57 results about "Information filtering system" patented technology

The invention relates to a system for filtering messages—the system includes a seed filter having associated therewith a false positive rate and a false negative rate. A new filter is also provided for filtering the messages, the new filter is evaluated according to the false positive rate and the false negative rate of the seed filter, the data used to determine the false positive rate and the false negative rate of the seed filter are utilized to determine a new false positive rate and a new false negative rate of the new filter as a function of threshold. The new filter is employed in lieu of the seed filter if a threshold exists for the new filter such that the new false positive rate and new false negative rate are together considered better than the false positive and the false negative rate of the seed filter.

A trust-based communication and information filtering system having rating features is user customizable. It is a system in which the raters remain anonymous. The anonymous ratings mimic real life person-to-person recommendation methods wherein recommendations are personal and cannot be controlled by persons or items being rated. The system uses contextually meaningful rating which are filtered explicitly by the end-user or implicitly based upon the environment of the end-user to facilitate discovery and minimize the potential for fraud and deception. Trust networks are constructed between the participants and the rating or information filtered or weighted according to the user's relative trust of the raters in the system. Ratings made by the inventive system can be for goods, services, people, businesses or virtually any item that can be rated and/or recommended.

The invention discloses a fraud information filtering system on the basis of the feature identification, which comprises a client and a server which are connected by a network. The client comprises a feature identification subsystem, a classification filtering subsystem and an information interception center; the feature identification subsystem is arranged in front of the classification filtering subsystem and is used for identifying fraud information; the classification filtering subsystem is used for identifying junk information; the information interception center is used for intercepting the fraud information and the junk information which are identified by the two subsystems; and the server is provided with a safety service cloud center and is used for monitoring the process of the client and carrying out data synchronism with the client by the network. The invention also discloses a fraud information filtering method on the basis of the system. According to the fraud information filtering system and the fraud information method, by feature detection, the fraud information with larger hazard is firstly filtered out before the junk information is filtered; and by the process linkage of the client and the server, a user is further prevented from accessing a malicious website, so that the probability that the fund account of the user is stolen is reduced.

The invention provides an ordering strategy-based information filtering system, which relates to the technical field of information filtering, and solves the problems of inconsistency between an optimization objective and a filtering problem evaluating indicator, the deviation of a model optimization result and restricted performance in the conventional information filtering model. The information filtering system of the invention consists of a training model, a filter and a feature weight library, wherein a method for identifying a new information unit by the filter comprises the following steps: converting an information filtering problem into an ordering problem; performing optimization aiming at a core evaluating indicator 1-ROCA; establishing an ordering strategy-based information filtering model, wherein the ordering strategy-based information filtering model adopts an ordering logistic regression learning algorithm and comprehensively uses a TONE strategy-based parameter weight updating algorithm and resampling technology to obtain a weight parameter and obtain a prediction score value of the new information unit; and judging the attribute of a new mail according to the result of comparison of the prediction score with a predetermined threshold. The method of the invention can be applied to various information filtering and information push systems.

An embodiment of the invention provides an information checking method and device. The information checking method includes acquiring user-submitted information to be published, and judging whether users are white-list users recorded in a preset user whitelist or not, wherein the information submitted by the white-list users to be submitted can be published without checking; if the users are whitelist users, importing the information to be published into a publishable information database for publishing; if the users are not whitelist users, importing the information to be published into to-be-checked information database so as to check the information to be published by a bad information filtering system. Workload of a platform server and platform operating cost can be reduced, and information publishing speed of the whitelist users is increased.

The invention provides an image fingerprint extracting method, an image fingerprint-based information filtering method and an image fingerprint-based information filtering system. The image fingerprint extracting method comprises the following steps: S1: performing interpolation processing on an original image; S2: blocking the image after the interpolation processing, and performing DCT conversion; S3: performing RGB grey scale processing on converted pictures; S4: quantizing an image result after the grey scale processing; S5, performing lossless compression on the image and outputting a binary sequence; and S6, performing serialized recombination on the binary sequence to obtain the image fingerprint. By using the methods and the system, the speed for identifying and processing data service contents can be greatly improved so that the real-time monitoring of full traffic flow of operator services becomes possible.

The invention discloses an information filtration method and a system for improving the reality of network information and the reliability of network business. The information filtration system of the invention determines a price distribution range according the price designated in goods information of each type of goods and divides the range into a plurality of price intervals; a price control interval is determined according to the proportion between the distributed quantity of goods information in each price interval and the total amount of goods information or the proportion between the distributed quantity of goods in each price interval and the total number of goods, wherein, the price control interval includes part or all of price intervals which have proportions beyond a threshold value; when receiving goods information, the information filtration system can judge whether the goods price designated in the goods information falls into the price control interval and accordingly make corresponding treatment. The system comprises a price control interval confirmation device and an information filtration device.

The invention discloses an information filtering system used for solving the problem that a large number of processing resources are consumed when the misjudgment rate is reduced based on a manual review system in the prior art. The information filtering system comprises an information filtering server and a positive feedback secondary filtering server, wherein the information filtering server is used for filtering an information set to be filtered according to a preset information filtering mechanism and outputting a first information set composed of determined suspicious information; the positive feedback secondary filtering server is used for obtaining the first information set output by the information filtering server, and respectively judging whether each piece of information in the first information set is matched with misjudged information characteristics according to a preset misjudged information characteristic library; the information matched with the misjudged information characteristics is released; the misjudged information characteristics are extracted from misjudged information which is misjudged as the suspicious information. The invention further discloses an information filtering method and device.

The invention discloses a system and a method for filtering the text information of a webpage. The system comprises a webpage browsing terminal, a proxy server, a network host and a text filtering center module, wherein the webpage browsing terminal receives, analyzes and sends a target request through a browser; the proxy server receives the target request, sends the target request to the network host, acquires returned source code information and sends the source code information to the text filtering center module for filtering; meanwhile, the proxy server is used for receiving a filtering result which is returned by the text filtering center module; the network host is used for receiving the target request and returning the source code information; and the text filtering center module is used for analyzing, filtering and determining the source code information and returning the filtering result. The invention has the advantages that: by using an object-oriented programming idea, a text is filtered and developed; by combining various data structures, the system is fully optimized; modules are independent of one another; and the reusability and the expandability of the system are greatly improved.

The invention provides a control method for setting an obstruction for junk information, which comprises the following steps: a, determining the credit rating of a user; b, determining the attribute of an identifying code according to the credit rating; and c, providing the identifying code to the user. The invention further provides a control device for setting the obstruction for the junk information, which comprises a first determining device, a second determining device and a first providing device, wherein the first determining device is used for determining the credit rating of the user; the second determining device is used for determining the attribute of the identifying code according to the credit rating; and the first providing device is used for providing the identifying code for the user. Through providing identifying codes with different attributes, such as different character lengths, for different users, the obstruction is set for the issuing of the junk information; simultaneously, the identifying code which is input easily is provided for a high-credit user; and the experience extent of the user is improved. The control method and the control device can be widely applicable to information filtering systems; through using the control method and the control device, the obstruction for the issuing of the information is set for a potential junk information issuer; and the issuing amount of the junk information in a network environment is reduced effectively.

Organization definition information M31 is stored in an organization definition information storage unit 31, contents M33 to be provided to a user is stored in a contents storage unit 33 and filter definition information M22 which is sent from a filter definition information generation unit 22 is stored in a filter definition information storage unit 32. A filtering execution unit 23 obtains information M10c on the contents, in which necessary information is stored, from the user, obtains filter definition information M32 on the contents, specified by the information M10c, from the filter definition information storage unit 32, obtains user's organization definition information M31, specified by filter definition information M32, from an organization definition information storage unit 31, builds a filter, and executes filtering to the contents M33.

The invention provides a method for filtering address book information based on a privacy policy. The method comprises the following steps: S10, making the privacy policy including four elements, namely a source, information, a target and a white list, wherein the source is a privacy protected object; the information is the protected field attribute; the target is a target object that the policy takes effect; the white list is the exception in the target object; and the required privacy policy is configured according to the four elements; and S20, obtaining address book data to be filtered, screening the privacy policy corresponding to a current operation user, filtering the address book data according to the privacy policy, and outputting an address book data list after privacy information is filtered. The invention further provides a system for filtering the address book information based on the privacy policy. Inconvenience due to the fact that the privacy information is shielded compulsively in the prior art can be solved; and the privacy filtering flexibility is improved.

The invention discloses a generalized zero-sample target classification method and device based on external distribution sample detection and related equipment. According to the method, an external distribution sample detector is trained by utilizing data of known classes and corresponding class semantic attributes, and each class is expressed as von Mises-Fisher (vMF) distribution in an implicitspace, so that a flow pattern boundary of each class is obtained. According to the flow pattern boundary of the known class, the provided external distribution sample detector can distinguish the characteristics of the unknown class from the characteristics of the known class. Therefore, the generalized zero sample classification problem can be simplified into a supervised classification problem and a traditional zero sample target classification problem, the feature confusion problem and the deviation problem in the generalized zero sample classification problem are avoided, and therefore thegeneralized zero sample classification performance is greatly improved. The method can be applied to an application environment which lacks training data and needs to identify unknown samples, such as an intelligent robot system, an intelligent recommendation system, a social media information filtering system and the like.

The invention relates to a method for querying a real MAC address corresponding to an IP through the IP by spanning networks, which comprises the following steps that: a host computer A acquires a network data packet through the Ethernet; an IP address needing acquiring an MAC address is extracted from the data packet; whether the extracted IP address is in the same VLAN as the host computer A or not is detected, and if the extracted IP address is in the same VLAN as the host computer A, an ARP or NETBIOS request is transmitted to the IP address to query the MAC address of the IP address; and the host computer A files the acquired MAC address and then the flow is ended. Compared with the prior art, the method can not only enable computer information security auditing systems or computer information filtering systems to restore data above the IP in the data packet, but also help the systems to acquire real MAC addresses.

The invention provides a network information filtering system of a WM string matching parallel algorithm based on MPI. The network information filtering system is characterized in that S1, a multi-core system is initialized, and a data message queue and a message identification queue are initialized; S2, cache messages are parallely loaded to the data message queue, and the messages are parallelyforwarded; S3, the WM algorithm is adopted to screen the data message queue parallely, and is used to investigate the message identification queue; S4, according to the network bandwidth and the loadof the multi-core system, instruction control based on message transmission is realized. The parallel improvement of the WM algorithm is carried out to realize the parallel processing of the messages,and the investigation content in the message can be identified, and a control module is used to optimize and design the calculation resources of the multi-core system and the bandwidth allocation, and therefore message processing speed is accelerated, and the message forwarding function is effectively improved; the network information filtering system is especially suitable for the filtering of the messages and the investigation of the content in the network information safety field, and degradation of performance caused by network attacks is prevented.

The invention belongs to the field of intelligent information filtering, in particular to a computer artificial intelligence information filtering system. An existing information filtering server generates a large amount of heat after working for a long time and is inconvenient to lose, the performance of the information filtering server is influenced; display cannot be carried out during heat dissipation; whether the information filtering server dissipates heat or not is uncertain; the following scheme is provided, the system comprises a filtering server, two top boxes are welded to the top of the filtering server, first holes are formed in the bottoms of the top boxes, two second holes are formed in the tops of the filtering server, the first holes are communicated with the correspondingsecond holes, two third holes are formed in the bottoms of the top boxes, two fourth holes are formed in the tops of the top boxes, and the third holes are communicated with the corresponding fourthholes. The LED lamp is good in practicability, when heat dissipation is needed, the heat dissipation opening can be automatically opened for heat dissipation, when heat dissipation is not needed, theheat dissipation opening can be automatically closed, and a good display effect is achieved.

A system and method for controlled introduction of noise to information filtering, comprises requesting, directly or indirectly, infatuation by a user having a user profile, obtaining the requested information, generating the noise related to the requested information and the user profile, and presenting the requested information and the noise in an information stream. Generating can further comprise finding aggregate profiles relevant to the user profile, obtaining the noise from non-overlapping parts of the aggregate profiles, and prioritizing the noise based on predefined rules. In one embodiment, each of the aggregate profiles comprises at least one characteristic found in the user profile. The aggregate profiles can be constructed using data mining or data aggregation mechanisms. In one embodiment, the noise is generated using random selection or complex selection algorithms.

The invention relates to the field of data filtering, in particular to an artificial intelligence information filtering system for a computer. The system comprises a data filtering model constructionmodule, which is used for generating a corresponding training parameter set based on an input filtering keyword group, realizing construction of a data filtering model based on the training parameterset, and realizing sequencing and series connection of the data filtering models based on the incidence relation among the filtering keyword groups; a data filling module, which is used for realizingdata filling processing based on an incomplete big data filling algorithm of deep learning; and a data filtering module, which is used for realizing filtering and classification of the data based on the series-connected data filtering model group. According to the method, filtering and classification of the data are achieved based on the data filtering models which are sequentially connected in series, each data filtering model corresponds to one data storage node, different data sets under various filtering standards can be obtained through one-time filtering, and the working efficiency of the system is greatly improved.

The invention provides an artificial intelligence information filtering system for a computer. The artificial intelligence information filtering system comprises a field definition module which firstly determines to-be-demanded information, defines a to-be-exported field description, carries out the coding according to a preset byte code, and transmits a coding byte to a control module, a point location establishing module which is used for determining a positioning code of each piece of field information according to the corresponding field, and a processing module which combines the field information with the positioning code and assembles the field information into the field information with the positioning code, wherein the positioning codes are in one-to-one correspondence with the corresponding field information, and the field information can be uniquely determined; and the data format of the field information is a format of a header + the positioning code + the field code. According to the artificial intelligence information filtering system for the computer, in the information filtering process, the positioning codes are adopted for increasing and sequentially circulating,so that sequential updating of the data after information filtering is achieved, and the data does not need to be returned to the data starting end again, and repeated calculation of a program is notneeded.