AU2019100854A4 - Long-term trend prediction method based on network hotspot single-peak topic propagation model - Google Patents
Long-term trend prediction method based on network hotspot single-peak topic propagation model Download PDFInfo
- Publication number
- AU2019100854A4 AU2019100854A4 AU2019100854A AU2019100854A AU2019100854A4 AU 2019100854 A4 AU2019100854 A4 AU 2019100854A4 AU 2019100854 A AU2019100854 A AU 2019100854A AU 2019100854 A AU2019100854 A AU 2019100854A AU 2019100854 A4 AU2019100854 A4 AU 2019100854A4
- Authority
- AU
- Australia
- Prior art keywords
- topic
- peak
- time
- discussion
- persons
- 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.)
- Ceased
Links
- 230000007774 longterm Effects 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000002085 persistent effect Effects 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 description 26
- 230000008859 change Effects 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- 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
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The present invention discloses a long-term trend prediction method based on network hotspot single-peak topic propagation model which includes the following steps: 1) detecting in real time characteristics of persons participating in discussion of a target network hotspot single-peak topic over the network, thereby obtaining a quantity R(t) of potential single-peak topic discussers at a time t, a quantity D(t) of single-peak topic discussers at the time t and a quantity E(t) of single-peak topic discussion quitters at the time t; 2) establishing differential equations for the quantity R(t) of potential single peak topic discussers, the quantity D(t) of single-peak topic discussers and the quantity E(t) of single-peak topic discussion quitters with respect to the time t, thereby establishing a network single-peak topic propagation model for reflecting a propagation law of the target network hotspot single-peak topic; 3) based on the network single peak topic propagation model of the step 2), providing a network single-peak topic long-term trend prediction method. The present invention can intuitively and quickly predict whether the long-term trend of network single-peak topic is to be weakly persistent or dying out. circle_2 - circle N j -N 7 ..- DD(t) "N - .' ~ N circle-3
Description
[0001] The present invention relates to the field of network public opinions, and in particular to a long-term trend prediction method based on network hotspot singlepeak topic propagation model.
BACKGROUND [0002] With the development of the Internet, especially the mobile Internet, its role as information transmission interaction in people's daily life is becoming more obvious and important. Meanwhile, various bad public opinion information, violence information, and pornographic information pervading the Internet also bring uneasiness and potential threats to people's daily life and social stability. It is an important and urgent content of current research on network public opinions about how to effectively depict the propagation law and propagation mechanism of the bad public opinion information, violence information, and pornographic information on the Internet and then find out efficient and precise means to control bad public opinions.
[0003] There are many methods and researches for modeling and predicting trends for network public opinions especially network hotspot single-peak topics, which may be roughly summarized into three types including: (a) a method based on susceptible-infected model, (b) a method based on stochastic model and (c) a method based on data mining and big data analysis. Although these methods are related to information propagation modes of the network public opinions especially hotspot
2019100854 02 Aug 2019 single-peak topics, they do not study on a series of issues, such as the propagation law of the network hotspot single-peak topics, describing how network users participate in the discussion of hotspot single-peak topics and how to quit the discussion of hotspot single-peak topics as well as driving reasons behind it, how the propagation law and mechanism of the network hotspot single-peak topic are affected when the network environment changes and how to adjust the response. Therefore, there is an urgent need for a long-term trend prediction method based on network hotspot single-peak topic propagation model.
SUMMARY [0004] An object of the present invention is to overcome the shortcomings of the prior art described above by providing a long-term trend prediction method based on network hotspot single-peak topic propagation model, which can intuitively and rapidly predict future development trend of the single-peak topics.
[0005] In order to achieve the above object, a long-term trend prediction method based on network hotspot single-peak topic propagation model according to the present invention includes the following steps:
[0006] 1) detecting in real time characteristics of persons participating in discussion of a target network hotspot single-peak topic Ta over the network, thereby obtaining a quantity R(t) of potential single-peak topic discussers at a time t, a quantity D(t) of single-peak topic discussers at the time t and a quantity E(t) of single-peak topic discussion quitters at the time t;
2019100854 02 Aug 2019 [0007] 2) establishing differential equations for the quantity R(t) of potential single-peak topic discussers, the quantity D(t) of single-peak topic discussers and the quantity E(t) of single-peak topic discussion quitters with respect to the time t, thereby establishing a network single-peak topic propagation model for reflecting a propagation law of the target network hotspot single-peak topic Td;
[0008] 3) based on the network single-peak topic propagation model of the step
2), providing a network single-peak topic long-term trend prediction method.
[0009] In the single-peak topic propagation model, the differential equation for the quantity R(t) of potential single-peak topic discussers with respect to the time t is: dR(t)/dt=B(t)R(t)-p(t)R(t)D(t)-w(t)R(t); wherein B(t) is a proportional function for network single-peak topic persons becoming potential hotspot single-peak topic discussers at the time t, β(ί) is a average number of persons who view comments on the target network hotspot single-peak topic Td at the time t, and w(t) is an exit proportional function of potential persons of the target network hotspot single-peak topic Td at the time t.
[0010] The differential equation for the quantity D(t) of single-peak topic discussers with respect to the time t is: dD(t)/dt=A(t)D(t)+p(t)R(t)D(t)-y(t)D(t); wherein A(t) is a participation proportional function of persons who participate in the discussion of the target network hotspot single-peak topic Td at the time t, and y(t) is an exit proportional function of persons who quit the discussion of the target network hotspot single-peak topic Td at the time t.
2019100854 02 Aug 2019 [0011] The differential equation for the quantity E(t) of single-peak topic discussion quitters with respect to the time t is: dE(t)/dt=y(t)D(t).
[0012] When a single-peak topic Tr is a single-peak topic related to the target network hotspot single-peak topic Ta, then, the proportional function B(t) for network single-peak topic persons becoming potential hotspot single-peak topic discussers is expressed as: B(t)=q(t)/h(t-l); wherein h(t-l) is a quantity of persons who do not participate in discussion of the target network hotspot single-peak topic Ta and the single-peak topic Tr at a time (t-1), and q(t) is a quantity of persons who do not participate in discussion of the target network hotspot single-peak topic Ta and the single-peak topic Tr at the time (t-1) but participate in discussion of the single-peak topic Tr at the time t.
[0013] The exit proportional function w(t) of potential persons of the target network hotspot single-peak topic Td at the time t is expressed as: w(t)=z(t)/b(t-l); wherein z(t) is a quantity of persons who participate in discussion of the single-peak topic Tr at the time (t-1) and quit the discussion of the single-peak topic Tr at the time t, b(t-l) is a total quantity of persons who participate in discussion of the single-peak topic Tr at the time (t-1).
[0014] The participation proportional function A(t) of persons who participate in the discussion of the target network hotspot single-peak topic Td at the time t is expressed as: A(t)=c(t)/u(t-l); wherein c(t) is a quantity of persons who do not participate in discussion of the target network hotspot single-peak topic Td and the single-peak topic Tr at the time (t-1) but participate in discussion of the target network
2019100854 02 Aug 2019 hotspot single-peak topic Ta at the time t, u(t-l) is a total quantity of persons who participate in discussion of the target network hotspot single-peak topic Ta at the time (t-1).
[0015]
The exit proportional function y(t) of persons who quit the discussion of the target network hotspot single-peak topic Ta at the time t is expressed as: y(t)=a(t)/l(t1); wherein a(t) is a quantity of persons who participate in discussion of the target network hotspot single-peak topic Ta at the time (t-1) but quit the discussion of the target network hotspot single-peak topic Ta at the time t, l(t-l) is a total quantity of persons who participate in discussion of the target network hotspot single-peak topic Ta at the time (t-1); wherein A(t)>0, β(ί)>0, B(t)>0, w(t)>0, y(t)>0.
[0016] In the single-peak topic long-term trend prediction method based on the single-peak topic propagation model according to the present invention, determining the single-peak topic to be weakly persistent is based on the following threshold Q*:
(W).
(χ-Α(ί))' where (/ - A))’ = lim sup(- j (/ - A(sf)ds)
N=R+D+E;
[0017] when Q*> 1, determining that the long-term trend of the single-peak topic is weakly persistent.
[0018]
Determining the long-term trend of the single-peak topic to be dying out is based on the following threshold Q*:
(/-A
2019100854 02 Aug 2019 where (/ “ A\ = liminf(-f; (/ - A)ds) (sup(/7 Ν') + w(/) - B/ = lim sup(- J' (sup(/7 N) + w(s) - B)ds) t [0019] when Q*< 1, determining that the long-term trend of the single-peak topic is dying out.
[0020] The invention has the following beneficial effects:
[0021] According to the long-term trend prediction method based on network hotspot single-peak topic propagation model, in operation, by quantifying the quantity R(t) of potential single-peak topic discussers at the time t, the quantity D(t) of singlepeak topic discussers at the time t and the quantity E(t) of single-peak topic discussion quitters at the time t, then establishing differential equations for the quantity R(t) of potential single-peak topic discussers, the quantity D(t) of single-peak topic discussers and the quantity E(t) of single-peak topic discussion quitters with respect to the time t, a propagation law of the target network hotspot single-peak topic can be obtained by studying on the established differential equations. Then, essential mechanism of network information propagation can be objectively and truly reflected. Further, on the basis of the single-peak topic propagation model, a single-peak topic long-term trend prediction method is established with strong practicability.
2019100854 02 Aug 2019
BRIEF DESCRIPTION OF THE DRAWINGS [0022] Fig. 1 is a schematic diagram showing characteristics of persons participating in discussion of a target network hotspot single-peak topic and their dynamic relationship according to the present invention;
[0023] Fig. 2 is a schematic diagram showing variations of a quantity R(t) of potential single-peak topic discussers, a quantity D(t) of single-peak topic discussers and a quantity E(t) of single-peak topic discussion quitters with respect to time t, according to the present invention; and [0024] Fig. 3 is a schematic view of realizing long-term trend prediction for a single-peak topic based on a single-peak topic propagation model according to the present invention.
DETAILED DESCRIPTION [0025] The present invention will be further described in details hereinafter with reference to the accompanying drawings.
[0026] A long-term trend prediction method based on network hotspot singlepeak topic propagation model according to the present invention includes the following steps:
[0027] 1) detecting in real time characteristics of persons participating in discussion of a target network hotspot single-peak topic over the network, thereby obtaining a quantity R(t) of potential single-peak topic discussers at a time t, a quantity
2019100854 02 Aug 2019
D(t) of single-peak topic discussers at the time t and a quantity E(t) of single-peak topic discussion quitters at the time t;
[0028] 2) establishing differential equations for the quantity R(t) of potential single-peak topic discussers, the quantity D(t) of single-peak topic discussers and the quantity E(t) of single-peak topic discussion quitters with respect to the time t, thereby obtaining a propagation law of the target network hotspot single-peak topic.
[0029] A differential equation for the quantity R(t) of potential single-peak topic discussers with respect to the time t may be:
dR(t)/dt=B(t)R(t)-p(t)R(t)D(t)-w(t)R(t) [0030] where B(t) is a proportional function for network single-peak topic persons becoming potential hotspot single-peak topic discussers at the time t, β(ΐ) is a average number of persons who view comments on the target network hotspot singlepeak topic Td at the time t, and w(t) is an exit proportional function of potential persons of the target network hotspot single-peak topic Td at the time t.
[0031] A differential equation for the quantity D(t) of single-peak topic discussers with respect to the time t may be:
dD(t)/dt=A(t)D(t)+p(t)R(t)D(t)-y(t)D(t) [0032] where A(t) is a participation proportional function of persons who participate in the discussion of the target network hotspot single-peak topic Td at the time t, and y(t) is an exit proportional function of persons who quit the discussion of the target network hotspot single-peak topic Td at the time t.
2019100854 02 Aug 2019 [0033] A differential equation for the quantity E(t) of single-peak topic discussion quitters with respect to the time t may be:
dE(t)/dt=y(t)D(t).
[0034] Assuming that a single-peak topic Tr is a single-peak topic related to the target network hotspot single-peak topic Ta, then, the proportional function B(t) for network single-peak topic persons becoming potential hotspot single-peak topic discussers may be expressed as:
B(t)=q(t)/h(t-l) [0035] where h(t-l) is a quantity of persons who do not participate in discussion of the target network hotspot single-peak topic Ta and the single-peak topic Tr at a time (t-1), and q(t) is a quantity of persons who do not participate in discussion of the target network hotspot single-peak topic Ta and the single-peak topic Tr at the time (t-1) but participate in discussion of the single-peak topic Tr at the time t.
[0036] The exit proportional function w(t) of potential persons of the target network hotspot single-peak topic Ta at the time t may be expressed as:
w(t)=z(t)/b(t-l) [0037] where z(t) is a quantity of persons who participate in discussion of the single-peak topic Tr at the time (t-1) and quit the discussion of the single-peak topic Tr at the time t, b(t-l) is a total quantity of persons who participate in discussion of the single-peak topic Tr at the time (t-1).
2019100854 02 Aug 2019 [0038] The participation proportional function A(t) of persons who participate in the discussion of the target network hotspot single-peak topic Td at the time t may be expressed as:
A(t)=c(t)/u(t-l) [0039] where c(t) is a quantity of persons who do not participate in discussion of the target network hotspot single-peak topic Td and the single-peak topic Tr at the time (t-1) but participate in discussion of the target network hotspot single-peak topic Td at the time t, u(t-l) is a total quantity of persons who participate in discussion of the target network hotspot single-peak topic Td at the time (t-1).
[0040] The exit proportional function y(t) of persons who quit the discussion of the target network hotspot single-peak topic Td at the time t may be expressed as: Y(t)=a(t)/l(t-l) [0041] where a(t) is a quantity of persons who participate in discussion of the target network hotspot single-peak topic Td at the time (t-1) but quit the discussion of the target network hotspot single-peak topic Td at the time t, l(t-l) is a total quantity of persons who participate in discussion of the target network hotspot single-peak topic Td at the time (t-1).
[0042] A(t)>0, β(ί)>0, B(t)>0, w(t)>0, y(t)>0.
[0043] 3) based on the single-peak topic propagation model, providing a singlepeak topic long-term trend prediction method with the following features:
[0044] determining the single-peak topic to be weakly persistent based on the following threshold Q*:
2019100854 02 Aug 2019
c _ (W (/-«)’ | |
where | (ρ-Α(ί))' =limsup(-f (/-A(s))ds) t 0 (βΝ). =hminf(lj/Ws) “ t0 , N=R+D+E. |
[0045] | When Q*>1, the long-term trend of the single-peak topic is weakly |
persistent.
[0046] | The prediction method for determining the long-term trend of the single- |
peak topic to be dying out is based on the following threshold Q*:
where | . _ (sup(/7A) + w(0-5)’ (/-< (/ - A), = liminf(-/; (/ - A)ds) |
[0047] | (sup(/7N) + w(0 - By = lim sup(- J' (supQ?N) + w(s) - B)ds) t when Q*<1, the long-term trend of the single-peak topic is dying out. |
[0048] | Embodiment one |
[0049] | Referring to Fig. 1, each node represents a quantity of three types of |
persons associated with the target network hotspot single-peak topic, which is labeled with R(t), D(t), E(t), respectively. Directed edges between the three nodes indicate directions of transfer of the three types of persons. The label on each directed edge indicates a transfer ratio function of the three types of persons. The transfer ratio function of R(t)—>D(t) is β(ί). The transfer ratio function of D(t)—>E(t) is y(t).
[0050] | Referring to Fig. 2, according to analysis of changing factors of the total |
quantity of three types of persons related to the target network hotspot single-peak topic,
2019100854 02 Aug 2019 a change rule of the total quantity of the three types of persons with time is described in mathematical language as follows: first, a changing rule of R(t) with time t is analyzed. According to the circle_l shown in Fig. 2, it can be seen that factors affecting the change of R(t) include: a) the proportional function B(t) of the quantity of persons who do not participate in discussion of the single-peak topic Tr and the target network hotspot single-peak topic Td at the time (t-1) but participate in discussion of the singlepeak topic Tr at the time t; b) the proportional function β(ί) of the total quantity of persons who view comments on the target network hotspot single-peak topic Td at the time t and then are transferred as commentators of the target network hotspot singlepeak topic Td; c) the proportional function w(t) of the quantity of persons who participate in discussion of the single-peak topic Tr at the time (t-1) and quit the discussion of the single-peak topic Tr at the time t; thus, dR(t)/d(t)=B(t)R(t)p(t)R(t)D(t)-w(t)R(t).
[0051] Referring to Fig. 2, a changing rule of D(t) with time t is analyzed.
According to the circle_2 shown in Fig. 2, it can be seen that factors affecting the change of D(t) include: the proportional function A(t) of the quantity of persons who do not participate in discussion of the single-peak topic Tr and the target network hotspot single-peak topic Td at the time (t-1) but participate in discussion of the target network hotspot single-peak topic Td at the time t; the proportional function β(ί) of the total quantity of persons who view comments on the target network hotspot single-peak topic Td at the time (t-1) and then start at the time t to participate in the discussion of the target network hotspot single-peak topic Td; and the proportional function y(t) of
2019100854 02 Aug 2019 the total quantity of persons who participate in discussion of the target network hotspot single-peak topic Ta at the time (t-1) but quit the discussion of the target network hotspot single-peak topic Ta at the time t. Then, dD(t)/dt=A(t)D(t)+p(t)R(t)D(t)-y(t)D(t).
[0052]
Referring to Fig. 2, a changing rule of E(t) with time t is analyzed.
According to the circle_3 shown in Fig. 2, it can be seen that factors affecting the change of E(t) include: the proportional function y(t) of the quantity of persons who participate in discussion of the target network hotspot single-peak topic Ta at the time (t-1) but quit the discussion of the target network hotspot single-peak topic Ta at the time t. Then, dE(t)/dt=y(t)D(t).
[0053] The propagation law of the target network hotspot single-peak topic can be obtained according to dR(t)/d(t)=B(t)R(t)-p(t)R(t)D(t)-w(t)R(t), dD(t)/dt=A(t)D(t)+p(t)R(t)D(t)-y(t)D(t), and dE(t)/dt=y(t)D(t).
[0054]
Referring to Fig. 3, by establishing the single-peak topic long-term trend prediction method based on the single-peak topic propagation model, the long-term trend prediction for the single-peak topic can be realized.
[0055]
Determining the single-peak topic to be weakly persistent is based on the following threshold Q*:
(W).
(χ-Α(ί))' where (/ - Λ0Ϊ = limsup(-j (y - A(s))ds) (βΝ), = liminf(-j/?7V<A) f A
N=R+D+E.
2019100854 02 Aug 2019 [0056] When Q*>1, the long-term trend of the single-peak topic is weakly persistent.
[0057] The prediction method for determining the long-term trend of the singlepeak topic to be dying out is based on the following threshold Q*:
. _ (sup(J3N) + w(e)-B/ (/-Λ),
where | (χ - A), = liminf(-/; (/ - A)ds) (sup(/7 N) + w(i) - 5)’ = lim sup(- f' (sup(/7 N) + w(s) - 5)ώ) I |
[0058] | When Q*<1, the long-term trend of the single-peak topic is dying out. |
Claims (5)
1) detecting in real time characteristics of persons participating in discussion of a target network hotspot single-peak topic Td over the network, thereby obtaining a quantity R(t) of potential single-peak topic discussers at a time t, a quantity D(t) of single-peak topic discussers at the time t and a quantity E(t) of single-peak topic discussion quitters at the time t;
1. A long-term trend prediction method based on network hotspot single-peak topic propagation model comprising the following steps:
2. The long-term trend prediction method based on network hotspot single-peak topic propagation model according to claim 1, wherein in the single-peak topic propagation model, the differential equation for the quantity R(t) of potential single-peak topic discussers with respect to the time t is: dR(t)/dt=B(t)R(t)-p(t)R(t)D(t)-w(t)R(t); wherein B(t) is a proportional function for network single-peak topic persons becoming
2019100854 02 Aug 2019 potential hotspot single-peak topic discussers at the time t, β(ί) is a average number of persons who view comments on the target network hotspot single-peak topic Td at the time t, and w(t) is an exit proportional function of potential persons of the target network hotspot single-peak topic Td at the time t;
the differential equation for the quantity D(t) of single-peak topic discussers with respect to the time t is: dD(t)/dt=A(t)D(t)+p(t)R(t)D(t)-y(t)D(t); wherein A(t) is a participation proportional function of persons who participate in the discussion of the target network hotspot single-peak topic Td at the time t, and y(t) is an exit proportional function of persons who quit the discussion of the target network hotspot single-peak topic Td at the time t;
the differential equation for the quantity E(t) of single-peak topic discussion quitters with respect to the time t is: dE(t)/dt=y(t)D(t).
2) establishing differential equations for the quantity R(t) of potential singlepeak topic discussers, the quantity D(t) of single-peak topic discussers and the quantity E(t) of single-peak topic discussion quitters with respect to the time t, thereby establishing a network single-peak topic propagation model for reflecting a propagation law of the target network hotspot single-peak topic Ta;
3. The long-term trend prediction method based on network hotspot single-peak topic propagation model according to claim 2, wherein when a single-peak topic Tr is a single-peak topic related to the target network hotspot single-peak topic Td, then, the proportional function B(t) for network singlepeak topic persons becoming potential hotspot single-peak topic discussers is expressed as: B(t)=q(t)/h(t-l); wherein h(t-l) is a quantity of persons who do not participate in discussion of the target network hotspot single-peak topic Td and the single-peak topic Tr at a time (t-1), and q(t) is a quantity of persons who do not participate in discussion of the target network hotspot single-peak topic Td and the single-peak topic Tr at the time (t-1) but participate in discussion of the single-peak topic Tr at the time t;
2019100854 02 Aug 2019 the exit proportional function w(t) of potential persons of the target network hotspot single-peak topic Td at the time t is expressed as: w(t)=z(t)/b(t-l); wherein z(t) is a quantity of persons who participate in discussion of the single-peak topic Tr at the time (t-1) and quit the discussion of the single-peak topic Tr at the time t, b(t-l) is a total quantity of persons who participate in discussion of the single-peak topic Tr at the time (t-1);
the participation proportional function A(t) of persons who participate in the discussion of the target network hotspot single-peak topic Td at the time t is expressed as: A(t)=c(t)/u(t-l); wherein c(t) is a quantity of persons who do not participate in discussion of the target network hotspot single-peak topic Td and the single-peak topic Tr at the time (t-1) but participate in discussion of the target network hotspot singlepeak topic Td at the time t, u(t-l) is a total quantity of persons who participate in discussion of the target network hotspot single-peak topic Td at the time (t-1);
the exit proportional function y(t) of persons who quit the discussion of the target network hotspot single-peak topic Td at the time t is expressed as: y(t)=a(t)/l(t-1); wherein a(t) is a quantity of persons who participate in discussion of the target network hotspot single-peak topic Td at the time (t-1) but quit the discussion of the target network hotspot single-peak topic Td at the time t, l(t-l) is a total quantity of persons who participate in discussion of the target network hotspot single-peak topic Td at the time (t-1);
wherein A(t)>0, β(ΐ)>0, B(t)>0, w(t)>0, y(t)>0.
2019100854 02 Aug 2019
3) based on the network single-peak topic propagation model of the step 2), providing a network single-peak topic long-term trend prediction method.
4. The long-term trend prediction method based on network hotspot single-peak topic propagation model according to any one of claims 1 to 3, further comprising:
determining the single-peak topic to be weakly persistent based on the following threshold Q*:
wherein
7!
(A).
(/ - A))’ = lim sup(- j (/ - A(s))ds) , N=R+D+E;
when Q*>1, determining that the long-term trend of the single-peak topic is weakly persistent.
5. The long-term trend prediction method based on network hotspot single-peak topic propagation model according to any one of claims 1 to 4, further comprising:
determining the long-term trend of the single-peak topic to be dying out based on the following threshold Q*:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2019100854A AU2019100854A4 (en) | 2019-08-02 | 2019-08-02 | Long-term trend prediction method based on network hotspot single-peak topic propagation model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2019100854A AU2019100854A4 (en) | 2019-08-02 | 2019-08-02 | Long-term trend prediction method based on network hotspot single-peak topic propagation model |
Publications (1)
Publication Number | Publication Date |
---|---|
AU2019100854A4 true AU2019100854A4 (en) | 2019-09-05 |
Family
ID=67766798
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
AU2019100854A Ceased AU2019100854A4 (en) | 2019-08-02 | 2019-08-02 | Long-term trend prediction method based on network hotspot single-peak topic propagation model |
Country Status (1)
Country | Link |
---|---|
AU (1) | AU2019100854A4 (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111222032A (en) * | 2019-12-17 | 2020-06-02 | 中国平安人寿保险股份有限公司 | Public opinion analysis method and related equipment |
CN112685621A (en) * | 2021-01-06 | 2021-04-20 | 深圳市网联安瑞网络科技有限公司 | Network public opinion detection system and method integrating public opinion wind direction tracking and civil opinion prediction |
CN112765206A (en) * | 2021-02-05 | 2021-05-07 | 杭州同声相应科技有限公司 | Flow sensing and high K factor propagation prediction method, system and storage medium thereof |
CN112818125A (en) * | 2021-02-25 | 2021-05-18 | 西安理工大学 | Network topic structure evolution discovery method |
CN113688600A (en) * | 2021-09-08 | 2021-11-23 | 北京邮电大学 | Information propagation prediction method based on topic perception attention network |
-
2019
- 2019-08-02 AU AU2019100854A patent/AU2019100854A4/en not_active Ceased
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111222032A (en) * | 2019-12-17 | 2020-06-02 | 中国平安人寿保险股份有限公司 | Public opinion analysis method and related equipment |
CN111222032B (en) * | 2019-12-17 | 2024-04-30 | 中国平安人寿保险股份有限公司 | Public opinion analysis method and related equipment |
CN112685621A (en) * | 2021-01-06 | 2021-04-20 | 深圳市网联安瑞网络科技有限公司 | Network public opinion detection system and method integrating public opinion wind direction tracking and civil opinion prediction |
CN112765206A (en) * | 2021-02-05 | 2021-05-07 | 杭州同声相应科技有限公司 | Flow sensing and high K factor propagation prediction method, system and storage medium thereof |
CN112818125A (en) * | 2021-02-25 | 2021-05-18 | 西安理工大学 | Network topic structure evolution discovery method |
CN112818125B (en) * | 2021-02-25 | 2022-09-09 | 西安理工大学 | Network topic structure evolution discovery method |
CN113688600A (en) * | 2021-09-08 | 2021-11-23 | 北京邮电大学 | Information propagation prediction method based on topic perception attention network |
CN113688600B (en) * | 2021-09-08 | 2023-07-28 | 北京邮电大学 | Information propagation prediction method based on topic perception attention network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
AU2019100854A4 (en) | Long-term trend prediction method based on network hotspot single-peak topic propagation model | |
Vraga et al. | Cancer and social media: a comparison of traffic about breast cancer, prostate cancer, and other reproductive cancers on Twitter and Instagram | |
Skaza et al. | Modeling the infectiousness of Twitter hashtags | |
JP6367289B2 (en) | Network-oriented product rollout in online social networks | |
He et al. | Species–area relationships always overestimate extinction rates from habitat loss | |
US9542503B2 (en) | Estimation of closeness of topics based on graph analytics | |
Chan et al. | Forming first impressions: The role of gender and normative accuracy in personality perception | |
Cooper et al. | Developing a global indicator for Aichi Target 1 by merging online data sources to measure biodiversity awareness and engagement | |
Kiss et al. | Can epidemic models describe the diffusion of topics across disciplines? | |
Müller et al. | Residential segregation and ‘ethnic flight’vs.‘ethnic avoidance’in Sweden | |
Laflin et al. | Discovering and validating influence in a dynamic online social network | |
Zhou et al. | Analyzing and modeling dynamics of information diffusion in microblogging social network | |
Tse et al. | Social network based crowd sensing for intelligent transportation and climate applications | |
Zhang et al. | Structural diversity effect on hashtag adoption in Twitter | |
Hu et al. | An adaptive hawkes process formulation for estimating time-of-day zonal trip arrivals with location-based social networking check-in data | |
Foroozani et al. | Anomalous information diffusion in social networks: Twitter and Digg | |
Barnett et al. | Social and spatial clustering of people at humanity’s largest gathering | |
US20140365480A1 (en) | Personalized low latency communication | |
Sun et al. | Socialwave: visual analysis of spatio-temporal diffusion of information on social media | |
Xiao et al. | Dynamic model of information diffusion based on multidimensional complex network space and social game | |
Dou et al. | Social awareness of crisis events: A new perspective from social-physical network | |
CN112053269A (en) | Learning condition diagnosis method, device, equipment and storage medium | |
CN108520337B (en) | Riadry risk assessment method based on network risk entropy difference | |
Schneckenreither et al. | Modelling SIR-type epidemics by ODEs, PDEs, difference equations and cellular automata–A comparative study | |
Wilson et al. | A path toward the use of trail users’ tweets to assess effectiveness of the environmental stewardship scheme: an exploratory analysis of the Pennine Way National Trail |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FGI | Letters patent sealed or granted (innovation patent) | ||
MK22 | Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry |