A password reminding method, device and equipment
By using a supervised and reinforcement learning-based password reminder model, the probability of users forgetting their passwords is assessed and reminders are pushed, thus solving the problem of users forgetting their passwords and improving the user experience and business success rate of password verification.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
- Filing Date
- 2020-02-10
- Publication Date
- 2026-08-04
AI Technical Summary
In existing password verification methods, users are prone to forgetting their passwords, leading to business failures, impacting user experience, and potentially causing users to stop using the service.
A password reminder model based on supervised learning and reinforcement learning is adopted. By acquiring users' historical data and current observations, the probability of forgetting the password is assessed and a password modification or verification reminder is pushed.
Proactively remind users to change their passwords, reduce the probability of forgetting them, improve the user experience of password verification, and meet the password verification needs of scenarios requiring speed and immediacy.
Smart Images
Figure CN116208331B_ABST
Abstract
Description
Technical Field
[0001] This specification relates to the field of computer technology, and in particular to a password reminder method, apparatus, and device. Background Technology
[0002] With the development of information and the internet, e-commerce is becoming increasingly widespread. Password verification is one of the most important methods of authentication and identity verification in e-commerce. Although biometric authentication technologies based on fingerprints, facial recognition, and voice are developing rapidly, password verification remains widely used. This is mainly due to factors such as usage habits, usage scenarios, and devices. For example, it is difficult to collect fingerprints on PCs, and facial or voice verification is inconvenient in noisy or crowded environments.
[0003] Current password verification methods are prone to errors, such as forgetting the password. Data shows that in e-commerce, hundreds of thousands to millions of users experience transaction failures daily due to forgotten passwords. This not only creates a negative user experience but may also lead users to stop using the service altogether.
[0004] Therefore, in order to reduce the occurrence of forgotten passwords in existing password verification, a new method is needed to reduce or minimize password forgetting. Summary of the Invention
[0005] This specification provides a password reminder method, apparatus, and device to solve the following technical problem: during the password verification process, there is a situation where the password is forgotten, which leads to business failure, causes a bad user experience, and may even cause the user to stop using the account.
[0006] To solve the above-mentioned technical problems, the embodiments in this specification are implemented as follows:
[0007] This specification provides an embodiment of a password reminder method, including:
[0008] Acquire data to be processed, wherein the data to be processed includes password usage information, and / or user account value, and / or user password usage preference information, and / or password-based time information;
[0009] The data to be processed is input into the password reminder model to obtain the password forgetting probability corresponding to the data to be processed. The password reminder model is a model for scoring the password forgetting probability that is pre-trained based on a supervised learning method.
[0010] If the probability of forgetting the password is greater than or equal to the preset probability value, a password change reminder will be sent to the user.
[0011] This specification provides an embodiment of a password reminder method, including:
[0012] Acquire the data to be processed, wherein the data to be processed includes the current observation value and the user's historical information;
[0013] The data to be processed is input into the password verification model to obtain the benefit value. The password verification reminder model is a model pre-trained based on the reinforcement learning method. The observed value includes the password forgetting probability and / or the user's password preference information.
[0014] Based on the revenue value, determine whether it is necessary to remind the user to verify their password;
[0015] If a password verification reminder needs to be sent to a user, then a password verification reminder will be pushed to that user.
[0016] This specification provides an embodiment of a password reminder device, comprising:
[0017] The acquisition module acquires data to be processed, wherein the data to be processed includes password usage information, and / or user account value, and / or user password usage preference information, and / or password-based time information;
[0018] The scoring module inputs the data to be processed into the password reminder model to obtain the password forgetting probability corresponding to the data to be processed. The password reminder model is a model for scoring the password forgetting probability that is pre-trained based on a supervised learning method.
[0019] The password change reminder module sends a password change reminder to the user if the probability of forgetting the password is greater than or equal to a preset forgetting probability value.
[0020] This specification provides an embodiment of a password reminder device, comprising:
[0021] The acquisition module acquires the data to be processed, which includes the current observation value and the user's historical information.
[0022] The revenue module inputs the data to be processed into the password verification model to obtain a revenue value. The password verification reminder model is a model pre-trained based on a reinforcement learning method. The current observation value includes the password forgetting probability and / or the user's password preference information.
[0023] The decision module determines, based on the revenue value, whether or not a password verification reminder needs to be sent to the user.
[0024] The password verification module, if it needs to remind the user to verify the password, will push a password verification reminder to the user.
[0025] An electronic device provided in the embodiments of this specification includes:
[0026] At least one processor; and,
[0027] A memory communicatively connected to the at least one processor; wherein,
[0028] The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to:
[0029] Acquire data to be processed, wherein the data to be processed includes password usage information, and / or user account value, and / or user password usage preference information, and / or password-based time information;
[0030] The data to be processed is input into the password reminder model to obtain the password forgetting probability corresponding to the data to be processed. The password reminder model is a model for scoring the password forgetting probability that is pre-trained based on a supervised learning method.
[0031] If the probability of forgetting the password is greater than or equal to the preset probability value, a password change reminder will be sent to the user.
[0032] An electronic device provided in the embodiments of this specification includes:
[0033] At least one processor; and,
[0034] A memory communicatively connected to the at least one processor; wherein,
[0035] The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to:
[0036] Acquire the data to be processed, wherein the data to be processed includes the current observation value and the user's historical information;
[0037] The data to be processed is input into the password verification model to obtain the benefit value. The password verification reminder model is a model pre-trained based on the reinforcement learning method. The observed value includes the password forgetting probability and / or the user's password preference information.
[0038] Based on the revenue value, determine whether it is necessary to remind the user to verify their password;
[0039] If a password verification reminder needs to be sent to a user, then a password verification reminder will be pushed to that user.
[0040] The above-mentioned technical solutions adopted in the embodiments of this specification can achieve the following beneficial effects: The embodiments of this specification adopt a password reminder model to obtain the password forgetting probability corresponding to the data to be processed. If the password forgetting probability is greater than or equal to the preset forgetting probability value, a password modification reminder is pushed to the user to remind them to modify the password. Through proactive reminders, the user's memory of the password is strengthened, the password forgetting probability is reduced, and the user's user experience of password verification is improved. Attached Figure Description
[0041] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0042] Figure 1 A framework diagram of a password reminder method provided in the embodiments of this specification;
[0043] Figure 2 A schematic diagram illustrating yet another data notification method provided in the embodiments of this specification;
[0044] Figure 3 A framework diagram of a password reminder method provided in the embodiments of this specification;
[0045] Figure 4 A schematic diagram of a data alert device provided in the embodiments of this specification;
[0046] Figure 5 This is a schematic diagram of yet another data alert device provided in the embodiments of this specification. Detailed Implementation
[0047] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.
[0048] In existing technologies, platforms or websites using password verification typically include "forgot password," "change password," or "reset password" functions to allow users to retrieve a new password if they forget it. However, this design involves a user-initiated, passive process of obtaining a new password. Since most users are unaware that they have forgotten their password until they perform password verification, this approach fails to meet the needs of scenarios requiring quick or immediate password verification, such as when forgetting a password while queuing to buy movie tickets.
[0049] In the embodiments described in this specification, a password refers to a password composed of one or more characters, including numeric characters and / or alphabetic characters and / or special characters. The combination of passwords and / or the number of characters in the password do not constitute a limitation on this application.
[0050] Therefore, a new method is needed to provide password reminders before users forget their passwords, in order to meet the password verification needs of quick or immediate scenarios.
[0051] Figure 1 A framework diagram of a password reminder method provided in the embodiments of this specification is shown, specifically including:
[0052] Step S101: Obtain the data to be processed, wherein the data to be processed includes password usage information, and / or user account value, and / or user password usage preference information, and / or password-based time information.
[0053] In the embodiments of this specification, the data to be processed is the data of users who need to perform password verification, used to reflect the user's historical information on password verification. The data to be processed is data related to password verification. In specific implementation, the data to be processed includes password usage information, and / or the user's account value, and / or the user's password usage preference information, and / or password-based time information, and also includes the user's static information.
[0054] In the embodiments of this specification, the password usage information in the data to be processed is based on indicators formed by the user's password usage behavior during the password verification process. In specific implementation, the user's password usage behavior includes: the frequency of using the payment password, and / or the time of the most recent password use, and / or the time of the most recent forgotten password, and / or whether the password was forgotten during the most recent password use.
[0055] In the embodiments of this specification, the user's account value includes the number of cards linked to the account, and / or the account's transaction amount, and / or the number of friends the account has, and / or the frequency of account usage.
[0056] In the embodiments of this specification, the user's password preference information in the data to be processed refers to the user's personal preference for using passwords, which may specifically include the business scenario in which the user uses passwords, and / or the user's security preference, and / or the transaction risk level of the user using passwords, and / or the equipment used for password verification.
[0057] In the embodiments of this specification, the business scenario in which a user uses a password refers to the business scenario in which a user verifies their password. In specific implementation, the business environment in which a user uses a password includes: non-real-time scenarios and real-time scenarios. Non-real-time scenarios include, for example, prepaying utility bills; real-time scenarios include, for example, queuing to buy movie tickets.
[0058] In the embodiments of this specification, the user's security preference is a characterization of the user. For example, some people are more cautious and habitually use and change their passwords, while others are more casual and their passwords may be very simple. This information can be characterized through the user's historical operation behavior.
[0059] In the embodiments of this specification, the transaction risk level of a user using a password refers to the risk level of the transaction. This risk level is generally determined by the corresponding model or strategy. For example, transactions that are not in the user's usual location, transactions that are not in the user's usual device, and abnormal high-frequency operations are all considered high-risk transactions.
[0060] In the embodiments of this specification, the device used for password verification refers to whether a mobile device or a client is used when performing password verification.
[0061] In the embodiments of this specification, password-based time information refers to information based on a user's historical password usage, and / or payment activity, and / or payment patterns. In specific implementation, password-based time information includes: the number of days since the transaction, and / or the number of days since login, password change, or account re-binding, and / or payment verification methods, and / or the number of days since large transactions.
[0062] In the embodiments of this specification, the static information of the user in the data to be processed refers to the user's basic account attributes, which are used to reflect the basic characteristics of the user or account, including the user's age, and / or the account's opening time, and / or the account's authentication time, and / or the account type. The account type specifically includes whether the account is a corporate account or a personal account, and / or whether the account is used by a single person or multiple people.
[0063] Step S103: Input the data to be processed into the password reminder model to obtain the password forgetting probability corresponding to the data to be processed, wherein the password reminder model is a model for scoring the password forgetting probability obtained by pre-training based on a supervised learning method.
[0064] In the embodiments of this specification, the password reminder model is a model that scores the probability of forgetting a password. The password reminder model is a model pre-trained based on historical data using a supervised learning method.
[0065] Supervised learning methods are machine learning tasks that infer functions from labeled training datasets.
[0066] In the embodiments of this specification, when training the password reminder model, the sample label data of the password reminder model includes black sample label data and white sample label data, wherein,
[0067] Black sample labeled data consists of data from users who reset their passwords, searched for their passwords, or lost their passwords during the historical data process.
[0068] White sample label data consists of data from historical data of users who used passwords and whose passwords were entered correctly.
[0069] In one embodiment of this specification, the black sample label data refers to the data of users who retrieved passwords via port numbers and processed business transactions by resetting their passwords in historical data.
[0070] or
[0071] Historical data includes data on users who lost access while searching for their passwords.
[0072] or
[0073] Historical data includes user data lost during the password usage process.
[0074] In the actual implementation process, the password is found through the port in the historical data. This port can be the payment port or the settings port.
[0075] Black-labeled data is marked as 1, and white-labeled data is marked as 0.
[0076] In the embodiments of this specification, the statistical period for historical data can be selected as 3 to 6 months, and the statistical period for historical data does not constitute a specific limitation on this application.
[0077] In the embodiments of this specification, the password reminder model is a model obtained based on a forgetting function and user-related information. The forgetting function is a time-based function, and the user-related information includes the user's static information, and / or password usage information, and / or user's account information, and / or user's password usage preference information and / or password-based time information.
[0078] In the embodiments of this specification, the forgetting function and user-related information are used as inputs to the model for training the password reminder model. The forgetting function is used to reprocess and enhance time-related data, determining the degree of decay or weakening of time-related data within a specific time period.
[0079] In the embodiments described in this specification, the forgetting function x1 = f(t), where t is time;
[0080] If x2 represents user-related information, then the password forgetting probability y = f(x1, x2) is the probability obtained based on the forgetting function and user-related information.
[0081] Step S105: If the password forgetting probability is greater than or equal to the preset forgetting probability value, then push a password modification reminder to the user.
[0082] Using the method provided in the preceding steps, the probability of forgetting the password corresponding to the data to be processed can be obtained. Further, it is necessary to determine whether to push a password change reminder to the user based on the preset forgetting probability value.
[0083] If the probability of forgetting the password is lower than the preset probability value, there is no need to push a password change reminder to the user; if the probability of forgetting the password is greater than or equal to the preset probability value, a password change reminder will be pushed to the user to remind them to change their password.
[0084] In the embodiments described in this specification, the selection of the preset forgetting probability value is based on: ensuring a good user experience and / or financial situation.
[0085] In one embodiment of this specification, the preset forgetting probability value is 0.8.
[0086] After receiving a password change notification, users can decide whether or not to change their password, or they can set the system to require password changes.
[0087] The data reminder method provided in the embodiments of this specification can proactively push password change reminders during user login, thereby enhancing the user's password verification experience.
[0088] Figure 2 This is a schematic diagram illustrating yet another data alert method provided in the embodiments of this specification, specifically including:
[0089] Step S201: Obtain the data to be processed, wherein the data to be processed includes password usage information, and / or user account value, and / or user password usage preference information, and / or password-based time information.
[0090] Step S203: Input the data to be processed into the password reminder model to obtain the password forgetting probability corresponding to the data to be processed, wherein the password reminder model is a model for scoring the password forgetting probability obtained by pre-training based on a supervised learning method.
[0091] Step S205: If the password forgetting probability is greater than or equal to the preset forgetting probability value, then push a password modification reminder to the user.
[0092] In the embodiments of this specification, the users who receive password change reminders are those who are prone to forgetting their passwords. In order to strengthen the user's memory of the password and thus avoid forgetting the password, after sending the password change reminder to the user, it is necessary to further send the user a password verification reminder.
[0093] Step S207: Based on the current observations and the user's historical information, obtain the reward value using the password verification model, wherein the password verification model is a model pre-trained based on a reinforcement learning method, and the current observations include the password forgetting probability and / or the user's password preference information.
[0094] In the embodiments of this specification, the current observation value is the probability of the user forgetting their password in this transaction or the current transaction, and / or the user's password preference information.
[0095] Reinforcement learning is a machine learning method that enables agents to learn through trial and error in an interactive environment, based on their own actions and experience feedback.
[0096] The basic idea of reinforcement learning is: tuples (s) consisting of (state, behavior, reward, next state) t ,a t ,r t +1 ,s t+1 ) are used as samples for training, where s t As the current state, a t For the action executed in the current state, r t+1 The reward after executing the action, s t+1 This is the next state.
[0097] In the embodiments of this specification, obtaining the password verification model includes:
[0098] The historical information, the data to be processed, and the probability of forgetting the password are used as state data.
[0099] Whether or not to use password verification will be used as a decision variable;
[0100] Calculate the revenue function corresponding to the state transition function formed by the state data and the decision variables. When the revenue function meets the preset conditions, push a password verification reminder to the user.
[0101] In one embodiment of this specification, the status data specifically includes:
[0102] Preset historical information and current observations within a historical period, among which,
[0103] The historical information within the preset historical period includes password verification and result sequences.
[0104] The observations include the probability of forgetting the current transaction password and / or user password preference information.
[0105] It should be noted that the preset historical period can be a specific time frame or the average period of password usage. In practice, the preset historical period can be set in weeks or days. The preset historical period can be 1 week, 30 days, 90 days, or 180 days. The specific length of the preset historical period does not constitute a limitation on this application.
[0106] In the embodiments of this specification, password verification in historical information refers to the decision made at each time t whether to require the user to enter a password for verification, which is pushed to the user by the business end; while the result sequence in historical information is the result of the user's password verification, i.e., the feedback information. The password verification and result sequence are sequential over the entire time interval.
[0107] In one embodiment of this specification, the state transition function is an estimate of the cryptographic verification result.
[0108] S t+1 =p t =P(a t |S t O t )
[0109] Among them, a t Indicates whether a password is required, O t S is the current observation value. t For historical information, p t This represents the probability of forgetting the password.
[0110] In the embodiments of this specification, a t It belongs to a time-related sequence and can be measured in days or hours, depending on the business scenario.
[0111] The state transition function is a probability function of the action in the current state, and it is also an estimate of the password verification result. A probability value of 1 represents a successful password verification, and a probability value of 0 represents a failed password verification.
[0112] In one embodiment of this specification, the revenue function is the gain or loss corresponding to successful or failed password verification in the current business scenario.
[0113] r t =k y *p t
[0114] Where, r t Let k be the profit function. t For risk level, p t This represents the probability of forgetting the password.
[0115] It should be noted that the payoff function takes into account the current risk level, and / or the user's security preference, and / or the transaction scenario, and ultimately obtains the corresponding gain or loss for successful or failed password verification.
[0116] Based on the method provided in the embodiments of this specification, the corresponding value obtained from the revenue function is used as the revenue value. The revenue from providing or not providing password verification reminders can be determined, thereby determining whether or not to push password verification reminders to users.
[0117] Step S209: Based on the revenue value, determine whether it is necessary to remind the user to verify their password.
[0118] The revenue value obtained from the aforementioned steps is used to reflect the revenue from providing password verification reminders or not providing them. Based on this revenue value, it can be determined whether or not a verification reminder needs to be provided to the user.
[0119] Step S211: If it is necessary to remind the user to verify the password, then push the password verification reminder to the user.
[0120] The password verification reminder method provided in the embodiments of this specification requires a comprehensive consideration of time and business scenarios in practical applications. In specific implementation, it can be applied to non-instantaneous, small-amount payment scenarios, such as prepayment of utility bills. Using password verification reminders can strengthen users' memory of their passwords, thereby avoiding or reducing the likelihood of users forgetting their passwords in the future.
[0121] The method provided in the embodiments of this specification can proactively push password change reminders to users, strengthen users' memory of passwords, reduce the probability of forgetting passwords, and improve the user experience of password verification. Password verification reminders can strengthen users' memory of passwords, thereby avoiding or reducing the degree to which users forget passwords in the future.
[0122] This specification also provides a password reminder method in its embodiments, such as... Figure 3 As shown. Figure 3 This is a framework diagram of a password reminder method provided in an embodiment of this specification. The password reminder method includes:
[0123] Step S301: Obtain the data to be processed, wherein the data to be processed includes the current observation value and the user's historical information.
[0124] In the embodiments of this specification, the current observation value is the probability of the user forgetting their password in this transaction or the current transaction, and / or the user's password preference information.
[0125] Step S303: Input the data to be processed into the password verification model to obtain the benefit value, wherein the password verification reminder model is a model pre-trained based on the reinforcement learning method, and the observed value includes the password forgetting probability and / or the user's password preference information;
[0126] Step S305: Based on the revenue value, determine whether it is necessary to remind the user to verify their password;
[0127] Step S307: If it is necessary to remind the user to verify the password, then push the password verification reminder to the user.
[0128] The above describes a data reminder method in detail. Correspondingly, embodiments of this specification also provide a data reminder device, such as... Figure 4 As shown. Figure 4 This is a schematic diagram of a data alert device provided in an embodiment of this specification. The alert device includes:
[0129] The acquisition module 401 acquires data to be processed, wherein the data to be processed includes password usage information, and / or user account value, and / or user password usage preference information, and / or password-based time information;
[0130] The scoring module 403 inputs the data to be processed into the password reminder model to obtain the password forgetting probability corresponding to the data to be processed. The password reminder model is a model for scoring the password forgetting probability that is pre-trained based on a supervised learning method.
[0131] The password change reminder module 405 pushes a password change reminder to the user if the password forgetting probability is greater than or equal to a preset forgetting probability value.
[0132] The alert device includes:
[0133] Revenue module 407, based on current observations and the user's historical information, uses a password verification model to obtain a revenue value. The password verification model is a model pre-trained using a reinforcement learning method. The current observations include the password forgetting probability and / or the user's password usage preference information.
[0134] Decision module 409 determines, based on the revenue value, whether or not a password verification reminder needs to be sent to the user.
[0135] The password verification module 411, if it needs to remind the user to verify the password, will push a password verification reminder to the user.
[0136] Furthermore, the acquisition module 401 also includes:
[0137] The data to be processed also includes the user's static information, which includes the user's age, and / or occupation, and / or account type, and / or authentication duration, and / or activation time.
[0138] Furthermore, the scoring module 403 specifically includes:
[0139] The password reminder model is a model obtained based on a forgetting function and user-related information. The forgetting function is a time-based function, and the user-related information includes the user's static information, and / or password usage information, and / or the user's account value, and / or the user's password usage preference information, and / or password-based time information.
[0140] The sample data for the password reminder model includes black sample label data and white sample label data, wherein,
[0141] The black sample label data refers to the data of users who reset their passwords, searched for their passwords, or lost their passwords during the historical data process.
[0142] The white sample label data consists of data from users who used passwords in historical data and whose passwords were entered correctly.
[0143] The black sample label data refers to the data of users who retrieved passwords via port numbers and processed business transactions by resetting their passwords in historical data.
[0144] or
[0145] Historical data includes data on users who lost access while searching for their passwords.
[0146] or
[0147] Historical data includes user data lost during the password usage process.
[0148] Furthermore, the decision module 407 specifically includes:
[0149] The training of the password verification model includes:
[0150] The user's historical information and current observations are used as state data, where the user's historical information is historical information within a preset historical period;
[0151] Whether or not to use password verification will be used as a decision variable;
[0152] Calculate the payoff function corresponding to the state transition function formed by the state data and the decision variables. The state transition function is an estimate of the password verification result.
[0153] S t+1 =p t =P(a t |S t O t )
[0154] Among them, a t Indicates whether a password is required, O t S is the current observation value. t For historical information, p t This represents the probability of forgetting the password.
[0155] The revenue function represents the revenue value corresponding to successful or failed password verification in the current business scenario. This revenue value represents either a gain or a loss.
[0156] r t =k t *p t
[0157] Where, r t Let k be the profit function. t For risk level, p t This represents the probability of forgetting the password.
[0158] This specification also provides another data alert method in its embodiments, and correspondingly, this specification also provides another data alert device, such as... Figure 5 As shown. Figure 5 This is a schematic diagram of another data alert device provided in the embodiments of this specification. The alert device includes:
[0159] The acquisition module 501 acquires the data to be processed, wherein the data to be processed includes the current observation value and the user's historical information;
[0160] The revenue module 503 inputs the data to be processed into the password verification model to obtain a revenue value. The password verification reminder model is a model pre-trained based on a reinforcement learning method. The current observation value includes the password forgetting probability and / or the user's password preference information.
[0161] Decision module 505 determines, based on the revenue value, whether or not a password verification reminder needs to be sent to the user;
[0162] The password verification module 507, if it needs to remind the user to verify the password, will push a password verification reminder to the user.
[0163] Revenue module 503 further includes:
[0164] The training of the password verification model includes:
[0165] The user's historical information and current observations are used as state data, where the user's historical information is historical information within a preset historical period;
[0166] Whether or not to use password verification will be used as a decision variable;
[0167] Calculate the payoff function corresponding to the state transition function formed by the state data and the decision variables. The state transition function is an estimate of the password verification result.
[0168] S t+1 =p t =P(a t |S t O t )
[0169] Among them, a t Indicates whether a password is required, O t S is the current observation value. t For historical information, p t This represents the probability of forgetting the password.
[0170] The revenue function represents the revenue value corresponding to successful or failed password verification in the current business scenario. This revenue value represents either a gain or a loss.
[0171] r t =k t *p t
[0172] Where, r t Let k be the profit function. t For risk level, p t This represents the probability of forgetting the password.
[0173] This specification provides an electronic device, including:
[0174] At least one processor; and,
[0175] A memory communicatively connected to the at least one processor; wherein,
[0176] The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to:
[0177] Acquire data to be processed, wherein the data to be processed includes password usage information, and / or user account value, and / or user password usage preference information, and / or password-based time information;
[0178] The data to be processed is input into the password reminder model to obtain the password forgetting probability corresponding to the data to be processed. The password reminder model is a model for scoring the password forgetting probability that is pre-trained based on a supervised learning method.
[0179] If the probability of forgetting the password is greater than or equal to the preset probability value, a password change reminder will be sent to the user.
[0180] This specification provides an embodiment of an electronic device, including:
[0181] At least one processor; and,
[0182] A memory communicatively connected to the at least one processor; wherein,
[0183] The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to:
[0184] Acquire the data to be processed, wherein the data to be processed includes the current observation value and the user's historical information;
[0185] The data to be processed is input into the password verification model to obtain the benefit value. The password verification reminder model is a model pre-trained based on the reinforcement learning method. The observed value includes the password forgetting probability and / or the user's password preference information.
[0186] Based on the revenue value, determine whether it is necessary to remind the user to verify their password;
[0187] If a password verification reminder needs to be sent to a user, then a password verification reminder will be pushed to that user.
[0188] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.
[0189] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments for apparatus, electronic devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.
[0190] The apparatus, electronic device, and non-volatile computer storage medium and method provided in the embodiments of this specification are corresponding. Therefore, the apparatus, electronic device, and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, electronic device, and non-volatile computer storage medium will not be repeated here.
[0191] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should understand that by simply performing some logic programming on the method flow using one of these hardware description languages and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.
[0192] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.
[0193] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.
[0194] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in one or more software and / or hardware.
[0195] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0196] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0197] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0198] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0199] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0200] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0201] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. 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 technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0202] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0203] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside on local and remote computer storage media, including storage devices.
[0204] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.
[0205] The above description is merely an embodiment of this specification and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.
Claims
1. A password reminder method, comprising: Acquire data to be processed, wherein the data to be processed includes password usage information, user account value, user password usage preference information, and password-based time information; The data to be processed is input into the password reminder model to obtain the password forgetting probability corresponding to the data to be processed. The password reminder model is a model that scores the password forgetting probability based on a supervised learning method and is obtained based on a forgetting function and user-related information. The forgetting function is a time-based function. If the probability of forgetting the password is greater than or equal to the preset probability value, a password change reminder will be sent to the user. Following the push notification of password change to the user, the following is also included: Based on current observations and the user's historical information, a password verification model is used to obtain a benefit value reflecting whether or not to provide a password verification reminder. Based on the benefit value, a password verification reminder is pushed to the user. The current observations include the password forgetting probability and the user's password usage preference information. The historical information includes the decision on whether to require the user to enter a password for verification and the result of the user's password verification.
2. The method as described in claim 1, wherein the password verification model is a model pre-trained based on a reinforcement learning method; The user's password preference information includes the business scenarios in which the user uses passwords; The step of pushing a password verification reminder to the user based on the revenue value includes: Based on the revenue value, determine whether it is necessary to remind the user to verify their password; If a password verification reminder needs to be sent to a user, then a password verification reminder will be pushed to that user.
3. The method as described in claim 1, wherein the data to be processed further includes the user's static information, wherein, The static information includes the user's age, and / or occupation, and / or account type, and / or authentication duration, and / or activation time.
4. The method as described in claim 1, wherein the forgetting function is a time-based function, and the user-related information includes the user's static information, and / or password usage information, and / or the user's account value, and / or the user's password usage preference information, and / or password-based time information.
5. The method as described in claim 1, wherein the sample data of the password reminder model includes black sample label data and white sample label data, wherein, The black sample label data refers to the data of users who reset their passwords, searched for their passwords, or lost their passwords during the historical data process. The white sample label data consists of data from users who used passwords in historical data and whose passwords were entered correctly.
6. The method as described in claim 5, wherein the black sample label data is data of users who retrieved passwords via port and processed business transactions by resetting passwords in historical data. or Historical data includes data on users who lost access while searching for their passwords. or Historical data includes user data lost during the password usage process.
7. The method as described in claim 2, wherein training the cryptographic verification model comprises: The user's historical information and current observations are used as state data, where the user's historical information is historical information within a preset historical period; Whether or not to use password verification will be used as a decision variable; Calculate the payoff function corresponding to the state transition function formed by the state data and the decision variables.
8. The method as described in claim 7, wherein the state transition function is an estimate of the cryptographic verification result. in, Indicate whether to use a password. For the current observation value, For historical information, This represents the probability of forgetting the password.
9. The method as described in claim 7, wherein the revenue function is the revenue value corresponding to successful or failed password verification in the current business scenario, and the revenue value is either a gain or a loss. in, For the profit function, For risk level, This represents the probability of forgetting the password.
10. A password reminder method, comprising: Acquire data to be processed, wherein the data to be processed includes current observations and user historical information, wherein the current observations are the probability of the user forgetting their password in this transaction or the current transaction and the user's password preference information, wherein the user's password preference information includes the business scenarios in which the user uses their password; The data to be processed is input into the password verification model to obtain a benefit value. The password verification model is a model pre-trained based on a reinforcement learning method. The benefit value is used to reflect the benefit of providing a password verification reminder or not providing a password verification reminder. Based on the revenue value, determine whether it is necessary to remind the user to verify their password; If a password verification reminder needs to be sent to a user, then a password verification reminder will be pushed to that user.
11. The method of claim 10, wherein training the cryptographic verification model comprises: The user's historical information and current observations are used as state data, where the user's historical information is historical information within a preset historical period; Whether or not to use password verification will be used as a decision variable; Calculate the payoff function corresponding to the state transition function formed by the state data and the decision variables.
12. The method of claim 11, wherein the state transition function is an estimate of the cryptographic verification result. in, Indicate whether to use a password. For the current observation value, For historical information, This represents the probability of forgetting the password.
13. The method as described in claim 11, wherein the revenue function is the revenue value corresponding to successful or failed password verification in the current business scenario, and the revenue value is either a gain or a loss. in, For the profit function, For risk level, This represents the probability of forgetting the password.
14. A password reminder device, comprising: The acquisition module acquires data to be processed, wherein the data to be processed includes password usage information, user account value, user password usage preference information, and password-based time information; The scoring module inputs the data to be processed into the password reminder model to obtain the password forgetting probability corresponding to the data to be processed. The password reminder model is a model for scoring the password forgetting probability obtained by pre-training based on a supervised learning method. The password reminder model is a model obtained based on a forgetting function and user-related information. The forgetting function is a time-based function. The password change reminder module pushes a password change reminder to the user if the probability of forgetting the password is greater than or equal to a preset forgetting probability value. Following the push notification of password change to the user, the following is also included: Based on current observations and the user's historical information, a password verification model is used to obtain a benefit value reflecting whether or not to provide a password verification reminder. Based on the benefit value, a password verification reminder is pushed to the user. The current observations include the password forgetting probability and the user's password usage preference information. The historical information includes the decision on whether to require the user to enter a password for verification and the result of the user's password verification.
15. A password reminder device, comprising: The acquisition module acquires data to be processed, wherein the data to be processed includes the current observation value and the user's historical information. The current observation value is the probability of the user forgetting the password in the current transaction and the user's password preference information. The user's password preference information includes the business scenario in which the user uses the password. The revenue module inputs the data to be processed into the password verification model to obtain a revenue value. The password verification model is a model pre-trained based on a reinforcement learning method. The revenue value is used to reflect the revenue from providing a password verification reminder or not providing a password verification reminder. The decision module determines, based on the revenue value, whether or not a password verification reminder needs to be sent to the user. The password verification module, if it needs to remind the user to verify the password, will push a password verification reminder to the user.
16. An electronic device comprising: At least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: Acquire data to be processed, wherein the data to be processed includes password usage information, user account value, user password usage preference information, and password-based time information; The data to be processed is input into the password reminder model to obtain the password forgetting probability corresponding to the data to be processed. The password reminder model is a model that scores the password forgetting probability based on a supervised learning method and is obtained based on a forgetting function and user-related information. The forgetting function is a time-based function. If the probability of forgetting the password is greater than or equal to the preset probability value, a password change reminder will be sent to the user. Following the push notification of password change to the user, the following is also included: Based on current observations and the user's historical information, a password verification model is used to obtain a benefit value reflecting whether or not to provide a password verification reminder. Based on the benefit value, a password verification reminder is pushed to the user. The current observations include the password forgetting probability and the user's password usage preference information. The historical information includes the decision on whether to require the user to enter a password for verification and the result of the user's password verification.
17. An electronic device comprising: At least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: Acquire data to be processed, wherein the data to be processed includes current observations and user historical information, wherein the current observations are the probability of the user forgetting their password in this transaction or the current transaction and the user's password preference information, wherein the user's password preference information includes the business scenarios in which the user uses their password; The data to be processed is input into the password verification model to obtain a benefit value. The password verification model is a model pre-trained based on a reinforcement learning method. The benefit value is used to reflect the benefit of providing a password verification reminder or not providing a password verification reminder. Based on the revenue value, determine whether a password verification reminder needs to be sent to the user; if a password verification reminder needs to be sent to the user, then push a password verification reminder to the user.