CN110737845A - method, computer storage medium and system for realizing information analysis - Google Patents
method, computer storage medium and system for realizing information analysis Download PDFInfo
- Publication number
- CN110737845A CN110737845A CN201910977377.5A CN201910977377A CN110737845A CN 110737845 A CN110737845 A CN 110737845A CN 201910977377 A CN201910977377 A CN 201910977377A CN 110737845 A CN110737845 A CN 110737845A
- Authority
- CN
- China
- Prior art keywords
- entity
- product
- social media
- determining
- consumer
- 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
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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Abstract
method, computer storage medium and system for realizing information analysis, including matching and analyzing social media information processed by natural language according to preset industry rules, identifying entities contained in the social media information and marking the entities, and extracting entity relations of the marked social media information through a trained relation model to determine relations between the entities in the social media information.
Description
Technical Field
This document relates to, but is not limited to, data processing technology and, more particularly, to methods, computer storage media and systems for performing information analysis.
Background
According to the application development of the mobile internet, social media application becomes an important channel for people to acquire product information, information communication and share, preliminary analysis on users can be achieved through social media accounts, Key Opinion Leaders (KOLs) and famous people which are popular among the users can be known through information published by certain social media accounts, enterprises can be helped to carry out market analysis, master brand popularity and carry out business activities more accurately (including selecting KOLs, speakers and the like), users can be portrayed through acquiring certain time period published information of the social media accounts, the enterprises can visually and comprehensively analyze consumption information of the users through the user portrayal, consumption requirements of the users can be accurately grasped, and personalized goods and services are provided for the users.
Currently, information published by users in social media mainly depends on the analysis mode mentioned at the same time, and information such as series, brands, components, efficacies, speakers and the like related to products is combed out. Fig. 1 is a schematic diagram illustrating a result of information analysis in the related art, and as shown in fig. 1, when information analysis is performed in a simultaneous mentioning manner, brands and categories that are mentioned in information issued by a user can be analyzed by preset component keywords, brand keywords, and category keywords. In the related art, the analysis result of the analysis method mentioned at the same time can only reflect the key words contained in the information issued by the user, so that the comprehensive information analysis cannot be performed, and the value of the analysis result is not high.
Disclosure of Invention
The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.
The embodiment of the invention provides methods and devices for realizing information analysis, a computer storage medium and a terminal, which can improve the information analysis quality of the simultaneous reference method.
The embodiment of the invention provides methods for realizing information analysis, which comprise the following steps:
according to preset industry rules, matching and analyzing the social media information processed by natural language, identifying entities contained in the social media information and marking the entities;
and extracting entity relations of the marked social media information through a trained relation model so as to determine the relations among the entities in the social media information.
In exemplary embodiments, the industry rule relates to industries including or any combination of the following industries, namely, cosmetic industry, automobile industry, mother and infant industry, clothing industry, household appliance industry, and film and television industry;
of the industry rules include industry vocabulary as entities and keywords for identifying the industry vocabulary, the keywords including inclusion words or including inclusion words and exclusion words.
In exemplary embodiments, the tagging the entity includes tagging a category of the entity;
the determining of the relationship between the entities in the social media information includes determining the relationship between entities with a category of products and entities with or categories of brands, product series, efficacies, ingredients, contestants, activities, programs, speakers, key opinion leaders KOL, usage scenarios.
In exemplary embodiments, the tagging the entity includes tagging a category of the entity;
the determining of the relationship between the entities in the social media information includes determining a relationship between an entity of which a category is a consumer and an entity of which or categories are KOL, product, brand, star, activity, program, hobby.
In exemplary embodiments, the extracting entity relationships from the tagged social media information through the trained relationship model includes or or more ways:
determining, by a relationship model of brand + th predicate + product, that an inclusion relationship exists between a brand entity and a product entity when the th predicate representing the inclusion relationship, the product entity and a preset inclusion relationship appear in the same text block of the social media information;
determining that an inclusion relationship exists between a product series entity and a product entity when the product series entity, the product entity and a preset second predicate representing the inclusion relationship appear in a same text block of the social media information through a relationship model of the product series + the second predicate + the product;
determining that an inclusion relationship exists between a product entity and a component entity when the product entity, the component entity and a preset third predicate representing the inclusion relationship appear in a same text block of the social media information through a relationship model of the product + the third predicate + the component;
determining that an inclusion relationship exists between a product entity and an efficacy when a product entity, the efficacy entity and a preset fourth predicate representing the inclusion relationship appear in a same text block of the social media information through a relationship model of the product + the fourth predicate + the efficacy;
and (3) referring to the product + emotion judgment relation model through the KOL, when a product entity and a preset emotion word appear in an article published by the KOL entity through the social media information, determining that the emotion judgment is positive through the emotion word, determining that the KOL entity is a KOL giving a good comment to the product entity, determining that the emotion judgment is negative through the emotion word, and determining that the KOL entity is a KOL giving a poor comment to the product entity.
In exemplary embodiments, the extracting entity relationships from the tagged social media information through the trained relationship model includes or or more ways:
determining that a positive emotional relationship or a negative emotional relationship exists between a product entity and a use scene entity through emotional word judgment when the product entity, the use scene entity and a preset emotional word appear in a same text block of the social media information through a relation model of product + use scene + emotional judgment;
and determining that the product entities are in the relationship of the product and the competitive product when two or more product entities appear in the same text block of the social media information and a preset fifth predicate representing a competitive relationship exists through a relationship model of two or more product + fifth predicate.
In exemplary embodiments, the extracting entity relationships from the tagged social media information through the trained relationship model includes or or more ways:
through a relation model of consumer mentioning product + emotion judgment, when a product entity and a preset emotion word appear in an article published by a consumer entity through the social media information, determining that the emotion judgment is positive through the emotion word, determining that the consumer entity is a good consumer for the product entity, and determining that the emotion judgment is negative through the emotion word, and determining that the consumer entity is a bad consumer for the product entity;
through a relation model of brand and emotion judgment mentioned by a consumer, when a brand entity and a preset emotion word appear in an article published by the consumer entity through the social media information, determining that the emotion judgment is positive through the emotion word, determining that the consumer entity is a good-rated consumer for the brand entity, determining that the emotion judgment is negative through the emotion word, and determining that the consumer entity is a bad-rated consumer for the brand entity;
determining the attention degree of the consumer to the efficacy according to the frequency of the efficacy entities appearing in the preset time length when the efficacy entities appear in the articles published by the consumer entity through the social media information through a relation model of the efficacy mentioned by the consumer;
determining the preference of the consumer for each interest according to the frequency of each interest entity appearing in a preset time length when the interest entity appears in an article published by the consumer entity through the social media information through a relation model of the consumer mentioning the interest;
and determining the preference of the consumer for each program according to the frequency of each program entity appearing in the preset time length when the program entity appears in the article published by the consumer entity through the social media information through the relation model of the consumer mentioning the program.
In exemplary embodiments, the constructing a knowledge graph of social media based on relationships between the entities as determined by a relationship model includes:
and constructing a knowledge graph of the social media according to the relationship between the entities determined by the relationship model and the preset fixed relationship between the partial entities.
In another aspect, embodiments of the present invention further provide computer storage media, in which computer-executable instructions are stored, and the computer-executable instructions are configured to perform the above-mentioned method for implementing information analysis.
, embodiments of the present invention also provide systems comprising a memory and a processor, wherein,
the processor is configured to execute program instructions in the memory;
the program instructions read and execute the method for realizing the information analysis on the processor.
Compared with the related art, the technical scheme of the application comprises the following steps: according to preset industry rules, matching and analyzing the social media information processed by natural language, identifying entities contained in the social media information and marking the entities; and extracting entity relations of the marked social media information through a trained relation model so as to determine the relations among the entities in the social media information. According to the embodiment of the invention, the incidence relation between the entities is determined through the relation model, and the information analysis quality of the simultaneous mentioning method is improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings are included to provide a further understanding of the present invention and constitute a part of this specification, serve to explain the present invention with example of the present application and do not constitute a limitation on the present invention.
FIG. 1 is a diagram illustrating the results of information analysis performed by the related art;
FIG. 2 is a flow chart of a method for implementing information analysis according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of setting an industry rule according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating an embodiment of querying information using a knowledge graph.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be noted that the embodiments and features of the embodiments in the present application may be arbitrarily combined with each other without conflict.
The steps illustrated in the flowchart of the figure may be performed in a computer system such as sets of computer-executable instructions and, although a logical order is illustrated in the flowchart, in some cases, the steps illustrated or described may be performed in an order different than that illustrated herein.
Fig. 2 is a flowchart of a method for implementing information analysis according to an embodiment of the present invention, as shown in fig. 2, including:
in exemplary embodiments, the industry rule relates to industries including or any combination of the following industries, namely, cosmetic industry, automobile industry, mother and infant industry, clothing industry, household appliance industry, and film and television industry;
of the industry rules include industry vocabulary as entities and keywords for identifying the industry vocabulary, the keywords including inclusion words or including inclusion words and exclusion words.
The household appliance industry comprises a 3C industry, the 3C industry comprises a Computer, Communication and Consumer Electronics Consumer Electronics, the industry rules in the embodiment of the invention can include but are not limited to Natural Language Processing (NLP) and related rules preset by technicians in the field, the industry rules can include rules constructed by the technicians according to keywords needing to be analyzed, FIG. 3 is a schematic diagram of the industry rules set in the embodiment of the invention, as shown in FIG. 3, when the industry rules of a certain product are set, the industry names, including words and excluding words in the industry rules can be firstly determined, and by taking a certain brand mobile phone as an example, the including words in the industry rules of the brand mobile phone can include all models of the brand mobile phone, Chinese names and English names of the brand, and the excluding words can include names of Chinese and English at the same time, mobile phone names with national names, mobile phones (not including brands).
Through analysis, the association between the entities established in the related technology is mainly constructed manually by technicians, the number of association relations is small, and the frequently-changed entity relations cannot be obtained through a manual construction mode and comprise products and brands, products and KOLs, products and speakers and the like. According to the embodiment of the invention, the collection of the entity relation is realized through the trained relation model, and the efficiency of determining the incidence relation between the entities is improved.
In exemplary embodiments, the tagging the entity includes tagging a category of the entity;
the determining of the relationship between the entities in the social media information includes determining the relationship between entities with a category of products and entities with or categories of brands, product series, efficacies, ingredients, contestants, activities, programs, speakers, key opinion leaders KOL, usage scenarios.
In exemplary embodiments, the extracting entity relationships from the tagged social media information through the trained relationship model includes or or more ways:
through a relation model of brand + predicate + product, when a brand entity, a product entity and a preset predicate representing an inclusion relation appear in the same text block of the social media information, determining that the inclusion relation exists between the brand entity and the product entity, wherein the predicate may include a released predicate representing the inclusion relation, for example, brand a releases product B, and in the statement, the released predicate is a preset predicate representing that brand a contains product B;
determining that an inclusion relationship exists between a product series entity and a product entity when the product series entity, the product entity and a preset second predicate representing the inclusion relationship appear in a same text block of the social media information through a relationship model of the product series + the second predicate + the product;
through a relation model of product + third predicate + component, when a product entity, a component entity and a preset third predicate representing an inclusion relation appear in the same text block of the social media information, it is determined that the inclusion relation exists between the product entity and the component entity, wherein the third predicate may include words such as using, adding and including, for example, my skin becomes better because the C product for i contains (or adds) a D component.
Through a relation model of product + fourth predicate + efficacy, when a product entity, an efficacy entity and a preset fourth predicate representing an inclusion relation appear in the same text block of the social media information, determining that the inclusion relation exists between the product entity and the efficacy;
referring to a product + emotion judgment relation model through a KOL, when a product entity and a preset emotion word appear in an article published by the KOL entity through the social media information, determining that the emotion judgment is positive if the emotion word determines that the product entity is a koL giving a good comment, determining that the emotion judgment is negative if the emotion word determines that the product entity is a koL giving a bad comment;
in exemplary embodiments, the method of the present invention further comprises determining active fans of the KOL by monitoring fans that participate in forwarding, commenting, and commenting after the posting of the KOL;
in exemplary embodiments, the extracting entity relationships from the tagged social media information through the trained relationship model includes or or more ways:
according to a relation model of product + use scene + emotion judgment, when a product entity, a use scene entity and preset emotion words appear in a text block of of the social media information, positive emotion relation or negative emotion relation exists between the product entity and the use scene entity through emotion word judgment, wherein the emotion words can comprise words expressing emotion such as like, Chinese, recommendation and the like, and the association relation can comprise the preference of star for the product.
Determining that the product entities are in a relationship between products and competitors when two or more product entities appear in the same text block of the social media information and a preset fifth predicate representing a competitive relationship exists through a relationship model of two or more product + fifth predicate;
in exemplary embodiments, the extracting entity relationships from the tagged social media information through the trained relationship model according to the embodiments of the present invention includes the following or or more ways:
determining the relationship between the product entities and the competitive products through a relationship model with the same efficacy when the multiple product entities have the same efficacy exceeding a set proportion;
determining that an activity entity of social media information is an activity of the product entity when the activity entity includes a product entity through a relationship model of the product included in the activity;
and converting the video of the program entity into an image and converting the audio of the program entity into a text through a relation model of products appearing in the program, and if the product entity appears in the image obtained through conversion and/or the product entity is mentioned in the converted text, determining that the program entity is the program of the product entity through pushing .
In exemplary embodiments, the text block may be a whole article, post, paragraphs, sentences, or multiple characters, and may be set to different ranges by one skilled in the art according to different scenes and determination of association.
In exemplary embodiments, the tagging the entity includes tagging a category of the entity;
the determining of the relationship between the entities in the social media information includes determining a relationship between an entity of which a category is a consumer and an entity of which or categories are KOL, product, brand, star, activity, program, hobby.
In exemplary embodiments, the extracting entity relationships from the tagged social media information through the trained relationship model includes or or more ways:
through a relation model of consumer mentioning product + emotion judgment, when a product entity and a preset emotion word appear in an article published by a consumer entity through the social media information, determining that the emotion judgment is positive through the emotion word, determining that the consumer entity is a good consumer for the product entity, and determining that the emotion judgment is negative through the emotion word, and determining that the consumer entity is a bad consumer for the product entity;
through a relation model of brand and emotion judgment mentioned by a consumer, when a brand entity and a preset emotion word appear in an article published by the consumer entity through the social media information, determining that the emotion judgment is positive through the emotion word, determining that the consumer entity is a good-rated consumer for the brand entity, determining that the emotion judgment is negative through the emotion word, and determining that the consumer entity is a bad-rated consumer for the brand entity;
determining the attention degree of the consumer to the efficacy according to the frequency of the efficacy entities appearing in the preset time length when the efficacy entities appear in the articles published by the consumer entity through the social media information through a relation model of the efficacy mentioned by the consumer;
determining the preference of the consumer for each interest according to the frequency of each interest entity appearing in a preset time length when the interest entity appears in an article published by the consumer entity through the social media information through a relation model of the consumer mentioning the interest;
and determining the preference of the consumer for each program according to the frequency of each program entity appearing in the preset time length when the program entity appears in the article published by the consumer entity through the social media information through the relation model of the consumer mentioning the program.
In exemplary embodiments, the constructing a knowledge graph of social media based on relationships between the entities as determined by a relationship model includes:
and constructing a knowledge graph of the social media according to the relationship between the entities determined by the relationship model and the preset fixed relationship between the partial entities.
In exemplary embodiments, after determining the association relationship between entities, the embodiments of the present invention may refer to a method for constructing a knowledge graph in the related art to construct a knowledge graph in the embodiments of the present invention, the knowledge graph constructed in the embodiments of the present invention may be a knowledge graph surrounding both the user and the product, fig. 4 is a schematic diagram of information query using a knowledge graph in the embodiments of the present invention, as shown in fig. 4, after the user inputs a query keyword, various types of information related to the keyword, including related expansion information, may be quickly queried through the constructed knowledge graph, for example, after querying a certain product, the efficacy, composition, auction, product, brand, category, and characteristic of the product, and the program, speaker, consumer group, related activity, topic, etc. of the query result displayed may be set and adjusted by the user according to the needs.
In exemplary embodiments, the method of the present invention further comprises querying the analysis results in the knowledge-graph through the received query keywords.
The invention relies on the established knowledge graph, can design an inquiry system according to related theories, and can help enterprises to efficiently carry out information of social media by inquiring the knowledge graph.
The embodiment of the invention can solve the problem of isolated social media information by the established knowledge graph, and can quickly establish the knowledge graph by determining the association relationship between the entities with the help of less manual training and algorithm. The analysis processing efficiency of the social media information is improved, data query can be efficiently and comprehensively carried out through the established knowledge graph, and a more accurate information analysis result is provided for a user.
Compared with the related art, the technical scheme of the application comprises the following steps: according to preset industry rules, matching and analyzing the social media information processed by natural language, identifying entities contained in the social media information and marking the entities; and extracting entity relations of the marked social media information through a trained relation model so as to determine the relations among the entities in the social media information. According to the embodiment of the invention, the incidence relation between the entities is determined through the relation model, and the information analysis quality of the simultaneous mentioning method is improved.
The embodiment of the present invention further provides computer storage media, where the computer storage media store computer-executable instructions, and the computer-executable instructions are used to execute the above method for implementing information analysis.
Embodiments of the present invention also provide systems comprising a memory and a processor, wherein,
the processor is configured to execute program instructions in the memory;
the program instructions read and execute the method for realizing the information analysis on the processor.
The system of the embodiment of the invention can be arranged in a cloud server to realize the application of functions including information analysis.
It will be understood by those skilled in the art that all or part of the steps of the above methods may be implemented by a program instructing associated hardware (e.g., a processor), and the program may be stored in a computer readable storage medium such as a read-only memory, a magnetic or optical disk, etc. alternatively, all or part of the steps of the above embodiments may be implemented by or more integrated circuits.
Although the embodiments of the present invention have been described above, the above description is only for the convenience of understanding the present invention, and is not intended to limit the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1, an information processing method, comprising:
according to preset industry rules, matching and analyzing the social media information processed by natural language, identifying entities contained in the social media information and marking the entities;
and extracting entity relations of the marked social media information through a trained relation model so as to determine the relations among the entities in the social media information.
2. The method of claim 1, wherein the industry related to the industry rule comprises or any combination of the following industries, namely, cosmetic industry, automobile industry, mother and infant industry, clothing industry, household appliance industry, and film and television industry;
of the industry rules include industry vocabulary as entities and keywords for identifying the industry vocabulary, the keywords including inclusion words or including inclusion words and exclusion words.
3. The method of claim 1, wherein the tagging the entity comprises: tagging the category of the entity;
the determining of the relationship between the entities in the social media information includes determining the relationship between entities with a category of products and entities with or categories of brands, product series, efficacies, ingredients, contestants, activities, programs, speakers, key opinion leaders KOL, usage scenarios.
4. The method of claim 1, wherein the tagging the entity comprises: tagging the category of the entity;
the determining of the relationship between the entities in the social media information includes determining a relationship between an entity of which a category is a consumer and an entity of which or categories are KOL, product, brand, star, activity, program, hobby.
5. The method of claim 3, wherein the extracting entity relationships from the labeled social media information through the trained relationship model comprises or or more ways:
determining, by a relationship model of brand + th predicate + product, that an inclusion relationship exists between a brand entity and a product entity when the th predicate representing the inclusion relationship, the product entity and a preset inclusion relationship appear in the same text block of the social media information;
determining that an inclusion relationship exists between a product series entity and a product entity when the product series entity, the product entity and a preset second predicate representing the inclusion relationship appear in a same text block of the social media information through a relationship model of the product series + the second predicate + the product;
determining that an inclusion relationship exists between a product entity and a component entity when the product entity, the component entity and a preset third predicate representing the inclusion relationship appear in a same text block of the social media information through a relationship model of the product + the third predicate + the component;
determining that an inclusion relationship exists between a product entity and an efficacy when a product entity, the efficacy entity and a preset fourth predicate representing the inclusion relationship appear in a same text block of the social media information through a relationship model of the product + the fourth predicate + the efficacy;
and (3) referring to the product + emotion judgment relation model through the KOL, when a product entity and a preset emotion word appear in an article published by the KOL entity through the social media information, determining that the emotion judgment is positive through the emotion word, determining that the KOL entity is a KOL giving a good comment to the product entity, determining that the emotion judgment is negative through the emotion word, and determining that the KOL entity is a KOL giving a poor comment to the product entity.
6. The method of claim 3, wherein the extracting entity relationships from the labeled social media information through the trained relationship model comprises or or more ways:
determining that a positive emotional relationship or a negative emotional relationship exists between a product entity and a use scene entity through emotional word judgment when the product entity, the use scene entity and a preset emotional word appear in a same text block of the social media information through a relation model of product + use scene + emotional judgment;
and determining that the product entities are in the relationship of the product and the competitive product when two or more product entities appear in the same text block of the social media information and a preset fifth predicate representing a competitive relationship exists through a relationship model of two or more product + fifth predicate.
7. The method of claim 4, wherein the extracting entity relationships from the labeled social media information through the trained relationship model comprises or or more ways:
through a relation model of consumer mentioning product + emotion judgment, when a product entity and a preset emotion word appear in an article published by a consumer entity through the social media information, determining that the emotion judgment is positive through the emotion word, determining that the consumer entity is a good consumer for the product entity, and determining that the emotion judgment is negative through the emotion word, and determining that the consumer entity is a bad consumer for the product entity;
through a relation model of brand and emotion judgment mentioned by a consumer, when a brand entity and a preset emotion word appear in an article published by the consumer entity through the social media information, determining that the emotion judgment is positive through the emotion word, determining that the consumer entity is a good-rated consumer for the brand entity, determining that the emotion judgment is negative through the emotion word, and determining that the consumer entity is a bad-rated consumer for the brand entity;
determining the attention degree of the consumer to the efficacy according to the frequency of the efficacy entities appearing in the preset time length when the efficacy entities appear in the articles published by the consumer entity through the social media information through a relation model of the efficacy mentioned by the consumer;
determining the preference of the consumer for each interest according to the frequency of each interest entity appearing in a preset time length when the interest entity appears in an article published by the consumer entity through the social media information through a relation model of the consumer mentioning the interest;
and determining the preference of the consumer for each program according to the frequency of each program entity appearing in the preset time length when the program entity appears in the article published by the consumer entity through the social media information through the relation model of the consumer mentioning the program.
8. The method of any of claims 1-7, wherein constructing a knowledge graph of social media based on relationships between the entities as determined by a relationship model comprises:
and constructing a knowledge graph of the social media according to the relationship between the entities determined by the relationship model and the preset fixed relationship between the partial entities.
computer storage media having stored thereon computer-executable instructions for performing the method of enabling information analysis of any of claims 1-8 .
10, system comprising a memory and a processor, wherein,
the processor is configured to execute program instructions in the memory;
the program instructions read by a processor to perform the method for performing information analysis according to any of claims 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910977377.5A CN110737845A (en) | 2019-10-15 | 2019-10-15 | method, computer storage medium and system for realizing information analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910977377.5A CN110737845A (en) | 2019-10-15 | 2019-10-15 | method, computer storage medium and system for realizing information analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110737845A true CN110737845A (en) | 2020-01-31 |
Family
ID=69269329
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910977377.5A Pending CN110737845A (en) | 2019-10-15 | 2019-10-15 | method, computer storage medium and system for realizing information analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110737845A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112182244A (en) * | 2020-09-28 | 2021-01-05 | 时趣互动(北京)科技有限公司 | Brand knowledge graph construction method and device and terminal |
CN112463915A (en) * | 2021-02-02 | 2021-03-09 | 冠传网络科技(南京)有限公司 | Method, system and storage medium for mining social media comments of makeup product |
CN113420677A (en) * | 2021-06-25 | 2021-09-21 | 联仁健康医疗大数据科技股份有限公司 | Method and device for determining reasonable image, electronic equipment and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090216563A1 (en) * | 2008-02-25 | 2009-08-27 | Michael Sandoval | Electronic profile development, storage, use and systems for taking action based thereon |
CN103984777A (en) * | 2014-06-06 | 2014-08-13 | 浪潮电子信息产业股份有限公司 | Public opinion analysis system optimization method based on database synchronization |
CN104199972A (en) * | 2013-09-22 | 2014-12-10 | 中科嘉速(北京)并行软件有限公司 | Named entity relation extraction and construction method based on deep learning |
CN106327211A (en) * | 2016-08-25 | 2017-01-11 | 互动派科技股份有限公司 | SCRM system based on social media and development method thereof |
CN108038200A (en) * | 2017-12-12 | 2018-05-15 | 北京百度网讯科技有限公司 | Method and apparatus for storing data |
CN108984675A (en) * | 2018-07-02 | 2018-12-11 | 北京百度网讯科技有限公司 | Data query method and apparatus based on evaluation |
CN110188191A (en) * | 2019-04-08 | 2019-08-30 | 北京邮电大学 | A kind of entity relationship map construction method and system for Web Community's text |
-
2019
- 2019-10-15 CN CN201910977377.5A patent/CN110737845A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090216563A1 (en) * | 2008-02-25 | 2009-08-27 | Michael Sandoval | Electronic profile development, storage, use and systems for taking action based thereon |
CN104199972A (en) * | 2013-09-22 | 2014-12-10 | 中科嘉速(北京)并行软件有限公司 | Named entity relation extraction and construction method based on deep learning |
CN103984777A (en) * | 2014-06-06 | 2014-08-13 | 浪潮电子信息产业股份有限公司 | Public opinion analysis system optimization method based on database synchronization |
CN106327211A (en) * | 2016-08-25 | 2017-01-11 | 互动派科技股份有限公司 | SCRM system based on social media and development method thereof |
CN108038200A (en) * | 2017-12-12 | 2018-05-15 | 北京百度网讯科技有限公司 | Method and apparatus for storing data |
CN108984675A (en) * | 2018-07-02 | 2018-12-11 | 北京百度网讯科技有限公司 | Data query method and apparatus based on evaluation |
CN110188191A (en) * | 2019-04-08 | 2019-08-30 | 北京邮电大学 | A kind of entity relationship map construction method and system for Web Community's text |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112182244A (en) * | 2020-09-28 | 2021-01-05 | 时趣互动(北京)科技有限公司 | Brand knowledge graph construction method and device and terminal |
CN112463915A (en) * | 2021-02-02 | 2021-03-09 | 冠传网络科技(南京)有限公司 | Method, system and storage medium for mining social media comments of makeup product |
CN113420677A (en) * | 2021-06-25 | 2021-09-21 | 联仁健康医疗大数据科技股份有限公司 | Method and device for determining reasonable image, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107346336B (en) | Information processing method and device based on artificial intelligence | |
CN106302085B (en) | Recommendation method and system for instant messaging group | |
EP2506522B1 (en) | Method and device for pushing data | |
WO2019084810A1 (en) | Information processing method and terminal, and computer storage medium | |
WO2016197767A2 (en) | Method and device for inputting expression, terminal, and computer readable storage medium | |
CN108520046B (en) | Method and device for searching chat records | |
Gruber | Quoting and retweeting as communicative practices in computer mediated discourse | |
KR20160055930A (en) | Systems and methods for actively composing content for use in continuous social communication | |
WO2012011092A1 (en) | System, method and device for intelligent textual conversation system | |
CN105868267B (en) | A kind of modeling method of mobile social networking user interest | |
CN110737845A (en) | method, computer storage medium and system for realizing information analysis | |
WO2015196987A1 (en) | Natural language supported data query method, open platform and user terminal | |
CN109992781B (en) | Text feature processing method and device and storage medium | |
CN111107444B (en) | User comment generation method, electronic device and storage medium | |
CN111027838B (en) | Crowd-sourced task pushing method, device, equipment and storage medium thereof | |
CN108600083A (en) | Message prompt method and equipment | |
Santovena Casal | Conversations, debates and affiliation networks on Twitter. | |
CN110475158B (en) | Video learning material providing method and device, electronic equipment and readable medium | |
JP2011053992A (en) | Question recommending device, method and program | |
CN110505143A (en) | It is a kind of for sending the method and apparatus of target video | |
JP2014142738A (en) | Management method, management device and management program | |
CN111787042A (en) | Method and device for pushing information | |
CN110633410A (en) | Information processing method and device, storage medium, and electronic device | |
CN107483595B (en) | Information pushing method and device | |
JP5102883B2 (en) | User utterance extraction apparatus, method and program |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20201224 Address after: A108, 1 / F, curling hall, winter training center, 68 Shijingshan Road, Shijingshan District, Beijing 100041 Applicant after: Beijing second hand Artificial Intelligence Technology Co.,Ltd. Address before: 100080 area C, 3rd floor, building 2, zone B, Dongsheng Science Park, Zhongguancun, Haidian District, Beijing Applicant before: ADMASTER TECHNOLOGY (BEIJING) Co.,Ltd. |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200131 |