CN111199002A - Information processing method and device - Google Patents

Information processing method and device Download PDF

Info

Publication number
CN111199002A
CN111199002A CN201911299125.8A CN201911299125A CN111199002A CN 111199002 A CN111199002 A CN 111199002A CN 201911299125 A CN201911299125 A CN 201911299125A CN 111199002 A CN111199002 A CN 111199002A
Authority
CN
China
Prior art keywords
data node
similarity
information
information source
determined
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201911299125.8A
Other languages
Chinese (zh)
Inventor
张熙
裴中跃
吴旭
方滨兴
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing University of Posts and Telecommunications
Original Assignee
Beijing University of Posts and Telecommunications
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing University of Posts and Telecommunications filed Critical Beijing University of Posts and Telecommunications
Priority to CN201911299125.8A priority Critical patent/CN111199002A/en
Publication of CN111199002A publication Critical patent/CN111199002A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking

Abstract

The embodiment of the invention provides an information processing method and device. The scheme is as follows: acquiring an information source to be determined and information to be processed issued by the information source to be determined on different platforms in a preset network; the preset network is constructed according to the structural similarity and the content similarity among a plurality of data nodes generated by information issued by a plurality of information sources on different platforms; calculating the similarity between the information source to be determined and a target information source in a preset network according to the structural similarity and the content similarity; determining the category of the information source to be determined according to the similarity and the category of the target information source; and processing the information to be processed according to the category of the information source to be determined. By the technical scheme provided by the embodiment of the invention, the accuracy of information identification is improved, and the loss caused by information identification errors is reduced.

Description

Information processing method and device
Technical Field
The present invention relates to the field of internet technologies, and in particular, to an information processing method and apparatus.
Background
With the continuous development of internet technology, the internet is full of a great deal of information. Especially in different social platforms a lot of information is present every moment. The method also enables a large amount of network rumors, false advertisements or junk information and the like to appear in the network, and is particularly important for reducing the propagation of the information, reducing the harm to the society, finding the information in time and blocking the propagation of the information.
Currently, most of the identification of network rumors, false advertisements, or spam in the network is focused on identifying such information. However, for massive network information, extremely high accuracy is required in the information identification process, and even a small error will bring about a great loss.
Disclosure of Invention
Embodiments of the present invention provide an information processing method and apparatus, so as to improve accuracy of information identification and reduce loss caused by information identification errors. The specific technical scheme is as follows:
the embodiment of the invention provides an information processing method, which comprises the following steps:
acquiring an information source to be determined and information to be processed issued by the information source to be determined on different platforms in a preset network; the preset network is constructed according to the structural similarity and the content similarity among a plurality of data nodes generated by information issued by a plurality of information sources on different platforms;
calculating the similarity between the information source to be determined and a target information source in the preset network according to the structural similarity and the content similarity;
determining the category of the information source to be determined according to the similarity and the category of the target information source;
and processing the information to be processed according to the category of the information source to be determined.
Optionally, before obtaining the information source to be determined in the preset network and the information to be processed issued by the information source to be determined on different platforms, the method further includes:
generating a plurality of data nodes according to information issued by a plurality of information sources on different platforms;
calculating the structural similarity between every two data nodes by using a Path simulation (PathSim) algorithm;
determining a first feature vector corresponding to each content information by using a term Frequency-Inverse text Frequency index (TF-IDF) algorithm according to the content information corresponding to each data node, and calculating the content similarity between each two data nodes according to the first feature vector;
and constructing a preset network according to the structural similarity and the content similarity between every two data nodes.
Optionally, the step of calculating the structural similarity between every two data nodes by using the PathSim algorithm includes:
calculating the structural similarity between every two data nodes by using the following formula:
Figure BDA0002321409790000021
Figure BDA0002321409790000022
wherein x represents a data node with type x, y represents a data node with type y, P represents a unary path P, s (x, y | P) represents the similarity between the data node with type x and the data node with type y under the unary path P, and Px→xFor the path instances between type x data nodes and type x data nodes, py→yFor instance of a path between a node of type y and a node of type y, px→yIs a path instance between an x-type data node and a y-type data node, | | is the number of path instances, px→y:px→ye.P is a path example from the x type data node to the y type data node satisfying P, Px→x:px→xe.P is the path instance from the x type data node to the x type data node satisfying P, Py→y:py→yE.g. P as y type data node satisfying PAnd S (x, y) is the structural similarity between the x type data node and the y type data node, and P is a meta path set.
Optionally, the step of calculating the similarity between the information source to be determined and the target information source in the preset network according to the structural similarity and the content similarity includes:
selecting a target information source from a preset network;
determining a second feature vector of the information source to be determined and a third feature vector of the target information source by using a preset objective function after iteration; the preset objective function is determined according to the structural similarity and the content similarity between every two data nodes in the preset network;
and calculating the similarity between the second feature vector and the third feature vector.
Optionally, the preset objective function OamlneExpressed as:
Oamlne＝Owithin+α1*Ocross+α2*Oattr+Oclass
Figure BDA0002321409790000031
Figure BDA0002321409790000032
Figure BDA0002321409790000033
wherein, OwithinFor structural similarity in layers, α1To preset a first hyperparameter, Ocrossα for similarity of interlayer structure2To preset a second hyperparameter, OattrFor text similarity between nodes, OclassFor the preset regularization term of the cross-platform information,
Figure BDA0002321409790000034
viis a node corresponding to the ith information source, L is a set of labeled nodes, w is a preset parameter set, u is a preset parameter setiIs a node viCharacteristic vector of (y)iIs the node viIs a label vector of |2For two-norm operation, g is the number of layers of the predetermined network, osIs a data node in the predetermined network, otIs another data node in the predetermined network, (o)s,ot)∈ElRepresents the data node osAnd said data node otSet of edges belonging to layer l of said predetermined network, S (o)s,ot) For the data node osAnd said data node otStructural similarity between them, log (-) is a base 10 logarithmic operation, p (o)s,ot) For the data node osAnd said data node otRepresents the data node osAnd said data node otThe weight of the edge in between,
Figure BDA0002321409790000041
exp is the base e exponential operation, T is the transpose operation,
Figure BDA0002321409790000042
for the data node osIs determined by the feature vector of (a),
Figure BDA0002321409790000043
as a data node osD (i, j) ═ 1 denotes a connection with an edge between the ith and jth layers in the predetermined network, EijFor the set of edges between the nodes of the i-th and j-th layers in the pre-defined network, (o)s,ot)∈EijFor the data node osAnd said data node otThe edge belongs to the set of edges between the nodes of the ith layer and the jth layer in the preset network, p (o)s|ot) For the data node osAnd said data node otThe second-order similarity of (a) to (b),
Figure BDA0002321409790000044
os′for the data node osAny data node in the edge, C (o)s,ot) For the data node osAnd said data node otInter-content similarity.
An embodiment of the present invention further provides an information processing apparatus, where the apparatus includes:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring an information source to be determined in a preset network and information to be processed issued by the information source to be determined on different platforms; the preset network is constructed according to the structural similarity and the content similarity among a plurality of data nodes generated by information issued by a plurality of information sources on different platforms;
the first calculation module is used for calculating the similarity between the information source to be determined and a target information source in the preset network according to the structural similarity and the content similarity;
the determining module is used for determining the category of the information source to be determined according to the similarity and the category of the target information source;
and the processing module is used for processing the information to be processed according to the category of the information source to be determined.
Optionally, the apparatus further comprises:
the generating module is used for generating a plurality of data nodes according to information issued by a plurality of information sources on different platforms;
the second calculation module is used for calculating the structural similarity between every two data nodes by using a PathSim algorithm;
the third calculation module is used for determining a first feature vector corresponding to each content information by using a TF-IDF algorithm according to the content information corresponding to each data node, and calculating the content similarity between every two data nodes according to the first feature vector;
and the construction module is used for constructing the preset network according to the structural similarity and the content similarity between every two data nodes.
Optionally, the second calculating module is specifically configured to calculate a structural similarity between each two data nodes by using the following formula:
Figure BDA0002321409790000051
Figure BDA0002321409790000052
wherein x represents a data node with type x, y represents a data node with type y, P represents a unary path P, s (x, y | P) represents the similarity between the data node with type x and the data node with type y under the unary path P, and Px→xFor the path instances between type x data nodes and type x data nodes, py→yFor instance of a path between a node of type y and a node of type y, px→yIs a path instance between an x-type data node and a y-type data node, | | is the number of path instances, px→y:px→ye.P is a path example from the x type data node to the y type data node satisfying P, Px→x:px→xe.P is the path instance from the x type data node to the x type data node satisfying P, Py→y:py→yE.P is a path example from the y type data node to the y type data node which meets the requirement of P, S (x, y) is the structural similarity between the x type data node and the y type data node, and P is a meta-path set.
Optionally, the first computing module is specifically configured to select a target information source from a preset network; determining a second feature vector of the information source to be determined and a third feature vector of the target information source by using a preset objective function after iteration; the preset objective function is determined according to the structural similarity and the content similarity between every two data nodes in the preset network; and calculating the similarity between the second feature vector and the third feature vector.
Optionally, the preset objective function OamlneExpressed as:
Oamlne＝Owithin+α1*Ocross+α2*Oattr+Oclass
Figure BDA0002321409790000061
Figure BDA0002321409790000062
Figure BDA0002321409790000063
wherein, OwithinFor structural similarity in layers, α1To preset a first hyperparameter, Ocrossα for similarity of interlayer structure2To preset a second hyperparameter, OattrFor text similarity between nodes, OclassFor the preset regularization term of the cross-platform information,
Figure BDA0002321409790000064
viis a node corresponding to the ith information source, L is a set of labeled nodes, w is a preset parameter set, u is a preset parameter setiIs a node viCharacteristic vector of (y)iIs the node viIs a label vector of |2For two-norm operation, g is the number of layers of the predetermined network, osIs a data node in the predetermined network, otIs another data node in the predetermined network, (o)s,ot)∈ElRepresents the data node osAnd said data node otSet of edges belonging to layer l of said predetermined network, S (o)s,ot) For the data node osAnd said data node otStructural similarity between them, log (-) is a base 10 logarithmic operation, p (o)sOt) is the data node osAnd said data node otRepresents the data node osAnd said data node otThe weight of the edge in between,
Figure BDA0002321409790000065
exp is the base e exponential operation, T is the transpose operation,
Figure BDA0002321409790000066
for the data node osIs determined by the feature vector of (a),
Figure BDA0002321409790000067
as a data node osD (i, j) ═ 1 denotes a connection with an edge between the ith and jth layers in the predetermined network, EijFor the set of edges between the nodes of the i-th and j-th layers in the pre-defined network, (o)s,ot)∈EijFor the data node osAnd said data node otThe edge belongs to the set of edges between the nodes of the ith layer and the jth layer in the preset network, p (o)s|ot) For the data node osAnd said data node otThe second-order similarity of (a) to (b),
Figure BDA0002321409790000071
osis the data node osAny data node in the edge, C (o)s,ot) For the data node osAnd said data node otInter-content similarity.
The embodiment of the invention also provides electronic equipment, which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete mutual communication through the communication bus;
a memory for storing a computer program;
and a processor for implementing any of the above-described steps of the information processing method when executing the program stored in the memory.
An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the computer program implements any of the steps of the information processing method described above.
Embodiments of the present invention further provide a computer program product including instructions, which when run on a computer, cause the computer to execute any of the above-mentioned information processing methods.
The embodiment of the invention has the following beneficial effects:
the embodiment of the invention provides an information processing method and device, wherein an information source to be determined and information to be processed issued by the information source to be determined on different platforms are acquired in a preset network; the preset network is constructed according to the structural similarity and the content similarity among a plurality of data nodes generated by information issued by a plurality of information sources on different platforms; calculating the similarity between the information source to be determined and a target information source in a preset network according to the structural similarity and the content similarity; determining the category of the information source to be determined according to the similarity and the category of the target information source; and processing the information to be processed according to the category of the information source to be determined. According to the technical scheme provided by the embodiment of the invention, the target information source similar to the information source to be determined is determined according to the structural similarity and the content similarity between every two data nodes in the preset network, and the category of the information source to be determined is further determined, so that the similarity of different information sources on the network structure and the content information is fully considered when the category of the information source to be determined is determined, the accuracy of determining the category of the information source to be determined is improved, the accuracy of information identification is improved, and the loss caused by information identification errors is reduced.
Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a first flowchart of an information processing method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a default network according to an embodiment of the present invention;
FIG. 3 is a second flowchart of an information processing method according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to solve the problem of loss caused by poor information identification in the existing information identification process, the embodiment of the invention provides an information processing method. The method may be applied to any electronic device. In the method provided by the embodiment of the invention, the electronic equipment can acquire the information source to be determined in a preset network and the information to be processed issued by the information source to be determined on different platforms; the preset network is constructed according to the structural similarity and the content similarity among a plurality of data nodes generated by information issued by a plurality of information sources on different platforms; calculating the similarity between the information source to be determined and a target information source in a preset network according to the structural similarity and the content similarity; determining the category of the information source to be determined according to the similarity and the category of the target information source; and processing the information to be processed according to the category of the information source to be determined.
According to the method provided by the embodiment of the invention, the target information source similar to the information source to be determined is determined according to the structural similarity and the content similarity between every two data nodes in the preset network, and the category of the information source to be determined is further determined, so that the similarity of different information sources on the network structure and the content information is fully considered when the category of the information source to be determined is determined, the accuracy of determining the category of the information source to be determined is improved, the accuracy of information identification is improved, and the loss caused by information identification errors is reduced.
The following examples illustrate the present invention.
As shown in fig. 1, fig. 1 is a first flowchart illustrating an information processing method according to an embodiment of the present invention. The method specifically comprises the following steps.
Step S101, information sources to be determined and information to be processed issued by the information sources to be determined on different platforms are obtained in a preset network, wherein the preset network is constructed according to structural similarity and content similarity among a plurality of data nodes generated by information issued by a plurality of information sources on different platforms.
In this step, the electronic device may select an information source as an information source to be determined according to information sources included in the preset network, and acquire information issued by the information source to be determined on different platforms as information to be processed.
Regarding the preset network, the electronic device may obtain information published by a plurality of information sources on different platforms to construct the preset network. For convenience of understanding, fig. 2 is taken as an example for explanation, and fig. 2 is a schematic structural diagram of a default network according to an embodiment of the present invention. The preset network comprises three types of data nodes, namely platform nodes such as a platform 1 and a platform 2, information source nodes such as an information source 1-an information source 3, and information nodes such as an information 1-an information 4. The connection relationship between different types of data nodes can be represented as information issued by information sources on corresponding platforms. Taking the connection relationship among the platform 1, the information source 1 and the information 1 as an example, the connection relationship among the platform 1, the information source 1 and the information 1 is a path example, which is specifically indicated that the information source 1 publishes the information 1 on the platform 1. In addition, in the preset network shown in fig. 2, a connection relationship may exist between different information source nodes, or a connection relationship may not exist. For example, there is a connection between the information source 2 and the information source 1, but there is no connection between the information source 2 and the information source 1. In practical applications, the connection relationship between different information sources may be determined according to the behavior of the user, for example, the information source 1 and the information source 2 concern each other, and then the connection relationship exists between the information source 1 and the information source 2. For a specific construction method of the default network, see the following description, and will not be specifically described here.
In the embodiment of the present invention, each information source in the preset network has corresponding label information, that is, each information source node has corresponding label information. The tag information may be used to indicate the category of the information source. For example, the category of the information source distributing the network rumor, the false advertisement or the spam is determined as a high-quality information source, and the category of the information source distributing other information is determined as a common information source. If a label information in the preset network is a data node of a high-quality information source, the information source corresponding to the data node is an information source for releasing network rumors, false advertisements or junk information. Here, the tag information of each information source in the predetermined network is not particularly limited.
For convenience of description, the following description will be made by taking the categories of information sources as high-quality information sources and common information sources as examples.
In an optional embodiment, for other types of data nodes in the preset network, such as the platform node and the information node, the data nodes may or may not have corresponding tag information. Taking an information node as an example, when the information node has corresponding tag information, the tag information may be the release time of the information corresponding to the information node, an information keyword, and the like. Here, the tag information of other types of data nodes is not particularly limited.
In an optional embodiment, when the information source to be determined is obtained, the electronic device may obtain, as the information source to be determined, an information source in which tag information corresponding to an information source node in a preset network is a null value. For example, there exists a newly registered information source, and the tag information of the information source corresponding to the preset network is null, and the electronic device may determine the information source as the information source to be determined, so that according to the method provided by the embodiment of the present invention, the category of the information source is determined, the information issued by the information source is processed according to the determined category, the category of the information source is identified in time, and the issued information is processed according to the identified category, thereby reducing loss.
In another optional embodiment, when the information source to be determined is obtained, the electronic device may obtain, as the information source to be determined, an information source in which tag information corresponding to an information source node in a preset network is a common information source. In the internet, a certain risk of theft exists in a user account or user equipment and the like corresponding to each information source, and by determining the information source of which the label information is a common information source as the information source to be determined, the label information of the information source can be updated in time when the account or the equipment and the like corresponding to the information source are stolen, namely the category of the information source is updated, so that the accuracy of the category of each information source in a preset network is improved, the accuracy of information processing is improved, and the loss is reduced.
And step S102, calculating the similarity between the information source to be determined and the target information source in the preset network according to the structural similarity and the content similarity.
In this step, the electronic device may select a target information source in the preset network, and calculate the similarity between the information source to be determined and the target information source according to the structural similarity of each two data nodes in the preset network on the network structure and the content similarity of each two data nodes on the content information.
In the embodiment of the present invention, the target information source may be all information sources or part of information sources in a preset network except the information source to be determined. Specifically, the electronic device may select the target information source according to an actual application scenario, a user requirement, and the like. Here, the selection of the target information source is not particularly limited.
In an optional embodiment, in the step S102, the similarity between the information source to be determined and the target information source in the preset network is calculated according to the structural similarity and the content similarity, which may specifically include the following steps.
Step one, selecting a target information source from a preset network.
In this step, the electronic device may select, as the target information source, an information source whose tag information is a non-null value from a preset network.
For example, the electronic device may select, from a preset network, all information sources whose tag information is the high-quality information source and all information sources whose tag information is a common information source as target information sources.
And step two, determining a second feature vector of the information source to be determined and a third feature vector of the target information source by using the iterated preset target function. The preset objective function is determined according to the structural similarity and the content similarity between every two data nodes in the preset network.
In this step, the electronic device may determine a preset objective function according to the structural similarity and the content similarity between every two data nodes in the preset network. And performing multiple iterations on the preset objective function by utilizing the information issued by the plurality of information sources on different platforms and the category corresponding to each information source to obtain the well-iterated preset objective function. And determining a second eigenvector of the information source to be determined and a third eigenvector of each target information source according to a preset target function of the iteration number.
And step three, calculating the similarity between the second feature vector and the third feature vector.
In this step, the electronic device may calculate, according to the second feature and the third feature vector, a similarity between the second feature vector and each third feature vector, that is, a similarity between the information source to be determined and each target information source.
In an embodiment of the present invention, the electronic device may calculate the similarity between the second feature vector and the third feature vector according to a plurality of similarity algorithms. For example, the similarity calculation method such as euclidean distance, manhattan distance, and the like. Wherein, when the similarity is expressed by the distance, the greater the distance, the smaller the similarity. The smaller the distance, the greater the similarity.
In an alternative embodiment, the predetermined objective function O isamlneCan be expressed as:
Oamlne＝Owithin+α1*Ocross+α2*Oattr+Oclass
Figure BDA0002321409790000121
Figure BDA0002321409790000122
Figure BDA0002321409790000123
wherein, OwithinFor structural similarity in layers, α1To preset a first hyperparameter, Ocrossα for similarity of interlayer structure2To preset a second hyperparameter, OattrIs the text similarity between nodes, i.e. the content similarity between nodes, OclassFor the preset regularization term of the cross-platform information,
Figure BDA0002321409790000124
viis a node corresponding to the ith information source, L is a set of labeled nodes, w is a preset parameter set, u is a preset parameter setiIs a node viCharacteristic vector of (y)iIs a node viIs a label vector of |2For two-norm operation, g is the number of layers of the default network, osFor provisioning a data node in the network, otTo preset another data node in the network, (o)s,ot)∈ElRepresenting a data node osAnd a data node otSet of edges belonging to layer l of the preset network, S (o)s,ot) As a data node osAnd a data node otStructural similarity between them, log (-) is a base 10 logarithmic operation, p (o)s,ot) As a data node osAnd data sectionPoint otFirst order similarity of (d), representing data node osAnd a data node otThe weight of the edge in between,
Figure BDA0002321409790000125
exp is the base e exponential operation, T is the transpose operation,
Figure BDA0002321409790000126
as a data node osIs determined by the feature vector of (a),
Figure BDA0002321409790000127
as a data node osD (i, j) ═ 1 denotes a connection with an edge between the ith and jth layers in the predetermined network, EijFor a set of edges between nodes of the i-th and j-th layers in a predetermined network, (o)s,ot)∈EijFor the data node osAnd said data node otThe edge belongs to the set of edges between the nodes of the ith layer and the jth layer in the preset network, p (o)s|ot) As a data node osAnd a data node otThe second-order similarity of (a) to (b),
Figure BDA0002321409790000128
os′as a data node osAny data node in the edge, C (o)s,ot) As a data node osAnd a data node otInter-content similarity.
And step S103, determining the category of the information source to be determined according to the similarity and the category of the target information source.
In this step, the electronic device may determine, according to the similarity, that is, according to the similarity between the information source to be determined and each target information source, the category of the target information source similar to the information source to be determined as the category of the information source to be determined, in combination with the category corresponding to each target information source.
In an optional embodiment, in the step S103, determining the category of the information source to be determined according to the similarity and the category of the target information source may include the following steps.
Step one, acquiring a target information source with the similarity larger than a preset similarity threshold.
In this step, the electronic device may compare the similarity between the information source to be determined and the target information source in each preset network with a preset similarity threshold, and select the target information source with the similarity greater than the preset similarity threshold.
And step two, determining the number of the target information sources of each category in the target information sources with the similarity greater than a preset similarity threshold.
In this step, after the electronic device determines to acquire the target information sources with the similarity greater than the preset similarity threshold, the electronic device may count the number of the target information sources corresponding to each category in the acquired target information sources.
And step three, determining the category of the target information source with the largest quantity as the category of the information source to be determined.
In this step, the electronic device may determine the category as the category of the information source to be determined according to the category of the largest number of target information sources. For example, the number of target information sources having similarity greater than a preset similarity threshold with the information source to be determined is 100, wherein the categories of 90 target information sources are high-quality information sources, and the categories of 10 target information sources are common information sources. At this time, the electronic device may determine that the category of the information source to be determined is a high-quality information source.
And step S104, processing the information to be processed according to the category of the information source to be determined.
In this step, after determining the category of the information source to be determined, the electronic device may process the information to be processed, which is issued by the information source to be determined on different data platforms, according to the category.
In an optional embodiment, when the type of the information source to be determined is the high-quality information source, the electronic device may perform deletion processing, shielding processing, and the like on the information to be processed issued by the information source on different platforms. When the type of the information source to be determined is the common information source, the electronic device may not process the information to be processed issued by the information source on different platforms, that is, not delete or shield the information to be processed issued by the information source on different platforms.
In another optional embodiment, if the type of the information source to be determined is the high-quality information source and the information to be processed is currently issued by the information source, the electronic device may not allow the information to be processed issued by the information source. If the type of the information source to be determined is the common information source and the information to be processed is the information currently issued by the information source, the electronic device may allow the information source to normally issue the information to be processed.
In the embodiment of the invention, the electronic device can process the information to be processed in different processing modes according to different practical application scenes. Here, the processing method of the information to be processed is not particularly limited.
In summary, by using the method provided by the embodiment of the present invention, according to the structural similarity and the content similarity between every two data nodes in the preset network, the target information source similar to the information source to be determined is determined, and then the category of the information source to be determined is determined, so that when the category of the information source to be determined is determined, the similarities of different information sources on the network structure and the content information are fully considered, the accuracy of determining the category of the information source to be determined is improved, the accuracy of information identification is improved, and thus the loss caused by information identification errors is reduced.
In an optional embodiment, according to the information processing method shown in fig. 1, an embodiment of the present invention further provides an information processing method. As shown in fig. 3, fig. 3 is a second flowchart of the information processing method according to the embodiment of the present invention. The method specifically comprises the following steps.
Step S301, a plurality of data nodes are generated according to information issued by a plurality of information sources on different platforms.
In this step, the electronic device may obtain information published by the plurality of information sources on different platforms, and generate a plurality of data nodes according to each information source, the information published by each information source, and the platform corresponding to each information publication. That is, a plurality of information source nodes, platform nodes and information nodes are generated according to information issued by a plurality of information sources on different platforms.
In the embodiment of the invention, each information published by each information source on each platform can form a meta path. For example, information 1 published on platform 1 by information source 1 in fig. 2 may constitute a unary path. The electronic equipment can construct a meta-path set according to information issued by a plurality of information sources on different platforms, wherein each meta-path comprises different types of data nodes, namely information source nodes, platform nodes and information nodes.
Step S302, calculating the structural similarity between every two data nodes by using the PathSim algorithm.
In this step, the electronic device may calculate a structural similarity between every two data solutions in the meta-path set by using the PathSim algorithm.
In an alternative embodiment, the electronic device may calculate the structural similarity between each two data nodes by using the following formula:
Figure BDA0002321409790000151
Figure BDA0002321409790000152
wherein x represents a data node with type x, y represents a data node with type y, P represents a unary path P, s (x, y | P) represents the similarity between the data node with type x and the data node with type y under the unary path P, and Px→xFor the path instances between type x data nodes and type x data nodes, py→yFor instance of a path between a node of type y and a node of type y, px→yIs a path instance between an x-type data node and a y-type data node, | | is the number of path instances, px→y:px→ye.P is a path example from the x type data node to the y type data node satisfying P, Px→x:px→xe.P is the path instance from the x type data node to the x type data node satisfying P, Py→y:py→yE.P is a path example from the y type data node to the y type data node which meets the requirement of P, S (x, y) is the structural similarity between the x type data node and the y type data node, and P is a meta-path set.
P in the above formulax→y:px→y∈P，px→x:px→x∈P，py→y:py→yE P can be understood as q.q.e.Q.the set q.q.q.q can be understood as all path instances of Q. Qqqq ∈ Q | is the number of path instances included in the set { Q: qq ∈ Q }.
In the embodiment of the invention, the PathSim algorithm is a TOP-K similarity search algorithm based on meta-paths in a heterogeneous information network. Here, the PathSim algorithm is not specifically described.
Step S303, according to the content information corresponding to each data node, determining a first feature vector corresponding to each content information by using a TF-IDF algorithm, and according to the first feature vector, calculating the content similarity between every two data nodes.
In this step, the electronic device may determine, according to content information corresponding to each data node in the meta-path set, a first feature vector corresponding to each content information by using a TF-IDF algorithm. The electronic device may calculate content similarity of each two data nodes on the content information according to the first feature vector corresponding to each data node in the meta-path set.
In an alternative embodiment, after determining the first feature vector corresponding to each data node, the electronic device may calculate the content similarity C (x, y) between each two data nodes by using the following formula:
C(x,y)＝cos(x,y)
c (x, y) is content similarity between content information corresponding to the data node x and the data node y, and cos (·) is cosine operation.
In the embodiment of the present invention, the electronic device may further use another algorithm to determine the first feature vector corresponding to each data node, for example, a word2vec algorithm. In addition, the electronic device may also use another algorithm to calculate the content similarity between every two data nodes, for example, the above-mentioned algorithm such as the euclidean distance. Here, the algorithm used for the calculation of the similarity between the first feature vector and the content is not particularly limited.
And step S304, constructing a preset network according to the structural similarity and the content similarity between every two data nodes.
In this step, the electronic device may establish a connection relationship between different data nodes according to the structural similarity and the content similarity between every two data nodes, so as to obtain a preset network.
Step S305, obtaining an information source to be determined and information to be processed issued by the information source to be determined on different platforms in a preset network, wherein the preset network is constructed according to the structural similarity and the content similarity among a plurality of data nodes generated by the information issued by a plurality of information sources on different platforms.
And step S306, calculating the similarity between the information source to be determined and the target information source in the preset network according to the structural similarity and the content similarity.
Step S307, determining the category of the information source to be determined according to the similarity and the category of the target information source.
Step S308, processing the information to be processed according to the category of the information source to be determined.
The above steps S305 to S308 are the same as the above steps S101 to S104.
Based on the same inventive concept, according to the information processing method provided by the embodiment of the invention, the embodiment of the invention also provides an information processing device. As shown in fig. 4, fig. 4 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present invention. The apparatus includes the following modules.
The obtaining module 401 is configured to obtain an information source to be determined in a preset network and to-be-processed information issued by the information source to be determined on different platforms. The preset network is constructed according to the structural similarity and the content similarity among a plurality of data nodes generated by information issued by a plurality of information sources on different platforms.
The first calculating module 402 is configured to calculate a similarity between the information source to be determined and a target information source in a preset network according to the structural similarity and the content similarity.
The determining module 403 is configured to determine the category of the information source to be determined according to the similarity and the category of the target information source.
The processing module 404 is configured to process the information to be processed according to the category of the information source to be determined.
Optionally, the information processing apparatus may further include:
and the generating module is used for generating a plurality of data nodes according to the information issued by the plurality of information sources on different platforms.
And the second calculation module is used for calculating the structural similarity between every two data nodes by using the PathSim algorithm.
And the third calculation module is used for determining a first feature vector corresponding to each content information by using a TF-IDF algorithm according to the content information corresponding to each data node, and calculating the content similarity between every two data nodes according to the first feature vector.
And the construction module is used for constructing the preset network according to the structural similarity and the content similarity between every two data nodes.
Optionally, the second calculating module may be specifically configured to calculate a structural similarity between each two data nodes by using the following formula:
Figure BDA0002321409790000181
Figure BDA0002321409790000182
wherein x represents a data node with type x, y represents a data node with type y, P represents a unary path P, s (x, y | P) represents the similarity between the data node with type x and the data node with type y under the unary path P, and Px→xFor x type data node and x type data nodeInstance of path between points, py→yFor instance of a path between a node of type y and a node of type y, px→yIs a path instance between an x-type data node and a y-type data node, | | is the number of path instances, px→y:px→ye.P is a path example from the x type data node to the y type data node satisfying P, Px→x:px→xe.P is the path instance from the x type data node to the x type data node satisfying P, Py→y:py→yE.P is a path example from the y type data node to the y type data node which meets the requirement of P, S (x, y) is the structural similarity between the x type data node and the y type data node, and P is a meta-path set.
Optionally, the first calculating module 402 is specifically configured to select a target information source from a preset network; determining a second feature vector of an information source to be determined and a third feature vector of a target information source by using the iterated preset target function; the preset objective function is determined according to the structural similarity and the content similarity between every two data nodes in a preset network; and calculating the similarity between the second feature vector and the third feature vector.
Optionally, the preset objective function O isamlneCan be expressed as:
Oamlne＝Owithin+α1*Ocross+α2*Oattr+Oclass
Figure BDA0002321409790000183
Figure BDA0002321409790000184
Figure BDA0002321409790000191
wherein, OwithinFor structural similarity in layers, α1To preset a first hyperparameter, Ocrossα for similarity of interlayer structure2To preset a second hyperparameter, OattrFor text similarity between nodes, OclassFor the preset regularization term of the cross-platform information,
Figure BDA0002321409790000192
viis a node corresponding to the ith information source, L is a set of labeled nodes, w is a preset parameter set, u is a preset parameter setiIs a node viCharacteristic vector of (y)iIs a node viIs a label vector of |2For two-norm operation, g is the number of layers of the default network, osFor provisioning a data node in the network, otTo preset another data node in the network, (o)s,ot)∈ElRepresenting a data node osAnd a data node otSet of edges belonging to layer l of the preset network, S (o)s,ot) As a data node osAnd a data node otStructural similarity between them, log (-) is a base 10 logarithmic operation, p (o)s,ot) As a data node osAnd a data node otFirst order similarity of (d), representing data node osAnd a data node otThe weight of the edge in between,
Figure BDA0002321409790000193
exp is the base e exponential operation, T is the transpose operation,
Figure BDA0002321409790000194
as a data node osIs determined by the feature vector of (a),
Figure BDA0002321409790000195
as a data node osD (i, j) ═ 1 denotes a connection with an edge between the ith and jth layers in the predetermined network, EijFor a set of edges between nodes of the i-th and j-th layers in a predetermined network, (o)s,ot)∈EijFor the data node osAnd said data node otThe edge belongs to the set of edges between the nodes of the ith layer and the jth layer in the preset network, p (o)s|ot) As a data node osAnd a data node otThe second-order similarity of (a) to (b),
Figure BDA0002321409790000196
os′as a data node osAny data node in the edge, C (o)s,ot) As a data node osAnd a data node otInter-content similarity.
According to the device provided by the embodiment of the invention, the target information source similar to the information source to be determined is determined according to the structural similarity and the content similarity between every two data nodes in the preset network, and the category of the information source to be determined is further determined, so that the similarity of different information sources on the network structure and the content information is fully considered when the category of the information source to be determined is determined, the accuracy of determining the category of the information source to be determined is improved, the accuracy of information identification is improved, and the loss caused by information identification errors is reduced.
Based on the same inventive concept, according to the information processing method provided by the above embodiment of the present invention, an embodiment of the present invention further provides an electronic device, as shown in fig. 5, including a processor 501, a communication interface 502, a memory 503 and a communication bus 504, where the processor 501, the communication interface 502 and the memory 503 complete communication with each other through the communication bus 504;
a memory 503 for storing a computer program;
the processor 501, when executing the program stored in the memory 503, implements the following steps:
acquiring an information source to be determined and information to be processed issued by the information source to be determined on different platforms in a preset network; the preset network is constructed according to the structural similarity and the content similarity among a plurality of data nodes generated by information issued by a plurality of information sources on different platforms;
calculating the similarity between the information source to be determined and a target information source in a preset network according to the structural similarity and the content similarity;
determining the category of the information source to be determined according to the similarity and the category of the target information source;
and processing the information to be processed according to the category of the information source to be determined.
According to the electronic equipment provided by the embodiment of the invention, the target information source similar to the information source to be determined is determined according to the structural similarity and the content similarity between every two data nodes in the preset network, and the category of the information source to be determined is further determined, so that the similarity of different information sources on the network structure and the content information is fully considered when the category of the information source to be determined is determined, the accuracy of determining the category of the information source to be determined is improved, the accuracy of information identification is improved, and the loss caused by information identification errors is reduced.
The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component.
Based on the same inventive concept, according to the information processing method provided by the above embodiment of the present invention, an embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, and the computer program realizes the steps of any of the above information processing methods when executed by a processor.
Based on the same inventive concept, according to the information processing method provided by the above embodiment of the present invention, an embodiment of the present invention also provides a computer program product containing instructions that, when run on a computer, cause the computer to execute any of the information processing methods in the above embodiments.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for embodiments such as the apparatus, the electronic device, the computer-readable storage medium, and the computer program product, since they are substantially similar to the method embodiments, the description is simple, and for relevant points, reference may be made to part of the description of the method embodiments.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims (10)

1. An information processing method, characterized in that the method comprises:
acquiring an information source to be determined and information to be processed issued by the information source to be determined on different platforms in a preset network; the preset network is constructed according to the structural similarity and the content similarity among a plurality of data nodes generated by information issued by a plurality of information sources on different platforms;
calculating the similarity between the information source to be determined and a target information source in the preset network according to the structural similarity and the content similarity;
determining the category of the information source to be determined according to the similarity and the category of the target information source;
and processing the information to be processed according to the category of the information source to be determined.
2. The method according to claim 1, wherein before obtaining the information source to be determined in a preset network and the information to be processed issued by the information source to be determined on different platforms, the method further comprises:
generating a plurality of data nodes according to information issued by a plurality of information sources on different platforms;
calculating the structural similarity between every two data nodes by utilizing a path simulation PathSim algorithm;
determining a first feature vector corresponding to each content information by using a word frequency-inverse text frequency index (TF-IDF) algorithm according to the content information corresponding to each data node, and calculating the content similarity between every two data nodes according to the first feature vector;
and constructing a preset network according to the structural similarity and the content similarity between every two data nodes.
3. The method according to claim 2, wherein the step of calculating the structural similarity between each two data nodes by using the PathSim algorithm comprises:
calculating the structural similarity between every two data nodes by using the following formula:
Figure FDA0002321409780000011
Figure FDA0002321409780000012
wherein x represents a data node with type x, and y represents a data node with type yP denotes a meta path P, s (x, y | P) is the similarity between the x-type data node and the y-type data node under the meta path P, Px→xFor the path instances between type x data nodes and type x data nodes, py→yFor instance of a path between a node of type y and a node of type y, px→yIs a path instance between an x-type data node and a y-type data node, | | is the number of path instances, px→y：px→ye.P is a path example from the x type data node to the y type data node satisfying P, Px→x：px→xe.P is the path instance from the x type data node to the x type data node satisfying P, Py→y：py→yE.P is a path example from the y type data node to the y type data node which meets the requirement of P, S (x, y) is the structural similarity between the x type data node and the y type data node, and P is a meta-path set.
4. The method according to any one of claims 1 to 3, wherein the step of calculating the similarity between the information source to be determined and the target information source in the preset network according to the structural similarity and the content similarity comprises:
selecting a target information source from a preset network;
determining a second feature vector of the information source to be determined and a third feature vector of the target information source by using a preset objective function after iteration; the preset objective function is determined according to the structural similarity and the content similarity between every two data nodes in the preset network;
and calculating the similarity between the second feature vector and the third feature vector.
5. The method of claim 4, wherein the predetermined objective function OamlneExpressed as:
Oamlne＝Owithin+α1*Ocross+α2*Oattr+Oclass
Figure FDA0002321409780000021
Figure FDA0002321409780000022
Figure FDA0002321409780000023
wherein, OwithinFor structural similarity in layers, α1To preset a first hyperparameter, Ocrossα for similarity of interlayer structure2To preset a second hyperparameter, OattrFor text similarity between nodes, OclassFor the preset regularization term of the cross-platform information,
Figure FDA0002321409780000031
viis a node corresponding to the ith information source, L is a set of labeled nodes, w is a preset parameter set, u is a preset parameter setiIs a node viCharacteristic vector of (y)iIs the node viThe label vector, | | | non-calculation vision2For two-norm operation, g is the number of layers of the predetermined network, osIs a data node in the predetermined network, otIs another data node in the predetermined network, (o)s，ot)∈ElRepresents the data node osAnd said data node otSet of edges belonging to layer l of said predetermined network, S (o)s，ot) For the data node osAnd said data node otStructural similarity between them, log (-) is a base 10 logarithmic operation, p (o)s，ot) For the data node osAnd said data node otRepresents the data node osAnd said data node otThe weight of the edge in between,
Figure FDA0002321409780000032
exp is the base e exponential operation, T is the transpose operation,
Figure FDA0002321409780000033
for the data node osIs determined by the feature vector of (a),
Figure FDA0002321409780000035
as a data node osD (i, j) ═ 1 denotes a connection with an edge between the ith and jth layers in the predetermined network, EijFor the set of edges between the nodes of the i-th and j-th layers in the pre-defined network, (o)s，ot)∈EijFor the data node osAnd said data node otThe edge belongs to the set of edges between the nodes of the ith layer and the jth layer in the preset network, p (o)s|ot) For the data node osAnd said data node otThe second-order similarity of (a) to (b),
Figure FDA0002321409780000034
os′for the data node osAny data node in the edge, C (o)s，ot) For the data node osAnd said data node otInter-content similarity.
6. An information processing apparatus characterized in that the apparatus comprises:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring an information source to be determined in a preset network and information to be processed issued by the information source to be determined on different platforms; the preset network is constructed according to the structural similarity and the content similarity among a plurality of data nodes generated by information issued by a plurality of information sources on different platforms;
the first calculation module is used for calculating the similarity between the information source to be determined and a target information source in the preset network according to the structural similarity and the content similarity;
the determining module is used for determining the category of the information source to be determined according to the similarity and the category of the target information source;
and the processing module is used for processing the information to be processed according to the category of the information source to be determined.
7. The apparatus of claim 6, further comprising:
the generating module is used for generating a plurality of data nodes according to information issued by a plurality of information sources on different platforms;
the second calculation module is used for calculating the structural similarity between every two data nodes by utilizing a path simulation PathSim algorithm;
the third calculation module is used for determining a first feature vector corresponding to each content information by using a word frequency-inverse text frequency index TF-IDF algorithm according to the content information corresponding to each data node, and calculating the content similarity between every two data nodes according to the first feature vector;
and the construction module is used for constructing the preset network according to the structural similarity and the content similarity between every two data nodes.
8. The apparatus according to claim 7, wherein the second calculating module is specifically configured to calculate the structural similarity between each two data nodes by using the following formula:
Figure FDA0002321409780000041
Figure FDA0002321409780000042
wherein x represents a data node with type x, y represents a data node with type y, P represents a unary path P, s (x, y | P) represents the similarity between the data node with type x and the data node with type y under the unary path P, and Px→xFor the path instances between type x data nodes and type x data nodes, py→yFor instance of a path between a node of type y and a node of type y, px→yIs a path instance between an x-type data node and a y-type data node, | | is the number of path instances, px→y：px→ye.P is a path example from the x type data node to the y type data node satisfying P, Px→x：px→xe.P is the path instance from the x type data node to the x type data node satisfying P, Py→y：py→yE.P is a path example from the y type data node to the y type data node which meets the requirement of P, S (x, y) is the structural similarity between the x type data node and the y type data node, and P is a meta-path set.
9. The apparatus according to any one of claims 6 to 8, wherein the first computing module is specifically configured to select a target information source from a preset network; determining a second feature vector of the information source to be determined and a third feature vector of the target information source by using a preset objective function after iteration; the preset objective function is determined according to the structural similarity and the content similarity between every two data nodes in the preset network; and calculating the similarity between the second feature vector and the third feature vector.
10. The apparatus of claim 9, wherein the predetermined objective function O is setamlneExpressed as:
Oamlne＝Owithin+α1*Ocross+α2*Oattr+Oclass
Figure FDA0002321409780000051
Figure FDA0002321409780000052
Figure FDA0002321409780000053
wherein, OwithinFor structural similarity in layers, α1To preset a first hyperparameter, Ocrossα for similarity of interlayer structure2To preset a second hyperparameter, OattrFor text similarity between nodes, OclassFor the preset regularization term of the cross-platform information,
Figure FDA0002321409780000054
viis a node corresponding to the ith information source, L is a set of labeled nodes, w is a preset parameter set, u is a preset parameter setiIs a node viCharacteristic vector of (y)iIs the node viThe label vector, | | | non-calculation vision2For two-norm operation, g is the number of layers of the predetermined network, osIs a data node in the predetermined network, otIs another data node in the predetermined network, (o)s，ot)∈ElRepresents the data node osAnd said data node otSet of edges belonging to layer l of said predetermined network, S (o)s，ot) For the data node osAnd said data node otStructural similarity between them, log (-) is a base 10 logarithmic operation, p (o)s，ot) For the data node osAnd said data node otRepresents the data node osAnd said data node otThe weight of the edge in between,
Figure FDA0002321409780000061
exp is the base e exponential operation, T is the transpose operation,
Figure FDA0002321409780000062
for the data node osIs determined by the feature vector of (a),
Figure FDA0002321409780000063
as a data node osIs determined by the feature vector of (a),d (i, j) ═ 1 denotes a connection with an edge between the ith and jth layers in the preset network, EijFor the set of edges between the nodes of the i-th and j-th layers in the pre-defined network, (o)s，ot)∈EijFor the data node osAnd said data node otThe edge belongs to the set of edges between the nodes of the ith layer and the jth layer in the preset network, p (o)s|ot) For the data node osAnd said data node otThe second-order similarity of (a) to (b),
Figure FDA0002321409780000064
os′for the data node osAny data node in the edge, C (o)s，ot) For the data node osAnd said data node otInter-content similarity.
CN201911299125.8A 2019-12-17 2019-12-17 Information processing method and device Pending CN111199002A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911299125.8A CN111199002A (en) 2019-12-17 2019-12-17 Information processing method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911299125.8A CN111199002A (en) 2019-12-17 2019-12-17 Information processing method and device

Publications (1)

Publication Number Publication Date
CN111199002A true CN111199002A (en) 2020-05-26

Family

ID=70746562

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911299125.8A Pending CN111199002A (en) 2019-12-17 2019-12-17 Information processing method and device

Country Status (1)

Country Link
CN (1) CN111199002A (en)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102456062A (en) * 2010-11-04 2012-05-16 中国人民解放军国防科学技术大学 Community similarity calculation method and social network cooperation mode discovery method

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102456062A (en) * 2010-11-04 2012-05-16 中国人民解放军国防科学技术大学 Community similarity calculation method and social network cooperation mode discovery method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
裴中跃: "基于表示学习的社交网络谣言信息源发现技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Similar Documents

Publication Publication Date Title
Peng et al. Pythagorean fuzzy Choquet integral based MABAC method for multiple attribute group decision making
CN110168523B (en) Change monitoring cross-graph query
US8468146B2 (en) System and method for creating search index on cloud database
US20120023586A1 (en) Determining privacy risk for database queries
US8918382B1 (en) Learning common spelling errors through content matching
US20180218088A1 (en) Adjacency structures for executing graph algorithms in a relational database
CN110555172A (en) user relationship mining method and device, electronic equipment and storage medium
CN107679916A (en) For obtaining the method and device of user interest degree
TWI780355B (en) Damage assessment method and device for maintenance object, and electronic equipment
CN111639696A (en) User classification method and device
US9785724B2 (en) Secondary queue for index process
CN111209403B (en) Data processing method, device, medium and electronic equipment
CN112965943A (en) Data processing method and device, electronic equipment and storage medium
Khan et al. On uniform convergence of undiscounted optimal programs in the Mitra–Wan forestry model: the strictly concave case
CN111199002A (en) Information processing method and device
CN110827101A (en) Shop recommendation method and device
CN115758271A (en) Data processing method, data processing device, computer equipment and storage medium
CN114356885A (en) Intelligent matching method for scientific and technological service projects, storage medium and equipment
US20110131245A1 (en) Identifying a group of products relevant to data provided by a user
US8712995B2 (en) Scoring records for sorting by user-specific weights based on relative importance
CN112598507A (en) Excessive credit granting risk prediction system and method based on knowledge graph
CN112395510A (en) Method and device for determining target user based on activity
CN114328755B (en) Data writing method, data reading device and electronic equipment
CN110197056B (en) Relation network and associated identity recognition method, device, equipment and storage medium
US11500933B2 (en) Techniques to generate and store graph models from structured and unstructured data in a cloud-based graph database system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20200526