A business risk control method, device, storage medium and electronic device

Abstract

This specification discloses a business risk control method, device, storage medium and electronic device. The embodiments of this specification determine the proportion of each guide character in the guide character set based on the number of users in the user group to be risk controlled, and send the guide character set and risk survey information that meet the proportion to the client of each user. Each client returns a response result for the risk survey information determined based on the guide character randomly extracted from the guide character set. The server determines the risk probability of the user group based on the response result and the expected character for the guide character set, and performs risk control on the business performed by each user based on the risk probability. In this method, the server cannot know the guide character extracted by the client, and thus cannot know whether a single user is at risk, and each user responds in the form of characters rather than directly in text, so that attackers cannot obtain the user's accurate response to the survey questions, thereby protecting the user's privacy.

Description

Technical Field

[0001] This specification relates to the field of computers, and in particular to a business risk control method, device, storage medium, and electronic device. Background Art

[0002] In a risk control scenario, a sampling survey can be conducted on the user group that performs business to determine whether the surveyed user group faces risks when performing business.

[0003] Currently, when conducting surveys on user groups, user privacy is easily leaked. Therefore, there is an urgent need for a method to perform business risk control on user groups while protecting user privacy. Summary of the Invention

[0004] The embodiments of this specification provide a business risk control method, device, storage medium and electronic device to partially solve the problems existing in the above-mentioned prior art.

[0005] The embodiments of this specification adopt the following technical solutions:

[0006] This specification provides a business risk control method, which is applied to a server and includes:

[0007] Identify the user groups to be risk-controlled;

[0008] determining, based on the number of users in the user group, a proportion of each guide character in the guide character set, wherein the guide characters are used to guide the information that users can respond to when answering the risk survey information;

[0009] Sending a guide character set that meets the proportion and risk investigation information to a client used by each user in the user group;

[0010] receiving a response result to the risk survey information returned by each user in the user group through the client used, wherein the response result returned by each user is determined based on a guide character randomly selected from the guide character set by the client used by the user;

[0011] determining the risk probability corresponding to the user group according to a response result returned by each user through the client used and the expected characters for the guide character set determined based on the proportion;

[0012] Perform risk control on the business performed by the user group based on the risk probability.

[0013] Optionally, determining the proportion of each guide character in the guide character set according to the number of users in the user group specifically includes:

[0014] The proportion of each guide character in the guide character set is determined based on the number of users in the user group, a first preset parameter, and a second preset parameter, wherein the first preset parameter is used to represent a privacy budget involved in a risk survey of the user group, and the second preset parameter is used to represent a variance of the risk probability corresponding to the user group determined under the first preset parameter.

[0015] Optionally, determining the risk probability corresponding to the user group according to the response result returned by each user through the client used and the expected character for the guide character set determined based on the proportion specifically includes:

[0016] Based on the proportion of each guide character in the guide character set, performing weighted summation on each guide character to obtain an expected character for the guide character set;

[0017] Averaging the response results returned by each user through the client used to obtain the mean of all response results;

[0018] The risk probability corresponding to the user group is determined according to the expected characters of the guide character set, the average of all the response results, and the number of types of each guide character.

[0019] Optionally, risk control is performed on the business executed by the user group based on the risk probability, specifically including:

[0020] If the risk probability is greater than a risk threshold, the service executed by each user in the user group is blocked or an alarm is issued for the service executed by each user in the user group.

[0021] This specification provides a business risk control method, which is applied to the client of each user to be risk-controlled, and includes:

[0022] Receiving risk investigation information and a guide character set sent by the server, wherein the proportion of each guide character in the guide character set is determined by the number of users in the user group to be risk controlled;

[0023] randomly extracting a guide character from the guide character set, and determining a response result for the risk survey information based on the extracted guide character;

[0024] The response result is returned to the server, so that the server determines the risk probability corresponding to the user group based on the response result received from each user in the user group through the client used and the expected characters for the guide character set determined based on the proportion, so as to perform risk control on the business performed by the user group according to the risk probability.

[0025] Optionally, determining a response result to the risk investigation information based on the extracted guide character specifically includes:

[0026] If it is determined that the user using the client has risk attributes, the extracted guide characters are processed according to the number of types of each guide character to obtain processed characters as a response result to the risk investigation information.

[0027] Optionally, the extracted guide characters are processed according to the number of types of each guide character to obtain processed characters, specifically including:

[0028] The number of each type of guide characters is summed with the third preset parameter to obtain an initial character;

[0029] The difference between the initial character and the extracted guide character is used as the processed character.

[0030] Optionally, determining a response result to the risk investigation information based on the extracted guide character specifically includes:

[0031] If it is determined that the user using the client does not have the risk attribute, the extracted guide character is used as a response result to the risk investigation information.

[0032] Optionally, randomly extracting a guide character from the guide character set specifically includes:

[0033] Deleting the guide characters sent by other clients from the guide character set and re-determining the guide character set; wherein the guide characters sent by other clients are guide characters randomly selected by the other clients from the guide character set sent by the server;

[0034] A guide character is randomly drawn from the re-determined guide character set.

[0035] This specification provides a business risk control system, which includes: a server, a plurality of clients of users to be risk controlled;

[0036] The server is configured to determine a user group to be risk-controlled, determine a proportion of each guide character in a guide character set based on the number of users in the user group, the guide characters being used to guide the information that a user can reply to when responding to risk survey information, and send a guide character set that satisfies the proportion and the risk survey information to a client used by each user in the user group;

[0037] The client is configured to receive the risk investigation information and the guide character set sent by the server, randomly extract a guide character from the guide character set, and determine a response result for the risk investigation information based on the extracted guide character, and return the response result to the server;

[0038] The server is configured to receive a response result regarding the risk survey information returned by each user in the user group through the client used, determine a risk probability corresponding to the user group based on the response result returned by each user through the client used and the expected characters for the guide character set determined based on the proportion; and perform risk control on the business performed by the user group based on the risk probability.

[0039] Optionally, the server is configured to determine the proportion of each guide character in the guide character set based on the number of users in the user group, a first preset parameter, and a second preset parameter, wherein the first preset parameter is used to represent a privacy budget involved in a risk survey of the user group, and the second preset parameter is used to represent a variance of the risk probability corresponding to the user group determined under the first preset parameter.

[0040] Optionally, the server is specifically configured to perform weighted summation on each guide character based on the proportion of each guide character in the guide character set to obtain an expected character for the guide character set; average the response results returned by each user through the client used to obtain a mean value for all response results; and determine the risk probability corresponding to the user group based on the expected character for the guide character set, the mean value for all response results, and the number of types of each guide character.

[0041] Optionally, the client is specifically configured to process the extracted guide characters according to the number of types of each guide character if it is determined that the user using the client has risk attributes, and obtain processed characters as a response result to the risk investigation information.

[0042] Optionally, the client is specifically configured to use the extracted guide character as a response result to the risk investigation information if it is determined that the user using the client does not have the risk attribute.

[0043] Optionally, the client is specifically used to delete the guide characters sent by other clients from the guide character set and redetermine the guide character set; wherein the guide characters sent by the other clients are guide characters randomly selected from the guide character set sent by the other clients from the server; and the guide characters are randomly selected from the redetermined guide character set.

[0044] This specification provides a business risk control device, including:

[0045] The first determination module determines the user group to be risk-controlled;

[0046] a second determining module, configured to determine, based on the number of users in the user group, a proportion of each guiding character in the guiding character set, wherein the guiding characters are used to guide the information that users can reply to when answering the risk survey information;

[0047] a sending module, configured to send a guide character set that satisfies the proportion and risk investigation information to a client used by each user in the user group;

[0048] a receiving module, configured to receive a response result to the risk survey information returned by each user in the user group through the client used, wherein the response result returned by each user is determined based on a guide character randomly drawn from the guide character set by the client used by the user;

[0049] a third determining module, configured to determine the risk probability corresponding to the user group according to a response result returned by each user through the client used and the expected characters for the guide character set determined based on the proportion;

[0050] The risk control module is used to perform risk control on the business performed by the user group according to the risk probability.

[0051] This specification provides a business risk control device, including:

[0052] a receiving module, configured to receive risk investigation information and a guide character set sent by a server, wherein a proportion of each guide character in the guide character set is determined by the number of users in the user group to be risk controlled;

[0053] a determination module, configured to randomly extract a guide character from the guide character set and determine a response result for the risk survey information based on the extracted guide character;

[0054] The risk control module is used to return the response result to the server, so that the server determines the risk probability corresponding to the user group based on the response result returned by each user in the user group through the client used and the expected characters for the guide character set determined based on the proportion, so as to perform risk control on the business performed by the user group according to the risk probability.

[0055] This specification provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned business risk control method.

[0056] This specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned business risk control method is implemented.

[0057] At least one of the above technical solutions adopted in the embodiments of this specification can achieve the following beneficial effects:

[0058] In the embodiment of this specification, after determining the user group to be risk controlled, the proportion of each guide character in the guide character set is determined based on the number of users in the user group. A guide character set and risk survey information that meets the proportion are sent to the client of each user. Each client determines the response result for the risk survey information based on the guide characters randomly extracted from the guide character set, and returns it to the server. The server determines the risk probability of the user group based on the returned response result and the expected characters for the guide character set, and performs risk control on the business performed by each user based on the risk probability. In this method, the server cannot know the guide characters extracted by the client, and thus cannot know whether a single user is at risk, and each user responds in the form of characters rather than directly in text. In this way, attackers cannot obtain the user's accurate response to the survey questions, thereby protecting the user's privacy. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The exemplary embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation of this specification. In the drawings:

[0060] Figure 1 This is a schematic diagram of the interaction of the business risk control system provided in the embodiments of this specification;

[0061] Figure 2 A flowchart of a business risk control method provided in an embodiment of this specification;

[0062] Figure 3 A flowchart of another business risk control method provided in the embodiments of this specification;

[0063] Figure 4 A schematic diagram of the structure of a business risk control device provided in an embodiment of this specification;

[0064] Figure 5 A schematic diagram of the structure of another business risk control device provided in the embodiments of this specification;

[0065] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0066] The method based on the question investigation part provided in this specification can conduct a sensitive question investigation on the user group without the server knowing the real attributes of each user, so as to count the proportion of users with sensitive attributes in the user group. Among them, sensitive attributes can refer to attributes that represent user privacy information, such as: cheating, illness, fraud and other sensitive attributes. In the risk control scenario, the sensitive attribute of the user can be a risk attribute, such as: fraud. The server can perform risk control on the business performed by each user in the user group based on the proportion of risk attributes in the user group; in the medical scenario, the sensitive attribute of the user can be illness. The server can recommend medical information to each user in the user group based on the proportion of sensitive attributes in the user group.

[0067] To make the objectives, technical solutions, and advantages of this specification more clear, the following will clearly and completely describe the technical solutions of this specification in conjunction with the specific embodiments of this specification and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this specification.

[0068] The technical solutions provided by the various embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0069] In this specification, taking the risk control scenario as an example, it is possible to predict whether a user group has the risk of gang fraud. If gang fraud exists, risk control is performed on the business performed by this user group.

[0070] Figure 1 This is a diagram illustrating the interaction of a business risk control system provided in an embodiment of this specification. The business risk control system includes: a server and multiple client terminals of users to be risk-controlled. The users to be risk-controlled can be randomly selected or users with a high probability of fraud determined based on historical business data.

[0071] The server may first determine a user group to be risk-controlled. The users in the user group may be randomly selected from users performing business operations, or may be users whose fraud probability is greater than a threshold, as determined based on historical business data. Businesses performed by users may include lending, payment transactions, and the like.

[0072] The server can then determine the proportion of each guide character in the guide character set based on the number of users in the determined user group. The server then sends the guide character set that satisfies this proportion, along with risk survey information, to the client used by each user in the user group. The guide characters guide the user's responses to the risk survey information. The guide characters can represent numbers, and each guide character can represent a numerical value. The risk survey information can include survey questions regarding whether the business performed by the user is risky.

[0073] For any client used by a user undergoing risk control, the client receives the guide character set and risk investigation information from the server. It then randomly extracts a guide character from the set and, based on the extracted guide character, determines a response to the risk investigation information. Finally, the response is returned to the server. During this process, only the client knows which guide character was extracted; the server remains unaware.

[0074] The server may receive responses to the risk survey information from each user's client and determine the risk probability for the user group to be risk-controlled based on the responses from each user's client and the expected characters for the guide character set determined based on the percentage. The risk probability represents the probability that the user group as a whole is at risk.

[0075] After determining the risk probability corresponding to the user group to be risk-controlled, the server can perform risk control on the services executed by the user group based on the risk probability. If the risk probability exceeds the risk threshold, the server blocks the services executed by each user in the user group or issues an alert for the services executed by each user in the user group.

[0076] Next, the business risk control method in this manual is described with the server and client as the execution entities respectively.

[0077] Figure 2 This is a flow chart of a business risk control method provided in an embodiment of this specification. The business risk control method can be applied to a server, including:

[0078] S200: Determine the user group to be risk-controlled.

[0079] In this specification, the implementation process of a server conducting a survey on users without leaking their privacy is as follows: the server sends a set of numbers consisting of different numbers to the clients used by the users being surveyed, and each client receives the same set of numbers. For each client, the client randomly draws a number from the received set of numbers, and returns a number to the server based on whether the user using the client has risk attributes. The server performs statistical calculations based on the numbers returned by each client to determine the proportion of users with risk attributes among all surveyed users. In this process, the server can only obtain the numbers replied by the user, but cannot know the numbers drawn by the user, which can prevent the server from knowing the actual attributes of each user. For attackers, the attacker can only obtain the numbers replied by the user to the server, but cannot determine the actual attributes of the user based on the numbers replied alone, thereby protecting user privacy.

[0080] In the embodiments of this specification, in a risk control scenario, the server may first identify users performing designated services. These designated services may include lending services, payment transactions, and the like. Then, based on each user's historical service data, the server may determine the corresponding fraud probability for each user. Subsequently, users with a fraud probability exceeding a probability threshold may be selected from the users and included as the user group for risk control.

[0081] In addition, after determining the users who perform the specified business, the server can randomly select a specified number of users from the users as the user group to be risk controlled.

[0082] S202: Determine the proportion of each guide character in the guide character set according to the number of users in the user group, where the guide characters are used to guide the information that users can reply when answering risk survey information.

[0083] In an embodiment of this specification, after determining the user group to be risk-controlled, the proportion of each guide character in the guide character set can be determined based on the number of users in the user group. The guide characters are used to guide the user's responses to the risk survey information. The guide characters can represent numbers, and each guide character can represent a numerical value. The information that the user can respond to the risk survey information can represent numbers. Furthermore, the guide character set contains at least three types of guide characters.

[0084] When determining the proportion of each guide character in the guide character set, the proportion of each guide character in the guide character set can be determined based on the number of users in the user group, the first preset parameter, and the second preset parameter. The first preset parameter is used to represent the privacy budget involved in the risk investigation process of the user group, and the second preset parameter is used to represent the variance of the risk probability corresponding to the user group determined under the first preset parameter. In addition, the smaller the first preset parameter, the better the privacy protection during the risk investigation of the user group, but the worse the availability of the risk probability corresponding to the user group. Therefore, it is necessary to strike a balance between the degree of privacy protection and the availability of the risk probability based on actual conditions, that is, the first preset parameter cannot be zero. The smaller the second preset parameter, the more accurate the risk probability corresponding to the determined user group.

[0085] When determining the proportion of each guide character in the guide character set, the proportion of a specified guide character in the guide character set can be determined based on the number of users in the user group, the first preset parameter, and the second preset parameter. Then, based on the determined proportion of the specified guide character in the guide character set and the relationship between the proportions of different guide characters in the guide character set, the proportion of each guide character in the guide character set can be determined.

[0086] The relationship between the number of users in the user group, the first preset parameter, the second preset parameter, and the proportion of the designated guide character in the guide character set is shown in the following formula: or represents the variance of the risk probability for the user group, i.e., the second preset parameter, represents the estimated risk probability of the user group, N represents the number of users in the user group to be risk-controlled, ε represents the privacy budget, that is, the first preset parameter, and P2 can represent the proportion of the second type of guide character in the guide character set, that is, the proportion of the specified guide character in the guide character set. A It can be expressed that the maximum risk probability for the user group is obtained through simulation experiments. When determining the proportion of each guide character in the guide character set, π A is a constant.

[0087] The relationship between the proportions of different guide characters is as follows: or, {1 can represent the proportion of the first type of guide character in the guide character set, and P3 can represent the proportion of the third type of guide character in the guide character set. After determining P2, the proportion of each type of guide character in the guide character set can be determined based on the above relationship, that is, P1 and P3 are determined.

[0088] S204: Sending a guide character set that meets the proportion and risk investigation information to a client used by each user in the user group.

[0089] S206: Receive a response result to the risk survey information returned by each user in the user group through the client used. For each user, the response result returned by the user is determined based on a guide character randomly drawn from the guide character set by the client used by the user.

[0090] In an embodiment of the present specification, after determining the proportion of each guide character in the guide character set, the server can send a guide character set and risk survey information that meets the proportion to the client used by each user in the user group, so that the client randomly selects a guide character from the guide character set to determine the response result to the risk survey information.

[0091] When the user group randomly extracts the guide character, in the first case, the client used by each user in the user group can randomly extract the guide character from the guide character set sent by the server without interfering with each other. In the second case, the clients used by each user can interfere with each other, and the client used by each user can randomly extract a guide character from the remaining guide characters in the guide character set in turn.

[0092] For these two situations, the server sends the boot character set and risk investigation information to the user group in different ways.

[0093] For the first case:

[0094] The server may simultaneously send a guide character set and risk investigation information that satisfies the proportion to the client used by each user in the user group.

[0095] Any client in the user group receives the guide character set and risk survey information from the server. The client then randomly extracts a guide character from the guide character set and, based on the extracted guide character, determines a response to the risk survey information. Finally, the response is returned to the server.

[0096] For the second case:

[0097] After determining the user group to be risk-controlled, the server can send the communication information corresponding to the client used by each user in the user group to each client in the user group. The communication information may include the identifier and network address of the client used by each user.

[0098] When sending the risk survey information and the boot character set, the server may first determine the order in which to send the risk survey information and the boot character set to the client used by each user in the user group. Then, according to the determined order, the server sequentially sends the boot character set and risk survey information that satisfies the specified percentage to the client used by each user. The server sends the same boot character set to each client.

[0099] For any client used by a user in the user group, the client can first receive pilot characters sent by other clients. After receiving the pilot character set and risk investigation information sent by the server, the client can remove the pilot characters sent by the other clients from the pilot character set sent by the server and redefine the pilot character set after removing the pilot characters sent by the other clients. The client can then randomly select a pilot character from the redefined pilot character set and, based on the selected pilot character, determine a response to the risk investigation information. Finally, the response is returned to the server. The pilot characters sent by the other clients are randomly selected from the pilot character set sent by the server. After the client randomly selects a pilot character from the redefined pilot character set, the client can send the selected pilot character to other clients other than itself, causing the other clients to remove the received pilot character from the pilot character set sent by the server. Alternatively, after the client randomly selects a pilot character from the redefined pilot character set, the client can send the selected pilot character to other clients that did not select the selected pilot character, causing the other clients to remove the received pilot character from the pilot character set sent by the server.

[0100] Regardless of the first or second case, the server may receive a response result regarding the risk investigation information returned by each user in the user group through the client used.

[0101] S208: Determine the risk probability corresponding to the user group according to the response result returned by each user through the client used and the expected characters for the guide character set determined based on the proportion.

[0102] S210: Perform risk control on the business executed by the user group according to the risk probability.

[0103] In the embodiment of this specification, after receiving the response result returned by each client, the server can determine the risk probability corresponding to the user group according to the response result returned by each user through the client used and the expected character for the guide character set.

[0104] When determining the expected character for the guide character set, each guide character may be weighted and summed based on the proportion of each guide character in the guide character set to obtain the expected character for the guide character set (ie, the expected value).

[0105] The formula for determining the expected character for the leading character set is: k represents the kth type of guide character, and the number represented by the guide character is k.

[0106] To determine the risk probability for a user group, the responses returned by each user through their client can be averaged to obtain a mean value for all responses. The risk probability for the user group can then be determined based on the expected characters in the guide character set, the mean value for all responses, and the number of each type of guide character.

[0107] The formula for determining the risk probability of a user group is: represents the mean of all response results, X i Indicates the response result of the i-th user's reply.

[0108] After determining the risk probability corresponding to the user group, the server can perform risk control on the business (or designated business) performed by the user group based on the risk probability.

[0109] Specifically, if the risk probability of a user group is greater than the risk threshold, the services executed by each user in the user group are blocked or an alarm is issued for the services executed by each user in the user group. If the risk probability of the user group is not greater than the risk threshold, the services required by each user in the user group continue to be executed.

[0110] Figure 3 This is a flow chart of another business risk control method provided in an embodiment of this specification. This business risk control method can be applied to any client used by a user to be risk controlled, including:

[0111] S300: Receive risk investigation information and a guide character set sent by a server, wherein the proportion of each guide character in the guide character set is determined by the number of users in the user group to be risk controlled.

[0112] S302: randomly extracting a guide character from the guide character set, and determining a response result for the risk survey information based on the extracted guide character.

[0113] In the embodiment of the present specification, after the server determines the user group to be risk controlled, the server may determine the proportion of each guide character in the guide character set according to the number of users in the user group.

[0114] For the first case, the server can simultaneously send a set of guiding characters that meet the ratio and risk survey information to the client used by each user in the user group. The guiding characters are used to guide the user in answering the risk survey information.

[0115] In the first scenario, the clients used by each user in the user group do not interfere with each other when extracting pilot characters. Each client receives the risk survey information and the pilot character set from the server. The client then randomly extracts pilot characters from the server's pilot character set and, based on the extracted pilot characters, determines a response to the risk survey information.

[0116] When determining the response result to the risk investigation information, if the client determines that the user using the client has a risk attribute, the client may process the extracted guide characters based on the number of types of each guide character to obtain processed characters, and use the processed characters as the response result to the risk investigation information. The risk attribute may indicate an attribute of the user that is risky, such as fraud, low credit, etc.

[0117] When determining the processed character, the number of each type of guide character may be summed with a third preset parameter to obtain the initial character, where the third preset parameter may be 1. The difference between the initial character and the extracted guide character is then used as the processed character.

[0118] The formula for determining the processed character is: L+1-k. L represents the number of each type of guide character, 1 is the third preset parameter, k represents the guide character extracted by the client, and L+1 represents the initial character.

[0119] If the client determines that the user using the client does not have the risk attribute, the client can directly use the guide character extracted by the client as the response result for the risk investigation information.

[0120] For example, if the number of each type of guide character in the guide character set is 3, and the guide character randomly drawn by the client is 1, assuming the user has a risk attribute, the response result is 3. If the user does not have a risk attribute, the response result is 1.

[0121] For the second scenario, after determining the user group to be risk-controlled, the server can send the communication information corresponding to the client used by each user in the user group to each client in the user group. When sending the risk investigation information and the guidance character set, the server can sequentially send the guidance character set and risk investigation information that meet the specified ratio to each client used by each user in the user group.

[0122] In the second case, the clients used by each user in the user group interfere with each other when extracting the guide characters. For the client used by any user, the client can first receive the guide characters sent by other clients except itself. After receiving the risk investigation information and the guide character set sent by the server, the guide characters sent by other clients can be deleted from the guide character set sent by the server, and the guide character set after deleting the guide characters sent by other clients can be re-determined. Then, the client randomly extracts a guide character from the re-determined guide character set, and based on the extracted guide character, determines the response result to the risk investigation information. Among them, the guide characters sent by other clients are guide characters randomly extracted by other clients from the guide character set sent by the server. After the client randomly extracts a guide character from the re-determined guide character set, the client can send the extracted guide character to other clients except itself, so that other clients will delete the received guide character from the guide character set sent by the server. Alternatively, after the client randomly extracts a pilot character from the re-determined pilot character set, the client may send the extracted pilot character to other clients that have not extracted the pilot character, so that the other clients delete the received pilot character from the pilot character set sent by the server.

[0123] It should be noted that in the second case, the client determines the response result to the risk investigation information based on the extracted guide characters in the same way as in the first case.

[0124] S304: Return the response result to the server, so that the server determines the risk probability corresponding to the user group based on the response result received from each user in the user group through the client used and the expected characters for the guide character set determined based on the proportion, so as to perform risk control on the business performed by the user group according to the risk probability.

[0125] In an embodiment of the present specification, for the client used by each user in the user group, after determining the response result to the risk survey information, the client can return the response result to the server, so that the server can determine the risk probability corresponding to the user group based on the response result returned by the client used by each user and the expected character for the guide character set determined based on the proportion of each guide character in the guide character set, so as to perform risk control on the business performed by the user group according to the risk probability.

[0126] In the second case, a client may be attacked when sending a guide character to another client, resulting in the leakage of the guide character. Similarly, when the client returns a response result to the server, the response result may also be leaked, which may lead to the leakage of the privacy of the user of this client. Therefore, in the second case, for the client used by each user in the user group, the client can encrypt the response result, obtain the ciphertext for the response result, and return the ciphertext to the server. The server decrypts the received ciphertext to obtain the response result returned by the client used by each user, and determines the risk probability corresponding to the user group based on the response result returned by the client used by each user and the expected character for the guide character set determined based on the proportion of each guide character in the guide character set, so as to perform risk control on the business performed by the user group according to the risk probability.

[0127] Through the above Figure 2 and Figure 3 As can be seen from the method shown, after determining the user group to be risk controlled, this manual determines the proportion of each guide character in the guide character set based on the number of users in the user group. A guide character set and risk survey information that meets the proportion are sent to the client of each user. Each client determines the response result for the risk survey information based on the guide characters randomly extracted from the guide character set, and returns it to the server. The server determines the risk probability of the user group based on the returned response result and the expected characters for the guide character set, and performs risk control on the business performed by each user based on the risk probability. In this method, the server cannot know the guide characters extracted by the client, and thus cannot know whether a single user is at risk, and each user responds in the form of characters rather than directly in text. In this way, attackers cannot obtain the user's accurate response to the survey questions, thereby protecting the user's privacy.

[0128] In addition, in step S202 and step S210, the risk probability formula for the user group and the variance formula for the risk probability for the user group are derived as follows: When the user in the user group determines the response result, if the user has the risk attribute, then the user replies L+1-k, and if the user does not have the risk attribute, then the user replies k. Where k is the number represented by the randomly selected guide character. Therefore, when the user replies k, the probability that the user randomly extracts the guide character k is P k , the probability that the user randomly extracts the L+1-k guide character is P L+1―k .

[0129] The expected response result for the reply is: X i represents the response result of the i-th user, and Y represents the number represented by the guide character randomly drawn by the user.

[0130] π a Perform unbiased estimation to obtain the risk probability formula for the user group

[0131] When each user in the user group randomly extracts the guide character without interfering with each other, the variance of the risk probability for the user group is: When each user in the user group interferes with each other when randomly extracting the guide character, the variance of the risk probability for the user group is:

[0132] Under the condition that each user in the user group randomly extracts a guide character without interfering with each other, taking three guide characters as an example, the first guide character accounts for P1 in the guide character set, and the number represented by the first guide character is 1, the second guide character accounts for P2 in the guide character set, and the number represented by the second guide character is 2, and the third guide character accounts for P3 in the guide character set, and the number represented by the third guide character is 3. Calculated by the expectation formula and the variance formula, we get: E(Y) = 3-2P1-P2, D(Y) = 4P1+P2-4P1 2 -P2 2 -4P1P2, substitute into the variance formula of risk probability for the user group, and we get by As a constraint, solve f(P1,P2)→∞. Finally, we get therefore,

[0133] When each user in the user group randomly extracts the guide character and interferes with each other,

[0134] X i =(L+1―Y i )x i +Y i (1-x i ).x i It can be 0 or 1. When the user has risk attributes, x i is 1, when the user does not have risk attributes, x i is 0. i Indicates the number represented by the guide character extracted by the i-th user.

[0135] X i =(L+1―k)x i +k(1―xi ) get

[0136] Traverse m and n and finally get

[0137]

[0138] Substituting the above formula into as well as Finally got D

[0139]

[0140] The above is the business risk control method provided in the embodiments of this specification. Based on the same idea, this specification also provides corresponding devices, storage media and electronic devices.

[0141] Figure 4 This is a schematic diagram of the structure of a business risk control device provided in an embodiment of this specification, the device comprising:

[0142] The first determination module 401 is used to determine the user group to be risk-controlled;

[0143] A second determining module 402 is configured to determine, based on the number of users in the user group, a proportion of each type of guiding character in the guiding character set, wherein the guiding characters are used to guide the information that users can reply to when answering the risk survey information;

[0144] A sending module 403 is configured to send a guide character set that satisfies the proportion and risk investigation information to a client used by each user in the user group;

[0145] a receiving module 404 configured to receive a response result regarding the risk survey information returned by each user in the user group through the client used, wherein the response result returned by each user is determined based on a guide character randomly selected from the guide character set by the client used by the user;

[0146] The third determining module 405 is configured to determine the risk probability corresponding to the user group according to the response result returned by each user through the client used and the expected characters for the guide character set determined based on the proportion;

[0147] The risk control module 406 is configured to perform risk control on the services executed by the user group according to the risk probability.

[0148] Optionally, the second determination module 402 is specifically used to determine the proportion of each guide character in the guide character set based on the number of users in the user group, a first preset parameter and a second preset parameter, wherein the first preset parameter is used to represent the privacy budget involved in the risk investigation process of the user group, and the second preset parameter is used to represent the variance of the risk probability corresponding to the user group determined under the first preset parameter.

[0149] Optionally, the third determination module 405 is used to perform weighted summation of each guide character based on the proportion of each guide character in the guide character set to obtain the expected character for the guide character set; average the response results returned by each user through the client used to obtain the mean of all response results; and determine the risk probability corresponding to the user group based on the expected character for the guide character set, the mean of all response results, and the number of types of each guide character.

[0150] Optionally, the risk control module 406 is specifically configured to block the business executed by each user in the user group or issue an alarm for the business executed by each user in the user group if the risk probability is greater than a risk threshold.

[0151] Figure 5 This is a schematic diagram of the structure of another business risk control device provided in an embodiment of this specification, the device comprising:

[0152] A receiving module 501 is configured to receive risk investigation information and a guide character set sent by a server, wherein the proportion of each guide character in the guide character set is determined by the number of users in the user group to be risk controlled;

[0153] A determination module 502 is configured to randomly extract a guide character from the guide character set and determine a response result for the risk survey information based on the extracted guide character;

[0154] The risk control module 503 is used to return the response result to the server, so that the server can determine the risk probability corresponding to the user group based on the response result returned by each user in the user group through the client used and the expected characters for the guide character set determined based on the proportion, so as to perform risk control on the business performed by the user group according to the risk probability.

[0155] Optionally, the determination module 502 is specifically configured to, if it is determined that the user using the client has risk attributes, process the extracted guide characters according to the number of types of each guide character to obtain processed characters as a response result to the risk investigation information.

[0156] Optionally, the determining module 502 is specifically configured to sum the number of types of each guide character and a third preset parameter to obtain an initial character; and use the difference between the initial character and the extracted guide character as the processed character.

[0157] Optionally, the determining module 502 is specifically configured to, if it is determined that the user using the client does not have a risk attribute, use the extracted guide character as a response result to the risk investigation information.

[0158] Optionally, the determination module 502 is specifically used to delete the guide characters sent by other clients from the guide character set and redetermine the guide character set; wherein the guide characters sent by the other clients are guide characters randomly selected from the guide character set sent by the other clients from the server; and randomly select the guide characters from the redetermined guide character set.

[0159] This specification also provides a computer-readable storage medium, wherein the storage medium stores a computer program, which can be used to perform the above-mentioned Figure 2 and Figure 3 Provided business risk control methods.

[0160] based on Figure 2 and Figure 3 The business risk control method shown in this specification also provides Figure 6 The structural diagram of the electronic device shown in FIG. Figure 6 At the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory. Of course, it may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 2 and Figure 3 The business risk control method described.

[0161] Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0162] In the 1990s, technological improvements could be clearly distinguished as either hardware improvements (for example, improvements to circuit structures like diodes, transistors, and switches) or software improvements (improvements to process flows). However, with the advancement of technology, many process flow improvements today can now be considered direct improvements to hardware circuit structures. Designers almost always create the corresponding hardware circuit structure by programming the improved process flow into the hardware circuit. Therefore, it cannot be said that a process flow improvement cannot be implemented using hardware modules. For example, a programmable logic device (PLD), such as a field programmable gate array (FPGA), is an integrated circuit whose logical function is determined by user programming. Designers can "integrate" a digital system on a PLD through their own programming, without having to hire a chip manufacturer to design and manufacture a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly done using "logic compiler" software. This is similar to the software compiler used when developing programs. Before compilation, the original code must also be written in a specific programming language, called a hardware description language (HDL). There is not just one HDL, but many, 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, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art will also understand that by simply programming the method flow in one of these hardware description languages and then programming it into an integrated circuit, a hardware circuit that implements the logic method flow can be easily obtained.

[0163] The controller can be implemented in any suitable manner. For example, the controller 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 Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also know that in addition to implementing the controller in a purely computer-readable program code format, the controller can be implemented in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software modules that implement the method and structures within the hardware component.

[0164] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, 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.

[0165] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0166] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0167] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0168] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0169] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0170] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0171] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0172] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules 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 disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0173] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0174] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Thus, this specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0175] This specification may be described in the general context of computer-executable instructions, such as program modules, executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media, including storage devices.

[0176] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0177] The foregoing is merely an example of the present invention and is not intended to limit the present invention. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be included within the scope of the claims of the present invention.

Claims

1. A business risk control method, characterized in that: The method is applied to a server and includes: Identify the user groups to be risk-controlled; determining, based on the number of users in the user group, a proportion of each guide character in the guide character set, wherein the guide characters are used to guide the information that users can respond to when answering the risk survey information; Sending a guide character set that meets the proportion and risk investigation information to a client used by each user in the user group; receiving a response result to the risk survey information returned by each user in the user group through the client used, wherein the response result returned by each user is determined based on a guide character randomly selected from the guide character set by the client used by the user; determining the risk probability corresponding to the user group according to a response result returned by each user through the client used and the expected characters for the guide character set determined based on the proportion; Perform risk control on the business performed by the user group based on the risk probability.

2. The method according to claim 1, wherein Determining the proportion of each guide character in the guide character set according to the number of users in the user group includes: The proportion of each guide character in the guide character set is determined based on the number of users in the user group, a first preset parameter, and a second preset parameter, wherein the first preset parameter is used to represent a privacy budget involved in a risk survey of the user group, and the second preset parameter is used to represent a variance of the risk probability corresponding to the user group determined under the first preset parameter.

3. The method according to claim 1, wherein Determining the risk probability corresponding to the user group according to the response result returned by each user through the client used and the expected character for the guide character set determined based on the proportion, specifically includes: Based on the proportion of each guide character in the guide character set, performing weighted summation on each guide character to obtain an expected character for the guide character set; Averaging the response results returned by each user through the client used to obtain the mean of all response results; The risk probability corresponding to the user group is determined according to the expected characters of the guide character set, the average of all the response results, and the number of types of each guide character.

4. The method according to claim 1, wherein Based on the risk probability, risk control is performed on the business executed by the user group, specifically including: If the risk probability is greater than a risk threshold, the service executed by each user in the user group is blocked or an alarm is issued for the service executed by each user in the user group.

5. A business risk control method, characterized in that: The method is applied to the client of each user to be risk-controlled, and the method includes: Receiving risk investigation information and a guide character set sent by the server, wherein the proportion of each guide character in the guide character set is determined by the number of users in the user group to be risk controlled; randomly extracting a guide character from the guide character set, and determining a response result for the risk survey information based on the extracted guide character; The response result is returned to the server, so that the server determines the risk probability corresponding to the user group based on the response result received from each user in the user group through the client used and the expected characters for the guide character set determined based on the proportion, so as to perform risk control on the business performed by the user group according to the risk probability.

6. The method according to claim 5, wherein Based on the extracted guide character, a response result for the risk survey information is determined, specifically including: If it is determined that the user using the client has risk attributes, the extracted guide characters are processed according to the number of types of each guide character to obtain processed characters as a response result to the risk investigation information.

7. The method according to claim 6, wherein According to the number of types of each guide character, the extracted guide characters are processed to obtain processed characters, specifically including: The number of each type of guide characters is summed with the third preset parameter to obtain an initial character; The difference between the initial character and the extracted guide character is used as the processed character.

8. The method according to claim 5, wherein Based on the extracted guide character, a response result for the risk survey information is determined, specifically including: If it is determined that the user using the client does not have the risk attribute, the extracted guide character is used as a response result to the risk investigation information.

9. The method according to claim 5, wherein Randomly extracting a guide character from the guide character set specifically includes: Deleting the guide characters sent by other clients from the guide character set and re-determining the guide character set; wherein the guide characters sent by other clients are guide characters randomly selected by the other clients from the guide character set sent by the server; A guide character is randomly drawn from the re-determined guide character set.

10. A business risk control system, characterized in that: The system includes: a server, and clients of multiple users to be risk-controlled; The server is configured to determine a user group to be risk-controlled, determine a proportion of each guide character in a guide character set based on the number of users in the user group, the guide characters being used to guide the information that a user can reply to when responding to risk survey information, and send a guide character set that satisfies the proportion and the risk survey information to a client used by each user in the user group; The client is configured to receive the risk investigation information and the guide character set sent by the server, randomly extract a guide character from the guide character set, and determine a response result for the risk investigation information based on the extracted guide character, and return the response result to the server; The server is configured to receive a response result regarding the risk survey information returned by each user in the user group through the client used, determine a risk probability corresponding to the user group based on the response result returned by each user through the client used and the expected characters for the guide character set determined based on the proportion; and perform risk control on the business performed by the user group based on the risk probability.

11. The system according to claim 10, wherein: The server is configured to determine a proportion of each guide character in a guide character set based on the number of users in the user group, a first preset parameter, and a second preset parameter, wherein the first preset parameter is used to represent a privacy budget involved in a risk survey of the user group, and the second preset parameter is used to represent a variance of a risk probability corresponding to the user group determined under the first preset parameter.

12. The system according to claim 10, wherein: The server is specifically configured to perform a weighted summation on each guide character based on the proportion of each guide character in the guide character set to obtain an expected character for the guide character set; and average the response results returned by each user through the client used to obtain a mean value for all response results; The risk probability corresponding to the user group is determined according to the expected characters of the guide character set, the average of all the response results, and the number of types of each guide character.

13. The system according to claim 10, wherein: The client is specifically configured to process the extracted guide characters according to the number of types of each guide character if it is determined that the user using the client has risk attributes, and obtain processed characters as a response result to the risk investigation information.

14. The system according to claim 10, wherein: The client is specifically configured to use the extracted guide character as a response result to the risk investigation information if it is determined that the user using the client does not have the risk attribute.

15. The system according to claim 10, wherein: The client is specifically used to delete the guide characters sent by other clients from the guide character set and redefine the guide character set; wherein the guide characters sent by the other clients are guide characters randomly selected from the guide character set sent by the server; and the guide characters are randomly selected from the redetermined guide character set.

16. A business risk control device, characterized in that: include: The first determination module determines the user group to be risk-controlled; a second determining module, configured to determine, based on the number of users in the user group, a proportion of each guiding character in the guiding character set, wherein the guiding characters are used to guide the information that users can reply to when answering the risk survey information; a sending module, configured to send a guide character set that satisfies the proportion and risk investigation information to a client used by each user in the user group; a receiving module, configured to receive a response result to the risk survey information returned by each user in the user group through the client used, wherein the response result returned by each user is determined based on a guide character randomly drawn from the guide character set by the client used by the user; a third determining module, configured to determine the risk probability corresponding to the user group according to a response result returned by each user through the client used and the expected characters for the guide character set determined based on the proportion; The risk control module is used to perform risk control on the business performed by the user group according to the risk probability.

17. A business risk control device, characterized in that: include: a receiving module, configured to receive risk investigation information and a guide character set sent by a server, wherein a proportion of each guide character in the guide character set is determined by the number of users in the user group to be risk controlled; a determination module, configured to randomly extract a guide character from the guide character set and determine a response result for the risk survey information based on the extracted guide character; The risk control module is used to return the response result to the server, so that the server determines the risk probability corresponding to the user group based on the response result returned by each user in the user group through the client used and the expected characters for the guide character set determined based on the proportion, so as to perform risk control on the business performed by the user group according to the risk probability.

18. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

19. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method according to any one of claims 1 to 9 is implemented.

Images