Digital asset risk assessment method and device, electronic equipment and storage medium

Abstract

The invention provides a digital asset risk assessment method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a reference blacklist user set and a to-be-classified user set, and dividing the to-be-classified user set into a target blacklist user set and a target white list user set according to the reference blacklist user set, obtaining a digital asset application frequency sequence of each digital asset institution in the target historical period of time of each target blacklist user and each target white list user, and according to the digital asset application frequency sequence of each digital asset institution in the target historical period of time of each target blacklist user and each target white list user, obtaining a digital asset application frequency sequence of each digital asset institution in the target historical period of time of each target blacklist user and each target white list user; and obtaining the risk level of each target white list user. According to the invention, the risk level of the digital asset application user can be evaluated through the digital asset application frequency of the digital asset application user in each digital asset institution under the condition that data such as a consumption record and an application digital asset value do not need to be acquired.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a digital asset risk assessment method, device, electronic device, and storage medium. Background Art

[0002] Generally speaking, when digital asset institutions assess the credit risk of digital asset applicants, they usually rely on data such as the digital asset applicants’ consumption records on their own platforms and the value of the digital assets applied for to conduct a comprehensive evaluation.

[0003] However, digital asset service agencies can only obtain limited information, such as the number of digital asset applications made by digital asset applicants at various digital asset agencies, but lack more comprehensive data such as consumption records and the value of applied digital assets. This data limitation makes it difficult for digital asset service agencies to assess the credit risk of digital asset applicants.

[0004] Therefore, it is necessary to propose a digital asset risk assessment method to solve at least one of the above technical problems. Summary of the invention

[0005] The embodiments of the present disclosure propose a digital asset risk assessment method, device, electronic device and storage medium, so that a digital asset service agency can assess the credit risk of a digital asset applicant based on limited information (for example, the number of digital asset applications made by the digital asset applicant at each digital asset agency).

[0006] In a first aspect, the present disclosure provides a digital asset risk assessment method, comprising:

[0007] Obtain a reference blacklist user set and a to-be-classified user set;

[0008] Dividing the user set to be classified into a target blacklist user set and a target whitelist user set according to the reference blacklist user set;

[0009] Obtain the sequence of the number of digital asset applications by each target blacklist user and each target whitelist user at each digital asset institution during the target historical period;

[0010] The risk level of each target whitelist user is obtained according to the sequence of the number of digital asset applications of each target blacklist user and each target whitelist user at each digital asset institution within a target historical period.

[0011] In some optional implementations, dividing the user set to be classified into a target blacklist user set and a target whitelist user set according to the reference blacklist user set includes:

[0012] For each user to be classified, if the user to be classified exists in the reference blacklist user set, determining the user to be classified as the target blacklist user;

[0013] If the user to be classified does not exist in the reference blacklist user set, the user to be classified is determined to be the target whitelist user.

[0014] In some optional implementations, obtaining the risk level of each target whitelist user according to the sequence of the number of digital asset applications of each target blacklist user and each target whitelist user at each digital asset institution within a target historical period includes:

[0015] According to the sequence of the number of digital asset applications of each target whitelist user at each digital asset institution in the target historical period and the sequence of the number of digital asset applications of each target blacklist user at each digital asset institution in the target historical period, the digital asset institution similarity and / or digital asset application behavior similarity of each target whitelist user and each target blacklist user applying for digital assets at each digital asset institution are obtained;

[0016] The risk level of each target whitelist user is determined based on the similarity of the digital asset institutions in which each target whitelist user applies for digital assets and / or the similarity of the digital asset application behavior with each target blacklist user at each digital asset institution.

[0017] In some optional implementations, obtaining the digital asset institution similarity and / or digital asset application behavior similarity of each target whitelist user and each target blacklist user applying for digital assets at each digital asset institution according to the digital asset application frequency sequence of each target whitelist user at each digital asset institution within the target historical period and the digital asset application frequency sequence of each target blacklist user at each digital asset institution within the target historical period includes:

[0018] For each of the target whitelist users, calculate the cosine distance between the sequence of digital asset application times of the target whitelist user at each digital asset institution during the target historical period and the sequence of digital asset application times of the target blacklist user at each digital asset institution during the target historical period;

[0019] The digital asset institution similarity between the target whitelist user and each target blacklist user in applying for digital assets at each digital asset institution is obtained according to the cosine distance.

[0020] In some optional implementations, obtaining the digital asset institution similarity and / or digital asset application behavior similarity of each target whitelist user and each target blacklist user applying for digital assets at each digital asset institution according to the digital asset application frequency sequence of each target whitelist user at each digital asset institution within the target historical period and the digital asset application frequency sequence of each target blacklist user at each digital asset institution within the target historical period includes:

[0021] For each of the target whitelist users, calculate the cosine projection distance between the sequence of digital asset application times of the target whitelist user at each digital asset institution during the target historical period and the sequence of digital asset application times of each of the target blacklist users at each digital asset institution during the target historical period;

[0022] The similarity of the digital asset application behavior of the target whitelist user and each target blacklist user in applying for digital assets at each digital asset institution is obtained according to the cosine projection distance.

[0023] In some optional implementations, obtaining the digital asset institution similarity and / or digital asset application behavior similarity of each target whitelist user and each target blacklist user applying for digital assets at each digital asset institution according to the digital asset application frequency sequence of each target whitelist user at each digital asset institution within the target historical period and the digital asset application frequency sequence of each target blacklist user at each digital asset institution within the target historical period includes:

[0024] For each of the target whitelist users, calculate the cosine distance between the sequence of digital asset applications of the target whitelist user at each digital asset institution during the target historical period and the sequence of digital asset applications of the target blacklist user at each digital asset institution during the target historical period, and calculate the cosine projection distance between the sequence of digital asset applications of the target whitelist user at each digital asset institution during the target historical period and the sequence of digital asset applications of the target blacklist user at each digital asset institution during the target historical period;

[0025] According to the cosine distance and the cosine projection distance, the digital asset institution similarity and the digital asset application behavior similarity between the target whitelist user and each target blacklist user in applying for digital assets at each digital asset institution are obtained.

[0026] In a second aspect, the present disclosure provides a digital asset risk assessment device, comprising:

[0027] A first acquisition unit, used to acquire a reference blacklist user set and a to-be-classified user set;

[0028] A division unit, configured to divide the to-be-classified user set into a target blacklist user set and a target whitelist user set according to the reference blacklist user set;

[0029] The second acquisition unit is used to obtain the sequence of the number of digital asset applications of each target blacklist user and each target whitelist user in each digital asset institution within a target historical period;

[0030] The generating unit is used to obtain the risk level of each target whitelist user according to the sequence of the number of digital asset applications of each target blacklist user and each target whitelist user in each digital asset institution within a target historical period.

[0031] In a third aspect, the present disclosure provides an electronic device, including:

[0032] one or more processors;

[0033] a storage device having one or more programs stored thereon,

[0034] When the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any embodiment of the first aspect of the present disclosure.

[0035] In a fourth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by one or more processors, implements the method described in any embodiment of the first aspect of the present disclosure.

[0036] In a fifth aspect, the present disclosure provides a computer program product, comprising a computer program / instructions, which, when executed by a processor, implement the method described in any embodiment of the first aspect of the present disclosure.

[0037] The digital asset risk assessment method, device, electronic device and storage medium provided by the embodiments of the present disclosure first obtain a reference blacklist user set and a user set to be classified, then divide the user set to be classified into a target blacklist user set and a target whitelist user set according to the reference blacklist user set, obtain the digital asset application frequency sequence of each target blacklist user and each target whitelist user in each digital asset institution within the target historical period, and finally obtain the risk level of each target whitelist user according to the digital asset application frequency sequence of each target blacklist user and each target whitelist user in each digital asset institution within the target historical period. The present disclosure divides the user set to be classified into a target blacklist user and a target whitelist user by using a reference blacklist user set, and then obtains the risk level of each target whitelist user according to the digital asset application frequency sequence of each target blacklist user and each target whitelist user in each digital asset institution within the target historical period. The risk level of the digital asset application user can be evaluated according to the digital asset application frequency sequence of the digital asset application user in each digital asset institution without obtaining consumption records, application digital asset values ​​and other data. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Other features, objects and advantages of the present disclosure will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for the purpose of illustrating specific embodiments and are not to be considered as limiting the present invention. In the drawings:

[0039] Figure 1 is a system architecture diagram in which an embodiment of the digital asset risk assessment method disclosed herein can be applied;

[0040] Figure 2 is a flow chart of an embodiment of a digital asset risk assessment method according to the present disclosure;

[0041] Figure 3 is a structural schematic diagram of an embodiment of a digital asset risk assessment device according to the present disclosure;

[0042] Figure 4 It is a structural diagram of a computer system of an electronic device suitable for implementing an embodiment of the present disclosure. DETAILED DESCRIPTION

[0043] The present disclosure is further described in detail below in conjunction with the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0044] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0045] Figure 1 An exemplary system architecture 100 is shown to which embodiments of the digital asset risk assessment method, apparatus, terminal device, and storage medium of the present disclosure may be applied.

[0046] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various communication connection types, such as a wired communication link, a wireless communication link, and the like.

[0047] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as digital asset risk assessment applications, voice interaction applications, video conferencing applications, short video social applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0048] Terminal devices 101, 102, 103 can be hardware or software. When terminal devices 101, 102, 103 are hardware, they can be various electronic devices with microphones and speakers, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Compression Standard Audio Layer 3), MP4 players (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Compression Standard Audio Layer 4), portable computers and desktop computers, etc. When terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. It can be implemented as multiple software or software modules (for example, obtaining a reference blacklist user set and a set of users to be classified), or it can be implemented as a single software or software module. No specific limitation is made here.

[0049] The server 105 may be a server that provides various services, such as a background server that processes webpage content information obtained by the terminal devices 101, 102, and 103. The background server may perform corresponding processing based on the webpage content information obtained by the terminal devices.

[0050] In some cases, the digital asset risk assessment method provided by the present disclosure can be jointly performed by the terminal devices 101, 102, 103 and the server 105. For example, the step of "obtaining a reference blacklist user set and a to-be-classified user set" can be performed by the terminal devices 101, 102, 103, and the step of "dividing the to-be-classified user set into a target blacklist user set and a target whitelist user set according to the reference blacklist user set" can be performed by the server 105. The present disclosure does not limit this. Accordingly, the digital asset risk assessment device can also be respectively set in the terminal devices 101, 102, 103 and the server 105.

[0051] In some cases, the digital asset risk assessment method provided by the present disclosure may be executed by the server 105 , and accordingly, the digital asset risk assessment device may also be set in the server 105 . In this case, the system architecture 100 may not include the terminal devices 101 , 102 , and 103 .

[0052] In some cases, the digital asset risk assessment method provided by the present disclosure can be executed by the terminal devices 101, 102, and 103. Accordingly, the digital asset risk assessment device can also be set in the terminal devices 101, 102, and 103. In this case, the system architecture 100 may not include the server 105.

[0053] It should be noted that the server 105 can be hardware or software. When the server 105 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server 105 is software, it can be implemented as multiple software or software modules (for example, for providing distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0054] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0055] The information, data and signals involved in this disclosure are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions.

[0056] Continue to refer Figure 2 , Figure 2 A flowchart 200 of an embodiment of a digital asset risk assessment method according to the present disclosure is shown. Figure 2 The digital asset risk assessment method shown can be applied to Figure 1The process 200 at least includes the following steps 201-204.

[0057] Step 201: Obtain a reference blacklist user set and a to-be-classified user set.

[0058] The reference blacklist user set has at least one reference blacklist user. The reference blacklist user may refer to a digital asset applicant who has an abnormal record for the applied digital assets (such as failure to return the assets within the agreed period), that is, a high-risk digital asset applicant. Here, various methods can be used to obtain reference blacklist users from various digital asset institutions.

[0059] The reference blacklist user set includes each reference blacklist user identifier, and the reference blacklist user identifier is used to identify the identity of the reference blacklist user. In some examples, the reference blacklist user identifier may include but is not limited to the reference blacklist user username, the reference blacklist user account, the reference blacklist user device ID, etc. In other examples, the reference blacklist user identifier may include authorized user information, such as identity identification element information, contact information, etc. The present disclosure embodiment does not specifically limit the user identifier.

[0060] There is at least one user to be classified in the set of users to be classified. The user to be classified may refer to a digital asset application user of the digital asset service agency. The digital asset service agency may obtain the number of digital asset applications of each user to be classified in each digital asset agency.

[0061] The users to be classified in the set of users to be classified can apply for high-risk digital asset users, or can apply for risk-free digital asset users or low-risk digital asset users.

[0062] The set of users to be classified includes the identifiers of the users to be classified, and the identifiers of the users to be classified are used to identify the identities of the users to be classified. In some examples, the identifiers of the users to be classified may include, but are not limited to, the usernames of the users to be classified, the accounts of the users to be classified, the device IDs of the users to be classified, etc. In other examples, the identifiers of the users to be classified may include the authorized user information, such as the identity identification element information, the contact information, etc. The embodiments of the present disclosure do not specifically limit the user identifiers.

[0063] Step 202: divide the user set to be classified into a target blacklist user set and a target whitelist user set according to the reference blacklist user set.

[0064] In some optional implementations, for each user to be classified, if the user to be classified exists in the reference blacklist user set, the user to be classified is determined to be a target blacklist user; if the user to be classified does not exist in the reference blacklist user set, the user to be classified is determined to be a target whitelist user.

[0065] Specifically, for each user to be classified, the user identifier to be classified can be matched with each reference blacklist user identifier. If there is a user identifier identical to the user identifier to be classified among the reference blacklist user identifiers, it means that the user to be classified exists in the reference blacklist users, and the user to be classified is determined as the target blacklist user. If there is no user identifier identical to the user identifier to be classified among the reference blacklist user identifiers, it means that the user to be classified does not exist in the reference blacklist users, and the user to be classified is determined as the target whitelist user.

[0066] For example, the reference blacklist user set includes reference blacklist user 1, reference blacklist user 2, and reference blacklist user 3, and the corresponding reference blacklist user identifiers are A, B, and C, respectively.

[0067] For the set of users to be classified including user 1 to be classified, user 2 to be classified, user 3 to be classified, user 4 to be classified, user 5 to be classified and user 6 to be classified, the corresponding user identifiers to be classified are A, B, C, D, E and F respectively.

[0068] The user identifiers of the user to be classified 1, the user to be classified 2 and the user to be classified 3 are respectively the same as the reference blacklist user identifiers of the reference blacklist user set including the reference blacklist user 1, the reference blacklist user 2 and the reference blacklist user 3. Therefore, the user to be classified 1, the user to be classified 2 and the user to be classified 3 can be classified as target blacklist users and added to the target blacklist user set.

[0069] If the user identifiers of user 4, user 5 and user 6 are different from the reference blacklist user identifiers of any reference blacklist user, user 4, user 5 and user 6 are classified as target whitelist users and added to the target whitelist user set.

[0070] The target blacklist user set may include at least one target blacklist user, and the target whitelist user set may include at least one target whitelist user.

[0071] It should be noted that, since each target blacklist user in the target blacklist user set is a user to be classified in the user set to be classified and exists in the reference blacklist user set, the target blacklist user set can be a subset of the reference blacklist user set. Therefore, each target blacklist user in the target blacklist user set can be a high-risk digital asset application user.

[0072] The target whitelist users are users to be classified in the set of users to be classified that do not exist in the set of reference blacklist users. The target whitelist users may be high-risk digital asset applicants, risk-free digital asset applicants, or low-risk digital asset applicants.

[0073] By dividing the set of users to be classified into a target blacklist user set and a target whitelist user set, the digital asset service agency can directly obtain the number of digital asset applications of the target blacklist users (high-risk digital asset application users) and the target whitelist users in each digital asset agency. Then, the risk level of each target whitelist user can be evaluated based on the number of digital asset applications of the high-risk digital asset application users and the number of digital asset applications of the target whitelist users in each digital asset agency.

[0074] Step 203: Obtain the sequence of digital asset application times of each target blacklist user and each target whitelist user at each digital asset institution within the target historical period.

[0075] After dividing the set of users to be classified into a target blacklist user set and a target whitelist user set, this step can obtain the sequence of the number of digital asset applications made by each target blacklist user and each target whitelist user in each digital asset institution within a target historical period.

[0076] The target historical period can refer to the past month, quarter, or year, etc., and there is no restriction here.

[0077] Taking the past year as an example for explanation, for example, the digital asset institutions may include digital asset institution a, digital asset institution b and digital asset institution c. For the target blacklist user 1 (user to be classified 1), the number of digital asset applications in digital asset institution a, digital asset institution b and digital asset institution c in the past year may be 0, 3 and 1 respectively.

[0078] For target blacklist user 2 (user to be classified 2), the number of digital asset applications in digital asset institution a, digital asset institution b and digital asset institution c in the past year can be 1, 0 and 0 respectively.

[0079] Correspondingly, the sequence of the number of digital asset applications of target blacklist user 1 in each digital asset institution during the target historical period is [0, 3, 1], and the sequence of the number of digital asset applications of target blacklist user 2 in each digital asset institution during the target historical period is [1, 0, 0].

[0080] For target whitelist user 1 (user to be classified 4), the number of digital asset applications made in digital asset institution a, digital asset institution b, and digital asset institution c in the past year can be 4 times, 3 times, and 0 times respectively.

[0081] Correspondingly, the sequence of digital asset application times of target whitelist user 1 in various digital asset institutions during the target historical period is [4, 3, 0].

[0082] It should be noted that there is no restriction on the execution order between step 202 and step 303. Step 202 can be executed first and then step 203, or step 203 can be executed first, that is, after obtaining the sequence of the number of digital asset applications of each user to be classified (including target blacklist users and target whitelist users) in each digital asset institution within the target historical period, step 202 is executed to divide the set of users to be classified.

[0083] Step 204, obtaining the risk level of each target whitelist user according to the sequence of digital asset application times of each target blacklist user and each target whitelist user at each digital asset institution within the target historical period.

[0084] In some optional implementations, first, the digital asset institution similarity and / or digital asset application behavior similarity of each target whitelist user and each target blacklist user in applying for digital assets at each digital asset institution can be obtained based on the digital asset application frequency sequence of each target whitelist user in each digital asset institution during the target historical period and the digital asset application frequency sequence of each target blacklist user in each digital asset institution during the target historical period. Then, the risk level of each target whitelist user is determined based on the digital asset institution similarity and / or digital asset application behavior similarity of each target whitelist user and each target blacklist user in applying for digital assets at each digital asset institution.

[0085] In this way, the digital asset institution similarity and / or digital asset application behavior similarity of the two when applying for digital assets within the target historical period can be obtained based on the digital asset application frequency sequence of high-risk digital asset applicants and the digital asset application frequency sequence of target whitelist users. Therefore, the risk level of each target whitelist user can be judged based on the digital asset institution similarity and / or digital asset application behavior similarity.

[0086] In some optional implementations, for each target whitelist user, the cosine distance between the sequence of the number of digital asset applications of the target whitelist user at each digital asset institution during the target historical period and the sequence of the number of digital asset applications of each target blacklist user at each digital asset institution during the target historical period can be calculated, and the similarity of the digital asset institutions in which the target whitelist user and each target blacklist user apply for digital assets at each digital asset institution can be obtained based on the cosine distance.

[0087] Here, the cosine distance can be used to characterize the similarity in the angular direction between the sequence of digital asset application times of any target whitelist user in each digital asset institution during the target historical period and the sequence of digital asset application times of any target blacklist user in each digital asset institution during the target historical period, and the value range is [-1, 1].

[0088] The calculation formula of cosine distance can be expressed as:

[0089]

[0090] Among them, X i represents the value of the i-th element in the sequence X of the number of digital asset applications made by the target whitelist user in each digital asset institution during the target historical period, Y i Represents the value of the i-th element in the sequence Y of the number of digital asset applications made by the target blacklist user in each digital asset institution during the target historical period. It represents the modulus length of the sequence X of the number of digital asset applications by the target whitelist users in each digital asset institution during the target historical period. It represents the modulus length of the sequence Y of the number of digital asset applications made by the target blacklisted users in each digital asset institution during the target historical period.

[0091] For example, the target whitelist user 1 (user 4 to be classified) has a digital asset application frequency sequence of [4, 3, 0] in each digital asset institution during the target historical period, and its cosine distance from the target blacklist user 1 and the target blacklist user 2 has a digital asset application frequency sequence of [0, 3, 1] and [1, 0, 0] in each digital asset institution during the target historical period are 0.569 and 0.8 respectively.

[0092] When the cosine distance between the sequence of digital asset applications of any target whitelist user in each digital asset institution during the target historical period and the sequence of digital asset applications of any target blacklist user in each digital asset institution during the target historical period is closer to 1, it means that the direction of the sequence of digital asset applications of the target whitelist user in each digital asset institution during the target historical period is more similar to that of the target blacklist user in each digital asset institution during the target historical period, that is, the closer the similarity of the digital asset institutions for the target whitelist user and the target blacklist user to apply for digital assets in each digital asset institution is to 1, it means that the digital asset institutions selected by the target whitelist user and the target blacklist user when applying for digital assets during the target historical period are more similar.

[0093] When the cosine distance between the sequence of digital asset application times of any target whitelist user in each digital asset institution during the target historical period and the sequence of digital asset application times of any target blacklist user in each digital asset institution during the target historical period tends to -1, it means that the direction of the sequence of digital asset application times of the target whitelist user in each digital asset institution during the target historical period and the sequence of digital asset application times of the target blacklist user in each digital asset institution during the target historical period tends to be opposite, that is, the similarity of the digital asset institutions in which the target whitelist user and the target blacklist user apply for digital assets in each digital asset institution tends to -1, which means that the digital asset institutions selected by the target whitelist user and the target blacklist user when applying for digital assets in the target historical period are less similar.

[0094] It can be understood that the more consistent the digital asset institutions selected by a target whitelist user and a target blacklist user when applying for digital assets in the target historical period, the more similar the behaviors of the target whitelist user and the target blacklist user when applying for digital assets. Therefore, the risk level of each target whitelist user can be determined by the similarity of the digital asset institutions in which the target whitelist user and each target blacklist user apply for digital assets. This can be achieved by evaluating the risk level of the digital asset applicant based on the number of digital asset applications made by the digital asset applicant at each digital asset institution without obtaining data such as consumption records and applied digital asset values.

[0095] In some optional implementations, for each target whitelist user, the cosine projection distance between the sequence of the number of digital asset applications of the target whitelist user at each digital asset institution within the target historical period and the sequence of the number of digital asset applications of each target blacklist user at each digital asset institution within the target historical period is calculated, and the similarity of the digital asset application behavior of the target whitelist user and each target blacklist user in applying for digital assets at each digital asset institution is obtained based on the cosine projection distance.

[0096] Here, the cosine projection distance can be used to characterize the similarity in angle and direction between the sequence of digital asset application times of any target whitelist user in each digital asset institution during the target historical period and the sequence of digital asset application times of any target blacklist user in each digital asset institution during the target historical period, and the value range is [-1, 1].

[0097] The calculation formula of cosine projection distance can be expressed as:

[0098] CosProject x,y =Cos x,y *min[normalize(model x),normalize(model y )]

[0099] Among them, Cos xj It can represent the cosine distance between the sequence X of digital asset applications of the target whitelist users in each digital asset institution during the target historical period and the sequence Y of digital asset applications of the target blacklist users in each digital asset institution during the target historical period. x It can represent the modulus of the sequence X of the number of digital asset applications of the target whitelist users in each digital asset institution during the target historical period. y It can represent the modulus of the sequence Y of the number of digital asset applications of the target blacklisted users in each digital asset institution during the target historical period. Normalize is a normalization function, which is defined as:

[0100]

[0101] Where n can be the modulus of the number of digital asset applications of the target whitelist users in each digital asset institution in the target historical period X or the number of digital asset applications of the target blacklist users in each digital asset institution in the target historical period Y, that is, model x or model y , k, a, b are adjustment coefficients, and their specific values ​​can be selected according to actual conditions. e is usually called the Euler number, which represents the base of the natural logarithm. The purpose of the normalization function is to make the modulus of the number of digital asset applications of the target whitelist users in each digital asset institution in the target historical period X and the number of digital asset applications of the target blacklist users in each digital asset institution in the target historical period Y be between [0, 1].

[0102] For example, the values ​​of k, a, and b can be 1, 1, and 0, respectively.

[0103] For whitelist user 1 (user 4 to be classified), the sequence of digital asset application times in various digital asset institutions during the target historical period is [4, 3, 0], and the cosine projection distances between it and the sequences of digital asset application times in various digital asset institutions of target blacklist user 1 and target blacklist user 2 during the target historical period [0, 3, 1] and [1, 0, 0] are 0.5447 and 0.5848 respectively.

[0104] Similarly, when the cosine projection distance between the sequence of digital asset application times of any target whitelist user in each digital asset institution during the target historical period and the sequence of digital asset application times of any target blacklist user in each digital asset institution during the target historical period is closer to 1, it means that the sequence of digital asset application times of the target whitelist user in each digital asset institution during the target historical period and the sequence of digital asset application times of the target blacklist user in each digital asset institution during the target historical period are more similar in direction and length, that is, the closer the similarity of digital asset application behavior of the target whitelist user and the target blacklist user in applying for digital assets in each digital asset institution is to 1, it means that the digital asset institutions selected by the target whitelist user and the target blacklist user when applying for digital assets during the target historical period and the number of applications for digital assets in each digital asset institution are more similar.

[0105] When the cosine projection distance between the sequence of digital asset application times of any target whitelist user in each digital asset institution during the target historical period and the sequence of digital asset application times of any target blacklist user in each digital asset institution during the target historical period tends to -1, it means that the sequence of digital asset application times of the target whitelist user in each digital asset institution during the target historical period and the sequence of digital asset application times of the target blacklist user in each digital asset institution during the target historical period are more different in direction and length, that is, the more the similarity of digital asset application behavior of the target whitelist user and the target blacklist user in applying for digital assets in each digital asset institution tends to -1, it means that the digital asset institutions selected by the target whitelist user and the target blacklist user when applying for digital assets in each digital asset institution during the target historical period and the number of applications for digital assets in each digital asset institution are more dissimilar.

[0106] It can be understood that the more consistent the digital asset institutions selected by a target whitelist user and a target blacklist user when applying for digital assets in the target historical period and the number of applications for digital assets in each digital asset institution are, the more similar the behaviors of the target whitelist user and the target blacklist user when applying for digital assets are. Therefore, the risk level of each target whitelist user can be determined by the similarity of the digital asset application behavior of the target whitelist user and each target blacklist user in applying for digital assets in each digital asset institution. It is possible to evaluate the risk level of the digital asset applicant based on the number of digital asset applications by the digital asset applicant in each digital asset institution without obtaining data such as consumption records and applied digital asset values.

[0107] In some optional implementations, for each target whitelist user, the cosine distance between the sequence of digital asset application times of the target whitelist user in each digital asset institution during the target historical period and the sequence of digital asset application times of each target blacklist user in each digital asset institution during the target historical period is calculated, and the cosine projection distance between the sequence of asset application times of the target whitelist user in each digital asset institution during the target historical period and the sequence of digital asset application times of each target blacklist user in each digital asset institution during the target historical period is calculated, and the digital asset institution similarity and digital asset application behavior similarity of the target whitelist user and each target blacklist user in applying for digital assets in each digital asset institution are obtained based on the cosine distance and the cosine projection distance.

[0108] Similarly, the risk level of each target whitelist user can be generated through the similarity of digital asset institutions and the similarity of digital asset application behaviors. This can be achieved by evaluating the risk level of digital asset applicants based on the number of digital asset applications they have made at various digital asset institutions without having to obtain data such as consumption records and applied digital asset values.

[0109] In some optional embodiments, for each target whitelist user, the risk level of each target whitelist user is determined based on the derivative values ​​of the cosine distance and / or cosine projection distance between the digital asset application number sequences of the target whitelist user and each target blacklist user in each digital asset institution and the threshold values ​​corresponding to the derivative values.

[0110] Among them, the derived value of the cosine distance may include the maximum cosine distance, minimum cosine distance, average cosine distance, cosine distance greater than or equal to a certain quantity threshold, etc. between the digital asset application number sequences of the target whitelist user and each target blacklist user in each digital asset institution.

[0111] The derived values ​​of the cosine projection distance may include the maximum cosine projection distance, the minimum cosine projection distance, the average cosine projection distance, the cosine projection distance greater than or equal to a certain quantity threshold, etc. between the digital asset application number sequences of the target whitelist user and each target blacklist user in each digital asset institution.

[0112] In some optional implementations, for each target whitelist user, if the maximum cosine distance of the target whitelist user relative to each target blacklist user is greater than or equal to a first cosine distance threshold, then the target whitelist user is determined to be a high-risk digital asset application user; when the maximum cosine distance is less than the first cosine distance threshold, then the target whitelist user is determined to be a risk-free digital asset application user or a low-risk digital asset application user.

[0113] For example, the first cosine distance threshold may be 0.8. The specific first cosine distance threshold may be selected according to actual conditions and is not specifically limited here.

[0114] When the first cosine distance threshold is 0.75, the cosine distances between the target whitelist user 1 (user 4 to be classified) and the target blacklist user 1 and the target blacklist user 2 are 0.569 and 0.8 respectively. Since the maximum cosine distance (the cosine distance between the target whitelist user 1 and the target blacklist user 2) is equal to 0.8, the target whitelist user 1 is determined to be a high-risk digital asset application user.

[0115] In some optional implementations, for each target whitelist user, if the minimum cosine distance of the target whitelist user relative to each target blacklist user is greater than or equal to a second cosine distance threshold, then the target whitelist user is determined to be a high-risk digital asset application user; when the maximum cosine distance is less than the second cosine distance threshold, then the target whitelist user is determined to be a risk-free digital asset application user or a low-risk digital asset application user.

[0116] For example, the second cosine distance threshold may be 0.5. The specific second cosine distance threshold may be selected according to actual conditions and is not specifically limited here.

[0117] When the second cosine distance threshold is 0.5, the cosine distances between the target whitelist user 1 (to-be-classified user 4) and the target blacklist user 1 and the target blacklist user 2 are 0.569 and 0.8 respectively. Since the minimum cosine distance (the cosine distance between the target whitelist user 1 and the target blacklist user 1) 0.569 is greater than 0.5, the target whitelist user 1 is determined to be a high-risk digital asset application user.

[0118] In some optional implementations, for each target whitelist user, if the average cosine distance of the target whitelist user relative to each target blacklist user is greater than or equal to a third cosine distance threshold, then the target whitelist user is determined to be a high-risk digital asset application user; when the average cosine distance is less than the third cosine distance threshold, then the target whitelist user is determined to be a risk-free digital asset application user or a low-risk digital asset application user.

[0119] For example, the third cosine distance threshold may be 0.65. The specific third cosine distance threshold may be selected according to actual conditions and is not specifically limited here.

[0120] When the second cosine distance threshold is 0.5, the cosine distances between the target whitelist user 1 (user 4 to be classified) and the target blacklist user 1 and the target blacklist user 2 are 0.569 and 0.8 respectively. Since the average cosine distance between the target whitelist user 1 and the target blacklist user 1 and the target blacklist user 2 is 0.6845, and the average cosine distance is greater than 0.65, the target whitelist user 1 is determined to be a high-risk digital asset application user.

[0121] In some optional implementations, for each target whitelist user, if the number of cosine distances of the target whitelist user that are greater than or equal to the fourth cosine distance threshold is greater than or equal to the first number threshold relative to each target blacklist user, then the target whitelist user is determined to be a high-risk digital asset application user; if the number of cosine distances that are less than the fourth cosine distance is less than the first number threshold, then the target whitelist user is determined to be a risk-free digital asset application user or a low-risk digital asset application user.

[0122] For example, the fourth cosine distance threshold may be 0.65, and the first quantity threshold may be 3. The specific fourth cosine distance threshold and the first quantity threshold may be selected according to actual conditions and are not specifically limited here.

[0123] When the fourth cosine distance threshold is 0.65, the cosine distances between the target whitelist user 1 (user to be classified 4) and the target blacklist user 1 and the target blacklist user 2 are 0.569 and 0.8 respectively. For example, the cosine distances between the target whitelist user 1 (user to be classified 4) and the target blacklist user 3, target blacklist user 4, target blacklist user 5 and target blacklist user 6 may be 0.7, 0.5, 0.89 and 0.9 respectively.

[0124] Since the target blacklist users corresponding to the cosine distances greater than the fourth cosine distance threshold include target blacklist user 2, target blacklist user 3, target blacklist user 5 and target blacklist user 6, there are a total of four target blacklist users whose cosine distances with the target whitelist user 1 are greater than or equal to the fourth cosine distance threshold, and greater than the first quantity threshold 3. Therefore, it can be determined that the target whitelist user 1 is a high-risk digital asset application user.

[0125] In some optional implementations, for each target whitelist user, if the maximum cosine projection distance of the target whitelist user relative to each target blacklist user is greater than or equal to the fifth cosine projection distance threshold, then the target whitelist user is determined to be a high-risk digital asset application user; if the maximum cosine projection distance is less than the fifth cosine projection distance threshold, then the target whitelist user is determined to be a risk-free digital asset application user or a low-risk digital asset application user.

[0126] For example, the fifth cosine projection distance threshold may be 0.55. The specific fifth cosine projection distance threshold may be selected according to actual conditions and is not specifically limited here.

[0127] When the fifth cosine projection distance threshold is 0.55, the cosine projection distances between the target whitelist user 1 (user 4 to be classified) and the target blacklist user 1 and the target blacklist user 2 are 0.5447 and 0.5848 respectively. Since the maximum cosine projection distance (the cosine projection distance between the target whitelist user 1 and the target blacklist user 2) is greater than 0.55, the target whitelist user 1 is determined to be a high-risk digital asset application user.

[0128] In some optional implementations, for each target whitelist user, if the minimum cosine projection distance of the target whitelist user relative to each target blacklist user is greater than or equal to the sixth cosine projection distance threshold, then the target whitelist user is determined to be a high-risk digital asset application user; when the maximum cosine projection distance is less than the sixth cosine projection distance threshold, then the target whitelist user is determined to be a risk-free digital asset application user or a low-risk digital asset application user.

[0129] For example, the sixth cosine projection distance threshold can be 0.4, and the specific sixth cosine projection distance threshold can be selected according to the actual situation, and is not specifically limited here. When the fifth cosine projection distance threshold is 0.4, the cosine projection distances between the target whitelist user 1 (user 4 to be classified) and the target blacklist user 1 and the target blacklist user 2 are 0.5447 and 0.5848 respectively. Since the minimum cosine projection distance (the cosine projection distance between the target whitelist user 1 and the target blacklist user 1) is greater than 0.4, the target whitelist user 1 is determined to be a high-risk digital asset application user.

[0130] In some optional implementations, for each target whitelist user, if the average cosine projection distance of the target whitelist user relative to each target blacklist user is greater than or equal to the seventh cosine projection distance threshold, then the target whitelist user is determined to be a high-risk digital asset application user; when the average cosine projection distance is less than the seventh cosine projection distance threshold, then the target whitelist user is determined to be a risk-free digital asset application user or a low-risk digital asset application user.

[0131] For example, the seventh cosine projection distance threshold may be 0.5. The specific seventh cosine projection distance threshold may be selected according to actual conditions and is not specifically limited here.

[0132] When the seventh cosine projection distance threshold is 0.5, the cosine projection distances between the target whitelist user 1 (user 4 to be classified) and the target blacklist user 1 and the target blacklist user 2 are 0.5447 and 0.5848 respectively. Since the average cosine projection distance between the target whitelist user 1 and the target blacklist user 1 and the target blacklist user 2 is 0.5648 and the average cosine projection distance is greater than 0.5, the target whitelist user 1 is determined to be a high-risk digital asset application user.

[0133] In some optional implementations, for each target whitelist user, if the number of cosine projection distances of the target whitelist user that is greater than or equal to the eighth cosine projection distance threshold is greater than or equal to the second number threshold relative to each target blacklist user, then the target whitelist user is determined to be a high-risk digital asset application user; if the number of cosine projection distances that are less than the eighth cosine distance is less than the second number threshold, then the target whitelist user is determined to be a risk-free digital asset application user or a low-risk digital asset application user.

[0134] For example, the eighth cosine projection distance threshold may be 0.5, and the second quantity threshold may be 3. The eighth cosine projection distance threshold and the second quantity threshold may be selected according to actual conditions and are not specifically limited here.

[0135] When the eighth cosine distance threshold is 0.5, the cosine projection distances between the target whitelist user 1 (user 4 to be classified) and the target blacklist user 1 and the target blacklist user 2 are 0.5447 and 0.5848 respectively. For example, the cosine projection distances between the target whitelist user 1 (user 4 to be classified) and the target blacklist user 3, the target blacklist user 4, the target blacklist user 5 and the target blacklist user 6 may be 0.5534, 0.428, 0.652 and 0.689 respectively.

[0136] Since the target blacklist users corresponding to the cosine projection distance greater than the eighth cosine distance threshold include target blacklist user 1, target blacklist user 2, target blacklist user 3, target blacklist user 5 and target blacklist user 6, there are a total of five target blacklist users whose cosine projection distances with the target whitelist user 1 are greater than or equal to the eighth cosine projection distance threshold, and greater than the second quantity threshold 3, therefore, it can be determined that the target whitelist user 1 is a high-risk digital asset application user. In some optional implementations, for each target whitelist user, if the maximum cosine distance of the target whitelist user relative to each target blacklist user is greater than or equal to the ninth cosine distance threshold, and at the same time, the maximum cosine projection distance is greater than or equal to the tenth cosine projection distance threshold, then the target whitelist user is determined to be a high-risk digital asset application user, and when the maximum cosine distance is less than the ninth cosine distance threshold, and at the same time, the maximum cosine projection distance is less than the tenth cosine projection distance threshold, then the target whitelist user is determined to be a risk-free digital asset application user or a low-risk digital asset application user.

[0137] For example, the ninth cosine distance threshold may be 0.8, and the tenth cosine projection distance threshold may be 0.55. The ninth cosine distance threshold and the tenth cosine projection distance threshold may be selected according to actual conditions and are not specifically limited here.

[0138] When the ninth cosine distance threshold is 0.75 and the tenth cosine projection distance threshold is 0.55, the cosine distances between the target whitelist user 1 (user 4 to be classified) and the target blacklist user 1 and the target blacklist user 2 are 0.569 and 0.8 respectively, and the cosine projection distances between the target whitelist user 1 (user 4 to be classified) and the target blacklist user 1 and the target blacklist user 2 are 0.5447 and 0.5848 respectively.

[0139] Since the maximum cosine distance (the cosine distance between the target whitelist user 1 and the target blacklist user 2) is equal to 0.8, and the maximum cosine projection distance (the cosine projection distance between the target whitelist user 1 and the target blacklist user 2) is greater than 0.55, it is determined that the target whitelist user 1 is a high-risk digital asset applicant user.

[0140] In some optional embodiments, for each target whitelist user, if the minimum cosine distance of the target whitelist user relative to each target blacklist user is greater than or equal to the eleventh cosine distance threshold, and at the same time, the minimum cosine projection distance is greater than or equal to the twelfth cosine projection distance threshold, then the target whitelist user is determined to be a high-risk digital asset application user; if the maximum cosine distance is less than the eleventh cosine distance threshold, and at the same time, the maximum cosine projection distance is less than the twelfth cosine projection distance threshold, then the target whitelist user is determined to be a risk-free digital asset application user or a low-risk digital asset application user.

[0141] For example, the eleventh cosine distance threshold may be 0.5, and the twelfth cosine projection distance threshold may be 0.4. The eleventh cosine distance threshold and the twelfth cosine projection distance threshold may be selected according to actual conditions and are not specifically limited herein.

[0142] When the eleventh cosine distance threshold is 0.5 and the twelfth cosine projection distance threshold is 0.4, the cosine distances between the target whitelist user 1 (user 4 to be classified) and the target blacklist user 1 and the target blacklist user 2 are 0.569 and 0.8 respectively, and the cosine projection distances between the target whitelist user 1 (user 4 to be classified) and the target blacklist user 1 and the target blacklist user 2 are 0.5447 and 0.5848 respectively.

[0143] Since the minimum cosine distance (the cosine distance between the target whitelist user 1 and the target blacklist user 1) is greater than 0.5, and the minimum cosine projection distance (the cosine projection distance between the target whitelist user 1 and the target blacklist user 2) is greater than 0.4, the target whitelist user 1 is determined to be a high-risk digital asset applicant.

[0144] In some optional embodiments, for each target whitelist user, if the average cosine distance of the target whitelist user relative to each target blacklist user is greater than or equal to the thirteenth cosine distance threshold, and at the same time, the average cosine projection distance is greater than or equal to the fourteenth cosine projection distance threshold, then the target whitelist user is determined to be a high-risk digital asset application user; if the average cosine distance is less than the thirteenth cosine distance threshold, and at the same time, the average cosine projection distance is less than the fourteenth cosine projection distance threshold, then the target whitelist user is determined to be a risk-free digital asset application user or a low-risk digital asset application user.

[0145] For example, the thirteenth cosine distance threshold may be 0.65, and the fourteenth cosine projection distance threshold may be 0.5. The thirteenth cosine distance threshold and the fourteenth cosine projection distance threshold may be selected according to actual conditions and are not specifically limited herein.

[0146] When the thirteenth cosine distance threshold is 0.65 and the fourteenth cosine projection distance threshold is 0.5, the cosine distances between the target whitelist user 1 (user 4 to be classified) and the target blacklist user 1 and the target blacklist user 2 are 0.569 and 0.8 respectively, and the average cosine distance between the target whitelist user 1 and the target blacklist user 1 and the target blacklist user 2 is 0.6845, and the average cosine distance is greater than 0.65. In addition, the cosine projection distances between the target whitelist user 1 (user 4 to be classified) and the target blacklist user 1 and the target blacklist user 2 are 0.5447 and 0.5848 respectively, and the average cosine projection distance between the target whitelist user 1 and the target blacklist user 1 and the target blacklist user 2 is 0.5648, and the average cosine projection distance is greater than 0.5, and the target whitelist user 1 is determined to be a high-risk digital asset application user.

[0147] In some optional embodiments, for each target whitelist user, if, relative to each target blacklist user, the number of cosine distances of the target whitelist user that is greater than or equal to the fifteenth cosine distance threshold is greater than or equal to the third quantity threshold, and at the same time, the number of cosine projection distances that is greater than or equal to the sixteenth cosine projection distance threshold is greater than or equal to the fourth quantity threshold, then the target whitelist user is determined to be a high-risk digital asset application user; if the number of cosine distances that is greater than or equal to the fifteenth cosine distance threshold is less than the third quantity threshold, and at the same time, the number of cosine projection distances that is less than the sixteenth cosine projection distance threshold, then the target whitelist user is determined to be a risk-free digital asset application user or a low-risk digital asset application user.

[0148] For example, the fifteenth cosine distance threshold can be 0.65, the third quantity threshold can be 3, the sixteenth cosine projection distance threshold can be 0.5, and the fourth quantity threshold can be 3. The specific fifteenth cosine distance threshold, the third quantity threshold, the sixteenth cosine projection distance threshold and the fourth quantity threshold can be selected according to actual conditions and are not specifically limited here.

[0149] When the fifteenth cosine distance threshold is 0.65, the cosine distances between the target whitelist user 1 (user to be classified 4) and the target blacklist user 1 and the target blacklist user 2 are 0.569 and 0.8 respectively. For example, the cosine distances between the target whitelist user 1 (user to be classified 4) and the target blacklist user 3, target blacklist 4, target blacklist user 5 and target blacklist user 6 may be 0.7, 0.5, 0.89 and 0.9 respectively.

[0150] When the sixteenth cosine distance threshold is 0.5, the cosine projection distances between the target whitelist user 1 (user to be classified 4) and the target blacklist user 1 and the target blacklist user 2 are 0.5447 and 0.5848 respectively. For example, the cosine projection distances between the target whitelist user 1 (user to be classified 4) and the target blacklist user 3, target blacklist user 4, target blacklist user 5 and target blacklist user 6 may be 0.5534, 0.428, 0.652 and 0.689 respectively.

[0151] Since the target blacklist users corresponding to the cosine distance greater than the fifteenth cosine distance threshold include target blacklist user 2, target blacklist user 3, target blacklist user 5 and target blacklist user 6, there are a total of four target blacklist users whose cosine distances with the target whitelist user 1 are greater than or equal to the fifteenth cosine distance threshold, which is greater than the third quantity threshold 3. At the same time, since the target blacklist users corresponding to the cosine projection distance greater than the sixteenth cosine distance threshold include target blacklist user 1, target blacklist user 2, target blacklist user 3, target blacklist user 5 and target blacklist user 6, there are a total of five target blacklist users whose cosine projection distances with the target whitelist user 1 are greater than or equal to the sixteenth cosine projection distance threshold, which is greater than the fourth quantity threshold 3. Therefore, it can be determined that target whitelist user 1 is a high-risk digital asset application user.

[0152] The digital asset risk assessment method provided by the embodiment of the present disclosure first obtains a reference blacklist user set and a user set to be classified, then divides the user set to be classified into a target blacklist user set and a target whitelist user set according to the reference blacklist user set, obtains the digital asset application frequency sequence of each target blacklist user and each target whitelist user in each digital asset institution within the target historical period, and finally, obtains the risk level of each target whitelist user according to the digital asset application frequency sequence of each target blacklist user and each target whitelist user in each digital asset institution within the target historical period. The present disclosure divides the user set to be classified into a target blacklist user and a target whitelist user by using a reference blacklist user set, and then obtains the risk level of each target whitelist user according to the digital asset application frequency sequence of each target blacklist user and each target whitelist user in each digital asset institution within the target historical period. The risk level of the digital asset application user can be evaluated according to the digital asset application frequency sequence of the digital asset application user in each digital asset institution without obtaining consumption records, application digital asset values ​​and other data.

[0153] Further references Figure 3 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a digital asset risk assessment device. Figure 2Corresponding to the method embodiment shown, the apparatus can be specifically applied to various terminal devices.

[0154] like Figure 3 As shown, the digital asset risk assessment device of this embodiment, the device 300 includes: a first acquisition unit 301, a division unit 302, a second acquisition unit 303 and a generation unit 304. Among them, the first acquisition unit 301 is used to obtain a reference blacklist user set and a to-be-classified user set; the division unit 302 is used to divide the to-be-classified user set into a target blacklist user set and a target whitelist user set according to the reference blacklist user set; the second acquisition unit 303 is used to obtain the digital asset application frequency sequence of each target blacklist user and each target whitelist user in each digital asset institution within the target historical period; the generation unit 304 is used to obtain the risk level of each target whitelist user according to the digital asset application frequency sequence of each target blacklist user and each target whitelist user in each digital asset institution within the target historical period.

[0155] In this embodiment, the specific processing of the first acquisition unit 301, the division unit 302, the second acquisition unit 303 and the generation unit 304 and the technical effects thereof can be referred to in Figure 2 The relevant descriptions of step 201 to step 204 in the corresponding embodiment are not repeated here.

[0156] In some optional implementations, the dividing unit 302 may be further configured to:

[0157] For each user to be classified, if the user to be classified exists in the reference blacklist user set, the user to be classified is determined to be a target blacklist user;

[0158] If the user to be classified does not exist in the reference blacklist user set, the user to be classified is determined to be a target whitelist user.

[0159] In some optional implementations, the generating unit 304 may be further configured to:

[0160] According to the sequence of the number of digital asset applications of each target whitelist user at each digital asset institution during the target historical period and the sequence of the number of digital asset applications of each target blacklist user at each digital asset institution during the target historical period, the similarity of digital asset institutions and / or the similarity of digital asset application behaviors of each target whitelist user and each target blacklist user in applying for digital assets at each digital asset institution are obtained;

[0161] The risk level of each target whitelist user is obtained based on the similarity of digital asset institutions and / or digital asset application behaviors of each target whitelist user and each target blacklist user in applying for digital assets at each digital asset institution.

[0162] In some optional implementations, the generating unit 304 may be further configured to:

[0163] For each target whitelist user, calculate the cosine distance between the sequence of digital asset application times of the target whitelist user at each digital asset institution during the target historical period and the sequence of digital asset application times of each target blacklist user at each digital asset institution during the target historical period;

[0164] The digital asset institution similarity between the target whitelist user and each target blacklist user in applying for digital assets in each digital asset institution is obtained based on the cosine distance.

[0165] In some optional implementations, the generating unit 304 may be further configured to:

[0166] For each target whitelist user, calculate the cosine projection distance between the sequence of digital asset applications of the target whitelist user at each digital asset institution during the target historical period and the sequence of digital asset applications of each target blacklist user at each digital asset institution during the target historical period;

[0167] The similarity of digital asset application behaviors between the target whitelist user and each target blacklist user in applying for digital assets at each digital asset institution is obtained based on the cosine projection distance.

[0168] In some optional implementations, the generating unit 304 may be further configured to:

[0169] For each target whitelist user, calculate the cosine distance between the sequence of digital asset applications of the target whitelist user at each digital asset institution during the target historical period and the sequence of digital asset applications of the target blacklist user at each digital asset institution during the target historical period, and calculate the cosine projection distance between the sequence of digital asset applications of the target whitelist user at each digital asset institution during the target historical period and the sequence of digital asset applications of the target blacklist user at each digital asset institution during the target historical period;

[0170] The digital asset institution similarity and digital asset application behavior similarity between the target whitelist user and each target blacklist user in applying for digital assets in each digital asset institution are obtained based on the cosine distance and the cosine projection distance.

[0171] It should be noted that the implementation details and technical effects of each unit in the digital asset risk assessment device provided in the embodiments of the present disclosure can be referred to the description of other embodiments in the present disclosure and will not be repeated here.

[0172] Reference below Figure 4, which shows a schematic diagram of the structure of a computer system 400 of a terminal device suitable for implementing the present disclosure. Figure 4 The computer system 400 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0173] like Figure 4 As shown, the computer system 400 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage device 408 to a random access memory (RAM) 403. Various programs and data required for the operation of the computer system 400 are also stored in the RAM 403. The processing device 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0174] Typically, the following devices may be connected to the I / O interface 405: input devices 406 including, for example, a touch screen, a touch pad, a keypad, a mouse, a camera, a microphone, etc.; output devices 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 408 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 409. The communication devices 409 may allow the computer system 400 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The computer system 400 of an electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0175] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 409, or installed from a storage device 408, or installed from a ROM 402. When the computer program is executed by the processing device 401, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0176] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0177] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0178] The computer readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device implements the following Figure 2 The illustrated embodiment and its optional implementations illustrate a method for obtaining and distributing information.

[0179] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0180] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0181] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a unit does not limit the unit itself in some cases. For example, the first acquisition unit may also be described as a "unit for acquiring a reference blacklist user set and a to-be-classified user set".

[0182] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

Claims

1. A digital asset risk assessment method, characterized in that: include: Obtain a reference blacklist user set and a to-be-classified user set; Dividing the user set to be classified into a target blacklist user set and a target whitelist user set according to the reference blacklist user set; Obtain the sequence of the number of digital asset applications by each target blacklist user and each target whitelist user at each digital asset institution during the target historical period; The risk level of each target whitelist user is obtained according to the sequence of the number of digital asset applications of each target blacklist user and each target whitelist user at each digital asset institution within a target historical period.

2. The method according to claim 1, characterized in that The step of dividing the user set to be classified into a target blacklist user set and a target whitelist user set according to the reference blacklist user set includes: For each user to be classified, if the user to be classified exists in the reference blacklist user set, determining the user to be classified as the target blacklist user; If the user to be classified does not exist in the reference blacklist user set, the user to be classified is determined to be the target whitelist user.

3. The method according to claim 1, characterized in that The step of obtaining the risk level of each target whitelist user according to the sequence of the number of digital asset applications of each target blacklist user and each target whitelist user at each digital asset institution within the target historical period includes: According to the sequence of the number of digital asset applications of each target whitelist user at each digital asset institution in the target historical period and the sequence of the number of digital asset applications of each target blacklist user at each digital asset institution in the target historical period, the digital asset institution similarity and / or digital asset application behavior similarity of each target whitelist user and each target blacklist user applying for digital assets at each digital asset institution are obtained; The risk level of each target whitelist user is determined based on the similarity of the digital asset institutions in which each target whitelist user applies for digital assets and / or the similarity of the digital asset application behavior with each target blacklist user at each digital asset institution.

4. The method according to claim 3, characterized in that The obtaining of the digital asset institution similarity and / or digital asset application behavior similarity of each target whitelist user and each target blacklist user applying for digital assets at each digital asset institution according to the digital asset application frequency sequence of each target whitelist user at each digital asset institution within the target historical period and the digital asset application frequency sequence of each target blacklist user at each digital asset institution within the target historical period includes: For each of the target whitelist users, calculate the cosine distance between the sequence of digital asset application times of the target whitelist user at each digital asset institution during the target historical period and the sequence of digital asset application times of the target blacklist user at each digital asset institution during the target historical period; The digital asset institution similarity between the target whitelist user and each target blacklist user in applying for digital assets at each digital asset institution is obtained according to the cosine distance.

5. The method according to claim 3, characterized in that: The obtaining of the digital asset institution similarity and / or digital asset application behavior similarity of each target whitelist user and each target blacklist user applying for digital assets at each digital asset institution according to the digital asset application frequency sequence of each target whitelist user at each digital asset institution within the target historical period and the digital asset application frequency sequence of each target blacklist user at each digital asset institution within the target historical period includes: For each of the target whitelist users, calculate the cosine projection distance between the sequence of digital asset application times of the target whitelist user at each digital asset institution during the target historical period and the sequence of digital asset application times of each of the target blacklist users at each digital asset institution during the target historical period; The similarity of the digital asset application behavior of the target whitelist user and each target blacklist user in applying for digital assets at each digital asset institution is obtained according to the cosine projection distance.

6. The method according to claim 3, characterized in that The obtaining of the digital asset institution similarity and / or digital asset application behavior similarity of each target whitelist user and each target blacklist user applying for digital assets at each digital asset institution according to the digital asset application frequency sequence of each target whitelist user at each digital asset institution within the target historical period and the digital asset application frequency sequence of each target blacklist user at each digital asset institution within the target historical period includes: For each of the target whitelist users, calculate the cosine distance between the sequence of digital asset applications of the target whitelist user at each digital asset institution during the target historical period and the sequence of digital asset applications of the target blacklist user at each digital asset institution during the target historical period, and calculate the cosine projection distance between the sequence of digital asset applications of the target whitelist user at each digital asset institution during the target historical period and the sequence of digital asset applications of the target blacklist user at each digital asset institution during the target historical period; According to the cosine distance and the cosine projection distance, the digital asset institution similarity and the digital asset application behavior similarity between the target whitelist user and each target blacklist user in applying for digital assets at each digital asset institution are obtained.

7. A digital asset risk assessment device, comprising: A first acquisition unit, used to acquire a reference blacklist user set and a to-be-classified user set; A division unit, configured to divide the to-be-classified user set into a target blacklist user set and a target whitelist user set according to the reference blacklist user set; The second acquisition unit is used to obtain the sequence of the number of digital asset applications of each target blacklist user and each target whitelist user in each digital asset institution within a target historical period; The generating unit is used to obtain the risk level of each target whitelist user according to the sequence of the number of digital asset applications of each target blacklist user and each target whitelist user in each digital asset institution within a target historical period.

8. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, When one or more programs are executed by one or more processors, the one or more processors are caused to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, wherein: When the computer program is executed by one or more processors, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program / instruction, wherein when the computer program / instruction is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images