Business handling authentication method and device
By classifying and weighting the user target behavior data and flexibly selecting appropriate authentication methods combinations, the problem that authentication methods cannot be flexibly adjusted in the existing technology is solved, the efficiency and success rate of business authentication is improved, and the user experience is improved.
Patent Information
- Application Number
- CN202411495233.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-24
- Publication Date
- 2025-02-11
AI Technical Summary
At this stage, the authentication method of customer service system for business processing cannot be flexibly adjusted based on the various business indicators involved in the user's business processing, resulting in a decrease in the efficiency and success rate of business processing certification, affecting the user experience.
By classifying user target behavior data based on multiple classification indicators, multiple classification data are obtained, and the top-ranked multiple target authentication methods combinations are filtered from the authentication method combinations corresponding to multiple classification data based on the weights of each classification indicator. , perform user business certification.
It realizes flexible selection of authentication methods based on multiple business indicators of users, improves the efficiency and success rate of business certification, and thus improves the overall efficiency and success rate of business processing, and improves the user experience.
Smart Images
Figure CN119417405A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of authentication technology, and in particular to a business handling authentication method and device. Background Art
[0002] Against the backdrop of rapid social, economic and financial technology development, customer service systems involve an increasing number of businesses, including some sensitive businesses. Therefore, it is often necessary to authenticate users for business operations in order to ensure the security and compliance of business operations handled by online customer service systems.
[0003] At present, the authentication method for handling business in the customer service system is mainly to configure different authentication methods according to the different sensitivity levels of the business. However, this method will display the same set of authentication methods for businesses with the same sensitivity level when the customer service handles the business. It is impossible to flexibly adjust the authentication method according to the various business indicators including the sensitivity level involved in the current user's business handling, resulting in a decrease in the efficiency and success rate of business handling authentication, which in turn leads to a decrease in the overall efficiency and success rate of business handling, affecting the user experience. Summary of the invention
[0004] The embodiments of the present application provide a business processing authentication method and device to solve the technical problem that the current authentication method for business processing in the customer service system cannot flexibly adjust the authentication method according to various business indicators including sensitivity levels involved in the current user's business processing, resulting in reduced efficiency and success rate of business processing authentication, and further reduced overall efficiency and success rate of business processing, affecting user experience.
[0005] In a first aspect, an embodiment of the present application provides a service handling authentication method, including: Classify the user target behavior data based on multiple classification indicators to obtain multiple classification data; Based on the weight of each classification indicator when selecting the authentication method combination, a plurality of target authentication method combinations ranked top under the plurality of classification indicator combinations are screened out from the authentication method combinations corresponding to the plurality of classification data; The user's business processing authentication is performed based on the combination of the multiple target authentication methods.
[0006] In one embodiment, the top ranking combinations of multiple target authentication methods under any classification indicator combination are determined based on the following method: Based on the weight of each classification indicator when selecting the authentication method combination, calculating the score of the authentication method combination corresponding to the multiple classification data under the classification indicator combination; The authentication method combinations with higher scores are determined as the multiple target authentication method combinations that are ranked higher under the classification indicator combination.
[0007] In one embodiment, the multiple classification indicators include business characteristics, call scenarios, authority levels, age distribution, city of origin, and sensitivity level; The user target behavior data includes target business feature data, target call scenario data, target authority level data, target age distribution data, target city data and target sensitivity level data.
[0008] In one embodiment, performing a user's service handling authentication based on the combination of the multiple target authentication methods includes: Based on the target service feature data and the target sensitivity level data of the current user, screening out a plurality of matching authentication method combinations from the plurality of target authentication method combinations; Based on the weight of each classification indicator when selecting the authentication method combination and the scores of the multiple matching authentication method combinations on each classification indicator, obtaining multiple comprehensive scores corresponding to the multiple matching authentication method combinations; Determine the matching authentication method combination corresponding to the highest comprehensive score among the multiple comprehensive scores as the optimal authentication method combination; The business handling authentication of the current user is performed based on the optimal authentication method combination.
[0009] In one embodiment, after authenticating the current user's service based on the optimal authentication method combination, the following steps are included: When the result of the business handling authentication is passed, the weight of the optimal authentication method combination is saved in a weight calculator; When the current user performs a service again, returning to the step of screening out multiple matching authentication method combinations from the multiple target authentication method combinations based on the target service feature data and the target sensitivity level data of the current user, until the weight of the optimal authentication method combination is saved to the weight calculator again; Calculating the weight sum of the optimal authentication method combination corresponding to the current user in the weight calculator; When the sum of the weights reaches a weight threshold, it is determined that the current user meets the sensitive service handling conditions.
[0010] In one embodiment, the user target behavior data is determined based on the following method: Collecting behavior data of multiple users corresponding to the multiple classification indicators; The behavior data is preprocessed to obtain the user target behavior data; the preprocessing includes data cleaning, data conversion and data standardization.
[0011] In a second aspect, an embodiment of the present application provides a service handling authentication device, including: A classification module is used to classify user target behavior data based on multiple classification indicators to obtain multiple classification data; The authentication method combination screening module is used to: based on the weight of each classification index when selecting the authentication method combination, screen out multiple target authentication method combinations with top rankings under multiple classification index combinations from the authentication method combinations corresponding to the multiple classification data; The business processing authentication module is used to: perform business processing authentication of the user based on the combination of the multiple target authentication methods.
[0012] In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory storing a computer program, wherein when the processor executes the program, the steps of the business processing authentication method described in the first aspect are implemented.
[0013] In a fourth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the business processing authentication method described in the first aspect.
[0014] In a fifth aspect, an embodiment of the present application provides a non-transitory computer-readable storage medium, including a computer program, which, when executed by a processor, implements the steps of the business processing authentication method described in the first aspect.
[0015] The business handling authentication method and device provided by the present application classifies user target behavior data based on multiple classification indicators to obtain multiple classification data, and based on the weight of each classification indicator when selecting the authentication method combination, multiple target authentication method combinations with top rankings under multiple classification indicator combinations are screened out from the authentication method combinations corresponding to the multiple classification data, and the user's business handling authentication is performed based on the multiple target authentication method combinations. The present application classifies user target behavior data based on multiple classification indicators, and can maximize the similarity of user target behavior data in each classification data on multiple classification indicators, so as to quickly and accurately obtain the authentication method combination corresponding to each classification data, and then based on the weight of each classification indicator when selecting the authentication method combination, multiple target authentication method combinations with top rankings under multiple classification indicator combinations are screened out from the authentication method combinations corresponding to each classification data, that is, multiple target authentication method combinations corresponding to important classification indicator combinations are screened out, and the user's business handling authentication is performed based on multiple target authentication method combinations, so as to realize the user's flexible selection and adjustment of the authentication method based on multiple business indicators and their importance, improve the efficiency and success rate of business handling authentication, and then improve the overall efficiency and success rate of business handling, and effectively improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0017] Figure 1 This is one of the flowcharts of the business handling authentication method provided in the embodiment of the present application; Figure 2 This is the second flow chart of the business handling authentication method provided in the embodiment of the present application; Figure 3 This is the third flow chart of the business handling authentication method provided in the embodiment of the present application; Figure 4 This is a schematic diagram of a diversified multi-factor authentication MFA model of a business handling authentication method provided in an embodiment of the present application; Figure 5 This is the fourth flow chart of the business handling authentication method provided in the embodiment of the present application; Figure 6 It is a structural diagram of a business handling authentication device provided in an embodiment of the present application; Figure 7 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0018] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0019] Figure 1 This is one of the flow charts of the business handling authentication method provided in the embodiment of the present application. Figure 1 , the present application embodiment provides a service handling authentication method, which may include: 101. Classify the user target behavior data based on multiple classification indicators to obtain multiple classification data; 102. Based on the weight of each classification indicator when selecting the authentication method combination, select multiple target authentication method combinations that are ranked top under multiple classification indicator combinations from the authentication method combinations corresponding to the multiple classification data; 103. Perform user business authentication based on a combination of multiple target authentication methods.
[0020] In step 101, the multiple classification indicators may be multiple business indicators involved in the user's business handling, and the user target behavior data is the user behavior data corresponding to these business indicators. Any clustering method may be used to classify the user target behavior data, which is not limited here. In this embodiment, the specific clustering method may be as follows: A preset number of users are randomly selected from multiple users as cluster center users, and user target behavior data of multiple users are clustered based on the user target behavior data of the cluster center users to obtain multiple cluster clusters, and the intra-cluster sum of squares of the multiple cluster clusters is calculated. If the intra-cluster sum of squares does not reach a minimum value, the step of randomly selecting a preset number of users from multiple users as cluster center users is returned until the intra-cluster sum of squares reaches a minimum value, and multiple target cluster clusters are obtained, for example: Assumptions to Respectively represent the user target behavior data of the first user to the user target behavior data of the nth user, to They represent the user target behavior data of the user at the 1st cluster center to the user target behavior data of the user at the kth cluster center, that is, there are k clusters in total, and the calculation formula of the intra-cluster sum of squares WCSS can be as follows: ; in, For the The user target behavior data set of all users in the clusters, for The User goal behavior data of each user, for The user target behavior data of the cluster center user can be adjusted continuously to change the value of WCSS, and finally the value of WCSS is minimized. At this time, the k clusters are the k target clusters, that is, k classification data.
[0021] In step 102 to step 103, the authentication method combination can be a combination of at least one of account and password authentication, SMS authentication, face authentication, and protocol authentication, and there is no need to limit the authentication order of each authentication in each authentication method combination.
[0022] In addition, the weight of each classification indicator when selecting the authentication method combination can reflect the importance of each classification indicator to the selection of the authentication method combination, and the weight can be determined based on expert evaluation, historical data analysis or consultation with business stakeholders.
[0023] In the traditional authentication method, user information is verified in the order of account and password authentication, SMS authentication, face authentication, and protocol authentication. This strongly associated authentication step can indeed provide higher security, but it may also lead to a decline in user experience, because each authentication step requires users to invest extra time and thinking. In addition, each of the above authentication steps is necessary, and the appropriate authentication method will not be intelligently recommended based on the various business indicators involved in the user's business handling, which may result in a waste of authentication resources. As the time of the authentication link is lost, the efficiency of business handling will also decrease. For example: the camera of a middle-aged or elderly user is damaged, making it impossible to perform face authentication, which results in the inability to handle business.
[0024] The method of this embodiment can remove the strong correlation between the number and order of authentication steps in the traditional authentication method, and obtain multiple target authentication method combinations under multiple classification indicator combinations from a large number of authentication method combinations according to the weight of each classification indicator when selecting the authentication method combination, so as to provide users with a variety of target authentication method combinations for selection, improve the efficiency and success rate of business handling, reduce the waste of authentication resources, and improve user satisfaction.
[0025] The business handling authentication method provided in this embodiment classifies user target behavior data based on multiple classification indicators to obtain multiple classification data, and based on the weight of each classification indicator when selecting the authentication method combination, multiple target authentication method combinations with top rankings under multiple classification indicator combinations are screened out from the authentication method combinations corresponding to the multiple classification data, and the user's business handling authentication is performed based on the multiple target authentication method combinations. This embodiment classifies user target behavior data based on multiple classification indicators, which can maximize the similarity of user target behavior data in each classification data on multiple classification indicators, thereby quickly and accurately obtaining the authentication method combination corresponding to each classification data, and then based on the weight of each classification indicator when selecting the authentication method combination, multiple target authentication method combinations with top rankings under multiple classification indicator combinations are screened out from the authentication method combinations corresponding to each classification data, that is, multiple target authentication method combinations corresponding to important classification indicator combinations are screened out, and the user's business handling authentication is performed based on the multiple target authentication method combinations, so that the user can flexibly select and adjust the authentication method based on multiple business indicators and their importance, improve the efficiency and success rate of business handling authentication, and then improve the overall efficiency and success rate of business handling, and effectively improve user experience.
[0026] In one embodiment, the top multiple target authentication method combinations under any classification index combination may be determined based on the following method: Based on the weight of each classification indicator when selecting an authentication method combination, the scores of the authentication method combinations corresponding to the multiple classification data under the classification indicator combination are calculated, and the authentication method combinations with higher scores are determined as the multiple target authentication method combinations that are ranked top under the classification indicator combination.
[0027] Assuming that there are classification indicators A, B, and C, and A+B is used as a classification indicator combination, the scores of the authentication method combinations corresponding to each classification data under A+B are calculated based on the weights of A and B when selecting the authentication method combination, and the zset data structure is used to obtain the 5 authentication method combinations with the highest scores as the multiple target authentication method combinations under A+B; the same can be said for the multiple target authentication method combinations under the classification indicator combinations B+C, A+C or A+B+C, which will not be repeated here.
[0028] Among them, each target authentication method combination can be expressed in the form of key-value-score, where key represents the classification indicator combination value. Taking the classification indicator combination A+B as an example, its classification indicator combination value can be expressed as AB, where "-" represents connection; value represents the name of the target authentication method combination; score represents the number of times the target authentication method combination has been selected and used by the customer service in history.
[0029] In addition, a weight may be assigned to each target authentication method combination, and each target authentication method combination may be stored in a database as a key-value-score, and the corresponding weight may also be stored in the database.
[0030] This embodiment calculates the score of the authentication method combination corresponding to each classification data under any classification indicator combination by using the weight of each classification indicator when selecting the authentication method combination. The score can be used to accurately measure the importance of the classification indicator combination to the selection of the authentication method combination, thereby conveniently and quickly screening out the target authentication method combination corresponding to the important classification indicator combination.
[0031] In one embodiment, the multiple classification indicators include business characteristics, call scenarios, authority levels, age distribution, city of origin, and sensitivity level; User target behavior data includes target business feature data, target call scenario data, target authority level data, target age distribution data, target city data and target sensitivity level data.
[0032] It should be noted that the user target behavior data also includes user target authentication method combination data, so as to obtain the authentication method combination corresponding to each classification data after classification.
[0033] In addition, classification indicators and user target behavior data can be increased or decreased according to actual needs, which is not limited here.
[0034] This embodiment sets multiple classification indicators as business characteristics, call scenarios, authority levels, age distribution, city of origin and sensitivity level, and the user target behavior data corresponds to each classification indicator. It can analyze the user target behavior data based on multiple business indicators that are closely related to the authentication method combination involved in user business processing, and provide a basis for providing multiple authentication method selections under the consideration of multiple business indicators.
[0035] Figure 2 This is the second flow chart of the business handling authentication method provided in the embodiment of the present application. Figure 2 In one embodiment, the user's service handling authentication based on a combination of multiple target authentication methods may include: 201. Based on the target business feature data and target sensitivity level data of the current user, select multiple matching authentication method combinations from multiple target authentication method combinations; 202. Based on the weight of each classification indicator when selecting the authentication method combination and the scores of the multiple matching authentication method combinations on each classification indicator, obtain multiple comprehensive scores corresponding to the multiple matching authentication method combinations; 203. Determine the matching authentication method combination corresponding to the highest comprehensive score among the multiple comprehensive scores as the optimal authentication method combination; 204. Perform business authentication for the current user based on the optimal authentication method combination.
[0036] In step 201, the target business feature data and target sensitivity level data of the current user can be traversed and compared with the target business feature data and target sensitivity level data of the users corresponding to each target authentication method combination, and an I / O model can be established to screen out multiple users who are consistent with the target business feature data and target sensitivity level data of the current user, and the target authentication method combinations of these users can be determined as multiple matching authentication method combinations for the current user.
[0037] In step 202 to step 203, the first of the multiple matching authentication method combinations Matching authentication method combinations The corresponding comprehensive score It can be expressed by the following formula: ; in, For each classification indicator The weight of each classification indicator when selecting a combination of authentication methods. for In the The scores on the classification indicators are is the number of classification indicators.
[0038] Since the scores of multiple matching authentication method combinations on the same classification indicator are different, this will lead to differences in the comprehensive scores of each matching authentication method combination. Based on this difference, the matching authentication method combination corresponding to the highest comprehensive score can be determined as the optimal authentication method combination for the current user.
[0039] This embodiment first uses the target business feature data and target sensitivity level data of the current user as screening conditions, and accurately screens out multiple matching authentication method combinations that are highly compatible with the current user from multiple target authentication method combinations, and then obtains a comprehensive score for the matching authentication method combination based on the weighted sum of the scores of the matching authentication method combination on each classification indicator, thereby expanding the importance of the classification indicator combination to the importance of each classification indicator, and screening out the optimal authentication method combination with the most balanced importance of each classification indicator.
[0040] Figure 3 This is the third flow chart of the business handling authentication method provided in the embodiment of the present application. Figure 3 In one embodiment, after the service handling authentication of the current user is performed based on the optimal authentication mode combination, the following may be included: 301. When the result of the business handling authentication is passed, the weight of the optimal authentication method combination is saved in the weight calculator; 302. When the current user performs a business again, return to the step of selecting multiple matching authentication method combinations from multiple target authentication method combinations based on the target business feature data and target sensitivity level data of the current user, until the weight of the optimal authentication method combination is saved to the weight calculator again; 303. Calculate the weight sum of the optimal authentication method combination corresponding to the current user in the weight calculator; 304. When the weight sum reaches the weight threshold, it is determined that the current user meets the sensitive business processing conditions.
[0041] In step 301, if the service handling authentication of the current user is passed based on the optimal authentication method combination, the weight of the optimal authentication method combination among the weights of multiple target authentication method combinations previously saved in the database is taken out and saved again in the weight calculator.
[0042] In step 302, since the current user may handle the same or different services multiple times, the user target behavior data may change each time the user handles a service. Therefore, each time the user handles a service, it is necessary to re-compare the user target behavior data of the user corresponding to the target authentication method combination, screen out the matching authentication method combination and the optimal authentication method combination of the current user each time the user handles a service, and then authenticate based on the optimal authentication method combination. If it passes, the weight of the optimal authentication method combination is saved in the weight calculator. Therefore, the number of times the current user handles services corresponds to the number of optimal authentication method combinations obtained, and the number of corresponding weights saved in the weight calculator corresponds to the number of optimal authentication method combinations that pass the authentication.
[0043] In step 303, the weights of all the optimal authentication method combinations that have passed authentication for the current user are added up to obtain a weighted sum.
[0044] In step 304, if the weight sum is greater than the weight threshold, it means that the optimal authentication method combination for the current user to handle multiple services has been fully authenticated, and the current user can subsequently handle sensitive services based on the obtained optimal authentication method.
[0045] This embodiment authenticates the optimal authentication method combination obtained by the current user each time, and saves and sums the weights of the optimal authentication method combination that has passed the authentication. When the sum of the weights reaches the weight threshold, it means that the authentication of the optimal authentication method combination for the current user has reached a higher authentication standard, thereby determining that the current user can handle sensitive business based on the optimal authentication method combination, thereby ensuring the security and compliance of sensitive business handling.
[0046] In one embodiment, user target behavior data may be determined based on the following method: Collecting behavior data corresponding to multiple users and multiple classification indicators, preprocessing the behavior data, and obtaining user target behavior data; Preprocessing includes data cleaning, data conversion, and data standardization; The behavioral data corresponding to the various classification indicators include business feature data, call scenario data, authority level data, age distribution data, city data and sensitivity level data. In addition, it also includes authentication method combination data. These data can be based on the voice or video conversation established between the customer service and the user. Through the establishment of a channel and with the user's authorization, they can be collected and saved to the big data analysis platform.
[0047] Among them, the business characteristics in the multiple classification indicators include business type, transaction amount, etc., call scenarios include call status, call duration, etc., authority level includes user's authority level in the system, etc., and sensitivity level includes the sensitivity of business operations, such as low sensitivity level, medium sensitivity level and high sensitivity level.
[0048] Furthermore, the preprocessing process can be as follows: Data cleaning: Use the isnull() or isna() function in the Pandas library to identify missing values in business feature data, call scenario data, permission level data, age distribution data, city data, sensitivity level data, and authentication method combination data, and directly delete user data with missing values. That is, if the behavior data corresponding to any classification indicator of a user contains missing values, all behavior data of the user will be directly deleted; Data conversion: After data cleaning, each line of data is converted into a format suitable for analysis. Encode categorical data into numerical data through one-hot encoding and label encoding. In addition, it is necessary to ensure the correctness of all data types, such as converting a string in date format into a date type; Data standardization: In order to make the numerical data of different magnitudes at the same magnitude after data conversion, so as to facilitate subsequent processing, the data can be scaled to the interval [0, 1] through minimum and maximum standardization, and then the scaled data can be converted into a distribution with a mean of 0 and a standard deviation of 1 through Z-score standardization.
[0049] This embodiment collects a variety of important business indicator data involved in user business processing and pre-processes them to form user target behavior data, which can make the user target behavior data highly complete and in a unified format, effectively improving the efficiency of subsequent data processing.
[0050] Figure 4 This is a schematic diagram of a diversified multi-factor authentication MFA model for a business handling authentication method provided in an embodiment of the present application. Figure 4 ,In one embodiment, the diversified MFA model includes a big data analysis platform, a data processing module, and a MySql database; The model collects behavioral data corresponding to multiple users and multiple classification indicators from the big data analysis platform and transmits them to the data processing module. The data processing module performs data cleaning, data conversion and data standardization on these data in turn to obtain user target behavior data, and performs cluster analysis on the user target behavior data to obtain clustering results. In the clustering results, the top 5 authentication method combinations are screened out as target authentication method combinations, and weights are assigned to these target authentication method combinations. These target authentication method combinations and their weights are stored in the MySql database.
[0051] Figure 5 This is the fourth flow chart of the business handling authentication method provided in the embodiment of the present application. Figure 5 In one embodiment, the process of the current user handling sensitive services can be described as follows: 501. Based on the voice conversation or video conversation established between the current user and the customer service, the behavior data of the current user corresponding to multiple classification indicators are collected through the establishment of a channel and with the authorization of the user, and the behavior data are pre-processed to form the user target behavior data of the current user; 502. Based on the user target behavior data of the current user, a plurality of matching authentication method combinations that match the current user are obtained through the I / O model, and a comprehensive score of each matching authentication method combination is obtained based on the weights of the plurality of classification indicators and the scores of the matching authentication method combination on the plurality of classification indicators, and the comprehensive scores are sorted and displayed; 503. Start the weight calculator, dynamically monitor the weight change of the optimal authentication method combination, and respond according to the weight sum of the optimal authentication method combination; 504. Authenticate the optimal authentication method combination, obtain the weight of the optimal authentication method combination after the authentication is passed, and save the optimal authentication method combination and its weight in the form of a key-value pair; 505. The weight calculator continuously obtains the weights of the optimal authentication method combination that passes the authentication and adds them up. When the weight sum is less than the preset weight threshold, sensitive business cannot be processed. When the weight sum is greater than or equal to the preset weight threshold, sensitive business can be processed.
[0052] The following is a description of a business processing authentication device provided in an embodiment of the present application. The business processing authentication device described below and the business processing authentication method described above can be referenced to each other.
[0053] Figure 6 Schematic diagram of the structure of the business handling authentication device provided in the embodiment of the present application. Figure 6 The embodiment of the present application provides a service handling authentication device, which may include: The classification module 601 is used to classify the user target behavior data based on multiple classification indicators to obtain multiple classification data; The authentication method combination screening module 602 is used to: based on the weight of each classification index when selecting the authentication method combination, screen out multiple target authentication method combinations with top rankings under multiple classification index combinations from the authentication method combinations corresponding to the multiple classification data; The business processing authentication module 603 is used to: perform business processing authentication of the user based on the combination of the multiple target authentication methods.
[0054] The service handling authentication device provided in this embodiment classifies the user target behavior data based on multiple classification indicators to obtain multiple classification data, and based on the weight of each classification indicator when selecting the authentication method combination, selects multiple target authentication method combinations with top rankings under multiple classification indicator combinations from the authentication method combinations corresponding to the multiple classification data, and performs the user's service handling authentication based on the multiple target authentication method combinations. This embodiment classifies the user target behavior data based on multiple classification indicators, which can maximize the similarity of the user target behavior data in each classification data on multiple classification indicators, thereby quickly and accurately obtaining the authentication method combination corresponding to each classification data, and then based on the weight of each classification indicator when selecting the authentication method combination, selects multiple target authentication method combinations with top rankings under multiple classification indicator combinations from the authentication method combinations corresponding to each classification data, that is, selects multiple target authentication method combinations corresponding to important classification indicator combinations, and performs the user's service handling authentication based on multiple target authentication method combinations, so as to realize the user's flexible selection and adjustment of the authentication method based on multiple business indicators and their importance, improve the efficiency and success rate of the service handling authentication, and then improve the overall efficiency and success rate of the service handling, and effectively improve the user experience.
[0055] In one embodiment, the authentication mode combination screening module 602 is specifically used to: Based on the weight of each classification indicator when selecting the authentication method combination, calculating the score of the authentication method combination corresponding to the multiple classification data under the classification indicator combination; The authentication method combinations with higher scores are determined as the multiple target authentication method combinations that are ranked higher under the classification indicator combination.
[0056] In one embodiment, the multiple classification indicators include business characteristics, call scenarios, authority levels, age distribution, city of origin, and sensitivity level; The user target behavior data includes target business feature data, target call scenario data, target authority level data, target age distribution data, target city data and target sensitivity level data.
[0057] In one embodiment, the business handling authentication module 603 is specifically used to: Based on the target service feature data and the target sensitivity level data of the current user, screening out a plurality of matching authentication method combinations from the plurality of target authentication method combinations; Based on the weight of each classification indicator when selecting the authentication method combination and the scores of the multiple matching authentication method combinations on each classification indicator, obtaining multiple comprehensive scores corresponding to the multiple matching authentication method combinations; Determine the matching authentication method combination corresponding to the highest comprehensive score among the multiple comprehensive scores as the optimal authentication method combination; The business handling authentication of the current user is performed based on the optimal authentication method combination.
[0058] In one embodiment, a sensitive business handling module (not shown in the figure) is further included, which is used to: When the result of the business handling authentication is passed, the weight of the optimal authentication method combination is saved in a weight calculator; When the current user performs a service again, returning to the step of screening out multiple matching authentication method combinations from the multiple target authentication method combinations based on the target service feature data and the target sensitivity level data of the current user, until the weight of the optimal authentication method combination is saved to the weight calculator again; Calculating the weight sum of the optimal authentication method combination corresponding to the current user in the weight calculator; When the sum of the weights reaches a weight threshold, it is determined that the current user meets the sensitive service handling conditions.
[0059] In one embodiment, the user target behavior data is determined based on the following method: Collecting behavior data of multiple users corresponding to the multiple classification indicators; The behavior data is preprocessed to obtain the user target behavior data; the preprocessing includes data cleaning, data conversion and data standardization.
[0060] FIG. 7 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 7 As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730 and a communication bus 740, wherein the processor 710, the communication interface 720 and the memory 730 communicate with each other through the communication bus 740. The processor 710 may call a computer program in the memory 730 to execute the steps of the service handling authentication method, for example including: Classify the user target behavior data based on multiple classification indicators to obtain multiple classification data; Based on the weight of each classification indicator when selecting the authentication method combination, a plurality of target authentication method combinations ranked top under the plurality of classification indicator combinations are screened out from the authentication method combinations corresponding to the plurality of classification data; The user's business processing authentication is performed based on the combination of the multiple target authentication methods.
[0061] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0062] On the other hand, an embodiment of the present application further provides a computer program product, the computer program product including a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer can perform the steps of the business handling authentication method provided in the above embodiments, for example, including: Classify the user target behavior data based on multiple classification indicators to obtain multiple classification data; Based on the weight of each classification indicator when selecting the authentication method combination, a plurality of target authentication method combinations ranked top under the plurality of classification indicator combinations are screened out from the authentication method combinations corresponding to the plurality of classification data; The user's business processing authentication is performed based on the combination of the multiple target authentication methods.
[0063] On the other hand, an embodiment of the present application further provides a non-transitory computer-readable storage medium on which a computer program is stored, and the computer program is used to enable a processor to execute the steps of the business handling authentication method provided in the above embodiments, for example, including: Classify the user target behavior data based on multiple classification indicators to obtain multiple classification data; Based on the weight of each classification indicator when selecting the authentication method combination, a plurality of target authentication method combinations ranked top under the plurality of classification indicator combinations are screened out from the authentication method combinations corresponding to the plurality of classification data; The user's business processing authentication is performed based on the combination of the multiple target authentication methods.
[0064] The non-transitory computer-readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)), etc.
[0065] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0066] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0067] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A business handling authentication method, characterized in that: include: Classify the user target behavior data based on multiple classification indicators to obtain multiple classification data; Based on the weight of each classification indicator when selecting the authentication method combination, a plurality of target authentication method combinations ranked top under the plurality of classification indicator combinations are screened out from the authentication method combinations corresponding to the plurality of classification data; The user's business processing authentication is performed based on the combination of the multiple target authentication methods.
2. The business handling authentication method according to claim 1, characterized in that: The top ranking combinations of multiple target authentication methods under any classification indicator combination are determined based on the following methods: Based on the weight of each classification indicator when selecting the authentication method combination, calculating the score of the authentication method combination corresponding to the multiple classification data under the classification indicator combination; The authentication method combinations with higher scores are determined as the multiple target authentication method combinations that are ranked higher under the classification indicator combination.
3. The business handling authentication method according to claim 1, characterized in that: The multiple classification indicators include business characteristics, call scenarios, authority levels, age distribution, city of origin, and sensitivity level; The user target behavior data includes target business feature data, target call scenario data, target authority level data, target age distribution data, target city data and target sensitivity level data.
4. The business handling authentication method according to claim 3, characterized in that: Performing user service authentication based on the combination of the multiple target authentication methods includes: Based on the target service feature data and the target sensitivity level data of the current user, screening out a plurality of matching authentication method combinations from the plurality of target authentication method combinations; Based on the weight of each classification indicator when selecting the authentication method combination and the scores of the multiple matching authentication method combinations on each classification indicator, obtaining multiple comprehensive scores corresponding to the multiple matching authentication method combinations; Determine the matching authentication method combination corresponding to the highest comprehensive score among the multiple comprehensive scores as the optimal authentication method combination; The business handling authentication of the current user is performed based on the optimal authentication method combination.
5. The business handling authentication method according to claim 4, characterized in that: After the service handling authentication of the current user is performed based on the optimal authentication method combination, the method includes: When the result of the business handling authentication is passed, the weight of the optimal authentication method combination is saved in a weight calculator; When the current user performs a service again, returning to the step of screening out multiple matching authentication method combinations from the multiple target authentication method combinations based on the target service feature data and the target sensitivity level data of the current user, until the weight of the optimal authentication method combination is saved to the weight calculator again; Calculating the weight sum of the optimal authentication method combination corresponding to the current user in the weight calculator; When the sum of the weights reaches a weight threshold, it is determined that the current user meets the sensitive service handling conditions.
6. The business handling authentication method according to claim 1, characterized in that: The user target behavior data is determined based on the following method: Collecting behavior data of multiple users corresponding to the multiple classification indicators; Preprocessing the behavior data to obtain the user target behavior data; The preprocessing includes data cleaning, data conversion and data standardization.
7. A business handling authentication device, characterized in that: include: A classification module is used to classify user target behavior data based on multiple classification indicators to obtain multiple classification data; The authentication method combination screening module is used to: based on the weight of each classification index when selecting the authentication method combination, screen out multiple target authentication method combinations with top rankings under multiple classification index combinations from the authentication method combinations corresponding to the multiple classification data; The business processing authentication module is used to: perform business processing authentication of the user based on the combination of the multiple target authentication methods.
8. An electronic device comprising a processor and a memory storing a computer program, characterized in that: When the processor executes the computer program, the steps of the business processing authentication method described in any one of claims 1 to 6 are implemented.
9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the business processing authentication method according to any one of claims 1 to 6 are implemented.
10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the business processing authentication method according to any one of claims 1 to 6 are implemented.