CN112579866B - Method for analyzing event development trend based on time heat index - Google Patents
Method for analyzing event development trend based on time heat index Download PDFInfo
- Publication number
- CN112579866B CN112579866B CN202011448341.7A CN202011448341A CN112579866B CN 112579866 B CN112579866 B CN 112579866B CN 202011448341 A CN202011448341 A CN 202011448341A CN 112579866 B CN112579866 B CN 112579866B
- Authority
- CN
- China
- Prior art keywords
- weight
- development trend
- time
- event
- heat
- 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
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
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention relates to a method for analyzing event development trend based on time heat index, which records the starting time t of event occurrence 1 And the current time t up to now 2 The method comprises the steps of carrying out a first treatment on the surface of the Drawing time t 1 ‑t 2 Finding out the time period marked as t with the maximum slope k based on the graph 2 '‑t 3 ' find t 2 '‑t 3 Weight type Q affecting event heat development trend in' time period m The method comprises the steps of carrying out a first treatment on the surface of the Analysis time point t 2 ' previous time period t 1 '‑t 2 ' in, time point t 3 ' last time period t 3 '‑t 4 In' weight types affecting the trend of event heat development are respectively marked as P n And G j And then, carrying out heat development trend p analysis, wherein the invention can analyze the future development trend of the event based on the initial development trend of the event and two indexes of time and heat index, and analyze according to the weight affecting the heat index of the event in the development trend.
Description
Technical Field
The invention relates to the field of event heat analysis, in particular to a method for analyzing event development trend based on a time heat index.
Background
The event heat index is an important index for measuring the value, and in the process of analyzing the event heat index, two indexes of time and heat index are generally considered, so that the analysis of the existing hot event can only be realized, the prediction of the hot event can not be performed, and the future development trend of the event is not guided.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a method for analyzing the event development trend based on a time heat index, which can analyze the future development trend of an event based on the initial development trend of the event and two indexes of the time and the heat index and analyze the future development trend of the event according to the weight affecting the heat index of the event in the development trend.
The aim of the invention is realized by the following technical scheme:
a method for analyzing event development trend based on a time heat index, the method comprising:
s100: recording the starting time t 1 of the event occurrence and the current time t 2 up to now;
s200: analyzing the heat development trend p of the event along with time t 1-t 2 in a time period t 1-t 2 based on big data analysis and a heat index evaluation model, and drawing a graph;
s300: finding out a time period with the maximum slope k as t 2'-t 3' based on the graph, and finding out weight types Q m affecting the event heat development trend in the time period of t 2'-t 3', wherein m is the number of the weight types;
s400: analyzing weight types affecting the heat development trend of the event in a period t 1'-t 2' before a time point t 2 'and in a period t 3' -t 4 'after a time point t 3', and respectively marking as P n and G j, wherein n and j respectively represent the number of the weight types;
s500: and (3) analyzing the heat development trend p, wherein the heat development trend p comprises the following three conditions:
(1) The weight types Q m and P n and G j are all the same, and the index variation of each weight is analyzed, so that the weight type affecting the heat development trend p is obtained, and the control of the event development trend is realized by adjusting the index of the weight type;
(2) The weight types Q m, P n and G j are newly increased or decreased, and the indexes of the same weight types are unchanged, the newly increased or decreased weight types are analyzed to obtain weight types affecting the heat development trend p, and the control of the event development trend is realized by adjusting the indexes of the weight types;
(3) The weight types Q m, P n and G j are newly increased or decreased, and indexes of the same weight type are also changed, so that the weight type affecting the change of the heat development trend p is further analyzed by taking the part of weight types with the newly increased or decreased weight types as a whole, and the control of the event development trend is realized by adjusting the index of the weight type.
Further, the time period t 2'-t 3' is a time period with the maximum slope k determined by traversing the time period t 1-t 2.
Further, in the traversing process, the minimum time unit changed according to the slope k is sequentially traversed as a time node, and the part with the same slope is used as an integral time period.
Further, the time t 1'-t 2' is a period of constant slope k before the time point t 2', and the time period t 3' -t 4 'is a period of constant slope k after the time point t 3'.
Further, the specific steps of (3) in S500 are as follows:
s01: listing changed weight types, including a newly added weight type or a reduced weight type, and a type in which a weight index is changed, wherein the newly added weight type is an increased weight type of a time period t 2'-t 3' compared with a time period t 1'-t 2', and the reduced weight type is a weight type of a time period t 3'-t 4' compared with a time period t 2'-t 3';
s02: the substantial influence quantity of the weight type in S01 on the event heat development trend p is specifically analyzed, and the substantial influence quantity is arranged from high to low, so that the weight type with the largest influence on the heat development trend p is obtained;
s03: and the control of the event development trend is realized by adjusting the weight type which has the greatest influence on the heat development trend p or adjusting all the weight types which generate the change in proportion.
Further, the substantial influence in S02 includes a sum of the reading amount and the propagation amount.
Further, the propagation volume includes forwarding and referencing.
The beneficial effects of the invention are as follows: compared with the traditional event analysis, the method and the system have the advantages that the curve graph formed by the two indexes of the time index and the heat index is utilized, and the explosion point of the event is analyzed or predicted based on the heat change rate, namely the slope of the curve, so that the index affecting the heat of the event is found.
Drawings
Fig. 1 is a schematic diagram of the present invention.
Detailed Description
The technical scheme of the present invention is described in further detail below with reference to specific embodiments, but the scope of the present invention is not limited to the following description.
A method for analyzing event development trend based on a time heat index, the method comprising:
s100: recording the starting time t 1 of the event occurrence and the current time t 2 up to now;
s200: based on the big data analysis and the heat index evaluation model, the heat development trend p of the event with time t 1-t 2 in the time period t 1-t 2 is analyzed, and is drawn into a graph, and is shown with reference to fig. 1. The heat index evaluation model can be any of various models known in the art. The time units are divided according to the types of the events, the events with longer fermentation time can be counted by taking days as units, and the events with rapid burst are counted by taking hours as units.
S300: and (3) finding out a time period with the maximum slope k and marking the time period as t 2'-t 3' based on the graph, and finding out a weight type Q m influencing the development trend of the event heat in the time period of t 2'-t 3', wherein m is the number of weight types, the weight mainly comprises the weight influencing the development trend of the time heat, and in event analysis, the weight mainly comprises the propagation path and the platform type of the event.
S400: analyzing weight types affecting the heat development trend of the event in a period t 1'-t 2' before a time point t 2 'and in a period t 3' -t 4 'after a time point t 3', and respectively marking as P n and G j, wherein n and j respectively represent the number of the weight types;
s500: and (3) analyzing the heat development trend p, wherein the heat development trend p comprises the following three conditions:
(1) The weight types Q m and P n and G j are all the same, the index change amount of each weight is analyzed, so that the weight type influencing the heat development trend p is obtained, the control of the event development trend is realized by adjusting the index of the weight type, and in the case, the weight type is unchanged, that is, the propagation path and the platform in the event propagation process are not changed, and the change is only whether the propagation path is optimized or not, so that the data is optimized as the index change of the path.
(2) The weight types Q m, P n and G j are newly increased or decreased, and the indexes of the same weight types are unchanged, the newly increased or decreased weight types are analyzed to obtain weight types affecting the heat development trend p, and the control of the event development trend is realized by adjusting the indexes of the weight types;
(3) The weight types Q m, P n and G j are newly increased or decreased, and indexes of the same weight type are also changed, so that the weight type affecting the change of the heat development trend p is further analyzed by taking the part of weight types with the newly increased or decreased weight types as a whole, and the control of the event development trend is realized by adjusting the index of the weight type.
Optionally, a method for analyzing the development trend of an event based on a time heat index is provided, wherein the time period t 2'-t 3' adopts a mode of traversing the time period t 1-t 2 to determine the time period with the maximum slope k.
Optionally, in the traversing process, the minimum time unit changed according to the slope k is sequentially traversed as a time node, and the part with the same slope is used as an integral time period.
Optionally, in the method for analyzing the event development trend based on the time heat index, the time t 1'-t 2' is a period of constant slope k before the time point t 2', and the time period t 3' -t 4 'is a period of constant slope k after the time point t 3'.
Optionally, a method for analyzing an event development trend based on a time heat index, and the specific steps of (3) in S500 are as follows:
s01: listing changed weight types, including a newly added weight type or a reduced weight type, and a type in which a weight index is changed, wherein the newly added weight type is an increased weight type of a time period t 2'-t 3' compared with a time period t 1'-t 2', and the reduced weight type is a weight type of a time period t 3'-t 4' compared with a time period t 2'-t 3';
s02: the substantial influence quantity of the weight type in S01 on the event heat development trend p is specifically analyzed, and the substantial influence quantity is arranged from high to low, so that the weight type with the largest influence on the heat development trend p is obtained;
s03: and the control of the event development trend is realized by adjusting the weight type which has the greatest influence on the heat development trend p or adjusting all the weight types which generate the change in proportion.
Optionally, a method for analyzing an event development trend based on a time heat index, wherein the substantial influence amount in S02 includes a sum of a reading amount and a propagation amount.
Optionally, a method for analyzing the event development trend based on the time heat index, wherein the propagation quantity comprises forwarding and quoting.
The foregoing is merely a preferred embodiment of the invention, and it is to be understood that the invention is not limited to the form disclosed herein but is not to be construed as excluding other embodiments, but is capable of numerous other combinations, modifications and environments and is capable of modifications within the scope of the inventive concept, either as taught or as a matter of routine skill or knowledge in the relevant art. And that modifications and variations which do not depart from the spirit and scope of the invention are intended to be within the scope of the appended claims.
Claims (7)
1. A method for analyzing an event development trend based on a time heat index, the method comprising:
s100: recording the start time t of event occurrence 1 And the current time t up to now 2 ；
S200: based on the big data analysis and the heat index evaluation model, the analysis is carried out in a time period t 1 -t 2 In, time t of the event 1 -t 2 Heat development trend p of (2) and drawingMaking a graph;
s300: finding a time period with the maximum slope k based on the graph, denoted as t 2 '-t 3 ' find t 2 '-t 3 Weight type Q affecting event heat development trend in' time period m Wherein m is the number of weight types;
s400: analysis time point t 2 ' previous time period t 1 '-t 2 ' in, time point t 3 ' last time period t 3 '-t 4 In' weight types affecting the trend of event heat development are respectively marked as P n And G j Wherein n, j represent the number of types of weights, respectively;
s500: and (3) analyzing the heat development trend p, wherein the heat development trend p comprises the following three conditions:
(1) Weight type Q m And P n And G j The weight types in the model (a) are all the same, and the index variation of each weight is analyzed, so that the weight type affecting the heat development trend p is obtained, and the control of the event development trend is realized by adjusting the index of the weight type;
(2) Weight type Q m And P n And G j If the weight types in the model (a) are newly increased or reduced and the indexes of the same weight types are unchanged, analyzing the newly increased or reduced weight types to obtain weight types affecting the heat development trend p, and controlling the event development trend by adjusting the indexes of the weight types;
(3) Weight type Q m And P n And G j The weight types in the model (a) are newly increased or reduced, and indexes of the same weight type are also changed, so that the weight types which influence the change of the heat development trend p are further analyzed by taking part of weight types with the changed indexes and the newly increased or reduced weight types as a whole, and the control of the event development trend is realized by adjusting the index of the weight types.
2. The method for analyzing event development trend based on time heat index as claimed in claim 1, wherein the time period t 2 '-t 3 ' employ traversal period t 1 -t 2 The time period during which the slope k is greatest.
3. The method according to claim 2, wherein the traversing process is sequentially traversed by using the minimum time unit changed according to the slope k as a time node, and using the same slope part as an overall time period.
4. A method for analyzing event development trend based on time heat index as set forth in claim 3, wherein said time t 1 '-t 2 ' is the time point t 2 ' a period of constant pre-slope k, a period of time t 3 '-t 4 ' is the time point t 3 The' post slope k is a constant segment.
5. The method for analyzing event development trend based on time heat index according to claim 4, wherein the specific steps of (3) in S500 are as follows:
s01: listing the weight types with change, including the weight type added or reduced, and the weight index changed type, wherein the weight type added is the time period t 2 '-t 3 ' compared to time period t 1 '-t 2 ' increased weight type, decreased weight type is time period t 3 '-t 4 ' in the period t 2 '-t 3 ' reduced weight type;
s02: the substantial influence quantity of the weight type in S01 on the event heat development trend p is specifically analyzed, and the substantial influence quantity is arranged from high to low, so that the weight type with the largest influence on the heat development trend p is obtained;
s03: and the control of the event development trend is realized by adjusting the weight type which has the greatest influence on the heat development trend p or adjusting all the weight types which generate the change in proportion.
6. The method of claim 5, wherein the substantial impact in S02 comprises a sum of a reading amount and a propagation amount.
7. The method of analyzing event trends based on a time heat index according to claim 6, wherein the propagation quantity includes forwarding and referencing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011448341.7A CN112579866B (en) | 2020-12-09 | 2020-12-09 | Method for analyzing event development trend based on time heat index |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011448341.7A CN112579866B (en) | 2020-12-09 | 2020-12-09 | Method for analyzing event development trend based on time heat index |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112579866A CN112579866A (en) | 2021-03-30 |
| CN112579866B true CN112579866B (en) | 2023-06-20 |
Family
ID=75132217
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011448341.7A Active CN112579866B (en) | 2020-12-09 | 2020-12-09 | Method for analyzing event development trend based on time heat index |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112579866B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016063341A1 (en) * | 2014-10-21 | 2016-04-28 | 株式会社日立製作所 | Time series prediction apparatus and time series prediction method |
| CN108549957A (en) * | 2018-04-11 | 2018-09-18 | 中译语通科技股份有限公司 | Internet topic trend auxiliary prediction technique and system, information data processing terminal |
| CN109033133A (en) * | 2018-06-01 | 2018-12-18 | 杭州电子科技大学 | Event detection and tracking based on Feature item weighting growth trend |
| CN109508416A (en) * | 2018-11-09 | 2019-03-22 | 四川大学 | Microblogging public sentiment event temperature and prediction of the development trend method based on number of reviews |
| CN111581983A (en) * | 2020-05-13 | 2020-08-25 | 中国人民解放军国防科技大学 | Method for predicting social concern hotspots in network public opinion events based on group analysis |
-
2020
- 2020-12-09 CN CN202011448341.7A patent/CN112579866B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016063341A1 (en) * | 2014-10-21 | 2016-04-28 | 株式会社日立製作所 | Time series prediction apparatus and time series prediction method |
| CN108549957A (en) * | 2018-04-11 | 2018-09-18 | 中译语通科技股份有限公司 | Internet topic trend auxiliary prediction technique and system, information data processing terminal |
| CN109033133A (en) * | 2018-06-01 | 2018-12-18 | 杭州电子科技大学 | Event detection and tracking based on Feature item weighting growth trend |
| CN109508416A (en) * | 2018-11-09 | 2019-03-22 | 四川大学 | Microblogging public sentiment event temperature and prediction of the development trend method based on number of reviews |
| CN111581983A (en) * | 2020-05-13 | 2020-08-25 | 中国人民解放军国防科技大学 | Method for predicting social concern hotspots in network public opinion events based on group analysis |
Non-Patent Citations (3)
| Title |
|---|
| 朱张祥等.基于CSSCI图情领域网络舆情研究的知识图谱分析.图书情报导刊.2020,第5卷(第3期),50-59. * |
| 林丽娜等.一种基于时间序列网络舆情热点事件发现模型.太原师范学院学报(自然科学版).2016,第15卷(第3期),52-56. * |
| 赵磊等.基于BP神经网络的舆情热度趋势仿真模型研究.《情报学报》.2016,第35卷(第9期),989-999. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112579866A (en) | 2021-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111173573B (en) | Identification method for power object model of steam turbine regulating system | |
| CN110210495B (en) | XGboost soft measurement modeling method based on parallel LSTM self-encoder dynamic feature extraction | |
| CN109583585A (en) | A kind of station boiler wall temperature prediction neural network model | |
| CN108779506A (en) | Phosphorus concentration method of estimation and control device is bessemerized in molten steel | |
| CN108363902A (en) | A kind of accurate prediction technique of pathogenic hereditary variation | |
| CN111859249A (en) | Ocean numerical forecasting method based on analytical four-dimensional set variation | |
| CN113987033A (en) | Main transformer online monitoring data group deviation identification and calibration method | |
| CN112579866B (en) | Method for analyzing event development trend based on time heat index | |
| CN114487976B (en) | Method and system for evaluating traceability uncertainty of MCM electronic transformer calibrator | |
| CN107527110A (en) | Based on cuckoo chess game optimization MGM（1, N）Prediction of annual electricity consumption method | |
| CN110320227B (en) | Two-dimensional nuclear magnetic resonance D-T2 spectrum inversion method and device | |
| CN107463781B (en) | Data reduction processing method and device for blast furnace molten iron silicon content prediction model | |
| CN107844679A (en) | A kind of segmented blast furnace molten iron silicon content Forecasting Methodology and device | |
| CN113569467B (en) | Soft measurement modeling method for temperature of blast furnace tuyere swirling zone based on width learning | |
| CN114627963B (en) | Protein data filling method, system, computer device and readable storage medium | |
| CN112819085B (en) | Model optimization method, device and storage medium based on machine learning | |
| CN116227674A (en) | Carbon emission prediction method based on online updating model | |
| CN112381510A (en) | Salary recommendation method based on machine learning | |
| CN115035304A (en) | Image description generation method and system based on course learning | |
| CN112579904B (en) | Analysis method for realizing migration and propagation based on graph relationship and time | |
| CN113408186A (en) | Method for determining influence factors of metallurgical coke quality prediction | |
| CN112257215B (en) | Maximum likelihood estimation solving method and system for product life distribution parameters | |
| CN112750495A (en) | Prediction method for biological metabolic pathway based on neural network | |
| JP3612428B2 (en) | Software reliability prediction method and apparatus and recording medium | |
| CN116734847B (en) | Laser strapdown inertial measurement unit temperature compensation method |
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 |