Business role identification method, device, equipment and storage medium

Abstract

The present application relates to artificial intelligence technology, and discloses a business role recognition method, comprising: classifying a business data set by source to obtain multiple business subsets of different sources; extracting a business subset in the multiple business subsets that meets a preset source condition as a target subset, performing initial role recognition on the target subset, and determining a target business user as a first role when the role recognition result is the target business user as the first role; when the role verification passes, the target business user is determined as the first role; the role recognition result is the target business user as a second role, and a keyword of a target field in the multiple target subsets is extracted; the target business user is subdivided according to the keyword to obtain the role of the target business user. In addition, the present application also relates to blockchain technology, and the target subset can be stored in a node of the blockchain. The present application also provides a business role recognition device, an electronic device and a storage medium. The present application can improve the efficiency of business role recognition.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and in particular to a business role recognition method and device, electronic equipment and a computer readable storage medium. BACKGROUND

[0002] In different business fields, the order is a key part of the business. By simplifying the order process, reducing the workload of the order operator, and improving the order efficiency, the purpose of improving the order personnel productivity and reducing the company's operating costs can be achieved. Accurately identifying the role of the order personnel is the primary condition for simplifying the order process.

[0003] The traditional method of identifying the role of the business personnel is to query and compare the business role database to obtain the role to which the current business personnel belongs. This method needs to compare the current business personnel with the data in the business role database one by one, and then confirm the business role, thereby resulting in low efficiency of business role identification. SUMMARY

[0004] The present application provides a business role recognition method, device and computer readable storage medium, which mainly aims to improve the efficiency of business role identification.

[0005] To achieve the above purpose, the present application provides a business role recognition method, comprising:

[0006] Obtain a business data set, classify the data sources of the business data set, and obtain a plurality of business subsets of different sources;

[0007] Extract a plurality of business subsets that meet the preset source conditions as target subsets, and perform initial role recognition on the target subsets to obtain a role recognition result;

[0008] When the role recognition result is that the target business user corresponding to the target subset is a first role, the role of the target business user is verified, and when the role verification is passed, the target business user is determined as the first role;

[0009] When the role recognition result is that the target business user corresponding to the target subset is a second role, a plurality of target fields in the target subset are extracted, and a plurality of target fields are subjected to keyword extraction;

[0010] According to the keywords, the role of the target business user is subdivided to obtain the role corresponding to the target business user.

[0011] Optionally, the classification of the data sources of the business data set to obtain a plurality of business subsets of different sources comprises:

[0012] standardizing the business data set to obtain a standard data set;

[0013] performing source identification on the standard data set by using a pre-trained source identification model to obtain sources corresponding to a plurality of standard data in the standard data set;

[0014] clustering the data of the same source to obtain a plurality of business subsets of different sources.

[0015] Optionally, the standardizing the business data set to obtain a standard data set comprises:

[0016] performing data cleaning on the business data in the business data set to obtain a cleaned data set;

[0017] retaining data in the cleaned data set that meets a preset configuration rule as the standard data set.

[0018] Optionally, the role subdivision of the target business user according to the keyword to obtain the role corresponding to the target business user comprises:

[0019] performing keyword label marking on the target business user based on the keyword;

[0020] indexing a key role corresponding to the keyword label in a preset keyword role library, and taking the key role as the role corresponding to the target business user.

[0021] Optionally, the keyword extraction on a plurality of target fields comprises:

[0022] collecting a training data set and constructing a deep neural network;

[0023] training the deep neural network by using the training data set to obtain a trained keyword extraction model;

[0024] outputting the target field to the keyword extraction model to obtain a keyword corresponding to the target field.

[0025] Optionally, the role verification of the target business user comprises:

[0026] obtaining corresponding role information in a preset role information reference library based on the first role;

[0027] performing information verification on the target business user according to the role information, and determining the target business user as the first role when the information verification is passed.

[0028] Optionally, the initial role identification of the target subset to obtain a role identification result comprises:

[0029] The target subset is compared with data in a preset personal information library, and a personal role corresponding to data consistent with the target subset is taken as an initial role of a target business user corresponding to the target subset;

[0030] The target subset is initially verified according to related information of the initial role, and when the initial verification is passed, the initial role is determined as a role corresponding to the target business user corresponding to the target subset.

[0031] To solve the above problems, the application further provides a business role identification device, which comprises:

[0032] A source classification module is configured to obtain a business data set, classify data sources of the business data set, and obtain a plurality of business subsets of different sources;

[0033] An initial identification module is configured to extract a business subset meeting a preset source condition from the plurality of business subsets as a target subset, and perform initial role identification on the target subset to obtain a role identification result;

[0034] A role verification module is configured to perform role verification on a target business user corresponding to the target subset when the role identification result is that the target business user is a first role, and determine the target business user as the first role when the role verification is passed;

[0035] A role subdivision module is configured to extract a plurality of target fields in the target subset when the role identification result is that the target business user corresponding to the target subset is a second role, perform keyword extraction on the plurality of target fields, and perform role subdivision on the target business user according to the keywords to obtain a role corresponding to the target business user.

[0036] To solve the above problems, the application further provides an electronic device, which comprises:

[0037] At least one processor; and

[0038] A memory in communication connection with the at least one processor; wherein

[0039] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the business role identification method.

[0040] To solve the above problems, the application further provides a computer readable storage medium, wherein at least one computer program is stored in the computer readable storage medium, and the at least one computer program is executed by a processor in an electronic device to implement the business role identification method.

[0041] The embodiment of the application classifies the business data set according to data sources to obtain a plurality of business subsets of different sources, the data source classification can be used as a basis for preliminary division of the business data set, and a plurality of business subsets meeting preset source conditions are extracted from the plurality of business subsets as target subsets, so that the accuracy of the sources of the target subsets is ensured. The initial role identification is performed on the target subsets to obtain role identification results, and the role verification or role subdivision is performed according to the role identification results, so that the efficiency of role identification is improved while the accuracy of role identification is ensured. Therefore, the business role identification method, device, electronic device and computer readable storage medium provided by the application can solve the problem of low efficiency of business role identification. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 A flowchart of a business role identification method provided by an embodiment of the application is shown in the figure.

[0043] Figure 2 A function module diagram of a business role identification device provided by an embodiment of the application is shown in the figure.

[0044] Figure 3 A structure diagram of an electronic device for implementing the business role identification method provided by an embodiment of the application is shown in the figure.

[0045] The implementation, functional features and advantages of the application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0046] It should be understood that the specific embodiments described herein are only used to explain the application, and are not used to limit the application.

[0047] The embodiment of the application provides a business role recognition method. The execution subject of the business role recognition method includes but is not limited to at least one of electronic devices such as a server, a terminal and the like which can be configured to execute the method provided by the embodiment of the application. In other words, the business role recognition method can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to a single server, a server cluster, a cloud server or a cloud server cluster and the like. The server can be a stand-alone server, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

[0048] Referring to Figure 1 FIG. 1 is a flowchart of a business role recognition method provided by an embodiment of the application. In this embodiment, the business role recognition method includes the following steps.

[0049] S1, obtaining a business data set, classifying data sources of the business data set to obtain a plurality of business subsets of different sources.

[0050] In the embodiment of the application, the business data set includes order data from different system sources such as a company internal system, a company external interface platform and a collective internal interface platform. Since the data from different system sources is operated by different business personnel, the system source can be used as an initial reference for role recognition.

[0051] Specifically, the classification of the data sources of the business data set to obtain a plurality of business subsets of different sources includes the following steps.

[0052] standardizing the business data set to obtain a standard data set;

[0053] using a pre-trained source recognition model to recognize the sources of the standard data set to obtain the sources corresponding to a plurality of standard data in the standard data set;

[0054] clustering the data of the same source to obtain a plurality of business subsets of different sources.

[0055] Further, the standardization of the business data set to obtain a standard data set includes the following steps.

[0056] performing data cleaning on the business data in the business data set to obtain a cleaned data set;

[0057] retaining data in the cleaned data set that meets a preset configuration rule as the standard data set.

[0058] In detail, the data cleaning includes performing a deletion operation on an abnormal value in the business data set and performing a completion operation on a missing value in the business data set. The abnormal value in the business data can be detected by using a Java statement with abnormality detection. When there is a missing value in the business data set, the business data set can be completed by using an existing missing value filling method, including but not limited to filling a default value, a mean value, a mode value, and KNN filling.

[0059] The preset configuration rule is specified according to specific conditions, and in the present scheme, the configuration rule is to delete a blank field in the business data.

[0060] Specifically, before the standard data set is subjected to source identification by using the pre-trained source identification model, the method further includes:

[0061] The standard data set is input into a preset source identification model to perform source prediction, and a predicted source label is obtained.

[0062] The predicted source label is compared with a preset real source label.

[0063] When the predicted source label is consistent with the real source label, the source identification model is output as a pre-trained source identification model.

[0064] When the predicted source label is inconsistent with the real source label, the source identification model is subjected to model parameter adjustment to obtain an adjusted source identification model.

[0065] The standard data set is input into the adjusted source identification model to perform source prediction, and a new predicted source label is obtained. When the new predicted source label is consistent with the real source label, the adjusted source identification model is a trained source identification model.

[0066] In detail, the preset source identification model can be a convolutional neural network model.

[0067] Specifically, the standard data set is input into a preset source identification model to perform source prediction, and a predicted source label is obtained, including:

[0068] The standard data set is subjected to convolution processing and pooling processing by using a convolution layer and a pooling layer in the source identification model, and a feature data set is obtained.

[0069] The feature data set is input into a preset activation function, and an activation probability corresponding to the feature data set is obtained.

[0070] According to the activation probability and a preset label reference table, a corresponding predicted source label is obtained.

[0071] Further, the data of the same source are clustered to obtain a plurality of business subsets of different sources.

[0072] S2, extracting a business subset meeting a preset source condition from the plurality of business subsets as a target subset, and performing initial role identification on the target subset to obtain a role identification result.

[0073] In the embodiment of the application, the preset source condition can be a company internal, and the business subset meeting the preset source condition from the plurality of business subsets is extracted as the target subset, that is, the business subset with data source being the company internal from the plurality of business subsets is extracted as the target subset.

[0074] Specifically, the initial role identification on the target subset to obtain the role identification result comprises:

[0075] comparing the target subset with data in a preset personal information library, and taking a personal role corresponding to the data consistent with the target subset as an initial role of a target business user corresponding to the target subset;

[0076] performing initial verification on the target subset according to related information of the initial role, and when the initial verification passes, determining that the initial role is a role corresponding to the target business user corresponding to the target subset.

[0077] In detail, the personal information library contains a plurality of employee information, and the related information of the initial role is basic identity information and the like about the initial role.

[0078] For example, the target subset is compared with data in the preset personal information library, and employee belonging to a business line in the employee information judges whether the employee is a business employee or an internal staff; the roles of the order recording personnel are judged by using the employee UM account, the employee Chinese name, the related information such as the associated order recording operator in the employee information table, for example, whether it is an order recording internal staff or a business employee.

[0079] S3, when the role identification result is that the target business user corresponding to the target subset is a first role, performing role verification on the target business user, and when the role verification passes, determining that the target business user is the first role.

[0080] In the embodiment of the application, the first role is a business employee. That is, when the role identification result is that the target business user corresponding to the target subset is a first role, role verification is performed on the target business user.

[0081] Specifically, the role verification on the target business user comprises:

[0082] Obtaining corresponding role information in a preset role information reference library based on the first role;

[0083] Performing information verification on the target business user according to the role information, and determining the target business user as the first role when the information verification is passed.

[0084] In detail, the role information reference library comprises different roles and corresponding role information of the different roles.

[0085] S4, when the role recognition result is that the target business user corresponding to the target subset is the second role, extracting a plurality of target fields in the target subset, and performing keyword extraction on the plurality of target fields.

[0086] In the embodiment of the application, the second role can be a customer. Since the customer can be further divided into different roles such as an agent or a broker, the customer can be further subdivided.

[0087] Specifically, the extracting a plurality of target fields in the target subset comprises:

[0088] Finding a name index in the target subset;

[0089] Taking a field under the name index as the plurality of target fields in the target subset.

[0090] In detail, taking data contained under the name index in the target subset as the plurality of target fields in the target subset, for example, the name index is “customer name”, and the target field is an agent Zhang San.

[0091] Further, the keyword extraction on the plurality of target fields comprises:

[0092] Collecting a training data set and constructing a deep neural network;

[0093] Training the deep neural network by using the training data set to obtain a trained keyword extraction model;

[0094] Outputting the target field to the keyword extraction model to obtain keywords corresponding to the plurality of target fields.

[0095] Specifically, the training data set can be collected by using a crawler technology. The target field is output to the keyword extraction model to obtain keywords corresponding to the plurality of target fields, which can be keywords “agent” and “economy”.

[0096] S5, role subdivide the target business user according to the keyword, and obtain the role corresponding to the target business user.

[0097] In the embodiment of the application, the role corresponding to the target business user is obtained by role subdivide the target business user according to the keyword, and the role subdivide the target business user according to the keyword comprises:

[0098] The target business user is marked with a keyword tag based on the keyword.

[0099] The keyword tag is indexed in a preset keyword role library to obtain a key role corresponding to the keyword tag, and the key role is taken as the role corresponding to the target business user.

[0100] In detail, the keyword can be "agent" or "economy", the keyword "agent" and the keyword "economy" are taken as the keyword tags of the target business user, the keyword role library contains a plurality of role names related to the keyword tags, similar to "agent" or "broker". The keyword tag "agent" is indexed in the preset keyword role library to obtain the key role "agent", and the key role "agent" is taken as the role corresponding to the target business user.

[0101] The embodiment of the application classifies the business data set according to the data source to obtain a plurality of business subsets of different sources, the data source classification can be used as a basis for preliminary division of the business data set, and a plurality of business subsets meeting a preset source condition are extracted from the business subsets as target subsets, so as to ensure the accuracy of the source of the target subset. The initial role recognition is performed on the target subset to obtain a role recognition result, and the role verification or role subdivide is performed according to the role recognition result, so as to improve the efficiency of role recognition while ensuring the accuracy of role recognition. Therefore, the business role recognition method provided by the application can solve the problem of low efficiency of business role recognition.

[0102] As shown in Figure 2 Fig. 1 is a functional module diagram of a business role recognition device provided by an embodiment of the application.

[0103] The business role recognition device 100 provided by the application can be installed in an electronic device. According to the functions to be implemented, the business role recognition device 100 can include a source classification module 101, an initial recognition module 102, a role verification module 103, and a role subdivide module 104. The modules provided by the application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete a fixed function, and are stored in the memory of the electronic device.

[0104] In the embodiment, the functions of each module / unit are as follows:

[0105] The source classification module 101 is configured to obtain a business data set, perform data source classification on the business data set, and obtain a plurality of business subsets of different sources.

[0106] The initial identification module 102 is configured to extract a business subset meeting a preset source condition from the plurality of business subsets as a target subset, perform initial role identification on the target subset, and obtain a role identification result.

[0107] The role verification module 103 is configured to, when the role identification result is that a target business user corresponding to the target subset is a first role, perform role verification on the target business user, and determine the target business user as the first role when the role verification is passed.

[0108] The role subdivision module 104 is configured to, when the role identification result is that the target business user corresponding to the target subset is a second role, extract a plurality of target fields in the target subset, perform keyword extraction on the plurality of target fields, perform role subdivision on the target business user according to the keywords, and obtain a role corresponding to the target business user.

[0109] In detail, the specific implementation of each module of the business role identification apparatus 100 is as follows:

[0110] Step 1: Obtain a business data set, perform data source classification on the business data set, and obtain a plurality of business subsets of different sources.

[0111] In the example of the application, the business data set includes order data from different system sources such as a company internal system, a company external interface platform, and a collective internal interface platform. Since the data from different system sources is operated by different business personnel, the system source can be used as an initial reference for role identification.

[0112] Specifically, the data source classification on the business data set to obtain a plurality of business subsets of different sources includes:

[0113] Standardizing the business data set to obtain a standard data set;

[0114] Performing source identification on the standard data set by using a pre-trained source identification model to obtain sources corresponding to a plurality of standard data in the standard data set;

[0115] Clustering the data of the same source to obtain a plurality of business subsets of different sources.

[0116] Further, the standardization of the business data set to obtain a standard data set includes:

[0117] data cleaning is performed on the business data in the business data set to obtain a cleaned data set;

[0118] data in the cleaned data set that meets a preset configuration rule is retained as a standard data set.

[0119] In detail, the data cleaning includes performing a deletion operation on an abnormal value in the business data set and performing a completion operation on a missing value in the business data set. The business data can be detected for abnormality by using a java statement with abnormality detection. When there is a missing value in the business data set, the business data set can be completed by using an existing missing value filling method, which includes but is not limited to filling a default value, a mean value, a mode value, and KNN filling.

[0120] The preset configuration rule is specified according to specific conditions, and in the present scheme, the configuration rule is to delete a blank field in the business data.

[0121] Specifically, before the standard data set is subjected to source identification by using the pre-trained source identification model, the following operations are further performed:

[0122] The standard data set is input into a preset source identification model to perform source prediction, to obtain a predicted source label;

[0123] The predicted source label is compared with a preset real source label;

[0124] When the predicted source label is consistent with the real source label, the source identification model is output as a pre-trained source identification model;

[0125] When the predicted source label is inconsistent with the real source label, the source identification model is subjected to model parameter adjustment to obtain an adjusted source identification model;

[0126] The standard data set is input into the adjusted source identification model to perform source prediction, to obtain a new predicted source label, and when the new predicted source label is consistent with the real source label, the adjusted source identification model is a trained source identification model.

[0127] In detail, the preset source identification model can be a convolutional neural network model.

[0128] Specifically, the standard data set is input into a preset source identification model to perform source prediction, to obtain a predicted source label, including:

[0129] Convolutional layers and pooling layers in the source identification model are used to perform convolutional processing and pooling processing on the standard data set, to obtain a feature data set;

[0130] The feature data set is input into a preset activation function, to obtain an activation probability corresponding to the feature data set;

[0131] According to the activation probability and a preset label reference table, a corresponding predicted source label is obtained.

[0132] Further, the data of the same source are clustered to obtain a plurality of business subsets of different sources.

[0133] Step two, extracting a business subset meeting a preset source condition from the plurality of business subsets as a target subset, and performing initial role identification on the target subset to obtain a role identification result.

[0134] In the embodiment of the application, the preset source condition can be a company internal, and extracting a business subset meeting a preset source condition from the plurality of business subsets as a target subset means extracting a business subset whose data source is a company internal from the plurality of business subsets as a target subset.

[0135] Specifically, the initial role identification on the target subset to obtain a role identification result comprises:

[0136] Comparing the target subset with data in a preset personal information library, and taking a personal role corresponding to data consistent with the target subset as an initial role of a target business user corresponding to the target subset;

[0137] According to related information of the initial role, the target subset is initially verified, and when the initial verification is passed, the initial role is determined as a role corresponding to the target business user corresponding to the target subset.

[0138] In detail, the personal information library contains a plurality of employee information, and the related information of the initial role is basic identity information and the like about the initial role.

[0139] For example, comparing the target subset with data in a preset personal information library, employee belonging to a business line in employee information is used to determine whether an employee is a business employee or an internal staff; and related information such as an employee UM account, an employee Chinese name, and an associated order recording operator in an employee information table is used to preferentially determine a role of an order recording personnel, such as whether it is an order recording internal staff or a business employee.

[0140] Step three, when the role recognition result is that the target business user corresponding to the target subset is a first role, performing role verification on the target business user, and when the role verification passes, determining the target business user as the first role.

[0141] In the embodiment of the application, the first role is a business staff.

[0142] Specifically, the role verification on the target business user comprises:

[0143] acquiring corresponding role information in a preset role information reference library based on the first role;

[0144] performing information verification on the target business user according to the role information, and determining the target business user as the first role when the information verification passes.

[0145] In detail, the role information reference library contains different roles and role information corresponding to different roles.

[0146] Step four, when the role recognition result is that the target business user corresponding to the target subset is a second role, extracting a plurality of target fields in the target subset, and performing keyword extraction on the plurality of target fields.

[0147] In the embodiment of the application, the second role can be a customer.

[0148] Specifically, the extraction of the plurality of target fields in the target subset comprises:

[0149] finding a name index in the target subset;

[0150] taking a field under the name index as the plurality of target fields in the target subset.

[0151] In detail, data contained under the name index in the target subset is taken as the plurality of target fields in the target subset.

[0152] Further, the keyword extraction on the plurality of target fields comprises:

[0153] collecting a training data set and constructing a deep neural network;

[0154] The deep neural network is trained using the training dataset to obtain a trained keyword extraction model;

[0155] The target fields are output to the keyword extraction model to obtain keywords corresponding to multiple target fields.

[0156] Specifically, a training dataset can be collected using web crawling technology. The target fields are then output to the keyword extraction model to obtain keywords corresponding to multiple target fields, such as the keyword "proxy" and the keyword "economy".

[0157] Step 5: Based on the keywords, segment the target business users into roles to obtain the roles corresponding to the target business users.

[0158] In this embodiment of the invention, the step of segmenting the target business user into roles based on the keywords to obtain the roles corresponding to the target business user includes:

[0159] Based on the keywords, the target business users are tagged with keyword tags;

[0160] The key roles corresponding to the keyword tags are indexed from the preset keyword role library, and the key roles are used as the roles corresponding to the target business users.

[0161] Specifically, the keywords can be "agent" or "economy," so the keywords "agent" and "economy" are used as keyword tags for the target business user. The keyword role library contains multiple role names related to keyword tags, such as "agent" or "broker." The key role "agent" corresponding to the keyword tag "agent" is indexed from the preset keyword role library, and the key role "agent" is used as the role corresponding to the target business user.

[0162] This invention, through data source classification of a business dataset, yields multiple business subsets from different sources. This data source classification serves as a preliminary basis for dividing the business dataset. Furthermore, business subsets meeting preset source conditions are extracted as target subsets, ensuring the accuracy of the target subsets' sources. Initial role recognition is then performed on the target subsets to obtain role recognition results. Based on these results, role verification or subdivision is performed, improving the efficiency of role recognition while maintaining accuracy. Therefore, the business role recognition device proposed in this invention effectively solves the problem of insufficient efficiency in business role recognition.

[0163] like Figure 3 The diagram shown is a structural schematic of an electronic device for implementing a business role recognition method according to an embodiment of the present invention.

[0164] The electronic device 1 can include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and can further include a computer program, such as a business role identification program, stored in the memory 11 and executable on the processor 10.

[0165] The processor 10 can be composed of integrated circuits in some embodiments, for example, can be composed of a single packaged integrated circuit, or can be composed of multiple packaged integrated circuits with the same function or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, combinations of various control chips, etc. The processor 10 is the control core of the electronic device, which connects various components of the entire electronic device through various interfaces and lines, executes programs or modules stored in the memory 11 (such as executing a business role identification program, etc.), and calls data stored in the memory 11 to perform various functions of the electronic device and process data.

[0166] The memory 11 includes at least one type of readable storage medium, including a flash memory, a mobile hard disk, a multimedia card, a card-type memory (such as an SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 can be an internal storage unit of the electronic device in some embodiments, for example, a mobile hard disk of the electronic device. The memory 11 can also be an external storage device of the electronic device in other embodiments, for example, a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device. Further, the memory 11 can include both an internal storage unit and an external storage device of the electronic device. The memory 11 can be used not only to store application software and various data installed on the electronic device, such as the code of a business role identification program, but also to temporarily store data that has been output or will be output.

[0167] The communication bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0168] The communication interface 13 is used for communication between the electronic device and other devices, including a network interface and a user interface. Optionally, the network interface can include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used to establish a communication connection between the electronic device and other electronic devices. The user interface can be a display, an input unit (such as a keyboard), and optionally, the user interface can also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, etc. The display can also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visualized user interface.

[0169] Figure 3 Only the electronic device with components is shown, and those skilled in the art can understand that, Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and can include fewer or more components than shown, or combine certain components, or different component arrangements.

[0170] For example, although not shown, the electronic device can also include a power supply (such as a battery) for powering each component. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, so that functions such as charge management, discharge management, and power consumption management can be realized through the power management device. The power supply can also include one or more direct current or alternating current power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and any other components. The electronic device can also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which are not described here.

[0171] It should be understood that the embodiments are only for illustration and are not limited in the scope of the patent application by this structure.

[0172] The service role recognition program stored in the memory 11 in the electronic device 1 is a combination of multiple instructions, which, when running in the processor 10, can realize:

[0173] Obtaining a service data set, classifying the data sources of the service data set to obtain multiple service subsets of different sources;

[0174] Extracting multiple service subsets that meet the preset source conditions as target subsets, and performing initial role recognition on the target subsets to obtain role recognition results;

[0175] When the role recognition result is that the target business user corresponding to the target subset is a first role, performing role verification on the target business user, and when the role verification passes, determining the target business user as the first role;

[0176] When the role recognition result is that the target business user corresponding to the target subset is a second role, extracting a plurality of target fields in the target subset, and performing keyword extraction on the plurality of target fields;

[0177] Performing role subdivision on the target business user according to the keyword, to obtain a role corresponding to the target business user.

[0178] Specifically, the specific implementation method of the processor 10 on the above instructions can refer to the description of the related steps in the corresponding embodiments of the drawings, which will not be repeated here.

[0179] Further, the modules / units integrated in the electronic device 1 are implemented in the form of software function units and sold or used as independent products, which can be stored in a computer readable storage medium. The computer readable storage medium can be volatile or non-volatile. For example, the computer readable medium can include any entity or device capable of carrying the computer program code, a recording medium, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM).

[0180] The application also provides a computer readable storage medium, which stores a computer program, and the computer program can realize the following when executed by a processor of an electronic device:

[0181] Obtaining a business data set, classifying data sources of the business data set to obtain a plurality of business subsets of different sources;

[0182] Extracting a business subset meeting a preset source condition from the plurality of business subsets as a target subset, and performing initial role recognition on the target subset to obtain a role recognition result;

[0183] When the role recognition result is that the target business user corresponding to the target subset is a first role, performing role verification on the target business user, and when the role verification passes, determining the target business user as the first role;

[0184] When the role recognition result is that the target business user corresponding to the target subset is a second role, extracting a plurality of target fields in the target subset, and performing keyword extraction on the plurality of target fields;

[0185] According to the keyword, the target business user is role-subdivided, and a role corresponding to the target business user is obtained.

[0186] In several embodiments provided by the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other manners. For example, the described embodiments of the apparatus are merely schematic, and the division of the modules is merely a logical function division, and there can be another division manner in actual implementation.

[0187] The modules illustrated as separated components can or can not be physically separated, and the components illustrated as modules can or can not be physical units, that is, can be located in one place, or can be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purposes of the embodiments.

[0188] In addition, each function module in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware, or in the form of hardware plus software function module.

[0189] It is obvious for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0190] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting, and the scope of the present application is defined by the appended claims rather than the above description, and therefore all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present application. Any additional reference signs in the claims should not be considered as limiting the claims involved.

[0191] The blockchain referred to in the present application is a new application mode of distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm and other computer technologies. Blockchain, in essence, is a decentralized database, which is a series of data blocks associated using cryptography. Each data block contains information about a batch of network transactions, which is used to verify the validity (anti-fake) of the information and generate the next block. The blockchain can include a blockchain underlying platform, a platform product service layer, and an application service layer.

[0192] Embodiments of the present application can acquire and process related data based on artificial intelligence technology. Among them, artificial intelligence (AI) is to use digital computers or computer-controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0193] Furthermore, the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. Multiple units or devices stated in a system claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names and not to indicate any particular order.

[0194] Finally, it should be pointed out that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit it. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A business role identification method, characterized by, The method comprises: obtaining a business data set, performing data source classification on the business data set to obtain a plurality of business subsets of different sources; extracting a business subset in the plurality of business subsets that meets a preset source condition as a target subset, and performing initial role identification on the target subset to obtain a role identification result; when the role identification result is that a target business user corresponding to the target subset is a first role, obtaining corresponding role information of the first role in a preset role information reference library, performing information verification on the target business user according to the role information, and determining the target business user as the first role when the information verification is passed; when the role identification result is that the target business user corresponding to the target subset is a second role, finding a name index in the target subset, taking fields under the name index as a plurality of target fields in the target subset, training a preset deep neural network using a training data set to obtain a trained keyword extraction model, outputting the plurality of target fields into the keyword extraction model to obtain keywords corresponding to the plurality of target fields; performing role segmentation on the target business user according to the keywords to obtain a role corresponding to the target business user; wherein the initial role identification on the target subset to obtain the role identification result comprises: comparing the target subset with data in a preset personal information library, and taking a personal role corresponding to data consistent with the target subset as an initial role of a target business user corresponding to the target subset; performing initial verification on the target subset according to related information of the initial role, and determining the initial role as a role corresponding to the target business user corresponding to the target subset when the initial verification is passed.

2. The business role identification method of claim 1, wherein, The data source classification on the business data set to obtain a plurality of business subsets of different sources comprises: performing standardization processing on the business data set to obtain a standard data set; performing source identification on the standard data set using a pre-trained source identification model to obtain sources corresponding to a plurality of standard data in the standard data set; clustering data of the same source to obtain a plurality of business subsets of different sources.

3. The business role identification method of claim 2, wherein, The standardization processing on the business data set to obtain a standard data set comprises: performing data cleaning on business data in the business data set to obtain a cleaned data set; retaining data in the cleaned data set that meets a preset configuration rule as a standard data set.

4. The business role identification method of claim 1, wherein, The role segmentation on the target business user according to the keywords to obtain a role corresponding to the target business user comprises keyword label marking on the target business user based on the keywords; indexing a key role corresponding to the keyword label in a preset keyword role library, and taking the key role as a role corresponding to the target business user.

5. A business role identifying apparatus for implementing the business role identifying method according to any one of claims 1 to 4, characterized by, The device comprises: a source classification module configured to obtain a business data set, perform data source classification on the business data set, and obtain a plurality of business subsets of different sources; An initial identification module is configured to extract a service subset meeting a preset source condition from the plurality of service subsets as a target subset, and perform initial role identification on the target subset to obtain a role identification result; A role verification module is configured to, when the role identification result indicates that a target service user corresponding to the target subset is a first role, perform role verification on the target service user, and determine the target service user as the first role when the role verification is passed; A role subdivision module is configured to, when the role identification result indicates that a target service user corresponding to the target subset is a second role, extract a plurality of target fields in the target subset, perform keyword extraction on the plurality of target fields, and perform role subdivision on the target service user according to the keywords to obtain a role corresponding to the target service user.

6. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the service role identification method according to any one of claims 1 to 4.

7. A computer readable storage medium storing a computer program, characterized in that, The computer program is executed by the processor to implement the service role identification method according to any one of claims 1 to 4.

Images