WO2019100771A1 - 问题推送方法及装置 - Google Patents

问题推送方法及装置 Download PDF

Info

Publication number
WO2019100771A1
WO2019100771A1 PCT/CN2018/100757 CN2018100757W WO2019100771A1 WO 2019100771 A1 WO2019100771 A1 WO 2019100771A1 CN 2018100757 W CN2018100757 W CN 2018100757W WO 2019100771 A1 WO2019100771 A1 WO 2019100771A1
Authority
WO
WIPO (PCT)
Prior art keywords
verification
question
verification question
determining
target user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2018/100757
Other languages
English (en)
French (fr)
Inventor
王伟
赵秀丽
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alibaba Group Holding Ltd
Original Assignee
Alibaba Group Holding Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Alibaba Group Holding Ltd filed Critical Alibaba Group Holding Ltd
Publication of WO2019100771A1 publication Critical patent/WO2019100771A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
    • H04L9/40—Network security protocols
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/60—Protecting data
    • G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
    • G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
    • G06F21/6245—Protecting personal data, e.g. for financial or medical purposes

Definitions

  • the present specification relates to the field of security verification, and in particular, to a method and device for pushing a problem.
  • the problem verification service is a kind of nucleus method for user authentication based on information or knowledge in the user's memory. Problem authentication is undergoing an iterative process of improving security.
  • the problem library for the initial problem authentication is based on the user's personal information. For example, when a user registers an account with a chat software, he or she will fill in some questions: "What is your father's name?", "Where is your birthplace?" "Wait, these problems were later used as links for users to retrieve passwords, that is, to verify whether the user who is currently looking for a secret is himself. However, since these problems are based on the user's personal information, such data as personal information is very easy to leak through social networking sites, Trojans, social engineering, etc., there is a greater security risk.
  • the assembly of the questionnaire (that is, which questions the user has to answer) is performed by randomly extracting or prioritizing the problem according to the manual experience. For example, a user may have more than a dozen questions such as "purchased goods”, “people who may know”, “common addresses”, “numbers used by users”, etc., when performing problem verification, from this ten Randomly extract a question from several questions for verification.
  • this kind of questionnaire assembly method does not guarantee security.
  • the purpose of one or more embodiments of the present specification is to provide a problem pushing method and apparatus for improving the problem pushing mechanism so that the pushing problem is more targeted.
  • one or more embodiments of the present specification provide a method for pushing a problem, including:
  • Determining a feature attribute of the verification question of the target user wherein the feature attribute includes: at least one of a correct answer rate, a security level, and a privacy level of the verification question;
  • a target verification question pushed to the target user is determined based on a push score for each of the verification questions.
  • the determining, according to the feature attribute of the verification question, the push score of the verification question including:
  • the weight of the feature attribute of the verification question and the weight value of the attribute value are determined as the push score of the verification question.
  • the determining the weight of the feature attribute of the verification question includes:
  • the feature attribute includes a correct answer rate of the verification question
  • determining attribute values of the feature attributes of the verification question including:
  • the historical behavior data includes historical usage behavior information for the service, historical answer behavior information for the verification question, and the verification problem At least one of the answer scores;
  • the historical behavior data is trained as sample data of the specified two-category model to obtain a correct answer rate of the verification question.
  • the historical answer behavior information includes a reply result, and the answer result includes a correct result or an incorrect result;
  • the method further includes:
  • the feature attribute includes the security level
  • determining attribute values of the feature attributes of the verification question including:
  • the security level of the verification question is determined based on the amount of information, wherein the amount of information is proportional to the degree of security.
  • the feature attribute includes the degree of privacy
  • determining attribute values of the feature attributes of the verification question including:
  • determining, according to the push score of each of the verification questions, a target verification problem pushed to the target user including:
  • the verification question corresponding to the push score that reaches the preset threshold is determined as the target verification question pushed to the target user.
  • one or more embodiments of the present disclosure provide a problem pushing device, including:
  • the first determining module determines a feature attribute of the verification question of the target user, where the feature attribute includes: at least one of a correctness rate, a security level, and a privacy level of the verification question;
  • a second determining module determining, according to the feature attribute of the verification question, a push score of the verification question
  • the third determining module determines, according to the push score of each of the verification questions, a target verification question pushed to the target user.
  • the second determining module includes:
  • a first determining unit determining a weight of the feature attribute of the verification question, and determining an attribute value of the feature attribute of the verification question
  • the second determining unit determines the weight of the feature attribute of the verification question and the weight value of the attribute value as the push score of the verification question.
  • the first determining unit determines a weight of the feature attribute of the verification question according to a scenario and/or a service type of the verification service corresponding to the target user.
  • the feature attribute includes a correct answer rate of the verification question
  • the first determining unit acquires historical behavior data of the target user in a service corresponding to the current verification service, where the historical behavior data includes historical usage behavior information of the service, and a historical answer to the verification question. At least one of behavioral information, a question passing rate score of the verification question; constructing a specified two-category model; training the historical behavior data as sample data of the specified two-category model to obtain a question of the verification question Correct rate.
  • the historical answer behavior information includes a reply result, and the answer result includes a correct result or an incorrect result;
  • the device also includes:
  • the update module updates the correct answer rate of the target verification question according to the answer result for the target verification question.
  • the feature attribute includes the security level
  • the feature attribute includes the degree of privacy
  • the first determining unit determines a degree of relevance between the verification question and the personal information of the target user; determining a privacy level of the verification question according to the relevance, wherein the relevance and the privacy The degree is proportional.
  • the third determining module includes:
  • a third determining unit determining the verification question with the highest push score as the target verification problem pushed to the target user
  • the fourth determining unit determines the verification question corresponding to the push score that reaches the preset threshold as the target verification question pushed to the target user.
  • one or more embodiments of the present disclosure provide a problem pushing device, including:
  • a memory arranged to store computer executable instructions that, when executed, cause the processor to:
  • Determining a feature attribute of the verification question of the target user wherein the feature attribute includes: at least one of a correct answer rate, a security level, and a privacy level of the verification question;
  • a target verification question pushed to the target user is determined based on a push score for each of the verification questions.
  • one or more embodiments of the present specification provide a storage medium for storing computer executable instructions that, when executed, implement the following processes:
  • Determining a feature attribute of the verification question of the target user wherein the feature attribute includes: at least one of a correct answer rate, a security level, and a privacy level of the verification question;
  • a target verification question pushed to the target user is determined based on a push score for each of the verification questions.
  • the technical solution of one or more embodiments of the present specification it is possible to determine the feature attribute of the verification question of the target user (including at least one of the correctness rate, the security level, and the privacy level of the verification question), and determine the verification problem according to the feature attribute.
  • the push score, and then the target verification question pushed to the target user is determined according to the push score of each verification question. Therefore, when the verification solution is pushed to the user, the technical solution can balance the correctness rate, security level, and/or privacy level of the verification question of the target user, thereby being more targeted and flexible when using the question and answer form for identity verification.
  • the user pushes the verification problem to the user, improves the push mechanism of the verification problem, and improves the user's answer rate and the security and privacy of the verification service, thereby improving the user's experience of the verification service.
  • FIG. 1 is a schematic flow chart of a problem pushing method according to an embodiment of the present specification
  • FIG. 2 is a schematic block diagram of a problem pushing device according to an embodiment of the present specification
  • FIG. 3 is a schematic block diagram of a problem pushing device according to an embodiment of the present specification.
  • One or more embodiments of the present specification provide a problem pushing method and apparatus for improving a problem pushing mechanism to make the push problem more specific.
  • FIG. 1 is a schematic flowchart of a method for pushing a problem according to an embodiment of the present specification. As shown in FIG. 1, the method includes:
  • Step S102 determining a feature attribute of the verification question of the target user.
  • the feature attribute includes at least one of a correctness rate, a security level, and a privacy level of the verification question.
  • Step S104 determining a push score of the verification question according to the feature attribute of the verification question.
  • Step S106 determining a target verification problem pushed to the target user according to the push score of each verification question.
  • the technical solution of one or more embodiments of the present specification it is possible to determine the feature attribute of the verification question of the target user (including at least one of the correctness rate, the security level, and the privacy level of the verification question), and determine the verification problem according to the feature attribute.
  • the push score, and then the target verification question pushed to the target user is determined according to the push score of each verification question. Therefore, when the verification solution is pushed to the user, the technical solution can balance the correctness rate, security level, and/or privacy level of the verification question of the target user, thereby being more targeted and flexible when using the question and answer form for identity verification.
  • the user pushes the verification problem to the user, improves the push mechanism of the verification problem, and improves the user's answer rate and the security and privacy of the verification service, thereby improving the user's experience of the verification service.
  • the push score of the verification question when determining the push score of the verification question according to the feature attribute of the verification question, first determining the weight of the feature attribute of the verification question, and determining the attribute value of the feature attribute of the verification question; and further verifying the feature of the problem.
  • the weight of the attribute and the weighted value of the attribute value are determined as the push score for the verification question.
  • the weight of the feature attribute of the verification question may be determined according to the scenario and/or the service type of the verification service corresponding to the target user.
  • the verification service scenario is such as using an account to log in, modifying information, and the like; and verifying the service type of the service, such as shopping, games, and finance.
  • different weights can be set for the feature attributes of the verification question. For example, when the scenario of the verification service is modification information, a higher weight may be set for the security level and the privacy level of the feature attribute; when the service type of the verification service belongs to the financial category, the security level of the feature attribute may be set. High weight; when the business type of the verification service belongs to the shopping category, a higher weight can be set for the correct rate of the verification question in the feature attribute; and the like.
  • the weights of the feature attributes of each verification question may be set to be the same or may be set to be different.
  • the characterization of the attribute value may take the form of a score, a probability, or the like.
  • the attribute value corresponding to the user's correct answer rate for each question may be the correct answer rate itself
  • the attribute value corresponding to the security level of each question may be a security score
  • the attribute value corresponding to the privacy degree of each question may be a privacy score.
  • the sum of the weights corresponding to each feature attribute of the same verification question is 1.
  • the correct answer rate of the verification question ie, the attribute value of the correct answer rate
  • the correct answer rate of the verification question ie, the attribute value of the correct answer rate
  • the historical answer behavior information includes the answer result, and the answer result includes the correct result or the wrong result.
  • Table 1 exemplarily shows the answer passing rate score of a certain verification question.
  • Table 1 shows the correspondence between the passing rate of the verification question and the passing rate of the answering question. For example, if the answering rate of the verification question is 50%, the corresponding answer passing rate score is 50 points; If the answer rate of the verification question is 60%, the corresponding answer passing rate score is 70 points; if the answering question pass rate is 90%, the corresponding answer passing rate score is 98 points; .
  • the answer scores of the verification questions may be the same or different.
  • factors such as difficulty level, security level, privacy level, etc. of each verification question may be comprehensively considered, and the difficulty level, security level or privacy according to each verification question may be considered.
  • Different factors such as the degree can set different answer pass rate scores for each verification question. For example, if the verification problem is more difficult, a higher answer pass rate score can be set for the verification question.
  • the historical behavior data is trained as the sample data of the specified two-category model, and the correct answer rate of the verification problem is obtained.
  • the specified two-category model may be an xgboost binary classification model, and the process of training the sample data by using the xgboost binary classification model is prior art, and therefore will not be described again.
  • the specified two-category model may also be another type of two-category model, which is not limited in this embodiment.
  • the security level of the verification question (ie, the attribute value of the security level) may be determined as follows: First, the amount of information carried by the verification question is determined according to the keywords included in the verification question; Secondly, the security level of the verification problem is determined according to the amount of information, wherein the amount of information is proportional to the degree of security.
  • the more keywords included in the verification question the larger the amount of information carried, and the higher the security of the verification problem.
  • the keywords included include “the most expensive”, “what is”
  • the keywords contained in it only include “what is”; obviously, the amount of information carried in verification question 1 is greater than the amount of information carried in verification question 2, and the security level of verification problem 1 is higher than the verification problem. 2 the degree of security.
  • the degree of privacy of the verification question (ie, the attribute value of the privacy level) may be determined as follows: first, the degree of correlation between the verification question and the personal information of the target user is determined; secondly, according to Relevance determines the degree of privacy of the verification question, where the relevance is proportional to the degree of privacy.
  • the personal information of the target user may include a name, a nickname, an account information, a bound bank card number, a mobile phone number, and the like.
  • verification question 3 “Which is the bank card number to which your current account is bound?"
  • verification question 4 “Which is the wifi you use?”
  • the privacy level of the verification question 3 is higher than the privacy level of the verification question 4.
  • the verification service is performed in Taobao.
  • the server will verify the identity of the user by using the problem kernel mode, that is, display one or two verification questions related to Taobao to the target user for the user to answer. Then, the multiple verification process and the usage behavior information of the target user using Taobao can be utilized to determine the target user's answer rate for each question.
  • the historical behavior data includes the historical usage behavior information of the user on Taobao, the historical answer behavior information of each verification question, and the passing rate score of each verification question.
  • the target user's historical usage behavior information of Taobao and the historical answer behavior information of each verification question may be recorded and counted in advance, and the answer rate score for each verification question may be pre-stored on the server side.
  • the target user's historical usage behavior information for Taobao the user purchased the product A, the product B, and the product C in the most recent month, and the wifi used by the user to log in to the Taobao account within the last six months is “12345678”; the target user
  • the historical answer behavior information for each verification question is as follows: there are 3 correct results and 2 incorrect results for question a, and 10 correct results for question b; the answer rate scores of each verification question are shown in Table 1.
  • the answer scores of the verification questions in this embodiment may be the same.
  • the xgboost binary classification model is constructed.
  • the historical behavior data is trained as the sample data of the xgboost binary classification model, and the correct answer rate of the verification problem is obtained.
  • the target user has a correct answer rate of 70% for question a, 98% correct answer rate for question b, and 80% correct answer rate for question c, and so on.
  • the above examples are used to determine the attribute values and weights of the feature attributes of the verification question.
  • the attribute value of the feature attribute is represented by a score and/or a probability form, and may specifically include verifying the user's correct answer rate for the verification question, the security score of the verification question, and the privacy score.
  • a, problem b, and problem c are examples of verification problems listed in this embodiment, such as problem a, problem b, and problem c. In practice, the number of verification problems in the problem library is usually much larger than three.
  • Table 2 - Table 4 exemplarily show the attribute values and weights respectively corresponding to the respective characteristic attributes of the question a, the question b, and the question c, respectively.
  • the sum of the weights corresponding to each feature attribute of each question is 1.
  • each verification question can be sorted according to the push score of each verification question.
  • the verification questions are sorted in descending order according to the push scores of the verification questions. Since the push score of the problem c is the highest, the push score of the question a is the second highest, and the push score of the question b is high. The lowest, so the sort result is question c> question a> question b.
  • the verification question with the highest push score may be determined as the target verification question pushed to the target user; or the push score corresponding to the preset threshold may be The verification question is determined to be a target verification issue that is pushed to the target user.
  • the target verification problem can be pushed to Taobao according to the sorting result. Assuming that the target verification problem is the verification question with the highest push score, the problem c can be pushed to the target user as the target verification problem.
  • the correct answer rate of the verification question is related to the historical behavior data of the target user in the service corresponding to the current verification service
  • the security level of the verification problem is related to the amount of information carried by the target user
  • the information amount is related to the target user.
  • Relevant historical behavior information in the business, and the degree of privacy of the verification question is related to the personal information of the target user. Since different users have different historical behavior data and different personal information, the feature attributes of the verification problem are different for different target users, which makes the same verification problem when pushing the verification problem for different target users. The corresponding push scores are also different.
  • the target user answers the target verification question.
  • the correct answer rate of the target verification question may be updated according to the answer result, and then the push score of the target verification question is updated according to the updated correct answer rate.
  • the target verification problem is question c.
  • the target user solves the problem of the target--the answer to the question c is the correct result, then the correct rate of the answer to the question c is updated according to the result of the answer. At this time, the correct answer rate of the target user to the question c is updated. improve.
  • the correct answer rate of the target verification question can be updated based on the target user's answer to the target verification question, and then the push score of the target verification question can be updated, so that the push score of the verification question can be matched with the target user.
  • the result of the verification question is updated in time, so that the target verification problem pushed to the target user is more in line with the target user's answering requirement, that is, the error rate of the target user's answer is reduced.
  • one or more embodiments of the present specification further provide a problem pushing device.
  • FIG. 2 is a schematic block diagram of a problem pushing device in accordance with an embodiment of the present specification. As shown in Figure 2, the device comprises:
  • the first determining module 210 is configured to determine a feature attribute of the verification question of the target user, where the feature attribute includes: at least one of a correct answer rate, a security level, and a privacy level of the verification question;
  • the second determining module 220 determines a push score of the verification question according to the feature attribute of the verification question
  • the third determining module 230 determines the target verification problem pushed to the target user according to the push score of each verification question.
  • the second determining module 220 includes:
  • a first determining unit determining a weight of the feature attribute of the verification question, and determining an attribute value of the feature attribute of the verification question
  • the second determining unit determines the weight of the feature attribute of the verification question and the weight value of the attribute value as the push score of the verification question.
  • the first determining unit determines the weight of the feature attribute of the verification question according to the scenario and/or the service type of the verification service corresponding to the target user.
  • the feature attribute includes a correct answer rate of the verification question
  • the first determining unit acquires historical behavior data of the target user in the service corresponding to the current verification service, and the historical behavior data includes historical usage behavior information of the service, historical answer behavior information for the verification problem, and a passing rate score of the verification question At least one of the items; constructing the specified two-category model; training the historical behavior data as the sample data of the specified two-category model, and obtaining the correct answer rate of the verification question.
  • the historical answer behavior information includes a result of the answer, and the answer result includes a correct result or an incorrect result;
  • the above device also includes:
  • the update module updates the correct answer rate of the target verification question according to the result of the answer to the target verification question.
  • the feature attribute includes a degree of security
  • the first determining unit determines the amount of information carried by the verification question according to the keywords included in the verification question; and determines the security level of the verification question according to the amount of information, wherein the amount of information is proportional to the degree of security.
  • the feature attribute includes a degree of privacy
  • the first determining unit determines the degree of relevance between the verification question and the personal information of the target user; and determines the privacy level of the verification question according to the relevance, wherein the degree of relevance is proportional to the degree of privacy.
  • the third determining module 230 includes:
  • the third determining unit determines the verification question with the highest push score as the target verification problem pushed to the target user; or
  • the fourth determining unit determines the verification question corresponding to the push score that reaches the preset threshold as the target verification problem pushed to the target user.
  • the apparatus of one or more embodiments of the present specification it is possible to determine a feature attribute of the verification question of the target user (including at least one of a correctness rate, a security level, and a privacy level of the verification question), and determine the verification problem according to the feature attribute.
  • the score is pushed, and the target verification question pushed to the target user is determined according to the push score of each verification question. Therefore, when the verification solution is pushed to the user, the technical solution can balance the correctness rate, security level, and/or privacy level of the verification question of the target user, thereby being more targeted and flexible when using the question and answer form for identity verification.
  • the user pushes the verification problem to the user, improves the push mechanism of the verification problem, and improves the user's answer rate and the security and privacy of the verification service, thereby improving the user's experience of the verification service.
  • problem pushing device in FIG. 2 can be used to implement the problem pushing method described above, and the detailed description thereof should be similar to the description in the foregoing method section. To avoid cumbersome, no further details are provided herein.
  • the problem push device may vary considerably depending on configuration or performance, and may include one or more processors 301 and memory 302 in which one or more storage applications or data may be stored.
  • the memory 302 can be short-term storage or persistent storage.
  • the application stored in memory 302 may include one or more modules (not shown), each of which may include a series of computer executable instructions in the problem pushing device.
  • the processor 301 can be arranged to communicate with the memory 302 to execute a series of computer executable instructions in the memory 302 on the problem push device.
  • the problem push device may also include one or more power sources 303, one or more wired or wireless network interfaces 304, one or more input and output interfaces 305, one or more keyboards 306.
  • the problem pushing device includes a memory, and one or more programs, wherein one or more programs are stored in the memory, and one or more programs may include one or more modules, and each A module can include a series of computer executable instructions in a problem pushing device, and configured to be executed by one or more processors.
  • the one or more programs are included for performing the following computer executable instructions:
  • Determining a feature attribute of the verification question of the target user wherein the feature attribute includes: at least one of a correct answer rate, a security level, and a privacy level of the verification question;
  • a target verification question pushed to the target user is determined based on a push score for each of the verification questions.
  • the weight of the feature attribute of the verification question and the weight value of the attribute value are determined as the push score of the verification question.
  • the computer executable instructions when executed, may also cause the processor to:
  • the feature attribute includes a correct answer rate of the verification question; when the computer executable instruction is executed, the processor may further be:
  • the historical behavior data includes historical usage behavior information for the service, historical answer behavior information for the verification question, and the verification problem At least one of the answer scores;
  • the historical behavior data is trained as sample data of the specified two-category model to obtain a correct answer rate of the verification question.
  • the historical answer behavior information includes a answer result
  • the answer result includes a correct result or an error result
  • the processor may further be:
  • the feature attribute includes the security level; when the computer executable instructions are executed, the processor may also be:
  • the security level of the verification question is determined based on the amount of information, wherein the amount of information is proportional to the degree of security.
  • the feature attribute includes the degree of privacy; when the computer executable instructions are executed, the processor may further be:
  • the computer executable instructions when executed, may also cause the processor to:
  • the verification question corresponding to the push score that reaches the preset threshold is determined as the target verification question pushed to the target user.
  • One or more embodiments of the present specification also provide a computer readable storage medium storing one or more programs, the one or more programs including instructions that when included in a plurality of applications When the electronic device is executed, the electronic device can be configured to perform the above problem pushing method, and is specifically used to execute:
  • Determining a feature attribute of the verification question of the target user wherein the feature attribute includes: at least one of a correct answer rate, a security level, and a privacy level of the verification question;
  • a target verification question pushed to the target user is determined based on a push score for each of the verification questions.
  • the system, device, module or unit illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product having a certain function.
  • a typical implementation device is a computer.
  • the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or A combination of any of these devices.
  • one or more embodiments of the present specification can be provided as a method, system, or computer program product.
  • one or more embodiments of the present specification can take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware.
  • one or more embodiments of the present specification can employ a computer program embodied on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer usable program code embodied therein. The form of the product.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
  • a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory.
  • RAM random access memory
  • ROM read only memory
  • Memory is an example of a computer readable medium.
  • Computer readable media includes both permanent and non-persistent, removable and non-removable media.
  • Information storage can be implemented by any method or technology.
  • the information can be computer readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device.
  • computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.
  • program modules include routines, programs, objects, components, data structures, and the like that perform particular tasks or implement particular abstract data types.
  • the present application can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are connected through a communication network.
  • program modules can be located in both local and remote computer storage media including storage devices.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Bioethics (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Medical Informatics (AREA)
  • Computer Hardware Design (AREA)
  • Software Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Electrically Operated Instructional Devices (AREA)

Abstract

本说明书一个或多个实施例公开了一种问题推送方法及装置，用以完善问题推送机制，以使推送的问题更具针对性。所述方法包括：确定目标用户的验证问题的特征属性；其中，所述特征属性包括：验证问题的答题正确率、安全程度、隐私程度中的至少一项；根据所述验证问题的特征属性，确定所述验证问题的推送分值；根据每个所述验证问题的推送分值，确定向所述目标用户推送的目标验证问题。

Description

问题推送方法及装置 技术领域
本说明书涉及安全验证领域，尤其涉及一种问题推送方法及装置。
背景技术
问题验证服务是基于用户记忆中的信息或知识来进行用户身份验证的一种核身方式。问题鉴权正在经历一个提高安全性的迭代过程。最初的问题鉴权的问题库是基于用户个人信息设计的，比如，当用户注册某聊天软件的账户时会填一些问题：“您的父亲名字是什么？”、“您的出生地是哪里？”等等，这些问题后来被用做用户找回密码等环节中，即验证当前找密的用户是否是本人。但是，由于这些问题是基于用户个人信息的，而个人信息这类数据非常容易通过社交网站、木马程序、社交工程等途径泄露，存在较大的安全风险。
近来，一些利用大数据技术通过用户在某系统中留下的行为足迹来挖掘用户记忆深刻的事情，并将其提炼成问题和答案的方式以对用户在特殊场景下进行身份核实鉴权。问题核身通过大数据挖掘获得用户可用的问题，问题可能包含多种类型，比如购买过的商品，可能认识的人、常用的地址、用户使用过的号码等。这种方式比最初的问题鉴权有灵活性上的优势，随着用户的行为足迹在系统中不断产生，对用户的问题和答案也在不断更新，从而提高了问题的灵活性、安全性。
现有的问题验证服务中对于问卷的组装(即用户要回答哪些问题)采用随机抽取或按照人工经验设定问题的优先级来进行。比如，一个用户可能有“购买过的商品”、“可能认识的人”、“常用的地址”、“用户使用过的号码”等十几个问题，在进行问题核身验证时，从这十几个问题中随机抽取一个问题进行验证。这种问卷组装方式一方面并不能保障安全性，一方面也不能保障所抽取的问题适合每类用户去回答，因此针对性较差。
发明内容
本说明书一个或多个实施例的目的是提供一种问题推送方法及装置，用以完善问题推送机制，以使推送的问题更具针对性。
为解决上述技术问题，本说明书一个或多个实施例是这样实现的：
一方面，本说明书一个或多个实施例提供一种问题推送方法，包括：
确定目标用户的验证问题的特征属性；其中，所述特征属性包括：验证问题的答题正确率、安全程度、隐私程度中的至少一项；
根据所述验证问题的特征属性，确定所述验证问题的推送分值；
根据每个所述验证问题的推送分值，确定向所述目标用户推送的目标验证问题。
可选地，所述根据所述验证问题的特征属性，确定所述验证问题的推送分值，包括：
确定所述验证问题的特征属性的权值，以及，确定所述验证问题的特征属性的属性值；
将所述验证问题的特征属性的权值以及属性值的加权值确定为所述验证问题的推送分值。
可选地，所述确定所述验证问题的特征属性的权值，包括：
根据所述目标用户所对应的验证服务的场景和/或业务类型，确定所述验证问题的特征属性的权值。
可选地，所述特征属性包括所述验证问题的答题正确率；
相应的，确定所述验证问题的特征属性的属性值，包括：
获取所述目标用户在当前验证服务所对应的业务中的历史行为数据，所述历史行为数据包括对所述业务的历史使用行为信息、针对所述验证问题的历史答题行为信息、所述验证问题的答题通过率得分中的至少一项；
构建指定二分类模型；
将所述历史行为数据作为所述指定二分类模型的样本数据进行训练，得到所述验证问题的答题正确率。
可选地，所述历史答题行为信息包括答题结果，所述答题结果包括正确结果或错误结果；
所述方法还包括：
获取所述目标用户在当前验证服务中针对所述目标验证问题的答题结果；
根据针对所述目标验证问题的答题结果，更新所述目标验证问题的答题正确率。
可选地，所述特征属性包括所述安全程度；
相应的，确定所述验证问题的特征属性的属性值，包括：
根据所述验证问题中包含的关键词，确定所述验证问题所携带的信息量；
根据所述信息量确定所述验证问题的安全程度，其中，所述信息量与所述安全程度成正比。
可选地，所述特征属性包括所述隐私程度；
相应的，确定所述验证问题的特征属性的属性值，包括：
确定所述验证问题和所述目标用户的个人信息之间的相关度；
根据所述相关度确定所述验证问题的隐私程度，其中，所述相关度与所述隐私程度成正比。
可选地，根据每个所述验证问题的推送分值，确定向所述目标用户推送的目标验证问题，包括：
将所述推送分值最高的验证问题确定为向所述目标用户推送的目标验证问题；或，
将达到预设阈值的推送分值所对应的验证问题确定为向所述目标用户推送的目标验证问题。
另一方面，本说明书一个或多个实施例提供一种问题推送装置，包括：
第一确定模块，确定目标用户的验证问题的特征属性；其中，所述特征属性包括：验证问题的答题正确率、安全程度、隐私程度中的至少一项；
第二确定模块，根据所述验证问题的特征属性，确定所述验证问题的推送分值；
第三确定模块，根据每个所述验证问题的推送分值，确定向所述目标用户推送的目标验证问题。
可选地，所述第二确定模块包括：
第一确定单元，确定所述验证问题的特征属性的权值，以及，确定所述验证问题的特征属性的属性值；
第二确定单元，将所述验证问题的特征属性的权值以及属性值的加权值确定为所述 验证问题的推送分值。
可选地，所述第一确定单元，根据所述目标用户所对应的验证服务的场景和/或业务类型，确定所述验证问题的特征属性的权值。
可选地，所述特征属性包括所述验证问题的答题正确率；
所述第一确定单元，获取所述目标用户在当前验证服务所对应的业务中的历史行为数据，所述历史行为数据包括对所述业务的历史使用行为信息、针对所述验证问题的历史答题行为信息、所述验证问题的答题通过率得分中的至少一项；构建指定二分类模型；将所述历史行为数据作为所述指定二分类模型的样本数据进行训练，得到所述验证问题的答题正确率。
可选地，所述历史答题行为信息包括答题结果，所述答题结果包括正确结果或错误结果；
所述装置还包括：
获取模块，获取所述目标用户在当前验证服务中针对所述目标验证问题的答题结果；
更新模块，根据针对所述目标验证问题的答题结果，更新所述目标验证问题的答题正确率。
可选地，所述特征属性包括所述安全程度；
所述第一确定单元，根据所述验证问题中包含的关键词，确定所述验证问题所携带的信息量；根据所述信息量确定所述验证问题的安全程度，其中，所述信息量与所述安全程度成正比。
可选地，所述特征属性包括所述隐私程度；
所述第一确定单元，确定所述验证问题和所述目标用户的个人信息之间的相关度；根据所述相关度确定所述验证问题的隐私程度，其中，所述相关度与所述隐私程度成正比。
可选地，所述第三确定模块包括：
第三确定单元，将所述推送分值最高的验证问题确定为向所述目标用户推送的目标验证问题；或，
第四确定单元，将达到预设阈值的推送分值所对应的验证问题确定为向所述目标用 户推送的目标验证问题。
再一方面，本说明书一个或多个实施例提供一种问题推送设备，包括：
处理器；以及
被安排成存储计算机可执行指令的存储器，所述可执行指令在被执行时使所述处理器：
确定目标用户的验证问题的特征属性；其中，所述特征属性包括：验证问题的答题正确率、安全程度、隐私程度中的至少一项；
根据所述验证问题的特征属性，确定所述验证问题的推送分值；
根据每个所述验证问题的推送分值，确定向所述目标用户推送的目标验证问题。
再一方面，本说明书一个或多个实施例提供一种存储介质，用于存储计算机可执行指令，所述可执行指令在被执行时实现以下流程：
确定目标用户的验证问题的特征属性；其中，所述特征属性包括：验证问题的答题正确率、安全程度、隐私程度中的至少一项；
根据所述验证问题的特征属性，确定所述验证问题的推送分值；
根据每个所述验证问题的推送分值，确定向所述目标用户推送的目标验证问题。
采用本说明书一个或多个实施例的技术方案，能够确定目标用户的验证问题的特征属性(包括验证问题的答题正确率、安全程度、隐私程度中的至少一项)，根据特征属性确定验证问题的推送分值，进而根据每个验证问题的推送分值确定向目标用户推送的目标验证问题。因此，该技术方案在向用户推送验证问题时，能够兼顾目标用户的验证问题的答题正确率、安全程度和/或隐私程度，从而在采用问答形式进行身份验证时能够更加有针对性地、灵活地向用户推送验证问题，完善了验证问题的推送机制，且提升用户的答题通过率以及验证服务的安全性和隐私性，进而提升用户对验证服务的体验度。
附图说明
为了更清楚地说明本说明书一个或多个实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本说明书一个或多个实施例中记载的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1是根据本说明书一实施例的一种问题推送方法的示意性流程图；
图2是根据本说明书一实施例的一种问题推送装置的示意性框图；
图3是根据本说明书一实施例的一种问题推送设备的示意性框图。
具体实施方式
本说明书一个或多个实施例提供一种问题推送方法及装置，用以完善问题推送机制，以使推送的问题更具针对性。
为了使本技术领域的人员更好地理解本说明书一个或多个实施例中的技术方案，下面将结合本说明书一个或多个实施例中的附图，对本说明书一个或多个实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本说明书一部分实施例，而不是全部的实施例。基于本说明书一个或多个实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都应当属于本说明书一个或多个实施例保护的范围。
图1是根据本说明书一实施例的一种问题推送方法的示意性流程图，如图1所示，该方法包括：
步骤S102，确定目标用户的验证问题的特征属性。
其中，特征属性包括验证问题的答题正确率、安全程度、隐私程度中的至少一项。
步骤S104，根据验证问题的特征属性，确定验证问题的推送分值。
步骤S106，根据每个验证问题的推送分值，确定向目标用户推送的目标验证问题。
采用本说明书一个或多个实施例的技术方案，能够确定目标用户的验证问题的特征属性(包括验证问题的答题正确率、安全程度、隐私程度中的至少一项)，根据特征属性确定验证问题的推送分值，进而根据每个验证问题的推送分值确定向目标用户推送的目标验证问题。因此，该技术方案在向用户推送验证问题时，能够兼顾目标用户的验证问题的答题正确率、安全程度和/或隐私程度，从而在采用问答形式进行身份验证时能够更加有针对性地、灵活地向用户推送验证问题，完善了验证问题的推送机制，且提升用户的答题通过率以及验证服务的安全性和隐私性，进而提升用户对验证服务的体验度。
在一个实施例中，根据验证问题的特征属性确定验证问题的推送分值时，首先确定验证问题的特征属性的权值，以及，确定验证问题的特征属性的属性值；进而将验证问 题的特征属性的权值以及属性值的加权值确定为验证问题的推送分值。
本实施例中，验证问题的特征属性的权值可根据目标用户所对应的验证服务的场景和/或业务类型来确定。其中，验证服务的场景如使用账号进行登录、修改信息等；验证服务的业务类型如购物类、游戏类、金融类等。根据验证服务的场景和/或业务类型的不同，可针对验证问题的特征属性设置不同的权值。例如，当验证服务的场景为修改信息时，可对特征属性中安全程度和隐私程度均设置较高的权值；当验证服务的业务类型属于金融类时，可对特征属性中安全程度设置较高的权值；当验证服务的业务类型属于购物类时，可对特征属性中对验证问题的答题正确率设置较高的权值；等等。
通常情况下，同一用户可对应多个不同的验证问题。因此，对于目标用户的多个验证问题，各验证问题的特征属性的权值可设置为相同，也可设置为不同。
本实施例中，属性值的表征方式可采用分值、概率等形式。例如，用户对各问题的答题正确率对应的属性值可以是答题正确率本身，各问题的安全程度对应的属性值可以是安全分值，各问题的隐私程度对应的属性值可以是隐私分值。同一验证问题的各特征属性分别对应的权值的和为1。
以下详细介绍如何确定验证问题的特征属性的属性值。
当特征属性包括验证问题的答题正确率时，可按照如下方式确定验证问题的答题正确率(即答题正确率的属性值)：
首先，获取目标用户在当前验证服务所对应的业务中的历史行为数据，该历史行为数据包括对该业务的历史使用行为信息、针对验证问题的历史答题行为信息、验证问题的答题通过率得分中的至少一项。
其中，历史答题行为信息包括答题结果，答题结果包括正确结果或错误结果。
表1示例性地示出了某个验证问题的答题通过率得分情况。由表1可看出该验证问题的答题通过率与答题通过率得分之间的对应关系，例如，若该验证问题的答题通过率为50％，则其对应的答题通过率得分为50分；若该验证问题的答题通过率为60％，则其对应的答题通过率得分为70分；若该验证问题的答题通过率为90％，则其对应的答题通过率得分为98分；等等。
表1
答题通过率 答题通过率得分
50％ 50分
60％ 70分
90％ 98分
各验证问题的答题通过率得分情况可以相同，也可以不相同。在一个实施例中，为各验证问题预设答题通过率得分时，可综合考虑各验证问题的难易程度、安全程度、隐私程度等因素，根据各验证问题的难易程度、安全程度或隐私程度等因素的不同，可为各验证问题设定不同的答题通过率得分。例如，若验证问题的难度较高，则可为该验证问题设置较高的答题通过率得分。
其次，构建指定二分类模型。
再次，将历史行为数据作为指定二分类模型的样本数据进行训练，得到验证问题的答题正确率。
其中，指定二分类模型可以是xgboost二分类模型，利用xgboost二分类模型对样本数据进行训练的过程为现有技术，因此不再赘述。当然，指定二分类模型还可以是其他类型的二分类模型，本实施例对此不做限定。
当特征属性包括验证问题的安全程度时，可按照如下方式确定验证问题的安全程度(即安全程度的属性值)：首先，根据验证问题中包含的关键词，确定验证问题所携带的信息量；其次，根据信息量确定验证问题的安全程度，其中，信息量与安全程度成正比。
具体的，验证问题中包含的关键词越多，其所携带的信息量越大，那么该验证问题的安全程度也就越高。例如，对于验证问题1——“您近期购买过的最贵的商品是什么？”，其中包含的关键词包括“最贵的”、“是什么”；对于验证问题2——“您近期购买过的商品是什么？”，其中包含的关键词仅包括“是什么”；显然，验证问题1所携带的信息量大于验证问题2所携带的信息量，验证问题1的安全程度高于验证问题2的安全程度。
当特征属性包含验证问题的隐私程度时，可按照如下方式确定验证问题的隐私程度(即隐私程度的属性值)：首先，确定验证问题和目标用户的个人信息之间的相关度；其次，根据相关度确定验证问题的隐私程度，其中，相关度与隐私程度成正比。
具体的，验证问题和目标用户的个人信息之间的相关度越高，该验证问题的隐私程度就越高；反之，验证问题和目标用户的个人信息之间的相关度月底，则该验证问题的隐私程度就越低。其中，目标用户的个人信息可包括姓名、昵称、账号信息、绑定的银行卡号、手机号码等。例如，对于验证问题3——“哪个是您当前账号所绑定的银行卡号？”，以及验证问题4——“哪个是您使用的wifi？”，由于验证问题3与目标用户的个人信息(即银行卡号)相关度很高，而验证问题4不涉及目标用户的个人信息，因此验证问题3的隐私程度高于验证问题4的隐私程度。
举例而言，在淘宝中进行验证服务。目标用户每次登录淘宝账户时，服务器会采用问题核身方式验证用户身份，即，向目标用户展示一个或两个与淘宝相关的验证问题供用户答题。那么，可利用多次验证过程以及目标用户使用淘宝的使用行为信息来确定目标用户对各问题的答题通过率。
首先获取目标用户在淘宝中的历史行为数据。其中，该历史行为数据包括用户对淘宝的历史使用行为信息、对各验证问题的历史答题行为信息以及各验证问题的答题通过率得分。目标用户对淘宝的历史使用行为信息以及对各验证问题的历史答题行为信息可预先进行记录并统计，针对各验证问题的答题通过率得分可预先存储于服务器端。例如，目标用户对淘宝的历史使用行为信息如：该用户在最近一个月内购买过商品A、商品B以及商品C，该用户最近半年内登录淘宝账户时使用的wifi为“12345678”；目标用户对各验证问题的历史答题行为信息如：针对问题a有3次正确结果和2次错误结果，针对问题b有10次正确结果；各验证问题的答题通过率得分如表1所示。为简便说明，本实施例中各验证问题的答题通过率得分情况可相同。
获取到目标用户在淘宝中的历史行为数据之后，构建xgboost二分类模型。
构建xgboost二分类模型之后，将历史行为数据作为xgboost二分类模型的样本数据进行训练，得到验证问题的答题正确率。例如，目标用户对问题a的答题正确率为70％，对问题b的答题正确率为98％，对问题c的答题正确率为80％，等等。
沿用上述举例来确定验证问题的特征属性的属性值和权值。其中，特征属性的属性值采用和分值和/或概率形式表征，具体可包括验证用户对验证问题的答题正确率、验证问题的安全分值以及隐私分值。为简便说明，本实施例中仅列举三个验证问题，如问题a、问题b以及问题c，实际应用中问题库中的验证问题数量通常远大于三。
表2-表4示例性地分别示出了问题a、问题b以及问题c的各特征属性分别对应 的属性值和权值。其中，各问题的各特征属性分别对应的权值的和为1。
表2
问题a的特征属性 属性值 权值
答题通过率 80％ 40％
安全分值 80分 40％
隐私分值 50分 20％
表3
问题b的特征属性 属性值 权值
答题通过率 98％ 50％
安全分值 60分 30％
隐私分值 50分 20％
表4
问题c的特征属性 属性值 权值
答题通过率 70％ 30％
安全分值 40分 10％
隐私分值 80分 60％
基于表2-表4示出的问题a、问题b以及问题c的各特征属性分别对应的属性值和权值，将各问题的各特征属性分别对应的属性值和权值进行加权求和，即可计算出各问题的推送分值。
具体的，问题a的推送分值Ta＝80％*40％+80*40％+50*20％＝42.32；问题b的推送分值Tb＝98％*50％+60*30％+50*20％＝28.49；问题c的推送分值Tc＝70％*30％+40*10％+80*60％＝52.21。
计算出问题a、问题b以及问题c的推送分值之后，根据各验证问题的推送分值即可对各验证问题进行排序。本实施例中，按照各验证问题的推送分值由高到低的顺序对各验证问题进行排序，由于问题c的推送分值最高，问题a的推送分值次高，问题b的推送分值最低，因此排序结果为问题c>问题a>问题b。
在一个实施例中，向用目标用户推送目标验证问题时，可将推送分值最高的验证问题确定为向目标用户推送的目标验证问题；或，将达到预设阈值的推送分值所对应 的验证问题确定为向目标用户推送的目标验证问题。
沿用上述举例，得到排序结果之后，即可根据排序结果向淘宝推送目标验证问题。假设目标验证问题为推送分值最高的验证问题，那么可将问题c作为目标验证问题推送至目标用户。
由以上实施例可知，验证问题的答题正确率与目标用户在当前验证服务所对应的业务中的历史行为数据相关，验证问题的安全程度与其所携带的信息量相关，该信息量与目标用户在该业务中的历史行为信息有关，验证问题的隐私程度与目标用户的个人信息相关。由于不同用户对应有各自不同的历史行为数据以及不同的个人信息，因此，针对不同的目标用户，验证问题的特征属性均有所不同，这使得为不同的目标用户推送验证问题时，相同验证问题对应的推送分值也有所不同。
在一个实施例中，将目标验证问题推送至目标用户之后，目标用户对目标验证问题进行答题。通过获取目标用户在当前验证服务中针对目标验证问题的答题结果，可根据该答题结果更新目标验证问题的答题正确率，进而根据更新后的答题正确率更新目标验证问题的推送分值。例如，目标验证问题为问题c。假设目标用户对目标验证问题——问题c的答题结果为正确结果，则根据该答题结果对问题c的答题正确率进行更新，此时，目标用户对问题c的答题正确率被更新后有所提高。
本实施例中，能够基于目标用户对目标验证问题的答题结果对目标验证问题的答题正确率进行更新，进而更新目标验证问题的推送分值，使得验证问题的推送分值能够随着目标用户对验证问题的答题结果及时得以更新，从而使推送至目标用户的目标验证问题更加符合目标用户的答题需求，即降低目标用户答题的错误率。
综上，已经对本主题的特定实施例进行了描述。其它实施例在所附权利要求书的范围内。在一些情况下，在权利要求书中记载的动作可以按照不同的顺序来执行并且仍然可以实现期望的结果。另外，在附图中描绘的过程不一定要求示出的特定顺序或者连续顺序，以实现期望的结果。在某些实施方式中，多任务处理和并行处理可以是有利的。
以上为本说明书一个或多个实施例提供的问题推送方法，基于同样的思路，本说明书一个或多个实施例还提供一种问题推送装置。
图2是根据本说明书一实施例的一种问题推送装置的示意性框图。如图2所示，该装置包括：
第一确定模块210，确定目标用户的验证问题的特征属性；其中，特征属性包括：验证问题的答题正确率、安全程度、隐私程度中的至少一项；
第二确定模块220，根据验证问题的特征属性，确定验证问题的推送分值；
第三确定模块230，根据每个验证问题的推送分值，确定向目标用户推送的目标验证问题。
可选地，第二确定模块220包括：
第一确定单元，确定验证问题的特征属性的权值，以及，确定验证问题的特征属性的属性值；
第二确定单元，将验证问题的特征属性的权值以及属性值的加权值确定为验证问题的推送分值。
可选地，第一确定单元，根据目标用户所对应的验证服务的场景和/或业务类型，确定验证问题的特征属性的权值。
可选地，特征属性包括验证问题的答题正确率；
第一确定单元，获取目标用户在当前验证服务所对应的业务中的历史行为数据，历史行为数据包括对业务的历史使用行为信息、针对验证问题的历史答题行为信息、验证问题的答题通过率得分中的至少一项；构建指定二分类模型；将历史行为数据作为指定二分类模型的样本数据进行训练，得到验证问题的答题正确率。
可选地，历史答题行为信息包括答题结果，答题结果包括正确结果或错误结果；
上述装置还包括：
获取模块，获取目标用户在当前验证服务中针对目标验证问题的答题结果；
更新模块，根据针对目标验证问题的答题结果，更新目标验证问题的答题正确率。
可选地，特征属性包括安全程度；
第一确定单元，根据验证问题中包含的关键词，确定验证问题所携带的信息量；根据信息量确定验证问题的安全程度，其中，信息量与安全程度成正比。
可选地，特征属性包括隐私程度；
第一确定单元，确定验证问题和目标用户的个人信息之间的相关度；根据相关度确定验证问题的隐私程度，其中，相关度与隐私程度成正比。
可选地，第三确定模块230包括：
第三确定单元，将推送分值最高的验证问题确定为向目标用户推送的目标验证问题；或，
第四确定单元，将达到预设阈值的推送分值所对应的验证问题确定为向目标用户推送的目标验证问题。
采用本说明书一个或多个实施例的装置，能够确定目标用户的验证问题的特征属性(包括验证问题的答题正确率、安全程度、隐私程度中的至少一项)，根据特征属性确定验证问题的推送分值，进而根据每个验证问题的推送分值确定向目标用户推送的目标验证问题。因此，该技术方案在向用户推送验证问题时，能够兼顾目标用户的验证问题的答题正确率、安全程度和/或隐私程度，从而在采用问答形式进行身份验证时能够更加有针对性地、灵活地向用户推送验证问题，完善了验证问题的推送机制，且提升用户的答题通过率以及验证服务的安全性和隐私性，进而提升用户对验证服务的体验度。
本领域的技术人员应可理解，图2中的问题推送装置能够用来实现前文所述的问题推送方法，其中的细节描述应与前文方法部分描述类似，为避免繁琐，此处不另赘述。
基于同样的思路，本说明书一个或多个实施例还提供一种问题推送设备，如图3所示。问题推送设备可因配置或性能不同而产生比较大的差异，可以包括一个或一个以上的处理器301和存储器302，存储器302中可以存储有一个或一个以上存储应用程序或数据。其中，存储器302可以是短暂存储或持久存储。存储在存储器302的应用程序可以包括一个或一个以上模块(图示未示出)，每个模块可以包括对问题推送设备中的一系列计算机可执行指令。更进一步地，处理器301可以设置为与存储器302通信，在问题推送设备上执行存储器302中的一系列计算机可执行指令。问题推送设备还可以包括一个或一个以上电源303，一个或一个以上有线或无线网络接口304，一个或一个以上输入输出接口305，一个或一个以上键盘306。
具体在本实施例中，问题推送设备包括有存储器，以及一个或一个以上的程序，其中一个或者一个以上程序存储于存储器中，且一个或者一个以上程序可以包括一个或一个以上模块，且每个模块可以包括对问题推送设备中的一系列计算机可执行指令，且经配置以由一个或者一个以上处理器执行该一个或者一个以上程序包含用于进行以下计算机可执行指令：
确定目标用户的验证问题的特征属性；其中，所述特征属性包括：验证问题的答题正确率、安全程度、隐私程度中的至少一项；
根据所述验证问题的特征属性，确定所述验证问题的推送分值；
根据每个所述验证问题的推送分值，确定向所述目标用户推送的目标验证问题。
可选地，确定所述验证问题的特征属性的权值，以及，确定所述验证问题的特征属性的属性值；
将所述验证问题的特征属性的权值以及属性值的加权值确定为所述验证问题的 推送分值。
可选地，计算机可执行指令在被执行时，还可以使所述处理器：
根据所述目标用户所对应的验证服务的场景和/或业务类型，确定所述验证问题的特征属性的权值。
可选地，所述特征属性包括所述验证问题的答题正确率；计算机可执行指令在被执行时，还可以使所述处理器：
获取所述目标用户在当前验证服务所对应的业务中的历史行为数据，所述历史行为数据包括对所述业务的历史使用行为信息、针对所述验证问题的历史答题行为信息、所述验证问题的答题通过率得分中的至少一项；
构建指定二分类模型；
将所述历史行为数据作为所述指定二分类模型的样本数据进行训练，得到所述验证问题的答题正确率。
可选地，所述历史答题行为信息包括答题结果，所述答题结果包括正确结果或错误结果；计算机可执行指令在被执行时，还可以使所述处理器：
获取所述目标用户在当前验证服务中针对所述目标验证问题的答题结果；
根据针对所述目标验证问题的答题结果，更新所述目标验证问题的答题正确率。
可选地，所述特征属性包括所述安全程度；计算机可执行指令在被执行时，还可以使所述处理器：
根据所述验证问题中包含的关键词，确定所述验证问题所携带的信息量；
根据所述信息量确定所述验证问题的安全程度，其中，所述信息量与所述安全程度成正比。
可选地，所述特征属性包括所述隐私程度；计算机可执行指令在被执行时，还可以使所述处理器：
确定所述验证问题和所述目标用户的个人信息之间的相关度；
根据所述相关度确定所述验证问题的隐私程度，其中，所述相关度与所述隐私程度成正比。
可选地，计算机可执行指令在被执行时，还可以使所述处理器：
将所述推送分值最高的验证问题确定为向所述目标用户推送的目标验证问题；或，
将达到预设阈值的推送分值所对应的验证问题确定为向所述目标用户推送的目标验证问题。
本说明书一个或多个实施例还提出了一种计算机可读存储介质，该计算机可读存储介质存储一个或多个程序，该一个或多个程序包括指令，该指令当被包括多个应用程序的电子设备执行时，能够使该电子设备执行上述问题推送方法，并具体用于执行：
确定目标用户的验证问题的特征属性；其中，所述特征属性包括：验证问题的答题正确率、安全程度、隐私程度中的至少一项；
根据所述验证问题的特征属性，确定所述验证问题的推送分值；
根据每个所述验证问题的推送分值，确定向所述目标用户推送的目标验证问题。
上述实施例阐明的系统、装置、模块或单元，具体可以由计算机芯片或实体实现，或者由具有某种功能的产品来实现。一种典型的实现设备为计算机。具体的，计算机例如可以为个人计算机、膝上型计算机、蜂窝电话、相机电话、智能电话、个人数字助理、媒体播放器、导航设备、电子邮件设备、游戏控制台、平板计算机、可穿戴设备或者这些设备中的任何设备的组合。
为了描述的方便，描述以上装置时以功能分为各种单元分别描述。当然，在实施本说明书一个或多个实施例时可以把各单元的功能在同一个或多个软件和/或硬件中实现。
本领域内的技术人员应明白，本说明书一个或多个实施例可提供为方法、系统、或计算机程序产品。因此，本说明书一个或多个实施例可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本说明书一个或多个实施例可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本说明书一个或多个实施例是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中，计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
内存可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。内存是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、商品或者设备中还存在另外的相同要素。
本说明书一个或多个实施例可以在由计算机执行的计算机可执行指令的一般上下文中描述，例如程序模块。一般地，程序模块包括执行特定任务或实现特定抽象数据类型的例程、程序、对象、组件、数据结构等等。也可以在分布式计算环境中实践本申请，在这些分布式计算环境中，由通过通信网络而被连接的远程处理设备来执行任务。在分布式计算环境中，程序模块可以位于包括存储设备在内的本地和远程计算机存储介质中。
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于 系统实施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
以上所述仅为本说明书一个或多个实施例而已，并不用于限制本说明书。对于本领域技术人员来说，本说明书一个或多个实施例可以有各种更改和变化。凡在本说明书一个或多个实施例的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本说明书一个或多个实施例的权利要求范围之内。

Claims (18)

  1. 一种问题推送方法，包括：
    确定目标用户的验证问题的特征属性；其中，所述特征属性包括：验证问题的答题正确率、安全程度、隐私程度中的至少一项；
    根据所述验证问题的特征属性，确定所述验证问题的推送分值；
    根据每个所述验证问题的推送分值，确定向所述目标用户推送的目标验证问题。
  2. 根据权利要求1所述的方法，所述根据所述验证问题的特征属性，确定所述验证问题的推送分值，包括：
    确定所述验证问题的特征属性的权值，以及，确定所述验证问题的特征属性的属性值；
    将所述验证问题的特征属性的权值以及属性值的加权值确定为所述验证问题的推送分值。
  3. 根据权利要求2所述的方法，所述确定所述验证问题的特征属性的权值，包括：
    根据所述目标用户所对应的验证服务的场景和/或业务类型，确定所述验证问题的特征属性的权值。
  4. 根据权利要求2所述的方法，所述特征属性包括所述验证问题的答题正确率；
    相应的，确定所述验证问题的特征属性的属性值，包括：
    获取所述目标用户在当前验证服务所对应的业务中的历史行为数据，所述历史行为数据包括对所述业务的历史使用行为信息、针对所述验证问题的历史答题行为信息、所述验证问题的答题通过率得分中的至少一项；
    构建指定二分类模型；
    将所述历史行为数据作为所述指定二分类模型的样本数据进行训练，得到所述验证问题的答题正确率。
  5. 根据权利要求4所述的方法，所述历史答题行为信息包括答题结果，所述答题结果包括正确结果或错误结果；
    所述方法还包括：
    获取所述目标用户在当前验证服务中针对所述目标验证问题的答题结果；
    根据针对所述目标验证问题的答题结果，更新所述目标验证问题的答题正确率。
  6. 根据权利要求2所述的方法，所述特征属性包括所述安全程度；
    相应的，确定所述验证问题的特征属性的属性值，包括：
    根据所述验证问题中包含的关键词，确定所述验证问题所携带的信息量；
    根据所述信息量确定所述验证问题的安全程度，其中，所述信息量与所述安全程度成正比。
  7. 根据权利要求2所述的方法，所述特征属性包括所述隐私程度；
    相应的，确定所述验证问题的特征属性的属性值，包括：
    确定所述验证问题和所述目标用户的个人信息之间的相关度；
    根据所述相关度确定所述验证问题的隐私程度，其中，所述相关度与所述隐私程度成正比。
  8. 根据权利要求1所述的方法，根据每个所述验证问题的推送分值，确定向所述目标用户推送的目标验证问题，包括：
    将所述推送分值最高的验证问题确定为向所述目标用户推送的目标验证问题；或，
    将达到预设阈值的推送分值所对应的验证问题确定为向所述目标用户推送的目标验证问题。
  9. 一种问题推送装置，包括：
    第一确定模块，确定目标用户的验证问题的特征属性；其中，所述特征属性包括：验证问题的答题正确率、安全程度、隐私程度中的至少一项；
    第二确定模块，根据所述验证问题的特征属性，确定所述验证问题的推送分值；
    第三确定模块，根据每个所述验证问题的推送分值，确定向所述目标用户推送的目标验证问题。
  10. 根据权利要求9所述的装置，所述第二确定模块包括：
    第一确定单元，确定所述验证问题的特征属性的权值，以及，确定所述验证问题的特征属性的属性值；
    第二确定单元，将所述验证问题的特征属性的权值以及属性值的加权值确定为所述验证问题的推送分值。
  11. 根据权利要求10所述的装置，所述第一确定单元，根据所述目标用户所对应的验证服务的场景和/或业务类型，确定所述验证问题的特征属性的权值。
  12. 根据权利要求10所述的装置，所述特征属性包括所述验证问题的答题正确率；
    所述第一确定单元，获取所述目标用户在当前验证服务所对应的业务中的历史行为数据，所述历史行为数据包括对所述业务的历史使用行为信息、针对所述验证问题的历史答题行为信息、所述验证问题的答题通过率得分中的至少一项；构建指定二分类模型；将所述历史行为数据作为所述指定二分类模型的样本数据进行训练，得到所述验证问题的答题正确率。
  13. 根据权利要求12所述的装置，所述历史答题行为信息包括答题结果，所述答题结果包括正确结果或错误结果；
    所述装置还包括：
    获取模块，获取所述目标用户在当前验证服务中针对所述目标验证问题的答题结果；
    更新模块，根据针对所述目标验证问题的答题结果，更新所述目标验证问题的答题正确率。
  14. 根据权利要求10所述的方法，所述特征属性包括所述安全程度；
    所述第一确定单元，根据所述验证问题中包含的关键词，确定所述验证问题所携带的信息量；根据所述信息量确定所述验证问题的安全程度，其中，所述信息量与所述安全程度成正比。
  15. 根据权利要求10所述的方法，所述特征属性包括所述隐私程度；
    所述第一确定单元，确定所述验证问题和所述目标用户的个人信息之间的相关度；根据所述相关度确定所述验证问题的隐私程度，其中，所述相关度与所述隐私程度成正比。
  16. 根据权利要求9所述的装置，所述第三确定模块包括：
    第三确定单元，将所述推送分值最高的验证问题确定为向所述目标用户推送的目标验证问题；或，
    第四确定单元，将达到预设阈值的推送分值所对应的验证问题确定为向所述目标用户推送的目标验证问题。
  17. 一种问题推送设备，包括：
    处理器；以及
    被安排成存储计算机可执行指令的存储器，所述可执行指令在被执行时使所述处理器：
    确定目标用户的验证问题的特征属性；其中，所述特征属性包括：验证问题的答题正确率、安全程度、隐私程度中的至少一项；
    根据所述验证问题的特征属性，确定所述验证问题的推送分值；
    根据每个所述验证问题的推送分值，确定向所述目标用户推送的目标验证问题。
  18. 一种存储介质，用于存储计算机可执行指令，所述可执行指令在被执行时实现以下流程：
    确定目标用户的验证问题的特征属性；其中，所述特征属性包括：验证问题的答题 正确率、安全程度、隐私程度中的至少一项；
    根据所述验证问题的特征属性，确定所述验证问题的推送分值；
    根据每个所述验证问题的推送分值，确定向所述目标用户推送的目标验证问题。
PCT/CN2018/100757 2017-11-24 2018-08-16 问题推送方法及装置 Ceased WO2019100771A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711194194.3A CN109948038B (zh) 2017-11-24 2017-11-24 问题推送方法及装置
CN201711194194.3 2017-11-24

Publications (1)

Publication Number Publication Date
WO2019100771A1 true WO2019100771A1 (zh) 2019-05-31

Family

ID=66630427

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/100757 Ceased WO2019100771A1 (zh) 2017-11-24 2018-08-16 问题推送方法及装置

Country Status (3)

Country Link
CN (2) CN112182401B (zh)
TW (1) TWI697808B (zh)
WO (1) WO2019100771A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112487485A (zh) * 2020-05-09 2021-03-12 支付宝(杭州)信息技术有限公司 基于零知识证明的个人数据处理方法、装置及电子设备
CN112506903A (zh) * 2020-12-02 2021-03-16 苏州龙石信息科技有限公司 采用标本线的数据质量表示方法

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111784358A (zh) * 2020-07-31 2020-10-16 支付宝(杭州)信息技术有限公司 基于用户隐私保护的身份核实方法及装置
CN114186562B (zh) * 2020-09-14 2024-10-01 大众问问(北京)信息科技有限公司 一种语料获取方法、装置及设备
CN116346409B (zh) * 2023-01-30 2025-12-19 中国建设银行股份有限公司 网络安全防御方法、装置、设备及存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105809023A (zh) * 2014-12-29 2016-07-27 中兴通讯股份有限公司 密码验证方法及装置
CN106657164A (zh) * 2017-03-06 2017-05-10 泰华智慧产业集团股份有限公司 一种用于实名认证的身份识别复合算法及系统
CN107070871A (zh) * 2017-01-12 2017-08-18 阿里巴巴集团控股有限公司 一种身份验证的方法及装置

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4178549B2 (ja) * 2003-02-17 2008-11-12 カシオ計算機株式会社 音楽教習装置および音楽教習プログラム
CN100552680C (zh) * 2007-05-17 2009-10-21 腾讯科技（深圳）有限公司 一种知识共享系统及问题搜索方法、问题发布方法
US20100087155A1 (en) * 2008-10-06 2010-04-08 Philippe Sebastien Dubost On-premises restaurant communication system for collecting feedback
US8086951B2 (en) * 2008-10-22 2011-12-27 Appone Services, Inc. Remote web-based document creation system and method
CN102637170A (zh) * 2011-02-10 2012-08-15 北京百度网讯科技有限公司 一种问题推送方法及系统
CN102799589B (zh) * 2011-05-25 2016-05-11 阿里巴巴集团控股有限公司 一种信息推送方法和装置
CN102279889B (zh) * 2011-08-29 2017-06-30 百度在线网络技术（北京）有限公司 一种基于地理信息的问题推送方法及系统
CN104112235B (zh) * 2013-04-22 2018-05-29 中广核工程有限公司 核电项目经验反馈信息搜索的方法及系统
US20150039549A1 (en) * 2013-07-30 2015-02-05 Reccosend LLC System and method for computerized recommendation delivery, tracking, and prioritization
CN105471581B (zh) * 2014-09-10 2019-06-07 阿里巴巴集团控股有限公司 一种身份验证方法及装置
CN106295832B (zh) * 2015-05-12 2020-05-19 阿里巴巴集团控股有限公司 产品信息推送方法及装置
CN106470109A (zh) * 2015-08-21 2017-03-01 阿里巴巴集团控股有限公司 一种身份识别方法和设备
CN105068869A (zh) * 2015-09-29 2015-11-18 北京网诺星云科技有限公司 在移动终端中的信息推送的方法及装置
CN105262814A (zh) * 2015-10-21 2016-01-20 重庆微客巴巴信息技术有限公司 信息推送方法
CN105897847A (zh) * 2015-12-15 2016-08-24 乐视网信息技术（北京）股份有限公司 一种信息推送方法及信息推送装置
CN105528931B (zh) * 2016-01-18 2018-02-16 浙江工商大学 Spoc平台中基于同学参与的分段累加式习题数据库构建方法及系统
JP2017134184A (ja) * 2016-01-26 2017-08-03 株式会社ウォーカー 学習者と教材の継続評価機能をする学習支援システム
CN106897334B (zh) * 2016-06-24 2020-07-14 阿里巴巴集团控股有限公司 一种问题推送方法和设备

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105809023A (zh) * 2014-12-29 2016-07-27 中兴通讯股份有限公司 密码验证方法及装置
CN107070871A (zh) * 2017-01-12 2017-08-18 阿里巴巴集团控股有限公司 一种身份验证的方法及装置
CN106657164A (zh) * 2017-03-06 2017-05-10 泰华智慧产业集团股份有限公司 一种用于实名认证的身份识别复合算法及系统

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112487485A (zh) * 2020-05-09 2021-03-12 支付宝(杭州)信息技术有限公司 基于零知识证明的个人数据处理方法、装置及电子设备
CN112487485B (zh) * 2020-05-09 2022-12-27 支付宝(杭州)信息技术有限公司 基于零知识证明的个人数据处理方法、装置及电子设备
CN112506903A (zh) * 2020-12-02 2021-03-16 苏州龙石信息科技有限公司 采用标本线的数据质量表示方法
CN112506903B (zh) * 2020-12-02 2024-02-23 苏州龙石信息科技有限公司 采用标本线的数据质量表示方法

Also Published As

Publication number Publication date
TWI697808B (zh) 2020-07-01
CN112182401A (zh) 2021-01-05
CN112182401B (zh) 2024-03-29
CN109948038A (zh) 2019-06-28
CN109948038B (zh) 2020-09-15
TW201926087A (zh) 2019-07-01

Similar Documents

Publication Publication Date Title
US20210150415A1 (en) Feature selection method, device and apparatus for constructing machine learning model
CN107563429B (zh) 一种网络用户群体的分类方法及装置
US9779236B2 (en) Risk assessment modeling
WO2019100771A1 (zh) 问题推送方法及装置
US20160034968A1 (en) Method and device for determining target user, and network server
US11693949B2 (en) Password security warning system
US20130132360A1 (en) Iterative and dynamic search of publicly available data based on augmentation of search terms and validation of data relevance
CN104899266A (zh) 一种应用推荐方法及装置
CN104090967A (zh) 应用程序推荐方法及推荐装置
CN106951528B (zh) 一种推荐信息确定方法及装置
US10769270B2 (en) Password protection question setting method and device
US20190087859A1 (en) Systems and methods for facilitating deals
CN107256465A (zh) 风险账户的识别方法及装置
CN108932646A (zh) 基于运营商的用户标签验证方法、装置和电子设备
CN110322281A (zh) 相似用户的挖掘方法及装置
US11601509B1 (en) Systems and methods for identifying entities between networks
CN107070871A (zh) 一种身份验证的方法及装置
US20170124196A1 (en) System and method for returning prioritized content
JP6377789B1 (ja) サーバー、認証方法およびコンピュータプログラム
CN106779926A (zh) 关联规则生成方法、装置及终端
US12346426B2 (en) Computer authentication using knowledge of former devices
CN104091131B (zh) 应用程序与权限的关系确定方法及确定装置
WO2015191741A1 (en) Systems and methods for conducting relationship dependent online transactions
CN115329214A (zh) 一种用户推荐方法、装置、电子设备及存储介质
CN110062023B (zh) 一种安全教育信息推送方法、装置及设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18880393

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18880393

Country of ref document: EP

Kind code of ref document: A1