CN109635074B - Entity relationship analysis method and terminal equipment based on public opinion information - Google Patents

Entity relationship analysis method and terminal equipment based on public opinion information Download PDF

Info

Publication number
CN109635074B
CN109635074B CN201811343920.8A CN201811343920A CN109635074B CN 109635074 B CN109635074 B CN 109635074B CN 201811343920 A CN201811343920 A CN 201811343920A CN 109635074 B CN109635074 B CN 109635074B
Authority
CN
China
Prior art keywords
entity
nodes
relation
public
network
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.)
Active
Application number
CN201811343920.8A
Other languages
Chinese (zh)
Other versions
CN109635074A (en
Inventor
吴壮伟
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.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
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 Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Priority to CN201811343920.8A priority Critical patent/CN109635074B/en
Publication of CN109635074A publication Critical patent/CN109635074A/en
Application granted granted Critical
Publication of CN109635074B publication Critical patent/CN109635074B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G06F40/295—Named entity recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/01—Social networking

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Artificial Intelligence (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention provides an entity relation analysis method and terminal equipment based on public opinion information, which are applicable to the technical field of data processing, wherein the method comprises the following steps: respectively analyzing the acquired pieces of public opinion information to obtain a plurality of initial entity relation networks corresponding to the public opinion information, wherein a plurality of entity nodes and entity relations among the entity nodes are recorded in the entity relation networks; extracting public nodes contained in the entity relation network, wherein the public nodes are entity nodes which exist in at least two entity relation networks at the same time; and combining the entity relationship networks based on the public nodes until the entity relationship network obtained by combining does not contain the public nodes, thereby obtaining the combined entity relationship network. The embodiment of the invention fully realizes the deep analysis of all entity relations possibly related to the entity and realizes the deep analysis and tracking of the entity relation network.

Description

Entity relationship analysis method and terminal equipment based on public opinion information
Technical Field
The invention belongs to the technical field of data processing, and particularly relates to an entity relationship analysis method and terminal equipment based on public opinion information.
Background
The public opinion system can provide a query function of entity relationship for users, and the public opinion system can analyze the entity relationship of the entity to be queried on the public opinion information provided by the channel source and output a corresponding entity relationship analysis result only by inputting the entity name to be queried. The entity refers to people, places, institutions and the like in public opinion information, and the entity relationship refers to the relationship among the people, places and institutions, such as Zhang three is a wife of Liqu, beijing is a capital of China and the like.
In practical situations, the existing public opinion system can only analyze the entity relationship in a single piece of public opinion information, but because the information quantity provided by the single piece of public opinion information is extremely limited and the credibility of the single piece of public opinion information is difficult to be well ensured, only a limited relationship network among a plurality of entities is often obtained only according to the analysis of the single piece of public opinion information, the depth of analyzing and tracking the relationship network among the entities is shallow, the credibility of the obtained entity relationship network is low, and the increasing practical demands of users cannot be met.
Disclosure of Invention
In view of the above, the embodiment of the invention provides an entity relationship analysis method and terminal equipment based on public opinion information, so as to solve the problem that the public opinion system in the prior art cannot realize deep analysis and tracking of an entity relationship network.
A first aspect of an embodiment of the present invention provides a public opinion information-based entity relationship analysis method, including:
Respectively analyzing the acquired pieces of public opinion information to obtain a plurality of initial entity relation networks corresponding to the public opinion information, wherein a plurality of entity nodes and entity relations among the entity nodes are recorded in the entity relation networks;
extracting public nodes contained in the entity relation network, wherein the public nodes are entity nodes which exist in at least two entity relation networks at the same time;
and carrying out combination processing on the entity relationship networks based on the public nodes until the entity relationship networks obtained by combination do not contain the public nodes, thereby obtaining the entity relationship networks after combination.
A second aspect of the embodiment of the present invention provides a terminal device, where the terminal device includes a memory and a processor, where the memory stores a computer program that can be run on the processor, and the processor implements the following steps when executing the computer program.
Respectively analyzing the acquired pieces of public opinion information to obtain a plurality of initial entity relation networks corresponding to the public opinion information, wherein a plurality of entity nodes and entity relations among the entity nodes are recorded in the entity relation networks;
extracting public nodes contained in the entity relation network, wherein the public nodes are entity nodes which exist in at least two entity relation networks at the same time;
and carrying out combination processing on the entity relationship networks based on the public nodes until the entity relationship networks obtained by combination do not contain the public nodes, thereby obtaining the entity relationship networks after combination.
A third aspect of an embodiment of the present invention provides an entity relationship analysis apparatus based on public opinion information, including:
The network analysis module is used for respectively analyzing the acquired public opinion information to obtain a plurality of initial entity relation networks corresponding to the public opinion information, wherein a plurality of entity nodes and entity relations among the entity nodes are recorded in the entity relation networks;
the node extraction module is used for extracting public nodes contained in the entity relation network, wherein the public nodes are entity nodes which exist in at least two entity relation networks at the same time;
And the network merging module is used for merging the entity relationship networks based on the public nodes until the entity relationship network obtained by merging does not contain the public nodes, so as to obtain the entity relationship network after merging.
A fourth aspect of embodiments of the present invention provides a computer-readable storage medium comprising: a computer program is stored, characterized in that the computer program, when executed by a processor, implements the steps of the public opinion information based entity relationship analysis method as described above.
Compared with the prior art, the embodiment of the invention has the beneficial effects that: according to the embodiment of the invention, the public opinion information analysis is carried out to obtain the simple entity relation networks, the public nodes are extracted, the simple entity relation networks are combined according to the public nodes, and the analysis and combination of the entity relation networks are terminated until the public nodes are not included among all the entity relation networks, namely, the depth of all the entity relation networks is maximized, so that the deep analysis of all the entity relations possibly related to the entity is fully realized, and the deep analysis and tracking of the entity relation networks are realized.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic implementation flow chart of an entity relationship analysis method based on public opinion information according to an embodiment of the present invention;
fig. 2 is a schematic implementation flow chart of an entity relationship analysis method based on public opinion information according to a second embodiment of the present invention;
fig. 3 is a schematic implementation flow chart of an entity relationship analysis method based on public opinion information according to the third embodiment of the present invention;
fig. 4 is a schematic implementation flow chart of an entity relationship analysis method based on public opinion information according to a fourth embodiment of the present invention;
fig. 5 is a schematic implementation flow chart of an entity relationship analysis method based on public opinion information according to a fifth embodiment of the present invention;
fig. 6 is a schematic implementation flow chart of an entity relationship analysis method based on public opinion information according to the sixth embodiment of the present invention;
fig. 7 is a schematic structural diagram of an entity relationship analysis device based on public opinion information according to a seventh embodiment of the present invention;
Fig. 8 is a schematic diagram of a terminal device according to an eighth embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
In order to illustrate the technical scheme of the invention, the following description is made by specific examples.
For ease of understanding, embodiments of the invention will be briefly described herein: in the prior art, when the entity relation analysis in public opinion information is performed, the entity relation analysis is performed by directly using some existing natural language analysis algorithms, and because the existing natural language analysis algorithms can only analyze and process the content of a single article, the entity relation analysis of single public opinion information can only be realized in the prior art, and further the deep analysis and tracking of the entity relation network cannot be realized in the prior art.
Considering whether the analysis of the entity relationship network is deep enough, the most intuitive criterion is whether all the entities contained in the entity relationship network cannot establish entity relationship with the entities in other entity relationship networks, i.e. the entity relationship network and the other entity relationship networks do not have any public entity nodes, for example, it is assumed that two entity relationship networks of the entity relationship network A and the entity relationship network B are shared, wherein the entity relationship network A contains the person relationship among the person a, the person B, the person c and the person d, the entity relationship network B contains the person relationship among the person d, the person e, the person f and the person g, at this time, since both entity relationship networks contain the person d of the public node, the two descriptions can be further combined into one network through the relationship existing between the person d and the other entity, at this time, the analysis of both entity relationship networks at this time is not deep enough, and if the entity relationship network B only contains the person e, the person f and the person g of the two entity relationship is assumed, at this time, the two entity relationship networks cannot be connected through the entity relationship node, i.e, the analysis of the two entity relationship is realized, and the deep analysis of the deep analysis is realized.
Therefore, in order to realize deep analysis of the entity relationship network, the embodiment of the invention further extracts public nodes based on the simple entity relationship network obtained by single public opinion information analysis based on the prior art, and further merges the entity relationship networks based on the public nodes until no public node is included among the finally obtained entity relationship networks, so as to realize deep analysis and tracking of the entity relationship network, which is described in detail as follows:
fig. 1 shows a flowchart of an implementation of an entity relationship analysis method based on public opinion information according to an embodiment of the present invention, which is described in detail below:
S101, respectively analyzing the acquired public opinion information to obtain a plurality of initial entity relation networks corresponding to the public opinion information, wherein a plurality of entity nodes and entity relations among the entity nodes are recorded in the entity relation networks.
The public opinion information refers to news, blogs, information and the like acquired from channel sources. In the embodiment of the invention, the channel source for obtaining the public opinion information is selected and set by a technician according to actual conditions, including but not limited to social media, news websites, forums and the like.
In the embodiment of the present invention, firstly, analysis of entity relationship is performed on each piece of obtained public opinion information to obtain entity relationship networks included in each piece of public opinion information, for example, if a person a is assumed to have a friend b in one piece of public opinion information, then the entity relationship networks with corresponding person a and person b being in a friend relationship with each other can be obtained, but it should be understood that, not every piece of public opinion information necessarily includes entity relationships among a plurality of entities, for example, if a person a is assumed to be a singer in one piece of public opinion information, but the relationship between the person a and any other entity is not mentioned, then analysis of the public opinion information is not performed to obtain any entity relationship network. In consideration of the fact that more natural language analysis algorithms capable of performing entity relationship analysis exist in the prior art, such as a common entity relationship analysis algorithm based on a neural network, the embodiment of the invention does not limit a specifically used entity relationship analysis method, and can be set by a technician according to actual requirements.
S102, extracting public nodes contained in the entity relation network, wherein the public nodes are entity nodes which exist in at least two entity relation networks at the same time.
In the above example, assuming that the entity relationship network a includes the person relationships among the person a, the person B, the person c and the person d, and the entity relationship network B includes the person relationships among the person d, the person e, the person f and the person g, the person d is the public node in the two entity relationship networks. Because the number of the simple entity relation networks obtained by analysis in the embodiment of the invention is unknown, and the specific conditions of the entities contained in the entity relation networks cannot be predicted in advance, the number of the public nodes which can be extracted at the moment cannot be predicted in advance, and the number is determined according to the actual conditions of the entity relation networks.
S103, combining the entity relation networks based on the public nodes until the entity relation network obtained by combining does not contain the public nodes, and obtaining the entity relation network after combining.
In practical application, when one entity relation network and any other entity relation network do not have public nodes, the relation between each entity and other entities in the entity relation network can be extended, which is included in the entity relation network, namely, maximization of analysis of the entity-entity relation network under the existing public opinion information condition is realized. Therefore, after determining the public nodes included in the entity relationship network, in order to implement the deep analysis on the entity relationship network, the embodiment of the present invention merges the entity relationship networks including the public nodes until all the finally obtained entity relationship networks do not include any public nodes.
Specifically, when entity relationship network merging is performed, considering that the number of entity relationship networks in which one public node may exist simultaneously is not fixed, and the number of public nodes existing between different entity relationship networks cannot be determined, that is, in actual situations, due to the fact that the number of entity relationship networks obtained by analyzing public opinion information is large, the situation of the public nodes between the entity relationship networks obtained by final analysis is complex, therefore, when entity relationship network merging is performed, due to different actual requirements, a technician can select or set a merging method meeting the actual requirements of the technician, and is not limited herein, for example, when the technician wants to reduce the technical difficulty in merging, the technician can select from one entity relationship network including the public node, select one other entity relationship network including the public node, merge the public nodes of the two entity relationship networks to achieve network merging of the two entity relationship networks, and then detect whether the public node including the public node of the other entity relationship network is included after the entity relationship network is obtained, if the public node including the public node is included, the operation is repeated until the finally obtained merging network does not include any public node, and when the technician wants to improve the technical difficulty in merging, for the entity relationship network including the public node is selected, and if the entity relationship network including the public node is not included, and the public relationship network is obtained continuously merging network at the final time.
In this embodiment of the present invention, the number of the finally obtained entity relationship networks not including the public node is not determinable, that is, only one entity may be possible, or a plurality of entity relationship networks may be possible at the same time.
According to the embodiment of the invention, the public opinion information analysis is carried out to obtain the simple entity relation networks, the public nodes are extracted, the simple entity relation networks are combined according to the public nodes, and the analysis and combination of the entity relation networks are terminated until the public nodes are not included among all the entity relation networks, namely, the depth of all the entity relation networks is maximized, so that the deep analysis of all the entity relations possibly related to the entity is fully realized, and the deep analysis and tracking of the entity relation networks are realized.
In the second embodiment of the present invention, considering that the first embodiment of the present invention is a final entity relationship network obtained by merging based on public nodes on the basis of the entity relationship network obtained by analyzing each public opinion information, so that although the merging analysis of the entity relationship network is realized, a more deeply analyzed entity relationship network can be obtained, in the actual case, in the entity relationship network obtained by merging in this way, only the record of the entity relationship obtained by directly recording and analyzing the public opinion information can be realized, but the entity relationship without direct record in the public opinion information can not be obtained, for example, in the final entity relationship network, three children Zhang Si are provided, and father Zhang Wu are provided, and in this case, according to the first embodiment of the present invention, the analysis of the entity relationship network in the first embodiment of the present invention is not deep enough, and in order to realize the more deep analysis tracking of the entity relationship network, the second embodiment of the present invention further analyzes the entity relationship between the entity nodes included in the entity relationship network without public nodes based on the first embodiment of the entity relationship network obtained by the present invention, as shown in fig. 2, which includes:
S201, carrying out random combination on the entity nodes in the entity relation network after combination, and analyzing the entity relation between 2 entity nodes in each combination.
In order to reduce the task amount in the embodiment of the present invention, the combination of the entity nodes that have the entity relationship may not be considered when the two-to-two combination analysis is performed, for example, the three-to-one and Zhang Si-to-five in the above example have the entity relationship, and if the three nodes are analyzed in a two-to-two combination manner, only the Zhang Si +to-five combination in which the entity relationship does not exist may be analyzed, and two combinations of the three+to four and the three+to five may not be considered.
In order to realize the analysis of the entity relationship between the entity node combinations which have no entity relationship in the public opinion information, the embodiment of the invention can preset the entity relationship rule according to the possible condition of the entity relationship in the actual life, for example, a relative relationship rule can be set according to the actual relative relationship, and then whether the obtained entity node combinations meet the set entity relationship rule is judged, and if the relationship exists between Zhang Si and five, the entity relationship between the two combinations can be obtained at the moment according to the relative relationship rule. Wherein the specific preset entity relationship rules can be set by the technician at his own discretion, preferably, in order to achieve an in-depth analysis of the entity relationship network, the more and the better these entity relationship rules are set.
S202, updating the entity relationship in the combined entity relationship network based on the entity relationship among the 2 entity nodes in each combination obtained through analysis.
After obtaining the entity relations between the entity nodes, the entity relations are directly recorded in the merged entity relation network obtained in the first embodiment of the invention, so that the updating of the entity relations can be realized.
The embodiment of the invention breaks through the limitation that the relationship between the entity nodes can be obtained and determined only by analyzing single public opinion information in the prior art and the first embodiment of the invention, and realizes that even the entities appearing in different public opinion information can still obtain the corresponding entity relationship through reasonable entity relationship reasoning analysis, thereby enabling the embodiment of the invention to realize deeper analysis and tracking of the entity relationship network.
As a specific implementation manner of entity relationship network merging based on public nodes in the embodiment of the present invention, considering that the data size of public opinion information that can be obtained by a public opinion system in actual situations is extremely huge, the workload of the public opinion system is also very great when the public opinion system performs merging processing, in order to improve the merging efficiency, in the embodiment of the present invention, a plurality of public nodes are simultaneously used as merging starting points, and the merging of entity relationship networks to which a plurality of public nodes belong is synchronously performed, as shown in fig. 3, the third embodiment of the present invention includes:
S301, randomly selecting a plurality of public nodes, and respectively merging the entity relationship networks to which each public node belongs in the plurality of public nodes to obtain a plurality of merged entity relationship networks.
The specific number of the public nodes can be set by a technician, and the specific number is more than or equal to 2. Considering that the data size of public opinion information is very large in practical situations, the simple entity relation network obtained by analysis is also very large, so that the workload required when operations such as screening and searching are involved is very large. In order to reduce the workload during merging, a random selection method is adopted when the public nodes are selected in the embodiment of the invention, so that the workload caused by conditional screening is avoided as much as possible.
After the public nodes are selected, the entity relationship networks corresponding to the public nodes are queried, and the corresponding entity relationship networks are combined based on the public nodes, for example, the public node a exists in the entity relationship network A, the entity relationship network B and the entity relationship network C at the same time, and at the moment, the three entity relationship networks can be combined through the public node a. Wherein, considering that an entity relationship network may simultaneously contain several selected public nodes, it may be randomly allocated to one of the public nodes.
S302, detecting whether public nodes exist in the entity relation network after the merging.
Because one entity relationship network may include multiple public nodes at the same time, the combination of all entity relationship networks including the same public node cannot be realized at one time only by combining one public node, for example, the public node a exists in the entity relationship network a, the entity relationship network B and the entity relationship network C at the same time, but the entity relationship network a also exists in the public node B with the entity relationship network D, and if the entity relationship network a, the entity relationship network B and the entity relationship network C are combined according to the public node a, at this time, the combined entity relationship network must also exist in the entity relationship network B with the entity relationship network D, that is, the combined entity relationship network may still continue to be further analyzed.
S303, if the public nodes exist in the entity relation networks after the merging, returning to execute the operation of extracting the public nodes contained in the entity relation network based on the entity relation networks after the merging.
When the common node still exists in the merged entity relationship network, it is indicated that the merged entity relationship network may continue to perform merging analysis, so that the embodiment of the present invention may continue to return to the operation of extracting the common node in the first embodiment of the present invention, so as to continue merging the common node until no common node exists in the finally merged entity relationship network. And when the entity relation network after combination does not have a public node, the entity relation network after combination is not capable of combining, and deep analysis and tracking of the entity relation network are completed.
In the actual situation, the public opinion information data volume obtained by the public opinion system is extremely large, the quantity of the included entities is extremely large, and not all the entities can have certain entity relations directly or indirectly, so that when the merging is performed, a part of the obtained multiple merged entity relation networks possibly have no public nodes, but the other part still has public nodes, and only the entity relation network still having the public nodes needs to be returned to the operation step of extracting the public nodes in the first embodiment of the invention.
As an embodiment of the present invention, considering that in the actual situation, a single piece of public opinion information is not necessarily true, so that the credibility of the entity relationship obtained by analyzing the single piece of public opinion information is difficult to be ensured, and there is a high possibility that the entity relationship obtained by analyzing two pieces of public opinion information conflicts, for example, a person a is a father of a person B according to analysis of public opinion information a, but another person a is a person B grandpa according to analysis of public opinion information B, it is obvious that the two entity relationships are conflicting, and there is a wrong entity relationship, so that in order to ensure that the entity relationship in the entity relationship network obtained in the embodiment of the present invention is true and reliable, the embodiment of the present invention analyzes a combination of entity nodes having two or more entity relationships, and proposes a entity relationship having a problem therein, as shown in fig. 4, including:
S401, a first node group in the combined entity relation network is found, wherein the first node group is a combination of 2 entity nodes with the corresponding entity relation number being more than or equal to 2.
Because different public opinion information may record different entity relationships existing in the same two entity nodes, the node relationships may be the conflicting relationship in the analysis, or may be the node relationship without the conflict, for example, if it is assumed that person a is the father of person b according to public opinion information a analysis, person a is the person b colleague according to another public opinion information C analysis, at this time, there is no conflict between the two entity relationships, after merging, the relationships are recorded in the merged entity relationship network, and in order to find out the entity node combinations in which the number of the entity relationships is greater than or equal to 2, in the embodiment of the invention, all the entity node combinations are the two-by-two combinations between the entity nodes, that is, only two entity nodes are included.
S402, a second node group is selected from the first node groups, wherein the second node group is the first node group containing entity relations and having preset relation combinations.
As analyzed above, not all entity relationships have a conflict, and therefore, even if there are multiple entity relationships between two entity nodes, there is not necessarily a conflict relationship. Therefore, in order to eliminate unreasonable conflict relationships, in the embodiment of the present invention, the entity relationships with conflicts are screened from the entity node combinations including the plurality of entity relationships. In order to realize screening of entity relationships with conflicts, in the embodiment of the invention, some combinations of entity relationships with conflicts, namely preset relationship combinations, such as entity relationship combinations with conflicts including father, son, grand, son, brother, sister and the like, are preset, query is performed according to the preset relationship combinations, whether entity relationships contained in the entity relationship group have the conflicting entity relationship combinations is judged, and if so, the entity relationship group is screened out. For example, in the above example, the public opinion information a is analyzed to obtain that the person a is the father of the person b, and another public opinion information C is analyzed to obtain that the person a is the colleague of the person b, and at this time, in the combination of the entity nodes of the entity node a and the entity node b, there is a conflict relation combination of father and son+grandson satisfying the preset relation combination, and the combination of the entity nodes can be screened out. The specific preset care combination setting rules can be set by technicians according to actual conditions.
S403, analyzing the preset relation combination based on the public opinion information corresponding to each entity relation in the preset relation combination, screening out the entity relation uniquely corresponding to the two entity nodes in the second node group, and updating the combined entity relation network based on the uniquely corresponding entity relation.
After determining the entity node combinations with the conflict entity relationships, the embodiment of the invention screens the conflict entity relationships to determine only one corresponding entity relationship. However, it should be understood that, the filtering is only specific to the entity relationship with conflict, and other entity relationships with no conflict are not processed here, so that the two entity relationships directly obtained by the final entity node may not be unique, but only the entity relationship with conflict no longer exists therein, for example, the public opinion information a is analyzed to obtain the person a as the father of the person b in the above example, the other public opinion information C is analyzed to obtain the person a as the person b colleague, that is, the entity node combination of the entity node a and the entity node b shares three entity relationships of father+grandson+colleague+colleague. The screening method of the specific conflict entity relationship is not limited herein, and the skilled person may choose the setting according to the actual situation, including but not limited to, for example, randomly selecting one of the reservations, or referring to the fifth embodiment of the present invention for processing.
As a specific implementation manner for screening conflict entity relations in the fourth embodiment of the present invention, considering that channel sources of public opinion information are numerous and heterogeneous, the importance degree of different channel sources on entity relations is greatly different, for example, the reliability of public opinion information published by government websites is far higher than that of some entertainment news websites, so that the reliability of entity relations obtained by analysis from channel sources with high reliability is far higher than that of channel sources with low reliability, on the other hand, because the real-time characteristics of public opinion information are obvious, the relationship between the included entity relations and time is relatively close, so that the publishing time of public opinion information corresponding to the entity relations is also an important factor for determining the reliability of entity relations, and in order to ensure accurate screening of conflict entity relations, as shown in FIG. 5, the fifth embodiment of the present invention includes:
s501, obtaining channel sources and release time of the public opinion information corresponding to each entity relationship in the preset relationship combination, wherein the channel sources are channel sources for providing the public opinion information.
Because each entity relationship is obtained by analysis from the public opinion information, the channel source for providing the public opinion information and the release time of the public opinion information can be inquired directly according to the corresponding public opinion information.
S502, calculating weight values corresponding to each entity relation in the preset relation combination based on the channel source, the release time and the preset weight coefficient, and screening out entity relations uniquely corresponding to two entity nodes of the second node group based on the weight values.
In order to realize screening of conflicting entity relationships according to channel sources and release time, the embodiment of the invention firstly quantifies the channel sources, for example, a corresponding credibility score can be set for each channel source in advance, for example, a website score related to government is set to be 100, a score of entertainment news website is set to be 60, other websites are set to be 80, and meanwhile, corresponding credibility scores are set for different release times, for example, the release time is set to be 100 in half a year, 80 in half a year to one year, 60 in one year or more, and the like, and meanwhile, a technician sets corresponding weight coefficient for the channel sources and the release time score of each entity relationship in advance, and then based on the weight coefficient, the channel source score and the release time score of each entity relationship are respectively used for realizing quantification score calculation of the entity relationship credibility, so as to obtain a corresponding weight value. And finally, according to the entity relationship with the highest credibility, the entity relationship is used as the only reserved entity relationship in the conflicting entity relationship. The specific values of the weight coefficients corresponding to the channel sources and the release time are set by technicians according to actual conditions.
As a sixth embodiment of the present invention, in order to facilitate the use of the entity relationship query function by the subsequent user, in this embodiment of the present invention, each finally obtained entity relationship network is classified, for example, a person relationship network, a place relationship network, an event relationship network, etc., as shown in fig. 6, including:
s601, identifying the category of the relationship network corresponding to the merged entity relationship network based on the category of the entity and the category of the entity relationship contained in the merged entity relationship network.
The entity relationship network may be classified into the above-mentioned person relationship network, place relationship network, event relationship network, etc., and the corresponding entity and entity relationship division criteria may be set according to the actual situation of each entity relationship network, for example, for the person relationship network, its internal entity includes only person relationship, its physical relationship includes only person relationship, for the place relationship network, its internal entity includes only place relationship, its physical relationship includes only place relationship, and for the event relationship network, its internal entity may include both person, place and mechanism, and the entity relationship may include multiple kinds, so that the actual situation of each entity relationship network may be preset according to the actual situation of each entity relationship network to set the corresponding entity and entity relationship division criteria, and then classification may be performed according to the situation of the actually obtained entity relationship network.
S602, adding a corresponding type label for the combined entity relationship network according to the type of the relationship network corresponding to the combined entity relationship network.
After determining the type of each finally obtained entity relationship network, the embodiment of the invention also adds a corresponding type label to each entity relationship network, for example, a character relationship label can be added to a character relationship network, a place relationship is added to a place relationship network, an event relationship label is added to an event relationship network, and the like, so that when a user performs entity relationship query, the classified query can be quickly realized according to the type of the entity relationship required to be queried.
According to the embodiment of the invention, the public opinion information analysis is carried out to obtain the simple entity relation networks, the public nodes are extracted, the simple entity relation networks are combined according to the public nodes, and the analysis and combination of the entity relation networks are terminated until the public nodes are not included among all the entity relation networks, namely, the depth of all the entity relation networks is maximized, so that the deep analysis of all the entity relations possibly related to the entity is fully realized, and the deep analysis and tracking of the entity relation networks are realized. Meanwhile, on the basis of the method, the device and the system, the analysis of the entity relationship is carried out on each entity node combination in the entity relationship network, so that each possible entity relationship in the finally obtained entity relationship network can be repeatedly mined, analyzed and processed, the entity relationship with conflict among the entity nodes is screened, and only one entity relationship with highest credibility is reserved, so that the reality and reliability of the finally obtained entity relationship network are ensured.
Fig. 7 shows a block diagram of an entity relationship analysis device based on public opinion information according to an embodiment of the present invention, and for convenience of explanation, only the parts related to the embodiment of the present invention are shown. The public opinion information-based entity relationship analysis apparatus illustrated in fig. 7 may be an execution subject of the public opinion information-based entity relationship analysis method provided in the first embodiment.
Referring to fig. 7, the entity relationship analysis apparatus based on public opinion information includes:
The network analysis module 71 is configured to analyze the obtained pieces of public opinion information respectively to obtain a plurality of initial entity relationship networks corresponding to the public opinion information, where a plurality of entity nodes and entity relationships among the plurality of entity nodes are recorded in the entity relationship networks.
The node extraction module 72 is configured to extract a common node included in the entity-relationship network, where the common node is an entity node that exists in at least two entity-relationship networks at the same time.
And the network merging module 73 is configured to perform merging processing on the entity relationship networks based on the common node until the entity relationship network obtained by merging does not include the common node, and obtain the entity relationship network after merging.
Further, the entity relationship analysis device based on public opinion information further comprises:
And the node combination module is used for carrying out random combination on the entity nodes in the combined entity relationship network, and analyzing the entity relationship between 2 entity nodes in each combination.
And the relation updating module is used for updating the entity relation in the combined entity relation network based on the analyzed entity relation among 2 entity nodes in each combination.
Further, the network merging module 73 includes:
And randomly selecting a plurality of public nodes, and respectively merging the entity relationship networks to which each public node belongs in the public nodes to obtain a plurality of merged entity relationship networks.
And detecting whether a public node exists in the entity relation network after the merging.
And if the public nodes exist in the entity relation networks after the merging, returning to execute the operation of extracting the public nodes contained in the entity relation network based on the entity relation networks after the merging.
Further, the entity relationship analysis device based on public opinion information further comprises:
And the multi-relation node searching module is used for searching a first node group in the combined entity relation network, wherein the first node group is a combination of 2 entity nodes with the corresponding entity relation number being more than or equal to 2.
And the relation group screening module is used for screening a second node group from the first node group, wherein the second node group is a first node group containing entity relations and having preset relation combinations.
And the node relation updating module is used for analyzing the preset relation combination based on the public opinion information corresponding to each entity relation in the preset relation combination, screening out the entity relation uniquely corresponding to the two entity nodes in the second node group, and updating the merged entity relation network based on the uniquely corresponding entity relation.
Further, the node relation updating module includes:
and obtaining channel sources and release time of the public opinion information corresponding to each entity relationship in the preset relationship combination, wherein the channel sources are channel sources for providing the public opinion information.
And calculating weight values respectively corresponding to each entity relation in the preset relation combination based on the channel source, the release time and the preset weight coefficient, and screening out entity relations uniquely corresponding to two entity nodes of the second node group based on the weight values.
Further, the entity relationship analysis device based on public opinion information further comprises:
And identifying the type of the relationship network corresponding to the merged entity relationship network based on the type of the entity and the type of the entity relationship contained in the merged entity relationship network.
And adding a corresponding type label for the combined entity relationship network according to the type of the relationship network corresponding to the combined entity relationship network.
The process of implementing the respective functions of each module in the entity relationship analysis device based on public opinion information provided in the embodiment of the present invention may refer to the description of the first embodiment shown in fig. 1, and will not be repeated here.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
It will also be understood that, although the terms "first," "second," etc. may be used herein in some embodiments of the invention to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, a first table may be named a second table, and similarly, a second table may be named a first table without departing from the scope of the various described embodiments. The first table and the second table are both tables, but they are not the same table.
Fig. 8 is a schematic diagram of a terminal device according to an embodiment of the present invention. As shown in fig. 8, the terminal device 8 of this embodiment includes: a processor 80, a memory 81, said memory 81 having stored therein a computer program 82 executable on said processor 80. The processor 80, when executing the computer program 82, implements the steps of the above-described embodiments of the public opinion information based entity relationship analysis method, such as steps 101 to 103 shown in fig. 1. Or the processor 80, when executing the computer program 82, performs the functions of the modules/units of the device embodiments described above, e.g. the functions of the modules 71 to 73 of fig. 7.
The terminal device 8 may be a computing device such as a desktop computer, a notebook computer, a palm computer, a cloud server, etc. The terminal device may include, but is not limited to, a processor 80, a memory 81. It will be appreciated by those skilled in the art that fig. 8 is merely an example of a terminal device 8 and does not constitute a limitation of the terminal device 8, and may include more or less components than illustrated, or may combine certain components, or different components, e.g., the terminal device may also include an input transmitting device, a network access device, a bus, etc.
The Processor 80 may be a central processing unit (Central Processing Unit, CPU), other general purpose Processor, digital signal Processor (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), off-the-shelf Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 81 may be an internal storage unit of the terminal device 8, such as a hard disk or a memory of the terminal device 8. The memory 81 may also be an external storage device of the terminal device 8, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the terminal device 8. Further, the memory 81 may also include both an internal storage unit and an external storage device of the terminal device 8. The memory 81 is used for storing the computer program as well as other programs and data required by the terminal device. The memory 81 may also be used for temporarily storing data that has been transmitted or is to be transmitted.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.

Claims (5)

1. The utility model provides an entity relation analysis method based on public opinion information, which is characterized by comprising the following steps:
Respectively analyzing the acquired pieces of public opinion information to obtain a plurality of initial entity relation networks corresponding to the public opinion information, wherein a plurality of entity nodes and entity relations among the entity nodes are recorded in the entity relation networks;
extracting public nodes contained in the entity relation network, wherein the public nodes are entity nodes which exist in at least two entity relation networks at the same time;
Combining the entity relationship networks based on the public nodes until the entity relationship network obtained by combining does not contain the public nodes, thereby obtaining the entity relationship network after combining;
After the entity relationship network after the merging is obtained, the method further comprises:
Carrying out random combination on the entity nodes in the combined entity relationship network, and analyzing the entity relationship among 2 entity nodes in each combination in which the entity relationship does not exist;
updating the entity relationship in the combined entity relationship network based on the entity relationship among 2 entity nodes in each combination obtained by analysis;
the merging processing is performed on the entity relationship networks based on the public node until the entity relationship network obtained by merging does not contain the public node, and the merged entity relationship network is obtained, including:
Randomly selecting a plurality of public nodes, and respectively merging the entity relationship networks to which each public node belongs in the plurality of public nodes to obtain a plurality of merged entity relationship networks;
Detecting whether public nodes exist in the entity relation network after the merging;
If public nodes exist in the entity relation networks after the merging, returning to execute the operation of extracting the public nodes contained in the entity relation network based on the entity relation networks after the merging;
After the entity relationship network after the merging is obtained, the method further comprises:
Searching a first node group in the combined entity relation network, wherein the first node group is a combination of 2 entity nodes with the number of corresponding entity relations being more than or equal to 2;
Screening a second node group from the first node group, wherein the second node group is a first node group containing entity relations and having preset relation combinations;
Analyzing the preset relation combination based on the public opinion information respectively corresponding to each entity relation in the preset relation combination, screening out the entity relation uniquely corresponding to two entity nodes in the second node group, and updating the combined entity relation network based on the uniquely corresponding entity relation;
the step of analyzing the preset relation combination based on the public opinion information corresponding to each entity relation in the preset relation combination, and screening out the entity relation uniquely corresponding to two entity nodes in the second node group, includes:
obtaining channel sources and release time of the public opinion information corresponding to each entity relationship in the preset relationship combination, wherein the channel sources are channel sources for providing the public opinion information;
calculating weight values respectively corresponding to each entity relation in the preset relation combination based on the channel source, the release time and the preset weight coefficient, and screening out entity relations uniquely corresponding to two entity nodes of the second node group based on the weight values;
After the entity relationship network after the merging is obtained, the method further comprises:
Identifying the type of the relationship network corresponding to the entity relationship network after merging based on the type of the entity and the type of the entity relationship contained in the entity relationship network after merging;
And adding a corresponding type label for the combined entity relationship network according to the type of the relationship network corresponding to the combined entity relationship network.
2. A terminal device, characterized in that the terminal device comprises a memory, a processor, the memory storing a computer program executable on the processor, the processor executing the computer program implementing the steps of:
Respectively analyzing the acquired pieces of public opinion information to obtain a plurality of initial entity relation networks corresponding to the public opinion information, wherein a plurality of entity nodes and entity relations among the entity nodes are recorded in the entity relation networks;
extracting public nodes contained in the entity relation network, wherein the public nodes are entity nodes which exist in at least two entity relation networks at the same time;
Combining the entity relationship networks based on the public nodes until the entity relationship network obtained by combining does not contain the public nodes, thereby obtaining the entity relationship network after combining;
After the entity relationship network after the merging is obtained, the method further comprises:
Carrying out random combination on the entity nodes in the combined entity relationship network, and analyzing the entity relationship among 2 entity nodes in each combination in which the entity relationship does not exist;
updating the entity relationship in the combined entity relationship network based on the entity relationship among 2 entity nodes in each combination obtained by analysis;
the merging processing is performed on the entity relationship networks based on the public node until the entity relationship network obtained by merging does not contain the public node, and the merged entity relationship network is obtained, including:
Randomly selecting a plurality of public nodes, and respectively merging the entity relationship networks to which each public node belongs in the plurality of public nodes to obtain a plurality of merged entity relationship networks;
Detecting whether public nodes exist in the entity relation network after the merging;
If public nodes exist in the entity relation networks after the merging, returning to execute the operation of extracting the public nodes contained in the entity relation network based on the entity relation networks after the merging;
After the entity relationship network after the merging is obtained, the method further comprises:
Searching a first node group in the combined entity relation network, wherein the first node group is a combination of 2 entity nodes with the number of corresponding entity relations being more than or equal to 2;
Screening a second node group from the first node group, wherein the second node group is a first node group containing entity relations and having preset relation combinations;
Analyzing the preset relation combination based on the public opinion information respectively corresponding to each entity relation in the preset relation combination, screening out the entity relation uniquely corresponding to two entity nodes in the second node group, and updating the combined entity relation network based on the uniquely corresponding entity relation;
the step of analyzing the preset relation combination based on the public opinion information corresponding to each entity relation in the preset relation combination, and screening out the entity relation uniquely corresponding to two entity nodes in the second node group, includes:
obtaining channel sources and release time of the public opinion information corresponding to each entity relationship in the preset relationship combination, wherein the channel sources are channel sources for providing the public opinion information;
calculating weight values respectively corresponding to each entity relation in the preset relation combination based on the channel source, the release time and the preset weight coefficient, and screening out entity relations uniquely corresponding to two entity nodes of the second node group based on the weight values;
After the entity relationship network after the merging is obtained, the method further comprises:
Identifying the type of the relationship network corresponding to the entity relationship network after merging based on the type of the entity and the type of the entity relationship contained in the entity relationship network after merging;
And adding a corresponding type label for the combined entity relationship network according to the type of the relationship network corresponding to the combined entity relationship network.
3. The terminal device of claim 2, wherein the processor when executing the computer program further performs the steps of:
Carrying out random combination on the entity nodes in the combined entity relationship network, and analyzing the entity relationship between 2 entity nodes in each combination;
And updating the entity relationship in the combined entity relationship network based on the entity relationship among the 2 entity nodes in each combination obtained by analysis.
4. An entity relationship analysis device based on public opinion information, comprising:
The network analysis module is used for respectively analyzing the acquired public opinion information to obtain a plurality of initial entity relation networks corresponding to the public opinion information, wherein a plurality of entity nodes and entity relations among the entity nodes are recorded in the entity relation networks;
the node extraction module is used for extracting public nodes contained in the entity relation network, wherein the public nodes are entity nodes which exist in at least two entity relation networks at the same time;
The network merging module is used for merging the entity relationship networks based on the public nodes until the entity relationship network obtained by merging does not contain the public nodes, so as to obtain the entity relationship network after merging;
The node combination module is used for carrying out random combination on the entity nodes in the combined entity relationship network, and analyzing the entity relationship among 2 entity nodes in each combination in which the entity relationship does not exist;
The relationship updating module is used for updating the entity relationship in the combined entity relationship network based on the entity relationship among 2 entity nodes in each combination obtained through analysis;
The network merging module is specifically configured to:
Randomly selecting a plurality of public nodes, and respectively merging the entity relationship networks to which each public node belongs in the plurality of public nodes to obtain a plurality of merged entity relationship networks;
Detecting whether public nodes exist in the entity relation network after the merging;
If public nodes exist in the entity relation networks after the merging, returning to execute the operation of extracting the public nodes contained in the entity relation network based on the entity relation networks after the merging;
the entity relationship analysis device based on public opinion information further comprises:
The multi-relation node searching module is used for searching a first node group in the combined entity relation network, wherein the first node group is a combination of 2 entity nodes with the number of corresponding entity relations being more than or equal to 2;
the relation group screening module is used for screening a second node group from the first node group, wherein the second node group is a first node group containing entity relations and having preset relation combinations;
the node relation updating module is used for analyzing the preset relation combination based on the public opinion information corresponding to each entity relation in the preset relation combination, screening out the entity relation uniquely corresponding to two entity nodes in the second node group, and updating the merged entity relation network based on the uniquely corresponding entity relation;
The node relation updating module is specifically configured to:
obtaining channel sources and release time of the public opinion information corresponding to each entity relationship in the preset relationship combination, wherein the channel sources are channel sources for providing the public opinion information;
calculating weight values respectively corresponding to each entity relation in the preset relation combination based on the channel source, the release time and the preset weight coefficient, and screening out entity relations uniquely corresponding to two entity nodes of the second node group based on the weight values;
The entity relationship analysis device based on public opinion information is further used for:
Identifying the type of the relationship network corresponding to the entity relationship network after merging based on the type of the entity and the type of the entity relationship contained in the entity relationship network after merging;
And adding a corresponding type label for the combined entity relationship network according to the type of the relationship network corresponding to the combined entity relationship network.
5. A computer readable storage medium storing a computer program, which when executed by a processor performs the steps of the method according to claim 1.
CN201811343920.8A 2018-11-13 2018-11-13 Entity relationship analysis method and terminal equipment based on public opinion information Active CN109635074B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811343920.8A CN109635074B (en) 2018-11-13 2018-11-13 Entity relationship analysis method and terminal equipment based on public opinion information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811343920.8A CN109635074B (en) 2018-11-13 2018-11-13 Entity relationship analysis method and terminal equipment based on public opinion information

Publications (2)

Publication Number Publication Date
CN109635074A CN109635074A (en) 2019-04-16
CN109635074B true CN109635074B (en) 2024-05-07

Family

ID=66067864

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811343920.8A Active CN109635074B (en) 2018-11-13 2018-11-13 Entity relationship analysis method and terminal equipment based on public opinion information

Country Status (1)

Country Link
CN (1) CN109635074B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113157866B (en) * 2021-04-27 2024-05-14 平安科技（深圳）有限公司 Data analysis method, device, computer equipment and storage medium

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103207860A (en) * 2012-01-11 2013-07-17 北大方正集团有限公司 Method and device for extracting entity relationships of public sentiment events
CN103544255A (en) * 2013-10-15 2014-01-29 常州大学 Text semantic relativity based network public opinion information analysis method
CN104268271A (en) * 2014-10-13 2015-01-07 北京建筑大学 Interest and network structure double-cohesion social network community discovering method
CN105302823A (en) * 2014-06-27 2016-02-03 首都师范大学 Overlapped community parallel discovery method and system
CN105373619A (en) * 2015-12-03 2016-03-02 中国联合网络通信集团有限公司 User big data based user group analysis method and system
CN106204161A (en) * 2016-07-26 2016-12-07 郑州郑大智能科技股份有限公司 A kind of power consumer group analytic method under internet environment
CN106991090A (en) * 2016-01-20 2017-07-28 北京国双科技有限公司 The analysis method and device of public sentiment event entity
WO2018023981A1 (en) * 2016-08-03 2018-02-08 平安科技（深圳）有限公司 Public opinion analysis method, device, apparatus and computer readable storage medium

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140108152A1 (en) * 2012-10-12 2014-04-17 Google Inc. Managing Social Network Relationships Between A Commercial Entity and One or More Users
US20150178372A1 (en) * 2013-12-19 2015-06-25 OpenGov, Inc. Creating an ontology across multiple semantically-related data sets
US10833954B2 (en) * 2014-11-19 2020-11-10 Battelle Memorial Institute Extracting dependencies between network assets using deep learning

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103207860A (en) * 2012-01-11 2013-07-17 北大方正集团有限公司 Method and device for extracting entity relationships of public sentiment events
CN103544255A (en) * 2013-10-15 2014-01-29 常州大学 Text semantic relativity based network public opinion information analysis method
CN105302823A (en) * 2014-06-27 2016-02-03 首都师范大学 Overlapped community parallel discovery method and system
CN104268271A (en) * 2014-10-13 2015-01-07 北京建筑大学 Interest and network structure double-cohesion social network community discovering method
CN105373619A (en) * 2015-12-03 2016-03-02 中国联合网络通信集团有限公司 User big data based user group analysis method and system
CN106991090A (en) * 2016-01-20 2017-07-28 北京国双科技有限公司 The analysis method and device of public sentiment event entity
CN106204161A (en) * 2016-07-26 2016-12-07 郑州郑大智能科技股份有限公司 A kind of power consumer group analytic method under internet environment
WO2018023981A1 (en) * 2016-08-03 2018-02-08 平安科技（深圳）有限公司 Public opinion analysis method, device, apparatus and computer readable storage medium

Also Published As

Publication number Publication date
CN109635074A (en) 2019-04-16

Similar Documents

Publication Publication Date Title
US11977541B2 (en) Systems and methods for rapid data analysis
US10482285B2 (en) Event processing system
US9424319B2 (en) Social media based content selection system
Strotmann et al. Author name disambiguation: What difference does it make in author‐based citation analysis?
JP5635691B2 (en) Data analysis using multiple systems
US20190026491A1 (en) Event processing system
US11113317B2 (en) Generating parsing rules for log messages
CN104077723B (en) A kind of social networks commending system and method
US8880440B2 (en) Automatic combination and mapping of text-mining services
CN112100396B (en) Data processing method and device
US11461680B2 (en) Identifying attributes in unstructured data files using a machine-learning model
WO2021175021A1 (en) Product push method and apparatus, computer device, and storage medium
WO2016049034A1 (en) Guided data exploration
Liu et al. Digger: Detect similar groups in heterogeneous social networks
CN109635074B (en) Entity relationship analysis method and terminal equipment based on public opinion information
CN112148841B (en) Object classification and classification model construction method and device
EP2551781A1 (en) Data analysis system
CN110874366A (en) Data processing and query method and device
CN112069175A (en) Data query method and device and electronic equipment
US20220292127A1 (en) Information management system
CN105245380B (en) Message propagation mode identification method and device
CN115329748A (en) Log analysis method, device, equipment and storage medium
Das et al. Automated inference of point of view from user interactions in collective intelligence venues
US20190197069A1 (en) Social Media Based Content Selection System
CN112184370A (en) Method and device for pushing product

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
GR01 Patent grant
GR01 Patent grant