CN114817323A - Rule pool generation method and device, electronic equipment and storage medium - Google Patents
Rule pool generation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114817323A CN114817323A CN202210376812.0A CN202210376812A CN114817323A CN 114817323 A CN114817323 A CN 114817323A CN 202210376812 A CN202210376812 A CN 202210376812A CN 114817323 A CN114817323 A CN 114817323A
- Authority
- CN
- China
- Prior art keywords
- rule
- pool
- sample set
- preset algorithm
- target
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24564—Applying rules; Deductive queries
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明实施例涉及一种规则池生成方法、装置、电子设备及存储介质，包括：获取第一样本集；调用第一预设算法库，以根据第一样本集构建第一样本集对应的第一规则池，第一预设算法库中的每个第一预设算法用于构建单变量规则；调用第二预设算法库，以根据第一样本集构建第一样本集对应的第二规则池，第二预设算法库中的每个第二预设算法用于构建多变量规则；融合第一规则池和第二规则池，得到第一样本集对应的目标规则池。由此，本发明提高了规则池构建的效率，并且不依赖于业务经验和专家经验，使得所构建的规则池更为全面。
Embodiments of the present invention relate to a method, apparatus, electronic device, and storage medium for generating a rule pool, including: acquiring a first sample set; calling a first preset algorithm library to construct a first sample set according to the first sample set In the corresponding first rule pool, each first preset algorithm in the first preset algorithm library is used to construct a univariate rule; the second preset algorithm library is called to construct the first sample set according to the first sample set The corresponding second rule pool, each second preset algorithm in the second preset algorithm library is used to construct a multivariate rule; fuse the first rule pool and the second rule pool to obtain the target rule corresponding to the first sample set pool. Thus, the present invention improves the efficiency of rule pool construction, and does not depend on business experience and expert experience, so that the constructed rule pool is more comprehensive.
Description
Technical Field
The embodiment of the invention relates to the technical field of wind control, in particular to a rule pool generation method and device, electronic equipment and a storage medium.
Background
At present, business personnel usually rely on business experience and expert experience to construct a rule pool containing univariate rules and multivariate rules, but the formulation of the rule pool is easily influenced by personal sensibility, so that the obtained rules are incomplete, and when new variables are met, a lot of time is spent on trying different segmentation schemes and variable combination modes to construct the rule pool, so that the construction efficiency of the rule pool is low.
Disclosure of Invention
In view of this, to solve the technical problems or some technical problems, embodiments of the present invention provide a method and an apparatus for generating a rule pool, an electronic device, and a storage medium.
In a first aspect, an embodiment of the present invention provides a method for generating a rule pool, including:
acquiring a first sample set;
calling a first preset algorithm library to construct a first rule pool corresponding to the first sample set according to the first sample set, wherein each first preset algorithm in the first preset algorithm library is used for constructing a univariate rule;
calling a second preset algorithm library to construct a second rule pool corresponding to the first sample set according to the first sample set, wherein each second preset algorithm in the second preset algorithm library is used for constructing a multi-variable rule;
and fusing the first rule pool and the second rule pool to obtain a target rule pool corresponding to the first sample set.
In a possible embodiment, the fusing the first rule pool and the second rule pool to obtain the target rule pool includes:
executing deduplication operation on all first rules in the first rule pool to obtain a first deduplication result;
executing deduplication operation on all second rules in the second rule pool to obtain a second deduplication result;
and fusing the first duplicate removal result and the second duplicate removal result to obtain a target rule pool corresponding to the first sample set.
In one possible embodiment, the method further comprises:
for each target rule in the target rule pool, determining an index value corresponding to the target rule according to the first sample set to obtain an index value set corresponding to the target rule pool;
and determining at least one target rule corresponding to the preset index value set from the target rule pool according to the index value set.
In a possible embodiment, the determining an index value corresponding to the target rule according to the first sample set includes:
determining a rule hit result of each target rule in the target rule pool according to the first sample set;
and determining an index value corresponding to each target rule in the target rule pool according to the hit result of each rule.
In a possible embodiment, the invoking a first preset algorithm library to construct a first rule pool corresponding to the first sample set according to the first sample set includes:
and calling the first preset algorithm aiming at each first preset algorithm in the first preset algorithm library so as to construct at least one first rule corresponding to the first sample set according to the first sample set, and obtain a first rule pool corresponding to the first sample set.
In a possible embodiment, the invoking a second preset algorithm library to construct a second rule pool corresponding to the first sample set according to the first sample set includes:
and calling the second preset algorithm aiming at each second preset algorithm in the second preset algorithm library so as to construct at least one second rule corresponding to the first sample set according to the first sample set and obtain a second rule pool corresponding to the second sample set.
In one possible embodiment, the method further comprises:
determining a characteristic variable from the first samples aiming at each first sample in the first sample set to obtain a characteristic variable set;
determining a first rule variable set and a second rule variable set corresponding to the characteristic variable set; each first rule variable in the first rule variable set corresponds to a single characteristic variable, and each second rule variable in the second rule variable set is obtained by combining a plurality of characteristic variables according to a preset combination mode;
constructing a first rule pool corresponding to the first sample set according to the first rule variable set;
and constructing a second rule pool corresponding to the first sample set according to the second rule variable set.
In a second aspect, an embodiment of the present invention provides a rule pool generating apparatus, including:
an obtaining module, configured to obtain a first sample set;
the construction module is used for calling a first preset algorithm library to construct a first rule pool corresponding to the first sample set according to the first sample set, and each first preset algorithm in the first preset algorithm library is used for constructing a univariate rule;
the construction module is further configured to invoke a second preset algorithm library to construct a second rule pool corresponding to the first sample set according to the first sample set, where each second preset algorithm in the second preset algorithm library is used to construct a multivariate rule;
and the fusion module is used for fusing the first rule pool and the second rule pool to obtain a target rule pool.
In a third aspect, an embodiment of the present invention provides an electronic device, including: a processor and a memory, the processor being configured to execute a rule pool generation program stored in the memory to implement the rule pool generation method as described above.
In a fourth aspect, an embodiment of the present invention provides a storage medium storing one or more programs, which are executable by one or more processors to implement the rule pool generating method described above.
The method for generating the rule pool provided by the embodiment of the invention comprises the following steps: acquiring a first sample set; calling a first preset algorithm library to construct a first rule pool corresponding to the first sample set according to the first sample set, wherein each first preset algorithm in the first preset algorithm library is used for constructing a univariate rule; calling a second preset algorithm library to construct a second rule pool corresponding to the first sample set according to the first sample set, wherein each second preset algorithm in the second preset algorithm library is used for constructing a multi-variable rule; and fusing the first rule pool and the second rule pool to obtain a target rule pool corresponding to the first sample set. The method and the device obtain the final target rule pool by fusing the univariate rule pool and the multivariate rule pool obtained by different preset algorithm libraries, improve the efficiency of rule pool construction, and are independent of business experience and expert experience, so that the constructed rule pool is more comprehensive.
Drawings
Fig. 1 is a schematic structural diagram of a rule pool generating method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a rule pool generating apparatus according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;
in the above drawings:
10. an acquisition module; 20. building a module; 30. a fusion module;
400. an electronic device; 401. a processor; 402. a memory; 4021. an operating system; 4022. an application program; 403. a user interface; 404. a network interface; 405. a bus system.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
For the convenience of understanding of the embodiments of the present invention, the following description will be further explained with reference to specific embodiments, which are not to be construed as limiting the embodiments of the present invention.
Referring to fig. 1, fig. 1 is a schematic flowchart of a rule pool generating method according to an embodiment of the present invention. The method for generating the rule pool provided by the embodiment of the invention comprises the following steps:
s101: a first set of samples is obtained.
In this embodiment, the first sample set corresponds to a user group, and the first sample set is obtained by processing an original sample set corresponding to the user group. Each user corresponds to one first sample, each first sample comprises a characteristic variable, a characteristic variable value and an identification value, the characteristic variable can be the behavior characteristic of the user, the characteristic variable value corresponds to the characteristic parameter, and the characteristic variable value is data corresponding to the behavior characteristic of the user. The first sample further comprises risk performance data of the user, the risk performance data are obtained from statistics of loan behaviors of the user, and the identification value corresponds to the risk performance data of the user, wherein the identification value can be obtained by marking the risk performance data of the user according to a preset marking mode, the preset marking mode can be set according to preset service requirements, and the embodiment is not specifically limited herein. For example, when the preset service requirement is to formulate a passing rule set, the mark of the good user is 1, and the mark of the bad user is 0; when the preset service requirement is to formulate a rejection rule set, the preset marking mode can also be that the mark of a good user is 0, and the mark of a bad user is 1. The good users and the bad users can be distinguished through the following method, the risk performance data sets corresponding to user groups are collected through a crawler method, each risk performance data in the risk performance data sets is judged according to a preset risk index threshold, when the risk performance data exceed the preset risk index threshold, the users corresponding to the risk performance data are marked as the good users, and when the risk performance data do not exceed the preset risk index threshold, the users corresponding to the risk performance data are marked as the bad users. On the basis of determining whether each user is a good user or a bad user, marking can be carried out on each user according to preset service requirements (namely, marking is carried out on each first sample), so that a foundation is laid for determining the target rule pool.
S102: and calling a first preset algorithm library to construct a first rule pool corresponding to the first sample set according to the first sample set, wherein each first preset algorithm in the first preset algorithm library is used for constructing a univariate rule.
The first preset algorithm library at least comprises one first preset algorithm, wherein the first preset algorithm is a single-variable binning algorithm, the single-variable binning algorithm can be selected according to actual needs, and the embodiment is not specifically limited. In order to ensure that the constructed univariate rule pool is more comprehensive, the selected univariate binning methods are an equal-frequency binning algorithm, an equidistant binning algorithm, a clustering binning algorithm, a chi-square binning algorithm, a decision tree binning algorithm, a Best-KS binning algorithm and a machine learning binning algorithm.
Processing the first sample set by the univariate binning method to obtain a first rule pool, which is as follows:
and calling the first preset algorithm aiming at each first preset algorithm in the first preset algorithm library so as to construct at least one first rule corresponding to the first sample set according to the first sample set, and obtaining a first rule pool corresponding to the first sample set.
In the foregoing, each first preset algorithm in the first preset algorithm library processes the first sample set to obtain at least one first rule, and the first rule pool can be obtained by combining processing results of each first preset algorithm on the first sample set.
In this embodiment, invoking a first preset algorithm library to construct a first rule pool specifically includes:
determining a characteristic variable from the first sample aiming at each first sample in the first sample set to obtain a characteristic variable set;
determining a first rule variable set corresponding to the characteristic variable set; each first rule variable in the first rule variable set corresponds to a single feature variable;
and constructing a first rule pool corresponding to the first sample set according to the first rule variable set.
After the characteristic variables in the characteristic variable set are divided to obtain a first rule variable set, a first preset algorithm library is called according to the first rule variable in the first rule variable set, the characteristic variable value corresponding to the first rule variable and the identification value corresponding to the first rule variable, and a first rule pool corresponding to the first sample set can be constructed.
S103: and calling a second preset algorithm library to construct a second rule pool corresponding to the first sample set according to the first sample set, wherein each second preset algorithm in the second preset algorithm library is used for constructing a multi-variable rule.
The second preset algorithm library at least comprises one second preset algorithm, wherein the second preset algorithm is a tree model algorithm, the tree model algorithm can be selected according to actual needs, and the embodiment is not specifically limited. In this embodiment, in order to ensure that the constructed multivariate rule pool is more comprehensive, the selected tree model algorithms are a Bagging tree model algorithm, a Boosting tree model algorithm and a Stacking tree model algorithm.
Processing the first sample set through the tree model algorithm to obtain a second rule pool, which is as follows:
and calling a second preset algorithm aiming at each second preset algorithm in the second preset algorithm library so as to construct at least one second rule corresponding to the first sample set according to the first sample set, and obtaining a second rule pool corresponding to the second sample set.
In the foregoing, each second preset algorithm in the second preset algorithm library processes the first sample set to obtain at least one second rule, and the second rule pool can be obtained by combining the processing results of each second preset algorithm on the first sample set.
In this embodiment, invoking a second preset algorithm library to construct a second rule pool specifically includes:
determining a characteristic variable from the first sample aiming at each first sample in the first sample set to obtain a characteristic variable set;
determining a second rule variable set corresponding to the characteristic variable set; each second rule variable in the second rule variable set is obtained by combining a plurality of characteristic variables according to a preset combination mode;
and constructing a first rule pool corresponding to the first sample set according to the first rule variable set.
After the feature variables in the feature variable set are combined to obtain a second rule variable set, a second preset algorithm library is called according to the second rule variables in the second rule variable set, the feature variable values corresponding to the second rule variables and the identification values corresponding to the second rule variables, and a second rule pool corresponding to the first sample set can be constructed. In this embodiment, when the feature variables are combined to obtain the second rule variable set, the feature variables may be combined in a random non-playback manner by specifying the feature variables, the feature variables may be combined in a random playback manner, and the feature variables may be combined in a random playback manner by specifying the feature variables.
S104: and fusing the first rule pool and the second rule pool to obtain a target rule pool corresponding to the first sample set.
And the constructed univariate rule pool and the constructed multivariate rule pool are fused to obtain a more comprehensive target rule pool.
Because the same rule may exist in the first rule pool and the second rule pool constructed by different preset algorithms, in order to reduce redundancy of the generated target rule pool, rule de-duplication processing needs to be performed on the first rule pool and the second rule pool to obtain the target rule pool. The determination method of the target rule pool is determined by the following method:
executing deduplication operation on all first rules in the first rule pool to obtain a first deduplication result;
executing deduplication operation on all second rules in the second rule pool to obtain a second deduplication result;
and fusing the first duplicate removal result and the second duplicate removal result to obtain a target rule pool corresponding to the first sample set.
In this embodiment, the deduplication operation means that at least one rule identical to a certain rule exists in the rule pool, and all rules identical to the certain rule are deleted from the rule pool to complete the deduplication operation of the rule pool.
In this embodiment, the generated target rule pool may have a rule that is not applicable to the wind control decision, and if the rule that is not applicable is not deleted from the target rule pool, when the rule that is not applicable is applied to the wind control decision, the result of the wind control decision may be inaccurate. In this embodiment, the target rule pool may be further screened in the following manner, so that the screened target rule pool better satisfies the wind control decision, specifically as follows:
aiming at each target rule in the target rule pool, determining an index value corresponding to the target rule according to the first sample set to obtain an index value set corresponding to the target rule pool;
and determining at least one target rule from the target rule pool according to the index value set.
The target rule pool can be a de-duplicated target rule pool, the index value is an index value of a first index, and the first index can comprise the number of hit user groups, the number of good users in the hit user groups and the number of bad users in the hit user groups.
In this embodiment, determining an index value corresponding to the target rule according to the first sample set includes:
determining a rule hit result of each target rule in the target rule pool according to the first sample set;
determining a third index value corresponding to each target rule according to the rule hit result;
deleting at least one target rule with a third index value smaller than a preset threshold value from the target rule pool according to a preset service requirement to obtain a deleted target rule pool;
and determining an index value corresponding to each target rule according to the rule hit result corresponding to each target rule in the deleted target rule pool.
The rule hit result is the number of first samples which accord with the first rule in the first sample set, and the number of the first samples is the number of hit user groups; and obtaining the number of hit user groups according to the rule hit result. According to the rule hit result and the corresponding relation between the first sample and the identification value, the number of good users in the hit user group and the number of bad users in the hit user group can be determined.
The index set may be an index value set corresponding to one first index, or may be an index value set corresponding to a plurality of first indexes, and the selection of the first index may be selected according to an actual requirement, which is not specifically limited in this embodiment.
In this embodiment, the preset service requirement is consistent with the above, and this embodiment is not described herein again. The third index value represents a first ratio of the number of good users in the hit user group to the number of hit user group or a second ratio of the number of bad users in the hit user group to the number of hit user group, and the generated rules comprise rules corresponding to the good users and rules corresponding to the bad users. When the preset service requirement is to formulate a rejection rule set, the rule corresponding to the good user is not applicable, so the rule can be deleted to reduce the subsequent calculation amount of the index value. In this embodiment, the preset service requirement is to formulate a rejection rule set, the third index value is a second ratio of the number of bad users in the hit user group to the number of hit user groups, the preset threshold value is a preset ratio of the number of bad users in the user group to the number of user groups, and at least one target rule having the second ratio smaller than the preset ratio is deleted from the target valley rule pool, so as to obtain a deleted target rule pool.
In this embodiment, determining at least one target rule from the target rule pool according to the index value set includes:
determining a target index value and a target rule corresponding to the target index value according to the index value set;
deleting the target rule from the target rule pool to obtain a first target rule set, and deleting a first sample corresponding to the target rule from the first sample set to obtain a second sample set;
and repeatedly executing the step of determining the target rule by using the index value set by using the first target rule set as a target rule set and the second sample set as a first sample set to obtain a plurality of target rules meeting a first preset condition.
Wherein, obtaining a plurality of target rules meeting a first preset condition comprises:
in the process of repeatedly executing the target rule determined by using the first index value set, when the preset index value set is empty, the repeated determination of the target rule is terminated, and a plurality of target rules are obtained.
In this embodiment, determining a target index value according to the index set includes:
aiming at each target rule in the target rule pool, determining an index value of a second index corresponding to the target rule according to the first sample set to obtain a second index value set corresponding to the target rule pool;
determining a preset index value set corresponding to a preset threshold range from the index set, wherein at least one preset index value in the preset index value set is preset;
determining a second index value corresponding to the preset index value aiming at each preset index value in the preset index values to obtain a plurality of second index values corresponding to the preset index values;
sequencing the plurality of second index values to obtain a sequencing result;
and determining a target index value according to the sorting result.
When the target rule is selected in each round, the preset threshold range in each round can be set according to actual needs, and the embodiment is not specifically limited herein. The second index includes hit user group risk multiple and hit user group coverage. Determining a third ratio according to the number of bad users (or good users) in the user group and the number of the user group, determining a fourth ratio according to the number of bad users (or good users) in the hit user group and the number of the hit user group, and determining hit risk multiple according to the multiple relation of the third ratio and the fourth ratio. And determining a fifth ratio according to the number of the hit user groups and the number of the user groups, wherein the fifth ratio is the coverage rate of the hit user groups. One index can be selected from the hit risk multiple and the hit user group coverage rate according to actual needs to serve as a second index. After a plurality of second index values corresponding to the preset index value set are obtained, the plurality of second index values can be sorted according to a relationship from large to small, the second index value at the head is used as a target index value, and a target rule corresponding to the target index value is determined according to the target index value. Of course, the sorting result may be displayed on a display interface, so that the user may select a target rule from the sorting result according to the sorting result.
The method for generating a rule pool provided by the embodiment includes: acquiring a first sample set; calling a first preset algorithm library to construct a first rule pool corresponding to the first sample set according to the first sample set, wherein each first preset algorithm in the first preset algorithm library is used for constructing a univariate rule; calling a second preset algorithm library to construct a second rule pool corresponding to the first sample set according to the first sample set, wherein each second preset algorithm in the second preset algorithm library is used for constructing a multi-variable rule; and fusing the first rule pool and the second rule pool to obtain a target rule pool corresponding to the first sample set. The method and the device have the advantages that the final target rule pool is obtained by fusing the univariate rule pool and the multivariate rule pool obtained by different preset algorithm libraries, the rule pool construction efficiency is improved, and the method and the device do not depend on business experience and expert experience, so that the constructed rule pool is more comprehensive.
Referring to fig. 2, fig. 2 is a schematic structural diagram of a rule pool generating device according to an embodiment of the present invention. The apparatus for generating a rule pool provided in the embodiment of the present invention includes an obtaining module 10, configured to obtain a first sample set; the construction module 20 is configured to invoke a first preset algorithm library to construct a first rule pool corresponding to the first sample set according to the first sample set, where each first preset algorithm in the first preset algorithm library is used to construct a univariate rule; the constructing module 20 is further configured to invoke a second preset algorithm library to construct a second rule pool corresponding to the first sample set according to the first sample set, where each second preset algorithm in the second preset algorithm library is used to construct a multivariate rule; and the fusion module 30 is configured to fuse the first rule pool and the second rule pool to obtain a target rule pool.
In this embodiment, the fusion module 30 is further configured to:
performing duplicate removal operation on all first rules in the first rule pool to obtain a first duplicate removal result;
executing deduplication operation on all second rules in the second rule pool to obtain a second deduplication result;
and fusing the first duplicate removal result and the second duplicate removal result to obtain a target rule pool corresponding to the first sample set.
In this embodiment, the rule pool generating apparatus further includes a determining module, where the determining module is configured to:
aiming at each target rule in the target rule pool, determining an index value corresponding to the target rule according to the first sample set to obtain an index value set corresponding to the target rule pool;
and determining at least one target rule from the target rule pool according to the index value set.
In this embodiment, the determining module is further configured to:
determining a rule hit result of each target rule in the target rule pool according to the first sample set;
and determining an index value corresponding to each target rule in the target rule pool according to the hit result of each rule.
In this embodiment, the building module 20 is further configured to:
and calling the first preset algorithm aiming at each first preset algorithm in the first preset algorithm library so as to construct at least one first rule corresponding to the first sample set according to the first sample set, and obtaining a first rule pool corresponding to the first sample set.
In this embodiment, the building module 20 is further configured to:
and calling a second preset algorithm aiming at each second preset algorithm in the second preset algorithm library so as to construct at least one second rule corresponding to the first sample set according to the first sample set, and obtaining a second rule pool corresponding to the second sample set.
In this embodiment, the building module 20 is further configured to:
determining a characteristic variable from the first sample aiming at each first sample in the first sample set to obtain a characteristic variable set;
determining a first rule variable set corresponding to the characteristic variable set, wherein each first rule variable in the first rule variable set corresponds to a single characteristic variable;
and constructing a first rule pool corresponding to the first sample set according to the first rule variable set.
In this embodiment, the building module 20 is further configured to:
determining a characteristic variable from the first sample aiming at each first sample in the first sample set to obtain a characteristic variable set;
determining a second rule variable set corresponding to the characteristic variable set; each second rule variable in the second rule variable set is obtained by combining a plurality of characteristic variables according to a preset combination mode;
and constructing a second rule pool corresponding to the first sample set according to the second rule variable set.
According to the rule pool generation method provided by the embodiment, the final target rule pool is obtained by fusing the univariate rule pool and the multivariate rule pool obtained by different preset algorithm libraries, so that the rule pool construction efficiency is improved, and the rule pool construction method is independent of business experience and expert experience, so that the constructed rule pool is more comprehensive.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, where the electronic device 400 shown in fig. 3 includes: at least one processor 401, memory 402, at least one network interface 404, and other user interfaces 403. The various components in the electronic device 400 are coupled together by a bus system 405. It is understood that the bus system 405 is used to enable connection communication between these components. The bus system 405 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 405 in fig. 3.
The user interface 403 may include, among other things, a display, a keyboard, or a pointing device (e.g., a mouse, trackball, touch pad, or touch screen, among others.
It will be appreciated that memory 402 in embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of illustration and not limitation, many forms of RAM are available, such as Static random access memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), Double Data Rate Synchronous Dynamic random access memory (ddr Data Rate SDRAM, ddr SDRAM), Enhanced Synchronous SDRAM (ESDRAM), synchlronous SDRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 402 described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
In some embodiments, memory 402 stores the following elements, executable units or data structures, or a subset thereof, or an expanded set thereof: an operating system 4021 and application programs 4022.
The operating system 4021 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, and is configured to implement various basic services and process hardware-based tasks. The application programs 4022 include various application programs, such as a Media Player (Media Player), a Browser (Browser), and the like, for implementing various application services. A program for implementing the method according to the embodiment of the present invention may be included in the application 4022.
In this embodiment of the present invention, by calling a program or an instruction stored in the memory 402, specifically, a program or an instruction stored in the application 4022, the processor 401 is configured to execute the method steps provided by the method embodiments, for example, including: acquiring a first sample set; calling a first preset algorithm library to construct a first rule pool corresponding to the first sample set according to the first sample set, wherein each first preset algorithm in the first preset algorithm library is used for constructing a univariate rule; calling a second preset algorithm library to construct a second rule pool corresponding to the first sample set according to the first sample set, wherein each second preset algorithm in the second preset algorithm library is used for constructing a multi-variable rule; and fusing the first rule pool and the second rule pool to obtain a target rule pool corresponding to the first sample set.
The method disclosed in the above embodiments of the present invention may be applied to the processor 401, or implemented by the processor 401. The processor 401 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 401. The Processor 401 may be a general-purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software elements in the decoding processor. The software elements may be located in ram, flash, rom, prom, or eprom, registers, among other storage media that are well known in the art. The storage medium is located in the memory 402, and the processor 401 reads the information in the memory 402 and completes the steps of the method in combination with the hardware.
It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or any combination thereof. For a hardware implementation, the Processing units may be implemented within one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units configured to perform the functions described herein, or a combination thereof.
For a software implementation, the techniques described herein may be implemented by means of units performing the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.
The electronic device provided in this embodiment may be the electronic device shown in fig. 3, and may execute all the steps of the rule pool generating method shown in fig. 1-2, so as to achieve the technical effect of the rule pool generating method shown in fig. 1-2, and for brevity, it is described with reference to fig. 1-2, which is not described herein again.
The embodiment of the invention also provides a storage medium (computer readable storage medium). The storage medium herein stores one or more programs. Among others, the storage medium may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, a hard disk, or a solid state disk; the memory may also comprise a combination of memories of the kind described above.
When one or more programs in the storage medium are executable by one or more processors, the above rule pool generating method performed on the rule pool generating device side is implemented.
The processor is configured to execute the rule pool generation program stored in the memory to implement the following steps of the rule pool generation method executed on the rule pool generation device side: acquiring a first sample set; calling a first preset algorithm library to construct a first rule pool corresponding to the first sample set according to the first sample set, wherein each first preset algorithm in the first preset algorithm library is used for constructing a univariate rule; calling a second preset algorithm library to construct a second rule pool corresponding to the first sample set according to the first sample set, wherein each second preset algorithm in the second preset algorithm library is used for constructing a multi-variable rule; and fusing the first rule pool and the second rule pool to obtain a target rule pool corresponding to the first sample set.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, a software module executed by a processor, or a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for generating a rule pool, comprising:
acquiring a first sample set;
calling a first preset algorithm library to construct a first rule pool corresponding to the first sample set according to the first sample set, wherein each first preset algorithm in the first preset algorithm library is used for constructing a univariate rule;
calling a second preset algorithm library to construct a second rule pool corresponding to the first sample set according to the first sample set, wherein each second preset algorithm in the second preset algorithm library is used for constructing a multi-variable rule;
and fusing the first rule pool and the second rule pool to obtain a target rule pool corresponding to the first sample set.
2. The method of claim 1, wherein fusing the first rule pool and the second rule pool to obtain a target rule pool comprises:
performing deduplication operation on all first rules in the first rule pool to obtain a first deduplication result;
executing deduplication operation on all second rules in the second rule pool to obtain a second deduplication result;
and fusing the first duplicate removal result and the second duplicate removal result to obtain a target rule pool corresponding to the first sample set.
3. The method of claim 1, further comprising:
for each target rule in the target rule pool, determining an index value corresponding to the target rule according to the first sample set to obtain an index value set corresponding to the target rule pool;
and determining at least one target rule from the target rule pool according to the index value set.
4. The method of claim 3, wherein determining the metric value corresponding to the target rule according to the first sample set comprises:
determining a rule hit result of each target rule in the target rule pool according to the first sample set;
and determining an index value corresponding to each target rule in the target rule pool according to the hit result of each rule.
5. The method of claim 1, wherein said invoking a first library of preset algorithms to construct a first rule pool corresponding to the first set of samples according to the first set of samples comprises:
and calling the first preset algorithm aiming at each first preset algorithm in the first preset algorithm library so as to construct at least one first rule corresponding to the first sample set according to the first sample set, and obtain a first rule pool corresponding to the first sample set.
6. The method according to claim 1, wherein said invoking a second library of preset algorithms to construct a second rule pool corresponding to the first sample set according to the first sample set comprises:
and calling the second preset algorithm aiming at each second preset algorithm in the second preset algorithm library so as to construct at least one second rule corresponding to the first sample set according to the first sample set and obtain a second rule pool corresponding to the first sample set.
7. The method of claim 1, further comprising:
determining a characteristic variable from the first samples aiming at each first sample in the first sample set to obtain a characteristic variable set;
determining a first rule variable set and a second rule variable set corresponding to the characteristic variable set; each first rule variable in the first rule variable set corresponds to a single characteristic variable, and each second rule variable in the second rule variable set is obtained by combining a plurality of characteristic variables according to a preset combination mode;
constructing a first rule pool corresponding to the first sample set according to the first rule variable set;
and constructing a second rule pool corresponding to the first sample set according to the second rule variable set.
8. An apparatus for generating a rule pool, comprising:
an obtaining module, configured to obtain a first sample set;
the construction module is used for calling a first preset algorithm library to construct a first rule pool corresponding to the first sample set according to the first sample set, and each first preset algorithm in the first preset algorithm library is used for constructing a univariate rule;
the construction module is further configured to call a second preset algorithm library to construct a second rule pool corresponding to the first sample set according to the first sample set, where each second preset algorithm in the second preset algorithm library is used to construct a multivariate rule;
and the fusion module is used for fusing the first rule pool and the second rule pool to obtain a target rule pool.
9. An electronic device, comprising: a processor and a memory, the processor being configured to execute a rule pool generation program stored in the memory to implement the rule pool generation method of any one of claims 1 to 7.
10. A storage medium storing one or more programs, the one or more programs being executable by one or more processors to implement the rule pool generating method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210376812.0A CN114817323A (en) | 2022-04-11 | 2022-04-11 | Rule pool generation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210376812.0A CN114817323A (en) | 2022-04-11 | 2022-04-11 | Rule pool generation method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114817323A true CN114817323A (en) | 2022-07-29 |
Family
ID=82534163
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210376812.0A Pending CN114817323A (en) | 2022-04-11 | 2022-04-11 | Rule pool generation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114817323A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108460523A (en) * | 2018-02-12 | 2018-08-28 | 阿里巴巴集团控股有限公司 | A kind of air control rule generating method and device |
| CN109063952A (en) * | 2018-06-15 | 2018-12-21 | 阿里巴巴集团控股有限公司 | Strategy generating and risk control method and device |
| CN110009479A (en) * | 2019-03-01 | 2019-07-12 | 百融金融信息服务股份有限公司 | Credit assessment method and device, storage medium, computer equipment |
| CN110609929A (en) * | 2019-09-03 | 2019-12-24 | 深圳中兴飞贷金融科技有限公司 | Data processing method and device, storage medium and electronic equipment |
| CN110945538A (en) * | 2017-04-03 | 2020-03-31 | 维择科技公司 | Automatic rule recommendation engine |
| CN111861703A (en) * | 2020-07-10 | 2020-10-30 | 深圳无域科技技术有限公司 | Data-driven wind control strategy rule generation method and system and risk control method and system |
| CN112862594A (en) * | 2021-02-01 | 2021-05-28 | 深圳无域科技技术有限公司 | Financial risk control method, system, device and computer readable medium |
| CN113610175A (en) * | 2021-08-16 | 2021-11-05 | 上海冰鉴信息科技有限公司 | Method, device and computer-readable storage medium for generating business policy |
| CN114139725A (en) * | 2021-12-02 | 2022-03-04 | 阿里巴巴达摩院(杭州)科技有限公司 | Service object prediction method, device and storage medium |
-
2022
- 2022-04-11 CN CN202210376812.0A patent/CN114817323A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110945538A (en) * | 2017-04-03 | 2020-03-31 | 维择科技公司 | Automatic rule recommendation engine |
| CN108460523A (en) * | 2018-02-12 | 2018-08-28 | 阿里巴巴集团控股有限公司 | A kind of air control rule generating method and device |
| CN109063952A (en) * | 2018-06-15 | 2018-12-21 | 阿里巴巴集团控股有限公司 | Strategy generating and risk control method and device |
| CN110009479A (en) * | 2019-03-01 | 2019-07-12 | 百融金融信息服务股份有限公司 | Credit assessment method and device, storage medium, computer equipment |
| CN110609929A (en) * | 2019-09-03 | 2019-12-24 | 深圳中兴飞贷金融科技有限公司 | Data processing method and device, storage medium and electronic equipment |
| CN111861703A (en) * | 2020-07-10 | 2020-10-30 | 深圳无域科技技术有限公司 | Data-driven wind control strategy rule generation method and system and risk control method and system |
| CN112862594A (en) * | 2021-02-01 | 2021-05-28 | 深圳无域科技技术有限公司 | Financial risk control method, system, device and computer readable medium |
| CN113610175A (en) * | 2021-08-16 | 2021-11-05 | 上海冰鉴信息科技有限公司 | Method, device and computer-readable storage medium for generating business policy |
| CN114139725A (en) * | 2021-12-02 | 2022-03-04 | 阿里巴巴达摩院(杭州)科技有限公司 | Service object prediction method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108089893B (en) | Method and device for determining redundant resources, terminal equipment and storage medium | |
| CN110221959B (en) | Application program testing method, device and computer readable medium | |
| CN112100071B (en) | Test case generation method and device, computer equipment and storage medium | |
| CN110188306A (en) | Method and device for automatically filling in web form | |
| US11775348B2 (en) | Managing custom workflows for domain objects defined within microservices | |
| JP6977724B2 (en) | Signature creation device, signature creation method, signature creation program, and software judgment system | |
| CN110610352A (en) | Process processing method, device, electronic device, and computer-readable storage medium | |
| CN112416710A (en) | User-operated recording method, device, electronic device, and storage medium | |
| CN112632930A (en) | Table data control method and device | |
| CN114817323A (en) | Rule pool generation method and device, electronic equipment and storage medium | |
| CN115688099A (en) | Computer virus retrieval method and device, computer equipment and storage medium | |
| CN120804097A (en) | Workflow setting method in table and related equipment | |
| KR20170062106A (en) | System and method for combining workflow | |
| CN116579669B (en) | Reliability evaluation method, reliability evaluation device, computer equipment and storage medium thereof | |
| CN109783139B (en) | Software interface feature extraction method, device and electronic device | |
| CN111124572A (en) | Display method, device, client and storage medium based on associated stocks | |
| CN118657488A (en) | Method and related device for determining the process status of an object | |
| CN116737574A (en) | Test method, device, equipment, storage medium and product for responding to code change | |
| JP6528285B2 (en) | Crisis response management device | |
| CN116049510A (en) | Analytical methods, systems, equipment and media for the ultimate shareholder of the enterprise | |
| CN109992514B (en) | Mobile application dynamic analysis method based on visual content | |
| CN114448679A (en) | Attack chain construction method and device, electronic equipment and storage medium | |
| CN115221852A (en) | Vxe-table based dynamic calculation table implementation method, device and computer equipment | |
| CN114897595B (en) | Data processing method, device, electronic device and storage medium | |
| CN113849386A (en) | Log data generation method and device, storage medium and electronic equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220729 |
|
| RJ01 | Rejection of invention patent application after publication |