Identity verification method and device, equipment, medium and product

Abstract

The invention relates to the technical field of Internet, and discloses an identity verification method, device and equipment, a medium and a product, and the method comprises the steps: obtaining target information and a target time period of a target object; inputting the target information into a target model in a target time period to obtain a target scoring grade; obtaining a target probability value according to the target scoring level and the mapping relation; under the condition that the target probability value is the same as the hit parameter, sampling inspection is conducted on the target object, an identity verification result is obtained, and the hit parameter is used for representing the condition for executing sampling inspection operation on the target object. According to the invention, spot check is carried out on the target object according to the target probability value corresponding to the target score level of the target object in the target time period, a differentiated identity verification strategy of the object dimension is realized, the risk control level in a high-risk scene is improved, the experience disturbance of the target object in a low-risk scene is reduced, and the experience experience of the target object is improved. The contradiction between frequency increasing and frequency reducing of identity verification is solved, and the refinement degree of an identity verification strategy is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of Internet technology, and in particular to identity authentication methods, devices, equipment, media and products. Background Art

[0002] With the booming development of the online ride-hailing industry, the safety of riding in an online ride-hailing car has received more and more attention. Therefore, it is particularly important to authenticate the identity of online ride-hailing drivers.

[0003] In response to the above problems, relevant technologies usually formulate online ride-hailing driver identity verification strategies based on the two dimensions of city and time period. However, this strategy has the following problems: In order to improve the compliance rate of orders and reduce business security risks, online ride-hailing platforms need to increase the frequency of identity verification for drivers during work. However, in order to improve their capacity scale advantage over other platforms, online ride-hailing platforms need to reduce the frequency of identity verification for drivers during work. Within the same city and time period, the contradiction between increasing and reducing the verification frequency cannot be resolved, and the verification strategy is not refined enough.

[0004] Therefore, the identity authentication strategies of related technologies cannot resolve the contradiction between frequency increase and frequency decrease of identity authentication and are not sufficiently refined. Summary of the invention

[0005] In view of this, the present disclosure provides an identity authentication method, apparatus, device, medium and product to solve the problem that the identity authentication strategy of the related technology cannot solve the contradiction between identity authentication frequency increase and frequency decrease and the degree of refinement is insufficient.

[0006] In a first aspect, the present disclosure provides an identity authentication method, the method comprising:

[0007] Obtaining target information and target time period of the target object, wherein the target information is used to authenticate the target object;

[0008] Input the target information into the target model under the target period to obtain the target rating level;

[0009] According to the target scoring level and the mapping relationship, the target probability value is obtained, wherein the target probability value represents the probability of the target object being sampled, and the mapping relationship is used to characterize the corresponding relationship between the scoring level list and the probability value list, the target scoring level is included in the scoring level list, and the target probability value is included in the probability value list;

[0010] When the target probability value is the same as the hit parameter, a random check is performed on the target object to obtain an identity authentication result, wherein the hit parameter is used to indicate the condition for performing a random check operation on the target object.

[0011] In the disclosed embodiment, by obtaining the target information and target time period of the target object, wherein the target information is used to authenticate the identity of the target object; inputting the target information into the target model under the target time period to obtain the target rating level; obtaining the target probability value according to the target rating level and the mapping relationship, wherein the target probability value represents the probability of the target object being sampled, the mapping relationship is used to characterize the correspondence between the rating level list and the probability value list, the target rating level is included in the rating level list, and the target probability value is included in the probability value list; when the target probability value is the same as the hit parameter, the target object is sampled to obtain the identity authentication result, wherein the hit parameter is used to represent the condition for performing the sampling operation on the target object. Since the disclosed embodiment samples the target object according to the target probability value corresponding to the target rating level of the target object under the target time period, a differentiated identity authentication strategy of the object dimension is implemented, the risk control level in high-risk scenarios is improved, the target object experience disturbance in low-risk scenarios is reduced, the contradiction between the frequency increase and frequency decrease of identity authentication is resolved, and the refinement of the identity authentication strategy is improved.

[0012] In an optional implementation, the target information is input into the target model under the target period to obtain the target scoring level, including:

[0013] Inputting the target information into the target prediction module under the target period to obtain the target scoring result, wherein the target prediction module is included in the target model;

[0014] According to the target scoring interval into which the target scoring result falls, the target scoring level corresponding to the target scoring interval is obtained.

[0015] In the disclosed embodiment, the target information is input into the target prediction module under the target time period to obtain the target scoring result, and the corresponding target scoring grade is obtained according to the target scoring interval into which the target scoring result falls, thereby realizing the grade classification of the target object in the object dimension.

[0016] In an optional implementation, after spot checking the target object and obtaining the identity verification result, the method further includes:

[0017] The preset scoring range is adjusted according to the target scoring level and the identity verification result, wherein the target scoring range is included in the preset scoring range.

[0018] In the disclosed embodiment, by adjusting the preset scoring interval according to the target scoring level and the identity authentication result, the setting of the preset scoring interval is made more reasonable, and the identity authentication strategy is optimized.

[0019] In an optional implementation, before inputting the target information into the target prediction module under the target period to obtain the target scoring result, the method further includes:

[0020] Obtain a training data set of a training object, wherein the training data carries sample labels under multiple time periods, the training data is used to authenticate the identity of the training object, the sample labels are historical identity authentication results of the training object, and the target time period is included in the multiple time periods;

[0021] Preprocess the training data to obtain mapping values;

[0022] Input the mapped value into the initial prediction module under the corresponding time period to obtain the initial scoring result;

[0023] According to the initial scoring results and sample labels, the preset parameters in the initial prediction module are adjusted to obtain the target prediction module, wherein the preset parameters are used to adjust the influence of the mapping value.

[0024] In the disclosed embodiment, by preprocessing the training data to obtain the mapping value, the quality and consistency of the training data can be ensured. By adjusting the preset parameters in the initial prediction module according to the initial scoring result and the sample label, the target prediction module can be obtained, and the target information can be processed to obtain the scoring result.

[0025] In an optional implementation, preprocessing the training data to obtain the mapping value includes:

[0026] Perform feature transformation on the training data to obtain feature values;

[0027] Map the eigenvalues ​​to obtain mapped values.

[0028] In the disclosed embodiment, the quality and consistency of the training data can be ensured by performing feature conversion on the training data to obtain feature values, and then mapping the feature values ​​to obtain mapping values.

[0029] In an optional implementation, before inputting the target information into the target model under the target period to obtain the target scoring level, the method further includes:

[0030] Match the target information on the preset platform to obtain the verification strategy;

[0031] Based on the verification strategy, multiple rounds of judgment are performed on the target object in sequence, wherein the multiple rounds of judgment are used to perform regular verification on the target object;

[0032] When multiple rounds of judgments do not satisfy the criteria, the target information is input into the target model under the target period to obtain the target rating level.

[0033] In the embodiment of the present disclosure, multiple rounds of judgments are performed on the target object in sequence according to the verification strategy obtained by matching the target information on the preset platform, thereby achieving conventional verification of the target object.

[0034] In a second aspect, the present disclosure provides an identity authentication device, the device comprising:

[0035] A first acquisition module is used to acquire target information and a target period of a target object, wherein the target information is used to authenticate the identity of the target object;

[0036] The first obtaining module is used to input the target information into the target model under the target period to obtain the target scoring level;

[0037] The second obtaining module is used to obtain a target probability value according to the target scoring level and the mapping relationship, wherein the target probability value represents the probability of the target object being sampled, the mapping relationship is used to characterize the corresponding relationship between the scoring level list and the probability value list, the target scoring level is included in the scoring level list, and the target probability value is included in the probability value list;

[0038] The third obtaining module is used to perform a random inspection on the target object to obtain the identity verification result when the target probability value is the same as the hit parameter, wherein the hit parameter is used to indicate the conditions for performing the random inspection operation on the target object.

[0039] In a third aspect, the present disclosure provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the identity authentication method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0040] In a fourth aspect, the present disclosure provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the identity authentication method of the first aspect or any corresponding embodiment thereof.

[0041] In a fifth aspect, the present disclosure provides a computer program product, including computer instructions, which are used to enable a computer to execute the identity authentication method of the above-mentioned first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the specific embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 is a flowchart of an identity authentication method according to an embodiment of the present disclosure;

[0044] Figure 2 is a flowchart of an identity authentication method according to another embodiment of the present disclosure;

[0045] Figure 3 is a daytime model effect diagram of the identity authentication method according to an embodiment of the present disclosure;

[0046] Figure 4 is a nighttime model effect diagram of the identity authentication method according to an embodiment of the present disclosure;

[0047] Figure 5 is a structural block diagram of an identity authentication device according to an embodiment of the present disclosure;

[0048] Figure 6 It is a schematic diagram of the hardware structure of the computer device of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0050] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the types, scopes of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to relevant users and their authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations. The relevant users may include any type of right holders, such as individuals, enterprises, and groups.

[0051] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly prompt the relevant user that the operation requested to be performed will require obtaining and using the information of the relevant user, so that the relevant user can independently choose whether to provide information to software or hardware such as an electronic device, application, server or storage medium that executes the operation of the technical solution of the present disclosure based on the prompt message.

[0052] As an optional but non-limiting implementation, in response to receiving an active request from a relevant user, a prompt message is sent to the relevant user, for example, in the form of a pop-up window, in which the prompt message may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to select "agree" or "disagree" to provide information to the electronic device.

[0053] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0054] With the booming development of the online ride-hailing industry, the safety of riding in an online ride-hailing car has received more and more attention. Therefore, it is particularly important to authenticate the identity of online ride-hailing drivers.

[0055] In response to the above problems, relevant technologies usually formulate online ride-hailing driver identity verification strategies based on the two dimensions of city and time period. However, this strategy has the following problems: In order to improve the compliance rate of orders and reduce business security risks, online ride-hailing platforms need to increase the frequency of identity verification for drivers during work. However, in order to improve their capacity scale advantage over other platforms, online ride-hailing platforms need to reduce the frequency of identity verification for drivers during work. Within the same city and time period, the contradiction between increasing and reducing the verification frequency cannot be resolved, and the verification strategy is not refined enough.

[0056] Therefore, the identity authentication strategies of related technologies cannot resolve the contradiction between frequency increase and frequency decrease of identity authentication and are not sufficiently refined.

[0057] In order to solve the above problems, according to an embodiment of the present disclosure, an identity authentication method embodiment is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0058] In this embodiment, an identity authentication method is provided, such as Figure 1 As shown, Figure 1 : is a flow chart of an identity authentication method according to an embodiment of the present disclosure, which can be applied to a server and includes the following steps:

[0059] Step S101, obtaining target information and target time period of a target object, wherein the target information is used to authenticate the identity of the target object.

[0060] Optionally, in the disclosed embodiment, the target object is the current driver whose identity is to be verified in the application scenario. The target information is used to authenticate the current driver, including identity information, organization information, device information, driver behavior information, and passenger feedback information.

[0061] Specifically, identity information includes the driver's age and gender; organizational information includes the platform, fleet and working city; device information includes the current device identity, the last operation identity and the time since the last operation; driver behavior information includes the time interval since the last verification, the time taken for the last verification, the driver's voiceprint, the driver's working hours on that day and the driver's violation rate in the past 7 days; passenger feedback information refers to the number of passenger complaints since the last verification.

[0062] Step S102, input the target information into the target model under the target period to obtain the target scoring level.

[0063] Optionally, in the disclosed embodiment, the target model adopts a scorecard model, which is a means of measuring the credit risk of an object, and divides the credit score level of the object according to various attributes and data of the object. The target score level refers to the credit score level of the current driver.

[0064] Specifically, the server inputs the target information into the target model under the target period to perform credit scoring and obtain a target scoring level (high credit, medium credit or low credit).

[0065] Step S103, obtaining the target probability value according to the target scoring level and the mapping relationship, wherein the target probability value represents the probability of the target object being sampled, and the mapping relationship is used to characterize the correspondence between the scoring level list and the probability value list, the target scoring level is included in the scoring level list, and the target probability value is included in the probability value list.

[0066] Optionally, in the disclosed embodiment, the target probability value represents the probability of the current driver being spot-checked, and the mapping relationship is used to characterize the correspondence between the scoring level list and the probability value list. The target scoring level is included in the scoring level list, and the target probability value is included in the probability value list.

[0067] It should be noted that in the mapping relationship, the higher the score level, the smaller the probability of being sampled, that is, the corresponding probability values ​​of high credit, medium credit, and low credit decrease in sequence.

[0068] Specifically, the server matches the corresponding probability value in the probability value list according to the target scoring level and the mapping relationship to obtain the target probability value.

[0069] Step S104, when the target probability value is the same as the hit parameter, a random check is performed on the target object to obtain an identity authentication result, wherein the hit parameter is used to indicate the condition for performing a random check operation on the target object.

[0070] Optionally, in the embodiment of the present disclosure, the method for authenticating the current driver may be face recognition.

[0071] Specifically, Figure 2 As shown, when the target probability value is the same as the hit parameter, the server performs face verification on the target object and obtains the identity verification result; when the target probability value is different from the hit parameter, no face verification is performed.

[0072] It should be noted that face recognition technology is a biometric technology that identifies people based on their facial features. Mainstream face recognition technologies are divided into two types: static detection and liveness detection. Static detection refers to the recognition of a single face image, while dynamic detection refers to the detection and recognition of a video stream or a series of continuous face images. Dynamic detection has a stronger ability to verify the authenticity of faces than static detection, but it is more disturbing to the subject.

[0073] In the disclosed embodiment, by obtaining the target information and target time period of the target object, wherein the target information is used to authenticate the identity of the target object; inputting the target information into the target model under the target time period to obtain the target rating level; obtaining the target probability value according to the target rating level and the mapping relationship, wherein the target probability value represents the probability of the target object being sampled, the mapping relationship is used to characterize the correspondence between the rating level list and the probability value list, the target rating level is included in the rating level list, and the target probability value is included in the probability value list; when the target probability value is the same as the hit parameter, the target object is sampled to obtain the identity authentication result, wherein the hit parameter is used to represent the condition for performing the sampling operation on the target object. Since the disclosed embodiment samples the target object according to the target probability value corresponding to the target rating level of the target object under the target time period, a differentiated identity authentication strategy of the object dimension is implemented, the risk control level in high-risk scenarios is improved, the target object experience disturbance in low-risk scenarios is reduced, the contradiction between the frequency increase and frequency decrease of identity authentication is resolved, and the refinement of the identity authentication strategy is improved.

[0074] In some optional implementations, the target information is input into the target model under the target period to obtain the target scoring level, including:

[0075] Inputting the target information into the target prediction module under the target period to obtain the target scoring result, wherein the target prediction module is included in the target model;

[0076] According to the target scoring interval into which the target scoring result falls, the target scoring level corresponding to the target scoring interval is obtained.

[0077] Optionally, in the disclosed embodiment, the target prediction module adopts a logistic regression model (LR), which is included in the scorecard model. The target score result is the predicted probability value of the face verification result (pass or fail) of the current driver, and the value range is any value between 0 and 1. The target score interval includes the target score result, which corresponds to the target score level.

[0078] It should be noted that logistic regression is a statistical method for classification problems, mainly used for binary classification (i.e., the result is 0 or 1). Its core idea is to use the features of linear combination to predict the probability of an event, and map the probability to between 0 and 1 through a logical function.

[0079] Specifically, the server inputs the target information into the target prediction module under the target time period for prediction, obtains the target scoring result, and matches the corresponding scoring level according to the target scoring interval into which the target scoring result falls, to obtain the target scoring level.

[0080] In the disclosed embodiment, the target information is input into the target prediction module under the target time period to obtain the target scoring result, and the corresponding target scoring grade is obtained according to the target scoring interval into which the target scoring result falls, thereby realizing the grade classification of the target object in the object dimension.

[0081] In some optional implementations, after spot checking the target object and obtaining the identity verification result, the method further includes:

[0082] The preset scoring range is adjusted according to the target scoring level and the identity verification result, wherein the target scoring range is included in the preset scoring range.

[0083] Optionally, in an embodiment of the present disclosure, the preset scoring interval includes a target scoring interval, and the preset scoring interval corresponds to a scoring level (including high credit, medium credit, and low credit) in the scoring level list.

[0084] Specifically, after the server performs a random check on the current driver to obtain the identity verification result, it adjusts the preset score range according to the target score level and the identity verification result (pass or fail).

[0085] In the disclosed embodiment, by adjusting the preset scoring interval according to the target scoring level and the identity authentication result, the setting of the preset scoring interval is made more reasonable, and the identity authentication strategy is optimized.

[0086] In some optional implementations, before inputting the target information into the target prediction module under the target period to obtain the target scoring result, the method further includes:

[0087] Obtain a training data set of a training object, wherein the training data carries sample labels under multiple time periods, the training data is used to authenticate the identity of the training object, the sample labels are historical identity authentication results of the training object, and the target time period is included in the multiple time periods;

[0088] Preprocess the training data to obtain mapping values;

[0089] Input the mapped value into the initial prediction module under the corresponding time period to obtain the initial scoring result;

[0090] According to the initial scoring results and sample labels, the preset parameters in the initial prediction module are adjusted to obtain the target prediction module, wherein the preset parameters are used to adjust the influence of the mapping value.

[0091] Optionally, in the disclosed embodiment, the training object is the historical driver of the online car-hailing platform, and the training data is used to authenticate the historical driver. The sample label is the historical identity authentication result of the historical driver (including pass and fail). The target time period is included in multiple time periods, for example, the daytime period (5:00-23:00) and the nighttime period (23:00-5:00). The mapping values ​​include 1, 0, and -1. The initial scoring result is the predicted probability value of the historical driver's face verification result (pass or fail), and the value range is any value between 0 and 1.

[0092] It should be noted that the initial prediction module is a logistic regression model. The server constructs a corresponding logistic regression model based on the mapping value X, the preset parameter β and the current time period. The logistic regression model is defined as follows:

[0093] z=β0+β1X1+β2X2+...+β n X n

[0094] Here, z is the output of the logistic regression model.

[0095] Then, the server can use the Sigmoid function to convert the output result z into a probability value. The Sigmoid function is defined as follows:

[0096]

[0097] The server inputs the historical driver training data of each time period into the corresponding logistic regression model to obtain the output result z, and then obtains the probability value σ(z) based on the output result z and the Sigmoid function to obtain the initial scoring result.

[0098] Specifically, the server first preprocesses the training data, and maps the positive, neutral, and negative effects of the training data on the initial prediction module to 1, 0, and -1, respectively, to obtain the mapping value. Then, the server inputs the mapping value into the initial prediction module under the corresponding time period for prediction, and obtains the initial scoring result. Finally, the server uses the optimization algorithm to adjust the preset parameters in the initial prediction module according to the initial scoring result and sample label to obtain the target prediction module.

[0099] The effect of the target prediction module during the daytime is as follows Figure 3 As shown, Figure 3 It is a daytime model effect diagram of the identity authentication method according to an embodiment of the present disclosure.

[0100] Figure 3 In the figure, the horizontal axis is the recall rate, which indicates the proportion of correctly predicted positive samples (i.e., the driver himself). The recall rate is defined as follows:

[0101]

[0102] Among them, TP is a true positive example, that is, the predicted result is a positive sample and the actual result is a positive sample. FN is a false negative example, that is, the predicted result is a negative sample and the actual result is a positive sample.

[0103] The vertical axis is the precision, which indicates the proportion of truly positive samples among the predicted positive samples. The precision is defined as follows:

[0104]

[0105] Among them, FP is a false positive example, that is, the predicted result is a positive sample and the true result is a negative sample.

[0106] The results of the target prediction module during the daytime period are shown in the following table:

[0107] Rating scale Rating range Personal rate High credit 0.99449～1 99.4％ China Credit 0.99252～0.99449 99.4％ Low credit 0～0.99252 96.2％

[0108] Among them, the personal rate is the proportion of operations actually performed by the driver himself under the target scoring level.

[0109] In the target prediction module during the daytime period, the score range of the high credit score level is 0.99449~1, and the personal rate is 99.4%; the score range of the medium credit score level is 0.99252~0.99449, and the personal rate is 99.4%; the score range of the low credit score level is 0~0.99252, and the personal rate is 96.2%.

[0110] The effect of the target prediction module during the night time is as follows: Figure 4 As shown, Figure 4 It is a night model effect diagram of the identity authentication method according to an embodiment of the present disclosure.

[0111] The results of the target prediction module during the night time period are shown in the following table:

[0112] Rating scale Rating range Personal rate High credit 0.99488～1 99.5％ China Credit 0.99296～0.99488 99.5％ Low credit 0～0.99296 97.1％

[0113] In the target prediction module during the night time period, the score range of the high credit score level is 0.99488~1, and the personal rate is 99.5%; the score range of the medium credit score level is 0.99296~0.99488, and the personal rate is 99.5%; the score range of the low credit score level is 0~0.99296, and the personal rate is 97.1%.

[0114] In the disclosed embodiment, by preprocessing the training data to obtain the mapping value, the quality and consistency of the training data can be ensured. By adjusting the preset parameters in the initial prediction module according to the initial scoring result and the sample label, the target prediction module can be obtained, and the target information can be processed to obtain the scoring result.

[0115] In some optional implementations, preprocessing the training data to obtain the mapping value includes:

[0116] Perform feature transformation on the training data to obtain feature values;

[0117] Map the eigenvalues ​​to obtain mapped values.

[0118] Optionally, in the disclosed embodiment, the mapping value includes 1, 0, and -1. The server first processes and transforms the training data to obtain a feature value, and then maps the positive, neutral, and negative effects of the feature value on the initial prediction module to 1, 0, and -1, respectively, to obtain a mapping value.

[0119] For example, if the driver's violation rate in the past seven days is 0, the impact on the initial prediction module is positive, mapped to 1; the driver's gender has a neutral impact on the initial prediction module, mapped to 0; and a large number of passenger complaints since the last verification has a negative impact on the initial prediction module, mapped to -1.

[0120] In the disclosed embodiment, the quality and consistency of the training data can be ensured by performing feature conversion on the training data to obtain feature values, and then mapping the feature values ​​to obtain mapping values.

[0121] In some optional implementations, before inputting the target information into the target model under the target period to obtain the target scoring level, the method further includes:

[0122] Match the target information on the preset platform to obtain the verification strategy;

[0123] Based on the verification strategy, multiple rounds of judgment are performed on the target object in sequence, wherein the multiple rounds of judgment are used to perform regular verification on the target object;

[0124] When multiple rounds of judgments do not satisfy the criteria, the target information is input into the target model under the target period to obtain the target rating level.

[0125] Optionally, in the disclosed embodiment, the preset platform is a scenario strategy configuration interface, which supports matching according to different business scenarios such as cities, platforms, default channels, etc., and when the server is running, it obtains and applies corresponding verification strategies in real time according to the driver's city and service provider.

[0126] It should be noted that multiple rounds of judgment are used for routine verification of the current driver, including whether there is a verification task to be executed, whether the login account has been changed, whether the login device has been changed, whether it is the first verification for the daily vehicle outing, whether the maximum time interval has exceeded the last verification, whether the current scenario is a login scenario and the last verification scenario was a forgotten password within 5 minutes, and whether there is a voiceprint to be verified.

[0127] Specifically, Figure 2 As shown, the server first obtains the target information and target time period of the current driver, and matches the "working city", "online car-hailing platform", "scenario type", "business type" and "scheme status" in the scenario strategy configuration interface according to the target information to obtain a strategy list. Then, the server makes a supplementary judgment on whether the driver's anti-disturbance strategy is hit, where the anti-disturbance strategy sets the maximum number of verifications within the time period based on the time period and scene. If the driver's anti-disturbance strategy is not hit, the server determines whether the client supports face recognition. If the client does not support face recognition, face verification is not performed; if the client supports face recognition, multiple rounds of judgments are performed on the current driver in sequence. If any of the multiple rounds of judgments are met, the server performs face verification on the current driver; if all the multiple rounds of judgments are not met, the current driver is spot-checked.

[0128] In the embodiment of the present disclosure, multiple rounds of judgments are performed on the target object in sequence according to the verification strategy obtained by matching the target information on the preset platform, thereby achieving conventional verification of the target object.

[0129] In this embodiment, an identity authentication device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0130] This embodiment provides an identity authentication device, such as Figure 5 As shown, including:

[0131] The first acquisition module 501 is used to acquire target information and target time period of a target object, wherein the target information is used to authenticate the identity of the target object;

[0132] The first obtaining module 502 is used to input the target information into the target model under the target period to obtain the target scoring level;

[0133] The second obtaining module 503 is used to obtain a target probability value according to the target scoring level and the mapping relationship, wherein the target probability value represents the probability of the target object being sampled, the mapping relationship is used to characterize the corresponding relationship between the scoring level list and the probability value list, the target scoring level is included in the scoring level list, and the target probability value is included in the probability value list;

[0134] The third obtaining module 504 is used to perform a random check on the target object to obtain the identity verification result when the target probability value is the same as the hit parameter, wherein the hit parameter is used to indicate the condition for performing a random check operation on the target object.

[0135] In the disclosed embodiment, by obtaining the target information and target time period of the target object, wherein the target information is used to authenticate the identity of the target object; inputting the target information into the target model under the target time period to obtain the target rating level; obtaining the target probability value according to the target rating level and the mapping relationship, wherein the target probability value represents the probability of the target object being sampled, the mapping relationship is used to characterize the correspondence between the rating level list and the probability value list, the target rating level is included in the rating level list, and the target probability value is included in the probability value list; when the target probability value is the same as the hit parameter, the target object is sampled to obtain the identity authentication result, wherein the hit parameter is used to represent the condition for performing the sampling operation on the target object. Since the disclosed embodiment samples the target object according to the target probability value corresponding to the target rating level of the target object under the target time period, a differentiated identity authentication strategy of the object dimension is implemented, the risk control level in high-risk scenarios is improved, the target object experience disturbance in low-risk scenarios is reduced, the contradiction between the frequency increase and frequency decrease of identity authentication is resolved, and the refinement of the identity authentication strategy is improved.

[0136] In some optional implementations, the first obtaining module 502 includes:

[0137] A first obtaining unit is used to input the target information into a target prediction module under the target period to obtain a target scoring result, wherein the target prediction module is included in the target model;

[0138] The second obtaining unit is used to obtain the target scoring level corresponding to the target scoring interval according to the target scoring interval into which the target scoring result falls.

[0139] In some optional embodiments, the device further comprises:

[0140] The adjustment module is used to adjust the preset scoring interval according to the target scoring level and the identity authentication result, wherein the preset scoring interval is set according to the predicted value and the target scoring interval is included in the preset scoring interval.

[0141] In some optional embodiments, the device further comprises:

[0142] A second acquisition module is used to acquire a training data set of a training object, wherein the training data carries sample labels under multiple time periods, the training data is used to authenticate the identity of the training object, the sample labels are historical identity authentication results of the training object, and the target time period is included in the multiple time periods;

[0143] The fourth obtaining module is used to pre-process the training data to obtain the mapping value;

[0144] The fifth obtaining module is used to input the mapping value into the initial prediction module under the corresponding time period to obtain the initial scoring result;

[0145] The sixth obtaining module is used to adjust the preset parameters in the initial prediction module according to the initial scoring results and the sample labels to obtain the target prediction module, wherein the preset parameters are used to adjust the influence of the mapping value.

[0146] In some optional implementations, the fourth obtaining module includes:

[0147] The third obtaining unit is used to perform feature conversion on the training data to obtain feature values;

[0148] The fourth obtaining unit is used to map the eigenvalue to obtain a mapping value.

[0149] In some optional embodiments, the device further comprises:

[0150] The seventh obtaining module is used to match the target information on a preset platform to obtain a verification strategy;

[0151] A judgment module, used to perform multiple rounds of judgment on the target object in sequence based on the verification strategy, wherein the multiple rounds of judgment are used to perform regular verification on the target object;

[0152] The eighth obtaining module is used to input the target information into the target model under the target period to obtain the target scoring level when multiple rounds of judgments are not satisfied.

[0153] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0154] The identity authentication device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0155] The present disclosure also provides a computer device having the above Figure 5 Authentication device shown.

[0156] See also Figure 6 , Figure 6 is a schematic diagram of a computer device provided by an optional embodiment of the present disclosure, such as Figure 6 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 A processor 10 is taken as an example.

[0157] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0158] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0159] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0160] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0161] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0162] The embodiments of the present disclosure also provide a computer-readable storage medium. The above-mentioned method according to the embodiments of the present disclosure can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium and downloaded through a network, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0163] A part of the present disclosure may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present disclosure through the operation of the computer. Those skilled in the art should understand that the existence of computer program instructions in computer-readable media includes, but is not limited to, source files, executable files, installation package files, etc., and accordingly, the way in which computer program instructions are executed by a computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0164] Although the embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. An identity authentication method, characterized in that: The method comprises: Acquire target information and target time period of a target object, wherein the target information is used to authenticate the identity of the target object; Inputting the target information into the target model under the target period to obtain a target scoring level; According to the target scoring level and the mapping relationship, a target probability value is obtained, wherein the target probability value represents the probability of the target object being sampled, the mapping relationship is used to characterize the corresponding relationship between the scoring level list and the probability value list, the target scoring level is included in the scoring level list, and the target probability value is included in the probability value list; In the case where the target probability value is the same as the hit parameter, a random check is performed on the target object to obtain an identity authentication result, wherein the hit parameter is used to indicate a condition for performing a random check operation on the target object.

2. The method according to claim 1, characterized in that The step of inputting the target information into the target model under the target period to obtain a target scoring level includes: Inputting the target information into a target prediction module under the target period to obtain a target scoring result, wherein the target prediction module is included in the target model; According to the target scoring interval into which the target scoring result falls, the target scoring level corresponding to the target scoring interval is obtained.

3. The method according to claim 2, characterized in that After the target object is sampled and the identity verification result is obtained, the method further includes: The preset scoring interval is adjusted according to the target scoring level and the identity authentication result, wherein the target scoring interval is included in the preset scoring interval.

4. The method according to claim 2, characterized in that: Before inputting the target information into the target prediction module under the target period to obtain the target scoring result, the method further includes: Acquire a training data set of a training object, wherein the training data carries sample labels under multiple time periods, the training data is used to authenticate the identity of the training object, the sample labels are historical identity authentication results of the training object, and the target time period is included in the multiple time periods; Preprocessing the training data to obtain a mapping value; Inputting the mapping value into the initial prediction module under the corresponding time period to obtain an initial scoring result; According to the initial scoring result and the sample label, the preset parameters in the initial prediction module are adjusted to obtain the target prediction module, wherein the preset parameters are used to adjust the influence of the mapping value.

5. The method according to claim 4, characterized in that The preprocessing of the training data to obtain a mapping value comprises: Performing feature conversion on the training data to obtain feature values; The characteristic value is mapped to obtain the mapped value.

6. The method according to claim 5, characterized in that Before inputting the target information into the target model under the target period to obtain the target scoring level, the method further includes: Matching is performed on a preset platform according to the target information to obtain a verification strategy; Based on the verification strategy, multiple rounds of judgment are performed on the target object in sequence, wherein the multiple rounds of judgment are used to perform conventional verification on the target object; When the multiple rounds of judgments do not satisfy the requirement, the target information is input into the target model under the target period to obtain the target scoring level.

7. An identity verification device, characterized in that: The device comprises: A first acquisition module is used to acquire target information and a target time period of a target object, wherein the target information is used to authenticate the identity of the target object; A first obtaining module is used to input the target information into the target model under the target period to obtain a target scoring level; A second obtaining module is used to obtain a target probability value according to the target scoring level and the mapping relationship, wherein the target probability value represents the probability of the target object being sampled, the mapping relationship is used to characterize the corresponding relationship between the scoring level list and the probability value list, the target scoring level is included in the scoring level list, and the target probability value is included in the probability value list; The third obtaining module is used to perform a random inspection on the target object to obtain an identity authentication result when the target probability value is the same as the hit parameter, wherein the hit parameter is used to indicate a condition for performing a random inspection operation on the target object.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the identity authentication method according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the identity authentication method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are used to cause a computer to execute the identity authentication method according to any one of claims 1 to 6.

Images