CN114881313A - Behavior prediction method and device based on artificial intelligence and related equipment - Google Patents
Behavior prediction method and device based on artificial intelligence and related equipment Download PDFInfo
- Publication number
- CN114881313A CN114881313A CN202210450910.4A CN202210450910A CN114881313A CN 114881313 A CN114881313 A CN 114881313A CN 202210450910 A CN202210450910 A CN 202210450910A CN 114881313 A CN114881313 A CN 114881313A
- Authority
- CN
- China
- Prior art keywords
- data table
- target
- prediction result
- prediction
- data
- 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; 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0609—Buyer or seller confidence or verification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Accounting & Taxation (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Human Resources & Organizations (AREA)
- Finance (AREA)
- Evolutionary Biology (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Computation (AREA)
- Operations Research (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, and provides a behavior prediction method, a behavior prediction device and related equipment based on artificial intelligence, wherein the method comprises the following steps: acquiring an original data set from data sources of a plurality of target parameters, and performing first preprocessing on the original data set to obtain a target data table; calling a rule class label, and acquiring a first prediction result from a target data table through a label management system based on the rule class label; extracting a characteristic factor set from the target data table, and inputting the characteristic factor set into a classification prediction model with a pre-trained characteristic factor set input value to obtain a second prediction result; and performing second preprocessing on the first prediction result and the second prediction result to obtain a target prediction result. According to the method and the device, the target prediction result is obtained according to the rule engine and the classification prediction model, and the accuracy of the purchasing fraud prediction result is improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a behavior prediction method and device based on artificial intelligence and related equipment.
Background
Along with the diversification of products, a purchasing link is used as a key operation link of a business system, the problem of fraud is easy to occur, the prior art uses expert experience to analyze and process large purchasing data, identifies abnormal purchasing business links which do not accord with external bidding regulations, internal management requirements of enterprises or rationality, and screens purchasing projects with fraud risks.
However, the expert experience is used for analyzing and processing the purchased big data, so that whether the purchased big data is avoided by the purchasing cheater cannot be identified, the accuracy of the purchased big data is low, and the accuracy of the purchasing cheat prediction is low.
Therefore, there is a need for a method for accurately predicting purchasing fraud.
Disclosure of Invention
In view of the above, it is necessary to provide an artificial intelligence-based behavior prediction method, an artificial intelligence-based behavior prediction device, and related equipment, so as to obtain a target prediction result according to a rule engine and a classification prediction model, and improve the accuracy of a purchasing fraud prediction result.
A first aspect of the invention provides a method of artificial intelligence based behavior prediction, the method comprising:
analyzing the received purchase fraud prediction request to obtain data sources of a plurality of target parameters;
acquiring an original data set from the data sources of the target parameters, and performing first preprocessing on the original data set to obtain a target data table;
calling a rule class label, and acquiring a first prediction result from the target data table through a label management system based on the rule class label;
extracting a characteristic factor set from the target data table, inputting the characteristic factor set into a classification prediction model with a pre-trained value, and obtaining a second prediction result;
and performing second preprocessing on the first prediction result and the second prediction result to obtain a target prediction result.
Optionally, the performing a first preprocessing on the original data set to obtain a target data table includes:
identifying a purchasing service system identification code corresponding to each original data table in the original data set;
classifying the original data set according to the purchasing service system identification code;
determining original data sets of the same purchasing service system as a first data set, and determining the remaining original data sets of different purchasing service systems as a second data set;
performing table merging processing on the original data table in the first data set to obtain a first data table, and performing table merging processing on the original data table in the second data set to obtain a second data table;
merging the first data table and the second data table to obtain a third data table;
and carrying out data cleaning on the third data table to obtain a target data table.
Optionally, the performing a table merging process on the original data table in the second data set to obtain a second data table includes:
identifying a field name for each original data table in the second data set;
merging a plurality of columns with the same field names of a plurality of original data tables, and deleting the plurality of columns participating in merging to obtain a new table;
calculating the total number of the field names of the new table, and acquiring the total number of preset vacant field according to the total number of the field names of the new table;
and expanding the new table based on the total number of the preset vacant fields to obtain a second data table.
Optionally, the invoking a rule class label, and based on the rule class label, obtaining a first prediction result through a preset rule engine includes:
converting the data in the target data table into a rule class label which can be identified by a preset rule engine;
and calling a preset rule engine to perform intelligent matching of the rule class labels to obtain a first prediction result.
Optionally, the extracting a characteristic factor set from the target data table includes:
acquiring the item information of the purchase item corresponding to the purchase item identification code in the purchase fraud prediction request and a preset processing script;
preprocessing the project information to obtain target project information;
and processing the target project information by adopting the preset processing script to obtain a characteristic factor set.
Optionally, the performing second preprocessing on the first prediction result and the second prediction result to obtain a target prediction result includes:
comparing the first predicted result with the second predicted result;
deleting the first prediction result which is the same as the second prediction result to obtain a target prediction result.
Optionally, the analyzing the received purchase fraud prediction request to obtain a data source of a plurality of target parameters includes:
analyzing the message of the purchase fraud prediction request to obtain message information carried by the message;
acquiring a forecast demand of purchasing fraud from the message information;
matching the purchasing item identification code in the purchasing fraud prediction requirement with a system identification code in a preset database, and acquiring a first interface of a purchasing service system corresponding to the purchasing item and a second interface of a third-party system interacting with the purchasing service system;
and calling the first interface and the second interface to obtain a data source of the corresponding target parameter.
A second aspect of the present invention provides an artificial intelligence based behavior prediction apparatus, the apparatus comprising:
the analysis module is used for analyzing the received purchase fraud prediction request to obtain a plurality of data sources of target parameters;
the first preprocessing module is used for acquiring an original data set from the data sources of the target parameters and performing first preprocessing on the original data set to obtain a target data table;
the building module is used for calling a rule class label and acquiring a first prediction result from the target data table through a label management system based on the rule class label;
the extraction and input module is used for extracting a characteristic factor set from the target data table and inputting the characteristic factor set into a classification prediction model with trained characteristic factor set input values in advance to obtain a second prediction result;
and the second preprocessing module is used for carrying out second preprocessing on the first prediction result and the second prediction result to obtain a target prediction result.
A third aspect of the invention provides an electronic device comprising a processor and a memory, the processor being configured to implement the artificial intelligence based behavior prediction method when executing a computer program stored in the memory.
A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the artificial intelligence based behavior prediction method.
In summary, according to the behavior prediction method, apparatus, and related device based on artificial intelligence, the original data set is first preprocessed, the rule class label is called, based on the rule class label, a first prediction result is obtained from the target data table through the label management system, and the feature factor set input value is pre-trained in the classification prediction model, so as to obtain a second prediction result, where the first prediction result is obtained based on the rule engine from the consideration of the system specification of the purchase item, and the second prediction result is obtained based on the classification prediction model from the consideration of the process of the purchase item, and the target prediction result is obtained according to the rule engine and the classification prediction model, so as to improve the accuracy of the prediction result of the purchase fraud.
Drawings
Fig. 1 is a flowchart of an artificial intelligence-based behavior prediction method according to an embodiment of the present invention.
Fig. 2 is a block diagram of an artificial intelligence-based behavior prediction apparatus according to a second embodiment of the present invention.
Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a detailed description of the present invention will be given below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and features of the embodiments may be combined with each other without conflict.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
Example one
Fig. 1 is a flowchart of an artificial intelligence-based behavior prediction method according to an embodiment of the present invention.
In this embodiment, the method for predicting behavior based on artificial intelligence may be applied to an electronic device, and for an electronic device that needs to perform behavior prediction based on artificial intelligence, the function of behavior prediction based on artificial intelligence provided by the method of the present invention may be directly integrated on the electronic device, or may be run in the electronic device in the form of a Software Development Kit (SDK).
The embodiment of the invention can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning, deep learning and the like.
As shown in fig. 1, the artificial intelligence based behavior prediction method specifically includes the following steps, and the order of the steps in the flowchart may be changed and some may be omitted according to different requirements.
And S11, analyzing the received purchasing fraud prediction request to obtain a plurality of data sources of target parameters, wherein the purchasing fraud prediction request contains a purchasing item identification code.
In this embodiment, when an enterprise or a user performs purchase fraud prediction, a client initiates a purchase fraud prediction request to a server, specifically, the client may be a smart phone, an IPAD or other existing intelligent devices, the server may be a purchase fraud prediction subsystem, and in the purchase fraud prediction process, if the client can send the purchase fraud prediction request to the purchase fraud prediction subsystem, the purchase fraud prediction subsystem is configured to receive the purchase fraud prediction request sent by the client.
In this embodiment, the data source of the target parameter may be at least one third-party system interacting with the purchasing service system, or may be at least one subsystem of the purchasing service system.
In an optional embodiment, the parsing the received purchase fraud prediction request to obtain a data source of a plurality of target parameters includes:
analyzing the message of the purchase fraud prediction request to obtain message information carried by the message;
acquiring a forecast demand of purchasing fraud from the message information;
and acquiring data sources of a plurality of target parameters according to the purchasing fraud prediction demand.
Specifically, the purchasing fraud prediction requirement comprises a purchasing item identification code, wherein the purchasing item identification code is used for uniquely identifying the identity of the purchasing service.
Further, the data source for obtaining a plurality of target parameters according to the forecast demand for purchasing fraud comprises:
matching the purchasing item identification code in the purchasing fraud prediction requirement with a system identification code in a preset database, and acquiring a first interface of a purchasing service system corresponding to the purchasing item and a second interface of a third-party system interacting with the purchasing service system;
and calling the first interface and the second interface to obtain a data source of the corresponding target parameter.
In this embodiment, since the associated data related to the purchasing service system may be sourced from the purchasing service system, a third-party system interacting with the purchasing service system, and a subsystem of the purchasing service system, the data source of the corresponding target parameter is obtained by calling the interface of the corresponding purchasing service system, and the data sources of all the target parameters of all the purchasing service systems do not need to be obtained, which is more targeted, and the accuracy of the obtained data source of the target parameter is improved.
S12, acquiring an original data set from the data sources of the target parameters, and performing first preprocessing on the original data set to obtain a target data table.
In this embodiment, the original data set refers to original data directly obtained from a data source of the target parameter, and the target data table refers to a data table obtained by processing each original data table in the original data set.
In an alternative embodiment, the obtaining the raw data set from the data sources of the plurality of target parameters includes:
analyzing the purchasing fraud prediction requirement in the purchasing fraud prediction request, and acquiring the acquisition requirement of the data source of each target parameter and a corresponding acquisition interface;
and calling a collection interface of the data source of each target parameter, and acquiring an original data set from the data source of each target parameter by adopting a crawler technology according to the collection requirement of the data source of each target parameter.
In this embodiment, the forecast demand for purchasing fraud further includes a collection demand of a data source of each target parameter and a corresponding collection interface. The crawler technology is prior art, and the embodiment is not described in detail herein.
In an optional embodiment, the performing the first preprocessing on the original data set to obtain the target data table includes:
identifying a purchasing service system identification code corresponding to each original data table in the original data set;
classifying the original data set according to the purchasing service system identification code;
determining original data sets of the same purchasing service system as a first data set, and determining the remaining original data sets of different purchasing service systems as a second data set;
performing table merging processing on the original data table in the first data set to obtain a first data table, and performing table merging processing on the original data table in the second data set to obtain a second data table;
merging the first data table and the second data table to obtain a third data table;
and carrying out data cleaning on the third data table to obtain a target data table.
In this embodiment, the data cleaning of the third data table by using the preset cleaning policy corresponding to the purchase service system to obtain the target data table includes:
specifically, the cleaning strategy can be set in advance according to the format requirements of the purchasing service system and a third-party system interacting with the purchasing service system, and the data of the third data table is cleaned through the preset cleaning strategy, so that the accuracy of the target data table is improved.
In this embodiment, the procurement services system identification code is used to uniquely identify the system to which each raw data table in the raw data set belongs.
In this embodiment, the original data tables in the first data set originate from the same procurement service system or a subsystem of the same procurement service system, and the data tables in the original data tables in the first data set have the same structure, so that all the original data tables in the first data set are directly subjected to union processing to obtain the first data table.
Further, the performing a table-combining process on the original data table in the second data set to obtain a second data table includes:
identifying a field name for each original data table in the second data set;
merging a plurality of columns with the same field names of a plurality of original data tables, and deleting the plurality of columns participating in merging to obtain a new table;
calculating the total number of the field names of the new table, and acquiring the total number of preset vacant field according to the total number of the field names of the new table;
and expanding the new table based on the total number of the preset vacant fields to obtain a second data table.
In this embodiment, the field name of each original data table is a name specified by each column in the table.
In this embodiment, the original data table in the second data set is derived from different purchasing service systems, and the original data table in the second data set needs to be processed if the data table structures of the different purchasing service systems are different.
In this embodiment, the total number of null fields may be preset, and the total number of null fields set for different data tables is different, for example, the second data set includes an original data table a, an original data table B, and an original data table C, where the original data table a includes 20 field names, the original data table B includes 20 field names, the original data table C includes 15 field names, 15 same field names exist in the original data table a and the original data table B, the same field names in the original data table a and the original data table B are merged, and the original data table C is merged to obtain a new table, the new table includes 40 field names, and a preset null field 5 corresponding to the 40 field names is obtained to obtain the second data table.
In this embodiment, in the process of processing the original data table in the second data set to obtain the second data table, the new table is expanded based on the total number of the preset empty fields, so that the new field names are conveniently added to the second data table directly when new field names are subsequently added, the processing is not required to be performed again, and the utilization rate of the second data table is improved.
And S13, calling a rule class label, and acquiring a first prediction result from the target data table through a label management system based on the rule class label.
In this embodiment, the rule class label refers to an association relationship between field names in the target data table, and the target data table has the rule class label: personnel information-project information-provider information. The first prediction result is a prediction result corresponding to the rule class label found in the target data table, that is, the associated data corresponding to the personnel information, the item information and the supplier information is found from the target data table.
In an optional embodiment, the invoking a rule class label, and based on the rule class label, obtaining a first prediction result through a preset rule engine includes:
converting the data in the target data table into a rule class label which can be identified by a preset rule engine;
and calling a preset rule engine to perform intelligent matching of the rule class labels to obtain a first prediction result.
In this embodiment, the rule class tag is pre-stored in the database, and after the target data table is obtained, the rule class tag is called, data in the target data table is converted into the rule class tag that can be identified by the preset rule engine, and the rule class tag is matched with the called rule class tag, so that a first prediction result is obtained.
In this embodiment, a rule engine may be preset, specifically, the rule engine performs intelligent matching of rule class labels, which belongs to the prior art, and this embodiment is not described in detail herein.
In this embodiment, the first prediction result is obtained by classifying from the target data table based on the rule class label through a preset rule engine, specifically, from a regulatory consideration of the procurement project.
And S14, extracting a characteristic factor set from the target data table, and inputting the characteristic factor set into a classification prediction model which is trained in advance to obtain a second prediction result.
In this embodiment, the characteristic factor is obtained by processing a field name associated with the forecast purchase fraud, for example, the person information, the project information, and the provider information in the field name are determined as a characteristic factor.
In an optional embodiment, the extracting the characteristic factor set from the target data table includes:
acquiring the item information of the purchase item corresponding to the purchase item identification code in the purchase fraud prediction request and a preset processing script;
preprocessing the project information to obtain target project information;
and processing the target project information by adopting the preset processing script to obtain a characteristic factor set.
In this embodiment, the target item information is obtained by preprocessing the item information, specifically, by preprocessing data corresponding to the field name associated with the purchase fraud in the item information, for example, correcting, format converting, and the like.
In this embodiment, the classification prediction model may be trained in advance, after the classification prediction model is trained, the extracted feature factor set is input into the classification prediction model, whether fraud information exists in the data information corresponding to each feature factor is determined, and a prediction result is output to obtain a second prediction result, where the second prediction result is obtained by considering from the process of purchasing a project.
In this embodiment, the input of the classification prediction model is a feature factor set, the feature factor set is used as a training set, a preset neural network model is trained, and the classification prediction model is obtained, and a specific training process is not limited herein.
And S15, performing second preprocessing on the first prediction result and the second prediction result to obtain a target prediction result.
In this embodiment, the second preprocessing is obtained by performing deduplication processing on the first prediction result and the second prediction result.
In an optional embodiment, the second preprocessing the first prediction result and the second prediction result to obtain a target prediction result includes:
comparing the first predicted result with the second predicted result;
deleting the first prediction result which is the same as the second prediction result to obtain a target prediction result.
Further, the method further comprises:
and sending the target prediction result to a client, and displaying the target prediction result on an interface of the client.
Further, the method further comprises:
and adding the target prediction result into a training set for training a classification prediction model, and retraining the classification prediction model.
In this embodiment, since the first prediction result is obtained based on the rule class label and the second prediction result is obtained based on the pre-trained classification prediction model, the first prediction result is compared with the second prediction result, for example, the first prediction result includes that the user a has the purchase fraud phenomenon, the second prediction result also includes that the user a has the purchase fraud phenomenon, the user a in the first prediction result is deleted from the purchase fraud phenomenon, the user a in the second prediction result is retained from the purchase fraud phenomenon, and the rule engine and the classification prediction model are combined to obtain the target prediction result, so that the integrity and the accuracy of the target prediction result are improved
In summary, in the artificial intelligence-based behavior prediction method according to this embodiment, the original data set is first preprocessed, a rule class label is called, based on the rule class label, a first prediction result is obtained from the target data table through a label management system, and a second prediction result is obtained from a classification prediction model in which the input values of the feature factor set are trained in advance, where the first prediction result is obtained based on a rule engine from the system specification of a purchase item, and the second prediction result is obtained based on the classification prediction model from the process of the purchase item, and the target prediction result is obtained according to the rule engine and the classification prediction model, so that the accuracy of the prediction result of the purchase fraud is improved.
Example two
Fig. 2 is a block diagram of an artificial intelligence-based behavior prediction apparatus according to a second embodiment of the present invention.
In some embodiments, the artificial intelligence based behavior prediction apparatus 20 may include a plurality of functional modules comprised of program code segments. The program code of each program segment in the artificial intelligence based behavior prediction apparatus 20 may be stored in a memory of the electronic device and executed by the at least one processor to perform (see fig. 1 for details) the artificial intelligence based behavior prediction function.
In this embodiment, the artificial intelligence based behavior prediction apparatus 20 may be divided into a plurality of functional modules according to the functions performed by the apparatus. The functional module may include: a parsing module 201, a first preprocessing module 202, a construction module 203, an extraction and input module 204, a second preprocessing module 205, a sending module 206 and an adding module 207. The module referred to herein is a series of computer readable instruction segments stored in a memory that can be executed by at least one processor and that can perform a fixed function. In the present embodiment, the functions of the modules will be described in detail in the following embodiments.
The analyzing module 201 is configured to analyze the received purchasing fraud prediction request to obtain data sources of a plurality of target parameters, where the purchasing fraud prediction request includes a purchasing item identification code.
In this embodiment, when an enterprise or a user performs purchase fraud prediction, a client initiates a purchase fraud prediction request to a server, specifically, the client may be a smart phone, an IPAD or other existing intelligent devices, the server may be a purchase fraud prediction subsystem, and in the purchase fraud prediction process, if the client can send the purchase fraud prediction request to the purchase fraud prediction subsystem, the purchase fraud prediction subsystem is configured to receive the purchase fraud prediction request sent by the client.
In this embodiment, the data source of the target parameter may be at least one third-party system interacting with the purchasing service system, or may be at least one subsystem of the purchasing service system.
In an alternative embodiment, the parsing module 201 parses the received purchase fraud prediction request to obtain a data source of a plurality of target parameters, including:
analyzing the message of the purchase fraud prediction request to obtain message information carried by the message;
acquiring a forecast demand of purchasing fraud from the message information;
and acquiring data sources of a plurality of target parameters according to the purchasing fraud prediction demand.
Specifically, the purchasing fraud prediction requirement comprises a purchasing item identification code, wherein the purchasing item identification code is used for uniquely identifying the identity of the purchasing service.
Further, the data source for obtaining a plurality of target parameters according to the forecast demand for purchasing fraud comprises:
matching the purchasing item identification code in the purchasing fraud prediction requirement with a system identification code in a preset database, and acquiring a first interface of a purchasing service system corresponding to the purchasing item and a second interface of a third-party system interacting with the purchasing service system;
and calling the first interface and the second interface to obtain a data source of the corresponding target parameter.
In this embodiment, since the associated data related to the purchasing service system may be sourced from the purchasing service system, a third-party system interacting with the purchasing service system, and a subsystem of the purchasing service system, the data source of the corresponding target parameter is obtained by calling the interface of the corresponding purchasing service system, and the data sources of all the target parameters of all the purchasing service systems do not need to be obtained, which is more targeted, and the accuracy of the obtained data source of the target parameter is improved.
The first preprocessing module 202 is configured to obtain an original data set from the data sources of the multiple target parameters, and perform first preprocessing on the original data set to obtain a target data table.
In this embodiment, the original data set refers to original data directly obtained from a data source of the target parameter, and the target data table refers to a data table obtained by processing each original data table in the original data set.
In an alternative embodiment, the first preprocessing module 202 obtaining the raw data set from the data sources of the plurality of target parameters includes:
analyzing the purchasing fraud prediction requirement in the purchasing fraud prediction request, and acquiring the acquisition requirement of the data source of each target parameter and a corresponding acquisition interface;
and calling a collection interface of the data source of each target parameter, and acquiring an original data set from the data source of each target parameter by adopting a crawler technology according to the collection requirement of the data source of each target parameter.
In this embodiment, the forecast demand for purchasing fraud further includes a collection demand of a data source of each target parameter and a corresponding collection interface. The crawler technology is prior art, and the embodiment is not described in detail herein.
In an optional embodiment, the first preprocessing module 202 performs first preprocessing on the original data set to obtain a target data table, including:
identifying a purchasing service system identification code corresponding to each original data table in the original data set;
classifying the original data set according to the purchasing service system identification code;
determining original data sets of the same purchasing service system as a first data set, and determining the remaining original data sets of different purchasing service systems as a second data set;
performing table merging processing on the original data table in the first data set to obtain a first data table, and performing table merging processing on the original data table in the second data set to obtain a second data table;
merging the first data table and the second data table to obtain a third data table;
and carrying out data cleaning on the third data table to obtain a target data table.
In this embodiment, the data cleaning of the third data table by using the preset cleaning policy corresponding to the purchase service system to obtain the target data table includes:
specifically, the cleaning strategy can be set in advance according to the format requirements of the purchasing service system and a third-party system interacting with the purchasing service system, and the data of the third data table is cleaned through the preset cleaning strategy, so that the accuracy of the target data table is improved.
In this embodiment, the procurement services system identification code is used to uniquely identify the system to which each raw data table in the raw data set belongs.
In this embodiment, the original data tables in the first data set originate from the same procurement service system or a subsystem of the same procurement service system, and the data tables in the original data tables in the first data set have the same structure, so that all the original data tables in the first data set are directly subjected to union processing to obtain the first data table.
Further, the performing a table-combining process on the original data table in the second data set to obtain a second data table includes:
identifying a field name for each original data table in the second data set;
merging a plurality of columns with the same field names of a plurality of original data tables, and deleting the plurality of columns participating in merging to obtain a new table;
calculating the total number of the field names of the new table, and acquiring the total number of preset vacant field according to the total number of the field names of the new table;
and expanding the new table based on the total number of the preset vacant fields to obtain a second data table.
In this embodiment, the field name of each original data table is a name specified by each column in the table.
In this embodiment, the original data table in the second data set is derived from different purchasing service systems, and the original data table in the second data set needs to be processed if the data table structures of the different purchasing service systems are different.
In this embodiment, the total number of null fields may be preset, and the total number of null fields set for different data tables is different, for example, the second data set includes an original data table a, an original data table B, and an original data table C, where the original data table a includes 20 field names, the original data table B includes 20 field names, the original data table C includes 15 field names, 15 same field names exist in the original data table a and the original data table B, the same field names in the original data table a and the original data table B are merged, and the original data table C is merged to obtain a new table, the new table includes 40 field names, and a preset null field 5 corresponding to the 40 field names is obtained to obtain the second data table.
In this embodiment, in the process of processing the original data table in the second data set to obtain the second data table, the new table is expanded based on the total number of the preset empty fields, so that the new field names are conveniently added to the second data table directly when new field names are subsequently added, the new field names do not need to be processed again, and the utilization rate of the second data table is improved.
The building module 203 is configured to invoke a rule class label, and obtain a first prediction result from the target data table through a label management system based on the rule class label.
In this embodiment, the rule class label refers to an association relationship between field names in the target data table, and the target data table has the rule class label: personnel information-project information-provider information. The first prediction result is a prediction result corresponding to the rule-class label found in the target data table, that is, the associated data corresponding to the personnel information, the item information and the supplier information is found from the target data table.
In an optional embodiment, the constructing module 203 invokes a rule class label, and based on the rule class label, obtaining the first prediction result through a preset rule engine includes:
converting the data in the target data table into a rule class label which can be identified by a preset rule engine;
and calling a preset rule engine to perform intelligent matching of the rule class labels to obtain a first prediction result.
In this embodiment, the rule class tag is pre-stored in the database, and after the target data table is obtained, the rule class tag is called, data in the target data table is converted into the rule class tag that can be identified by the preset rule engine, and the rule class tag is matched with the called rule class tag, so that a first prediction result is obtained.
In this embodiment, a rule engine may be preset, specifically, the rule engine performs intelligent matching of rule class labels, which belongs to the prior art, and this embodiment is not described in detail herein.
In this embodiment, the first prediction result is obtained by classifying from the target data table based on the rule class label through a preset rule engine, specifically, from a regulatory consideration of the procurement project.
And the extracting and inputting module 204 is configured to extract a characteristic factor set from the target data table, and input the characteristic factor set into a classification prediction model trained in advance to obtain a second prediction result.
In this embodiment, the characteristic factor is obtained by processing a field name associated with the forecast purchase fraud, for example, the person information, the project information, and the provider information in the field name are determined as a characteristic factor.
In an alternative embodiment, the extraction and input module 204 extracts the set of characteristic factors from the target data table including:
acquiring the item information of the purchase item corresponding to the purchase item identification code in the purchase fraud prediction request and a preset processing script;
preprocessing the project information to obtain target project information;
and processing the target project information by adopting the preset processing script to obtain a characteristic factor set.
In this embodiment, the target item information is obtained by preprocessing the item information, specifically, by preprocessing data corresponding to the field name associated with the purchase fraud in the item information, for example, correcting, format converting, and the like.
In this embodiment, the classification prediction model may be trained in advance, after the classification prediction model is trained, the extracted feature factor set is input into the classification prediction model, whether fraud information exists in the data information corresponding to each feature factor is determined, and a prediction result is output to obtain a second prediction result, where the second prediction result is obtained by considering from the process of purchasing a project.
In this embodiment, the input of the classification prediction model is a feature factor set, the feature factor set is used as a training set, a preset neural network model is trained, and the classification prediction model is obtained, and a specific training process is not limited herein.
A second preprocessing module 205, configured to perform second preprocessing on the first prediction result and the second prediction result to obtain a target prediction result.
In this embodiment, the second preprocessing is obtained by performing deduplication processing on the first prediction result and the second prediction result.
In an optional embodiment, the second preprocessing module 205 performs second preprocessing on the first prediction result and the second prediction result to obtain a target prediction result, where the second preprocessing comprises:
comparing the first predicted result with the second predicted result;
deleting the first prediction result which is the same as the second prediction result to obtain a target prediction result.
And the sending module 206 is configured to send the target prediction result to a client, and display the target prediction result on an interface of the client.
And an adding module 207, configured to add the target prediction result to a training set for training a classification prediction model, and retrain the classification prediction model.
In this embodiment, since the first prediction result is obtained based on the rule class label, and the second prediction result is obtained based on the pre-trained classification prediction model, the first prediction result is compared with the second prediction result, for example, the first prediction result includes that the user a has the purchase fraud phenomenon, the second prediction result also includes that the user a has the purchase fraud phenomenon, the user a in the first prediction result is deleted from the purchase fraud phenomenon, the user a in the second prediction result is retained from the purchase fraud phenomenon, and the rule engine and the classification prediction model are combined to obtain the target prediction result, so that the integrity and the accuracy of the target prediction result are improved.
In summary, in the artificial intelligence-based behavior prediction apparatus according to this embodiment, the original data set is first preprocessed, a rule class label is called, a first prediction result is obtained from the target data table through the label management system based on the rule class label, and a second prediction result is obtained from a classification prediction model in which the input values of the feature factor set are trained in advance, the first prediction result is obtained based on the rule engine from the system specification of the purchase item, and the second prediction result is obtained based on the classification prediction model from the process of the purchase item, and the target prediction result is obtained based on the rule engine and the classification prediction model, so that the accuracy of the prediction result of the purchase fraud is improved.
EXAMPLE III
Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention. In the preferred embodiment of the present invention, the electronic device 3 comprises a memory 31, at least one processor 32, at least one communication bus 33 and a transceiver 34.
It will be appreciated by those skilled in the art that the configuration of the electronic device shown in fig. 3 does not constitute a limitation of the embodiment of the present invention, and may be a bus-type configuration or a star-type configuration, and the electronic device 3 may include more or less other hardware or software than those shown, or a different arrangement of components.
In some embodiments, the electronic device 3 is an electronic device capable of automatically performing numerical calculation and/or information processing according to instructions set or stored in advance, and the hardware thereof includes but is not limited to a microprocessor, an application specific integrated circuit, a programmable gate array, a digital processor, an embedded device, and the like. The electronic device 3 may also include a client device, which includes, but is not limited to, any electronic product that can interact with a client through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device, for example, a personal computer, a tablet computer, a smart phone, a digital camera, and the like.
It should be noted that the electronic device 3 is only an example, and other existing or future electronic products, such as those that can be adapted to the present invention, should also be included in the scope of the present invention, and are included herein by reference.
In some embodiments, the memory 31 is used for storing program codes and various data, such as the artificial intelligence-based behavior prediction apparatus 20 installed in the electronic device 3, and realizes high-speed and automatic access to programs or data during the operation of the electronic device 3. The Memory 31 includes a Read-Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an electronically Erasable rewritable Read-Only Memory (Electrically-Erasable Programmable Read-Only Memory (EEPROM)), an optical Read-Only disk (CD-ROM) or other optical disk Memory, a magnetic disk Memory, a tape Memory, or any other medium readable by a computer capable of carrying or storing data.
In some embodiments, the at least one processor 32 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The at least one processor 32 is a Control Unit (Control Unit) of the electronic device 3, connects various components of the electronic device 3 by using various interfaces and lines, and executes various functions and processes data of the electronic device 3 by running or executing programs or modules stored in the memory 31 and calling data stored in the memory 31.
In some embodiments, the at least one communication bus 33 is arranged to enable connection communication between the memory 31 and the at least one processor 32 or the like.
Although not shown, the electronic device 3 may further include a power supply (such as a battery) for supplying power to each component, and optionally, the power supply may be logically connected to the at least one processor 32 through a power management device, so as to implement functions of managing charging, discharging, and power consumption through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 3 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The integrated unit implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, an electronic device, or a network device) or a processor (processor) to execute parts of the methods according to the embodiments of the present invention.
In a further embodiment, in conjunction with fig. 2, the at least one processor 32 may execute operating means of the electronic device 3 and various installed applications (such as the artificial intelligence based behavior prediction apparatus 20), program code, and the like, such as the various modules described above.
The memory 31 has program code stored therein, and the at least one processor 32 can call the program code stored in the memory 31 to perform related functions. For example, the modules illustrated in fig. 2 are program code stored in the memory 31 and executed by the at least one processor 32 to implement the functions of the modules for the purpose of artificial intelligence based behavior prediction.
Illustratively, the program code may be partitioned into one or more modules/units that are stored in the memory 31 and executed by the processor 32 to accomplish the present application. The one or more modules/units may be a series of computer readable instruction segments capable of performing certain functions, which are used for describing the execution process of the program code in the electronic device 3. For example, the program code may be partitioned into a parsing module 201, a first pre-processing module 202, a building module 203, an extraction and input module 204, a second pre-processing module 205, a sending module 206, and an adding module 207.
In one embodiment of the present invention, the memory 31 stores a plurality of computer-readable instructions that are executed by the at least one processor 32 to implement artificial intelligence based behavior prediction functionality.
Specifically, the at least one processor 32 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1, and details are not repeated here.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or that the singular does not exclude the plural. A plurality of units or means recited in the present invention may also be implemented by one unit or means through software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. An artificial intelligence based behavior prediction method, characterized in that the method comprises:
analyzing the received purchase fraud prediction request to obtain data sources of a plurality of target parameters;
acquiring an original data set from the data sources of the target parameters, and performing first preprocessing on the original data set to obtain a target data table;
calling a rule class label, and acquiring a first prediction result from the target data table through a label management system based on the rule class label;
extracting a characteristic factor set from the target data table, inputting the characteristic factor set into a classification prediction model with a pre-trained value, and obtaining a second prediction result;
and performing second preprocessing on the first prediction result and the second prediction result to obtain a target prediction result.
2. The artificial intelligence based behavior prediction method of claim 1, wherein the first preprocessing the raw data set to obtain a target data table comprises:
identifying a purchasing service system identification code corresponding to each original data table in the original data set;
classifying the original data set according to the purchasing service system identification code;
determining original data sets of the same purchasing service system as a first data set, and determining the remaining original data sets of different purchasing service systems as a second data set;
performing table merging processing on the original data table in the first data set to obtain a first data table, and performing table merging processing on the original data table in the second data set to obtain a second data table;
merging the first data table and the second data table to obtain a third data table;
and carrying out data cleaning on the third data table to obtain a target data table.
3. The artificial intelligence based behavior prediction method of claim 2, wherein the merging the original data table in the second data set into the second data table comprises:
identifying a field name for each original data table in the second data set;
merging a plurality of columns with the same field names of a plurality of original data tables, and deleting the plurality of columns participating in merging to obtain a new table;
calculating the total number of the field names of the new table, and acquiring the total number of preset vacant field according to the total number of the field names of the new table;
and expanding the new table based on the total number of the preset vacant fields to obtain a second data table.
4. The artificial intelligence based behavior prediction method according to claim 1, wherein the invoking a rule class label, and the obtaining a first prediction result through a preset rule engine based on the rule class label comprises:
converting the data in the target data table into a rule class label which can be identified by a preset rule engine;
and calling a preset rule engine to perform intelligent matching of the rule class labels to obtain a first prediction result.
5. The artificial intelligence based behavior prediction method of claim 1, wherein the extracting a set of characteristic factors from the target data table comprises:
acquiring the item information of the purchase item corresponding to the purchase item identification code in the purchase fraud prediction request and a preset processing script;
preprocessing the project information to obtain target project information;
and processing the target project information by adopting the preset processing script to obtain a characteristic factor set.
6. The artificial intelligence based behavior prediction method of claim 1, wherein the second preprocessing of the first prediction result and the second prediction result to obtain a target prediction result comprises:
comparing the first predicted result with the second predicted result;
deleting the first prediction result which is the same as the second prediction result to obtain a target prediction result.
7. The artificial intelligence based behavior prediction method of claim 1, wherein the parsing the received purchase fraud prediction request to obtain a data source of a plurality of target parameters comprises:
analyzing the message of the purchase fraud prediction request to obtain message information carried by the message;
acquiring a forecast demand of purchasing fraud from the message information;
matching the purchasing item identification code in the purchasing fraud prediction requirement with a system identification code in a preset database, and acquiring a first interface of a purchasing service system corresponding to the purchasing item and a second interface of a third-party system interacting with the purchasing service system;
and calling the first interface and the second interface to obtain a data source of the corresponding target parameter.
8. An artificial intelligence based behavior prediction apparatus, the apparatus comprising:
the analysis module is used for analyzing the received purchase fraud prediction request to obtain a plurality of data sources of target parameters;
the first preprocessing module is used for acquiring an original data set from the data sources of the target parameters and performing first preprocessing on the original data set to obtain a target data table;
the building module is used for calling a rule class label and acquiring a first prediction result from the target data table through a label management system based on the rule class label;
the extraction and input module is used for extracting a characteristic factor set from the target data table and inputting the characteristic factor set into a classification prediction model with trained characteristic factor set input values in advance to obtain a second prediction result;
and the second preprocessing module is used for performing second preprocessing on the first prediction result and the second prediction result to obtain a target prediction result.
9. An electronic device, characterized in that the electronic device comprises a processor and a memory, the processor being configured to implement the artificial intelligence based behavior prediction method according to any one of claims 1 to 7 when executing a computer program stored in the memory.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the artificial intelligence based behavior prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210450910.4A CN114881313A (en) | 2022-04-26 | 2022-04-26 | Behavior prediction method and device based on artificial intelligence and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210450910.4A CN114881313A (en) | 2022-04-26 | 2022-04-26 | Behavior prediction method and device based on artificial intelligence and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114881313A true CN114881313A (en) | 2022-08-09 |
Family
ID=82672440
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210450910.4A Pending CN114881313A (en) | 2022-04-26 | 2022-04-26 | Behavior prediction method and device based on artificial intelligence and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114881313A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115860677A (en) * | 2022-12-12 | 2023-03-28 | 中量工程咨询有限公司 | Component engineering quantity data processing method, system, equipment and storage medium |
-
2022
- 2022-04-26 CN CN202210450910.4A patent/CN114881313A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115860677A (en) * | 2022-12-12 | 2023-03-28 | 中量工程咨询有限公司 | Component engineering quantity data processing method, system, equipment and storage medium |
| CN115860677B (en) * | 2022-12-12 | 2024-03-22 | 中量工程咨询有限公司 | Component engineering quantity data processing method, system, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114663198A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN111949708A (en) | Multi-task prediction method, device, equipment and medium based on time sequence feature extraction | |
| CN114663223A (en) | Credit risk assessment method, device and related equipment based on artificial intelligence | |
| CN113435998A (en) | Loan overdue prediction method and device, electronic equipment and storage medium | |
| CN112948275A (en) | Test data generation method, device, equipment and storage medium | |
| CN114201328A (en) | Fault processing method and device based on artificial intelligence, electronic equipment and medium | |
| CN113256108A (en) | Human resource allocation method, device, electronic equipment and storage medium | |
| CN113435582A (en) | Text processing method based on sentence vector pre-training model and related equipment | |
| CN112950344A (en) | Data evaluation method and device, electronic equipment and storage medium | |
| CN113674065B (en) | Service contact-based service recommendation method and device, electronic equipment and medium | |
| CN114201212B (en) | Configuration file processing method, device, computer equipment and storage medium | |
| CN114880449A (en) | Reply generation method and device of intelligent question answering, electronic equipment and storage medium | |
| CN114881313A (en) | Behavior prediction method and device based on artificial intelligence and related equipment | |
| CN113268478A (en) | Big data analysis method and device, electronic equipment and storage medium | |
| CN111651452A (en) | Data storage method and device, computer equipment and storage medium | |
| CN114925674A (en) | File compliance checking method and device, electronic equipment and storage medium | |
| CN117252362A (en) | Scheduling method and device based on artificial intelligence, computer equipment and storage medium | |
| CN113254728B (en) | Task information display method and device, electronic equipment and storage medium | |
| CN116108276A (en) | Information recommendation method and device based on artificial intelligence and related equipment | |
| CN114996386A (en) | Business role identification method, device, equipment and storage medium | |
| CN115061895A (en) | Business process arranging method and device, electronic equipment and storage medium | |
| CN114239538A (en) | Assertion processing method and device, computer equipment and storage medium | |
| CN113987351A (en) | Artificial intelligence based intelligent recommendation method and device, electronic equipment and medium | |
| CN114580409A (en) | Text classification method and device, electronic equipment and storage medium | |
| CN113449037A (en) | AI-based SQL engine calling method, device, equipment and 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 |