CN112269793A

CN112269793A - Method and device for detecting user type based on block chain

Info

Publication number: CN112269793A
Application number: CN202010974987.2A
Authority: CN
Inventors: 陈文涛
Original assignee: Lianshang Xinchang Network Technology Co Ltd
Current assignee: Lianshang Xinchang Network Technology Co Ltd
Priority date: 2020-09-16
Filing date: 2020-09-16
Publication date: 2021-01-26

Abstract

The application aims to provide a method and equipment for detecting a user type based on a block chain, and the method and equipment comprise the following steps: determining a first illegal user judgment model uploaded to a block chain by a first node; acquiring downloading record information for downloading the first violation user judgment model from the block chain; determining one or more second illegal user judgment models corresponding to one or more second nodes, which are uploaded to the block chain by the one or more second nodes respectively; receiving a user detection request sent by user equipment of a target organization; and responding to the user detection request, and detecting the user data information according to the illegal user judgment model corresponding to the organization identifier to determine whether the target user is an illegal user detection book. The application can improve the detection accuracy and reduce the training cost.

Description

Method and device for detecting user type based on block chain

Technical Field

The present application relates to the field of communications, and in particular, to a technique for detecting a user type based on a block chain.

Background

With the rapid development of the internet, social networks have become an important social part of people's daily life. However, the abnormal users in the social network are in endless and increasingly serious. Therefore, the method for auditing the abnormal users in the social network plays an important role in improving user experience, maintaining good network environment and the like. At present, each company possessing social products generally detects users through machine auditing and manual auditing modes, and the auditing reliability can be ensured only by manually updating a database continuously, and the quantity of the users owned by each company is different.

Disclosure of Invention

An object of the present application is to provide a method and apparatus for detecting a user type based on a block chain.

According to an aspect of the present application, there is provided a method for detecting a user type based on a block chain, the method including:

determining a first illegal user judgment model uploaded to a block chain by a first node, wherein the first node is a node corresponding to a first organization, the first illegal user judgment model comprises organization identification information of the first organization, and the first illegal user judgment model is generated by training model data information of the first node;

acquiring download record information for downloading the first illegal user judgment model from the block chain, wherein the download record information comprises organization identification information respectively corresponding to one or more second organizations downloading the first illegal user judgment model;

determining one or more second illegal user determination models corresponding to one or more second nodes, which are uploaded to the blockchain respectively, of the one or more second nodes, wherein the one or more second nodes are used for characterizing the one or more second organizations, each of the one or more second illegal user determination models is matched with organization identification information of the corresponding second organization, and each second illegal user determination model is determined by updating the first illegal user determination model through model data increment information of the corresponding second node;

receiving a user detection request sent by user equipment of a target organization, wherein the user detection request comprises organization identification information of an organization to which a violation judgment model requested to be used belongs and user data information of a target user provided by the target organization;

and responding to the user detection request, and detecting the user data information according to the illegal user judgment model corresponding to the organization identifier to determine whether the target user is an illegal user.

According to an aspect of the present application, there is provided a network device for detecting a user type based on a block chain, the device including:

the system comprises a module, a module and a module, wherein the module is used for determining a first illegal user judgment model uploaded to a block chain by a first node, the first node is a node corresponding to a first organization, the first illegal user judgment model comprises organization identification information of the first organization, and the first illegal user judgment model is generated by training model data information of the first node;

a second module, configured to obtain download record information for downloading the first illegal user determination model from the blockchain, where the download record information includes organization identification information corresponding to each of one or more second organizations that download the first illegal user determination model;

a third module, configured to determine one or more second illegal user determination models corresponding to one or more second nodes, where the one or more second nodes are respectively uploaded to the blockchain, and the one or more second nodes are used to characterize the one or more second organizations, where each of the one or more second illegal user determination models is matched with organization identification information of the corresponding second organization, and is determined by updating the first illegal user determination model with model data incremental information of the corresponding second node;

a fourth module, configured to receive a user detection request sent by a user device of a target organization, where the user detection request includes organization identification information of an organization to which a violation determination model requested to be used belongs and user data information of a target user provided by the target organization;

and the fifth module is used for responding to the user detection request, and detecting the user data information according to the illegal user judgment model corresponding to the organization identifier so as to determine whether the target user is the illegal user.

According to an aspect of the present application, there is provided an apparatus for detecting a user type based on a block chain, the apparatus including:

a processor; and

a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the operations of any of the methods described above.

According to another aspect of the application, there is provided a computer readable medium storing instructions that, when executed, cause a system to perform the operations of any of the methods described above.

Compared with the prior art, the network equipment acquires a first illegal user judgment model for detecting the user type, acquires one or more iteratively updated illegal user judgment models which are updated and iterated based on the first illegal user judgment model, and identifies the user type of the target user according to the illegal user judgment model specified by the target organization after receiving the user detection request sent by the target organization. In the updating iteration process of the illegal user judgment model, a plurality of organizations (companies) maintain and update the illegal user judgment model together, so that the detection accuracy of the illegal user type can be improved, and meanwhile, the plurality of organizations maintain the model together, which is beneficial to reducing the training cost of each company, so that the purpose of cooperative cooperation among the plurality of organizations can be achieved.

Drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:

FIG. 1 illustrates a system topology according to the present application;

FIG. 2 is a flow diagram of a method for block chain based user type detection according to another embodiment of the present application;

FIG. 3 is a flow diagram illustrating a method for blockchain based detection of user types according to yet another embodiment of the present application;

fig. 4 is a schematic device diagram of a network device for detecting a user type based on a block chain according to an embodiment of the present application;

FIG. 5 illustrates an exemplary system that can be used to implement the various embodiments described in this disclosure.

The same or similar reference numbers in the drawings identify the same or similar elements.

Detailed Description

The present application is described in further detail below with reference to the attached figures.

In a typical configuration of the present application, the terminal, the device serving the network, and the trusted party each include one or more processors (e.g., Central Processing Units (CPUs)), input/output interfaces, network interfaces, and memory.

The Memory may include forms of volatile Memory, Random Access Memory (RAM), and/or non-volatile Memory in a computer-readable medium, such as Read Only Memory (ROM) or Flash Memory. Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, Phase-Change Memory (PCM), Programmable Random Access Memory (PRAM), Static Random-Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), electrically Erasable Programmable Read-Only Memory (EEPROM), flash Memory or other Memory technology, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device.

The device referred to in this application includes, but is not limited to, a user device, a network device, or a device formed by integrating a user device and a network device through a network. The user equipment includes, but is not limited to, any mobile electronic product, such as a smart phone, a tablet computer, etc., capable of performing human-computer interaction with a user (e.g., human-computer interaction through a touch panel), and the mobile electronic product may employ any operating system, such as an Android operating system, an iOS operating system, etc. The network Device includes an electronic Device capable of automatically performing numerical calculation and information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded Device, and the like. The network device includes but is not limited to a computer, a network host, a single network server, a plurality of network server sets or a cloud of a plurality of servers; here, the Cloud is composed of a large number of computers or web servers based on Cloud Computing (Cloud Computing), which is a kind of distributed Computing, one virtual supercomputer consisting of a collection of loosely coupled computers. Including, but not limited to, the internet, a wide area network, a metropolitan area network, a local area network, a VPN network, a wireless Ad Hoc network (Ad Hoc network), etc. Preferably, the device may also be a program running on the user device, the network device, or a device formed by integrating the user device and the network device, the touch terminal, or the network device and the touch terminal through a network.

Of course, those skilled in the art will appreciate that the foregoing is by way of example only, and that other existing or future devices, which may be suitable for use in the present application, are also encompassed within the scope of the present application and are hereby incorporated by reference.

In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.

Fig. 1 illustrates a typical scenario of the present application, where company a is a company having a plurality of social application products, each social application has a considerable number of users, and company a collects user data of all users, where the user data includes an application list in user equipment of a user, a user equipment model, user identification information of the user, and behavior data of the user in the social application, company a trains an illegal user determination model a of company a according to the user data and uploads the illegal user determination model a to a block chain, company B, company C, and company D respectively download the illegal user determination model a from the block chain, and company B, company C, and company D respectively train the illegal user determination model a to generate the illegal user determination model a by using the user data collected based on the products of the company_BRule violation user determination model A_CRule violation user determination model A_DThen, the illegal users are judged to be the model A respectively_BRule violation user determination model A_CRule violation user determination model A_DUploading into a blockchain. Company E and company F download illegal user judgment model A from block chain respectively_BAnd respectively training illegal user judgment model A by using user data collected based on products of the company_BGenerating an illegal user decision model A_BERule violation user determination model A_BFAnd judging the illegal user to be a model A_BERule violation user determination model A_BFUploading to a block chain; g company, H company and I company download illegal user judgment model A from block chain respectively_DAnd respectively training illegal user judgment model A by using user data collected based on products of the company_DGenerating violationsUser decision model A_DGRule violation user determination model A_DHRule violation user determination model A_DIAnd uploaded into the blockchain. By analogy, each company can obtain an illegal user judgment model, train the illegal user judgment model again and upload the illegal user judgment model to the block chain, and each trained user judgment model is provided with the mark of the corresponding company. The method comprises the steps that a target company sends a user detection request to network equipment, the network equipment responds to the user detection request, determines a corresponding target illegal user judgment template according to the detection request, and acquires the template from a block chain, for example, the target illegal user judgment model is one of illegal user judgment templates uploaded to the block chain, the network equipment inputs target user data corresponding to the user detection request into the target illegal user judgment template to obtain probability information that a target user corresponding to the target user data is the illegal user, if the probability information is larger than a preset probability threshold value, a threshold for enabling the target user to enter manual auditing can be subsequently improved, and when the illegal probability reaches a certain probability value, the network equipment can mark the target user as a high-risk user so as to be used as a reference during subsequent manual auditing.

Fig. 2 illustrates a method for detecting a user type based on a block chain according to an embodiment of the present application, which includes step S101, step S102, step S103, step S104, and step S105.

Specifically, in step S101, the network device determines a first illegal user determination model uploaded to the block chain by a first node, where the first node is a node corresponding to a first organization, the first illegal user determination model includes organization identification information of the first organization, and the first illegal user determination model is generated by training model data information of the first node. Wherein the first organization may be a company that collects user data in owned social products, and the first organization may correspond to an organization identification information indicating the organization, for example, the organization identification information includes a registered name or a default organization number (e.g., an assigned ID of the organization) of the organization; the blockchain is a decentralized distributed database, which is not tied to any centralized server, but is composed of millions of "small servers" and "nodes", where a node generally refers to a computer that downloads relevant cryptocurrency to participate in a peer-to-peer network, for example, computers in a blockchain network include a mobile phone, a mining machine, and a server. The person operating a node may be a normal wallet user, a miner, and multiple people collaborating, storing, and verifying, and the people may all be nodes of a blockchain. For example, the terminal devices responsible for maintaining the operation of the network may be referred to as nodes, and each node may be capable of obtaining a copy of the complete or partial record. Here, the first organization is taken as a node in the blockchain (for example, an operation subject of the first organization in the blockchain is represented by the first node), and the first node acquires user data information collected by the first organization and trains the data information through the neural network to generate a first illegal user judgment model corresponding to the first organization. In some embodiments, the first violation user determination model includes a first determination model and a second determination model. The first judgment model is trained based on data information such as an application list in user equipment, a user equipment model and user identification information of a user in model data information collected by a first organization, the second judgment model is trained based on behavior data of the user in the model data information collected by the first organization in a preset time period in social application, and the judgment models trained from different user data directions can not only determine the probability that the user is an illegal user type according to user identification, but also predict the behavior of the user in a period of time so as to predict whether the user conducts illegal behavior in the period of time, thereby predicting the probability that the user is an illegal user. The accuracy rate of detecting the user as the illegal user can be improved to a certain extent. In some embodiments, the first decision model is generated from user device samples of a plurality of users via machine learning training, wherein the user device sample of each user includes a list of applications in the user device of the user, a user device model number, and user identification information of the user, and the user device samples of the plurality of users belong to the model data information collected by the first organization. For example, the first organization owns a plurality of social applications and acquires model data information of a plurality of users through the plurality of social applications, wherein the model data information includes a list of applications in a user device of each user (e.g., including an installed application or a currently installed application), a model number of the user device of each user (e.g., a name, a MAC, a serial number, etc. of the device), and user identification information of each user (e.g., a user head portrait, a user name, a user ID, a phone number registered by the user, etc.), the network device takes the acquired model data information of the plurality of users as a plurality of user device samples, the plurality of user device samples are used for inputting neural network training to generate a first decision model, or can be trained in a plurality of ways such as NFM, FFM, DFM, linear classification, etc. to generate the first decision model, and a network model structure of the first decision model includes an input layer, a, The system comprises an embedding layer, an MLP layer and an output layer, and the probability that the user is the illegal user type is output from the output layer. The first determination model may predict the likelihood that the user is an offending user when the user is not socially active or has less socially active in the social application. In some embodiments, the first decision model is generated from user device samples of a plurality of users via machine learning training, including: classifying the user equipment samples of the plurality of users to determine a positive sample and a negative sample, wherein the positive sample comprises the user equipment sample of the non-violation user, and the negative sample comprises the user equipment sample of the violation user; and performing machine learning on the positive sample and the negative sample to generate the first judgment model, wherein the first judgment model is used for outputting probability information that the user is the illegal user type. For example, the network device may obtain marking information about whether each of the plurality of users is an offending user in advance, e.g., a human may preliminarily mark whether each user is an offending user, e.g., mark a user with an offending behavior such as malicious diversion, advertisement, advertising, e-mail, negative political emissions, etc., as an offending user, and mark a user without any of the offending behaviors as a non-offending user. According to the marking information of each user, the network device takes the user device sample corresponding to the user marked as the illegal user as a positive sample, and takes the user device sample corresponding to the user marked as the non-illegal user as a negative sample. The network device inputs a plurality of positive and negative samples into a neural network for training machine learning training, so that a trained first decision model can output the probability that a user is an illegal user based on input user device characteristic data (such as an application list in the user device, a user device model number and user identification information of the user), and the first decision model can accurately predict the user type when the user needing prediction has no social behaviors or is in an early stage of social behaviors.

In some embodiments, the second decision model is generated by machine learning training of user behavior samples of a plurality of users, the user behavior sample of each user includes behavior data of the user in social software M days before the current time period, where M is a positive integer, and the user behavior samples of the plurality of users belong to the model data information collected by the first organization. For example, a first organization owns a plurality of social applications and obtains model data information of a plurality of users through the plurality of social applications, wherein the model data information includes behavior data of each user in the social applications for M days before the current time period, and in some embodiments, the number of general M days cannot be too large, so that the rule is more accurate when the rule violation probability of the same number of days after the current time period is predicted later. The network equipment takes the acquired model data information of the users as a plurality of user behavior samples, and the user behavior samples are input into the bert, RNN, XLinet, LSTM and other time sequence models for training to generate a second judgment model, so that the probability that the user is an illegal user in the later time of the current time period is detected based on the second judgment model. In some embodiments, the second decision model is generated from user behavior samples of a plurality of users via machine learning training, including: classifying the user behavior samples of the plurality of users to determine a positive sample and a negative sample, wherein the positive sample comprises the user behavior sample of the non-violation user, and the negative sample comprises the user behavior sample of the violation user; and performing machine learning according to the positive sample and the negative sample to generate the second judgment model, wherein the second judgment model is used for outputting probability information that the user is in an illegal user type in M days after the current time period, and M is a positive integer. For example, the network device may obtain marking information about whether each of the plurality of users is an offending user in advance, e.g., a human may preliminarily mark whether each user is an offending user, e.g., mark a user with an offending behavior such as malicious traffic guidance, advertising, e-mail, negative political information, etc., as an offending user, and mark a user without any of the above-mentioned offending behaviors as a non-offending user. The network device takes a user behavior sample corresponding to a user marked as a user with illegal behavior as a positive sample, takes a user behavior sample corresponding to a user marked as a user without illegal behavior as a negative sample, inputs the positive sample and the negative sample into the time sequence model for training to obtain a second judgment model, and can accurately predict the probability that the time content of the user in the future of the current period is the illegal user.

In step S102, the network device obtains download record information for downloading the first illegal user determination model from the blockchain, where the download record information includes organization identification information respectively corresponding to one or more second organizations that download the first illegal user determination model. The first illegal user determination model in the blockchain is an open resource, the second organization can directly download the model from the blockchain, the second organization can be a company other than the first organization, the first organization is an owner of the first illegal user determination model, and the first illegal user determination model can be directly updated inside the first organization. The network device determines download record information of the first illegal user judgment model, and the download record information may also include download number information of the first illegal user judgment model.

In step S103, the network device determines one or more second illegal user determination models corresponding to one or more second nodes, which are uploaded to the blockchain respectively, by the one or more second nodes, where the one or more second nodes are used to characterize the one or more second organizations, each of the one or more second illegal user determination models is matched with the organization identification information of the corresponding second organization, and each of the one or more second illegal user determination models is determined by updating the first illegal user determination model with the model data incremental information of the corresponding second node. For example, the network device determines, according to the download record information, one or more second organizations that download the first illegal user determination model, and the presence of at least one of the one or more second organizations may directly use the first illegal user determination model for user type detection, for example, a second node corresponding to the at least one second organization inputs the collected user data owned by the organization into the first illegal user determination model to detect the user type of the corresponding user; or the first illegal user determination model may be updated by the presence of at least one second node corresponding to one of the one or more second organizations, for example, each of the at least one second organizations inputs the collected incremental information of the model data owned by the organization (for example, all or part of the user data collected by each second organization) into the first illegal user determination model through the corresponding second node to train the first illegal user determination model so as to obtain a second illegal user determination model corresponding to each second organization, which is more accurate for detecting the user type of the user owned by each corresponding second organization since each second illegal user determination model is trained based on the user data owned by each second organization, the training process of each second organization on the first illegal user judgment model may refer to the specific steps of training the first organization to generate the first illegal user judgment model (for example, model data increment information is respectively input into the first judgment model and the second judgment model for training so as to update the first judgment model and the second judgment model, and the updated first judgment model and the updated second judgment model are used as one second illegal user judgment model), and no repetition is performed here. After one or more second illegal user determination models corresponding to one or more second organizations, one or more second nodes corresponding to the one or more second organizations upload the one or more second illegal user determination models into the block chain, wherein each second illegal user determination model comprises an organization identifier of the corresponding second organization, and the organization identifier is used for subsequently marking a corresponding second organization trained model. In some embodiments, the corresponding one or more second nodes of the one or more second organizations in the blockchain are extension nodes below the first node. For example, the network device determines one or more objects (e.g., one or more second organizations and the target organization) operating in the blockchain as nodes in the blockchain, where the operations include uploading or downloading operations in the blockchain, and the one or more second nodes corresponding to the one or more second organizations perform model updating and iteration after acquiring the first violated user determination model of the first organization, so that the one or more second organizations are branch nodes of the first organization node in the blockchain, and preferably utilize characteristics of the blockchain, thereby providing a basis for continued iteration of subsequent models.

In step S104, the network device receives a user detection request sent by a user device of a target organization, where the user detection request includes organization identification information of an organization to which a violation determination model requested to be used belongs and user data information of a target user provided by the target organization. The target organization may be any company, and the user equipment of the target organization sends a user detection request to the network equipment, where the network equipment may be a server corresponding to any node in the block chain, and the network equipment may acquire operation information of any node in the block chain. In response to the user detection request, the network device obtains, from the blockchain, the violation determination model corresponding to the organization according to the organization identification information of the organization to which the violation determination model requested to be used belongs, where, for example, the violation determination model is generated by the organization after downloading other violation determination models from the blockchain and updating the other violation determination models with model data increment information of the organization.

In step S105, in response to the user detection request, the network device detects the user data information according to the illegal user determination model corresponding to the organization identifier to determine whether the target user is an illegal user. For example, on the premise that the network device obtains the illegal user determination model corresponding to the organization identifier from the blockchain, the network device inputs the user data information into the illegal user determination model to determine the target user, where the user data information includes an application list in the user device of the target user, a model of the user device, user identifier information of the user, and behavior information of the target user in social applications. And if the violation probability information output by the first violation user judgment model is greater than a preset probability threshold, the network equipment determines that the corresponding user is a violation user.

For example, a first company collects user data obtained by a company social product, and performs model training according to the user data by dividing whether a user violates rules into positive and negative samples to obtain a first violation user determination model, where the first violation user determination model may be used to output a probability that the user is a violation user. Subsequently, the first company uploads the first illegal user determination model to the blockchain, the second company may download the first illegal user determination model from the blockchain and update and train the model using user data of the second company to generate a second illegal user determination model, and the second company uploads the second illegal user determination model to the blockchain.

In some embodiments, the method further includes step S106 (not shown), in step S106, the network device determines, according to the download record information of the one or more second illegal user determination models, contribution information of one or more second organizations corresponding to the one or more second illegal user determination models; determining reward information available to the one or more second organizations according to the contribution information, wherein the reward information is used for writing the blockchain into the one or more second nodes. For example, the network device determines that the second illegal user determination model with the highest download frequency and iteration frequency in the one or more second illegal user determination models is the model most approved by other organizations, and on the basis, the network device may give more rewards to the second organization with a high quality to encourage the second organization, so as to provide a basis for the more organizations to continue updating the model. In some embodiments, the determining, according to the download record information of the one or more second illegal user determination models, contribution information of one or more second organizations corresponding to the one or more second illegal user determination models includes: acquiring downloading frequency information in the downloading record information of the one or more second violation user judgment models; and determining contribution information of one or more second organizations corresponding to the one or more second illegal user judgment models according to the downloading frequency information, wherein the downloading frequency information is in direct proportion to the contribution information. For example, one or more second violation user determination models exist in the blockchain (e.g., corresponding identifiers are a, respectively)_B、A_C、A_D) The network device determines that the information of the number of times that the three second illegal user judgment models are downloaded is 20, 30 and 40 respectively, so as to determine that the contribution information that the corresponding organizations of the three models can obtain is a, b and c respectively, wherein a>b>And c, providing a basis for determining the reward information of one or more organizations on the basis of the determined contribution information, wherein the reward information can comprise block resources in the block chain.

In some embodiments, the method further includes step S107 (not shown), in step S107, the network device acquires one or more third illegal user determination models, which are uploaded to the block chain and updated based on the one or more second illegal user determination models, wherein each of the one or more third illegal user determination models matches with organization identification information of a corresponding third organization; repeating the steps until one or more Nth illegal user judgment models which are uploaded to the block chain and updated based on the one or more Nth-1 illegal user judgment models are obtained, wherein each Nth illegal user judgment model in the one or more Nth illegal user judgment models is matched with the corresponding organization identifier of the Nth organization, and N is an integer greater than 2; determining contribution information of one or more organizations corresponding to the tracking mark information according to the tracking mark information of each Nth illegal user judgment model in the one or more Nth illegal user judgment models. For example, the network device may use one or more second illegal user determination models updated based on the first illegal user determination model as models of a first batch of iterations, use one or more third illegal user determination models updated based on the one or more second illegal user determination models as models of a second batch of iterations, and so on, and use one or more nth illegal user determination models updated based on one or more N-1 th illegal user determination models as models of an N-1 st batch of iterations, where each model corresponds to an organization identifier of an organization. In some embodiments, each batch of the iterated models is provided with tracking identification information, wherein the tracking identification information is used for determining tissue identification information of one or more tissues which update the template. For example, taking N as 4 as an example, the network device obtains the one or more fourth illegal user determination models, and for each fourth illegal user determination model, the network device determines, according to the tracking flag of each fourth illegal user determination model, organization information that each fourth illegal user determination model undergoes when it is iterated, for example, the fourth illegal user determination model a is uploaded after being updated by an a organization, and tracking flag information trained by an a1 organization, an a2 organization, and an A3 organization exists in the model a, and the network device determines, based on the tracking flag information, the user data amounts when the a1 organization, the a2 organization, the A3 organization, and the a organization are trained, and determines contribution information obtainable by each organization according to the size of the data amount information. On the basis, subsequent awarding is carried out on the updating of each organization, so that the subsequent updating operation of each organization is stimulated, and a basis is provided for generating a model with higher output accuracy. In some embodiments, the determining, from the tracking marker information of each nth violation user determination model of the one or more nth violation user determination models, contribution information of one or more organizations corresponding to the tracking marker information includes: determining tracking marker information for each Nth violation user decision model of the one or more Nth violation user decision models; performing data statistics on one or more organizations corresponding to the tracking mark information according to the tracking mark information of each Nth illegal user judgment model; determining corresponding contribution information from statistics of the one or more organizations, wherein the statistics are proportional to the contribution information. And on the basis of determining the statistical data of each organization, providing a basis for settlement of contribution information of each organization. In some embodiments, the performing data statistics on one or more tissues corresponding to the tracking marker information according to the tracking marker information of each nth violation user determination model includes: acquiring one or more organization identification information corresponding to the tracking mark information of each Nth illegal user judgment model; determining one or more corresponding organizations according to the one or more organization identification information; and accumulating the occurrence times of each piece of organization identification information in the one or more organizations to complete data statistics of the one or more organizations. On the basis of carrying out contribution information statistics on each organization, a foundation is provided for generating a model with higher output accuracy. For example, taking N as 4 as an example, as shown in fig. 3, A1 is a first illegal user decision model, a11, a12, a13 are one or more second illegal user decision models trained on A1 update, a111, a112, a113 are one or more third illegal user decision models trained on a11 update, a121, a122 are one or more third illegal user decision models trained on a12 update, a1111, a1112 are one or more fourth illegal user decision models trained on a111 update, a1131, a1132 are one or more fourth illegal user decision models trained on a113 update, a1221, a1222 are one or more fourth illegal user decision models trained on a122 update, and each user decision model is uploaded to the block chain by the corresponding organization, for example, a1 is uploaded by a1 organization, a11, a12, a13 are respectively uploaded by a11, a12, a13 organization …, and so on. The network device obtains the trace labels of each user decision model, for example, taking a11 as an example, the trace labels of the template include the tissue identification information of A1 tissue and a11 tissue (the data collected by the two tissues are trained into a11 template), and takes a1111 as an example, the trace labels of the template include the tissue identification information of A1 tissue, a11 tissue, a111 tissue, a1111 tissue (the data collected by the four tissues are trained into a1111 template), and so on the trace label information of other templates. After determining the tissues under the tracking marker information of each template, the network device performs data statistics on the number of occurrences of the involved tissues, for example, the number of occurrences of the a1111 template including A1, a11, a111, a1111 tissue is once, the number of occurrences of the a1112 template including A1, a11, a111, a1112 tissue is once, the number of occurrences of the a1131 template including A1, a11, a113, a1131 tissue is once, and so on, and finally obtains the number of occurrences of the A1 tissue as 14, the number of occurrences of the a11 as 7, and so on, counts the number of occurrences of each tissue in the templates, and determines the contribution information of each tissue based on the final data statistics result, for example, the number of occurrences of the A1 tissue is 14, and the maximum number of occurrences of the A1 is the highest.

In some embodiments, the method further includes step S108 (not shown), and in step S108, the network device uploads the model data information of the first node and the model data delta information to the blockchain. For example, in the process of updating the iterative violation user determination model, the original model data information (e.g., the model data information collected by the first organization) and the model data increment information newly added each time in the following are uploaded into the blockchain, so that the data can be analyzed in the following and the data can be saved conveniently. In some embodiments, if the organization identification information of the organization to which the violation determination model used by the request belongs includes the organization identification information of the first organization; in step S104, a network device receives a user detection request sent by a user device of a target organization, where the user detection request includes organization identification information of the first organization and user data information of a target user provided by the target organization; in step S105, in response to the detection request, the network device detects the user data information according to the first illegal user determination model and the illegal determination rule of the target user to determine whether the target user is an illegal user. For example, taking the example that the user detection request includes the organization identification information of the first organization, if the request is the organization identification information of other organizations, the present embodiment is also applicable, and in some embodiments, in response to the detection request, the network device detects the user data information according to the first illegal user determination model and the illegal determination rule of the target user to determine whether the target user is an illegal user, where the illegal determination rule is used to apply an illegal determination rule corresponding to the target user based on the type of the target user, so as to predict the user type more accurately. In some embodiments, the method further includes step S109 (not shown), and in step S109, the network device determines the violation determination rule of the target user. On the premise of determining the violation judgment rule of the target user, a basis is provided for improving the accuracy of detecting the user type based on the violation judgment rule subsequently. In some embodiments, the determining the violation decision rule for the target user includes: and the network equipment determines the violation judgment rule of the target user according to the user behavior phase information of the target user. In some embodiments, the determining the violation determination rule of the target user according to the user behavior phase information of the target user includes:

and matching the user behavior stage information of the target user in the mapping relation between the stage information and the violation judgment rule to determine the violation judgment rule of the target user. Wherein the user behavior phase information includes at least any one of:

1) when the user does not generate social behaviors in the social application, determining that the user is in a new user registration stage;

2) when the user generates social behaviors in the social application, but the time for generating the social behaviors is less than a first day threshold (for example, 3 days), determining that the user is in a stage of a vegetable and bird user;

3) when a user generates social behaviors in a social application, and the time for generating the social behaviors is greater than a first day threshold (e.g., 3 days) but less than a second day threshold (e.g., one week), determining that the user is in a middle user stage;

4) when the user generates social behaviors in the social application, but the time for generating the social behaviors is greater than or equal to a second day threshold (for example, one week), determining that the user is in a qualified user stage; the network device stores the mapping relationship between the user behavior stage information and the violation determination rule, and the mapping relationship is as follows:

1) and a new user registration stage: 100% is determined by the user equipment characteristics of the user and the user characteristics;

2) and (3) a vegetable and bird user stage: the user equipment characteristics and the user characteristics of the user are determined in 50 percent, the user behavior characteristics are determined in 50 percent, and the behavior characteristics in less than 3 days are complemented by 0;

3) and (3) a middle-level user stage: 25% by user equipment characteristics and user characteristics of the user + 75% by user behavior characteristics;

4) and (3) qualification user stage: 100% is determined by the user behavior characteristics. Here, the network device may determine the violation determination rule of the target user, and on the premise that the first violation user determination model includes a first determination model and a second determination model, the detecting the user data information based on the first violation user determination model and the violation determination rule of the target user includes at least one of:

1) if the target user is in a new registered user stage: and applying a first judgment model of 100% and a second judgment model of 0% to obtain the probability that the target user is the illegal user, so as to determine whether the target user is the illegal user.

2) If the target user is in the stage of the vegetable and bird user: and applying a first judgment model of 50% + a second judgment model of 50% to obtain the probability that the target user is the illegal user, so as to determine whether the target user is the illegal user.

3) If the target user is in a middle-level user stage: and applying 25% of the first judgment model + 75% of the second judgment model to obtain the probability that the target user is the illegal user, so as to determine whether the target user is the illegal user.

4) If the target user is in the stage of the qualified user: applying a first decision model of 100% to derive a probability that the target user is an offending user, thereby determining whether the target user is an offending user. Thereby making an accurate judgment of the users at different stages.

In some embodiments, the first violation user determination model further comprises a preset violation determination rule; the first organization collects model data information including user behavior phase information for a plurality of users. For example, in the process of training the first violation judgment model, the model data information collected by the first organization includes the user device samples of the multiple users, the user behavior samples of the multiple users, and the user behavior stage information of the multiple users, when the first violation user judgment model trained based on the model data information is used for detecting the subsequent input user data, the corresponding violation judgment rule is determined directly according to the user behavior stage information in the user data, and the violation judgment rule is combined with the first judgment model and the second judgment model, so as to output the most accurate violation user probability information according to the user behavior stage, calculating the violation user probability information according to the violation judgment template can be automatically performed in the first violation user judgment model, or can be subsequently calculated after obtaining the first judgment model and the second judgment model, the former improves the calculation efficiency and the subsequent accelerated model training efficiency.

Fig. 4 shows a network device for detecting a user type based on a block chain according to an embodiment of the present application, which includes a one-to-one module 101, a two-to-two module 102, a three-to-one module 103, a four-to-one module 104, and a one-to-five module 105.

The one-to-one module 101 is configured to determine a first illegal user determination model uploaded to a block chain by a first node, where the first node is a node corresponding to a first organization, the first illegal user determination model includes organization identification information of the first organization, and the first illegal user determination model is generated by training model data information of the first node. Wherein the first organization may be a company that collects user data in owned social products, and the first organization may correspond to an organization identification information indicating the organization, for example, the organization identification information includes a registered name or a default organization number (e.g., an assigned ID of the organization) of the organization; the blockchain is a decentralized distributed database, which is not tied to any centralized server, but is composed of millions of "small servers" and "nodes", where a node generally refers to a computer that downloads relevant cryptocurrency to participate in a peer-to-peer network, for example, computers in a blockchain network include a mobile phone, a mining machine, and a server. The person operating a node may be a normal wallet user, a miner, and multiple people collaborating, storing, and verifying, and the people may all be nodes of a blockchain. For example, the terminal devices responsible for maintaining the operation of the network may be referred to as nodes, and each node may be capable of obtaining a copy of the complete or partial record. Here, the first organization is taken as a node in the blockchain (for example, an operation subject of the first organization in the blockchain is represented by the first node), and the first node acquires user data information collected by the first organization and trains the data information through the neural network to generate a first illegal user judgment model corresponding to the first organization.

A second module 102, configured to obtain download record information for downloading the first illegal user determination model from the blockchain, where the download record information includes organization identifier information corresponding to one or more second organizations that download the first illegal user determination model, respectively; the first illegal user determination model in the blockchain is an open resource, the second organization can directly download the model from the blockchain, the second organization can be a company other than the first organization, the first organization is an owner of the first illegal user determination model, and the first illegal user determination model can be directly updated inside the first organization. The network device determines download record information of the first illegal user judgment model, and the download record information may also include download number information of the first illegal user judgment model.

A third module 103, configured to determine one or more second illegal user determination models corresponding to one or more second nodes, where the one or more second nodes are respectively uploaded to the blockchain, where the one or more second nodes are used to characterize the one or more second organizations, each of the one or more second illegal user determination models is matched with organization identification information of the corresponding second organization, and each second illegal user determination model is determined by updating the first illegal user determination model with model data incremental information of the corresponding second node. For example, the network device determines, according to the download record information, one or more second organizations that download the first illegal user determination model, and the presence of at least one of the one or more second organizations may directly use the first illegal user determination model for user type detection, for example, a second node corresponding to the at least one second organization inputs the collected user data owned by the organization into the first illegal user determination model to detect the user type of the corresponding user; or the first illegal user determination model may be updated by the presence of at least one second node corresponding to one of the one or more second organizations, for example, each of the at least one second organizations inputs the collected incremental information of the model data owned by the organization (for example, all or part of the user data collected by each second organization) into the first illegal user determination model through the corresponding second node to train the first illegal user determination model so as to obtain a second illegal user determination model corresponding to each second organization, which is more accurate for detecting the user type of the user owned by each corresponding second organization since each second illegal user determination model is trained based on the user data owned by each second organization, the training process of each second organization on the first illegal user judgment model may refer to the specific steps of training the first organization to generate the first illegal user judgment model (for example, model data increment information is respectively input into the first judgment model and the second judgment model for training so as to update the first judgment model and the second judgment model, and the updated first judgment model and the updated second judgment model are used as one second illegal user judgment model), and no repetition is performed here. After one or more second illegal user determination models corresponding to one or more second organizations, one or more second nodes corresponding to the one or more second organizations upload the one or more second illegal user determination models into the block chain, wherein each second illegal user determination model comprises an organization identifier of the corresponding second organization, and the organization identifier is used for subsequently marking a corresponding second organization trained model.

A fourth module 104, configured to receive a user detection request sent by a user device of a target organization, where the user detection request includes organization identification information of an organization to which a violation determination model requested to be used belongs and user data information of a target user provided by the target organization. The target organization may be any company, and the user equipment of the target organization sends a user detection request to the network equipment, where the network equipment may be a server corresponding to any node in the block chain, and the network equipment may acquire operation information of any node in the block chain. In response to the user detection request, the network device obtains, from the blockchain, the violation determination model corresponding to the organization according to the organization identification information of the organization to which the violation determination model requested to be used belongs, where, for example, the violation determination model is generated by the organization after downloading other violation determination models from the blockchain and updating the other violation determination models with model data increment information of the organization.

A fifth module 105, configured to, in response to the user detection request, detect the user data information according to the illegal user determination model corresponding to the organization identifier to determine whether the target user is an illegal user. For example, on the premise that the network device obtains the illegal user determination model corresponding to the organization identifier from the blockchain, the network device inputs the user data information into the illegal user determination model to determine the target user, where the user data information includes an application list in the user device of the target user, a model of the user device, user identifier information of the user, and behavior information of the target user in social applications. And if the violation probability information output by the first violation user judgment model is greater than a preset probability threshold, the network equipment determines that the corresponding user is a violation user.

Here, the specific implementation of the above one-to-one module 101, the two-to-one module 102, the one-to-three module 103, the one-to-four module 104, and the one-to-five module 105 is the same as or similar to the embodiment of step S101, step S102, step S103, step S104, and step S105 in fig. 2, and therefore, the detailed description is omitted, and the detailed implementation is incorporated herein by reference.

In some embodiments, the corresponding one or more second nodes of the one or more second organizations in the blockchain are extension nodes below the first node. The operation of the one or more second nodes corresponding to the one or more second organizations in the block chain as the extension nodes under the first node is the same as or similar to the embodiment shown in fig. 2, and therefore, the description is omitted, and the operation is incorporated herein by reference.

In some embodiments, the network device further includes step S106 (not shown), in step S106, the network device determines contribution information of one or more second organizations corresponding to the one or more second illegal user determination models according to the download record information of the one or more second illegal user determination models;

determining reward information available to the one or more second organizations according to the contribution information, wherein the reward information is used for writing the blockchain into the one or more second nodes. The specific implementation manner of the sixth module 106 is the same as or similar to the embodiment of the step S106, and therefore, the detailed description is omitted, and the detailed implementation manner is included herein by reference.

In some embodiments, the determining, according to the download record information of the one or more second illegal user determination models, contribution information of one or more second organizations corresponding to the one or more second illegal user determination models includes:

acquiring downloading frequency information in the downloading record information of the one or more second violation user judgment models;

and determining contribution information of one or more second organizations corresponding to the one or more second illegal user judgment models according to the downloading frequency information, wherein the downloading frequency information is in direct proportion to the contribution information. The operation of determining the contribution information of the one or more second organizations corresponding to the one or more second illegal user determination models according to the download record information of the one or more second illegal user determination models is the same as or similar to that of the embodiment shown in fig. 2, and therefore, the operation is not repeated and is included herein by reference.

In some embodiments, the network device further includes a seventh module 107 (not shown), the seventh module 107 configured to obtain one or more third illegal user determination models uploaded to the block chain and updated based on the one or more second illegal user determination models, where each of the one or more third illegal user determination models matches organization identification information of a corresponding third organization;

repeating the steps until one or more Nth illegal user judgment models which are uploaded to the block chain and updated based on the one or more Nth-1 illegal user judgment models are obtained, wherein each Nth illegal user judgment model in the one or more Nth illegal user judgment models is matched with the corresponding organization identifier of the Nth organization, and N is an integer greater than 2;

determining contribution information of one or more organizations corresponding to the tracking mark information according to the tracking mark information of each Nth illegal user judgment model in the one or more Nth illegal user judgment models. The specific implementation manner of the seventh module 107 is the same as or similar to the embodiment of the step S107, and therefore, the detailed description is omitted, and the detailed implementation manner is incorporated herein by reference.

In some embodiments, the determining, from the tracking marker information of each nth violation user determination model of the one or more nth violation user determination models, contribution information of one or more organizations corresponding to the tracking marker information includes:

determining tracking marker information for each Nth violation user decision model of the one or more Nth violation user decision models;

performing data statistics on one or more organizations corresponding to the tracking mark information according to the tracking mark information of each Nth illegal user judgment model;

determining corresponding contribution information from statistics of the one or more organizations, wherein the statistics are proportional to the contribution information. The operation of determining the contribution information of the one or more organizations corresponding to the tracking flag information according to the tracking flag information of each nth illegal user determination model in the one or more nth illegal user determination models is the same as or similar to that of the embodiment shown in fig. 2, and therefore, the operation is not repeated and is included herein by reference.

In some embodiments, the performing data statistics on one or more tissues corresponding to the tracking marker information according to the tracking marker information of each nth violation user determination model includes:

acquiring one or more organization identification information corresponding to the tracking mark information of each Nth illegal user judgment model;

determining one or more corresponding organizations according to the one or more organization identification information;

and accumulating the occurrence times of each piece of organization identification information in the one or more organizations to complete data statistics of the one or more organizations. The operation of performing data statistics on one or more organizations corresponding to the tracking flag information according to the tracking flag information of each nth illegal user determination model is the same as or similar to that of the embodiment shown in fig. 2, and therefore, is not repeated herein, and is included herein by reference.

In some embodiments, the network device further includes an eight module 108 (not shown), and an eight module 108 configured to upload the model data information of the first node and the model data delta information to the blockchain. The specific implementation manner of the eight module 108 is the same as or similar to the embodiment of the step S108, and therefore, the detailed description is omitted, and the detailed implementation manner is incorporated herein by reference.

In some embodiments, the first violation user determination model includes a first determination model and a second determination model. Operations of the first violation user determination model including the first determination model and the second determination model are the same as or similar to those of the embodiment shown in fig. 2, and therefore are not repeated herein, and are incorporated herein by reference.

In some embodiments, the first decision model is generated from user device samples of a plurality of users via machine learning training, wherein the user device sample of each user includes a list of applications in the user device of the user, a user device model number, and user identification information of the user, and the user device samples of the plurality of users belong to the model data information collected by the first organization. The operation of the first decision model is the same as or similar to that of the embodiment shown in FIG. 2, and therefore is not described herein again, and is incorporated herein by reference.

In some embodiments, the first decision model is generated from user device samples of a plurality of users via machine learning training, including:

classifying the user equipment samples of the plurality of users to determine a positive sample and a negative sample, wherein the positive sample comprises the user equipment sample of the non-violation user, and the negative sample comprises the user equipment sample of the violation user;

and performing machine learning on the positive sample and the negative sample to generate the first judgment model, wherein the first judgment model is used for outputting probability information that the user is the illegal user type. The operation of the first decision model generated by the machine learning training of the ue samples of the users is the same as or similar to that of the embodiment shown in fig. 2, and therefore is not repeated herein, and is incorporated herein by reference.

In some embodiments, the second decision model is generated by machine learning training of user behavior samples of a plurality of users, the user behavior sample of each user includes behavior data of the user in social software M days before the current time period, where M is a positive integer, and the user behavior samples of the plurality of users belong to the model data information collected by the first organization. The operation of the second decision model is the same as or similar to that of the embodiment shown in FIG. 2, and therefore is not described herein again, and is incorporated herein by reference.

In some embodiments, the second decision model is generated from user behavior samples of a plurality of users via machine learning training, including:

classifying the user behavior samples of the plurality of users to determine a positive sample and a negative sample, wherein the positive sample comprises the user behavior sample of the non-violation user, and the negative sample comprises the user behavior sample of the violation user;

and performing machine learning according to the positive sample and the negative sample to generate the second judgment model, wherein the second judgment model is used for outputting probability information that the user is in an illegal user type in M days after the current time period, and M is a positive integer. The operation of the second decision model generated by the machine learning training of the user behavior samples of the users is the same as or similar to that of the embodiment shown in fig. 2, and therefore, the description is omitted, and the description is incorporated herein by reference.

In some embodiments, if the organization identification information of the organization to which the violation determination model used by the request belongs includes the organization identification information of the first organization;

a fourth module 104, configured to receive a user detection request sent by a user equipment of a target organization, where the user detection request includes organization identification information of the first organization and user data information of a target user provided by the target organization;

a fifth module 105, configured to, in response to the detection request, detect the user data information according to the first illegal user determination model and the illegal determination rule of the target user to determine whether the target user is an illegal user. The operation of the organization identification information of the organization to which the violation determination model used in the request belongs, including the organization identification information of the first organization, is the same as or similar to the embodiment shown in fig. 2, and therefore, the operation is not repeated and is included herein by reference.

In some embodiments, the network device further includes a nine module 109 (not shown), and a nine module 109, for determining the violation determination rule of the target user. The specific implementation manner of the nine module 109 is the same as or similar to the embodiment of the step S109, and therefore, the detailed description is omitted, and the detailed implementation manner is included herein by reference.

In some embodiments, the determining the violation decision rule for the target user includes:

and determining the violation judgment rule of the target user according to the user behavior phase information of the target user. The operation of determining the rule for violation determination of the target user is the same as or similar to that of the embodiment shown in fig. 2, and therefore is not repeated here, and is incorporated herein by reference.

In some embodiments, the determining the violation determination rule of the target user according to the user behavior phase information of the target user includes:

and matching the user behavior stage information of the target user in the mapping relation between the user behavior stage information and the violation judgment rule to determine the violation judgment rule of the target user. The operation of determining the violation determination rule of the target user according to the user behavior phase information of the target user is the same as or similar to that of the embodiment shown in fig. 2, and therefore, the details are not repeated, and are included herein by reference.

In some embodiments, the first violation user determination model further comprises a preset violation determination rule; the first organization collects model data information including user behavior phase information for a plurality of users. The related first violation user judgment model further comprises a preset violation judgment rule; the operation of the model data information collected by the first organization including the user behavior phase information of a plurality of users is the same as or similar to the embodiment shown in fig. 2, and therefore, the description is omitted, and the description is incorporated herein by reference.

In addition to the methods and apparatus described in the embodiments above, the present application also provides a computer readable storage medium storing computer code that, when executed, performs the method as described in any of the preceding claims.

The present application also provides a computer program product, which when executed by a computer device, performs the method of any of the preceding claims.

The present application further provides a computer device, comprising:

one or more processors;

a memory for storing one or more computer programs;

the one or more computer programs, when executed by the one or more processors, cause the one or more processors to implement the method of any preceding claim.

FIG. 5 illustrates an exemplary system that can be used to implement the various embodiments described herein;

in some embodiments, as shown in FIG. 5, the system 300 can be implemented as any of the devices in the various embodiments described. In some embodiments, system 300 may include one or more computer-readable media (e.g., system memory or NVM/storage 320) having instructions and one or more processors (e.g., processor(s) 305) coupled with the one or more computer-readable media and configured to execute the instructions to implement modules to perform the actions described herein.

For one embodiment, system control module 310 may include any suitable interface controllers to provide any suitable interface to at least one of processor(s) 305 and/or any suitable device or component in communication with system control module 310.

The system control module 310 may include a memory controller module 330 to provide an interface to the system memory 315. Memory controller module 330 may be a hardware module, a software module, and/or a firmware module.

System memory 315 may be used, for example, to load and store data and/or instructions for system 300. For one embodiment, system memory 315 may include any suitable volatile memory, such as suitable DRAM. In some embodiments, the system memory 315 may include a double data rate type four synchronous dynamic random access memory (DDR4 SDRAM).

For one embodiment, system control module 310 may include one or more input/output (I/O) controllers to provide an interface to NVM/storage 320 and communication interface(s) 325.

For example, NVM/storage 320 may be used to store data and/or instructions. NVM/storage 320 may include any suitable non-volatile memory (e.g., flash memory) and/or may include any suitable non-volatile storage device(s) (e.g., one or more Hard Disk Drives (HDDs), one or more Compact Disc (CD) drives, and/or one or more Digital Versatile Disc (DVD) drives).

NVM/storage 320 may include storage resources that are physically part of the device on which system 300 is installed or may be accessed by the device and not necessarily part of the device. For example, NVM/storage 320 may be accessible over a network via communication interface(s) 325.

Communication interface(s) 325 may provide an interface for system 300 to communicate over one or more networks and/or with any other suitable device. System 300 may wirelessly communicate with one or more components of a wireless network according to any of one or more wireless network standards and/or protocols.

For one embodiment, at least one of the processor(s) 305 may be packaged together with logic for one or more controller(s) (e.g., memory controller module 330) of the system control module 310. For one embodiment, at least one of the processor(s) 305 may be packaged together with logic for one or more controller(s) of the system control module 310 to form a System In Package (SiP). For one embodiment, at least one of the processor(s) 305 may be integrated on the same die with logic for one or more controller(s) of the system control module 310. For one embodiment, at least one of the processor(s) 305 may be integrated on the same die with logic for one or more controller(s) of the system control module 310 to form a system on a chip (SoC).

In various embodiments, system 300 may be, but is not limited to being: a server, a workstation, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet, a netbook, etc.). In various embodiments, system 300 may have more or fewer components and/or different architectures. For example, in some embodiments, system 300 includes one or more cameras, a keyboard, a Liquid Crystal Display (LCD) screen (including a touch screen display), a non-volatile memory port, multiple antennas, a graphics chip, an Application Specific Integrated Circuit (ASIC), and speakers.

It should be noted that the present application may be implemented in software and/or a combination of software and hardware, for example, implemented using Application Specific Integrated Circuits (ASICs), general purpose computers or any other similar hardware devices. In one embodiment, the software programs of the present application may be executed by a processor to implement the steps or functions described above. Likewise, the software programs (including associated data structures) of the present application may be stored in a computer readable recording medium, such as RAM memory, magnetic or optical drive or diskette and the like. Additionally, some of the steps or functions of the present application may be implemented in hardware, for example, as circuitry that cooperates with the processor to perform various steps or functions.

In addition, some of the present application may be implemented as a computer program product, such as computer program instructions, which when executed by a computer, may invoke or provide methods and/or techniques in accordance with the present application through the operation of the computer. Those skilled in the art will appreciate that the form in which the computer program instructions reside on a computer-readable medium includes, but is not limited to, source files, executable files, installation package files, and the like, and that the manner in which the computer program instructions are executed by a computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Computer-readable media herein can be any available computer-readable storage media or communication media that can be accessed by a computer.

Communication media includes media by which communication signals, including, for example, computer readable instructions, data structures, program modules, or other data, are transmitted from one system to another. Communication media may include conductive transmission media such as cables and wires (e.g., fiber optics, coaxial, etc.) and wireless (non-conductive transmission) media capable of propagating energy waves such as acoustic, electromagnetic, RF, microwave, and infrared. Computer readable instructions, data structures, program modules, or other data may be embodied in a modulated data signal, for example, in a wireless medium such as a carrier wave or similar mechanism such as is embodied as part of spread spectrum techniques. The term "modulated data signal" means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. The modulation may be analog, digital or hybrid modulation techniques.

By way of example, and not limitation, computer-readable storage media may include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. For example, computer-readable storage media include, but are not limited to, volatile memory such as random access memory (RAM, DRAM, SRAM); and non-volatile memory such as flash memory, various read-only memories (ROM, PROM, EPROM, EEPROM), magnetic and ferromagnetic/ferroelectric memories (MRAM, FeRAM); and magnetic and optical storage devices (hard disk, tape, CD, DVD); or other now known media or later developed that can store computer-readable information/data for use by a computer system.

An embodiment according to the present application comprises an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the apparatus to perform a method and/or a solution according to the aforementioned embodiments of the present application.

It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the apparatus claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.

Claims

1. A method for detecting user types based on a block chain is applied to network equipment, wherein the method comprises the following steps:

2. The method of claim 1, wherein the corresponding one or more second nodes of the one or more second organizations in the blockchain are extension nodes below the first node.

3. The method of claim 2, wherein the method further comprises:

determining contribution information of one or more second organizations corresponding to the one or more second illegal user judgment models according to the downloading record information of the one or more second illegal user judgment models;

determining reward information available to the one or more second organizations according to the contribution information, wherein the reward information is used for writing the blockchain into the one or more second nodes.

4. The method according to claim 3, wherein the determining contribution information of one or more second organizations corresponding to the one or more second illegal user determination models according to the download record information of the one or more second illegal user determination models comprises:

and determining contribution information of one or more second organizations corresponding to the one or more second illegal user judgment models according to the downloading frequency information, wherein the downloading frequency information is in direct proportion to the contribution information.

5. The method of claim 2 or 3, wherein the method further comprises:

obtaining one or more third illegal user judgment models which are uploaded to the block chain and updated based on the one or more second illegal user judgment models, wherein each third illegal user judgment model in the one or more third illegal user judgment models is matched with the corresponding organization identification information of the third organization;

determining contribution information of one or more organizations corresponding to the tracking mark information according to the tracking mark information of each Nth illegal user judgment model in the one or more Nth illegal user judgment models.

6. The method of claim 5, wherein the determining, from tracking marker information of each Nth illegal user decision model of the one or more Nth illegal user decision models, contribution information of one or more organizations corresponding to the tracking marker information comprises:

determining corresponding contribution information from statistics of the one or more organizations, wherein the statistics are proportional to the contribution information.

7. The method of claim 6, wherein the performing data statistics on one or more organizations corresponding to the tracking marker information according to the tracking marker information of the Nth illegal user determination model comprises:

and accumulating the occurrence times of each piece of organization identification information in the one or more organizations to complete data statistics of the one or more organizations.

8. The method of claim 1, wherein the method further comprises:

and uploading the model data information of the first node and the model data increment information to a block chain.

9. The method of claim 1, wherein the first violation user determination model comprises a first determination model and a second determination model.

10. The method of claim 9, wherein the first decision model is generated from user device samples of a plurality of users via machine learning training, wherein the user device sample of each user includes a list of applications in the user device of the user, a user device model number, and user identification information of the user, the user device samples of the plurality of users belonging to the model data information collected by the first organization.

11. The method of claim 10, wherein the first decision model is generated by machine learning training of user device samples of a plurality of users, comprising:

and performing machine learning on the positive sample and the negative sample to generate the first judgment model, wherein the first judgment model is used for outputting probability information that the user is the illegal user type.

12. The method of claim 9, wherein the second decision model is generated by machine learning training of user behavior samples of a plurality of users, the user behavior sample of each user comprising behavior data of the user in social software M days before the current time period, wherein M is a positive integer, the user behavior samples of the plurality of users belonging to the model data information collected by the first organization.

13. The method of claim 12, wherein the second decision model is generated by machine learning training of user behavior samples of a plurality of users, comprising:

and performing machine learning according to the positive sample and the negative sample to generate the second judgment model, wherein the second judgment model is used for outputting probability information that the user is in an illegal user type in M days after the current time period, and M is a positive integer.

14. The method according to any one of claims 9 to 13, wherein if the organization identification information of the organization to which the violation determination model used by the request belongs includes the organization identification information of the first organization;

the receiving a user detection request sent by a user device of a target organization, where the user detection request includes organization identification information of an organization to which a violation determination model requested to be used belongs and user data information of a target user provided by the target organization, includes:

receiving a user detection request sent by user equipment of a target organization, wherein the user detection request comprises organization identification information of the first organization and user data information of a target user provided by the target organization;

the responding to the user detection request, detecting the user data information according to the illegal user judgment model corresponding to the organization identifier to determine whether the target user is an illegal user, including:

and responding to the detection request, and detecting the user data information according to the first illegal user judgment model and the illegal judgment rule of the target user to determine whether the target user is an illegal user.

15. The method of claim 14, wherein the method further comprises:

and determining the violation judgment rule of the target user.

16. The method of claim 15, wherein the determining the violation decision rule for the target user comprises:

and determining the violation judgment rule of the target user according to the user behavior phase information of the target user.

17. The method of claim 16, wherein the determining the violation decision rule for the target user according to the user behavior phase information of the target user comprises:

and matching the user behavior stage information of the target user in the mapping relation between the user behavior stage information and the violation judgment rule to determine the violation judgment rule of the target user.

18. The method of claim 9, wherein the first violating user decision model further includes preset violating decision rules; the first organization collects model data information including user behavior phase information for a plurality of users.

19. An apparatus for detecting a user type based on a block chain, the apparatus comprising:

a processor; and

a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the method of any of claims 1 to 18.

20. A computer-readable medium storing instructions that, when executed by a computer, cause the computer to perform operations of any of the methods of claims 1-18.