CN114219367A

CN114219367A - User scoring method, device, equipment and storage medium

Info

Publication number: CN114219367A
Application number: CN202210027419.0A
Authority: CN
Inventors: 刘锴靖
Original assignee: Ping An Puhui Enterprise Management Co Ltd
Current assignee: Ping An Puhui Enterprise Management Co Ltd
Priority date: 2022-01-11
Filing date: 2022-01-11
Publication date: 2022-03-22

Abstract

The invention relates to an artificial intelligence technology, and discloses a user scoring method, which comprises the following steps: generating a data tag according to user data of a user; dividing the data tags into a basic data tag set and a risk data tag set; calculating the basic data score of each basic data tag according to the user data corresponding to the basic data tag set and the corresponding optimal parameters; calculating the risk data score of each risk data label according to the user data corresponding to the risk data label set and the corresponding risk score model; and selecting one or more basic data tags and risk data tags as target tags according to the scoring types, selecting corresponding weight coefficients, and calculating scores corresponding to the target tags according to the weight coefficients to obtain comprehensive scores. In addition, the invention also relates to a block chain technology, and user data can be stored in the nodes of the block chain. The invention also provides a user scoring device, equipment and a medium. The invention can improve the accuracy and the applicability of user scoring.

Description

User scoring method, device, equipment and storage medium

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to a user scoring method, a user scoring device, electronic equipment and a computer-readable storage medium.

Background

At present, the application scene of scoring the user exists in the aspect of life. For example, credit consumption carries out rating evaluation on the aspects of consumption behaviors and the like of the user, and rating recommendation is required when an application program is logged in or registered according to attention information and age gender of the user. However, in the prior art, a general logistic regression model is mostly used to process user data uniformly, the final calculated result is the user score, the scoring result only corresponds to one scoring type, and if different scoring types are obtained, such as user stability scoring, user labor waste scoring, and the like, recalculation is required, so that the problem that the user score has low accuracy and cannot be applied to different scoring types is caused.

Disclosure of Invention

The invention provides a user scoring method, a user scoring device and a computer readable storage medium, and mainly aims to solve the problems of low user scoring accuracy and low applicability.

In order to achieve the above object, the present invention provides a user scoring method, including:

acquiring user data of a user and generating a data tag of the user data;

dividing the data tags into a basic data tag set and a risk data tag set;

calculating the basic data score of each basic data tag in the basic data tag set according to the user data corresponding to the basic data tag set and the corresponding preset optimal parameters;

calculating the risk data score of each risk data label in the risk data label set according to the user data corresponding to the risk data label set and a pre-trained risk score model;

according to a pre-selected scoring type, one or more basic data tags and one or more risk data tags are respectively selected from the basic data tag set and the risk data tag set, the weight coefficients of the basic data tags and the risk data tags are obtained, and the basic data scoring and the risk data scoring corresponding to the selected basic data tags and the risk data tags are subjected to weight calculation according to the weight coefficients, so that the comprehensive scoring of the user under the scoring type is obtained.

Optionally, the acquiring user data of the user includes:

acquiring identity data of the user;

capturing expansion data from the captured internet and/or a preset storage area according to the identity data;

and integrating the identity data and the expansion data to obtain user data.

Optionally, the generating a data tag of the user data includes:

splitting the user data into a plurality of data segments according to preset separators;

extracting paragraph semantics of each of the data segments;

and calculating to obtain a data label corresponding to each data segment according to the paragraph semantics and a preset label list.

Optionally, the splitting the user data into a plurality of data segments according to a preset splitter includes:

counting the position information of a preset separator in the user data;

and splitting the user data into a plurality of data segments according to the position information.

Optionally, the calculating a basic data score of each basic data tag in the basic data tag set according to the user data corresponding to the basic data tag set and the corresponding preset optimal parameter includes:

calculating the distance value between each basic data label in the basic data label set and the corresponding preset optimal parameter one by one;

and determining the basic data score of the corresponding basic data label according to the distance value.

Optionally, the calculating a risk data score of each risk data tag in the risk data tag set according to the user data corresponding to the risk data tag set and a pre-trained risk score model includes:

classifying the user data corresponding to the risk data tag set to obtain character type data and numerical type data;

respectively generating a first eigenvector and a second eigenvector according to the character type data and the numerical type data;

merging the first feature vector and the second feature vector to obtain a feature vector set;

and inputting the feature vector set into the risk scoring model to obtain the risk data score of the user.

Optionally, the obtaining of the weight coefficients of the basic data tags and the risk data tags, and performing weight calculation on the basic data scores and the risk data scores corresponding to the selected basic data tags and the selected risk data tags according to the weight coefficients to obtain a comprehensive score of the user under the score type includes:

acquiring the basic data labels corresponding to the grading types and the weight coefficients corresponding to the risk data labels from a preset weight list;

according to the following weight algorithm and the weight coefficient, carrying out weight calculation on the selected basic data score of the basic data label and the selected risk data score of the risk data label to obtain a comprehensive score of the user under the score type:

wherein G is the comprehensive score of the user under the score type, n is the number of data tags, and Q_iScoring the base data of the ith data tag, P_iAnd scoring the risk data of the ith data label, wherein alpha and beta are weight coefficients.

In order to solve the above problem, the present invention further provides a user scoring apparatus, including:

the data label generating module is used for acquiring user data of a user and generating a data label of the user data; dividing the data tags into a set of elemental data tags and a set of risk data tags;

the basic data score generation module is used for calculating the basic data score of each basic data tag in the basic data tag set according to the user data corresponding to the basic data tag set and the corresponding preset optimal parameters;

a risk data score generation module, configured to calculate a risk data score of each risk data tag in the risk data tag set according to the user data corresponding to the risk data tag set and a pre-trained risk score model corresponding to the risk data tag set;

and the comprehensive score generation module is used for respectively selecting one or more basic data tags and risk data tags from the basic data tag set and the risk data tag set according to a preset score type, selecting the weight coefficients of the basic data tags and the risk data tags, and performing weight calculation on scores corresponding to the selected basic data tags and the selected risk data tags according to the weight coefficients to obtain the comprehensive score of the user.

In order to solve the above problem, the present invention also provides an electronic device, including:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the user scoring method described above.

In order to solve the above problem, the present invention also provides a computer-readable storage medium, in which at least one computer program is stored, and the at least one computer program is executed by a processor in an electronic device to implement the user scoring method described above.

According to the embodiment of the invention, the user data are divided into two types according to the data tags, so that different types of user data are respectively subjected to different calculation methods to obtain scores of corresponding types, and the score calculation efficiency and the score calculation accuracy are improved; different scoring types correspond to different scoring labels, scoring of different scoring types is achieved by scoring the selected different basic data or scoring the risk data, and diversity of generated scores is improved. Therefore, the user scoring method, the user scoring device, the electronic equipment and the computer readable storage medium provided by the invention can solve the problems of low user scoring accuracy and low applicability.

Drawings

Fig. 1 is a schematic flow chart of a user scoring method according to an embodiment of the present invention;

fig. 2 is a schematic flow chart of generating a data tag of user data according to an embodiment of the present invention;

fig. 3 is a schematic flowchart of calculating a risk data score for each risk data tag according to an embodiment of the present invention;

FIG. 4 is a functional block diagram of a user scoring apparatus according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of an electronic device for implementing the user scoring method according to an embodiment of the present invention.

The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

The embodiment of the application provides a user scoring method. The execution subject of the user scoring method includes, but is not limited to, at least one of electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiments of the present application. In other words, the user scoring method may be performed by software or hardware installed in the terminal device or the server device, and the software may be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.

Fig. 1 is a schematic flow chart of a user scoring method according to an embodiment of the present invention.

In this embodiment, the user scoring method includes:

s1, acquiring user data of a user and generating a data label of the user data;

in the embodiment of the present invention, the user data includes personal information, income information, consumption information, and the like of the user, for example: the user is Zhang III, the user data is 30 years old, male and married, two children exist, and the annual income is 20 ten thousand; the data tag is a data type to which the user information belongs, for example: the data tag of 30 years old is age, the data tag of male is gender, the data tag of married is marital condition, and the data tag of annual income of 20 ten thousand is salary condition.

In the embodiment of the present invention, the acquiring user data of a user includes:

acquiring identity data of the user;

and integrating the identity data and the expansion data to obtain user data.

In detail, the embodiment of the invention can utilize a computer sentence (such as a java sentence, a python sentence, etc.) with a data fetching function to obtain the extension data of the user from the internet and/or a pre-constructed storage area for storing the data of the user, wherein the storage area includes, but is not limited to, a database, a block chain node, a network cache, etc.

In this embodiment of the present invention, referring to fig. 2, the generating the data tag of the user data includes:

s11, splitting the user data into a plurality of data segments according to preset separators;

s12, extracting paragraph semantics of each data segment;

and S13, calculating to obtain a data label corresponding to each data segment according to the paragraph semantics and a preset label list.

Specifically, the splitting the user data into a plurality of data segments according to a preset splitter includes:

counting the position information of a preset separator in the user data;

In an embodiment of the present invention, the separator may be a comma, a pause, a period, an exclamation mark, or the like.

In the embodiment of the invention, the data segment can be subjected to word segmentation processing, keywords are selected according to the processed word segmentation and word vector conversion is carried out, the keywords can be converted into word vectors by using a preset vector conversion model, and the word vectors are used as the paragraph semantics of the target paragraph, wherein the vector conversion model comprises but is not limited to a word2vec model and a bert model; based on the paragraph semantics, i.e. word vector, calculating the distance value between the word vector and the tags in the tag list, and selecting the tag with the smallest distance value as the data tag of the data segment.

S2, dividing the data labels into a basic data label set and a risk data label set;

in detail, the embodiment of the present invention divides the data tags into a basic data tag set and a risk data tag set according to a preset tag classification table.

In detail, the tag classification table includes preset basic data tags and risk data tags, and the data tags are divided into a basic data tag set and a risk data tag set by matching the data tags with the tag classification table in the embodiment of the present invention.

Specifically, the basic data tag set includes a plurality of basic data tags, the user data corresponding to the basic data tags is basic user data, the risk data tag set includes a plurality of risk data tags, and the user data corresponding to the risk data tags is risk user data.

S3, calculating the basic data score of each basic data label in the basic data label set according to the user data corresponding to the basic data label set and the corresponding preset optimal parameters;

in detail, in the embodiment of the present invention, the preset optimal parameter is a parameter that achieves an optimal result for a certain scoring scheme by collecting data of different users and performing statistical analysis. For example, suppose that the age is 40 years, the income of 30 ten thousand is the most stable, and the age 40 years and the income of 30 ten thousand are the optimal parameters.

The embodiment of the invention can determine whether the user data is close to the optimal parameter by calculating the distance value between the user data and the preset optimal parameter, and if the distance value is smaller, the user data is closer to the optimal parameter, so that the score of the user data is higher; if the distance value is larger, it can be said that the user data is farther from the optimal parameter, and the score of the user data is lower.

In an embodiment of the present invention, the calculating a basic data score of each basic data tag in the basic data tag set according to the user data corresponding to the basic data tag set and the corresponding preset optimal parameter includes:

Further, the embodiment of the present invention may calculate the distance value between the user data corresponding to each basic data tag and the corresponding preset optimal parameter by using the following formula:

wherein D is the distance value, R_iAnd T is corresponding preset optimal parameters for the user data corresponding to the basic data label, and theta is a preset coefficient.

Further, in the embodiment of the present invention, the distance value is calculated according to the corresponding basic data scoring rule, and then the basic data score of the user data is obtained, for example, the distance value is subjected to weight calculation, so as to obtain the basic data score.

In the embodiment of the invention, the calculation of the user score according to the user data corresponding to the basic data labels is more direct and accurate by determining the optimal parameters corresponding to the score types, a model does not need to be built for the user data corresponding to each data label, and the model is substituted for solving, so that the efficiency of generating the basic data score is improved.

S4, calculating the risk data score of each risk data label in the risk data label set according to the user data corresponding to the risk data label set and a pre-trained risk score model corresponding to the risk data label set;

in the embodiment of the invention, the risk scoring model is a model which is obtained by training the training data in advance and can detect and calculate the user data corresponding to the risk data labels, and the risk scoring model comprises but is not limited to a logistic regression model, a random forest, a GBM (gradient Boosting machine) type integrated tree and a deep learning sequence model.

In the embodiment of the invention, a model list corresponding to the risk data label can be searched in a preset database, and a risk scoring model corresponding to the risk data label is selected from the model list. And storing the mapping relation between the labels and the corresponding risk scoring models in the model list.

Further, the model list is used for storing labels and corresponding risk scoring models, and mapping relationships are formed between the labels and the risk scoring models.

In the embodiment of the present invention, referring to fig. 3, the calculating a risk data score of each risk data tag in the risk data tag set according to the user data corresponding to the risk data tag set and a pre-trained risk score model includes:

s41, classifying the user data corresponding to the risk data label set to obtain character type data and numerical type data;

s42, respectively generating a first eigenvector and a second eigenvector according to the character type data and the numerical type data;

s43, merging the first feature vector and the second feature vector to obtain a feature vector set;

and S44, inputting the feature vector set into the risk scoring model to obtain the risk data score of the user.

In this embodiment of the present invention, one-hot encoding may be performed on the character-type data, or hash calculation may be performed on the character-type data, so as to generate the first feature vector of the character-type data. For the second feature vector, creating an initial feature vector may be employed; and calculating to obtain a second feature vector of the numerical data according to the numerical data and the initial feature vector.

Further, in the embodiment of the present invention, the first feature vector and the second feature vector are merged, where the first feature vector is before the second feature vector is after the second feature vector, or the second feature vector is before the second feature vector and the first feature vector is after the second feature vector is after the first feature vector. And generating a feature vector of the risk data label according to the user data, wherein the feature vector can be used for characterizing unique attribute features of the risk data label.

Furthermore, the risk scoring model in the embodiment of the present invention may be a deep learning model, a feature vector set is input into the risk scoring model, the feature vector set is converted into a one-dimensional multi-dimensional matrix, and the one-dimensional multi-dimensional matrix is convolved and fully connected for a preset number of times by a plurality of neurons in a hidden layer to obtain scoring information; the scoring information is activated by an activation function (e.g., softmax) to obtain the user's score.

S5, according to a pre-selected scoring type, one or more basic data labels and risk data labels are respectively selected from the basic data label set and the risk data label set, the weight coefficients of the basic data labels and the risk data labels are obtained, and the basic data scoring and the risk data scoring corresponding to the selected basic data labels and risk data labels are subjected to weight calculation according to the weight coefficients, so that the comprehensive scoring of the user under the scoring type is obtained.

In the embodiment of the present invention, the scoring types are different types of user scores obtained according to user data analysis, for example: user wasting score, user attrition likelihood score, etc.

In the embodiment of the present invention, the step of selecting the basic data score and the risk data score according to the preset score type is similar to the step of classifying the data tags into the basic data tag set and the risk data tag set according to the preset data type, and thus, redundant description is omitted here.

Further, in the embodiment of the present invention, the obtaining the weight coefficients of the basic data tags and the risk data tags, and performing weight calculation on the scores corresponding to the selected basic data tags and the selected risk data tags according to the weight coefficients includes:

wherein G is the comprehensive score of the user under the score type, n is the number of data tags, and Q_iScoring the base data of the ith data tag, P_iAnd scoring the risk data of the ith data label, wherein alpha is a weight coefficient corresponding to the preset basic data score, and beta is a weight coefficient corresponding to the preset risk data score.

For example, the score type needs to be obtained as a score of the user loss probability, and the basic data score and the corresponding weight coefficient selected in the embodiment of the present invention are as follows: the marital condition score is 90, the weight coefficient is 0.1, the academic score is 60, the weight coefficient is 0.2, the salary condition score is 80, and the weight coefficient is 0.3; the selected risk data score and the corresponding weight coefficient are: and calculating the data score according to the weight algorithm and the weight coefficient, wherein the result is 69, namely the user loss possibility score, and the loan overdue score is 80, the weight coefficient is 0.2, the liability score is 40 and the weight coefficient is 0.2.

According to the embodiment of the invention, the user data are divided into two types according to the data tags, so that different types of user data are respectively subjected to different calculation methods to obtain scores of corresponding types, and the score calculation efficiency and the score calculation accuracy are improved; different scoring types correspond to different scoring labels, scoring of different scoring types is achieved by scoring the selected different basic data or scoring the risk data, and diversity of generated scores is improved. Therefore, the user scoring method provided by the invention can solve the problems of low user scoring accuracy and low applicability.

Fig. 4 is a functional block diagram of a user scoring apparatus according to an embodiment of the present invention.

The user scoring apparatus 100 according to the present invention may be installed in an electronic device. According to the realized functions, the user scoring device 100 may include a data tag generation module 101, a basic data score generation module 102, a risk data score generation module 103, and a composite score generation module 104. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.

In the present embodiment, the functions regarding the respective modules/units are as follows:

the data tag generation module 101 is configured to obtain user data of a user and generate a data tag of the user data; dividing the data tags into a basic data tag set and a risk data tag set;

the basic data score generating module 102 is configured to calculate a basic data score of each basic data tag in the basic data tag set according to the user data corresponding to the basic data tag set and a corresponding preset optimal parameter;

the risk data score generation module 103 is configured to calculate a risk data score of each risk data tag in the risk data tag set according to the user data corresponding to the risk data tag set and a pre-trained risk score model corresponding to the risk data tag set;

the comprehensive score generation module 104 selects one or more basic data tags and risk data tags from the basic data tag set and risk data tag set respectively according to a preselected score type, obtains weight coefficients of the basic data tags and the risk data tags, and performs weight calculation on the basic data scores and the risk data scores corresponding to the selected basic data tags and risk data tags according to the weight coefficients to obtain a comprehensive score of the user under the score type.

In detail, in the embodiment of the present invention, when the modules in the user scoring device 100 are used, the same technical means as the user scoring method described in fig. 1 to 3 are adopted, and the same technical effects can be produced, which is not described herein again.

Fig. 5 is a schematic structural diagram of an electronic device for implementing a user scoring method according to an embodiment of the present invention.

The electronic device 1 may comprise a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may further comprise a computer program, such as a user scoring program, stored in the memory 11 and executable on the processor 10.

In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same function or different functions, and includes one or more Central Processing Units (CPUs), a microprocessor, a digital Processing chip, a graphics processor, a combination of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device by running or executing programs or modules (e.g., executing a user scoring program, etc.) stored in the memory 11 and calling data stored in the memory 11.

The memory 11 includes at least one type of readable storage medium including flash memory, removable hard disks, multimedia cards, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disks, optical disks, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, for example a removable hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only to store application software installed in the electronic device and various types of data, such as codes of a user rating program, etc., but also to temporarily store data that has been output or will be output.

The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.

The communication interface 13 is used for communication between the electronic device and other devices, and includes a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which are typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.

Fig. 5 only shows an electronic device with components, and it will be understood by a person skilled in the art that the structure shown in fig. 5 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or a combination of certain components, or a different arrangement of components.

For example, although not shown, the electronic device may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management and the like are realized through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.

It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.

The user scoring program stored in the memory 11 of the electronic device 1 is a combination of instructions that, when executed in the processor 10, enable:

acquiring user data of a user and generating a data tag of the user data;

dividing the data tags into a basic data tag set and a risk data tag set;

Specifically, the specific implementation method of the instruction by the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to the drawings, which is not described herein again.

Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).

The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device, may implement:

acquiring user data of a user and generating a data tag of the user data;

dividing the data tags into a basic data tag set and a risk data tag set;

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.

The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.

The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.

Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A user scoring method, the method comprising:

acquiring user data of a user and generating a data tag of the user data;

dividing the data tags into a basic data tag set and a risk data tag set;

2. The user scoring method of claim 1, wherein the obtaining user data for a user comprises:

acquiring identity data of the user;

and integrating the identity data and the expansion data to obtain user data.

3. The user scoring method of claim 1, wherein the generating a data tag for the user data comprises:

extracting paragraph semantics of each of the data segments;

4. The user scoring method according to claim 3, wherein the splitting the user data into a plurality of data segments according to a preset splitter comprises:

counting the position information of a preset separator in the user data;

5. The method of claim 1, wherein the calculating the basic data score of each basic data tag in the basic data tag set according to the user data corresponding to the basic data tag set and the corresponding pre-set optimal parameters comprises:

6. The user scoring method of any one of claims 1 to 5, wherein the calculating a risk data score for each risk data tag in the risk data tag set according to the user data corresponding to the risk data tag set and a corresponding pre-trained risk score model comprises:

7. The user scoring method according to claim 1, wherein the obtaining of the weighting coefficients of the basic data labels and the risk data labels and the weighting calculation of the basic data scores and the risk data scores corresponding to the selected basic data labels and the selected risk data labels according to the weighting coefficients to obtain the comprehensive scores of the user in the scoring types comprise:

8. A user scoring apparatus, the apparatus comprising:

the data label generating module is used for acquiring user data of a user and generating a data label of the user data; dividing the data tags into a basic data tag set and a risk data tag set;

and the comprehensive score generation module is used for respectively selecting one or more basic data tags and risk data tags from the basic data tag set and the risk data tag set according to a preselected score type, acquiring the weight coefficients of the basic data tags and the risk data tags, and performing weight calculation on the basic data scores and the risk data scores corresponding to the selected basic data tags and risk data tags according to the weight coefficients to obtain the comprehensive score of the user under the score type.

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and the number of the first and second groups,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the user scoring method of any one of claims 1 to 7.

10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out a user scoring method according to any one of claims 1 to 7.