CN111367965B

CN111367965B - Target object determining method, device, electronic equipment and storage medium

Info

Publication number: CN111367965B
Application number: CN202010144805.9A
Authority: CN
Inventors: 刘志煌
Original assignee: Tencent Cloud Computing Beijing Co Ltd
Current assignee: Tencent Cloud Computing Beijing Co Ltd
Priority date: 2020-03-04
Filing date: 2020-03-04
Publication date: 2023-05-02
Anticipated expiration: 2040-03-04
Also published as: CN111367965A

Abstract

The invention provides a target object determining method, which comprises the following steps: acquiring resource transaction data corresponding to different objects; determining corresponding object coding features and behavior coding features, and determining corresponding candidate object sets according to the object coding features and the behavior coding features; determining a characteristic coding frequent sequence mode corresponding to the candidate object set; weighting the characteristic code frequent sequence modes corresponding to the candidate object set, and determining a weight parameter matched with the target object; clustering the object coding features and the behavior coding features respectively; and determining target objects matched with the screening conditions in the candidate object set according to the clustering results of the object coding features and the behavior coding features and the corresponding screening conditions. The invention also provides a processing device, electronic equipment and a storage medium. The method and the device can realize the efficient and accurate determination of the target object matched with the screening condition so as to facilitate different operations on the corresponding target object.

Description

Target object determining method, device, electronic equipment and storage medium

Technical Field

The present invention relates to a target object determining technology, and in particular, to a target object determining method, apparatus, electronic device, and storage medium.

Background

The identification and the excavation of the financial Key Opinion Leader (KOL) have very important significance for related application in the financial field, and the operation and the throwing of financial products and related businesses can be guided by excavating users with high financial potential and strong propagation force, so that the targeted user group can be more targeted for the information and the product release and pushing. For example, in the fields of financial investment and financing loan, the propagation effect of target customers of the product on enhanced customer groups is excavated, and the page access amount and the access user number of the product can be improved; and the financial opinion leader is determined, so that the market trend and the public opinion direction can be effectively controlled. Therefore, how to accurately and effectively identify and mine the financial KOL user group is extremely important to the information delivery technology.

Disclosure of Invention

In view of the above, embodiments of the present invention provide a method, an apparatus, an electronic device, and a storage medium for determining a target object, which can implement

The technical scheme of the embodiment of the invention is realized as follows:

the embodiment of the invention provides a target object determining method, which comprises the following steps:

Acquiring resource transaction data corresponding to different objects;

determining corresponding object coding features and behavior coding features based on the resource transaction data, and determining corresponding candidate object sets according to the object coding features and the behavior coding features;

determining a characteristic coding frequent sequence mode corresponding to the candidate object set;

weighting the characteristic code frequent sequence modes corresponding to the candidate object set, and determining a weight parameter matched with the target object;

clustering the object coding features and the behavior coding features respectively based on weight parameters matched with the target object;

and determining target objects matched with the screening conditions in the candidate object set according to the clustering results of the object coding features and the behavior coding features and the corresponding screening conditions.

The embodiment of the invention also provides a target object determining device, which comprises:

the information transmission module is used for acquiring resource transaction data corresponding to different objects;

the information processing module is used for determining corresponding object coding features and behavior coding features based on the resource transaction data, and determining corresponding candidate object sets according to the object coding features and the behavior coding features;

The information processing module is used for determining a characteristic code frequent sequence mode corresponding to the candidate object set;

the information processing module is used for weighting the characteristic code frequent sequence modes corresponding to the candidate object set and determining weight parameters matched with the target object;

the information processing module is used for respectively clustering the object coding features and the behavior coding features based on weight parameters matched with the target object;

and the information processing module is used for determining a target object matched with the screening condition in the candidate object set according to the clustering results of the object coding characteristic and the behavior coding characteristic and the corresponding screening condition.

In the above-described arrangement, the first and second embodiments,

the information transmission module is used for acquiring first resource transaction data of the different objects in a social resource exchange process;

the information transmission module is used for acquiring second resource transaction data of the different objects in a financial resource exchange process;

the information transmission module is used for establishing an association relation set of the first resource transaction data and the second resource transaction data so as to form resource transaction data corresponding to different objects.

In the above-described arrangement, the first and second embodiments,

the information processing module is used for respectively denoising the object coding features and the behavior coding features based on the resource transaction data so as to delete single-value features of corresponding dimensions;

the information processing module is used for determining abnormal values in the object coding feature and the behavior coding feature and deleting the abnormal values in the object coding feature and the behavior coding feature respectively;

the information processing module is used for respectively carrying out data filling and feature construction processing on the object coding features and the behavior coding features based on the deleted single-value features and the corresponding abnormal values of the corresponding dimensions.

In the above-described arrangement, the first and second embodiments,

the information processing module is used for determining corresponding feature types in the object coding features and the behavior coding features;

the information processing module is used for filling data through corresponding mean values when the feature type is continuous, and carrying out feature construction processing of box-division discretization on the continuous features;

and the information processing module is used for filling data through corresponding constants when the feature type is a discrete feature, and performing type coding processing on the discrete feature to realize corresponding feature construction.

In the above-described arrangement, the first and second embodiments,

the information processing module is used for determining basic object labels with different dimensions matched with the association relation set according to the association relation set of the first resource transaction data and the second resource transaction data;

and the information processing module is used for responding to the basic object labels of different dimensions matched with the association relation set, and screening the different objects to determine basic objects in the different objects.

In the above-described arrangement, the first and second embodiments,

the information processing module is used for determining the prefix of the object feature coding sequence in unit length and a corresponding projection data set based on a mode mining algorithm of prefix projection;

the information processing module is used for adding the prefix of the object feature coding sequence with the support degree higher than a minimum support degree threshold value to the data set to be projected based on the occurrence frequency of the prefix of the object feature coding sequence, and determining a corresponding frequent one-item set sequence mode;

the information processing module is used for carrying out iterative processing on the object feature coding sequence prefix based on the frequent one-item set sequence mode until the corresponding minimum support requirement parameter is reached;

and the information processing module is used for determining the feature code frequent sequence mode corresponding to the candidate object set according to the result of iterative processing on the object feature code sequence prefix.

In the above-described arrangement, the first and second embodiments,

the information processing module is used for deleting characteristic type fields which do not appear in all frequent prefixes;

the information processing module is used for adjusting the weight parameters of the feature type field according to the use environment of the target object;

the information processing module is configured to weight, based on the weight parameter of the feature type field, the feature code frequent sequence mode corresponding to the candidate object set, and determine that the field type average weight parameter of the object code feature sequence is a weight parameter matched with the target object.

In the above-described arrangement, the first and second embodiments,

the information processing module is used for weighting corresponding user characteristics based on field type average weight parameters of the object coding characteristic sequence and determining corresponding first sample characteristic vectors;

and the information processing module is used for determining a target object matched with the screening condition in the candidate object set according to the first sample feature vector and the clustering result.

In the above-described arrangement, the first and second embodiments,

The information processing module is used for carrying out weighting processing on the first sample feature vector and sample feature vectors corresponding to different objects and determining corresponding second sample feature vectors;

the information processing module is used for determining corresponding target object proportion parameters according to the first sample feature vector and the clustering result;

and the information processing module is used for determining a target object matched with the screening condition in the candidate object set based on the target object proportion parameter.

In the above-described arrangement, the first and second embodiments,

the information processing module is used for sending the object identification, the corresponding resource transaction data and the target object matched with the screening condition to the blockchain network so as to ensure that

And filling the object identifier, the corresponding resource transaction data and the target object matched with the screening condition into a new block by the node of the blockchain network, and adding the new block to the tail part of the blockchain when the new block is consistent in consensus.

In the above-described arrangement, the first and second embodiments,

the information processing module is used for receiving data synchronization requests of other nodes in the blockchain network;

responding to the data synchronization request, and verifying the authority of the other nodes;

And when the authority of the other nodes passes the verification, controlling the current node to perform data synchronization with the other nodes so as to realize that the other nodes acquire object identifications, corresponding resource transaction data and target objects matched with the screening conditions.

In the above-described arrangement, the first and second embodiments,

the information processing module is used for responding to the query request and analyzing the query request to obtain a corresponding object identifier;

acquiring authority information in a target block in a blockchain network according to the object identifier;

checking the matching property of the authority information and the object identification;

when the authority information is matched with the object identification, corresponding resource transaction data and a target object matched with the screening condition are acquired from the blockchain network;

and pushing the obtained corresponding resource transaction data and the target object matched with the screening condition to a corresponding client in response to the query request so as to enable the client to obtain the corresponding resource transaction data stored in the blockchain network and the target object matched with the screening condition.

The embodiment of the invention also provides electronic equipment, which comprises:

A memory for storing executable instructions;

and the processor is used for realizing the preface target object determining method when the executable instructions stored in the memory are run.

The embodiment of the invention also provides a computer readable storage medium which stores executable instructions which when executed by a processor realize the method for determining the target object of the preamble.

The embodiment of the invention has the following beneficial effects:

acquiring resource transaction data corresponding to different objects; determining corresponding object coding features and behavior coding features based on the resource transaction data, and determining corresponding candidate object sets according to the object coding features and the behavior coding features; determining a characteristic coding frequent sequence mode corresponding to the candidate object set; weighting the characteristic code frequent sequence modes corresponding to the candidate object set, and determining a weight parameter matched with the target object; clustering the object coding features and the behavior coding features respectively based on weight parameters matched with the target object; and determining target objects matched with the screening conditions in the candidate object set according to the clustering results of the object coding features and the behavior coding features and the corresponding screening conditions, thereby realizing efficient and accurate determination of the target objects matched with the screening conditions in different objects so as to facilitate different operations on the corresponding target objects.

Drawings

FIG. 1 is a schematic view of a usage environment of a target object determining method according to an embodiment of the present invention;

fig. 2 is a schematic diagram of a composition structure of a target object determining apparatus according to an embodiment of the present invention;

FIG. 3 is a schematic flow chart of an alternative method for determining a target object according to an embodiment of the present invention;

FIG. 4A is a schematic flow chart of an alternative method for determining a target object according to an embodiment of the present invention;

fig. 4B is a schematic diagram of front end display of a target object determining method according to an embodiment of the present invention;

fig. 5 is a schematic architecture diagram of a target object determining apparatus 100 according to an embodiment of the present invention;

FIG. 6 is a block chain diagram of a block chain network 200 according to an embodiment of the present invention;

FIG. 7 is a functional architecture diagram of a blockchain network 200 according to an embodiment of the present invention;

FIG. 8 is a schematic view of a usage environment of a target object determining method according to an embodiment of the present invention;

FIG. 9 is a schematic flow chart of an alternative method for determining a target object according to an embodiment of the present invention;

FIG. 10 is a schematic flow chart of an alternative method for determining a target object according to an embodiment of the present invention;

fig. 11 is a schematic flowchart of an alternative method for determining a target object according to an embodiment of the present invention.

Detailed Description

The present invention will be further described in detail with reference to the accompanying drawings, for the purpose of making the objects, technical solutions and advantages of the present invention more apparent, and the described embodiments should not be construed as limiting the present invention, and all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present invention.

In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with one another without conflict.

Before describing embodiments of the present invention in further detail, the terms and terminology involved in the embodiments of the present invention will be described, and the terms and terminology involved in the embodiments of the present invention will be used in the following explanation.

1) Transactions (transactions), which are equivalent to computer terms "transactions," include operations that need to be submitted to a blockchain network for execution, and do not refer solely to transactions in a business context, which embodiments of the present invention follow in view of the terminology "transactions" being colloquially used in blockchain technology.

For example, a deployment (Deploy) transaction is used to install a specified smart contract to a node in a blockchain network and is ready to be invoked; call (Invoke) transactions are used to append records of transactions in the blockchain by invoking smart contracts and to operate on the blockchain's state database, including update operations (including adding, deleting, and modifying key-value pairs in the state database) and query operations (i.e., querying key-value pairs in the state database).

2) A blockchain (Block chain) is a storage structure of encrypted, chained transactions formed by blocks (blocks).

For example, the header of each chunk may include both the hash values of all transactions in the chunk and the hash values of all transactions in the previous chunk, thereby enabling tamper-and anti-counterfeiting of transactions in the chunk based on the hash values; the newly generated transactions, after being filled into the block and passing through the consensus of the nodes in the blockchain network, are appended to the tail of the blockchain to form a chain growth.

3) A blockchain network (Block chain Network) incorporates new blocks into a set of nodes of the blockchain by way of consensus.

4) Ledger (Ledger), a generic term for blockchains (also known as Ledger data) and state databases that are synchronized with blockchains.

Wherein the blockchain records transactions in the form of files in a file system; the state database records transactions in the blockchain in the form of different types of Key (Key) Value pairs for supporting quick queries for transactions in the blockchain.

5) Smart contacts (Smart contacts), also known as Chain codes (Chain codes) or application codes, are deployed in the nodes of the blockchain network, which execute Smart Contracts invoked in received transactions to update or query the key values of the ledger database for data.

6) Consensus (Consensus), a process in a blockchain network for agreeing on transactions in blocks among the involved nodes, the agreed blocks will be appended to the tail of the blockchain, and the mechanisms implementing Consensus include Proof of Work (Po W, proof of Work), proof of equity (PoS, proof of status), proof of stock authority (D PoS, proof of-status), proof of elapsed time (Po ET, proof of Elapsed Time), and the like.

7) In response to a condition or state that is used to represent the condition or state upon which the performed operation depends, the performed operation or operations may be in real-time or with a set delay when the condition or state upon which it depends is satisfied; without being specifically described, there is no limitation in the execution sequence of the plurality of operations performed.

8) Terminals, including but not limited to: the system comprises a common terminal and a special terminal, wherein the common terminal is in long connection and/or short connection with a sending channel, and the special terminal is in long connection with the sending channel.

9) A client, a carrier in a terminal that implements a specific function, for example, a mobile client (APP), is a carrier of a specific function in a mobile terminal, for example, a function of performing payment consumption or a function of purchasing a financial product.

10 Pattern mining of Prefix projections, (PrefixSpan, prefix-Projected Pattern Growth), whose goal is to mine out frequent sequences meeting minimum support, which mine sequence patterns starting with a Prefix of length 1, search the corresponding projection database for frequent sequences corresponding to prefixes of length 1, and then recursively mine frequent sequences corresponding to prefixes of length 2. . . And so on, recursion until longer prefix excavations cannot be mined.

11 KOL): the key opinion leader (Key Opinion Leader, KOL for short) is a marketing concept, generally defined as: more and more accurate product information is possessed, and is accepted or trusted by the relevant group, and has greater influence on the purchasing behavior of the group. The financial KOL is a user with higher value in the financial field, especially financial investment and transaction behaviors, and the mining of the part of users has greater significance for popularization, operation and sales of financial products.

Fig. 1 is a schematic view of a usage scenario of a target object determining method provided by an embodiment of the present invention, referring to fig. 1, a terminal (including a terminal 10-1 and a terminal 10-2) is provided with a client capable of displaying software of corresponding resource transaction data, such as a client or a plug-in for performing financial activity on a virtual resource or entity resource or paying through a virtual resource, a user may obtain and display resource transaction data through the corresponding client, and trigger a corresponding target object determining process (such as a process of micro-letter financial payment or a process of purchasing an article in a micro-letter) in a virtual resource change process; the terminal is connected to the server 200 through the network 300, and the network 300 may be a wide area network or a local area network, or a combination of the two, and uses a wireless link to implement data transmission.

As an example, the server 200 is configured to arrange the target object determining apparatus to implement the target object determining method provided by the present invention, so as to obtain the resource transaction data corresponding to different objects; determining corresponding object coding features and behavior coding features based on the resource transaction data, and determining corresponding candidate object sets according to the object coding features and the behavior coding features; determining a characteristic coding frequent sequence mode corresponding to the candidate object set; weighting the characteristic code frequent sequence modes corresponding to the candidate object set, and determining a weight parameter matched with the target object; clustering the object coding features and the behavior coding features respectively based on weight parameters matched with the target object; and determining target objects matched with the screening conditions in the candidate object set according to the clustering results of the object coding features and the behavior coding features and the corresponding screening conditions.

Of course, the target object determining device provided by the invention can be applied to a virtual resource to perform financial activities or a use environment of information interaction through virtual resource payment environments (including but not limited to various types of virtual resource change environments) or social software, and resource transaction data of different data sources are usually processed in the process of performing financial activities or through virtual resource payment by the virtual resource, and finally the resource transaction data corresponding to the target object query request is presented on a User Interface (UI). The resource transaction data (such as virtual gift or non-physical currency such as virtual game currency) obtained by the user in the current display interface may also be invoked by other applications.

Of course, when the resource transaction data is determined by the target object determining device, the method specifically includes: acquiring resource transaction data corresponding to different objects; determining corresponding object coding features and behavior coding features based on the resource transaction data, and determining corresponding candidate object sets according to the object coding features and the behavior coding features; determining a characteristic coding frequent sequence mode corresponding to the candidate object set; weighting the characteristic code frequent sequence modes corresponding to the candidate object set, and determining a weight parameter matched with the target object; clustering the object coding features and the behavior coding features respectively based on weight parameters matched with the target object; and determining target objects matched with the screening conditions in the candidate object set according to the clustering results of the object coding features and the behavior coding features and the corresponding screening conditions.

The following describes in detail the structure of the target object determining apparatus according to the embodiment of the present invention, and the target object determining apparatus may be implemented in various forms, such as a dedicated terminal with a processing function of the target object determining apparatus, or may be a server provided with the processing function of the target object determining apparatus, for example, the server 200 in fig. 1. Fig. 2 is a schematic diagram of a composition structure of a target object determining apparatus according to an embodiment of the present invention, and it is understood that fig. 2 only shows an exemplary structure of the target object determining apparatus, but not all the structures, and that part or all of the structures shown in fig. 2 may be implemented as needed.

The target object determining device provided by the embodiment of the invention comprises the following components: at least one processor 201, a memory 202, a user interface 203, and at least one network interface 204. The various components in the target object determination apparatus are coupled together by a bus system 205. It is understood that the bus system 205 is used to enable connected communications between these components. The bus system 205 includes a power bus, a control bus, and a status signal bus in addition to the data bus. But for clarity of illustration the various buses are labeled as bus system 205 in fig. 2.

The user interface 203 may include, among other things, a display, keyboard, mouse, trackball, click wheel, keys, buttons, touch pad, or touch screen, etc.

It will be appreciated that the memory 202 may be either volatile memory or nonvolatile memory, and may include both volatile and nonvolatile memory. The memory 202 in embodiments of the present invention is capable of storing data to support operation of the terminal (e.g., 10-1). Examples of such data include: any computer program, such as an operating system and application programs, for operation on the terminal (e.g., 10-1). The operating system includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks. The application may comprise various applications.

In some embodiments, the object determining apparatus provided in the embodiments of the present invention may be implemented by combining software and hardware, and by way of example, the object determining apparatus provided in the embodiments of the present invention may be a processor in the form of a hardware decoding processor, which is programmed to perform the object determining method provided in the embodiments of the present invention. For example, a processor in the form of a hardware decoding processor may employ one or more application specific integrated circuits (ASICs, application Specific Integrated Circuit), DSPs, programmable logic devices (PLDs, programmable Logic Device), complex programmable logic devices (CPLDs, co mplex Programmable Logic Device), field programmable gate arrays (FPGAs, field-Progra mmable Gate Array), or other electronic components.

As an example of implementation of the object determining apparatus provided by the embodiment of the present invention by combining software and hardware, the object determining apparatus provided by the embodiment of the present invention may be directly embodied as a combination of software modules executed by the processor 201, the software modules may be located in a storage medium, the storage medium is located in the memory 202, and the processor 201 reads executable instructions included in the software modules in the memory 202, and performs the object determining method provided by the embodiment of the present invention in combination with necessary hardware (including, for example, the processor 201 and other components connected to the bus 205).

By way of example, the processor 201 may be an integrated circuit chip having signal processing capabilities such as a general purpose processor, such as a microprocessor or any conventional processor, a digital signal processor (DSP, digital Signal Processor), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like.

As an example of implementation of the object determining apparatus provided by the embodiment of the present invention by hardware, the apparatus provided by the embodiment of the present invention may be implemented directly by the processor 201 in the form of a hardware decoding processor, for example, by one or more application specific integrated circuits (ASIC, application Specific Integr ated Circuit), DSPs, programmable logic devices (PLD, programmable Logic Device), complex programmable logic devices (CPLD, complex Programmable Logic Device), field programmable gate arrays (FPGA, field-Programmable Gate Array) or other electronic components.

The memory 202 in embodiments of the present invention is used to store various types of data to support the operation of the target object determining apparatus. Examples of such data include: any executable instructions, such as executable instructions, for operation on the target object determining apparatus, a program implementing the method of determining from a target object of an embodiment of the present invention may be contained in the executable instructions.

In other embodiments, the object determining apparatus provided in the embodiments of the present invention may be implemented in software, and fig. 2 shows the object determining apparatus stored in the memory 202, which may be in the form of a program, a plug-in, or the like, and includes a series of modules, and as an example of the program stored in the memory 202, may include the object determining apparatus, where the object determining apparatus includes the following software module information transmission module 2081 and information processing module 2082. When the software modules in the target object determining apparatus are read into the RAM by the processor 201 and executed, the target object determining method provided by the embodiment of the present invention is implemented, where the functions of each software module in the target object determining apparatus include:

an information transmission module 2081, configured to obtain resource transaction data corresponding to different objects;

An information processing module 2082, configured to determine corresponding object coding features and behavior coding features based on the resource transaction data, and determine corresponding candidate object sets according to the object coding features and behavior coding features;

the information processing module 2082 is configured to determine a feature code frequent sequence mode corresponding to the candidate object set;

the information processing module 2082 is configured to weight the feature code frequent sequence patterns corresponding to the candidate object set, and determine a weight parameter matched with the target object;

the information processing module 2082 is configured to perform clustering processing on the object coding feature and the behavior coding feature based on weight parameters matched with the target object;

the information processing module 2082 is configured to determine, according to the clustering results of the object coding features and the behavior coding features, and the corresponding screening conditions, a target object in the candidate object set that is matched with the screening conditions.

The method for determining a target object according to the embodiment of the present invention is described with reference to the target object determining apparatus shown in fig. 2, and referring to fig. 3, fig. 3 is a schematic flowchart illustrating an alternative method for determining a target object according to the embodiment of the present invention, it may be understood that the steps shown in fig. 3 may be performed by various electronic devices running the target object determining apparatus, for example, may be a server or a server cluster with the target object determining apparatus, where a dedicated terminal with the target object determining apparatus may be packaged in the server shown in fig. 1 to execute corresponding software modules in the target object determining apparatus shown in fig. 2. The following is a description of the steps shown in fig. 3.

Step 301: the target object determining means acquires resource transaction data corresponding to different objects.

In some embodiments of the present invention, the acquisition of resource transaction data corresponding to different objects may be achieved by:

acquiring first resource transaction data of different objects in a social resource exchange process; acquiring second resource transaction data of the different objects in a financial resource exchange process; and establishing an association relation set of the first resource transaction data and the second resource transaction data to form resource transaction data corresponding to different objects.

In some embodiments of the invention, the resource transaction may be a transaction between physical resources (of different currencies), a transaction between virtual resources (electronic money or points, tokens), or a transaction between a physical resource and a virtual resource, for example: when the virtual resource is processed into the corresponding payment activity, the resources in the account corresponding to the target user and the resources required to be consumed for participating in the payment activity can have different expression forms, and the specific expression forms of the virtual resource are not limited in some embodiments of the present invention, and optionally, the virtual resource can be real funds, real financial products, virtual copper money, virtual precious stones, user points, vouchers, virtual shoe-shaped elements, virtual silver tickets and the like. The virtual resource in the account corresponding to the target user may be one expression form or may include multiple expression forms, for example, the virtual resource in the account corresponding to the target user may be in the form of unified real currency (single currency or mixed currency), and further, the virtual resource in the account corresponding to the target user may include multiple expression forms such as a virtual shoe-shaped gold ingot, a virtual silver ticket, a virtual precious stone, and the like. In some embodiments of the present invention, in order to conveniently represent the total number of virtual resources in the account corresponding to the target user, the virtual resources in the account corresponding to the target user are represented in one expression form, and optionally, virtual resources in other expression forms and virtual resources in expression forms in the account corresponding to the target user may be mutually converted.

Step 302: the target object determining device determines corresponding object coding features and behavior coding features based on the resource transaction data, and determines corresponding candidate object sets according to the object coding features and the behavior coding features.

In some embodiments of the invention, determining the respective object coding features and behavior coding features based on the resource transaction data may be achieved by:

based on the resource transaction data, respectively denoising the object coding features and the behavior coding features to delete single-value features of corresponding dimensions; determining abnormal values in the object coding feature and the behavior coding feature, and deleting the abnormal values in the object coding feature and the behavior coding feature respectively; and respectively carrying out data filling and feature construction processing on the object coding features and the behavior coding features based on the deleted single-value features and the corresponding abnormal values of the corresponding dimensions.

In some embodiments of the present invention, the data filling and feature construction processing of the object-coded features and behavior-coded features, respectively, based on the deleted single-value features and corresponding outliers of the corresponding dimensions may be implemented by:

Determining corresponding feature types in the object coding features and behavior coding features; when the feature type is continuous, filling data through a corresponding mean value, and carrying out feature construction processing of box-division discretization on the continuous feature; and when the feature type is a discrete feature, filling data through a corresponding constant, and performing type coding processing on the discrete feature to realize corresponding feature construction.

In some embodiments of the present invention, the target object determining method further includes:

according to the association relation set of the first resource transaction data and the second resource transaction data, determining basic object labels with different dimensions matched with the association relation set; and responding to basic object labels of different dimensions matched with the association relation set, and screening the different objects to determine basic objects in the different objects, so that the screening speed of an object sample pool where different target objects are positioned can be improved, the efficiency of determining corresponding target samples is improved, and information is pushed to target objects matched with corresponding screening conditions more quickly.

Step 303: the target object determining device determines the characteristic code frequent sequence mode corresponding to the candidate object set.

Continuing to describe the target object determining method provided by the embodiment of the present invention with reference to the target object determining apparatus shown in fig. 2, referring to fig. 4A, fig. 4A is an alternative flowchart of the target object determining method provided by the embodiment of the present invention, it will be understood that the steps shown in fig. 4A may be performed by various electronic devices running the target object determining apparatus, for example, a server or a server cluster with the target object determining apparatus, where a dedicated terminal with the target object determining apparatus may be packaged in the server shown in fig. 1 to execute the corresponding software module in the target object determining apparatus shown in fig. 2. The following is a description of the steps shown in fig. 4A.

Step 401: determining an object feature coding sequence prefix and a corresponding projection data set in unit length based on a mode mining algorithm of prefix projection;

step 402: based on the occurrence frequency of the object feature coding sequence prefix, adding the object feature coding sequence prefix with the support degree higher than the minimum support degree threshold value to the data set to be projected, and determining a corresponding frequent one-item set sequence mode;

step 403: performing iterative processing on the object feature coding sequence prefix based on the frequent one-item set sequence mode until the corresponding minimum support requirement parameter is reached;

Step 404: and determining the feature code frequent sequence mode corresponding to the candidate object set according to the result of iterative processing on the object feature code sequence prefix.

In this process, reference is made to fig. 4B, where fig. 4B is a schematic front-end display diagram of a target object determining method according to an embodiment of the present invention. The method comprises the steps that in platforms such as change communication of social software, users can conveniently and rapidly purchase financial products to obtain benefits and pay daily consumption, recognition and excavation of financial Key Opinion Leaders (KOL) are of great importance to related applications in the financial field facing different user groups, and through excavation of users with high financial potential and strong propagation force, operation and release of financial products and related services can be guided, targeted user groups are promoted more specifically, and the effect of half effort is achieved. In the fields of financial investment and financing loan, as shown in the preamble of fig. 8, the mining of the propagation effect of the target clients of the product has remarkable effects on enhancing the client group, and improving the PV (page access quantity) and UV (access user quantity) of the product; in financial information and forum, the development and guidance of the financial opinion leader can effectively bring about market trend and public opinion direction. Therefore, the user group mining the financial KOL can be accurately and effectively identified, and the method plays a vital role in investment financial management and financial events.

Step 304: and the target object determining device weights the characteristic code frequent sequence modes corresponding to the candidate object set and determines weight parameters matched with the target object.

In some embodiments of the present invention, weighting the feature code frequent sequence patterns corresponding to the candidate object set, and determining the weight parameter matched with the target object may be implemented by the following ways:

deleting feature type fields which do not appear in all frequent prefixes; according to the use environment of the target object, adjusting the weight parameter of the characteristic type field; and weighting the feature code frequent sequence mode corresponding to the candidate object set based on the weight parameter of the feature type field, and determining the field type average weight parameter of the object code feature sequence as the weight parameter matched with the target object.

Step 305: the target object determining device respectively performs clustering processing on the object coding features and the behavior coding features based on weight parameters matched with the target object.

Step 306: and the target object determining device determines a target object matched with the screening condition in the candidate object set according to the clustering results of the object coding characteristic and the behavior coding characteristic and the corresponding screening condition.

In some embodiments of the present invention, determining, according to the clustering results of the object coding features and the behavior coding features and the corresponding screening conditions, the target object in the candidate object set that matches the screening conditions may be implemented in the following manner:

based on the field type average weight parameter of the object coding feature sequence, weighting corresponding user features to determine corresponding first sample feature vectors; and determining target objects matched with the screening conditions in the candidate object set according to the first sample feature vector and the clustering result.

In the following, description will be given by taking as an example determining, in use environments of different screening conditions, a target object in a candidate object set, where the target object is matched with a corresponding screening condition, where relevant data may be generated in fields of social products, financial products, and the like in a target user activity, and features may be constructed from basic attribute dimensions and behavior dimensions, and may include the following information: different screening conditions such as screening a user of TOP N before the financial transaction number (N is selected according to the actual sample size, and can be set to be the actual sample size multiplied by 1/1000) as a corresponding financial KOL user, namely the target object, and screening a user of TOP N before the transfer and the transfer number as a corresponding financial KOL user as the target object can be set through the data.

based on the field type average weight parameter of the object coding feature sequence, weighting corresponding user features to determine corresponding first sample feature vectors; weighting the first sample feature vector and the sample feature vectors corresponding to the different objects to determine corresponding second sample feature vectors; determining corresponding target object proportion parameters according to the first sample feature vector and the clustering result; and determining the target object matched with the screening condition in the candidate object set based on the target object proportion parameter.

In combination with the foregoing embodiment, different screening conditions may be set by these data, for example, the user of the TOP 100 before screening the number of financial transactions in the financial information sample pool with the sample pool capacity of 10000 users, so that the target object of the TOP 100 screened has more and more accurate product information for the corresponding financial KOL target object, is accepted or trusted by the social group in which the target object is located, and has a larger influence on the purchasing behavior of the group. Therefore, different information can be pushed to the target objects corresponding to different screening conditions, so that the accuracy of information pushing is improved.

In some embodiments of the present invention, in order to store corresponding data through a blockchain network, the target object determining method provided by the present invention further includes:

and sending the object identification, the corresponding resource transaction data and the target object matched with the screening condition to a blockchain network so that nodes of the blockchain network fill the object identification, the corresponding resource transaction data and the target object matched with the screening condition into a new block, and when the new block is consistent with the consensus, adding the new block to the tail part of the blockchain. The embodiment of the invention can be realized by combining Cloud technology, wherein Cloud technology (Cloud technology) refers to a hosting technology for integrating hardware, software, network and other series resources in a wide area network or a local area network to realize calculation, storage, processing and sharing of data, and can also be understood as the general term of network technology, information technology, integration technology, management platform technology, application technology and the like applied based on a Cloud computing business model. Background services of technical network systems require a large amount of computing and storage resources, such as video websites, picture websites and more portal websites, so cloud technologies need to be supported by cloud computing.

It should be noted that cloud computing is a computing mode, which distributes computing tasks on a resource pool formed by a large number of computers, so that various application systems can acquire computing power, storage space and information service as required. The network that provides the resources is referred to as the "cloud". Resources in the cloud are infinitely expandable in the sense of users, and can be acquired at any time, used as needed, expanded at any time and paid for use as needed. As a basic capability provider of cloud computing, a cloud computing resource pool platform, referred to as a cloud platform for short, is generally called infrastructure as a service (IaaS, infrastructure as a Service), and multiple types of virtual resources are deployed in the resource pool for external clients to select for use. The cloud computing resource pool mainly comprises: computing devices (which may be virtualized machines, including operating systems), storage devices, and network devices.

As shown in fig. 1, the method for determining the target object provided by the embodiment of the present invention may be implemented by a corresponding cloud device, for example: the terminals (including the terminal 10-1 and the terminal 10-2) are connected to the server 200 located at the cloud through the network 300, and the network 300 may be a wide area network or a local area network, or a combination of the two. It should be noted that the server 200 may be a physical device or a virtualized device.

In some embodiments of the present invention, the method for determining a target object provided by the present invention further includes:

receiving data synchronization requests of other nodes in the blockchain network;

Further, in some embodiments of the present invention, in response to a query request, the query request is parsed to obtain a corresponding object identification;

Referring to fig. 5, fig. 5 is a schematic architecture diagram of a target object determining apparatus 100 according to an embodiment of the present invention, including a blockchain network 200 (illustrating a consensus node 210-1 to a consensus node 210-3), an authentication center 300, a service body 400, and a service body 500, respectively, as described below.

The type of blockchain network 200 is flexible and diverse, and may be any of public, private, or federated chains, for example. Taking public chains as an example, any electronic device of a business entity, such as a user terminal and a server, can access the blockchain network 200 without authorization; taking the alliance chain as an example, an electronic device (e.g., a terminal/server) under the jurisdiction of the service body after being authorized can access the blockchain network 200, and then becomes a client node in the blockchain network 200.

In some embodiments, the client node may be implemented by default or selectively (e.g., depending on the specific business needs of the business entity) as a watcher of the blockchain network 200 alone, i.e., to provide functionality to support the business entity to initiate transactions (e.g., for storing data in the uplink or querying data on the link), for the functionality of the consensus node 210 of the blockchain network 200, such as ordering functionality, consensus services, ledger functionality, etc. Thus, the data and service processing logic of the service body can be migrated to the blockchain network 200 to the greatest extent, and the credibility and traceability of the data and service processing process are realized through the blockchain network 200.

The consensus nodes in blockchain network 200 receive transactions submitted from client nodes of different business principals (e.g., business principal 400 and business principal 500 shown in fig. 1), such as client node 410 attributed to business principal 400 and client node 510 attributed to system 500 of electronic devices shown in fig. 1, execute the transactions to update or query the ledger, and various intermediate or final results of executing the transactions may be displayed back in the client nodes of the business principal.

For example, the client nodes 410/510 may subscribe to events of interest in the blockchain network 200, such as transactions occurring in a particular organization/channel in the blockchain network 200, with corresponding transaction notifications being pushed to the client nodes 410/510 by the consensus node 210, thereby triggering corresponding business logic in the client nodes 410/510.

An exemplary application of the blockchain network is described below taking as an example the access of multiple business entities to the blockchain network to achieve management of the target object determination.

Referring to fig. 5, a plurality of service principals involved in the management link, such as service principal 400 may be a target object determining device based on artificial intelligence, service principal 500 may be a display system with a target object determining function, register and obtain respective digital certificates from authentication center 300, the digital certificates include a public key of the service principal, and a digital signature signed by authentication center 300 for the public key and identity information of the service principal, and the digital signature is used to be attached to a transaction together with the digital signature of the service principal for the transaction, and sent to a blockchain network for the blockchain network to take out the digital certificate and signature from the transaction, verify the reliability (i.e. whether not it has not been tampered) of the message and the identity information of the service principal sending the message, and the blockchain network verifies according to the identity, for example, whether or not the authority to initiate the transaction is provided. A client operated by an electronic device (e.g., a terminal or a server) under the control of a service entity may request access from the blockchain network 200 to become a client node.

The client node 410 of the service body 400 is configured to obtain resource transaction data corresponding to different objects; determining the level information of the different objects according to the resource transaction data, and determining the basic objects in the different objects according to the level information; determining a difference feature vector matched with the different objects according to the resource transaction data; determining an association relationship network between the different objects based on the difference feature vectors matched with the different objects; determining a clustering result of an association relation network between different objects in response to the basic object; and determining target objects matched with the basic objects in the different objects according to the clustering result and the corresponding level information of the association relation network between the different objects, and sending object identifiers, corresponding resource transaction data and the target objects matched with the screening conditions to the blockchain network 200.

Wherein, the object identifier, the corresponding resource transaction data and the target object matched with the filtering condition are sent to the blockchain network 200, business logic may be set in advance in the client node 410, when the corresponding target object determination result is formed, the client node 410 automatically sends the object identifier, the corresponding resource transaction data and the target object matched with the filtering condition to the blockchain network 200, or a business person of the business body 400 logs in the client node 410, packages the object identifier, the corresponding resource transaction data and the target object matched with the filtering condition manually, and sends the object identifier, the corresponding resource transaction data and the target object matched with the filtering condition to the blockchain network 200. At the time of transmission, the client node 410 generates a transaction corresponding to the update operation according to the object identifier, the corresponding resource transaction data and the target object matched with the filtering condition, specifies the intelligent contract required to be invoked for implementing the update operation and the parameters transferred to the intelligent contract in the transaction, and the transaction also carries the digital certificate of the client node 410, the signed digital signature (for example, the digest of the transaction is encrypted by using the private key in the digital certificate of the client node 410) and broadcasts the transaction to the consensus node 210 in the blockchain network 200.

When a transaction is received in the consensus node 210 in the blockchain network 200, a digital certificate and a digital signature carried by the transaction are verified, after the verification is successful, whether the transaction main body 400 has transaction permission is confirmed according to the identity of the transaction main body 400 carried in the transaction, and any one verification judgment of the digital signature and the permission verification can cause the transaction to fail. Signing node 210's own digital signature after verification is successful (e.g., the digest of the transaction is encrypted using node 210-1's private key) and continues to broadcast in blockchain network 200.

After receiving a transaction that is successfully validated, the consensus node 210 in the blockchain network 200 populates the new block with the transaction and broadcasts the transaction. When a new block is broadcast by the consensus node 210 in the blockchain network 200, a consensus process is performed on the new block, if the consensus is successful, the new block is added to the tail of the blockchain stored in the new block, and the state database is updated according to the result of the transaction, so as to execute the transaction in the new block: for submitting and updating the transaction of the object identification, the corresponding resource transaction data and the target object matched with the screening condition, a key value pair comprising the object identification, the corresponding resource transaction data and the target object matched with the screening condition is added in a state database.

The business person of the business entity 500 logs in the client node 510, inputs the target object determination result or the target object query request, the client node 510 generates a transaction corresponding to the update operation/query operation according to the target object determination result or the target object query request, specifies an intelligent contract required to be invoked for implementing the update operation/query operation and parameters transferred to the intelligent contract in the transaction, the transaction further carries a digital certificate of the client node 510, a signed digital signature (for example, a digest of the transaction is encrypted using a private key in the digital certificate of the client node 510), and broadcasts the transaction to the consensus node 210 in the blockchain network 200.

After the transaction is verified, the block is filled and the consensus is consistent, the filled new block is added to the tail of the block chain stored by the block chain network 200, the state database is updated according to the result of the transaction, and the transaction in the new block is executed: updating a key value pair corresponding to a target object determination result in a state database according to a manual identification result for updating a transaction of a target object matched with the screening condition, wherein the target object identification and the corresponding resource transaction data are updated; for the submitted transaction for inquiring a certain target object determination result, inquiring a key value pair corresponding to the target object determination result from the state database, and returning a transaction result.

It should be noted that, in fig. 5, a process of directly linking the object identifier, the corresponding resource transaction data, and the target object matched with the filtering condition is exemplarily shown, but in other embodiments, for a case where the data size of the target object determination result is large, the client node 410 may pair up the hash of the target object determination result and the hash of the corresponding target object determination result, and store the original target object determination result and the corresponding target object determination result in the distributed file system or the database. After the client node 510 obtains the target object determination result and the corresponding target object determination result from the distributed file system or the database, it may perform verification in combination with the corresponding hash in the blockchain network 200, thereby reducing the workload of the uplink operation.

As an example of a blockchain, referring to fig. 6, fig. 6 is a schematic diagram of a blockchain structure in a blockchain network 200 according to an embodiment of the present invention, where a header of each block may include hash values of all transactions in the block, and also include hash values of all transactions in a previous block, and a record of a newly generated transaction is filled into the block and after passing through a node in the blockchain network, is appended to a tail of the blockchain to form a chain growth, and a chain structure based on the hash values between the blocks ensures tamper resistance and forgery resistance of transactions in the block.

Referring to fig. 7, fig. 7 is a schematic diagram of a functional architecture of a blockchain network 200 according to an embodiment of the present invention, including an application layer 201, a consensus layer 202, a network layer 203, a data layer 204, and a resource layer 205, which are described below.

The resource layer 205 encapsulates computing resources, storage resources, and communication resources that implement the various nodes 210 in the blockchain network 200.

Data layer 204 encapsulates various data structures that implement the ledger, including blockchains implemented with files in a file system, a state database of key values, and presence certificates (e.g., hash trees of transactions in blocks).

The network layer 203 encapsulates the functions of Point-to-Point (P2P) network protocols, data propagation mechanisms and data verification mechanisms, access authentication mechanisms, and service body identity management.

Wherein the P2P network protocol enables communication between nodes 210 in the blockchain network 200, a data propagation mechanism ensures propagation of transactions in the blockchain network 200, and a data verification mechanism is used to enable reliability of data transmission between nodes 210 based on cryptography methods (e.g., digital certificates, digital signatures, public/private key pairs); the access authentication mechanism is used for authenticating the identity of the service entity joining the blockchain network 200 according to the actual service scene, and giving the authority of the service entity to access the blockchain network 200 when the authentication is passed; the service principal identity management is used to store the identity of the service principal that is allowed to access the blockchain network 200, as well as the rights (e.g., the type of transaction that can be initiated).

The consensus layer 202 encapsulates the functionality of the mechanism by which nodes 210 in the blockchain network 200 agree on blocks (i.e., consensus mechanism), transaction management, and ledger management. The consensus mechanism comprises consensus algorithms such as POS, POW, DP OS and the like, and supports the pluggable of the consensus algorithm.

The transaction management is used for verifying the digital signature carried in the transaction received by the node 210, verifying the identity information of the service entity, and judging and confirming whether the service entity has authority to conduct the transaction according to the identity information (reading the related information from the identity management of the service entity); for the business entity that obtains authorization to access the blockchain network 200, all possess the digital certificates issued by the authentication center, and the business entity signs the submitted transaction with the private key in its own digital certificate, thereby declaring its legal identity.

Ledger management is used to maintain blockchains and state databases. For the block with consensus, adding to the tail of the block chain; executing the transaction in the block with consensus, updating the key value pairs in the state database when the transaction comprises an update operation, querying the key value pairs in the state database when the transaction comprises a query operation, and returning a query result to the client node of the business entity. Supporting query operations for multiple dimensions of a state database, comprising: querying the block according to the block vector number (e.g., hash value of the transaction); inquiring the block according to the block hash value; inquiring the block according to the transaction vector number; inquiring the transaction according to the transaction vector number; inquiring account data of the service body according to the account (vector number) of the service body; the blockchains in the channel are queried according to the channel name.

The application layer 201 encapsulates various services that the blockchain network can implement, including tracing, certification and verification of transactions, etc.

The method for determining a target object provided by the present invention is described below by taking a financial Key Opinion Leader (KOL) in determining financial transaction information as an example, wherein fig. 8 is a schematic view of a use environment of the method for determining a target object according to an embodiment of the present invention; referring to fig. 8, the terminals (including the terminal 10-1 and the terminal 10-2) are provided with corresponding clients capable of executing different functions, wherein the clients browse by acquiring different fund information from corresponding servers 200 through a network 300 for the terminals (including the terminal 10-1 and the terminal 10-2), the terminals are connected with the servers 200 through the network 300, the network 300 can be a wide area network or a local area network or a combination of the wide area network and the local area network, and the wireless links are used for realizing data transmission, the types of resource allocation processes of funds and the like acquired from the corresponding servers 200 through the network 300 by the terminals (including the terminal 10-1 and the terminal 10-2) can be the same or different, with the development of internet finance, the users can conveniently and rapidly purchase financial products on platforms such as change money, and are used for daily consumption payment, the identification and the excavation of Key Opinion (KOL) have very important significance for related applications in the financial field, and the financial group can be guided by excavating users with high potential and high transmission capability, and the related financial group can be more effective and the popularization and service can be realized by the users with a higher popularization effect on related financial group. In the fields of financial investment and financing loan, as shown in the preamble of fig. 8, the mining of the propagation effect of the target clients of the product has remarkable effects on enhancing the client group, and improving the PV (page access quantity) and UV (access user quantity) of the product; in financial information and forum, the development and guidance of the financial opinion leader can effectively bring about market trend and public opinion direction. Therefore, the user group mining the financial KOL can be accurately and effectively identified, and the method plays a vital role in investment financial management and financial events.

In the conventional art, the manner of identifying and mining the financial KOL user population includes:

1) The method comprises the steps of constructing a user social relation network based on a rule or a neural network and the like, firstly obtaining social data of a target user group, such as a red packet and a transfer relation, then designating a user affinity calculation rule or constructing a deep neural network, predicting and quantifying the association degree of other users and seed users, and extracting other users matched with the conditions according to the association degree as target users.

2) And acquiring historical data of all users through a plurality of dimension features based on the classification model, training and establishing a plurality of mining models for user prediction, determining a target mining model based on a plurality of classification regression models, and determining target KOL users from all users through the target mining model.

However, the defects of the conventional method mainly include:

1. based on classification or regression models, network relations among the users are ignored, namely, group effects exist among the KOL users, and the mining of the network relations of the user groups has important significance for the mining of the deep KOL users.

2. The method for constructing the user social relation network based on the rules and the like is high in interpretability, but the rules are required to be reassigned for mining different target groups, so that the universality is low, and the generalization performance of the model is low.

3. The method for constructing the user relationship chain based on the neural network needs to construct a huge network and a complex node relationship, and the training process of the neural network model is very time-consuming along with the increase of the number of nodes and node connection lines.

In order to solve the above-mentioned drawbacks, referring to fig. 9, fig. 9 is an optional flowchart of a target object determining method according to an embodiment of the present invention, which specifically includes the following steps:

step 901: and constructing user coding features and behavior coding features, and constructing a KOL user sample library.

The related data of the user in social products, financial products and the like are obtained, and features are constructed from basic attribute dimensions and behavior dimensions, and the information can be as follows: position, age, sex, education status (academic), number of times of sending/receiving red packets in the last N days (e.g. 7 days, 30 days, 90 days, etc.), number of times of transferring and being transferred in the last N days (e.g. 7 days, 30 days, 90 days, etc.), number of information receiving and sending people in the last N days (e.g. 7 days, 30 days, 90 days, etc.), number of transaction strokes, amount of transaction, historical purchase and redemption of financial products, amount of money, last purchase/redemption time, last interaction/exchange time, number of times of posting social product comment messages, ratio of sending/receiving information, ratio of attention to attention, number of times of interaction, number of times of invited answers to questions, etc.

With continued reference to fig. 10, fig. 10 is an optional flowchart of a target object determining method according to an embodiment of the present invention, where data preprocessing is performed and user features and behavior features are constructed in the following manner: the discrete type characteristic is subjected to type coding, the continuous type characteristic is subjected to box separation operation, and the processing steps specifically comprise:

step 1001: and discarding the feature with excessive missing values, wherein N can be set to be 0.4, filtering the feature if the number of missing data of a certain feature exceeds the threshold value, and deleting the single-value feature.

Step 1002: and performing outlier processing, namely discarding the characteristics with the characteristic values exceeding the corresponding thresholds according to the characteristic distribution.

For example, alternatively, outliers that are ranked first 0.0001 (ten-thousandth) may be discarded.

Step 1003: missing value processing, namely filling continuous features with an average value, and filling discrete features with constants as separate categories;

step 1004: the feature structure is that the continuous features are divided into boxes and discretized (wherein, the box dividing method can divide boxes according to the distribution proportion of the user feature fields in each section), and the discrete features are subjected to type coding.

Step 1005: and carrying out feature processing, namely carrying out box-division discretization on the continuous features and carrying out one-hot coding on the discrete features.

Step 1006: feature selection, i.e. feature selection using chi-square test.

Wherein, in some embodiments of the invention, age (continuous type feature) codes may be referenced in table 1:

TABLE 1

Gender (discrete feature) codes can be referenced in table 2:

sex (sex)	Sex encoding
		Man's body	Gender a
Female	Gender b

TABLE 2

The number of red packet transmissions (continuous characteristic) over the last N days (e.g., 7 days, 30 days, 90 days, etc.) code reference table 3:

number of red packet transmissions in recent N days	N-day reddening packet number coding
		0-10	Number of times of reddening packets per N days a
11-20	Number of times of reddening packets per N days b
		21-30	Number of times of reddening packets per N days c
31-40	Number of times of reddening packets per N days d
		41-50	Number of times of reddening packets in N days e
51-60	Number of times of reddening per N days f
		61-70	Number of times of reddening per N days g
70 or more	Number of times of reddening per N days h

TABLE 3 Table 3

And carrying out type coding on the user characteristics according to the types of the fields through the steps, so as to obtain the coding characteristic representation of the user.

Establishing a corresponding KOL user sample library based on actual conversion of the product users, recalling a batch of reference financial KOL users as classification sample tags through a data conversion dimension, wherein optional dimensions comprise: the specific different dimension choices can be correspondingly adjusted according to the type of the financial KOL user.

For users with financial product data, calculating to obtain sample scores based on the conversion dimensions, wherein the calculation method comprises the following steps: and (3) respectively carrying out Min-Max standardization on each dimension, multiplying to calculate scores, and constructing < user id and KOL score > corresponding to each user in the KOL user sample library.

Step 902: and mining the KOL user feature code frequent sequence pattern based on a sequence pattern mining algorithm.

The characteristic coding sequence mode of the KOL user sample can be mined based on a sequence mode algorithm (a prefixspan algorithm), and characteristic modes frequently appearing in the KOL user group can be mined.

And mining frequent sequence patterns of each length meeting the minimum support threshold in the KOL user feature coding matrix based on a Prefixspan algorithm. Meanwhile, a strategy with multiple minimum support is used, and the calculation method of the minimum support is shown as a formula (1):

min-sup＝a×n (1)

wherein n is the number of samples of a KOL user sample library, a is the minimum support rate, and the minimum support rate parameter is adjusted according to the number of sample sets, and meanwhile, the invention applies a method and thought of 'snowball rolling', namely, each round of mining is provided with higher support, the accuracy of mining of a behavior sequence mode is ensured, and the recall rate of the mode mining is improved through multiple rounds of iterative mining.

Referring to fig. 11, fig. 11 is an optional flowchart of a target object determining method according to an embodiment of the present invention, where the step of performing the sequence mode algorithm (prefixspan algorithm) includes:

step 1101: finding out a user characteristic coding sequence prefix with unit length of 1 and a corresponding projection data set;

step 1102: counting the occurrence frequency of the prefix of the user characteristic coding sequence, adding the prefix with the support degree higher than the minimum support degree threshold value into a data set, and obtaining a frequent one-set sequence mode;

step 1103: the recursive mining of all prefixes of length i and meeting the minimum support requirement can specifically include:

1) Mining the projection data set of the prefix, and returning to recursion if the projection data is an empty set;

2) Counting the minimum support degree of each item in the corresponding projection data set, combining each item meeting the support degree with the current prefix to obtain a new prefix, and recursively returning if the support degree requirement is not met;

3) Let i=i+1, the prefix is each new prefix after merging the single items, and the current steps are respectively recursively executed;

step 1104: and returning all frequent characteristic code sequence modes in the user characteristic code sequence sample set.

Continuing with the description of the principles of the Prefixspan algorithm, the following examples illustrate specific mining of the KOL user feature encoding matrix.

TABLE 4 Table 4

In table 4, the transmission/reception information ratio for N days=the number of pieces of information received in N days/the number of pieces of information transmitted in N days; the user relation of the financial products in the friends accounts for the ratio = the number of users of the financial products/the number of friends; attention to attention person count ratio=user attention person count/user attention person count.

Further, mining sequence patterns contained in the user feature sequence based on a Prefixspan algorithm, and firstly counting the frequencies of all types of features on the assumption that the set minimum support threshold is 0.5:

TABLE 5

One prefix and its corresponding suffix satisfying the threshold are respectively:

TABLE 6

Similarly, the two-term prefix and corresponding suffix that meet the minimum support threshold are:

TABLE 7

The three prefixes and corresponding suffixes that meet the minimum support threshold are:

TABLE 8

The method comprises the steps of obtaining a field type and a section corresponding to field coding by converting an algorithm mining result, wherein the mode that the obtained coding features frequently appear is common features commonly possessed by KOL user groups.

Step 903: and carrying out weighted calculation based on KOL related factor characteristics obtained by sequence pattern feature mining to obtain user sample weights.

According to the method, a KOL user sample frequent feature coding sequence mode is mined from a KOL user crowd feature coding sequence in step 902, so that the part of feature types are focused on in a modeling method, weighting processing is carried out on the part of feature types, field rejection is carried out on feature type fields which do not appear in all frequent prefixes of the sequence mode, and factors which have an insignificant effect on distinguishing the KOL users are filtered. The weighting weight is set to be the frequency duty ratio corresponding to each field type, for example, the minimum support threshold is set to be 0.5, if the frequency duty ratio of each type value of a certain field is smaller than the minimum support, the field is rejected, and if the frequency duty ratio of the field type 'N days of information receiving and transmitting number ratio e' is 0.75, the weighting weight of the field type is 0.75; the field type "attention to number of persons of interest duty cycle c" has an occurrence frequency duty cycle of 0.6, and then the field type weighting weight is 0.6. And calculating the field type average weight of the user coding feature sequence as the sample weight of the KOL user. Frequent feature sequence patterns for KOL users are:

TABLE 9

The sample weight of the KOL user is as follows: (0.6+0.75+0.9+0.88)/4=0.7825

Sample weights for each KOL user sample are constructed as shown.

Table 10

Step 904: and constructing a sample weighted clustering algorithm to cluster the user characteristics and the behavior characteristics.

And simultaneously removing the features with the occurrence frequency proportion of each type value of the feature codes smaller than the set minimum support degree by combining the preamble steps 901-903, so as to perform feature screening, and then performing box-division discretization and one-hot coding on the continuous features, so as to construct KOL user sample features.

And (3) weighting the characteristics of the user samples according to the sample weight of each sample calculated in the step 903, and constructing a sample weighted clustering algorithm to cluster the characteristic vectors, wherein the specific clustering process is as follows.

In the conventional clustering algorithm based on partitioning, clustering samples are generally treated equally, such as a K-means algorithm, an EM algorithm and the like. Under the premise of not considering the weight of a sample, the K-means clustering algorithm finishes clustering when the criterion function converges, and the formula of the criterion function is as follows:

wherein J is the degree of aggregation, and is used for measuring the clustering effect, k is the total number of class clusters, m _i Is the total number of members in class cluster i; / >

Is the j-th member in class cluster i; />

For the center vector of the class cluster i, the calculation formula is as follows: />

For text->

Is cluster-like central point->

Is a similarity of (3). The method of the invention uses cosine of the vector included angle to calculate the similarity. Considering a sample weighted clustering algorithm, and clustering the weighted samples according to a criterion function calculation formula: />

Wherein->

The class center vector weighted by the clustered samples is calculated as follows:

wherein w is _j Weight for clustering samples i, +.>

Corresponding to step 3

And obtaining a clustering result of the KOL user group through weighted clustering.

Step 905: and predicting the corresponding KOL user based on the clustering result and the preset condition.

And combining the processing procedure of the preamble step, removing the characteristics of which the frequency occupation ratio of each type value of the characteristic field is smaller than the set minimum support degree, performing characteristic screening, performing box-division discretization on continuous characteristics, performing one-hot coding on the discrete characteristics, and weighting the user sample characteristics according to the sample weight of each sample calculated in the step 903, thereby constructing new sample weighting characteristics. The probability that the new sample is a KOL user can be obtained in two ways:

the first way is to calculate the distance between the feature vector of the new sample and the center of the cluster, such as cosine distance. The closer the distance, the greater the probability that the new sample is a KOL user, which is predicted by distance calculation quantization.

And step 4, weighted clustering is carried out on the new sample feature vector and all the sample feature vectors of the user together, the proportion of KOL user samples in the category to which the new sample feature vector belongs is calculated after clustering is completed, the higher the proportion of KOL user samples in the category is, the greater the probability that the new user sample is the KOL user is represented, and the probability that the new sample is the KOL user is quantized according to the category proportion of the clustering result.

Compared with the traditional technology, the KOL user characteristics can be better constructed, the defect that importance quantification and further analysis processing are not better carried out on the user characteristics and the behavior characteristics in the traditional method is overcome, the characteristics with insignificant influence are removed, the influence of noise characteristics can be reduced to the greatest extent, and the accuracy of target object prediction is improved.

The beneficial technical effects are as follows:

the invention obtains the resource transaction data corresponding to different objects; determining corresponding object coding features and behavior coding features based on the resource transaction data, and determining corresponding candidate object sets according to the object coding features and the behavior coding features; determining a characteristic coding frequent sequence mode corresponding to the candidate object set; weighting the characteristic code frequent sequence modes corresponding to the candidate object set, and determining a weight parameter matched with the target object; clustering the object coding features and the behavior coding features respectively based on weight parameters matched with the target object; and determining target objects matched with the screening conditions in the candidate object set according to the clustering results of the object coding features and the behavior coding features and the corresponding screening conditions, thereby realizing efficient and accurate determination of the target objects matched with the screening conditions in different objects so as to facilitate different operations on the corresponding target objects.

The foregoing description of the embodiments of the invention is not intended to limit the scope of the invention, but is intended to cover any modifications, equivalents, and alternatives falling within the spirit and principles of the invention.

Claims

1. A method of determining a target object, the method comprising:

acquiring resource transaction data corresponding to different objects;

deleting feature type fields which do not appear in all frequent prefixes;

according to the use environment of the target object, adjusting the weight parameter of the characteristic type field;

weighting the feature code frequent sequence mode corresponding to the candidate object set based on the weight parameter of the feature type field, and determining that the field type average weight parameter of the object code feature sequence is the weight parameter matched with the target object;

2. The method of claim 1, wherein the obtaining resource transaction data corresponding to different objects comprises:

acquiring first resource transaction data of different objects in a social resource exchange process;

acquiring second resource transaction data of the different objects in a financial resource exchange process;

and establishing an association relation set of the first resource transaction data and the second resource transaction data to form resource transaction data corresponding to different objects.

3. The method of claim 1, wherein the determining respective object coding features and behavior coding features based on the resource transaction data comprises:

based on the resource transaction data, respectively denoising the object coding features and the behavior coding features to delete single-value features of corresponding dimensions;

Determining abnormal values in the object coding feature and the behavior coding feature, and deleting the abnormal values in the object coding feature and the behavior coding feature respectively;

and respectively carrying out data filling and feature construction processing on the object coding features and the behavior coding features based on the deleted single-value features and the corresponding abnormal values of the corresponding dimensions.

4. A method according to claim 3, wherein the data filling and feature construction processes of the object-coded features and behavior-coded features, respectively, based on the deleted single-valued features and corresponding outliers of the corresponding dimensions, comprise:

determining corresponding feature types in the object coding features and behavior coding features;

when the feature type is continuous, filling data through a corresponding mean value, and carrying out feature construction processing of box-division discretization on the continuous feature;

and when the feature type is a discrete feature, filling data through a corresponding constant, and performing type coding processing on the discrete feature to realize corresponding feature construction.

5. The method according to claim 4, wherein the method further comprises:

According to the association relation set of the first resource transaction data and the second resource transaction data, determining basic object labels with different dimensions matched with the association relation set;

and responding to the basic object labels of different dimensions matched with the association relation set, and screening the different objects to determine basic objects in the different objects.

6. The method of claim 1, wherein the determining the feature code frequent sequence pattern corresponding to the candidate object set comprises:

determining an object feature coding sequence prefix and a corresponding projection data set in unit length based on a mode mining algorithm of prefix projection;

based on the occurrence frequency of the object feature coding sequence prefix, adding the object feature coding sequence prefix with the support degree higher than the minimum support degree threshold value to the data set to be projected, and determining a corresponding frequent one-item set sequence mode;

performing iterative processing on the object feature coding sequence prefix based on the frequent one-item set sequence mode until the corresponding minimum support requirement parameter is reached;

and determining the feature code frequent sequence mode corresponding to the candidate object set according to the result of iterative processing on the object feature code sequence prefix.

7. The method according to claim 1, wherein the determining a target object in the candidate object set that matches the filtering condition according to the clustering result of the object coding feature and the behavior coding feature and the corresponding filtering condition includes:

based on the field type average weight parameter of the object coding feature sequence, weighting corresponding user features to determine corresponding first sample feature vectors;

and determining target objects matched with the screening conditions in the candidate object set according to the first sample feature vector and the clustering result.

8. The method according to claim 1, wherein the determining a target object in the candidate object set that matches the filtering condition according to the clustering result of the object coding feature and the behavior coding feature and the corresponding filtering condition includes:

weighting the first sample feature vector and the sample feature vectors corresponding to the different objects to determine corresponding second sample feature vectors;

Determining corresponding target object proportion parameters according to the first sample feature vector and the clustering result;

and determining the target object matched with the screening condition in the candidate object set based on the target object proportion parameter.

9. The method according to any one of claims 1-8, further comprising:

sending the object identification, the corresponding resource transaction data and the target object matched with the screening condition to a blockchain network so that

10. The method according to claim 9, wherein the method further comprises:

11. The method according to claim 9, wherein the method further comprises:

responding to a query request, and analyzing the query request to obtain a corresponding object identifier;

12. A target object determination apparatus, the apparatus comprising:

the information processing module is used for weighting the feature code frequent sequence mode corresponding to the candidate object set based on the weight parameter of the feature type field, and determining that the field type average weight parameter of the object code feature sequence is the weight parameter matched with the target object;

13. An electronic device, the electronic device comprising:

A memory for storing executable instructions;

a processor for implementing the target object determination method according to any one of claims 1 to 11 when executing executable instructions stored in said memory.

14. A computer readable storage medium storing executable instructions which when executed by a processor implement the target object determination method of any one of claims 1 to 11.