CN111931098A - Monitoring object determination method and device and electronic equipment - Google Patents
Monitoring object determination method and device and electronic equipment Download PDFInfo
- Publication number
- CN111931098A CN111931098A CN201910347627.7A CN201910347627A CN111931098A CN 111931098 A CN111931098 A CN 111931098A CN 201910347627 A CN201910347627 A CN 201910347627A CN 111931098 A CN111931098 A CN 111931098A
- Authority
- CN
- China
- Prior art keywords
- topic
- monitoring
- topics
- determining
- interest
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 155
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000004364 calculation method Methods 0.000 claims description 27
- 230000008859 change Effects 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 13
- 230000015654 memory Effects 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 13
- 238000001647 drug administration Methods 0.000 description 13
- 238000012549 training Methods 0.000 description 12
- 238000012545 processing Methods 0.000 description 9
- 238000004422 calculation algorithm Methods 0.000 description 7
- 239000013598 vector Substances 0.000 description 6
- 239000003814 drug Substances 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 229940079593 drug Drugs 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 239000002537 cosmetic Substances 0.000 description 3
- 230000036541 health Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013481 data capture Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000009429 distress Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000855 fermentation Methods 0.000 description 1
- 230000004151 fermentation Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A monitoring object determination method, a monitoring object determination device and electronic equipment comprise: determining a monitoring topic; calculating the correlation degree of the monitoring topic and the monitored subject; the monitored main bodies are a plurality of monitoring objects with attribute description; and determining the monitoring object related to the monitoring topic according to the relevance. By adopting the scheme of the application, the incidence relation between the monitoring topic and the monitoring main body can be established by determining the monitoring topic and calculating the correlation degree of the monitoring topic and the monitored main body, and the related party of the topic is rapidly determined at the first time after the topic is generated so as to be processed in time to promote social stability.
Description
Technical Field
The present application relates to an internet event monitoring technology, and in particular, to a method and an apparatus for determining a monitored object, and an electronic device.
Background
With the rapid development and popularization of networks, the internet has become a necessity for people's life. Ever since the network existed, people could publish anything they hear, see, feel on the web in various web spaces, web forums.
The hot topic generally refers to the hot problems which are most concerned by the public in a certain range and a certain time, and the hot problems can cause the public to pay strong attention and even cause continuous fermentation. For those hot topics which are discussed more, the supervision department needs to pay more attention, and accurately determine the enterprise or market subject involved in the topic from a large number of candidates in time for important monitoring in the first time so as to promote social stability.
Problems existing in the prior art:
at present, no effective means for timely processing network topics and determining topic related parties exists.
Disclosure of Invention
The embodiment of the application provides a method and a device for determining a monitored object and electronic equipment, so as to solve the technical problem.
According to a first aspect of an embodiment of the present application, there is provided a monitored object determination method, including:
determining a monitoring topic;
calculating the correlation degree of the monitoring topic and the monitored subject; the monitored main bodies are a plurality of monitoring objects with attribute description;
and determining the monitoring object related to the monitoring topic according to the relevance.
According to a second aspect of the embodiments of the present application, there is provided a monitored object determining apparatus, including:
the topic determining module is used for determining a monitoring topic;
the calculation module is used for calculating the correlation degree of the monitoring topic and the monitored subject; the monitored main bodies are a plurality of monitoring objects with attribute description;
and the object determining module is used for determining the monitoring object related to the monitoring topic according to the relevance.
According to a third aspect of embodiments of the present application, there is provided an electronic apparatus, including: one or more memories in which a computer program executable on the processor is stored and a processor which, when executed, implements the method as described above.
Has the advantages that:
by adopting the monitoring object determining method, the monitoring object determining device and the electronic equipment provided by the embodiment of the application, the monitoring object related to the monitoring topic is determined by determining the monitoring topic and calculating the correlation degree of the monitoring topic and the monitored main body, the association relation is established between the monitoring topic and the monitoring main body, and the related party of the topic can be rapidly determined at the first time after the topic is generated, so that the timely processing is carried out to promote the social stability.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 shows a schematic flow chart of an implementation of a monitored object determination method in embodiment 1 of the present application;
fig. 2 is a schematic flowchart illustrating an implementation of a monitored object determining method in embodiment 2 of the present application;
fig. 3 is a schematic flowchart illustrating an implementation of a monitored object determining method in embodiment 3 of the present application;
fig. 4 is a schematic flowchart illustrating an implementation of a monitored object determining method in embodiment 4 of the present application;
fig. 5 is a schematic structural diagram of a monitored object determining apparatus in embodiment 5 of the present application;
fig. 6 shows a schematic structural diagram of an electronic device in embodiment 6 of the present application.
Detailed Description
The scheme in the embodiment of the application can be implemented by adopting various computer languages, such as object-oriented programming language Java and transliterated scripting language JavaScript.
In order to make the technical solutions and advantages of the embodiments of the present application more apparent, the following further detailed description of the exemplary embodiments of the present application with reference to the accompanying drawings makes it clear that the described embodiments are only a part of the embodiments of the present application, and are not exhaustive of all embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Example 1
The embodiment of the present application provides a method for determining a monitored object, which is described below.
Fig. 1 shows a schematic flow chart of an implementation of a monitored object determining method in embodiment 1 of the present application.
As shown in the figure, the monitoring object determining method includes:
102, calculating the correlation degree of the monitoring topic and a monitored subject; the monitored main bodies are a plurality of monitoring objects with attribute description;
and 103, determining a monitoring object related to the monitoring topic according to the relevance.
In a specific implementation, the determining the monitoring topic may include: acquiring or receiving a monitoring topic input by a user; or the system automatically calculates according to a preset algorithm to obtain the monitoring topic.
The monitoring topics may be topics of hot search or hot meeting at the current time, such as: students in a certain school fall into the building for investigation, a certain building catches fire and the like.
The monitored main body can be an enterprise, a department, an individual and the like, can be in the global range, can also be in the domestic range, or in the city/province and the like, and can be specifically set according to actual needs. The monitored main bodies can be a plurality of main bodies, and all the main bodies have attribute description, the attribute description can be stored in the form of documents or folders and the like, and specifically can comprise names, registration information, geographic positions, service introduction and the like of enterprises or departments, or personal identity information, addresses, working conditions, academic information and the like.
In specific implementation, the correlation between the monitoring topic and the monitored subject is calculated, and an existing correlation calculation method may be adopted, for example: machine learning, K-Means clustering, euclidean distance calculation, etc., and the specific algorithm is not described herein.
The monitoring topic may include a plurality of articles or comment information and other contents, and in the embodiment of the present application, the relevance between the articles or comment information and the monitored subject may be calculated, so that the relevance between the articles or comment information and one or more monitored subjects is higher, and thus a list of the monitoring objects corresponding to the monitoring topic (i.e., one or more monitored subjects with higher relevance) is finally determined.
The monitoring objects can be one or more, and can be displayed in a list form, or can be displayed in combination with position information and the like in a network diagram form.
In specific implementation, when determining the monitoring object related to the monitoring topic, the strength of the correlation degree may be combined with other features or attributes of the monitored subject. For example: and determining a monitoring object related to the monitoring topic according to the strength of the correlation between the determined monitoring topic and the monitored subject, the region or the activity region of the monitored subject, the personnel scale or the asset scale of the monitored subject and the like.
By adopting the monitoring object determining method provided by the embodiment of the application, the monitoring object related to the monitoring topic is determined by determining the monitoring topic and calculating the correlation degree of the monitoring topic and the monitored main body, and the association relation is established between the network topic and the monitoring main body, so that the related party of the topic can be rapidly determined at the first time after the topic is generated, and the timely processing is carried out to promote the social stability.
Example 2
The embodiment of the present application provides a method for determining a monitored object, which is described below.
Fig. 2 shows a schematic flowchart of an implementation of the monitored object determining method in embodiment 2 of the present application.
As shown in the figure, the monitoring object determining method includes:
and 204, determining a monitoring object related to the monitoring topic according to the relevance.
According to the embodiment of the application, the system automatically determines the monitoring topic and calculates the correlation degree of the monitoring topic and the monitored main body to obtain the monitoring object related to the monitoring topic.
Specifically, according to the embodiment of the application, the monitoring topic can be selected from the multiple topics through the relevance of the interest points of the interest content and the multiple topics and the change trend of each topic, so that the system can automatically and timely determine the monitoring topic under the condition that a certain topic is sudden but not noticed or found by a supervisor, the purpose of early warning is achieved, and a monitoring object corresponding to the monitoring topic is determined so as to be convenient for the supervisor to process.
In one embodiment, the determining the content of interest comprises:
acquiring preset interest point keywords and/or information related to a supervisor;
and determining the interested content according to the interest point keywords and/or the information related to the supervisor.
In a specific implementation, the determination of the content of interest may be a keyword that is input or selected in advance by a user (a supervisor), for example: assuming that the supervision department is a drug administration, the supervisor of the drug administration can input keywords that the content of interest may be health products, food safety, etc. in advance. When a topic about a health care product is burst, the system can quickly determine that the topic belongs to the content concerned by the drug administration, and calculate the related party corresponding to the topic and inform the drug administration of the related party so as to facilitate the drug administration to process the topic.
In specific implementation, in order to be more intelligent, the embodiment of the present application may also be implemented in the following manner.
Acquiring information related to a supervisor;
determining the interested content according to the information related to the supervisor
In one embodiment, the information related to the administrator includes: articles issued by the supervisor, information describing the scope of the supervisor's business or the field of interest, etc.
In the embodiment of the application, the determination of the interesting content can be automatically determined through a system, manual input of a supervisor is not needed, and the method is more intelligent. For example: assuming that the monitoring party is a drug administration, the system may determine that the content of interest may further include cosmetics, medical devices, and the like through announcements, regulatory documents, authority lists, and the like in an official website of the drug administration, or media report articles about the drug administration acquired in other manners. When a certain topic about a cosmetic event happens suddenly, the system can quickly determine that the topic belongs to the content concerned by the drug administration, and calculate the related party corresponding to the topic and inform the drug administration of the related party for processing.
Example 3
The embodiment of the present application provides a method for determining a monitored object, which is described below.
Fig. 3 shows a schematic flowchart of an implementation of the monitored object determining method in embodiment 3 of the present application.
As shown in the figure, the monitoring object determining method includes:
301, acquiring multi-source information;
and step 306, determining the monitoring object related to the monitoring topic according to the relevance.
According to the embodiment of the application, various multi-source information can be obtained in advance, the multi-source information is divided into multiple topics according to semantic similarity, and then monitoring topics can be selected from the multiple topics.
In the current society, both information sources and information amount are large, and multi-source information may refer to information expressed by a plurality of information sources in a data form, and specifically, the multi-source information may be acquired in various ways (e.g., network data capture, system information purchase, etc.).
The information sources of the multi-source information may include: an internet website, a social platform, a social public or private information collection platform, a telephone channel such as a customer line 12315, or a customer service department of an enterprise, etc.
In specific implementation, after the multi-source information is acquired, the multi-source information can be divided into a plurality of topics according to semantic similarity. The semantic similarity can be implemented by using a similarity algorithm in the prior art, and the detailed algorithm is not described herein.
Because the multi-source information is more, a plurality of topics may be obtained after division, and subsequently, a monitoring topic can be determined from the plurality of topics according to the interest points of the monitoring party, for example: supposing that topics T1-T30000 are obtained according to multi-source information division, the monitoring topic determined by the interest point of the supervising user a may be T5, and the monitoring topics determined by the interest point of the supervising user B may be T233, T439, and T8001.
Example 4
The embodiment of the present application provides a method for determining a monitored object, which is described below.
Fig. 4 shows a schematic flowchart of an implementation of the monitored object determining method in embodiment 4 of the present application.
As shown in the figure, the monitoring object determining method includes:
and step 407, determining a monitoring object related to the monitoring topic according to the relevance.
The embodiment of the application can divide multi-source information into a plurality of topics according to semantic similarity, and then further divide the topics into positive topics and negative topics, so that the monitoring topics can be selected from the positive topics or the negative topics according to actual needs of a monitoring party, the range can be reduced when the monitoring topics are determined, and the monitoring topics can be determined more accurately and quickly.
For example: when a supervisor presets and sets some keywords to supervise and manage negative topics in some aspects, the system can determine that topics interested by the supervisor are negative topics according to the keywords, then, in the embodiment of the application, those topics which belong to negative topics among a plurality of topics obtained in advance can be selected, only the negative topics and determined interesting contents are subjected to interest point correlation calculation, and monitoring topics are selected from the negative topics according to the change trend of the negative topics and the interest point correlation, so that the topic range can be greatly reduced, and the monitoring topics can be quickly determined.
For another example: when a supervisor presets some keywords to search for positive topics in some aspects, the system determines that the topics interested by the supervisor are positive topics, then, in the embodiment of the application, the topics belonging to the positive are selected from a plurality of topics obtained in advance, only the positive topics and the determined interesting content are subjected to interest point correlation calculation, and monitoring topics are selected from the positive topics according to the change trend of the positive topics and the interest point correlation, so that the topic range can be greatly reduced, and the monitoring topics can be quickly determined.
In specific implementation, the division of multiple topics into positive topics and negative topics can be realized according to the existing topic classification mode, and the existing specific classification mode is not elaborated in detail herein.
For the convenience of the implementation description of the present application, the present application provides the following implementation mode to realize the positive and negative face classification of topics.
In one embodiment, the classifying the pre-obtained plurality of topics into positive and negative topics includes:
converting sentences included in each topic obtained in advance into word vectors;
performing sentiment analysis on the plurality of topics obtained in advance according to the word vector and a classifier obtained by training in advance;
the parameters of the classifier obtained through pre-training are obtained through training each sentence in a training data set, and the training data set comprises word vectors of each word obtained through training.
Those skilled in the art should understand that the above classification is only one implementation manner of the present application, and other schemes of classifying topics into positive and negative for performing subsequent operation steps of the present application are also within the protection scope of the present application.
In one embodiment, the trend of each topic is calculated in advance by the following steps:
determining the attribute value of each topic in the current time period or time point;
calculating to obtain first variable quantities of the N topics according to the attribute values of the topics in the current time period or time point and the attribute values of the topics in the previous N time periods or time points;
calculating a second variable quantity of the topic according to the first variable quantity of the N topics;
determining that the second amount of change of the topic is a measure of the trend of change of the topic.
In one embodiment, the time period may be in the range of hourly, daily, monthly, etc., and the time period may be referred to as the time interval Δ T.
In specific implementation, it is assumed that the number of discussed articles, the number of searched articles, and/or the number of articles related to a topic are n on the first day and m.
In the embodiment of the application, the latest time node T can be obtained0Initially, the value of the attribute for the current time period, Δ T, is determined, and then the current time period T may be utilized0Data, last time period T0Δ T data, last time period T0-2 Δ T data.. to calculate the first variation from the data of the first N time periods.
The embodiment of the application can accurately judge which topics need to be concerned by taking the variation trend as the basis for topic selection in advance, and the application is not the number of times that a certain topic is concerned in a certain time period in a simple time, but further calculates the first variation and then calculates the second variation by combining the data of the previous N time periods, so that which topics change fast and which topics change slowly can be determined more accurately, and then the topics which need to be concerned are determined accurately.
In one embodiment, calculating first variation amounts of N topics according to attribute values of the topics in a current time period or time point and attribute values of the topics in previous N time periods or time points includes:
respectively calculating the difference value between the attribute value of the topic in the current time period and the attribute value of the topic in the N-i time period, or respectively calculating the difference value between the attribute value of the topic at the current time point and the attribute value of the topic at the N-i time point; wherein i is an integer, i is more than or equal to 0 and is less than N;
and obtaining first variable quantities of the N topics according to the difference value.
In one embodiment, the obtaining the first variation of the N topics according to the difference may specifically be calculated according to the following formula:
wherein, f (T)0) Is the attribute value of the current time period or time point, f (T)0-i x Δ T) is the value of the property for the N-i th time period or time point, said Δ T being the step of the change of the time period or time point.
The first variation of the topic is a slope determined by the attribute values of the current time period and the previous (N-i) th time period.
In one embodiment, the calculating a second variation of the topic according to the first variation of the N topics includes:
fitting to obtain second variable quantities of the N topics according to the first variable quantities of the N topics;
the first variation of the N topics satisfies
Wherein k is the second amount of change of the topic,
is yiAverage value of yiIs the first amount of change, x, of the topiciIs yiCorresponding abscissa, xi＝T0-i*ΔT，
Is xiAverage value of (a).
In specific implementation, according to the first variation of the N topics, the slope (i.e., the second variation) of the first variation of the N topics may be obtained by fitting.
When the first variation of the N topics is on the same straight line, the difference value of the first variations of any two topics is the slope of the first variations of the N topics;
when the first variation of the N topics is not on the same straight line, fitting may be performed by using an existing fitting algorithm to obtain a slope of the first variation of the N topics. At least, the software such as Origin or excel has already provided with a corresponding fitting algorithm, and the specific process of the fitting algorithm in the embodiment of the application is not described in detail herein.
In one embodiment, the selecting a monitoring topic from the plurality of topics according to the interest point relevance and the pre-obtained trend of each topic includes:
normalizing the interest point relevance and the variation trend of each topic;
carrying out weighted calculation on the value of interest point correlation obtained by normalization and the value of the variation trend;
and determining the monitoring topic according to the weighting calculation result of each topic.
In specific implementation, the value of the correlation of the interest points and the value of the variation trend of each topic may be in different quantitative values, and in the embodiment of the present application, the correlation of the interest points and the variation trend of each topic may be normalized, for example, normalized to a numerical value between-1 and 1, and then weighted calculation is performed, and the monitored topic is determined according to a weighted calculation result.
In one embodiment, the method further comprises:
updating the attribute description of the monitored subject;
calculating the correlation degree of the monitoring topic and the monitored subject according to the updated attribute description;
and determining the monitoring object related to the monitoring topic according to the relevance.
The embodiment of the application can update the attribute description of the monitored subject regularly or irregularly, then calculate the correlation degree of the monitoring topic and the monitored subject according to the updated attribute description and determine the monitoring object related to the monitoring topic, and ensure the accuracy of the monitored subject through the updating of the attribute description of the monitored subject, thereby ensuring the accuracy of the monitoring object related to the subsequent monitoring topic.
Example 5
Based on the same inventive concept, the embodiment of the application provides a monitoring object determining device, the principle of solving the problem is similar to that of a monitoring object determining method, and repeated parts are not repeated.
Fig. 5 is a schematic structural diagram of a monitored object determining apparatus in embodiment 5 of the present application.
As shown in the drawing, the monitored object determining apparatus includes:
a topic determining module 501, configured to determine a monitoring topic;
a calculating module 502, configured to calculate a correlation between the monitoring topic and a monitored subject; the monitored main bodies are a plurality of monitoring objects with attribute description;
an object determining module 503, configured to determine, according to the relevancy, a monitoring object related to the monitoring topic.
In one embodiment, the topic determination module includes:
a correlation calculation unit, configured to calculate, according to the determined content of interest and a plurality of topics obtained in advance, point-of-interest correlations between the content of interest and the plurality of topics obtained in advance;
and the topic selecting unit is used for selecting a monitoring topic from the plurality of topics according to the relevance of the interest points and the obtained variation trend of each topic in advance.
In one embodiment, the apparatus further comprises:
the interest point determining module is used for acquiring preset interest point keywords and/or information related to a supervisor; and determining the interested content according to the interest point keywords and/or the information related to the supervisor.
In one embodiment, the information related to the administrator includes: articles issued by the supervisor, information describing the scope of the supervisor's business or the area of concern, and the like.
In one embodiment, the apparatus further comprises:
the topic set determining module is used for acquiring multi-source information; and dividing the multi-source information into a plurality of topics according to semantic similarity.
In one embodiment, the apparatus further comprises:
a topic classification module, configured to classify a plurality of topics obtained in advance into a positive topic and a negative topic before the calculating of the interest point relevance between the interest content and the plurality of topics obtained in advance;
and the topic selection module is used for selecting the positive topic or the negative topic as the topic for subsequently carrying out interest point relevance calculation according to the determined interesting content.
In one embodiment, the topic classification module includes:
the word conversion unit is used for converting sentences included in each topic obtained in advance into word vectors;
the analysis unit is used for carrying out sentiment analysis on the plurality of topics obtained in advance according to the word vectors and a classifier obtained through pre-training;
the parameters of the classifier obtained through pre-training are obtained through training each sentence in a training data set, and the training data set comprises word vectors of each word obtained through training.
In one embodiment, the apparatus further comprises:
the topic trend calculation module is used for determining the attribute value of each topic in the current time period or time point; calculating to obtain first variable quantities of the N topics according to the attribute values of the topics in the current time period or time point and the attribute values of the topics in the previous N time periods or time points; calculating a second variable quantity of the topic according to the first variable quantity of the N topics; determining that the second amount of change of the topic is a measure of the trend of change of the topic.
In one embodiment, the topic selection unit includes:
a normalizing subunit, configured to normalize the interest point relevance and the variation trend of each topic;
the calculating subunit is used for performing weighted calculation on the value of the interest point correlation obtained by normalization and the value of the variation trend;
and the determining subunit is used for determining the monitoring topic according to the weighted calculation result of each topic.
In one embodiment, the apparatus further comprises: the updating module is used for updating the attribute description of the monitored subject;
the calculation module is further used for calculating the correlation degree of the monitoring topic and the monitored subject according to the updated attribute description;
the object determination module is further used for determining the monitoring object related to the monitoring topic according to the relevance.
Example 6
Based on the same inventive concept, embodiments of the present application provide an electronic device, which is described below.
Fig. 6 shows a schematic structural diagram of an electronic device in embodiment 6 of the present application.
As shown, the electronic device includes: one or more memories 601 in which a computer program is stored that is executable on the processor, and a processor 602 that implements the method according to any of embodiments 1 to 4 when the computer program is executed by the processor.
Based on the same inventive concept, embodiments of the present application provide a computer storage medium having a computer program stored thereon, where the computer program is executed by a processor to perform the steps of the method according to any one of embodiments 1 to 4.
Example 7
The following embodiments of the present application are described in detail with reference to a specific example.
Assuming that a plurality of multi-source information is obtained from channels such as an internet website, a social platform, a social information collection platform, a telephone hotline and the like, the multi-source information is divided into different topic categories according to semantic similarity, as shown in the following table:
each obtained topic is further divided into a positive topic and a negative topic, and continuing the above table as an example, the negative topic may include a right-wind wheel distress.
The embodiment of the application can follow up each topic according to different time periods, for example: the number of the comments and the articles of a certain topic in the 3 month in 2018 is total, the number of the comments and the articles in the 4 month in 2018 is total, and … is used for calculating the change trend of the topic. Meanwhile, the interest point relevance of the supervisor can be calculated, for example: according to the attribute characteristics of the drug administration, the safety problems of food, medicine and cosmetics concerned by the drug administration can be determined, and the relevance of the drug administration and the interest points of various topics can be determined according to the safety problems.
Assuming that the point-of-interest correlation of the drug monitoring bureau and a certain topic is higher than a preset correlation threshold (for example, the point-of-interest correlation is 5), when the change trend of the topic (for example, the change trend is 6000) is determined to exceed the preset change threshold, the monitoring topic of the drug monitoring bureau is determined to be the topic.
Assume that information on each business and each person (monitored subject) nationwide is stored in the server cluster, for example: corporate representatives of enterprise a, registered funds, size of personnel, field of endeavor, etc., all of the information associated therewith may be stored in separate folders or documents by each enterprise or individual.
In the embodiment of the application, the determined monitoring topic and the monitored subject in the server cluster are subjected to relevancy calculation, for example: after the contents of the topic, the article and the like are subjected to relevancy calculation with enterprise information and personal information in the server cluster, the monitored subjects with relevancy ranking 3 can be determined to be company A, company B and person C.
Finally, when the topic change trend exceeds a preset change threshold, all related information of the company A, the company B and the person C (such as the address and the contact way of the company A, the identity information and the contact way of a legal representative and the like) is taken as a list of monitoring objects in time and pushed to a drug monitoring office so as to facilitate the drug monitoring office to perform subsequent processing.
In addition, the embodiment of the present application can also be applied to the interior of an enterprise, for example: a plurality of employees in an enterprise are taken as monitored main bodies, all attribute descriptions (such as employee numbers, names, academic calendars, addresses, published articles, contents in charge of work and the like) of each employee are prestored in the system, after an enterprise manager determines a certain interested content, the system can determine a monitoring topic according to the interested content of the manager, and then determines the employees related to the monitoring topic by calculating the correlation degree of the monitoring topic and each employee.
The application scenarios are not limited in the present application, and a person skilled in the art may apply the technical solution of the present application in multiple scenarios according to actual needs, and it is obvious that the technical solutions applied in these scenarios are all within the protection scope of the present application.
By adopting the scheme provided by the embodiment of the application, under the condition that the popularity of a certain topic to be discussed or concerned is increased in a short time, the topic can be timely and accurately selected from a plurality of topics as the monitoring topic, the monitoring object related to the topic is calculated, and specific information such as a responsible party, a victim and the like related to the topic is listed to be convenient for a supervision department to process.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (19)
1. A monitored object determination method is characterized by comprising the following steps:
determining a monitoring topic;
calculating the correlation degree of the monitoring topic and the monitored subject; the monitored main bodies are a plurality of monitoring objects with attribute description;
and determining the monitoring object related to the monitoring topic according to the relevance.
2. The method of claim 1, wherein the determining a monitoring topic comprises:
according to the determined interesting content and a plurality of topics obtained in advance, calculating the interest point relevance of the interesting content and the topics obtained in advance;
and selecting a monitoring topic from the plurality of topics according to the interest point relevance and the obtained change trend of each topic in advance.
3. The method of claim 2, wherein the determining the content of interest comprises: acquiring preset interest point keywords and/or information related to a supervisor; and determining the interested content according to the interest point keywords and/or the information related to the supervisor.
4. The method of claim 3, wherein the information related to the administrator comprises: articles issued by the supervisor, information describing the scope of the supervisor's business or the area of interest.
5. The method of claim 2, wherein the plurality of topics are previously obtained by:
acquiring multi-source information;
and dividing the multi-source information into a plurality of topics according to semantic similarity.
6. The method of claim 2, prior to said calculating point of interest relevance of said content of interest to a plurality of topics previously obtained, further comprising:
dividing a plurality of topics obtained in advance into positive topics and negative topics;
and selecting a positive topic or a negative topic as a topic for subsequent interest point relevance calculation according to the determined interesting content.
7. The method according to claim 2, characterized in that the trend of change of each topic is calculated in advance by the following steps:
determining the attribute value of each topic in the current time period or time point;
calculating to obtain first variable quantities of the N topics according to the attribute values of the topics in the current time period or time point and the attribute values of the topics in the previous N time periods or time points;
calculating a second variable quantity of the topic according to the first variable quantity of the N topics;
determining that the second amount of change of the topic is a measure of the trend of change of the topic.
8. The method of claim 2, wherein the selecting a monitoring topic from the plurality of topics according to the interest point relevance and a pre-obtained trend of each topic comprises:
normalizing the interest point relevance and the variation trend of each topic;
carrying out weighted calculation on the value of interest point correlation obtained by normalization and the value of the variation trend;
and determining the monitoring topic according to the weighting calculation result of each topic.
9. The method of claim 1, further comprising:
updating the attribute description of the monitored subject;
calculating the correlation degree of the monitoring topic and the monitored subject according to the updated attribute description;
and determining the monitoring object related to the monitoring topic according to the relevance.
10. A monitored object determination apparatus, comprising:
the topic determining module is used for determining a monitoring topic;
the calculation module is used for calculating the correlation degree of the monitoring topic and the monitored subject; the monitored main bodies are a plurality of monitoring objects with attribute description;
and the object determining module is used for determining the monitoring object related to the monitoring topic according to the relevance.
11. The apparatus of claim 10, wherein the topic determination module comprises:
a correlation calculation unit, configured to calculate, according to the determined content of interest and a plurality of topics obtained in advance, point-of-interest correlations between the content of interest and the plurality of topics obtained in advance;
and the topic selecting unit is used for selecting a monitoring topic from the plurality of topics according to the relevance of the interest points and the obtained variation trend of each topic in advance.
12. The apparatus of claim 11, further comprising:
the interest point determining module is used for acquiring preset interest point keywords and/or information related to a supervisor; and determining the interested content according to the interest point keywords and/or the information related to the supervisor.
13. The apparatus of claim 12, wherein the information related to the administrator comprises: articles issued by the supervisor, information describing the scope of the supervisor's business or the area of interest.
14. The apparatus of claim 11, further comprising:
the topic set determining module is used for acquiring multi-source information; and dividing the multi-source information into a plurality of topics according to semantic similarity.
15. The apparatus of claim 11, further comprising:
a topic classification module, configured to classify a plurality of topics obtained in advance into a positive topic and a negative topic before the calculating of the interest point relevance between the interest content and the plurality of topics obtained in advance;
and the topic selection module is used for selecting the positive topic or the negative topic as the topic for subsequently carrying out interest point relevance calculation according to the determined interesting content.
16. The apparatus of claim 11, further comprising:
the topic trend calculation module is used for determining the attribute value of each topic in the current time period or time point; calculating to obtain first variable quantities of the N topics according to the attribute values of the topics in the current time period or time point and the attribute values of the topics in the previous N time periods or time points; calculating a second variable quantity of the topic according to the first variable quantity of the N topics; determining that the second amount of change of the topic is a measure of the trend of change of the topic.
17. The apparatus as claimed in claim 11, wherein the topic selection unit comprises:
a normalizing subunit, configured to normalize the interest point relevance and the variation trend of each topic;
the calculating subunit is used for performing weighted calculation on the value of the interest point correlation obtained by normalization and the value of the variation trend;
and the determining subunit is used for determining the monitoring topic according to the weighted calculation result of each topic.
18. The apparatus of claim 10, further comprising: the updating module is used for updating the attribute description of the monitored subject;
the calculation module is further used for calculating the correlation degree of the monitoring topic and the monitored subject according to the updated attribute description;
the object determination module is further used for determining the monitoring object related to the monitoring topic according to the relevance.
19. An electronic device, comprising: one or more memories in which a computer program executable on the processor is stored and a processor which, when executed, implements the method of any of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910347627.7A CN111931098A (en) | 2019-04-28 | 2019-04-28 | Monitoring object determination method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910347627.7A CN111931098A (en) | 2019-04-28 | 2019-04-28 | Monitoring object determination method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111931098A true CN111931098A (en) | 2020-11-13 |
Family
ID=73282426
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910347627.7A Pending CN111931098A (en) | 2019-04-28 | 2019-04-28 | Monitoring object determination method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111931098A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104281607A (en) * | 2013-07-08 | 2015-01-14 | 上海锐英软件技术有限公司 | Microblog hot topic analyzing method |
| CN104933093A (en) * | 2015-05-19 | 2015-09-23 | 武汉泰迪智慧科技有限公司 | Regional public opinion monitoring and decision-making auxiliary system and method based on big data |
| CN106326481A (en) * | 2016-08-31 | 2017-01-11 | 中译语通科技（北京）有限公司 | Detection method of Weibo hot topics based on suddenness |
| CN106339463A (en) * | 2016-08-26 | 2017-01-18 | 中国传媒大学 | Network public opinion early-warning system based on logistic model and early-warning method thereof |
| CN109408620A (en) * | 2018-10-11 | 2019-03-01 | 杭州安恒信息技术股份有限公司 | A kind of method, apparatus, equipment and the storage medium of network public opinion trend prediction |
| CN109684481A (en) * | 2019-01-04 | 2019-04-26 | 深圳壹账通智能科技有限公司 | The analysis of public opinion method, apparatus, computer equipment and storage medium |
-
2019
- 2019-04-28 CN CN201910347627.7A patent/CN111931098A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104281607A (en) * | 2013-07-08 | 2015-01-14 | 上海锐英软件技术有限公司 | Microblog hot topic analyzing method |
| CN104933093A (en) * | 2015-05-19 | 2015-09-23 | 武汉泰迪智慧科技有限公司 | Regional public opinion monitoring and decision-making auxiliary system and method based on big data |
| CN106339463A (en) * | 2016-08-26 | 2017-01-18 | 中国传媒大学 | Network public opinion early-warning system based on logistic model and early-warning method thereof |
| CN106326481A (en) * | 2016-08-31 | 2017-01-11 | 中译语通科技（北京）有限公司 | Detection method of Weibo hot topics based on suddenness |
| CN109408620A (en) * | 2018-10-11 | 2019-03-01 | 杭州安恒信息技术股份有限公司 | A kind of method, apparatus, equipment and the storage medium of network public opinion trend prediction |
| CN109684481A (en) * | 2019-01-04 | 2019-04-26 | 深圳壹账通智能科技有限公司 | The analysis of public opinion method, apparatus, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fulvio et al. | Gender (im) balance in citation practices in cognitive neuroscience | |
| Williamson et al. | The estimation of population microdata by using data from small area statistics and samples of anonymised records | |
| US10747771B2 (en) | Method and apparatus for determining hot event | |
| Snaphaan et al. | Environmental criminology in the big data era | |
| Vaughan et al. | Web search volume as a predictor of academic fame: An exploration of G oogle trends | |
| CN105138577B (en) | Big data based event evolution analysis method | |
| Warren | Reverse migration to Mexico led to US undocumented population decline: 2010 to 2018 | |
| Raffalovich | Detrending time series: A cautionary note | |
| CN109783614B (en) | Differential privacy disclosure detection method and system for to-be-published text of social network | |
| US11640445B2 (en) | Gratitude prediction machine learning models | |
| Ahmad et al. | Using analytic hierarchy process for exploring prioritization of functional strategies in auto parts manufacturing SMEs of Pakistan | |
| Chi et al. | A supernetwork-based online post informative quality evaluation model | |
| US20130262355A1 (en) | Tools and methods for determining semantic relationship indexes | |
| Cernat et al. | Estimating crime in place: Moving beyond residence location | |
| Pabreja et al. | A predictive analytics framework for blood donor classification | |
| Bhargava et al. | An improved lexicon using logistic regression for sentiment analysis | |
| Li et al. | Probabilistic local expert retrieval | |
| CN112801806A (en) | Claims settlement method and system based on knowledge graph | |
| Solymosi | Exploring spatial patterns of guardianship through civic technology platforms | |
| Kovács et al. | Income-related spatial concentration of individual social capital in cities | |
| CN109144999B (en) | Data positioning method, device, storage medium and program product | |
| CN111931098A (en) | Monitoring object determination method and device and electronic equipment | |
| Sharma et al. | Automated system for detecting mental stress of users in social networks using data mining techniques | |
| Putri et al. | Content-based filtering model for recommendation of Indonesian legal article study case of klinik hukumonline | |
| CN112434126B (en) | Information processing method, device, equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201113 |
|
| RJ01 | Rejection of invention patent application after publication |