CN113592161A

CN113592161A - Access equipment identification method and device based on collection urging label and computer equipment

Info

Publication number: CN113592161A
Application number: CN202110797733.2A
Authority: CN
Inventors: 武佳琪; 付棋红; 苏绥绥
Original assignee: Beijing Qilu Information Technology Co Ltd
Current assignee: Beijing Qilu Information Technology Co Ltd
Priority date: 2021-07-14
Filing date: 2021-07-14
Publication date: 2021-11-02

Abstract

The invention provides an access device identification method and device based on an acquisition-promoting label and computer equipment. The method comprises the following steps: screening a specific user group according to a preset screening rule; calculating an evaluation index of the specific user group, generating an acceptance promoting label according to the evaluation index, and constructing an equipment risk prediction model based on the acceptance promoting label; and carrying out risk identification on the new access equipment by using the trained equipment risk prediction model. The invention can accurately screen out the users belonging to the specific user group and can accurately determine the user associated equipment corresponding to the users of the specific user group; by calculating the evaluation index of a specific user group, an induced collecting label for representing the risk size of the user-associated equipment is generated, an equipment risk prediction model based on the induced collecting label is constructed, and the risk calculation of the new access equipment is carried out through the equipment risk prediction, so that the risk condition of the new access equipment can be more accurately quantified, and whether the new access equipment is the risk equipment or not can be effectively identified.

Description

Access equipment identification method and device based on collection urging label and computer equipment

Technical Field

The invention relates to the field of computer information processing, in particular to an access device identification method and device based on an acquisition prompting label and computer equipment.

Background

Risk prediction is the quantification of risk and is a critical technique for risk management. At present, risk identification is generally carried out in a modeling mode, and in the process of establishing a model, the steps of data extraction, feature generation, feature selection, algorithm model generation, rationality evaluation and the like are mainly carried out.

In the prior art, the main purpose of equipment risk prediction is how to distinguish good customers from bad customers, evaluate the risk condition of users, so as to reduce credit risk and realize profit maximization. In general, some devices may be risk-free devices, but once there is a market risk, a risk-free device may be changed into a risk device following the change of the associated user from a good user to a risk user, in which case, a certain resource loss may be caused to the resource management platform. Furthermore, there is still much room for improvement in risk prediction, model parameter estimation, model computational accuracy, data update for a particular user group or user-associated device.

Therefore, there is a need to provide an access device authentication method based on a hasty tag to solve the above problems.

Disclosure of Invention

In order to solve the following problems: the balance of the resource management platform is reliably guaranteed, the influence of the resource recovery amount of a specific user group on the whole resource distribution and recovery use process is effectively avoided, the problem of user error refusal is reduced, the risk of user-associated equipment is accurately quantified, meanwhile, risk identification is carried out on new access equipment, the user experience is improved, and the loss of the resource management platform is reduced.

The first aspect of the present invention provides an access device authentication method based on an incoming call ticket, including: screening a specific user group according to a preset screening rule; calculating an evaluation index of the specific user group, generating an acceptance promoting label according to the evaluation index, and constructing an equipment risk prediction model based on the acceptance promoting label; and carrying out risk identification on the new access equipment by using the trained equipment risk prediction model.

According to an optional embodiment of the present invention, the calculating an evaluation index of the specific user group, and the generating the incentive tag according to the evaluation index comprises: and using the resource recovery rate in a specific time period from the resource recovery time point as an acceptance urging label value, and determining a good sample and a bad sample to establish a training data set.

According to an alternative embodiment of the invention, comprising: calculating an evaluation index by the following formula, wherein the evaluation index is the resource recovery rate:

the resource recovery rate refers to the ratio of the recoverable amount of the internet service resource amount to the promoted amount of the resource in a specific time period from the resource return time point; the amount recovered in x days is the amount of internet service resources which execute the charging-urging strategy and return the resources by the user within a specific time (namely x days) from the time point of returning the resources; the resource credit is the internet service resource amount which is not returned at the resource returning time point.

the resource recovery rate refers to the ratio of the recoverable amount of the internet service resource amount to the promoted amount of the resource in a specific time period from the resource return time point; the amount which is not recovered after (x +1) days is the amount of the internet service resources which are executed with the collection urging strategy and are not recovered by the user after a certain time plus one day from the time point of recovering the resources; the resource credit is the internet service resource amount which is not returned at the resource returning time point.

According to an alternative embodiment of the invention, comprising: the method comprises the steps of obtaining internet service resource limit, resource service time and resource urging time of a historical user, and calculating the resource urging amount.

According to an alternative embodiment of the present invention, the filtering the specific user group according to the predetermined filtering rule comprises: the preset screening rule comprises a configuration time parameter and a resource recovery rate threshold value, wherein the time parameter is within a specific time from the resource returning time; and screening out users which return the resources within a specific time from the resource returning time and are greater than the threshold value of the resource recovery rate, wherein the users belong to the specific user group, and the specific user group is used for representing the specific group with the increased resource returning risk under the influence of the market risk factors.

According to an optional embodiment of the present invention, the risk identification of the new access device using the trained device risk prediction model comprises: calculating a predicted value of the new access device by using the device risk prediction model; comparing the calculated predicted value with a set threshold value, and determining to provide internet service resources for the new access equipment when the calculated predicted value is less than or equal to the set threshold value; and when the calculated predicted value is larger than a set threshold value, determining not to provide the internet service resources for the new access equipment.

In addition, a second aspect of the present invention provides an access device authentication apparatus based on an incoming call ticket, including: the screening module screens a specific user group according to a preset screening rule; the calculation module is used for calculating the evaluation index of the specific user group, generating an acceptance promoting label according to the evaluation index and constructing an equipment risk prediction model based on the acceptance promoting label; and the prediction module is used for carrying out risk identification on the new access equipment by using the trained equipment risk prediction model.

Furthermore, a third aspect of the present invention provides a computer device comprising a processor and a memory for storing a computer executable program, which when executed by the processor performs the method for authenticating an access device based on an incoming call ticket according to the first aspect of the present invention.

Furthermore, a fourth aspect of the present invention provides a computer program product storing a computer executable program which, when executed, implements the method for authenticating an access device based on an incoming call ticket according to the first aspect of the present invention.

Advantageous effects

Compared with the prior art, the method and the device have the advantages that the user screening is carried out through the preset screening rule, the users belonging to the specific user group can be accurately screened, and the user associated equipment corresponding to the users of the specific user group can be accurately determined; and calculating the evaluation index of the specific user group to generate an acceptance urging label for representing the risk of the user-associated equipment, constructing an equipment risk prediction model based on the acceptance urging label, and calculating the risk of the new access equipment through the equipment risk prediction model, so that the risk condition of the new access equipment can be more accurately quantified, and whether the new access equipment is the risk equipment can be effectively identified.

Further, the risk equipment can be determined more accurately by performing the step of judging the number of the poor users for the associated users of the new access equipment; model parameters can be optimized by adjusting the model parameters in the equipment risk prediction model, the model authentication precision can be improved, and the construction process of the equipment risk prediction model can be optimized; by executing the collection-urging strategy, the resources of the users in the specific user group can be effectively ensured to be returned.

Drawings

In order to make the technical problems solved by the present invention, the technical means adopted and the technical effects obtained more clear, the following will describe in detail the embodiments of the present invention with reference to the accompanying drawings. It should be noted, however, that the drawings described below are only illustrations of exemplary embodiments of the invention, from which other embodiments can be derived by those skilled in the art without inventive faculty.

Fig. 1 is a flowchart of an example of an access device authentication method based on a proctoring tag according to embodiment 1 of the present invention.

Fig. 2 is a flowchart of another example of an access device authentication method based on a proctoring tag according to embodiment 1 of the present invention.

Fig. 3 is a flowchart of another example of an access device authentication method based on a proctoring tag according to embodiment 1 of the present invention.

Fig. 4 is a schematic diagram of an example of an access device authentication apparatus based on an induced receipt tag according to embodiment 2 of the present invention.

Fig. 5 is a schematic diagram of another example of an access device authentication apparatus based on an induced receipt tag according to embodiment 2 of the present invention.

Fig. 6 is a schematic diagram of another example of an access device authentication apparatus based on an induced receipt tag according to embodiment 2 of the present invention.

Fig. 7 is a schematic diagram of still another example of an access device authentication apparatus based on an induced receipt tag according to embodiment 2 of the present invention.

Fig. 8 is a block diagram of an exemplary embodiment of a computer device according to the present invention.

Fig. 9 is a block diagram of an exemplary embodiment of a computer program product according to the present invention.

Detailed Description

Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. The exemplary embodiments, however, may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these exemplary embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the invention to those skilled in the art. The same reference numerals denote the same or similar elements, components, or parts in the drawings, and thus their repetitive description will be omitted.

Features, structures, characteristics or other details described in a particular embodiment do not preclude the fact that the features, structures, characteristics or other details may be combined in a suitable manner in one or more other embodiments in accordance with the technical idea of the invention.

In describing particular embodiments, the present invention has been described with reference to features, structures, characteristics or other details that are within the purview of one skilled in the art to provide a thorough understanding of the embodiments. One skilled in the relevant art will recognize, however, that the invention may be practiced without one or more of the specific features, structures, characteristics, or other details.

The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.

The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.

It will be understood that, although the terms first, second, third, etc. may be used herein to describe various elements, components, or sections, these terms should not be construed as limiting. These phrases are used to distinguish one from another. For example, a first device may also be referred to as a second device without departing from the spirit of the present invention.

The term "and/or" and/or "includes any and all combinations of one or more of the associated listed items.

In view of the above problems, the present invention performs user screening by using a predetermined screening rule, can accurately screen out users belonging to a specific user group, and can accurately determine user-associated devices corresponding to users of the specific user group; and calculating the evaluation index of the specific user group to generate an acceptance urging label for representing the risk size of the user-associated equipment, constructing an equipment risk prediction model based on the acceptance urging label, and calculating the risk of the new access equipment through the equipment risk prediction, so that the risk condition of the new access equipment can be more accurately quantified, and whether the new access equipment is the risk equipment can be effectively identified.

It should be noted that, the innovation of the present invention is how to make the risk identification process of the user-associated device more automated, efficient and reduce the labor cost according to the interaction between the user-associated device and the internet service platform (i.e. the information interaction between objects). However, for convenience, the access device authentication is illustrated in the present invention by taking an internet service as an example, but the present invention is not to be construed as being limited thereto. The specific procedure of the access device authentication method will be described in detail below.

Example 1

Hereinafter, an embodiment of an access device authentication method based on an induced receipt tag according to the present invention will be described with reference to fig. 1 to 3.

Fig. 1 is a flowchart of an access device authentication method based on an incoming call ticket according to the present invention. As shown in fig. 1, the access device authentication method includes the following steps.

Step S101, according to the preset screening rule, screening the specific user group.

And step S102, calculating an evaluation index of the specific user group, generating an acceptance label according to the evaluation index, and constructing an equipment risk prediction model based on the acceptance label.

And step S103, carrying out risk identification on the new access equipment by using the trained equipment risk prediction model.

In order to accurately identify the risk of the access device, intensive research is carried out on the part of users which are changed from good users to bad users under the influence of external environment (wherein the users are all users provided with internet service resources, and the part of users are specific user groups), and the resource recycling rate of the part of users greatly influences the whole resource allocation and recycling using process of the resource management platform and even seriously influences the balance of income and expenditure of the resource management platform. Wherein, the specific user group particularly refers to a specific group with increased resource return risk under the influence of market risk factors. Therefore, in order to reliably ensure the balance of the resource management platform and effectively avoid the influence of the resource recovery amount of a specific user group on the whole resource allocation and recovery use process of the resource management platform, the resource recovery risk of the specific user group is quantized by establishing a machine learning model (namely an equipment risk prediction model) based on the collection urging label so as to represent the risk of user-associated equipment, so that the problem of false refusal of a user can be reduced, meanwhile, the risk identification can be carried out on new access equipment so as to effectively refuse the access of the risk equipment, the user experience can be improved, and the loss of the resource management platform can be reduced.

In the present invention, the internet service includes an internet service resource that provides, for example, shopping, riding, maps, takeout, shared bicycle, and the like in response to an application from the user-associated device to the internet service platform. Such as resource allocation services, resource usage services, resource guarantee services or mutual aid services, group buying and ride service, etc. Where resources refer to any available substances, information, time, information resources including computing resources and various types of data resources. The data resources include various private data in various domains. The user associated device refers to a device associated with a registered user when applying for a service on an internet service platform, and is generally represented by a device ID. After a user in a specific user group applies for using internet service and obtains resource allocation authorization, due to the influence of market risk factors, the user may have a default behavior or a risk behavior that resources are not returned, and the like, so that resource loss is caused to a resource management platform. The invention just predicts the risk caused by the risk behaviors so as to prevent the risks in advance or afterwards.

The specific process of the method of the present invention will be described below by taking an internet resource allocation service as an example.

First, in step S101, a specific user group is filtered according to a predetermined filtering rule.

In a specific embodiment, step S101 is divided into step S101 and step S201, and a step of configuring a predetermined filtering rule in advance (i.e., step S201) is performed before step S101 of filtering a specific user group is performed.

In step S201, a predetermined filtering rule is configured in advance.

Specifically, the predetermined screening rule includes configuring a time parameter and a resource recovery rate threshold, where the time parameter is within a specific time from the resource return time. For example, within 20 days from the time of return of the resource.

More specifically, the specific time is 7 days to 30 days, for example, 7 days, 15 days, 20 days, or 30 days, and the like.

It should be noted that, the time node for the resource allocation service is the resource return time, but not limited to this, in other examples of internet services, the time node is the resource connection time, the resource service payment time, or the resource service transaction time, etc. The foregoing is illustrative only and is not to be construed as limiting the invention.

Further, for the configuration of the resource recovery rate threshold, the resource recovery rate threshold of the user is configured, for example, by the relevant service personnel according to the total resource amount, the resource balance ratio or the historical resource recovery rate for different types of resource services within a certain period of time (e.g., within a half year, within a year, within two years, etc.). For example, the total resource amount of the resource allocation service in one year is 100 ten thousand, the historical resource recovery rate is 80%, and a resource recovery rate threshold of, for example, 80% to 90% of users is configured, specifically, the resource recovery rate threshold is, for example, 85%.

In one embodiment, the predetermined filtering rule is that the user has returned the resource within a certain time (e.g., 30 days) from the time of the resource return and the resource recovery rate is greater than the resource recovery rate threshold (e.g., 80%). When the predetermined screening rule is used for screening users, users who have returned resources within 30 days from the resource returning time and have resource recovery rates greater than a resource recovery rate threshold (for example, 80%) are screened, and then the users belong to the specific user group, and the associated devices of the users are devices (i.e., user associated devices) associated with the users when the users apply for internet resource services to the resource management platform or when the users register.

It should be noted that, the specific user group is used for characterizing the specific group which has increased resource return risk under the influence of market risk factors and is changed from a good user to a bad user, wherein the market risk factors include unexpected risk factors and environmental risk factors determined according to market risk indexes.

Specifically, the market risk indicators include unexpected risk indicators including risk indicators related to unexpected events of the resource-returning person (i.e., users belonging to a specific user group), for example, risk indicators indicating that the resource-returning person has reduced or no economic income due to an unexpected accident, or risk indicators indicating that the resource-returning person cannot return or has a possibility of not returning. The environmental risk index includes risk index related to risk caused by natural environment or social environment, for example, risk index indicating that resource return caused by natural disaster affects resource return due to physical or personal injury. For another example, the change of policy and law is expressed, so that the economic environment, production and operation of related enterprises are affected, and further the risk index of the resource returning person which can not return or has the possibility of not returning is affected.

In another embodiment, the predetermined filtering rule is that the user has returned the resource for a certain time (e.g., 20 days) from the time of the resource return and is greater than the resource recovery rate threshold (e.g., 85%). When the predetermined screening rule is used for screening users, users who have returned resources from the user within 20 days of the resource return time and are greater than the resource recovery rate threshold (for example, 85%) are screened, and then the users belong to the specific user group, and information data of the user-associated devices of the users, such as device IDs, device identification codes, device names, and the like of the user-associated devices, are screened.

Therefore, the users belonging to the specific user group can be accurately screened out through the predetermined screening rule, and the user-associated equipment corresponding to the users of the specific user group can be accurately determined.

It should be noted that the above description is only given by way of example, and the present invention is not limited thereto.

In order to ensure that the resources of the users in the specific user group are returned, an urging strategy is usually adopted to urge the users to return the resources, so that the invention uses the user sample data of the specific user group containing urging data to generate an urging label (namely the urging label of the users in the specific user group represents the risk of the user-associated equipment), uses the urging label to establish an equipment risk prediction model, and then uses the equipment risk prediction model to carry out risk identification on the new access equipment. The process of constructing the equipment risk prediction model will be described in detail below.

In step S102, an evaluation index of the specific user group is calculated, an acceptance label is generated according to the evaluation index, and an equipment risk prediction model based on the acceptance label is constructed.

Specifically, user sample data belonging to a specific user group in the historical users is obtained, and the user sample data comprises an internet service resource limit, resource service time, resource urging time, a resource returning period number, and an internet service resource amount (also referred to as a resource amount for short in the present invention) to be returned corresponding to the resource returning period number, wherein a plurality of resource returning time points can be determined according to the resource returning period number.

Further, according to the obtained user sample data, an evaluation index of the users in the specific user group is calculated, and a collection urging label is generated according to the evaluation index.

In an alternative embodiment, the evaluation index is calculated by the following formula:

the resource recovery rate refers to the ratio of the recoverable amount of the internet service resource amount to the promoted amount of the resource in a specific time period from the resource return time point; the amount recovered in x days is the internet service resource amount (also referred to as resource amount for short in the present invention) of the resource returned by the user within a specific time (i.e. x days) from the resource return time point after the execution of the charging-urging policy; the resource credit is the internet service resource amount which is not returned at the resource returning time point.

Specifically, the x days correspond to a specific time in step S101, for example, 7 to 30 days, such as 7, 15, 20, or 30 days, and so on.

In another alternative embodiment, the evaluation index is calculated by the following formula:

Specifically, the x +1 day corresponds to a specific time in step S101, for example, 8 to 31 days, such as 8, 16, 21, or 31 days, and so on.

Therefore, by calculating the resource recovery rate of the user, the resource recovery rate can be accurately calculated.

Specifically, for example, a device risk prediction model is constructed based on the hastelling label and using an XGBoost method or a deep neural network.

It should be noted that the above description is only given by way of example, and the present invention is not limited thereto. In other examples, a TextCNN algorithm, a random forest algorithm, a logistic regression algorithm, etc., or two or more of the above algorithms may also be used. In addition, the specific algorithm used may be determined according to the amount of sampled data and/or traffic demand.

As a specific embodiment, the resource recovery rate in a specific time period from the resource recovery time point is used as the collection urging tag value, and a good sample and a bad sample of the user-associated device are determined to establish a training data set, and the device risk prediction model is trained using the training data set.

For example, in the case of having the influence of the market risk factor, the user-associated device of the sample user whose resource return time point is within 30 days, that is, whose expiration time is 20 days or more and within 30 days, and whose resource recovery rate is higher than 80% is regarded as a bad sample (whereas the user is regarded as a good sample in the case of having no influence of the market risk factor). And the user associated equipment of the sample user with the overdue time less than 20 days and the resource recovery rate higher than 80% is taken as a good sample. And taking whether the overdue time is more than 20 days and less than 30 days and the resource recovery rate is higher than 80% as an acquisition urging tag value to establish a training data set, wherein the training data set comprises historical user associated equipment (the user associated equipment is represented by using the equipment ID) marked with the acquisition urging tag value.

For example, a user-associated device of a sample user who has an expiration time of 30 days or more and a resource recovery rate of more than 85% is taken as a bad sample with the influence of the market risk factor (whereas a user-associated device of the user is taken as a good sample without the influence of the market risk factor). And the user associated equipment of the sample user with the overdue time less than 30 days and the resource recovery rate higher than 85% is taken as a good sample. And establishing a training data set by taking whether the overdue time is more than 30 days and the resource recovery rate is higher than 80% as an acquisition promotion tag value, wherein the training data set comprises historical user associated equipment (the user associated equipment is represented by using the equipment ID) marked with the acquisition promotion tag value.

It should be noted that the Y value (i.e., the value of the hasty tag) of the equipment risk prediction model of the present invention is determined by two parameters, including the expiration time and the resource recovery rate. In the case of no market risk factor influence, a user with a long expiration time and a high recovery rate is a good user (or a good user), that is, the user-associated device of the user is a good sample (or an accepted sample), but in the case of market risk factor influence, a user with a long expiration time and a high recovery rate is a bad user, that is, the user-associated device of the user is a bad sample (or a rejected sample).

Further, for the calculation of the resource promulgation, the internet service resource limit, the resource service time and the resource promulgation time of the historical user are obtained, and the resource promulgation is calculated.

As a specific embodiment, for example, a historical user a applies for a resource allocation service of an internet service resource limit L (for example, thirty thousand yuan) to a resource management platform, the resource service time is 6 months, the number of resource return periods is 6 days, during the resource return period, the historical user a is affected by market risk factors, at the resource return time point of the x-th period (for example, the 3 rd period), an urging policy such as call urging or short message urging is performed on the historical user a, when the protocol-agreed return resource is returned after 20 days (i.e., within 30 days from the resource return time point), the historical user a belongs to a specific user group, and a user-associated device of the historical user a is a bad sample (or a rejected sample).

For training data samples of a training data set in model construction, the method further comprises the following steps: and judging whether the true probability of the rejected sample is consistent with the prediction probability.

Specifically, a relative deviation between a true probability and the output prediction probability is calculated, wherein when the calculated relative deviation is smaller than a set value, the true probability and the prediction probability are judged to be consistent; and when the calculated relative deviation value is larger than or equal to a set value, judging that the real probability is consistent with the prediction probability. Thereby, it is possible to more accurately judge whether or not the true probability and the prediction probability coincide.

It should be noted that the above description is given by way of example only, and is not to be construed as limiting the present invention, and in other embodiments, a difference between the true probability and the output prediction probability may be calculated to determine whether the true probability and the prediction probability coincide with each other. In this example, the set value is determined by a business person according to a statistical value of historical true probabilities. But is not limited thereto and in other examples, the determination may be made in other ways as well.

As an embodiment, after the step of determining whether the true probability and the predicted probability are consistent, it is determined whether a ratio of the number of the predicted probabilities consistent with the true probability to the number of all the training data samples is greater than a preset ratio.

And if so, converging the equipment risk prediction model to obtain the trained equipment risk prediction model.

If not, adjusting model parameters in the equipment risk prediction model, and re-passing the prediction probability of the equipment risk prediction model on the history rejected samples until the ratio of the number of the prediction probability consistent with the real probability to the number of all the training data samples is larger than a preset ratio.

It should be noted that, for the above step of determining whether the ratio of the number of the prediction probabilities consistent with the true probabilities to the number of all the training data samples is greater than a preset ratio value, etc., the machine learning method used for constructing the model may be replaced, and the equipment risk prediction model may be re-established, etc. The foregoing is illustrative only and is not to be construed as limiting the invention.

Therefore, by adjusting the model parameters in the equipment risk prediction model, the model parameters can be optimized, the model authentication precision can be improved, and the construction process of the equipment risk prediction model can be optimized.

In step S103, the trained device risk prediction model is used to perform risk identification on the new access device.

Specifically, device information of the newly accessed device is acquired, for example, the device information is a device ID or a device identification code.

Further, using the equipment risk prediction model, inputting the equipment ID of the new access equipment into the equipment risk prediction model, and calculating (or outputting) the predicted value of the new access equipment.

In one embodiment, the calculated predicted value is compared with a set threshold, and when the calculated predicted value is less than or equal to the set threshold, it is determined that the internet service resource is provided to the new access device.

For example, in the device risk identification process for the resource allocation service or the internet service of the resource support service, when the calculated predicted value is less than or equal to the set threshold, it is determined that the risk of the new access device is small, and it is determined that, for example, the resource allocation service or the resource support service can be provided to the new access device.

In another embodiment, when the calculated predicted value is greater than a set threshold, it is determined not to provide internet service resources to the new access device.

For example, when the calculated predicted value is greater than a set threshold value, it is determined that the risk of the new access apparatus is high, and it is determined that, for example, a resource allocation service or a resource provisioning service cannot be provided to the new access apparatus.

Therefore, by using the equipment risk prediction model to carry out risk identification on the new access equipment, the risk condition of the new access equipment can be accurately quantified, and the prediction precision of the equipment risk prediction model can be improved.

In another example, as shown in fig. 3, the access device authentication method includes a step S301 of determining the number of bad users among users associated with a new access device before calculating a predicted value of the new access device.

Specifically, in step S301, before calculating the predicted value of the new access device, the number of bad users in the users associated with the new access device is determined.

For example, the device information of the new access device and the user characteristic information of the associated user thereof are obtained, and the step of determining the number of the bad users is performed for each associated user of the new access device.

Specifically, for example, the number of associated users of the new access device is determined, for example, one or more.

And when the number of the associated users is judged to be multiple, comparing and inquiring the user characteristic information of the multiple users with the user characteristic information of a blacklist (poor quality user) in a pre-stored user database, judging the users similar to the user characteristic information of the poor quality user in the registered user and the applied resource service user, or judging whether the users are the poor quality users, and determining the number of the poor quality users.

Further, when the number of the poor users accounts for more than 60% of the total number, the new access device is preliminarily judged to be a device with a large risk, risk identification is carried out, and then the predicted value of the new access device is further calculated.

Therefore, the risk equipment can be determined more accurately by performing the step of judging the number of the poor users for the associated users of the new access equipment.

In another example, the access device authentication method includes optimizing model parameters of a device risk prediction model, the model parameters including weight parameters and bias parameters between layers of a deep neural network.

It should be noted that the above description is only given by way of example, and the present invention is not limited thereto. In other examples, the model parameters also include the number of layers of the deep neural network, the number of iterations, and the learning rate.

Specifically, for example, the prior probability of the model parameter is set to comply with the normal distribution, the MCMC method is used to sample the distribution of the weight parameter and the bias parameter for multiple times, so as to obtain a parameter combination set, wherein, when the parameter combination set is used for testing, the input same device ID is subjected to multiple forward propagation, the mean and the statistical variance of each model parameter are calculated, so as to optimize each model parameter, and finally, the parameter-optimized neural network is output. Thus, by optimizing the model parameters of the risk model, the model accuracy can be improved.

The above procedure of the access device authentication method is only for explanation of the present invention, and the order and number of steps are not particularly limited. In addition, the steps in the method can be split into two or three steps, or some steps can be combined into one step, and the steps are adjusted according to practical examples.

Those skilled in the art will appreciate that all or part of the steps to implement the above-described embodiments are implemented as programs (computer programs) executed by a computer data processing apparatus. When the computer program is executed, the method provided by the invention can be realized. Furthermore, the computer program may be stored in a computer readable storage medium, which may be a readable storage medium such as a magnetic disk, an optical disk, a ROM, a RAM, or a storage array composed of a plurality of storage media, such as a magnetic disk or a magnetic tape storage array. The storage medium is not limited to centralized storage, but may be distributed storage, such as cloud storage based on cloud computing.

Compared with the prior art, the method and the device have the advantages that the user screening is carried out through the preset screening rule, the users belonging to the specific user group can be accurately screened, and the user associated equipment corresponding to the users of the specific user group can be accurately determined; and calculating the evaluation index of the specific user group to generate an acceptance urging label for representing the risk size of the user-associated equipment, constructing an equipment risk prediction model based on the acceptance urging label, and calculating the risk of the new access equipment through the equipment risk prediction, so that the risk condition of the new access equipment can be more accurately quantified, and whether the new access equipment is the risk equipment can be effectively identified.

Example 2

Embodiments of the apparatus of the present invention are described below, which may be used to perform method embodiments of the present invention. The details described in the device embodiments of the invention should be regarded as complementary to the above-described method embodiments; reference is made to the above-described method embodiments for details not disclosed in the apparatus embodiments of the invention.

Referring to fig. 4 to 7, the present invention further provides an access device authentication apparatus based on an incoming call ticket, where the access device authentication apparatus 400 includes: a screening module 401, which screens a specific user group according to a predetermined screening rule; a calculating module 402, configured to calculate an evaluation index of the specific user group, generate an acceptance promoting label according to the evaluation index, and construct an equipment risk prediction model based on the acceptance promoting label; and a prediction module 403, configured to perform risk identification on the new access device by using the trained device risk prediction model.

In an embodiment, as shown in fig. 5, the apparatus further includes a configuration module 501, the screening module 401 is split into the configuration module 501 and the screening module 401, and the configuration module 501 is configured to pre-configure a predetermined screening rule.

Specifically, the predetermined screening rule includes a configuration time parameter and a resource recovery rate threshold, where the time parameter is within a specific time from the resource return time; and screening out users which return the resources within a specific time from the resource returning time and are greater than the threshold value of the resource recovery rate, wherein the users belong to the specific user group, and the specific user group is used for representing the specific group with the increased resource returning risk under the influence of the market risk factors.

More specifically, the time parameter is within a specific time from the resource return time. For example, within 20 days from the time of return of the resource. For example, the specific time is 7 days to 30 days, such as 7 days, 15 days, 20 days, or 30 days, and the like.

Specifically, as for the evaluation index, calculation may be performed according to the following two alternative embodiments.

In another embodiment, as shown in fig. 6, the access device identification apparatus 400 further includes a data obtaining module 601, where the data obtaining module 601 is configured to obtain an internet service resource amount, a resource service time, and a resource urging time of a historical user, and calculate the resource urging amount.

Specifically, the risk identification of the new access device by using the trained device risk prediction model includes: calculating a predicted value of the new access device by using the device risk prediction model; the calculated predicted value is compared with a set threshold.

In one embodiment, when the calculated predicted value is less than or equal to a set threshold, it is determined that the internet service resource is provided to the new access device.

In another embodiment, the access device authentication apparatus 400 further includes a determining module 701, where the determining module 701 is configured to determine the number of bad users in the users associated with the new access device before calculating the predicted value of the new access device.

For example, the device information of the new access device and the user feature information of the associated user thereof are obtained, and the determining module 701 performs the step of determining the number of the bad users for each associated user of the new access device.

For example, the determining module 701 first determines the number of associated users of the new access device, for example, one or more.

Therefore, the risk equipment can be determined more accurately by executing the judgment process of the number of the poor users for the associated users of the new access equipment.

In embodiment 2, the same portions as those in embodiment 1 are not described.

Those skilled in the art will appreciate that the modules in the above-described embodiments of the apparatus may be distributed as described in the apparatus, and may be correspondingly modified and distributed in one or more apparatuses other than the above-described embodiments. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.

Example 3

The following describes an embodiment of the computer apparatus of the present invention, which may be considered as a concrete physical implementation of the above-described embodiments of the method and system of the present invention. Details described in relation to the computer device embodiment of the present invention should be considered supplementary to the method or system embodiment described above; for details not disclosed in the computer device embodiments of the invention, reference may be made to the above-described method or system embodiments.

Fig. 8 is a block diagram of an exemplary embodiment of a computer device according to the present invention. A computer apparatus 200 according to this embodiment of the present invention is described below with reference to fig. 8. The computer device 200 shown in fig. 8 is only an example and should not bring any limitation to the function and the scope of use of the embodiments of the present invention.

As shown in FIG. 8, computer device 200 is in the form of a general purpose computing device. The components of computer device 200 may include, but are not limited to: at least one processing unit 210, at least one storage unit 220, a bus 230 connecting different device components (including the storage unit 220 and the processing unit 210), a display unit 240, and the like.

Wherein the storage unit stores program code executable by the processing unit 210 to cause the processing unit 210 to perform steps according to various exemplary embodiments of the present invention described in the processing method section of the above-mentioned computer apparatus of the present specification. For example, the processing unit 210 may perform the steps as shown in fig. 1.

The memory unit 220 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)2201 and/or a cache memory unit 2202, and may further include a read only memory unit (ROM) 2203.

The storage unit 220 may also include a program/utility 2204 having a set (at least one) of program modules 2205, such program modules 2205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 230 may be one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The computer device 200 may also communicate with one or more external devices 300 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the computer device 200, and/or with any devices (e.g., router, modem, etc.) that enable the computer device 200 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 250. Also, computer device 200 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) through network adapter 260. Network adapter 260 may communicate with other modules of computer device 200 via bus 230. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the computer device 200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments of the present invention described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to make a computing device (which can be a personal computer, a server, or a network device, etc.) execute the above-mentioned method according to the present invention. Which when executed by a data processing device, enables the computer program product to carry out the above-mentioned method of the invention.

As shown in fig. 9, the computer program may be stored on one or more computer program products. The computer program product may be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer program product include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The computer program product may comprise a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer program product may be transmitted, propagated, or transported for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on the computer program product may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

In summary, the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functionality of some or all of the components in embodiments in accordance with the invention may be implemented in practice using a general purpose data processing device such as a microprocessor or a Digital Signal Processor (DSP). The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such a program implementing the invention may be stored on a computer program product or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.

While the foregoing embodiments have described the objects, aspects and advantages of the present invention in further detail, it should be understood that the present invention is not inherently related to any particular computer, virtual machine or electronic device, and various general-purpose machines may be used to implement the present invention. The invention is not to be considered as limited to the specific embodiments thereof, but is to be understood as being modified in all respects, all changes and equivalents that come within the spirit and scope of the invention.

Claims

1. An access device authentication method based on a procuring label is characterized by comprising the following steps:

screening a specific user group according to a preset screening rule;

calculating an evaluation index of the specific user group, generating an acceptance promoting label according to the evaluation index, and constructing an equipment risk prediction model based on the acceptance promoting label;

and carrying out risk identification on the new access equipment by using the trained equipment risk prediction model.

2. The method according to claim 1, wherein the calculating an evaluation index of the specific user group and the generating the incoming call label according to the evaluation index comprises:

and using the resource recovery rate in a specific time period from the resource recovery time point as an acceptance urging label value, and determining a good sample and a bad sample to establish a training data set.

3. The access device authentication method based on procuring label as claimed in claim 2, comprising:

calculating an evaluation index by the following formula, wherein the evaluation index is the resource recovery rate:

4. The access device authentication method based on procuring label as claimed in claim 2, comprising:

5. The access device authentication method based on procuring label according to any one of claims 3 or 4, comprising:

the method comprises the steps of obtaining internet service resource limit, resource service time and resource urging time of a historical user, and calculating the resource urging amount.

6. The method for authenticating an access device according to claim 5, wherein the screening a specific user group according to a predetermined screening rule comprises:

the preset screening rule comprises a configuration time parameter and a resource recovery rate threshold value, wherein the time parameter is within a specific time from the resource returning time;

and screening out users which return the resources within a specific time from the resource returning time and are greater than the threshold value of the resource recovery rate, wherein the users belong to the specific user group, and the specific user group is used for representing the specific group with the increased resource returning risk under the influence of the market risk factors.

7. The method for authenticating an access device based on an hasten tag of claim 6, wherein the risk authentication of the new access device using the trained device risk prediction model comprises:

calculating a predicted value of the new access device by using the device risk prediction model;

comparing the calculated predicted value with a set threshold value, and determining to provide internet service resources for the new access equipment when the calculated predicted value is less than or equal to the set threshold value;

and when the calculated predicted value is larger than a set threshold value, determining not to provide the internet service resources for the new access equipment.

8. An access device authentication apparatus based on a procuring label, comprising:

the screening module screens a specific user group according to a preset screening rule;

the calculation module is used for calculating the evaluation index of the specific user group, generating an acceptance promoting label according to the evaluation index and constructing an equipment risk prediction model based on the acceptance promoting label;

and the prediction module is used for carrying out risk identification on the new access equipment by using the trained equipment risk prediction model.

9. A computer device comprising a processor and a memory for storing a computer executable program, which when executed by the processor performs the method of claim 1-7.

10. A computer program product storing a computer executable program which, when executed, implements a hasty tag-based access device authentication method as claimed in any one of claims 1-7.