CN114090771A - Big data based propagation proposition and consumer story analysis method and system - Google Patents
Big data based propagation proposition and consumer story analysis method and system Download PDFInfo
- Publication number
- CN114090771A CN114090771A CN202111217851.8A CN202111217851A CN114090771A CN 114090771 A CN114090771 A CN 114090771A CN 202111217851 A CN202111217851 A CN 202111217851A CN 114090771 A CN114090771 A CN 114090771A
- Authority
- CN
- China
- Prior art keywords
- elements
- consumer
- story
- data
- combination
- 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
- 238000004458 analytical method Methods 0.000 title claims description 25
- 238000007405 data analysis Methods 0.000 claims abstract description 30
- 238000005065 mining Methods 0.000 claims abstract description 27
- 238000010586 diagram Methods 0.000 claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims description 10
- 230000002996 emotional effect Effects 0.000 claims description 7
- 230000000630 rising effect Effects 0.000 claims description 4
- 230000001174 ascending effect Effects 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 230000036651 mood Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000008451 emotion Effects 0.000 description 14
- 238000011160 research Methods 0.000 description 7
- 230000006399 behavior Effects 0.000 description 3
- 230000001902 propagating effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 208000035475 disorder Diseases 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000686 essence Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- 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
- G06F16/35—Clustering; Classification
- G06F16/358—Browsing; Visualisation therefor
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
- G06F2216/03—Data mining
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Databases & Information Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for analyzing propagation claims and consumption stories based on big data, wherein the method comprises the following steps: s1: acquiring consumer internet data; s2: mining the acquired data by using an element mining algorithm to output concept elements related to the attention categories of the target consumers; s3: classifying the concept elements, then performing data analysis on each type of elements, and scoring a story model according to data analysis results; s4: integrating the essential elements into different element combinations according to different requirements of consumers, associating every two elements in each combination, calculating the associated acoustic quantity of each element combination, and taking the element combination with the maximum associated acoustic quantity as an optimal combination; s5: and combining and representing the two related elements into a mor-base diagram, and mining and expanding the element content in the range of the concerned element points by using the mor-base diagram. The invention improves the data processing and analyzing efficiency, reduces the manual investment, and provides a convenient new story generating path through the disassembly and combination of elements.
Description
Technical Field
The invention relates to the technical field of big data analysis, in particular to a big data-based propagation proposition and consumer story analysis method and system.
Background
The propagation assertion research is crucial for the enterprise to gain insight into the market. Whether the marketing research department carries out marketing insights of consumers or the marketing department positions products/brands, declares marketing propagation advices of brands/activities, produces advertisements and creatives and produces official content, the marketing research department does not research the propagation advices and analyzes and summarizes the consumer stories.
However, in the internet, User Generated Content (UGC) sounds are mostly disordered and appear as a multivariate dispersion of sound production platforms, data disorder, difficult collection and statistical analysis, and uneven sound quality. Traditional analytical research methods have difficulty in deeply parsing the propagation claims underlying large data information and constructing consumer stories. This has led to the inefficiency of propagating the claimed insights under traditional research methods and techniques, such as "who they are, based on what scenario purchase? What pain point is a solution in the market? What are also the potential needs? "and the like, which are closely related to consumer cognition, and cannot be systematically and comprehensively perceived and grasped.
In the prior art, the publication numbers are: the CN106779827A chinese invention patent discloses a big data method for internet user behavior collection and analysis detection in 2017, 5 and 31, which includes: (1) collecting and preprocessing data; (2) analyzing and mining data; (3) the results of the data analysis are utilized. Collecting internet user data, mainly microblog data, qq data and WeChat data, including personal basic information and network speech data of a user; and main internet business data, including e-commerce, industry forums, portal website related channels, mainly goods, goods sales, user evaluation, etc.; the collection is carried out by self-building a computing cluster, and undisclosed information, such as age prediction and the like, is predicted and supplemented according to the public information. Although the scheme acquires and analyzes the internet user behavior data, the propagation claims are not analyzed, and the consumer story is not subjected to fine analysis and research.
Disclosure of Invention
The invention provides a method and a system for propagating advocates and consumer story analysis based on big data, aiming at overcoming the defects that the prior art is lack of propagating advocates and consumer story analysis based on big data.
The primary objective of the present invention is to solve the above technical problems, and the technical solution of the present invention is as follows:
a big data based propagation proposition and consumption story analysis method comprises the following steps:
s1: acquiring consumer internet data;
s2: mining the acquired data by using an element mining algorithm to output concept elements related to the attention categories of the target consumers;
s3: classifying the concept elements, then performing data analysis on each type of elements, and scoring a story model according to data analysis results;
s4: integrating the essential elements into different element combinations according to different requirements of consumers, associating every two elements in each combination, calculating the associated acoustic quantity of each element combination, and taking the element combination with the maximum associated acoustic quantity as an optimal combination;
s5: and combining and representing the two related elements into a mor-base diagram, and mining and expanding the element content in the range of the concerned element points by using the mor-base diagram.
Further, the channels for consumer internet data acquisition include: general social media, forum websites, industry vertical forums.
Further, in step S2, the specific steps of mining the acquired data by using the element mining algorithm and outputting the concept elements related to the target consumer interest categories include:
determining the marked elements;
labeling the training data;
pre-training the existing named entity recognition model by utilizing a method for fine tuning the pre-training model, so that the named entity recognition model learns the information in the labeled data;
and inputting the text to be analyzed into the trained named entity recognition model, and outputting the concept elements.
Further, the step S3 of classifying the concept elements, then performing data analysis on each class of elements, and scoring the story model according to the data analysis result includes the specific steps of:
dividing concept elements into five types, and performing data analysis on each element type, wherein the data analysis comprises the following steps: heat ranking and rising speed ranking analysis based on the sound volume;
and inputting the data analysis result into the story model for scoring to obtain the story score of the consumer.
Further, the heat ranking based on the sound volume is calculated through the article mentioning sound volume value of the target elements appearing on the Internet within the screening time range; the ascending speed ranking is calculated according to the sound volume increase condition of the target element in each month in the past period.
Further, the story model is scored by three aspects of indicators: story type, mood of characters in the article, overall richness of the story.
Further, in step S4, the elements are integrated into different element combinations according to different requirements of the consumer, wherein the combinations taking emotional appeal of the consumer as requirements include the following element types: emotional demand, self-description, demand scenario; the combination with the product experience of the consumer as the demand comprises the following element types: pain point of the product, self description, use scenario.
Further, the specific process of step S4 is:
integrating the elements into different element combinations according to different requirements of consumers, associating every two elements in each combination, calculating the associated sound volume of each element combination, taking the element combination with the maximum associated sound volume as the optimal solution of the corresponding type combination, calculating a recommendation index according to the requirements and specific requirements of the users, and outputting the optimal combination.
Further, the thickness of a connecting line between two elements in the morgan diagram represents the degree of association between the two elements, the thicker the connecting line, the higher the association between the two elements, and the thinner the connecting line, the lower the association between the two elements.
The invention provides a big data based propagation proposition and consumer story analysis system, which comprises a memory and a processor, wherein the memory comprises a big data based propagation proposition and consumer story analysis method program, and the big data based propagation proposition and consumer story analysis method program realizes the following steps when being executed by the processor:
s1: acquiring consumer internet data;
s2: mining the acquired data by using an element mining algorithm to output concept elements related to the attention categories of the target consumers;
s3: classifying the concept elements, then performing data analysis on each type of elements, and scoring a story model according to data analysis results;
s4: integrating the essential elements into different element combinations according to different requirements of consumers, associating every two elements in each combination, calculating the associated acoustic quantity of each element combination, and taking the element combination with the maximum associated acoustic quantity as an optimal combination;
s5: and combining and representing the two related elements into a mor-base diagram, and mining and expanding the element content in the range of the concerned element points by using the mor-base diagram.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that:
according to the invention, based on the acquired consumer internet data, the optimal combination is further obtained through element association through element extraction, classification and story scoring, and simultaneously, element content can be mined and expanded based on pairwise associated elements.
Drawings
FIG. 1 is a flow chart of a big data-based propagation proposition and consumption story analysis method of the present invention.
FIG. 2 is a diagram illustrating the content of elements expanded by the Morse base diagram in combination with the knowledge-graph tool according to the embodiment of the present invention.
Fig. 3 is a block diagram of a big data-based propagation proposition and consumption story analysis system of the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
Example 1
As shown in fig. 1, a big data based propagation proposition and consumption story analysis method includes the following steps:
s1: acquiring consumer internet data;
it should be noted that the consumer internet data in the present invention may be product usage logs, product experience shares, etc. posted by consumers in forums or sites, the consumer internet data may be obtained from data sites where consumers have popular statements, and data points that are valuable only in data sites where feedback sounds of real consumer products of consumers exist are set, and in a specific implementation process, based on characteristics of industry categories, specific sites, such as general social media and forum websites, may provide consumer feedback sound collection for multiple category industries, and automobile industry categories, mother and infant industry categories may obtain consumer internet data through industry vertical forums.
S2: mining the acquired data by using an element mining algorithm to output concept elements related to the attention categories of the target consumers;
it should be noted that, since the consumer internet data obtained in step S1 is generally multivariate and scattered, it is necessary to mine concept elements related to consumer stories, in the present invention, the concept elements related to the target consumer interest categories are mined and output for the obtained data by using an element mining algorithm; the method comprises the following specific steps:
determining the marked elements;
labeling the training data;
pre-training the existing named entity recognition model by utilizing a method for fine tuning the pre-training model, so that the named entity recognition model learns the information in the labeled data;
and inputting the text to be analyzed into the trained named entity recognition model, and outputting the concept elements.
It should be noted that the training data may be selected from the internet data of the consumer obtained in step S1.
S3: classifying the concept elements, then performing data analysis on each type of elements, and scoring a story model according to data analysis results;
in the present invention, the concept elements are extracted from step S2, and classified into 5 categories, including: setting people, a demand scene, an emotional demand, a use scene and a product pain point; performing data analysis on each different element type, wherein the data analysis comprises heat ranking and rising speed ranking based on the sound volume, and the heat ranking based on the sound volume is calculated by the article mentioning sound volume value of the target element appearing on the Internet in the screening time range; the ascending speed ranking is calculated according to the sound volume increase condition of the target element in each month in the past period. The heat ranking and the rising speed ranking are set to facilitate independent comparison in related types in the follow-up process, namely in a certain industry class, the requirement scene or emotion requirement is most typical, and what is the most needed problem to be solved in a short term helps practitioners to quickly identify and obtain data analysis results;
and further, inputting the data analysis result into a story model for scoring to obtain a consumer story score. After the consumer story scores are obtained, the consumer story scores can be ranked according to the scores, and a most important story arrangement output is provided for practitioners.
In the invention, the story model is scored according to three indexes: story type, mood of characters in the article, overall richness of the story. The story type, namely the internet data of the consumers comprises product experience, life records, popular science articles, questioning contents, marketing advertisements and the like, different article types represent the article quality with different service values, different articles have different quality preferences, and the score of the story type index is correspondingly high compared with the high-quality content related to real consumer users.
The emotion of the character in the article is a description of the emotion in the internet data of the consumer, and the emotion of the character comprises: the fluctuation degree of the emotion is positive emotion and negative emotion, and the complexity degree of the emotion comprises: the expressions of basic simple emotions and the statements of complex emotions, such as words such as 'difficult to go up', 'logistics speed is ultra fast', 'the expectation of the thoughts of mind' and the like express positive emotions and also express basic simple emotions, and different emotion fluctuation degrees and emotion complexity degrees correspond to different scores.
The overall richness of the story is the number of concept elements, and the more the article contains the concept elements, the higher the overall richness score.
S4: integrating the essential elements into different element combinations according to different requirements of consumers, associating every two elements in each combination, calculating the associated acoustic quantity of each element combination, and taking the element combination with the maximum associated acoustic quantity as an optimal combination;
in the invention, the essences are integrated into different element combinations according to different requirements of consumers, wherein the combination taking the emotional appeal of the consumers as the requirements comprises the following element types: emotional demand, self-description, demand scenario; the combination with the product experience of the consumer as the demand comprises the following element types: pain point of the product, self description, use scenario.
More specifically, the key elements are integrated into different element combinations according to different requirements of consumers, every two element combinations in each combination are associated, the associated sound volume of each element combination is calculated, the element combination with the maximum associated sound volume is used as the optimal solution of the corresponding type combination, the recommendation index is calculated according to the requirements and specific appeal of the users, and the optimal combination is output.
It should be noted that, in the present invention, the associated sound volume refers to the common reference, and two elements are often referred to together in a story;
s5: and combining and representing the two related elements into a mor-base diagram, and mining and expanding the element content in the range of the concerned element points by using the mor-base diagram.
It should be noted that, after the two associated elements are combined and generated in step S4, the system can help business personnel to quickly generate a sang-based diagram from a business perspective to show the association relationship and the story line between the behaviors and preferences of the user, wherein the thicker the connecting line between the two elements in the sang-based diagram is, the higher the association degree of the two elements is, i.e. the more times of co-mentioning is, the thinner the connecting line is, the less times of co-mentioning is, and the lower the association degree is. In a specific embodiment, after the presentation of the morji diagram helps business personnel to complete basic item association relationship overview, based on a certain story link point, a user can continue to freely explore and expand based on the result of the morji diagram, and in combination with the existing knowledge graph tool, in the range of concerned element points, related element contents can be rapidly mined or expanded through knowledge association and expansion of the knowledge graph. Fig. 2 is a schematic diagram illustrating the content of elements expanded by combining the morgan diagram with the knowledge-graph tool in this embodiment.
As shown in fig. 3, a second aspect of the present invention provides a big data based propagation proposition and consumer story analysis system, including a memory and a processor, where the memory includes a big data based propagation proposition and consumer story analysis method program, and the big data based propagation proposition and consumer story analysis method program, when executed by the processor, implements the following steps:
s1: acquiring consumer internet data;
s2: mining the acquired data by using an element mining algorithm to output concept elements related to the attention categories of the target consumers;
s3: classifying the concept elements, then performing data analysis on each type of elements, and scoring a story model according to data analysis results;
s4: integrating the essential elements into different element combinations according to different requirements of consumers, associating every two elements in each combination, calculating the associated acoustic quantity of each element combination, and taking the element combination with the maximum associated acoustic quantity as an optimal combination;
s5: and combining and representing the two related elements into a mor-base diagram, and mining and expanding the element content in the range of the concerned element points by using the mor-base diagram.
It should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. A big data-based propagation proposition and consumption story analysis method is characterized by comprising the following steps:
s1: acquiring consumer internet data;
s2: mining the acquired data by using an element mining algorithm to output concept elements related to the attention categories of the target consumers;
s3: classifying the concept elements, then performing data analysis on each type of elements, and scoring a story model according to data analysis results;
s4: integrating concept elements into different element combinations according to different requirements of consumers, associating every two elements in each combination, calculating the associated acoustic quantity of each element combination, and taking the element combination with the maximum associated acoustic quantity as an optimal combination;
s5: and combining and representing the two related elements into a mor-base diagram, and mining and expanding the element content in the range of the concerned element points by using the mor-base diagram.
2. The big data based propagation claim and consumer story analysis method as claimed in claim 1, wherein the channel of consumer internet data acquisition comprises: general social media, forum websites, industry vertical forums.
3. The big data-based propagation claim and consumer story analysis method according to claim 1, wherein the step S2 of mining the obtained data by using the element mining algorithm to output concept elements related to the target consumer interest categories comprises the specific steps of:
determining the marked elements;
labeling the training data;
pre-training the existing named entity recognition model by utilizing a method for fine tuning the pre-training model, so that the named entity recognition model learns the information in the labeled data;
and inputting the text to be analyzed into the trained named entity recognition model, and outputting the concept elements.
4. The big data based propagation claim and consumer story analysis method as claimed in claim 1, wherein the step of classifying concept elements in step S3, then performing data analysis on each class of elements, and the specific step of performing story model scoring according to the data analysis result comprises:
dividing concept elements into five types, and performing data analysis on each element type, wherein the data analysis comprises the following steps: heat ranking and rising speed ranking analysis based on the sound volume;
and inputting the data analysis result into the story model for scoring to obtain the story score of the consumer.
5. The big data based propagation claim and consumer story analysis method as claimed in claim 4, wherein the volume-based ranking of heat is calculated by the volume value of article mentioning that the target element appears in the internet within the time frame of screening; the ascending speed ranking is calculated according to the sound volume increase condition of the target element in each month in the past period.
6. The big data based propagation claim and consumer story analysis method of claim 4, wherein the story model is scored by three aspects of indicators: story type, mood of characters in the article, overall richness of the story.
7. The big data based propagation claim and consumer story analysis method of claim 1, wherein the step S4 is implemented by integrating the elements into different element combinations according to different requirements of the consumer, wherein the combination using the emotional appeal of the consumer as the requirement comprises the following element types: emotional demand, self-description, demand scenario; the combination with the product experience of the consumer as the demand comprises the following element types: pain point of the product, self description, use scenario.
8. The big data-based propagation claim and consumer story analysis method according to claim 1, wherein the specific process of step S4 is as follows:
integrating the elements into different element combinations according to different requirements of consumers, associating every two elements in each combination, calculating the associated sound volume of each element combination, taking the element combination with the maximum associated sound volume as the optimal solution of the corresponding type combination, calculating a recommendation index according to the requirements and specific appeal of the users, and outputting the optimal combination.
9. The big-data-based propagation claim and consumer story analysis method as claimed in claim 1, wherein the thickness of the connecting line between two elements in the morgan diagram represents the degree of association between the two elements, the thicker the connecting line, the higher the association between the two elements, and the thinner the connecting line, the lower the association between the two elements.
10. A big data based propagation proposition and consumer story analysis system, comprising a memory and a processor, the memory including a big data based propagation proposition and consumer story analysis method program, the big data based propagation proposition and consumer story analysis method program when executed by the processor implementing the steps of:
s1: acquiring consumer internet data;
s2: mining the acquired data by using an element mining algorithm to output concept elements related to the attention categories of the target consumers;
s3: classifying the concept elements, then performing data analysis on each type of elements, and scoring a story model according to data analysis results;
s4: integrating concept elements into different element combinations according to different requirements of consumers, associating every two elements in each combination, calculating the associated acoustic quantity of each element combination, and taking the element combination with the maximum associated acoustic quantity as an optimal combination;
s5: and combining and representing the two related elements into a mor-base diagram, and mining and expanding the element content in the range of the concerned element points by using the mor-base diagram.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111217851.8A CN114090771A (en) | 2021-10-19 | 2021-10-19 | Big data based propagation proposition and consumer story analysis method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111217851.8A CN114090771A (en) | 2021-10-19 | 2021-10-19 | Big data based propagation proposition and consumer story analysis method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114090771A true CN114090771A (en) | 2022-02-25 |
Family
ID=80297190
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111217851.8A Pending CN114090771A (en) | 2021-10-19 | 2021-10-19 | Big data based propagation proposition and consumer story analysis method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114090771A (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1664819A (en) * | 2004-03-02 | 2005-09-07 | 微软公司 | Principles and methods for personalizing newsfeeds via an analysis of information dynamics |
US20090187736A1 (en) * | 2005-10-26 | 2009-07-23 | Cortica Ltd. | Computing Device, a System and a Method for Parallel Processing of Data Streams |
CN103559207A (en) * | 2013-10-10 | 2014-02-05 | 江苏名通信息科技有限公司 | Financial behavior analyzing system based on social media calculation |
US20140163965A1 (en) * | 2012-07-20 | 2014-06-12 | Veveo, Inc. | Method of and System for Using Conversation State Information in a Conversational Interaction System |
CN105022733A (en) * | 2014-04-18 | 2015-11-04 | 中科鼎富(北京)科技发展有限公司 | DINFO-OEC text analysis mining method and device thereof |
US20170098002A1 (en) * | 2015-10-02 | 2017-04-06 | Outlier AI, Inc. | System, apparatus, and method to identify intelligence using a data processing platform |
WO2018036239A1 (en) * | 2016-08-24 | 2018-03-01 | 慧科讯业有限公司 | Method, apparatus and system for monitoring internet media events based on industry knowledge mapping database |
CN109478205A (en) * | 2016-06-24 | 2019-03-15 | 元素认知有限责任公司 | Architecture and method for computer learning and understanding |
US20190340250A1 (en) * | 2018-05-02 | 2019-11-07 | International Business Machines Corporation | Associating characters to story topics derived from social media content |
CN111241300A (en) * | 2020-01-09 | 2020-06-05 | 中信银行股份有限公司 | Public opinion early warning and risk propagation analysis method, system, equipment and storage medium |
-
2021
- 2021-10-19 CN CN202111217851.8A patent/CN114090771A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1664819A (en) * | 2004-03-02 | 2005-09-07 | 微软公司 | Principles and methods for personalizing newsfeeds via an analysis of information dynamics |
US20090187736A1 (en) * | 2005-10-26 | 2009-07-23 | Cortica Ltd. | Computing Device, a System and a Method for Parallel Processing of Data Streams |
US20140163965A1 (en) * | 2012-07-20 | 2014-06-12 | Veveo, Inc. | Method of and System for Using Conversation State Information in a Conversational Interaction System |
CN103559207A (en) * | 2013-10-10 | 2014-02-05 | 江苏名通信息科技有限公司 | Financial behavior analyzing system based on social media calculation |
CN105022733A (en) * | 2014-04-18 | 2015-11-04 | 中科鼎富(北京)科技发展有限公司 | DINFO-OEC text analysis mining method and device thereof |
US20170098002A1 (en) * | 2015-10-02 | 2017-04-06 | Outlier AI, Inc. | System, apparatus, and method to identify intelligence using a data processing platform |
CN109478205A (en) * | 2016-06-24 | 2019-03-15 | 元素认知有限责任公司 | Architecture and method for computer learning and understanding |
WO2018036239A1 (en) * | 2016-08-24 | 2018-03-01 | 慧科讯业有限公司 | Method, apparatus and system for monitoring internet media events based on industry knowledge mapping database |
US20190340250A1 (en) * | 2018-05-02 | 2019-11-07 | International Business Machines Corporation | Associating characters to story topics derived from social media content |
CN111241300A (en) * | 2020-01-09 | 2020-06-05 | 中信银行股份有限公司 | Public opinion early warning and risk propagation analysis method, system, equipment and storage medium |
Non-Patent Citations (1)
Title |
---|
BO-WEI CHEN等: ""A Novel Video Summarization Based on Mining the Story-Structure and Semantic Relations Among Concept Entities"", 《 IEEE TRANSACTIONS ON MULTIMEDIA》, 31 October 2009 (2009-10-31), pages 295 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107918818B (en) | Supply chain management decision support system based on big data technology | |
US20160098480A1 (en) | Author moderated sentiment classification method and system | |
US10366117B2 (en) | Computer-implemented systems and methods for taxonomy development | |
Tyagi et al. | Sentiment analysis using logistic regression and effective word score heuristic | |
US20140304814A1 (en) | System and methods for automatically detecting deceptive content | |
KR20120109943A (en) | Emotion classification method for analysis of emotion immanent in sentence | |
CN109902229B (en) | Comment-based interpretable recommendation method | |
Zamani et al. | Sentiment analysis: determining people’s emotions in Facebook | |
Solomon et al. | Understanding the psycho-sociological facets of homophily in social network communities | |
Kachamas et al. | Application of artificial intelligent in the prediction of consumer behavior from Facebook posts analysis | |
Zhang et al. | Using neutral sentiment reviews to improve customer requirement identification and product design strategies | |
Awrahman et al. | Sentiment analysis and opinion mining within social networks using konstanz information miner | |
CN112115712A (en) | Topic-based group emotion analysis method | |
Gutiérrez | A comparative study of NLP and machine learning techniques for sentiment analysis and topic modeling on amazon | |
Qian et al. | Product Success Evaluation Model Based on Star Ratings, Reviews and Product Popularity | |
US20240062264A1 (en) | Ai- backed e-commerce for all the top rated products on a single platform | |
CN114090771A (en) | Big data based propagation proposition and consumer story analysis method and system | |
Namvar | A Novel Approach to Predict the Helpfulness of Online Reviews. | |
Song et al. | Research on product quality evaluation based on big data analysis | |
CN111967251A (en) | Intelligent customer sound insight system | |
Chenna et al. | Emotion And Sentiment Analysis From Twitter Text | |
Tsao et al. | From mining to meaning: How B2B marketers can leverage text to inform strategy | |
De et al. | Sentiment analysis on product purchase through e commerce | |
Lase et al. | Mental Health Sentiment Analysis on Social Media TikTok with the Naïve Bayes Algorithm | |
Drus et al. | It Takes Three to Tango: Understanding the World of Online Gossips through Netnography, Big Data Topic Modelling and Sentiment Analysis |
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 |