CN109409924B - Account scoring system, method, server and computer readable storage medium - Google Patents
Account scoring system, method, server and computer readable storage medium Download PDFInfo
- Publication number
- CN109409924B CN109409924B CN201811023052.5A CN201811023052A CN109409924B CN 109409924 B CN109409924 B CN 109409924B CN 201811023052 A CN201811023052 A CN 201811023052A CN 109409924 B CN109409924 B CN 109409924B
- Authority
- CN
- China
- Prior art keywords
- scoring
- account
- scored
- sub
- main
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention relates to a big data technology, and discloses an account scoring system, an account scoring method, a server and a computer-readable storage medium. When a first server receives a grading request sent by a second server, synchronizing configuration information stored in the second server and business data of accounts to be graded to a big data processing engine; the first server controls the big data processing engine to perform calculation based on the configuration information and the service data of each account to be scored, and scoring scores of each account to be scored are obtained; and the first server synchronizes the scoring value of each account to be scored, which is calculated by the big data processing engine, to the second server as a scoring result. Compared with the prior art, the method can efficiently process huge account data and quickly calculate the score.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an account scoring system, an account scoring method, a server and a computer-readable storage medium.
Background
According to the data of the user account, the user account is scored by adopting a certain scoring rule, so that the quantitative evaluation of the user account can be realized. In addition, data support can be further provided for accurate marketing, user research, personalized service, business decision and the like according to the score of the user account. Based on the above advantages, the user account scoring process is more and more emphasized in various industries.
However, with the expansion of services, the amount of account data to be processed is increasingly huge, and the traditional relational database cannot be used for efficiently processing the huge account data. Therefore, how to improve the efficiency of account score calculation has become a problem to be solved urgently.
Disclosure of Invention
The invention mainly aims to provide an account scoring system, an account scoring method, a server and a computer-readable storage medium, aiming at improving the efficiency of account scoring calculation.
In order to achieve the above object, the present invention provides an account scoring system, which includes a client, a first server, a second server and a big data processing engine, wherein the client is communicatively connected to the second server, and the first server is communicatively connected to the second server and the big data processing engine, respectively, wherein:
the first server includes a memory and a processor, the memory having stored thereon an account scoring program that when executed by the processor performs the steps of:
a first synchronization step: when a scoring request sent by the second server is received, synchronizing configuration information stored in the second server and business data of each account to be scored to a big data processing engine;
a first calculation step: controlling the big data processing engine to perform calculation based on the configuration information and the service data of each account to be scored to obtain a scoring score of each account to be scored;
a second synchronization step: and synchronizing the score value of each account to be scored, which is calculated by the big data processing engine, to the second server as a scoring result.
Preferably, the service data of each account to be scored includes characteristic values of a plurality of sub-scoring items corresponding to the account to be scored, and the configuration information includes a preset mapping relationship between a main scoring item and the sub-scoring items, a main scoring coefficient of each main scoring item, a sub-scoring value calculation rule of each sub-scoring item, and a sub-scoring coefficient;
the first calculating step includes:
a first determination step: controlling the big data processing engine to determine sub-score values of a plurality of sub-score items corresponding to the accounts to be scored according to the sub-score value calculation rule of each sub-score item and the characteristic value of each sub-score item corresponding to each account to be scored;
a second determination step: controlling the big data processing engine to determine a main scoring item corresponding to each account to be scored according to the mapping relation between the main scoring item and the sub scoring items corresponding to each account to be scored;
and (3) query step: controlling the big data processing engine to inquire a main scoring coefficient of a main scoring item corresponding to each account to be scored and a sub scoring coefficient of each sub scoring item corresponding to each account to be scored in the configuration information;
a second calculation step: and controlling the big data processing engine to calculate the scoring value of each account to be scored according to the main scoring coefficient of each main scoring item corresponding to each account to be scored, and the sub-scoring value and the sub-scoring coefficient of each sub-scoring item corresponding to each account to be scored.
Preferably, the second calculating step includes:
controlling the big data processing engine to calculate the main score of each main score corresponding to each account to be scored according to a first calculation formula and the sub score coefficient of each sub score corresponding to each account to be scored, wherein the first calculation formula is as follows:
wherein S is i Representing the main scoring value of the ith main scoring item corresponding to the account to be scored, S i,k A sub-score, W, representing the kth sub-score corresponding to the ith main-score i,k A sub-scoring coefficient representing the kth sub-scoring term corresponding to the ith main scoring term, i e [1,N]，k∈[1，n i ]N represents the total number of main scoring items corresponding to the account to be scored, N i Representing the total number of sub-scoring items corresponding to the ith main scoring item, i, k, n j 、n i Are all positive integers;
controlling the big data processing engine to calculate the score of each account to be scored according to a second calculation formula and the main scoring coefficient and the main scoring score of each main scoring item corresponding to each account to be scored, wherein the second calculation formula is as follows:
wherein S represents the score of an account to be scored, W i A main scoring coefficient representing the ith main scoring item corresponding to the account to be scored, S i And representing the main scoring value of the ith main scoring item corresponding to the account to be scored, wherein N represents the total number of the main scoring items corresponding to the account to be scored, and both i and N are positive integers.
Preferably, the client is configured to:
when a configuration information generation request or a configuration information updating request sent by a user is received, acquiring the configuration information input by the user;
and sending the configuration information to the second server for the second server to store and process the configuration information.
Preferably, the second server is configured to:
receiving a scoring request sent by the client, and forwarding the scoring request to the first server; and (c) a second step of,
and forwarding the scoring result to the client side for the client side to display the scoring result.
In addition, in order to achieve the above object, the present invention further provides an account scoring method, adapted to a first server, including:
a first synchronization step: when a grading request sent by a second server is received, synchronizing configuration information stored in the second server and service data of each account to be graded to a big data processing engine;
a first calculation step: controlling a big data processing engine to perform calculation based on the configuration information and the service data of each account to be scored to obtain the scoring value of each account to be scored;
a second synchronization step: and synchronizing the score value of each account to be scored, which is calculated by the big data processing engine, to a second server as a scoring result.
Preferably, the service data of each account to be scored includes characteristic values of a plurality of sub-scoring items corresponding to the account to be scored, and the configuration information includes a preset mapping relationship between a main scoring item and the sub-scoring items, a main scoring coefficient of each main scoring item, a sub-scoring value calculation rule of each sub-scoring item, and a sub-scoring coefficient;
the first calculating step includes:
a first determination step: controlling the big data processing engine to determine sub-score values of a plurality of sub-score items corresponding to the accounts to be scored according to the sub-score value calculation rule of each sub-score item and the characteristic value of each sub-score item corresponding to each account to be scored;
a second determination step: controlling the big data processing engine to determine a main scoring item corresponding to each account to be scored according to the mapping relation between the main scoring item and the sub scoring items corresponding to each account to be scored;
and (3) query step: controlling the big data processing engine to inquire a main scoring coefficient of a main scoring item corresponding to each account to be scored and a sub scoring coefficient of each sub scoring item corresponding to each account to be scored in the configuration information;
a second calculation step: and controlling the big data processing engine to calculate the scoring value of each account to be scored according to the main scoring coefficient of each main scoring item corresponding to each account to be scored, and the sub-scoring value and the sub-scoring coefficient of each sub-scoring item corresponding to each account to be scored.
Preferably, the second calculating step includes:
controlling a big data processing engine to calculate a main score of each main score corresponding to each account to be scored according to a first calculation formula and the sub-score coefficient of each sub-score corresponding to each account to be scored, wherein the first calculation formula is as follows:
wherein S is i Representing the account to be scored correspondsThe primary score of the ith primary score item of (1), S i,k A sub-score, W, representing the kth sub-score corresponding to the ith main-score i,k A sub-scoring coefficient representing the kth sub-scoring item corresponding to the ith main scoring item, i E [1,N]，k∈[1，n i ]N represents the total number of main scoring items corresponding to the account to be scored, N i Represents the total number of sub-scoring items corresponding to the ith main scoring item, i, k and n j 、n i Are all positive integers;
controlling a big data processing engine to calculate the score of each account to be scored according to a second calculation formula and the main scoring coefficient and the main scoring score of each main scoring item corresponding to each account to be scored, wherein the second calculation formula is as follows:
wherein S represents the score value of an account to be scored, W i A main scoring coefficient representing the ith main scoring item corresponding to the account to be scored, S i And representing the main scoring value of the ith main scoring item corresponding to the account to be scored, wherein N represents the total number of the main scoring items corresponding to the account to be scored, and both i and N are positive integers.
In addition, in order to achieve the above object, the present invention further provides a server, including a memory and a processor, where the memory stores an account scoring program, and the account scoring program, when executed by the processor, implements the following steps:
a first synchronization step: when a grading request sent by a second server is received, synchronizing configuration information stored in the second server and service data of each account to be graded to a big data processing engine;
a first calculation step: controlling a big data processing engine to perform calculation based on the configuration information and the service data of each account to be scored to obtain the scoring value of each account to be scored;
a second synchronization step: and synchronizing the scoring scores of the accounts to be scored, which are calculated by the big data processing engine, to a second server as scoring results.
Preferably, the service data of each account to be scored includes characteristic values of a plurality of sub-scoring items corresponding to the account to be scored, and the configuration information includes a preset mapping relationship between a main scoring item and the sub-scoring items, a main scoring coefficient of each main scoring item, a sub-scoring value calculation rule of each sub-scoring item, and a sub-scoring coefficient;
the first calculating step includes:
a first determination step: controlling the big data processing engine to determine sub-score values of a plurality of sub-score items corresponding to each account to be scored according to a sub-score value calculation rule of each sub-score item and the characteristic value of each sub-score item corresponding to each account to be scored;
a second determination step: controlling the big data processing engine to determine a main scoring item corresponding to each account to be scored according to the mapping relation between the main scoring item and the sub scoring items corresponding to each account to be scored;
and (3) query step: controlling the big data processing engine to inquire a main scoring coefficient of a main scoring item corresponding to each account to be scored and a sub scoring coefficient of each sub scoring item corresponding to each account to be scored in the configuration information;
a second calculation step: and controlling the big data processing engine to calculate the scoring value of each account to be scored according to the main scoring coefficient of each main scoring item corresponding to each account to be scored, and the sub-scoring value and the sub-scoring coefficient of each sub-scoring item corresponding to each account to be scored.
Preferably, the second calculating step includes:
controlling a big data processing engine to calculate a main score of each main score corresponding to each account to be scored according to a first calculation formula and the sub-score coefficient of each sub-score corresponding to each account to be scored, wherein the first calculation formula is as follows:
wherein S is i Represents the main scoring score of the ith main scoring item corresponding to the account to be scored, S i,k A sub-score, W, representing the kth sub-score corresponding to the ith main-score i,k A sub-scoring coefficient representing the kth sub-scoring term corresponding to the ith main scoring term, i e [1,N]，k∈[1，n i ]N represents the total number of main scoring items corresponding to the account to be scored, N i Representing the total number of sub-scoring items corresponding to the ith main scoring item, i, k, n j 、n i Are all positive integers;
controlling a big data processing engine to calculate the score of each account to be scored according to a second calculation formula and the main scoring coefficient and the main scoring score of each main scoring item corresponding to each account to be scored, wherein the second calculation formula is as follows:
wherein S represents the score of an account to be scored, W i A main scoring coefficient representing the ith main scoring item corresponding to the account to be scored, S i And representing the main scoring value of the ith main scoring item corresponding to the account to be scored, N representing the total number of the main scoring items corresponding to the account to be scored, and both i and N are positive integers.
Furthermore, to achieve the above object, the present invention also provides a computer-readable storage medium storing an account scoring program, which is executable by at least one processor to cause the at least one processor to execute the steps of the account scoring method according to any one of the above.
When a first server receives a grading request sent by a second server, synchronizing configuration information stored in the second server and business data of accounts to be graded to a big data processing engine; the first server controls the big data processing engine to execute calculation based on the configuration information and the service data of each account to be scored to obtain the scoring value of each account to be scored; and the first server synchronizes the scoring scores of the accounts to be scored, which are calculated by the big data processing engine, to the second server as scoring results. Compared with the prior art, the first server synchronizes the configuration information and the service data of the account to be scored from the second server to the big data processing engine and controls the big data processing engine to calculate the scoring value. In addition, the configuration information has configurability, so when the calculation rule is changed, the calculation code does not need to be modified, and only the configuration information needs to be updated, thereby being convenient for users to use and being suitable for various application scenes.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
FIG. 1 is a system architecture diagram of a first embodiment of an account scoring system according to the present invention;
FIG. 2 is a schematic diagram of an operating environment of a first embodiment of an account scoring program according to the present invention;
FIG. 3 is a block diagram of a first embodiment of an account scoring process of the present invention;
FIG. 4 is a block diagram of a refinement procedure of the calculation block of FIG. 3;
FIG. 5 is a flowchart illustrating a first embodiment of an account scoring method according to the present invention;
FIG. 6 is a detailed flowchart of step S20 in FIG. 5;
fig. 7 is a flowchart illustrating an account scoring method according to a second embodiment of the present invention.
The implementation, functional features and advantages of the present invention will be further described with reference to the accompanying drawings.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
Fig. 1 is a schematic diagram of a system architecture of the account scoring system according to the first embodiment of the present invention.
In this embodiment, the account scoring system includes a first server 1, a big data processing engine 2 (e.g., hive is a data warehouse infrastructure based on distribution is a storage system), a second server 3 (e.g., oracle server, oracle is a relational database management system of Oracle corporation), and a client 4, where the client 4 is communicatively connected to the second server 3, and the first server 1 is communicatively connected to the second server 3 and the big data processing engine 2, respectively, where:
the first server 1 is configured to:
when a scoring request sent by the second server 3 is received, synchronizing the configuration information stored in the second server 3 and the service data of each account to be scored to a big data processing engine 2;
controlling the big data processing engine 2 to perform calculation based on the configuration information and the service data of each account to be scored to obtain the scoring value of each account to be scored;
and synchronizing the score of each account to be scored, which is calculated by the big data processing engine 2, to the second server 3 as a scoring result.
The first server 1 can implement data synchronization between the second server 3 and the big data processing engine 2 by running a pre-stored synchronization script.
In addition, the first server 1 may control the big data processing engine 2 to perform calculation based on the configuration information and the service data of each account to be scored by running a pre-stored calculation script.
In this embodiment, when receiving a scoring request sent by the second server 3, the first server 1 synchronizes configuration information stored in the second server 3 and service data of each account to be scored to the big data processing engine 2; the first server 1 controls the big data processing engine 2 to execute calculation based on the configuration information and the service data of each account to be scored to obtain the scoring value of each account to be scored; and the first server 1 synchronizes the scoring scores of the accounts to be scored, which are calculated by the big data processing engine 2, to the second server 3 as scoring results. Compared with the prior art, in the embodiment, the first server 1 synchronizes the configuration information and the service data of the account to be scored from the second server 3 to the big data processing engine 2, and controls the big data processing engine 2 to calculate the score, because the big data processing engine 2 has a strong data processing capability, huge account data can be efficiently processed, and the score can be quickly calculated. In addition, the configuration information has configurability, so when the calculation rule is changed, the calculation code does not need to be modified, and only the configuration information needs to be updated, thereby being convenient for users to use and being suitable for various application scenes.
Further, in this embodiment, the service data of each account to be scored includes feature values of a plurality of sub-scoring items corresponding to the account to be scored, and the configuration information includes a preset mapping relationship between a main scoring item and the sub-scoring items, a main scoring coefficient of each main scoring item, a sub-scoring value calculation rule of each sub-scoring item, and a sub-scoring coefficient.
The main score items may be, for example: account, order, wind control.
The sub-scoring items corresponding to the main scoring item "account" include, but are not limited to, user age, account age, and card holding number.
The sub-scoring items corresponding to the main scoring item "order form" include, but are not limited to, active days, order placing activity, days of the day until the last order is placed, product class number, total order amount, daily average number, average order amount, successful payment pen number, order conversion rate, and large account ratio.
The sub-scoring items corresponding to the main scoring item "wind control" include, but are not limited to, a hit rule rate and a wind control interception rate.
Further, in this embodiment, the first server 1 is further configured to:
controlling the big data processing engine 2 to determine sub-score values of a plurality of sub-score items corresponding to the accounts to be scored according to the sub-score value calculation rule of each sub-score item and the characteristic value of each sub-score item corresponding to each account to be scored;
controlling the big data processing engine 2 to determine a main scoring item corresponding to each account to be scored according to the mapping relation between the main scoring item and the sub scoring items corresponding to each account to be scored;
controlling the big data processing engine 2 to inquire a main scoring coefficient of a main scoring item corresponding to each account to be scored and a sub scoring coefficient of each sub scoring item corresponding to each account to be scored in the configuration information;
and controlling the big data processing engine 2 to calculate the scoring value of each account to be scored according to the main scoring coefficient of each main scoring item corresponding to each account to be scored, and the sub-scoring value and the sub-scoring coefficient of each sub-scoring item corresponding to each account to be scored.
Further, in this embodiment, the configuration information further includes a plurality of feature value ranges corresponding to each sub-score item, and a mapping relationship between the sub-score value and the feature value range of the sub-score item, where the sub-score value calculation rule of each sub-score item includes:
determining the characteristic value range of the characteristic value of each sub-scoring item corresponding to each account to be scored according to a plurality of characteristic value ranges corresponding to each sub-scoring item pre-stored in the configuration information, and determining the sub-scoring value of each sub-scoring item corresponding to each account to be scored according to the mapping relation between the sub-scoring value pre-stored in the configuration information and the characteristic value range of the sub-scoring item.
Further, in this embodiment, the first server 1 is further configured to:
controlling the big data processing engine 2 to calculate the main score of each main score corresponding to each account to be scored according to a first calculation formula, and the sub score coefficient of each sub score corresponding to each account to be scored, where the first calculation formula is as follows:
wherein S is i Representing the main scoring value of the ith main scoring item corresponding to the account to be scored, S i,k A sub-score, W, representing the kth sub-score corresponding to the ith main-score i,k A sub-scoring coefficient representing the kth sub-scoring term corresponding to the ith main scoring term, i e [1,N]，k∈[1，n i ]N represents the total number of main scoring items corresponding to the account to be scored, N i Representing the total number of sub-scoring items corresponding to the ith main scoring item, i, k, n j 、n i Are all positive integers;
controlling the big data processing engine 2 to calculate the score of each account to be scored according to a second calculation formula and the main scoring coefficient and the main scoring score of each main scoring item corresponding to each account to be scored, wherein the second calculation formula is as follows:
wherein S represents the score of an account to be scored, W i A main scoring coefficient representing the ith main scoring item corresponding to the account to be scored, S i Representing the main scoring value of the ith main scoring item corresponding to the account to be scoredAnd N represents the total number of the main scoring items corresponding to the account to be scored, and i and N are positive integers.
Further, in this embodiment, the client 4 is configured to:
when a configuration information generation request or a configuration information updating request sent by a user is received, acquiring the configuration information input by the user;
sending the configuration information to the second server 3.
The second server 3 is configured to:
and receiving the configuration information sent by the client 4, and storing the configuration information.
In the embodiment, the user can set the configuration information according to specific needs without modifying the calculation code again, so that the user operation is simplified, and the method is suitable for various application scenarios.
In this embodiment, the client 4 is further configured to:
sending the scoring request to the second server 3; and receiving the scoring result returned by the second server 3.
The second server 3 is configured to:
receiving a scoring request sent by the client 4, and forwarding the scoring request to the first server 1; and the number of the first and second groups,
and forwarding the grading result to the client 4 for the client 4 to display the grading result.
The invention provides an account scoring program.
Please refer to fig. 2, which is a schematic view of an operating environment of the account scoring program 10 according to the first embodiment of the present invention.
In this embodiment, the account scoring program 10 is installed and run in the first server 1. The first server 1 may include, but is not limited to, a memory 11 and a processor 12 that communicate with each other via a program bus. Fig. 2 only shows the first server 1 with components 11, 12, but it is to be understood that not all shown components are required to be implemented, and that more or fewer components may be implemented instead.
The storage 11 may in some embodiments be an internal storage unit of the first server 1, such as a hard disk or a memory of the first server 1. The memory 11 may also be an external storage device of the first server 1 in other embodiments, such as a plug-in hard disk provided on the first server 1, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. Further, the memory 11 may also include both an internal storage unit of the first server 1 and an external storage device. The memory 11 is used for storing application software installed in the first server 1 and various data, such as program codes of the account scoring program 10. The memory 11 may also be used to temporarily store data that has been output or is to be output.
Processor 12, which in some embodiments may be a Central Processing Unit (CPU), microprocessor or other data Processing chip, operates program code stored in memory 11 or processes data, such as executing account scoring program 10.
Please refer to fig. 3, which is a block diagram of the account scoring program 10 according to the first embodiment of the present invention. In this embodiment, the account scoring program 10 may be divided into one or more modules, and the one or more modules are stored in the memory 11 and executed by one or more processors (in this embodiment, the processor 12) to complete the present invention. For example, in fig. 3, the account scoring program 10 may be partitioned into a first synchronization module 101, a calculation module 102, and a second synchronization module 103. The module referred to in the present invention refers to a series of computer program request segments capable of performing specific functions, and is more suitable than the program for describing the execution process of the account scoring program 10 in the first server 1, wherein:
and the first synchronization module 101 is configured to synchronize the configuration information stored in the second server and the service data of each account to be scored to a big data processing engine when the scoring request sent by the second server is received.
The scoring request is sent to the second server by the client, and is forwarded and sent to the first synchronization module 101 by the second server.
And the calculating module 102 is configured to control the big data processing engine to perform calculation based on the configuration information and the service data of each account to be scored, so as to obtain a scoring score of each account to be scored.
The calculation module 102 may control the big data processing engine to perform calculation based on the configuration information and the service data of each account to be scored by running a pre-stored calculation script.
Further, in this embodiment, the service data of each account to be scored includes feature values of a plurality of sub-scoring items corresponding to the account to be scored, and the configuration information includes a preset mapping relationship between a main scoring item and the sub-scoring items, a main scoring coefficient of each main scoring item, a sub-scoring value calculation rule of each sub-scoring item, and a sub-scoring coefficient.
The main score items may be, for example: account, order, wind control.
The sub-scoring items corresponding to the main scoring item "account" include, but are not limited to, user age, account age, and card number.
The sub-scoring items corresponding to the main scoring item "order form" include, but are not limited to, active days, order placing activity, days of the day until the last order is placed, product class number, total order amount, daily average number, average order amount, successful payment pen number, order conversion rate, and large account ratio.
The sub-scoring items corresponding to the main scoring item "wind control" include, but are not limited to, a hit rule rate and a wind control interception rate.
Further, referring to fig. 4, in this embodiment, the calculating module 102 includes: a first determining unit 1021, a second determining unit 1022, a querying unit 1023 and a calculating unit 1024, wherein:
the first determining unit 1021 is configured to control the big data processing engine to determine sub-score values of a plurality of sub-score items corresponding to each account to be scored according to a sub-score value calculation rule of each sub-score item and a feature value of each sub-score item corresponding to each account to be scored.
Further, in this embodiment, the configuration information further includes a plurality of feature value ranges corresponding to the sub-score items, and a mapping relationship between the sub-score items and the feature value ranges of the sub-score items.
The sub-score calculation rule of each sub-score item comprises the following steps:
determining the characteristic value range of the characteristic value of each sub-scoring item corresponding to each account to be scored according to a plurality of characteristic value ranges corresponding to the sub-scoring items pre-stored in the configuration information, and determining the sub-scoring value of each sub-scoring item corresponding to each account to be scored according to the mapping relation between the sub-scoring value pre-stored in the configuration information and the characteristic value range of the sub-scoring item.
The second determining unit 1022 is configured to control the big data processing engine to determine the main scoring item corresponding to each account to be scored according to the mapping relationship between the main scoring item and the sub scoring items corresponding to each account to be scored.
The query unit 1023 is configured to control the big data processing engine to query, in the configuration information, a main scoring coefficient of a main scoring item corresponding to each account to be scored and a sub scoring coefficient of each sub scoring item corresponding to each account to be scored.
The calculating unit 1024 is configured to control the big data processing engine to calculate the score of each account to be scored according to the main scoring coefficient of each main scoring item corresponding to each account to be scored, and the sub-scoring score and the sub-scoring coefficient of each sub-scoring item corresponding to each account to be scored.
Further, in this embodiment, the calculating unit 1024 is further configured to:
controlling the big data processing engine to calculate the main score of each main score corresponding to each account to be scored according to a first calculation formula and the sub score coefficient of each sub score corresponding to each account to be scored, wherein the first calculation formula is as follows:
wherein S is i Representing the main scoring value of the ith main scoring item corresponding to the account to be scored, S i,k A sub-score, W, representing the kth sub-score corresponding to the ith main-score i,k A sub-scoring coefficient representing the kth sub-scoring term corresponding to the ith main scoring term, i e [1,N]，k∈[1，n i ]N represents the total number of main scoring items corresponding to the account to be scored, N i Representing the total number of sub-scoring items corresponding to the ith main scoring item, i, k, n j 、n i Are all positive integers.
Controlling the big data processing engine to calculate the score of each account to be scored according to a second calculation formula and the main scoring coefficient and the main scoring score of each main scoring item corresponding to each account to be scored, wherein the second calculation formula is as follows:
wherein S represents the score of an account to be scored, W i A main scoring coefficient representing the ith main scoring item corresponding to the account to be scored, S i And representing the main scoring value of the ith main scoring item corresponding to the account to be scored, wherein N represents the total number of the main scoring items corresponding to the account to be scored, and both i and N are positive integers.
It should be noted that, the calling order of the first determining unit 1021, the second determining unit 1022 and the querying unit 1023 is not limited in this embodiment, and may be set according to a specific application scenario.
And the calculating module 103 is configured to synchronize the score of each account to be scored, which is calculated by the big data processing engine, to the second server as a scoring result, so that the second server forwards the scoring result to the client for display.
The first synchronization module 101 and the second synchronization module 103 may implement data synchronization between the second server and the big data processing engine by running a pre-stored synchronization script.
In this embodiment, when a scoring request sent by the second server is received, the configuration information stored in the second server and the service data of each account to be scored are synchronized to a big data processing engine; controlling the big data processing engine to perform calculation based on the configuration information and the service data of each account to be scored to obtain a scoring score of each account to be scored; and synchronizing the scoring scores of the accounts to be scored, which are calculated by the big data processing engine, to the second server as scoring results. Compared with the prior art, the configuration information and the service data of the account to be scored are synchronized to the big data processing engine from the second server, and the big data processing engine is controlled to calculate the scoring value. In addition, the configuration information has configurability, so when the calculation rule is changed, the calculation code does not need to be modified, and only the configuration information needs to be updated, thereby being convenient for users to use and being suitable for various application scenes.
In addition, the invention provides an account scoring method.
As shown in fig. 5, fig. 5 is a flowchart illustrating an account scoring method according to a first embodiment of the present invention.
In this embodiment, the method includes:
and step S10, when receiving the scoring request sent by the second server, the first server synchronizes the configuration information stored in the second server and the service data of each account to be scored to a big data processing engine.
The first server can realize the data synchronization of the second server and the big data processing engine by running a pre-stored synchronization script.
Further, in this embodiment, before step S10, the method further includes the steps of:
and the client sends a scoring request to a second server for the second server to transfer and send the scoring request to the first server.
Step S20, the first server controls the big data processing engine to execute calculation based on the configuration information and the service data of each account to be scored, and scoring values of the accounts to be scored are obtained.
The first server can control the big data processing engine to execute calculation based on the configuration information and the service data of each account to be scored by running a pre-stored calculation script.
Further, in this embodiment, the service data of each account to be scored includes characteristic values of a plurality of sub-scoring items corresponding to the account to be scored, and the configuration information includes a preset mapping relationship between a main scoring item and the sub-scoring items, a main scoring coefficient of each main scoring item, a sub-scoring value calculation rule of each sub-scoring item, and a sub-scoring coefficient.
The main score items may be, for example: account, order, wind control.
The sub-scoring items corresponding to the main scoring item "account" include, but are not limited to, user age, account age, and card number.
The sub-scoring items corresponding to the main scoring item "order" include, but are not limited to, active days, order placing activity, days of the day of the last order placing, product class number, total order amount, average daily number, average order amount, successful payment amount, number of successful payment strokes, order conversion rate, and large amount ratio.
The sub-scoring items corresponding to the main scoring item "wind control" include, but are not limited to, a hit rule rate and a wind control interception rate.
Further, referring to fig. 6, in this embodiment, the step S20 includes:
step S21, the first server controls the big data processing engine to determine the sub-score values of a plurality of sub-score items corresponding to the accounts to be scored according to the sub-score value calculation rule of each sub-score item and the characteristic value of each sub-score item corresponding to each account to be scored.
Further, in this embodiment, the configuration information further includes a plurality of feature value ranges corresponding to the sub-score items, and a mapping relationship between the sub-score items and the feature value ranges of the sub-score items.
The sub-score calculation rule of each sub-score item comprises the following steps:
determining the characteristic value range of the characteristic value of each sub-scoring item corresponding to each account to be scored according to a plurality of characteristic value ranges corresponding to the sub-scoring items pre-stored in the configuration information, and determining the sub-scoring value of each sub-scoring item corresponding to each account to be scored according to the mapping relation between the sub-scoring value pre-stored in the configuration information and the characteristic value range of the sub-scoring item.
Step S22, the first server controls the big data processing engine to determine the main scoring item corresponding to each account to be scored according to the mapping relation between the main scoring item and the sub scoring items corresponding to each account to be scored.
Step S23, the first server controls the big data processing engine to query, in the configuration information, a main scoring coefficient of a main scoring item corresponding to each account to be scored and a sub scoring coefficient of each sub scoring item corresponding to each account to be scored.
And S24, the first server controls the big data processing engine to calculate the scoring value of each account to be scored according to the main scoring coefficient of each main scoring item corresponding to each account to be scored, the sub-scoring value and the sub-scoring coefficient of each sub-scoring item corresponding to each account to be scored.
Further, in this embodiment, the step S24 includes:
the first server controls the big data processing engine to calculate the main scoring value of each main scoring item corresponding to each account to be scored according to a first calculation formula and the sub scoring value and the sub scoring coefficient of each sub scoring item corresponding to each account to be scored, wherein the first calculation formula is as follows:
wherein S is i Represents the main scoring score of the ith main scoring item corresponding to the account to be scored, S i,k A sub-score, W, representing the kth sub-score corresponding to the ith main-score i,k A sub-scoring coefficient representing the kth sub-scoring item corresponding to the ith main scoring item, i E [1,N]，k∈[1，n i ]N represents the total number of main scoring items corresponding to the account to be scored, N i Representing the total number of sub-scoring items corresponding to the ith main scoring item, i, k, n j 、n i Are all positive integers.
The first server controls the big data processing engine to calculate the scoring value of each account to be scored according to a second calculation formula and the main scoring coefficient and the main scoring value of each main scoring item corresponding to each account to be scored, wherein the second calculation formula is as follows:
wherein S represents the score of an account to be scored, W i A main scoring coefficient representing the ith main scoring item corresponding to the account to be scored, S i And representing the main scoring value of the ith main scoring item corresponding to the account to be scored, wherein N represents the total number of the main scoring items corresponding to the account to be scored, and both i and N are positive integers.
It should be noted that, in this embodiment, the execution sequence of steps S21, S22, and S23 is not limited, and may be set according to a specific application scenario.
And step S30, the first server synchronizes score values of the accounts to be scored, which are calculated by the big data processing engine and are used as scoring results, to the second server.
Further, in this embodiment, after step S30, the method further includes the steps of:
and the second server transmits the grading result to the client side for the client side to display the grading result.
In this embodiment, when receiving a scoring request sent by the second server, the first server synchronizes configuration information stored in the second server and service data of each account to be scored to a big data processing engine; the first server controls the big data processing engine to perform calculation based on the configuration information and the service data of each account to be scored, and scoring scores of each account to be scored are obtained; and the first server synchronizes the score of each account to be scored, which is calculated by the big data processing engine, to the second server as a scoring result. Compared with the prior art, in the embodiment, the first server synchronizes the configuration information and the service data of the account to be scored from the second server to the big data processing engine and controls the big data processing engine to calculate the scoring value. In addition, the configuration information has configurability, so when the calculation rule is changed, the calculation code does not need to be modified, and only the configuration information needs to be updated, thereby being convenient for users to use and being suitable for various application scenes.
Fig. 7 is a flowchart illustrating an account scoring method according to a second embodiment of the present invention, shown in fig. 7.
This embodiment is based on the first embodiment, and the method further includes:
step S40, when receiving a configuration information generation request or a configuration information update request sent by a user, the client acquires the configuration information input by the user.
And step S50, the client sends the configuration information to the second server for the second server to store and process the configuration information.
In the embodiment, the user can set the configuration information according to specific needs without modifying the calculation code again, so that the user operation is simplified, and the method is suitable for various application scenarios.
Further, the present invention also provides a computer-readable storage medium storing an account scoring program, which is executable by at least one processor to cause the at least one processor to execute the steps of the account scoring method in the first embodiment.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all modifications and equivalents of the present invention, which are made by the contents of the present specification and the accompanying drawings, or directly/indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (8)
1. An account scoring system, comprising a client, a first server, a second server and a big data processing engine, wherein the client is communicatively connected with the second server, and the first server is communicatively connected with the second server and the big data processing engine respectively, wherein:
the first server includes a memory and a processor, the memory having stored thereon an account scoring program that when executed by the processor performs the steps of:
a first synchronization step: when a grading request sent by the second server is received, synchronizing configuration information stored in the second server and service data of each account to be graded to a big data processing engine;
a first calculation step: controlling the big data processing engine to perform calculation based on the configuration information and the service data of each account to be scored to obtain the scoring value of each account to be scored;
a second synchronization step: synchronizing the scoring scores of the accounts to be scored, which are calculated by the big data processing engine, to the second server as scoring results;
the service data of each account to be scored comprises characteristic values of a plurality of sub-scoring items corresponding to the account to be scored, and the configuration information comprises preset mapping relations between main scoring items and the sub-scoring items, main scoring coefficients of the main scoring items, sub-scoring value calculation rules of the sub-scoring items and the sub-scoring coefficients;
the first calculating step includes: a first determination step: controlling the big data processing engine to determine sub-score values of a plurality of sub-score items corresponding to the accounts to be scored according to the sub-score value calculation rule of each sub-score item and the characteristic value of each sub-score item corresponding to each account to be scored; a second determination step: controlling the big data processing engine to determine a main scoring item corresponding to each account to be scored according to the mapping relation between the main scoring item and the sub scoring items corresponding to each account to be scored; and (3) query step: controlling the big data processing engine to inquire a main scoring coefficient of a main scoring item corresponding to each account to be scored and a sub scoring coefficient of each sub scoring item corresponding to each account to be scored in the configuration information; a second calculation step: and controlling the big data processing engine to calculate the scoring value of each account to be scored according to the main scoring coefficient of each main scoring item corresponding to each account to be scored, and the sub-scoring value and the sub-scoring coefficient of each sub-scoring item corresponding to each account to be scored.
2. The account scoring system of claim 1, wherein the second calculating step comprises:
controlling the big data processing engine to calculate a main score of each main score corresponding to each account to be scored according to a first calculation formula, and the sub-score coefficient of each sub-score corresponding to each account to be scored, wherein the first calculation formula is as follows:
wherein S is i Representing the main scoring value of the ith main scoring item corresponding to the account to be scored, S i,k A sub-score, W, representing the kth sub-score corresponding to the ith main-score i,k A sub-scoring coefficient representing the kth sub-scoring term corresponding to the ith main scoring term, i e [1,N]，k∈[1，n i ]N represents the total number of the main scoring items corresponding to the account to be scored, N i Representing the total number of sub-scoring items corresponding to the ith main scoring item, i, k, n j 、n i Are all positive integers;
controlling the big data processing engine to calculate the score of each account to be scored according to a second calculation formula and the main scoring coefficient and the main scoring score of each main scoring item corresponding to each account to be scored, wherein the second calculation formula is as follows:
wherein S represents the score value of an account to be scored, W i A main scoring coefficient representing the ith main scoring item corresponding to the account to be scored, S i And representing the main scoring value of the ith main scoring item corresponding to the account to be scored, wherein N represents the total number of the main scoring items corresponding to the account to be scored, and both i and N are positive integers.
3. An account scoring system according to claim 1 or 2, wherein the client is configured to:
when a configuration information generation request or a configuration information updating request sent by a user is received, acquiring the configuration information input by the user;
and sending the configuration information to the second server for the second server to store and process the configuration information.
4. An account scoring system according to claim 1 or 2, wherein the second server is operable to:
receiving a grading request sent by the client, and forwarding the grading request to the first server; and (c) a second step of,
and transmitting the grading result to the client in a transfer way, so that the client can display the grading result.
5. An account scoring method applied to a first server is characterized by comprising the following steps:
a first synchronization step: when a grading request sent by a second server is received, synchronizing configuration information stored in the second server and service data of each account to be graded to a big data processing engine;
a first calculation step: controlling a big data processing engine to perform calculation based on the configuration information and the service data of each account to be scored to obtain a scoring score of each account to be scored;
a second synchronization step: synchronizing the scoring scores of the accounts to be scored, which are calculated by the big data processing engine, to a second server as scoring results;
the service data of each account to be scored comprises characteristic values of a plurality of sub-scoring items corresponding to the account to be scored, and the configuration information comprises preset mapping relations between main scoring items and the sub-scoring items, main scoring coefficients of the main scoring items, sub-scoring value calculation rules of the sub-scoring items and the sub-scoring coefficients;
the first calculating step includes: a first determination step: controlling a big data processing engine to determine sub-score values of a plurality of sub-score items corresponding to the accounts to be scored according to the sub-score value calculation rule of each sub-score item and the characteristic value of each sub-score item corresponding to each account to be scored; a second determination step: controlling a big data processing engine to determine a main scoring item corresponding to each account to be scored according to the mapping relation between the main scoring item and the sub scoring items corresponding to each account to be scored; and (3) query step: controlling a big data processing engine to inquire a main scoring coefficient of a main scoring item corresponding to each account to be scored and a sub scoring coefficient of each sub scoring item corresponding to each account to be scored in the configuration information; a second calculation step: and controlling a big data processing engine to calculate the scoring value of each account to be scored according to the main scoring coefficient of each main scoring item corresponding to each account to be scored, and the sub-scoring value and the sub-scoring coefficient of each sub-scoring item corresponding to each account to be scored.
6. The account scoring method of claim 5, wherein the second calculating step comprises:
controlling a big data processing engine to calculate a main score of each main score corresponding to each account to be scored according to a first calculation formula and the sub-score coefficient of each sub-score corresponding to each account to be scored, wherein the first calculation formula is as follows:
wherein S is i Represents the main scoring score of the ith main scoring item corresponding to the account to be scored, S i,k A sub-score, W, representing the kth sub-score corresponding to the ith main-score i,k A sub-scoring coefficient representing the kth sub-scoring term corresponding to the ith main scoring term, i e [1,N]，k∈[1，n i ]N represents the total number of the main scoring items corresponding to the account to be scored, N i Represents the total number of sub-scoring items corresponding to the ith main scoring item, i, k and n j 、n i Are all positive integers;
controlling a big data processing engine to calculate the score of each account to be scored according to a second calculation formula and the main scoring coefficient and the main scoring score of each main scoring item corresponding to each account to be scored, wherein the second calculation formula is as follows:
wherein S represents the score value of an account to be scored, W i A main scoring coefficient representing the ith main scoring item corresponding to the account to be scored, S i And representing the main scoring value of the ith main scoring item corresponding to the account to be scored, wherein N represents the total number of the main scoring items corresponding to the account to be scored, and both i and N are positive integers.
7. A server comprising a memory and a processor, wherein the memory has stored thereon an account scoring program that, when executed by the processor, performs the steps of the account scoring method of claim 5 or 6.
8. A computer-readable storage medium storing an account scoring program executable by at least one processor to cause the at least one processor to perform the steps of the account scoring method of claim 5 or 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811023052.5A CN109409924B (en) | 2018-09-03 | 2018-09-03 | Account scoring system, method, server and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811023052.5A CN109409924B (en) | 2018-09-03 | 2018-09-03 | Account scoring system, method, server and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109409924A CN109409924A (en) | 2019-03-01 |
| CN109409924B true CN109409924B (en) | 2023-04-18 |
Family
ID=65463786
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811023052.5A Active CN109409924B (en) | 2018-09-03 | 2018-09-03 | Account scoring system, method, server and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109409924B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110866698A (en) * | 2019-11-14 | 2020-03-06 | 北京京东尚科信息技术有限公司 | Device for assessing service score of service provider |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107273540A (en) * | 2017-07-05 | 2017-10-20 | 北京三快在线科技有限公司 | Distributed search and index updating method, system, server and computer equipment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009107628A1 (en) * | 2008-02-27 | 2009-09-03 | 日本電気株式会社 | Retrieval system, retrieval method, and program |
| US10110634B2 (en) * | 2016-02-04 | 2018-10-23 | Amadeus S.A.S. | Monitoring user authenticity in distributed system |
| US10326787B2 (en) * | 2017-02-15 | 2019-06-18 | Microsoft Technology Licensing, Llc | System and method for detecting anomalies including detection and removal of outliers associated with network traffic to cloud applications |
-
2018
- 2018-09-03 CN CN201811023052.5A patent/CN109409924B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107273540A (en) * | 2017-07-05 | 2017-10-20 | 北京三快在线科技有限公司 | Distributed search and index updating method, system, server and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109409924A (en) | 2019-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2016382908B2 (en) | Short link processing method, device and server | |
| US10459978B2 (en) | Distributed graph processing system that support remote data read with proactive bulk data transfer | |
| CN108924250B (en) | Service request processing method and device based on block chain and computer equipment | |
| US9934263B1 (en) | Big-fast data connector between in-memory database system and data warehouse system | |
| WO2021042515A1 (en) | Graph data storage and query method and apparatus, and computer-readable storage medium | |
| EP1638018A2 (en) | Multistep master data cleansing in operative business process | |
| CN107038182B (en) | Method and device for checking completeness of sub-table data | |
| KR20140112427A (en) | Low latency query engine for apache hadoop | |
| CN111241061B (en) | Writing method of state database, data processing device and storage medium | |
| WO2020000720A1 (en) | Server, packet processing method, program, and computer-readable storage medium | |
| CN112637305B (en) | Data storage and query method, device, equipment and medium based on cache | |
| CN103761102B (en) | A kind of uniform data service platform and its implementation | |
| US11221986B2 (en) | Data management method and data analysis system | |
| CN104252501A (en) | Computing equipment and method for executing database operating command | |
| CN110019873B (en) | Face data processing method, device and equipment | |
| CN109409924B (en) | Account scoring system, method, server and computer readable storage medium | |
| US20140108367A1 (en) | Client apparatus and database server for resumable transaction and method thereof | |
| US20180018385A1 (en) | System, data combining method, integration server, data combining program, database system ,database system cooperation method, and database system cooperation program | |
| WO2022156087A1 (en) | Data blood relationship establishing method and apparatus, computer device, and storage medium | |
| CN113590703B (en) | ES data importing method and device, electronic equipment and readable storage medium | |
| CN111782157A (en) | Express bill printing management method, device and system | |
| JP2014041501A (en) | Fast reading method for batch processing target data and batch management system | |
| CN112527900A (en) | Method, device, equipment and medium for database multi-copy reading consistency | |
| CN114547184A (en) | Personnel information synchronization method, terminal device and storage medium | |
| CN110737662A (en) | data analysis method, device, server and computer storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |