CN112348279A - Information propagation trend prediction method and device, electronic equipment and storage medium - Google Patents
Information propagation trend prediction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112348279A CN112348279A CN202011299044.0A CN202011299044A CN112348279A CN 112348279 A CN112348279 A CN 112348279A CN 202011299044 A CN202011299044 A CN 202011299044A CN 112348279 A CN112348279 A CN 112348279A
- Authority
- CN
- China
- Prior art keywords
- propagation
- process curve
- comment data
- target information
- information
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 262
- 230000008569 process Effects 0.000 claims abstract description 209
- 238000004088 simulation Methods 0.000 claims abstract description 65
- 230000008451 emotion Effects 0.000 claims description 23
- 238000004458 analytical method Methods 0.000 claims description 16
- 230000002996 emotional effect Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 230000007935 neutral effect Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 description 16
- 230000008859 change Effects 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000007781 pre-processing Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 239000000969 carrier Substances 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000007480 spreading Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/338—Presentation of query results
-
- 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
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
Abstract
The embodiment of the application provides a method and a device for predicting an information propagation trend, electronic equipment and a storage medium, and relates to the technical field of information. The method comprises the following steps: obtaining comment data of target information from the release to the current time; searching a first propagation process curve of a propagation case with the highest similarity to the target information in a propagation case library according to the comment data; acquiring a target parameter value of a designated parameter in a propagation simulation model based on beta distribution regression and used for fitting a first propagation process curve; based on the target parameter value and the propagation simulation model, a second propagation process curve of the target information in a preset time period is determined. And an intuitive curve graph can be generated for the propagation process of the target information, so that the propagation process and the future propagation trend of the target information can be conveniently known.
Description
Technical Field
The present application relates to the field of information technology, and in particular, to a method and an apparatus for predicting an information propagation trend, an electronic device, and a storage medium.
Background
Along with the development and application of information technology and internet, the forms of culture propagation and positive energy propagation also show obvious change trend, from characters in the 2G era to pictures in the 3G era to the current propagation form mainly based on videos, information carriers are continuously changed, the content is continuously rich, audiences are more and more, and the transmittable information is also more and more diversified. In the face of such huge and rich content of various news assets in the current society, the embedded value of the news assets influences the network experience of each viewer, and the influence on the viewers is also subtly implied. Therefore, positive energy in information such as graphics, video, etc. is crucial for maintaining the internet environment. Therefore, it is very important to study the information dissemination and dissemination trend in the public.
However, there is a lack of prediction and evaluation of the dissemination and dissemination of such information to the general public in existing research and applications.
Disclosure of Invention
In view of the above, an object of the embodiments of the present application is to provide a method, an apparatus, an electronic device and a storage medium for predicting an information dissemination trend, so as to realize the prediction and evaluation of an information dissemination process.
In a first aspect, an embodiment of the present application provides a method for predicting an information propagation trend, where the method includes:
obtaining comment data of target information from the release to the current time;
searching a first propagation process curve of a propagation case with similarity greater than a similarity threshold and highest similarity with the target information in a propagation case library according to the comment data, wherein the first propagation process curve is used for representing the variation trend of the comment quantity of the propagation case in a propagation period;
acquiring a target parameter value of a designated parameter in a beta distribution-based propagation simulation model for fitting the first propagation process curve, wherein the propagation simulation model is constructed in advance;
and determining a second propagation process curve of the target information in a future preset time period based on the target parameter value and the propagation simulation model, wherein the second propagation process curve is used for representing the variation trend of the number of comments of the target information in the preset time period.
In the implementation process, firstly comment data of target information from release to current time needs to be acquired, then a propagation case with similarity greater than a similarity threshold and highest similarity with the target information is searched in a propagation case library with a plurality of propagation cases according to the comment data to obtain a first propagation process curve of the propagation case, the first propagation process curve is used for representing the variation trend of the comment number of the propagation case in a propagation period, then target parameter values of specified parameters in a propagation simulation model fitting the first propagation process curve are acquired, and a second propagation process curve of the target information in preset time is determined based on the target parameter values and the propagation simulation model. Therefore, the propagation condition of the target information in a future period of time can be predicted, and a visual graph can be generated for the propagation process of the target information, so that the propagation process and the future propagation trend of the target information can be conveniently known.
Optionally, the obtaining of comment data of the target information from the publication to the current time includes:
original comment data of the target information from the release to the current time is obtained, the target information comprises image-text information or video information, and the original comment data comprises a comment or a bullet screen;
and removing stop words from the original comment data, and arranging according to the generation time of the comments or the barrage to obtain the preprocessed comment data.
In the implementation process, preprocessing of original comment data in the target information can be completed, comment data which are arranged according to the generation time and are obtained after stop words are removed are used as comment data of the target information, wherein the target information comprises image-text information or video information, and the original comment data comprises comment or barrage data. Due to the fact that the original comment data in the target information are preprocessed, data processing amount and unnecessary characters or words can be reduced, and therefore efficiency and accuracy of a subsequent processing process are improved.
Optionally, the obtaining of the comment data of the target information from the publication to the current time further includes:
performing emotion analysis on the preprocessed comment data by using an emotion analysis algorithm to obtain comment data with emotion tendencies, wherein the comment data with emotion tendencies comprises positive comments or barrage, or negative comments or barrage, or/and neutral comments or barrages;
and obtaining comment data with specified emotional tendency from the comment data with emotional tendency as comment data of the target information from the release to the current time.
In the implementation process, after the original comment data is preprocessed, emotion analysis is carried out on the preprocessed comment data by using an emotion analysis algorithm, the sentiment analysis algorithm can identify, judge and classify the data in the comment data to obtain comment data with sentiment tendency, the comment data with sentiment tendency comprises forward comments or barrage, or negative comments or barrage, or/and neutral comments or barrage, so that comment data under different emotional tendencies can be acquired, providing data for researching the transmission process of the target information under a certain emotional tendency, wherein comment data with a specified emotional tendency are selected as comment data of the target information from the publication to the current time, and performing subsequent prediction on the basis of the information, so as to obtain the variation trend of the comment data of the target information with the specified emotional tendency in a future period of time.
Optionally, the searching, according to the comment data, a first propagation process curve of a propagation case in which the similarity with the target information is greater than a similarity threshold and the similarity is highest in a propagation case library includes:
determining a third propagation process curve of the target information from the release to the current time according to the comment data, wherein the third propagation process curve is used for representing the variation trend of the number of comments of the target information in the time period from the release to the current time;
searching a propagation process curve with the similarity higher than a similarity threshold and the highest similarity with the third propagation process curve in a propagation case library to obtain the first propagation process curve.
In the implementation process, the propagation process of the target information can be simulated and predicted through the propagation case with similar propagation process. According to the comment data of the target information from the publication to the current time, in combination with the generation time of the comment data, a third propagation curve used for representing the variation trend of the number of comments of the target information in the time period from the publication to the current time is constructed, and in the propagation case library, a propagation curve which has the highest similarity with the third propagation curve and the similarity higher than a similarity threshold is found, so that the first propagation process curve can be obtained.
Optionally, the searching, according to the comment data, a first propagation process curve of a propagation case in which the similarity with the target information is greater than a similarity threshold and the similarity is highest in a propagation case library includes:
acquiring the content of the target information and the keywords in the comment data;
searching a propagation case with the similarity greater than a similarity threshold value and the highest similarity with the target information in the propagation case library according to the keyword;
and acquiring a propagation process curve corresponding to the propagation case to obtain the first propagation process curve.
In the implementation process, the propagation process of the target information can be simulated and predicted through the propagation cases with similar contents. And determining the propagation cases in the propagation case library by comparing the content similarity of the target information and the information samples in the case library. Specifically, a propagation curve of a propagation case is obtained by extracting the content of the target information and the keywords in the comment data and searching the propagation case with the highest similarity to the target information in the propagation case library according to the keywords, so that a first propagation process curve is obtained.
Optionally, the method further comprises:
when the first propagation process curve is not found in the propagation case library, performing parameter search on the propagation simulation model according to the comment data to determine the target parameter value;
and determining a second propagation process curve of the target information in a preset time period based on the target parameter value and the propagation simulation model.
In the implementation process, when no propagation case with similarity greater than a similarity threshold with the target information is found in the case base, a broadcast process curve from publication to the current time is generated according to the comment data of the target information, and a parameter value of a specified parameter in a propagation simulation model based on beta distribution regression is determined in a parameter search mode, so that a propagation process curve of the target information in a future preset time period can be fitted by the propagation simulation model based on the searched target parameter value, and the propagation trend of the target information in the future preset time period is predicted.
Optionally, before the obtaining of the comment data of the target information from the publication to the current time, the method further includes:
obtaining comment data of each information sample in a plurality of information samples in a propagation period;
determining a fourth propagation process curve of each information sample in the propagation period according to the comment data of each information sample in the propagation period, wherein the fourth propagation process curve is used for representing the variation trend of the comment quantity of the corresponding information sample in the propagation period;
and creating the propagation case library according to a fourth propagation process curve of each information sample in the propagation period.
In the implementation process, comment data of each information sample in the propagation period are obtained, then a fourth propagation process curve of each information sample in the propagation period is finally determined according to the comment data of each information sample in the propagation period, the fourth propagation process curve is used for representing the variation trend of the comment number of the corresponding information sample in the propagation period, and a propagation case library is created according to the obtained fourth propagation process curves of the plurality of information samples. By creating the propagation case library, the similar cases which can be referred to by the newly issued information system can be provided when the newly issued information is predicted, so that a basis is provided for the prediction of the propagation process.
Optionally, the method further comprises:
and integrating the second propagation process curve in a specified time period to obtain a propagation value score of the target information in the specified time period, wherein the specified time period is in the preset time period.
In the implementation process, the propagation value score in a specified time period of the target information can be obtained by integrating the obtained second propagation process curve, and a further basis can be provided for the propagation process research of the target information.
In a second aspect, an embodiment of the present application further provides an apparatus for predicting an information propagation trend, where the apparatus includes:
the data acquisition module is used for acquiring comment data of the target information from the release to the current time;
the query module is used for searching a first propagation process curve of a propagation case with the highest similarity to the target information in a propagation case library according to the comment data, and the first propagation process curve is used for representing the variation trend of the comment quantity of the propagation case in a propagation period;
the parameter determination module is used for acquiring a target parameter value of a designated parameter in a propagation simulation model based on beta distribution regression and used for fitting the first propagation process curve;
and the prediction module is used for determining a second propagation process curve of the target information in a preset time period based on the target parameter value and the propagation simulation model.
In the implementation process, firstly comment data of target information from release to current time needs to be acquired, then a propagation case with similarity greater than a similarity threshold and highest similarity with the target information is searched in a propagation case library with a plurality of propagation cases according to the comment data to obtain a first propagation process curve of the propagation case, the first propagation process curve is used for representing the variation trend of the comment number of the propagation case in a propagation period, then target parameter values of specified parameters in a propagation simulation model fitting the first propagation process curve are acquired, and a second propagation process curve of the target information in preset time is determined based on the target parameter values and the propagation simulation model. Therefore, the propagation condition of the target information in a future period of time can be predicted, and a visual graph can be generated for the propagation process of the target information, so that the propagation process and the future propagation trend of the target information can be conveniently known.
In a third aspect, an embodiment of the present application further provides a readable storage medium, where computer program instructions are stored, and when the computer program instructions are read and executed by a processor, the steps in any implementation manner of the first aspect are executed.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
FIG. 1 is a flowchart illustrating a method for predicting information propagation trend according to an embodiment of the present disclosure;
FIG. 2 is a flowchart illustrating another method for predicting information propagation trend according to an embodiment of the present disclosure;
fig. 3 is a flowchart of a method for creating a propagation case base according to an embodiment of the present application;
fig. 4 is a flowchart of a comment data obtaining method provided in an embodiment of the present application;
fig. 5 is a flowchart of a propagation process curve obtaining method according to an embodiment of the present application;
fig. 6 is a flowchart of another propagation process curve obtaining method according to an embodiment of the present application;
fig. 7 is a structural diagram of an information propagation trend prediction apparatus according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of them. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without any creative effort belong to the protection scope of the embodiments of the present application.
The embodiment of the application provides a method for predicting an information propagation trend, which can be applied to an electronic device, for example, the electronic device can be an electronic device with a logic calculation function, such as a Personal Computer (PC), a tablet computer, a smart phone, a Personal Digital Assistant (PDA), and the like. The execution object of the method for predicting the information propagation trend provided by the embodiment of the application is various information which can be represented as various media carriers, such as video, short video, image-text information and the like. For convenience of description, the embodiment of the present application takes target information as an example, and describes a method for predicting an information propagation trend provided by the embodiment of the present application, where the target information may be understood as any one of graphics and text information or video to be predicted and scored.
Referring to fig. 1, fig. 1 is a flowchart illustrating a method for predicting an information propagation trend according to an embodiment of the present disclosure, where the method includes the following steps:
step S1, obtaining the comment data of the target information from the issue to the current time.
The target information can be image-text information or video to be predicted and evaluated, and the comment data comprises a comment issued by a user and aiming at the target information, or a bullet screen and the like. The comment data comprises the contents of the comments or the barrage of the target information from the time of publication to the current time, and related information such as the comment time of each comment or barrage.
Optionally, the comment data may be comment data obtained by preprocessing the original comment data, where the preprocessing may include, for example, removing stop words in each comment or bullet screen in the original comment data, sorting each comment or bullet screen according to time, and the like. Furthermore, emotion analysis can be performed, and data with specified emotion tendencies can be screened out to serve as processed comment data.
Step S2, searching a first propagation process curve of the propagation case with the similarity greater than the similarity threshold and the highest similarity with the target information in the propagation case library according to the comment data.
The first propagation process curve is used for representing the variation trend of the number of comments of the propagation case in the propagation period, and the first propagation process curve is generated by combining the comment data of the propagation case with the time generated by the data and is used for representing the variation trend of the number of comments of the propagation case in the propagation period. The propagation case library is pre-established, and stores a plurality of propagation cases and a propagation process curve of each propagation case, wherein each propagation case can be historical information, namely information of the completion of the propagation process, and the information can also be image-text information or video published once, and has a relatively complete propagation cycle.
And step S3, acquiring target parameter values of specified parameters in the beta distribution-based propagation simulation model for fitting the first propagation process curve.
For example, a plurality of propagation cases and a propagation process curve of each propagation case are stored in the propagation case library, wherein the propagation process curve of each propagation case is a fitting curve that best matches the actual propagation process of each propagation case, and the fitting of the propagation process curve of each propagation case can be obtained by fitting a propagation simulation model based on a Beta distribution. After the propagation simulation model is created, corresponding model parameters need to be determined for different propagation cases, and according to comment data of any propagation case in a propagation period of the propagation case, the model parameters with the optimal effect of fitting the propagation process curve of the propagation case can be determined in a parameter searching mode, so that the propagation process curve of the propagation case is fitted according to the determined model parameters and the propagation simulation model. The propagation process curve obtained by fitting in the above manner is the propagation process curve that is most matched with the actual propagation process of the propagation case. And finally, creating a propagation case library based on the propagation cases and the obtained propagation process curves of the propagation cases.
Therefore, since the first propagation process curve is the propagation process curve corresponding to the propagation case with the highest similarity to the current target information and the similarity higher than the similarity threshold, the model parameters of the propagation simulation model corresponding to the propagation process curve can be used to fit the propagation process curve of the target information, and after the first propagation process curve is obtained, the target parameter values of the designated parameters in the propagation simulation model when the first propagation process curve is fit need to be obtained.
Step S4, determining a second propagation process curve of the target information in a future predetermined time period based on the target parameter value and the propagation simulation model.
The second propagation process curve is used for representing the change trend of the number of the comments of the target information in a future preset time period, and the preset time period is a certain preset time period in the future. And obtaining a fitting curve output by the propagation simulation model by taking the obtained target parameter value and the preset time period as the input of the propagation simulation model, so as to obtain a second propagation process curve of the target information in the preset time period. Therefore, the change trend of the number of the comments of the target information in a period of time is predicted.
Through the implementation mode, the propagation condition of the target information in a future period of time can be predicted, and a visual graph can be generated for the propagation process of the target information, so that the propagation process and the future propagation trend of the target information can be conveniently known.
Referring to fig. 2, fig. 2 is a flowchart illustrating another method for predicting information propagation trend according to an embodiment of the present disclosure, which includes the following steps:
step S201, a propagation case library is created according to the obtained information samples.
For example, fig. 3 is a flowchart of a method for creating a propagation case base according to an embodiment of the present application, and as shown in fig. 3, step S201 may specifically include the following steps:
in step S2011, comment data of each information sample in the propagation cycle is obtained.
For example, the information samples may be historical information of the completed transmission process, and each information sample may be a once-issued teletext information or video with a relatively complete transmission cycle. The comment data of each information sample in the propagation period can include comments made by the user for the information sample, or barrage and the like, and related information such as comment time of each comment or barrage.
Optionally, the comment data may be comment data obtained by preprocessing the original comment data, where the preprocessing may include: based on natural language processing technology, stop words are removed from each original comment or bullet screen in the original comment data of the information sample, and stop words such as 'some, this, in' and the like in the original comment or bullet screen are filtered and removed. And arranging according to the generation time of the comments or the barrage after removing stop words to obtain the preprocessed comment data of the information sample.
Furthermore, emotion analysis can be performed, and data with specified emotion tendencies can be screened out to serve as processed comment data. Exemplary, may include: and performing emotion analysis on the preprocessed comment data of the information sample by using an emotion analysis algorithm to obtain comment data with emotion tendencies, wherein the comment data with emotion tendencies comprise positive comments or barrage, or negative comments or barrage, or/and neutral comments or barrages.
Then, comment data having a specified emotional tendency can be acquired from the comment data having an emotional tendency.
For example, if a positive energy comment or bullet screen propagation process is to be studied, we can choose a positive comment or bullet screen. And the comment data with the appointed emotional tendency obtained after screening is used as the final comment data of the information sample. By performing the above-mentioned processing on all the information samples, the comment data of each information sample in the propagation period can be obtained.
Step S2012, determining a fourth propagation process curve of each information sample in the propagation period according to the comment data of each information sample in the propagation period.
The fourth propagation process curve is used for representing the variation trend of the comment quantity of the corresponding information sample in the propagation period.
For example, the fourth propagation process curve of each information sample is a fitted curve that is fitted based on a propagation simulation model of a pre-established Beta distribution and that best matches the actual propagation process.
And fitting the propagation process curve of each propagation case to a fitting curve which is the best matched with the actual propagation process of each propagation case, wherein the fitting of the propagation process curve of each propagation case can be obtained by fitting a propagation simulation model based on Beta (Beta) distribution.
By way of example, the propagation simulation model F may include:
b represents a beta function and is formed by combining gamma functions, t represents a time period, C represents amplitude, alpha and beta are distribution regression shape parameters, and the value range of t is [0,1 ];
where gamma represents a gamma function.
Wherein, the value of t is in the interval of [0,1], and different values represent different stages in a propagation cycle. Different values of α and β can enable the propagation simulation model F to simulate different propagation effects, for example, comment data is a positive energy-related comment or bullet screen, and for different values of α and β, the following conditions can be included:
1.0< α <1,0< β <1, and α < β. In this case, the propagation process obtained from the propagation simulation model F behaves as follows: the influence drops rapidly after the positive energy has been propagated, but rises back up before the propagation period has ended.
2.α >1, β >1, α ≈ β, and both α and β are smaller. In this case, the propagation process obtained from the propagation simulation model F behaves as follows: the influence is always low after the positive energy is spread, the positive energy is slowly increased and decreased, and the positive energy is often not strong in spreading capability.
3.α >1, β >1, and α < β. In this case, the propagation process obtained from the propagation simulation model F behaves as follows: the influence is gradually increased after the positive energy is transmitted, and is gradually decreased after the influence reaches the peak, which is a common transmission mode.
4.α >1, β >1, and α < β. In this case, the propagation process obtained from the propagation simulation model F behaves as follows: after the positive energy is spread, the influence force quickly reaches a peak and then gradually decreases, and the positive energy is often not strong in spreading capability.
5.α >1, β >1, and α > β. In this case, the propagation process obtained from the propagation simulation model F behaves as follows: the influence is gradually increased after the positive energy is transmitted, and the type is often a classical work.
The influence of positive energy is mainly reflected in the number of positive energy-related comments or bullet screens.
After the propagation simulation model is created, parameter values of corresponding model parameters can be determined for different information samples, where the model parameters mainly include: c, α and β. The model parameter with the best effect of fitting the propagation process curve of the propagation case can be determined in a parameter searching mode according to the comment data of any information sample in the propagation period, so that the propagation process curve of the information sample can be fitted through the propagation simulation model according to the determined target parameter values of the model parameters C, alpha and beta and the target parameter values of C, alpha and beta, and the fourth propagation process curve of the information sample can be obtained.
The fourth propagation process curve obtained by fitting in the above way is the propagation process curve that is the best matched with the actual propagation process of the information case. Similarly, a fourth propagation process curve in each propagation period can be obtained.
Step S2013, creating the propagation case library according to the fourth propagation process curve of each information sample in the propagation period.
Taking each information sample as a propagation case, taking the fourth propagation process curve of each information sample as the corresponding propagation process curve of the propagation case, and recording the content of the propagation case and the corresponding propagation process curve in the propagation case library to complete the creation of the propagation case library. By creating the propagation case library, the similar cases which can be referred to by the newly issued information system can be provided when the newly issued information is predicted, so that a basis is provided for the prediction of the propagation process.
Further, when there is newly released information, if it is studied that prediction of the newly released information is required, the following steps may be performed:
step S202, obtaining the comment data of the target information from the issue to the current time.
For example, fig. 4 is a flowchart of a comment data obtaining method provided in an embodiment of the present application, and as shown in fig. 4, comment data of the target information from publication to current time may be obtained in the following manner:
step S2021, original comment data of the target information from the release to the current time is obtained, the target information comprises image-text information or video information, and the original comment data comprises comments or barrages.
Step S2022, removing stop words from the original comment data, and arranging according to the generation time of comments or barrages to obtain preprocessed comment data.
Step S2023, performing sentiment analysis on the preprocessed comment data by utilizing a sentiment analysis algorithm to obtain comment data with sentiment tendency, wherein the comment data with sentiment tendency comprises positive comments or barrage, or negative comments or barrage, or/and neutral comments or barrages.
Step S2024, obtaining comment data with specified emotional tendency from the comment data with emotional tendency as comment data of the target information from the post to the current time.
The method of steps S2021 to S2024 is the same as the method of acquiring the comment data shown in step S2011, and is not described again.
Step S203, searching a first propagation process curve of the propagation case with the similarity higher than the similarity threshold and the highest similarity with the target information in the propagation case library according to the comment data.
The similarity between the propagation cases and the target information in the propagation case library is greater than a similarity threshold value, the propagation case with the highest similarity can be any propagation case in the propagation case library, and the first propagation process curve is used for representing the variation trend of the comment number of the propagation case in the propagation period.
Because the first propagation process curve is the propagation process curve corresponding to the propagation case with the highest similarity to the current target information and the similarity higher than the similarity threshold, the model parameters of the propagation simulation model corresponding to the propagation process curve can be used for fitting the propagation process curve of the target information, and after the first propagation process curve is obtained, the target parameter values of the designated parameters in the propagation simulation model when the first propagation process curve is fitted need to be obtained.
The propagation simulation model may refer to the propagation simulation model F in step S2012, which is not described again, the specified parameters are model parameters C, α, and β in the propagation simulation model F, and the specific parameter values of the model parameters C, α, and β in the propagation simulation model F when the first propagation process curve is fitted are target parameter values that need to be obtained.
Further, the step S203 may determine the first propagation process curve of the propagation case with the similarity greater than the similarity threshold and the highest similarity through two implementation manners.
For example, fig. 5 is a flowchart of a propagation process curve obtaining method provided in an embodiment of the present application, and as shown in fig. 5, in an implementation manner, the step S203 may include:
step S2031 is to determine a third propagation process curve of the target information from the publication to the current time according to the comment data.
The third propagation process curve is a curve of an actual propagation process of target information from publication to the current time, and is used for representing a variation trend of the number of comments of the target information in the time period from publication to the current time.
Step S2032, searching for a propagation process curve with the highest similarity, of which the similarity with the third propagation process curve is greater than a similarity threshold, in a propagation case library to obtain the first propagation process curve.
For example, the similarity may be calculated by calculating a euclidean distance between the third propagation process curve and the propagation process curve of each propagation case in the propagation case library, where the distance represents the similarity between the third propagation process curve of the target information and the propagation process curve of each propagation case, and the smaller the distance is, the more similar the distance is. And then, taking the propagation process curve with the minimum distance and the distance smaller than a preset distance threshold value as the first propagation process curve.
For example, fig. 6 is a flowchart of another propagation process curve obtaining method provided in the embodiment of the present application, as shown in fig. 6, in another implementation, the step S203 may include:
step S2033, the content of the target information and the keywords in the comment data are obtained.
Step S2034, searching the propagation case with the similarity higher than the similarity threshold value and the highest similarity with the target information in the propagation case library according to the keyword.
For example, a first keyword set may be obtained by extracting the content of the target information and the keywords in the comment data, a second keyword set corresponding to each propagation case is respectively extracted from the content of each propagation case in the propagation case library, and by calculating an euclidean distance between the first keyword set and the second keyword set, the distance represents the similarity between the target information and each propagation case in content, and the smaller the distance is, the more similar the distance is. Then, the propagation case with the smallest distance is selected.
Step S2035, obtaining a propagation process curve corresponding to the propagation case to obtain the first propagation process curve.
And step S204, acquiring target parameter values of specified parameters in the beta distribution-based propagation simulation model for fitting the first propagation process curve.
The propagation simulation model, i.e., the propagation simulation model F, is not described in detail. The specified parameters are model parameters C, α and β in the propagation simulation model F, and specific parameter values of the model parameters C, α and β in the propagation simulation model F when the first propagation process curve is fitted are target parameter values to be acquired.
Step S205 is performed to determine a second propagation process curve of the target information in a predetermined time period based on the target parameter value and the propagation simulation model.
And the second propagation process curve is used for representing the variation trend of the number of the comments of the target information in a future preset time period. And obtaining a fitting curve of the target information output by the propagation simulation model in the propagation process within the preset time period by taking the obtained target parameter value and the preset time period as the input of the propagation simulation model, so as to obtain a second propagation process curve of the target information in the preset time period. The change trend of the target information in the propagation process within the preset time period can be intuitively reflected through the second propagation process curve, so that the change trend of the number of comments of the target information within a period of time can be predicted.
When the comment data of the target information is selected, if the comment or the bullet screen related to the positive energy is selected, the change trend of the number of the comments or the bullet screens related to the positive energy in the transmission process of the target information in the preset time period can be intuitively reflected through the second transmission process curve obtained in the mode. Thereby predicting the propagation of positive energy of the target information.
Further, the method may further include:
step S206, integrating the second propagation process curve in a specified time period to obtain a propagation value score of the target information in the specified time period, wherein the specified time period is within the preset time period.
For example, the propagation value scoring formula may include by integrating the second propagation process curve over a specified time period, the specified time period being within the preset time period:
wherein, B represents beta function composed of gamma functions, t represents time period, C represents amplitude, alpha and beta are distribution regression shape parameters, and t value range is [0, 1%]，t1And t2Respectively representing a start time and an end time of the specified time period.
Where gamma represents a gamma function.
Through the implementation mode, after the second propagation process curve is obtained, the second propagation process curve in the specified time period (t) can be calculated through integration1To t2) When the comment data of the selected target information is the comments or the barrage related to the positive energy, the second propagation process curve obtained in the mode can intuitively reflect the change trend of the quantity of the comments or the barrages related to the positive energy in the propagation process of the target information in the preset time period, predict the propagation condition of the positive energy of the target information, and score the positive energy propagation value of the target information in the specified time period, so that more bases are provided for the research on the positive energy propagation of the target information.
Further, the method may further include:
step S207, when the first propagation process curve is not found in the propagation case library, performing parameter search on the propagation simulation model according to the review data to determine the target parameter value.
The method for determining the target parameter value through parameter search is the same as the method described in step S2012, and is not repeated here.
Step S208, determining a second propagation process curve of the target information in a preset time period based on the target parameter value and the propagation simulation model.
Therefore, in the above embodiment, when no similar case is found in the case base, the propagation simulation model parameters can be determined in a parameter search manner, and the propagation simulation model is used to fit the propagation process curve of the target information, so as to simulate and predict the propagation condition and the propagation trend of the target information.
Referring to fig. 7, fig. 7 is a structural diagram of an information propagation trend prediction apparatus according to an embodiment of the present application, where the prediction apparatus can be applied to an electronic device, and can be used to perform the above information propagation trend prediction method, and the prediction apparatus 10 can include: a data acquisition module 101, a query module 102, a parameter determination module 103 and a prediction module 104.
The data acquisition module 101 is used for acquiring comment data of target information from the release to the current time;
the query module 102 is configured to search, according to the comment data, a first propagation process curve of a propagation case with the highest similarity to the target information in a propagation case library, where the first propagation process curve is used to represent a variation trend of the comment quantity of the propagation case in a propagation period.
A parameter determining module 103, configured to obtain a target parameter value of a specified parameter in a beta distribution-based propagation simulation model for fitting the first propagation process curve.
By way of example, the propagation simulation model includes:
b represents a beta function and is formed by combining gamma functions, t represents a time period, C represents amplitude, alpha and beta are distribution regression shape parameters, and the value range of t is [0,1 ];
where gamma represents a gamma function.
And the prediction module 104 is configured to determine, based on the target parameter value and the propagation simulation model, a second propagation process curve of the target information in a future preset time period, where the second propagation process curve is used to represent a variation trend of the number of comments of the target information in the preset time period.
Optionally, the data obtaining module 101 may include:
the obtaining submodule is used for obtaining original comment data of the target information from the time of publication to the current time, the target information comprises image-text information or video information, and the original comment data comprises a comment or a bullet screen;
and the arrangement submodule is used for removing stop words from the original comment data and arranging the original comment data according to the generation time of the comments or the barrage to obtain the preprocessed comment data.
Optionally, the data obtaining module 101 may further include:
the emotion analysis submodule is used for carrying out emotion analysis on the preprocessed comment data by utilizing an emotion analysis algorithm to obtain comment data with emotion tendencies, and the comment data with emotion tendencies comprise positive comments or barrage, or negative comments or barrage, or/and neutral comments or barrage;
and the screening submodule is used for acquiring the comment data with the specified emotional tendency from the comment data with the emotional tendency as the comment data of the target information from the publication to the current time.
Optionally, the query module 102 may include:
the trend determining submodule is used for determining a third propagation process curve of the target information from the publishing to the current time according to the comment data, and the third propagation process curve is used for representing the variation trend of the number of comments of the target information in the time period from the publishing to the current time;
and the similarity judgment submodule is used for searching the propagation process curve with the similarity higher than the similarity threshold and the highest similarity with the third propagation process curve in the propagation case library to obtain the first propagation process curve.
Alternatively, in another implementation, the query module 102 may include:
the keyword extraction submodule is used for acquiring the content of the target information and the keywords in the comment data;
the case screening submodule is used for searching a propagation case with the similarity higher than a similarity threshold value and the highest similarity with the target information in the propagation case library according to the keyword;
and the acquisition submodule is used for acquiring the propagation process curve corresponding to the propagation case so as to obtain the first propagation process curve.
Optionally, the information propagation trend prediction apparatus may further include:
the parameter searching module is used for searching parameters of the propagation simulation model according to the comment data to determine the target parameter value when the first propagation process curve is not found in the propagation case library;
and the curve fitting module is used for determining a second propagation process curve of the target information in a preset time period based on the target parameter value and the propagation simulation model.
Optionally, the information propagation trend prediction apparatus may further include: a trend determination module and a creation module;
the data acquisition module 101 is further configured to acquire comment data of each information sample in the plurality of information samples in a propagation cycle before the comment data of the acquired target information is published to the current time;
the trend determining module is used for determining a fourth propagation process curve of each information sample in the propagation period according to the comment data of each information sample in the propagation period, and the fourth propagation process curve is used for representing the variation trend of the comment quantity of the corresponding information sample in the propagation period;
the creating module is used for creating the propagation case library according to a fourth propagation process curve of each information sample in the propagation period.
Optionally, the information propagation trend prediction apparatus may further include:
and the scoring module is used for obtaining the propagation value score of the target information in the specified time period by integrating the second propagation process curve in the specified time period, wherein the specified time period is in the preset time period.
In one embodiment, the second propagation process curve may be integrated to calculate a propagation cost of the target information over the specified time period, and the propagation cost calculation formula includes:
wherein, B represents beta function composed of gamma functions, t represents time period, C represents amplitude, alpha and beta are distribution regression shape parameters, and t value range is [0, 1%]，t1And t2Respectively representing a start time and an end time of the specified time period.
An embodiment of the present application further provides an electronic device, where the electronic device includes a memory and a processor, where the memory stores program instructions, and the processor executes, when reading and executing the program instructions, the steps in any implementation of the above information propagation trend prediction method provided in the embodiment of the present application.
The embodiment of the present application further provides a computer-readable storage medium, on which computer program instructions are stored, and the computer program instructions, when executed by a processor, implement the steps in any one of the above-mentioned methods for predicting an information propagation trend provided by the embodiment of the present application.
In the several embodiments provided in the present application, it should be understood that the disclosed method, apparatus, and device may be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of devices according to various embodiments of the present application. In this regard, each block in the block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams, and combinations of blocks in the block diagrams, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Therefore, the present embodiment further provides a readable storage medium, in which computer program instructions are stored, and when the computer program instructions are read and executed by a processor, the computer program instructions perform the steps of any of the block data storage methods. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a RanDom Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Claims (10)
1. A method for predicting information propagation trend, the method comprising:
obtaining comment data of target information from the release to the current time;
searching a first propagation process curve of a propagation case with similarity greater than a similarity threshold and highest similarity with the target information in a propagation case library according to the comment data, wherein the first propagation process curve is used for representing the variation trend of the comment quantity of the propagation case in a propagation period;
acquiring a target parameter value of a designated parameter in a beta distribution-based propagation simulation model for fitting the first propagation process curve, wherein the propagation simulation model is constructed in advance;
and determining a second propagation process curve of the target information in a future preset time period based on the target parameter value and the propagation simulation model, wherein the second propagation process curve is used for representing the variation trend of the number of comments of the target information in the preset time period.
2. The method of claim 1, wherein the obtaining of comment data of the target information from publication to current time comprises:
original comment data of the target information from the release to the current time is obtained, the target information comprises image-text information or video information, and the original comment data comprises a comment or a bullet screen;
and removing stop words from the original comment data, and arranging according to the generation time of the comments or the barrage to obtain the preprocessed comment data.
3. The method of claim 2, wherein the obtaining of the comment data of the target information from the publication to the current time further comprises:
performing emotion analysis on the preprocessed comment data by using an emotion analysis algorithm to obtain comment data with emotion tendencies, wherein the comment data with emotion tendencies comprises positive comments or barrage, or negative comments or barrage, or/and neutral comments or barrages;
and obtaining comment data with specified emotional tendency from the comment data with emotional tendency as comment data of the target information from the release to the current time.
4. The method as claimed in claim 1, wherein the searching for the first propagation process curve of the propagation case with the similarity greater than the similarity threshold and the highest similarity in the propagation case library according to the comment data includes:
determining a third propagation process curve of the target information from publication to the current time according to the comment data, wherein the third propagation process curve is used for representing the variation trend of the number of comments of the target information in the time period from publication to the current time;
searching a propagation process curve with the similarity higher than a similarity threshold and the highest similarity with the third propagation process curve in a propagation case library to obtain the first propagation process curve.
5. The method as claimed in claim 1, wherein the searching for the first propagation process curve of the propagation case with the similarity greater than the similarity threshold and the highest similarity in the propagation case library according to the comment data includes:
acquiring the content of the target information and the keywords in the comment data;
searching a propagation case with the similarity greater than a similarity threshold value and the highest similarity with the target information in the propagation case library according to the keyword;
and acquiring a propagation process curve corresponding to the propagation case to obtain the first propagation process curve.
6. The method of claim 1, further comprising:
when the first propagation process curve is not found in the propagation case library, performing parameter search on the propagation simulation model according to the comment data to determine the target parameter value;
and determining a second propagation process curve of the target information in a preset time period based on the target parameter value and the propagation simulation model.
7. The method of claim 1, wherein before the obtaining of the comment data of the target information from the publication to the current time, the method further comprises:
obtaining comment data of each information sample in a plurality of information samples in a propagation period;
determining a fourth propagation process curve of each information sample in the propagation period according to the comment data of each information sample in the propagation period, wherein the fourth propagation process curve is used for representing the variation trend of the comment quantity of the corresponding information sample in the propagation period;
and creating the propagation case library according to a fourth propagation process curve of each information sample in the propagation period.
8. The method of claim 1, further comprising:
and integrating the second propagation process curve in a specified time period to obtain a propagation value score of the target information in the specified time period, wherein the specified time period is in the preset time period.
9. An apparatus for predicting information propagation trend, the apparatus comprising:
the data acquisition module is used for acquiring comment data of the target information from the release to the current time;
the query module is used for searching a first propagation process curve of a propagation case with similarity greater than a similarity threshold and highest similarity with the target information in a propagation case library according to the comment data, and the first propagation process curve is used for representing the variation trend of the comment quantity of the propagation case in a propagation period;
the parameter determination module is used for acquiring a target parameter value of a specified parameter in a propagation simulation model based on beta distribution and used for fitting the first propagation process curve;
and the prediction module is used for determining a second propagation process curve of the target information in a future preset time period based on the target parameter value and the propagation simulation model, and the second propagation process curve is used for representing the variation trend of the comment quantity of the target information in the preset time period.
10. A computer readable storage medium having computer program instructions stored thereon, which when executed by a processor, implement the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011299044.0A CN112348279B (en) | 2020-11-18 | 2020-11-18 | Information propagation trend prediction method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011299044.0A CN112348279B (en) | 2020-11-18 | 2020-11-18 | Information propagation trend prediction method, device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112348279A true CN112348279A (en) | 2021-02-09 |
| CN112348279B CN112348279B (en) | 2024-04-05 |
Family
ID=74363139
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011299044.0A Active CN112348279B (en) | 2020-11-18 | 2020-11-18 | Information propagation trend prediction method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112348279B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112632364A (en) * | 2021-03-09 | 2021-04-09 | 中译语通科技股份有限公司 | News propagation speed evaluation method and system |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104008150A (en) * | 2014-05-20 | 2014-08-27 | 中国科学院信息工程研究所 | Method and system for predicting social network information transmission trend |
| CN104915397A (en) * | 2015-05-28 | 2015-09-16 | 国家计算机网络与信息安全管理中心 | Method and device for predicting microblog propagation tendencies |
| US20160269431A1 (en) * | 2014-01-29 | 2016-09-15 | Hewlett Packard Enterprise Development Lp | Predictive analytics utilizing real time events |
| US9686341B1 (en) * | 2009-08-20 | 2017-06-20 | A9.Com, Inc. | Review trends |
| CN108564479A (en) * | 2017-12-20 | 2018-09-21 | 重庆邮电大学 | A kind of system and method for propagating trend based on hidden link analysis much-talked-about topic |
| CN108733782A (en) * | 2018-05-08 | 2018-11-02 | 平安科技（深圳）有限公司 | Method, apparatus, computer equipment and the storage medium of assets trend analysis |
| CN110096647A (en) * | 2019-05-10 | 2019-08-06 | 腾讯科技（深圳）有限公司 | Optimize method, apparatus, electronic equipment and the computer storage medium of quantitative model |
| CN110245792A (en) * | 2019-06-03 | 2019-09-17 | 北京清博大数据科技有限公司 | A kind of network public opinion prediction method, device, terminal and storage medium |
| CN110297984A (en) * | 2019-05-17 | 2019-10-01 | 中国传媒大学 | Information transmission dynamics system, construction method, device and medium based on microblogging |
| CN111222051A (en) * | 2020-01-16 | 2020-06-02 | 深圳市华海同创科技有限公司 | Training method and device of trend prediction model |
| CN111949848A (en) * | 2020-08-06 | 2020-11-17 | 国家计算机网络与信息安全管理中心 | Cross-platform propagation situation assessment and grading method based on specific events |
-
2020
- 2020-11-18 CN CN202011299044.0A patent/CN112348279B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9686341B1 (en) * | 2009-08-20 | 2017-06-20 | A9.Com, Inc. | Review trends |
| US20160269431A1 (en) * | 2014-01-29 | 2016-09-15 | Hewlett Packard Enterprise Development Lp | Predictive analytics utilizing real time events |
| CN104008150A (en) * | 2014-05-20 | 2014-08-27 | 中国科学院信息工程研究所 | Method and system for predicting social network information transmission trend |
| CN104915397A (en) * | 2015-05-28 | 2015-09-16 | 国家计算机网络与信息安全管理中心 | Method and device for predicting microblog propagation tendencies |
| CN108564479A (en) * | 2017-12-20 | 2018-09-21 | 重庆邮电大学 | A kind of system and method for propagating trend based on hidden link analysis much-talked-about topic |
| CN108733782A (en) * | 2018-05-08 | 2018-11-02 | 平安科技（深圳）有限公司 | Method, apparatus, computer equipment and the storage medium of assets trend analysis |
| CN110096647A (en) * | 2019-05-10 | 2019-08-06 | 腾讯科技（深圳）有限公司 | Optimize method, apparatus, electronic equipment and the computer storage medium of quantitative model |
| CN110297984A (en) * | 2019-05-17 | 2019-10-01 | 中国传媒大学 | Information transmission dynamics system, construction method, device and medium based on microblogging |
| CN110245792A (en) * | 2019-06-03 | 2019-09-17 | 北京清博大数据科技有限公司 | A kind of network public opinion prediction method, device, terminal and storage medium |
| CN111222051A (en) * | 2020-01-16 | 2020-06-02 | 深圳市华海同创科技有限公司 | Training method and device of trend prediction model |
| CN111949848A (en) * | 2020-08-06 | 2020-11-17 | 国家计算机网络与信息安全管理中心 | Cross-platform propagation situation assessment and grading method based on specific events |
Non-Patent Citations (2)
| Title |
|---|
| 彭丹 等: ""基于网络评论的网络舆情研究"", 《现代情报》, vol. 29, no. 12, pages 4 - 7 * |
| 赵丽 等: ""博客网络中具有突发性的话题传播模型"", 《软件学报》, vol. 20, no. 5, pages 1384 - 1392 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112632364A (en) * | 2021-03-09 | 2021-04-09 | 中译语通科技股份有限公司 | News propagation speed evaluation method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112348279B (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106649818B (en) | Application search intention identification method and device, application search method and server | |
| CN109033261B (en) | Image processing method, image processing apparatus, image processing device, and storage medium | |
| Liu et al. | Heterogeneous features and model selection for event-based media classification | |
| CN108304493B (en) | Hypernym mining method and device based on knowledge graph | |
| CN111026965B (en) | Hot topic tracing method and device based on knowledge graph | |
| CN104021140A (en) | Network video processing method and device | |
| CN111291177A (en) | Information processing method and device and computer storage medium | |
| WO2012111226A1 (en) | Time-series document summarization device, time-series document summarization method and computer-readable recording medium | |
| Shawon et al. | Website classification using word based multiple n-gram models and random search oriented feature parameters | |
| CN112883734A (en) | Block chain security event public opinion monitoring method and system | |
| Sharaff et al. | Analysing fuzzy based approach for extractive text summarization | |
| Kumar et al. | Key-lectures: keyframes extraction in video lectures | |
| CN109492401B (en) | Content carrier risk detection method, device, equipment and medium | |
| CN112348279B (en) | Information propagation trend prediction method, device, electronic equipment and storage medium | |
| Liang et al. | Mapping the increasing use of llms in scientific papers | |
| JP2004341948A (en) | Concept extraction system, concept extraction method, program therefor, and storing medium thereof | |
| KR102285080B1 (en) | Issue occurrence prediction system | |
| Karsdorp et al. | The love equation: Computational modeling of romantic relationships in french classical drama | |
| Seddati et al. | Towards human performance on sketch-based image retrieval | |
| CN112650834B (en) | Intention model training method and device | |
| JP4424125B2 (en) | Predictive topicality evaluation apparatus and program | |
| Hassaine et al. | Hyper rectangular trend analysis application to islamic rulings (fatwas) | |
| CN116136866B (en) | Knowledge graph-based correction method and device for Chinese news abstract factual knowledge | |
| CN111813964B (en) | Data processing method based on ecological environment and related equipment | |
| Gaur | Data mining and visualization on legal documents |
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 |