following steps:

[0181] Step 700: Obtain the camera image information of the calling terminal.

[0182] Lens image information refers to the image surrounding the lens of the calling terminal. Lens image information is acquired by taking pictures with the camera.

[0183] Step 701: When the lens image information contains preset film features, determine the film thickness value according to the lens image information, film features and preset reference objects, and obtain the terminal model information of the call terminal.

[0184] The "screen protector feature" refers to the characteristics of the handset when a protective film is applied. This feature is pre-defined by those skilled in the art and will not be elaborated upon here. The "reference object" refers to an object used to assist in measuring the thickness of the protective film. The size and position of the reference object are pre-defined by those skilled in the art and will not be elaborated upon here; the reference object is included in the lens image information. The "screen protector thickness value" refers to the thickness of the protective film. The "handset model information" refers to the specific model of the handset. This information is obtained by querying the model information app within the handset.

[0185] When the lens image information contains a screen protector feature, it indicates that a protective film is applied to the screen of the calling terminal. The thickness of the film needs to be determined first, and then the terminal model information of the calling terminal needs to be obtained for subsequent steps.

[0186] Step 702: Determine the terminal screen parameters based on the terminal model information.

[0187] Terminal screen parameters refer to a series of indicators used to describe the screen characteristics of a calling terminal. These include size, resolution, pixel density, screen ratio, screen thickness, refresh rate, color parameters, brightness, and contrast ratio. A pre-defined terminal database can be used to match the terminal model information with the corresponding terminal screen parameters. This database contains the correspondence between terminal model information and terminal screen parameters. The terminal database is manually set and will not be elaborated upon here.

[0188] Step 703: Determine the light influence value based on the terminal screen parameters.

[0189] The light impact value refers to the influence of different screen parameters on the light emitted by a light emitting device. A light impact database can be used to match the light impact values ​​corresponding to different terminal screen parameters, revealing the correlation between these parameters and the corresponding light impact values.

[0190] Step 704: Determine the screen thickness value based on the terminal screen parameters and the film thickness value.

[0191] The screen thickness value refers to the sum of the thickness of the handset's own screen and the thickness of the applied screen protector. The screen thickness value can be obtained by adding the thickness of the screen protector to the thickness of the handset's own screen.

[0192] Step 705: Determine the reference length value based on the light arrival location, light influence value, screen thickness value, and preset light emission location.

[0193] The light emission position refers to the position of the light emitted by the light emitting device. The light emission position is predetermined by those skilled in the art and will not be elaborated upon here. The reference length value can be calculated using the algorithm formula L=L0+(n*d*cosθ), where L is the reference length value, L0 is the light influence value, n is the refractive index of the film corresponding to the film feature, d is the film thickness value, and θ is the refraction angle of the light. n and θ are measured in advance by those skilled in the art and will not be elaborated upon here.

[0194] Based on the same inventive concept, embodiments of the present invention provide an identity data verification system, including:

[0195] The acquisition module is used to acquire trigger signals, call content, current person's voice, recognition execution signals, recognition image information, call number, call record information, current IP location, head-turning image information, difference image information, call image information, light length value, lens image information, and terminal model information;

[0196] A memory used to store a program for an identity data verification method;

[0197] A processor is used to load, execute, and implement programs stored in memory.

[0198] Based on the same inventive concept, embodiments of the present invention provide a smart terminal, including a memory and a processor, wherein the memory stores a computer program that can be loaded and executed by the processor to perform an identity data verification method.

[0199] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0200] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A method for verifying identity data, characterized in that, include: Obtain the trigger signal from the preset calling terminal; When the trigger signal matches the preset call signal, the call content of the call terminal is obtained; Based on the call content, identity keywords are matched from a preset content database; Identify the caller based on identity keywords; Based on the identity of the person making the call, the system matches the voice of a baseline person from a preset voice database and obtains the voice of the current person. When the voice of the baseline personnel is inconsistent with the voice of the current personnel, an identity abnormality warning will be reported. It also includes light detection methods: When the trigger signal and the call signal are consistent, the call image information of the call terminal is obtained; Determine whether the call image information contains a preset close-up feature; When the call image information contains close-fitting features, the location of light arrival is determined based on the call image information and the close-fitting features. Control the light emitting device pre-installed on the call terminal to emit light at the location where the light arrives, and obtain the light length value; When the light length value matches the preset baseline length value, an identity anomaly warning is reported. It also includes methods for obtaining the baseline length value: Obtain camera image information from the calling terminal; When the lens image information contains preset film features, the film thickness value is determined based on the lens image information, film features, and preset reference objects, and the terminal model information of the calling terminal is obtained. Determine the terminal screen parameters based on the terminal model information; The light impact value is determined based on the terminal screen parameters; The screen thickness value is determined based on the terminal screen parameters and the film thickness value. The reference length value is determined based on the light arrival location, light influence value, screen thickness value, and preset light emission location.

2. The identity data verification method according to claim 1, characterized in that, It also includes image recognition methods: When the voice of the baseline person matches the voice of the current person, determine whether the conversation contains preset sensitive words; When the call content contains sensitive words, obtain the recognition execution signal of the call terminal; When the recognition execution signal matches the preset recognition start signal, the recognition image information is acquired; When the recognized image information does not contain preset jewelry wearing characteristics, the current person's characteristics are determined based on the recognized image information and preset facial features; Identify the current person based on their current characteristics; If the current person's identity does not match the identity of the person in the call, an identity anomaly alert will be reported.

3. The identity data verification method according to claim 2, characterized in that, It also includes methods for identifying jewelry: When the image information contains preset jewelry wearing features, the jewelry wearing position is determined based on the image information, jewelry wearing features, and facial features. Based on the identified image information and the location of the jewelry, the missing and remaining feature areas can be determined. The detection angle value is matched from the preset verification database based on the missing feature area; Based on the detected angle value, the call terminal prompts the caller corresponding to the caller's identity to adjust the angle. Once the adjustment is complete, obtain the adjusted image information; When the adjusted image information contains missing feature parts, the missing feature parts are determined based on the adjusted image information, the missing feature parts, and the detection angle value. Determine complete facial features based on missing and remaining features; Identifying the current person is based on complete facial features.

4. The identity data verification method according to claim 3, characterized in that, Methods for identifying jewelry also include: When the adjusted image information does not contain missing feature parts, the range of jewelry occlusion is determined based on the recognized image information, jewelry wearing features, and facial features. When the area obscured by the jewelry exceeds the preset area of ​​influence obscuration, the location to remove the jewelry is determined based on the area obscured by the jewelry, the area of ​​influence obscuration, and the position of the jewelry. The system controls the communication terminal to report a notification of jewelry removal based on the location of the removed jewelry. Once the jewelry is removed, obtain the image information after removal; The characteristics of the removal site are determined based on post-removal image information, facial features, and the location of the removed jewelry; The identity of the current person is determined based on the characteristics of the removed part and the characteristics of the remaining part.

5. The identity data verification method according to claim 2, characterized in that, It also includes face-swapping recognition methods: When the current person's identity matches the identity of the person making the call, the playback device preset on the call terminal is controlled to play a sway detection prompt and acquire head sway image information; Determine whether the head-shaking image information contains preset face-swapping features; When the head-shaking image information contains face-swapping features, an identity anomaly warning will be reported. When the head-shaking image information does not contain face-swapping features, the face color and neck color are matched from the preset color database based on the head-shaking image information and preset face features. Based on the face color and neck color, color difference values ​​are matched from a preset difference database; When the color difference value exceeds the preset baseline difference value, the color difference position is determined based on the head-shaking image information, facial color, and neck color, and the difference image information of the color difference position is obtained. When the difference image information contains face-swapping features, an identity anomaly warning will be reported.

6. The identity data verification method according to claim 1, characterized in that, It also includes the algorithm formula for calculating the reference length value: L = L0 + (n * d * cosθ), where L is the reference length value, L0 is the light influence value, n is the refractive index of the film corresponding to the film feature, d is the film thickness value, and θ is the refraction angle of the light.

7. An identity data verification system, characterized in that, include: The acquisition module is used to acquire trigger signals, call content, current person's voice, recognition execution signals, recognition image information, adjusted image information, removed image information, head-shaking image information, difference image information, call image information, light length value, lens image information, and terminal model information; A memory for storing a program of an identity data verification method as described in any one of claims 1 to 6; A processor is used to load, execute, and implement programs stored in memory.

8. A smart terminal, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as described in any one of claims 1 to 6.

Images