CN111125561A - Network heat display method and device - Google Patents
Network heat display method and device Download PDFInfo
- Publication number
- CN111125561A CN111125561A CN201911195321.0A CN201911195321A CN111125561A CN 111125561 A CN111125561 A CN 111125561A CN 201911195321 A CN201911195321 A CN 201911195321A CN 111125561 A CN111125561 A CN 111125561A
- Authority
- CN
- China
- Prior art keywords
- corpus
- target data
- target
- type
- network 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9538—Presentation of query results
Abstract
The embodiment of the invention provides a method and a device for displaying network heat, wherein the method for displaying the network heat comprises the following steps: acquiring network information of different types of websites; classifying the network information according to the type of the source website of the network information, and storing each type of network information into different corpora; acquiring the occurrence frequency of the keywords of each piece of target data in each corpus, and calculating the intermediate heat value of each piece of target data in each corpus according to the frequency; calculating a target heat value of each piece of target data according to different preset weights corresponding to each corpus and the intermediate heat value; and sequencing and displaying the target data according to the target heat value. According to the invention, the popularity is calculated through the corpora storing different network information, and different preset weights corresponding to different corpora can reflect the importance degree of the network information in the corpora, so that the finally obtained target popularity value has a higher reference value.
Description
Technical Field
The invention relates to the field of network heat, in particular to a method and a device for displaying network heat.
Background
People aim at the word of heat in the Internet and are endowed with new meanings. Generally, the popularity of a topic refers to its interest in the internet. For a certain industry, a large amount of network information related to the industry can be collected, and then according to the frequency of a certain theme appearing in the network information, the corresponding heat of the theme is obtained, and the heat represents the attention of the theme in the industry to a certain extent. However, in some special industries or scenes, the heat is also required to have a greater reference value. For example, the popularity of stocks in the financial investment industry, requires that the popularity of stocks can be more in line with the opinion of professionals in the industry.
In some current methods for calculating the popularity of stocks, all information related to stocks is usually stored in the same corpus, and the popularity of each stock is determined according to the association relationship between the stocks and the corpora in the corpus.
Because the concerned people of different types of websites are different, the recorded information reflects the stock opinions of different people. If all network information of different types of websites are mixed together, the information related to the stocks is not distinguished, the finally obtained stock heat can only reflect the attention of all people to the stocks, but cannot reflect the opinions of part of important groups, and the reference value is small.
Disclosure of Invention
The embodiment of the invention provides a method and a device for displaying network heat, which aim to solve the problem that in the prior art, the heat does not emphasize aiming at different network information sources in the calculation process, so that the finally obtained heat value has smaller reference significance.
In a first aspect, an embodiment of the present invention provides a method for displaying network heat, where the method includes:
acquiring network information of different types of websites;
classifying the network information according to the type of the source website of the network information, and storing each type of network information into different corpora;
acquiring the occurrence frequency of the keywords of each piece of target data in each corpus, and calculating the intermediate heat value of each piece of target data in each corpus according to the frequency;
calculating a target heat value of each piece of target data according to different preset weights corresponding to each corpus and the intermediate heat value;
and sequencing and displaying the target data according to the target heat value.
Optionally, before obtaining the frequency of the keyword of each piece of target data appearing in each corpus and calculating the intermediate heat value of each piece of target data in each corpus according to the frequency, the method further includes:
and filtering out corpora of the keywords which do not contain the target data in each corpus.
Optionally, the different types of websites include: a first type website containing news information; a second type of web site containing discussion information; at least two types of websites in a third type of website containing announcements or reports and a fourth type of website containing reports;
and the network information from the first type of website is stored in the news corpus, the network information from the second type of website is stored in the discussion corpus, the network information from the third type of website is stored in the announcement corpus, and the network information from the fourth type of website is stored in the research corpus.
Optionally, the preset weight corresponding to the research corpus is greater than the preset weight corresponding to the news corpus; the preset weight corresponding to the news corpus is larger than the weight corresponding to the discussion corpus, and the preset weight corresponding to the discussion corpus is larger than the preset weight corresponding to the announcement corpus.
Optionally, when the different types of websites include at least a first type of website;
after the sorting and presenting the target data by the target heat value, the method further comprises:
determining target corpora respectively associated with the target data in the news corpus according to the keywords of the target data;
obtaining a news emotion quantization value of the target corpus according to a pre-trained machine learning algorithm model;
determining the emotion type of the target corpus according to the news emotion quantization value and a preset emotion threshold range, wherein the emotion type comprises: good, empty and neutral;
after receiving a first input of a user, displaying a target corpus corresponding to the target data indicated by the first input and a corresponding emotion type.
Optionally, when the different types of websites include at least a third type of website;
after the sorting and presenting the target data by the target heat value, the method further comprises:
according to keywords of the target data, financial reports respectively associated with the target data in the bulletin corpus are determined;
according to a pre-trained machine learning algorithm model, carrying out reliability analysis on the financial report to obtain a quality score;
after receiving a second input of the user, displaying a financial report corresponding to the target data indicated by the second input and a corresponding quality score.
Optionally, the sorting and displaying the target data according to the target heat value includes:
sequencing the target data according to the sequence of the target heat values from large to small;
and displaying the sorted target data.
In a second aspect, an embodiment of the present invention further provides a device for displaying network heat, where the device includes:
the acquisition module is used for acquiring network information of different types of websites;
the classification module is used for classifying the network information according to the type of the source website of the network information and storing each type of network information into different corpora;
the intermediate heat module is used for acquiring the frequency of the keywords of each piece of target data in each corpus and calculating the intermediate heat value of each stock and/or theme in each corpus according to the frequency;
the target heat value module is used for calculating a target heat value of each piece of target data according to different preset weights corresponding to each corpus and the intermediate heat value;
and the sequencing display module is used for sequencing and displaying the target data according to the target heat value.
Optionally, the apparatus further comprises:
and the filtering module is used for filtering the corpus which does not contain the keywords of the stocks and/or the subjects in each corpus.
Optionally, the different types of websites include: a first type website containing news information; a second type of web site containing discussion information; at least two types of websites in a third type of website containing announcements or reports and a fourth type of website containing reports;
and the network information from the first type of website is stored in the news corpus, the network information from the second type of website is stored in the discussion corpus, the network information from the third type of website is stored in the announcement corpus, and the network information from the fourth type of website is stored in the research corpus.
Optionally, the preset weight corresponding to the research corpus is greater than the preset weight corresponding to the news corpus; the preset weight corresponding to the news corpus is larger than the weight corresponding to the discussion corpus, and the preset weight corresponding to the discussion corpus is larger than the preset weight corresponding to the announcement corpus.
Optionally, when the different types of websites include at least a first type of website; the device further comprises:
the first screening module is used for determining target corpora respectively associated with each piece of target data in the news corpus according to keywords of the target data;
the first calculation module is used for obtaining a news emotion quantization value of the target corpus according to a pre-trained machine learning algorithm model;
and the type module is used for determining the emotion type of the target corpus according to the news emotion quantization value and a preset emotion threshold range, wherein the emotion type comprises: good, empty and neutral;
and the emotion display module is used for displaying the target linguistic data corresponding to the target data indicated by the first input and the corresponding emotion type after receiving the first input of the user.
Optionally, when the different types of websites include at least a third type of website; the device further comprises:
the second screening module is used for determining financial reports which are respectively associated with the target data in the announcement corpus according to keywords of the target data;
the second calculation module is used for carrying out reliability analysis on the financial report according to a machine learning algorithm model trained in advance to obtain a quality score;
and the financial report display module is used for displaying the financial report corresponding to the target data and the corresponding quality score indicated by the second input after receiving the second input of the user.
Optionally, the sorting display module includes:
the sorting unit is used for sorting the target data according to the sequence of the target heat values from large to small;
and the display unit is used for displaying the sorted target data.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor, when executing the computer program, implements the method for showing network heat as described above.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when being executed by a processor, the computer program is implemented in the method for showing network heat as described above.
In the embodiment of the invention, network information of different types of websites is obtained firstly; and classifying the acquired network information according to the type of the source website and storing the network information into different corpora, so that all the network information is not mixed into one. And then calculating to obtain a target heat value according to different preset weights corresponding to each corpus and the heat value of each target data in each corpus. And finally, sequencing and displaying the target data according to the target heat value. The importance degree of the network information in different corpora is reflected through different preset weights corresponding to different corpora, so that the target heat value of the finally displayed target data has a higher reference value.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
Fig. 1 is a flowchart of a method for displaying network heat according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating stocks according to a descending order of target popularity value according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating topics in descending order of target heat value according to an embodiment of the present invention;
FIG. 4 is a flow chart of the news emotional analysis step provided by the embodiment of the invention;
FIG. 5 is a schematic diagram of a news emotional display provided by an embodiment of the invention;
FIG. 6 is a flowchart of the financial report analysis steps provided by an embodiment of the present invention;
FIG. 7 is a schematic illustration of a financial report quality display provided by an embodiment of the present invention;
FIG. 8 is a flow chart of a centralized display according to an embodiment of the present invention;
FIG. 9 is a schematic illustration of a related discussion provided in connection with an embodiment of the present invention;
FIG. 10 is a schematic illustration of a related newspaper provided by an embodiment of the present invention;
FIG. 11 is a diagram illustrating details regarding a research corpus according to an embodiment of the present invention;
fig. 12 is a schematic diagram illustrating details about a news corpus according to an embodiment of the present invention;
FIG. 13 is a schematic diagram illustrating details regarding a discussion corpus according to an embodiment of the present invention;
fig. 14 is a schematic diagram illustrating details regarding an announcement corpus according to an embodiment of the present invention;
FIG. 15 is a block diagram of a device for showing network heat according to an embodiment of the present invention;
fig. 16 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
In various embodiments of the present invention, it should be understood that the sequence numbers of the following processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a method for displaying network heat, where the method includes:
It should be noted that the web addresses of a plurality of web sites may be determined in advance according to the needs, and the plurality of web sites relate to a plurality of types. Preferably, the different types of websites include: a first type website containing news information; a second type of web site containing discussion information; at least two types of websites from the third type of websites containing announcements or reports and the fourth type of websites containing reports. The first type website can be a financial news website, the second type website can be a website such as a post bar or a forum, and the third type website can be a website containing announcements or reports issued by various companies, such as a huge tide information network; a fourth type of web site may be a web site that has a large number of reports collected. When the network information is obtained, the network information can be crawled on a website through a web crawler technology.
And 102, classifying the network information according to the type of the source website of the network information, and storing each type of network information into different corpora.
It should be noted that the source websites can be classified according to the types of the source websites, and then the network information obtained according to each type of website is stored in different corpora. That is, all the network information obtained from the type a websites is stored in the type a corpus, all the network information obtained from the type B websites is stored in the type B corpus, and so on. Therefore, the number of corpora is the same as the number of types of source websites, that is, if network information is obtained from 4 types of websites, 4 corpora are generated, and each corpus stores network information on one type of website. Preferably, the network information from the first type of website is stored in a news corpus, the network information from the second type of website is stored in a discussion corpus, the network information from the third type of website is stored in an announcement corpus, and the network information from the fourth type of website is stored in a research corpus. The preset weight corresponding to the research corpus is larger than the preset weight corresponding to the news corpus; the preset weight corresponding to the news corpus is larger than the weight corresponding to the discussion corpus, and the preset weight corresponding to the discussion corpus is larger than the preset weight corresponding to the announcement corpus.
It should be noted that the target data may be stocks and/or topics. Taking target data as an example of stocks, a plurality of stocks can be stored in advance, then the frequency of occurrence of keywords of each stock in each corpus is counted, and the intermediate heat value of each stock in each corpus is calculated according to the frequency. Wherein the keyword of the stock may be the stock name. It is necessary to ensure that the intermediate heat value corresponding to the stock with high frequency is greater than the intermediate heat value corresponding to the stock with low frequency. When the target data is the subject, the calculation process of the intermediate heat value is similar to that of the stock, and is not repeated herein.
And 104, calculating to obtain a target heat value of each piece of target data according to different preset weights and intermediate heat values corresponding to each corpus.
It should be noted that, taking the target data as a stock as an example, when calculating the target heat value of a stock, the target heat value of the stock is equal to the sum of a plurality of products obtained by multiplying the intermediate heat value in each corpus by respective preset weights. For example, there are 4 corpora, the intermediate heat values of the stock in the 4 corpora are a, b, c, d, respectively, and the preset weights corresponding to the four corpora are A, B, C, D, respectively; the target heat value of the stock is a × a + B × B + C × C + D × D.
And 105, sequencing and displaying the target data according to the target heat value.
It should be noted that the target data may be sorted in order of the target heat value from large to small or from small to large.
In order to avoid interference of a large amount of irrelevant data, on the basis of the above embodiments of the present invention, in an embodiment of the present invention, before obtaining a frequency of occurrence of a keyword of each piece of target data in each corpus and calculating an intermediate heat value of each piece of target data in each corpus according to the frequency, the method further includes:
and filtering out corpora of the keywords which do not contain the target data in each corpus.
It should be noted that, when the target data is stocks, corpora not containing keywords of any stock in each corpus may be filtered out. When the target data is a topic, corpora which do not contain keywords of any topic in each corpus can be filtered out. When the target data contains stocks and topics, the corpus of each corpus, which contains neither the keywords of any stock nor the keywords of any topic, is filtered out.
In order to recommend the target data with high popularity to the user, on the basis of the above embodiments of the present invention, in the embodiments of the present invention, the sorting and displaying the target data according to the target popularity value includes:
sequencing the target data according to the sequence of the target heat values from large to small;
and displaying the sorted target data.
It should be noted that the number of the target data is plural, and when displaying the plural pieces of target data, all the sorted target data may be displayed, or of course, the target data of which the number is preset before the sorted target data may be displayed. For example, when the target data is stocks and the stocks are displayed, all the stocks are sorted in the order from large to small according to the target heat value, then a plurality of stocks which are sorted in the top are displayed, and of course, related information of the stocks can be displayed together when the stocks are displayed, as shown in fig. 2.
As shown in fig. 3, when the target data is a theme and the theme is displayed, each theme may be displayed in the order of the target heat value from large to small in the same way, and the related information of the theme may also be displayed together during the display.
In the embodiment of the invention, network information of different types of websites is obtained firstly; and classifying the acquired network information according to the type of the source website and storing the network information into different corpora, so that all the network information is not mixed into one. And then calculating to obtain a target heat value according to different preset weights corresponding to each corpus and the heat value of each target data in each corpus. And finally, sequencing and displaying the target data according to the target heat value. The importance degree of the network information in different corpora is reflected through different preset weights corresponding to different corpora, so that the target heat value of the finally displayed target data has a higher reference value.
As shown in fig. 4, in order to determine news opinions, on the basis of the above embodiments of the present invention, in the embodiment of the present invention, when the different types of websites include at least a first type of website; after the target data is sorted by the target heat value and displayed, the method further comprises:
It should be noted that if the news emotion quantization value of the corpus is greater than the maximum value of the preset emotion threshold range, the emotion type of the corpus is good; if the news emotion quantitative value of the corpus is smaller than the minimum value of the preset emotion threshold range, the emotion type of the corpus is a profit; and if the news emotion quantitative value of the corpus is within the preset emotion threshold value range, the emotion type of the corpus is neutral.
The machine learning algorithm model can be trained through a plurality of training samples, and the trained machine learning algorithm model is obtained. After a corpus related to profit is trained by the machine learning algorithm model, a news emotion quantitative value can be obtained, and the news emotion quantitative value is larger than the maximum value of a preset emotion threshold range. After a corpus related to the loss is subjected to a trained machine learning algorithm model, a news emotion quantization value can be obtained, and the news emotion quantization value is smaller than the minimum value of a preset emotion threshold range. After a corpus which is irrelevant to profit and loss is trained by the machine learning algorithm model, a news emotion quantitative value can be obtained and is within a preset emotion threshold value range.
The first input may be a keyword in the target data input by the user; of course, the method can also be used for clicking any piece of target data when the stock is displayed. As shown in fig. 5, when the target data is stock, a news emotional display diagram of stock a shows the corpus related to stock a and the emotional type of the corpus.
As shown in fig. 6, in order to obtain reliable financial information, on the basis of the foregoing embodiments of the present invention, in an embodiment of the present invention, when the different types of websites include at least a third type of website, after the target data is sorted by the target heat value and displayed, the method further includes:
601, determining financial reports respectively associated with the entry label data in the bulletin corpus according to keywords of the target data;
It should be noted that the advertisement corpus includes a large number of advertisements and reports, and different contents are involved in the advertisements and reports. In order to screen out the financial reports, a trained first machine learning algorithm model is used. After the financial reports are obtained, the quality score of each financial report is obtained by using a trained second machine learning algorithm model, and the financial report with the higher quality score has higher credibility.
The second input may be a keyword in the target data input by the user; of course, the method can also be used for clicking any piece of target data when the stock is displayed. As shown in fig. 7, when the target data is stocks, the financial report quality of stock a is shown schematically, and the financial report quality score of stock a are shown.
Fig. 8 is a schematic diagram of another embodiment of the present invention, which includes:
and (4) collecting the corpora, and grabbing a large amount of corpora in websites such as financial media, forums, posts and the like by using a web crawler.
Classifying and sorting, namely classifying the captured corpora according to four types of news, discussions, announcements and reports, and storing the classified corpora into different corpora respectively; and meanwhile, the corpora irrelevant to the stocks/topics are removed.
And (3) calculating the popularity and recommending the popularity, respectively counting the frequency of the related keywords of each stock/theme in each corpus to obtain the popularity value of each stock/theme in each corpus, and then weighting and calculating the comprehensive popularity value of each stock/theme according to the preset weight corresponding to each corpus.
And sequencing all stocks/topics according to the magnitude of the comprehensive heat value and the rising speed, and respectively obtaining 10 topics with the highest comprehensive heat value, 10 topics with the highest comprehensive heat value and 10 stocks with the highest comprehensive heat value for recommendation.
And (3) news emotion analysis, wherein emotion analysis is performed on the corpora in the corpus storing the news, preferably, a pre-trained machine learning algorithm model can be used for determining emotion quantification values of each corpus, and then each corpus is determined to be free, good or neutral according to a preset threshold range.
And (4) financial report screening and quality analysis of the financial reports, wherein the language material in the corpus storing the bulletins is screened by utilizing a pre-trained machine learning algorithm model to find out the financial reports in the corpus. And then, performing quality analysis on the financial reports by using another machine learning algorithm module which is trained in advance, calculating the reliability of each financial report, and obtaining a quality score, wherein the higher the quality score is, the higher the reliability is.
And (4) centralized display, namely, centralized display of the stocks/topics to be recommended, and centralized display of the contents of the hot data, the related news and news emotions, the related discussions, the related bulletins, the quality scores of the financial reports, the related research reports and the like of each stock/topic after integration.
The related data may be searched for and then presented according to the search terms. For example, after a search is performed on a stock, a related discussion, related news, related bulletins, and related discussion of a stock may be presented. Fig. 9 is a schematic diagram showing a related discussion of stock a. Fig. 10 is a schematic diagram showing a related newspaper of stock a.
Of course, the details of a certain stock in a separate corpus can be shown, see fig. 11, which is the related information of the a stock, the popularity data of the a stock in the research corpus, and the trend data of the research popularity and the stock price over time. Referring to fig. 12, it is the related information of the a stock, the popularity data of the a stock in the news corpus, and the trend data of news popularity and stock price over time. Referring to fig. 13, the related information of the a stock, the heat data of the a stock in the discussion corpus, and the trend data of the discussion heat and stock price over time. Referring to fig. 14, it is the related information of the a stock, the popularity data of the a stock in the announcement corpus, and the trend data of the announcement popularity and the stock price over time.
The method for calculating the keyword popularity provided by the embodiment of the present invention is described above, and a computing apparatus for the keyword popularity provided by the embodiment of the present invention is described below with reference to the accompanying drawings.
Referring to fig. 15, an embodiment of the present invention further provides a device for displaying network heat, where the device includes:
an obtaining module 151, configured to obtain network information of different types of websites;
the classification module 152 is configured to classify the network information according to a type of a source website of the network information, and store each type of network information into different corpora;
the intermediate heat module 153 is configured to obtain the frequency of the keyword of each piece of target data appearing in each corpus, and calculate an intermediate heat value of each stock and/or topic in each corpus according to the frequency;
a target heat value module 154, configured to calculate a target heat value of each piece of target data according to different preset weights and intermediate heat values corresponding to each corpus;
and the sequencing display module 155 is used for sequencing and displaying the target data according to the target heat value.
Optionally, the apparatus further comprises:
and the filtering module is used for filtering the corpus which does not contain the keywords of the stocks and/or the subjects in each corpus.
Optionally, the different types of websites include: a first type website containing news information; a second type of web site containing discussion information; at least two types of websites in a third type of website containing announcements or reports and a fourth type of website containing reports;
and the network information from the first type of website is stored in the news corpus, the network information from the second type of website is stored in the discussion corpus, the network information from the third type of website is stored in the announcement corpus, and the network information from the fourth type of website is stored in the research corpus.
Optionally, the preset weight corresponding to the research corpus is greater than the preset weight corresponding to the news corpus; the preset weight corresponding to the news corpus is larger than the weight corresponding to the discussion corpus, and the preset weight corresponding to the discussion corpus is larger than the preset weight corresponding to the announcement corpus.
Optionally, when the different types of websites include at least a first type of website; the device still includes:
the first screening module is used for determining target corpora respectively associated with the entry label data in the news corpus according to keywords of the target data;
the first calculation module is used for obtaining a news emotion quantization value of the target corpus according to a pre-trained machine learning algorithm model;
and the type module is used for determining the emotion type of the target corpus according to the news emotion quantization value and the preset emotion threshold range, wherein the emotion type comprises: good, empty and neutral;
and the emotion display module is used for displaying the target linguistic data corresponding to the target data indicated by the first input and the corresponding emotion type after receiving the first input of the user.
Optionally, when the different types of websites include at least a third type of website; the device still includes:
the second screening module is used for determining financial reports respectively associated with the entry label data in the bulletin corpus according to keywords of the target data;
the second calculation module is used for carrying out reliability analysis on the financial report according to a machine learning algorithm model trained in advance to obtain a quality score;
and the financial report display module is used for displaying the financial report corresponding to the target data indicated by the second input and the corresponding quality score after receiving the second input of the user.
Optionally, the sorting display module includes:
the sorting unit is used for sorting the target data according to the sequence of the target heat values from large to small;
and the display unit is used for displaying the sorted target data.
In the embodiment of the invention, network information of different types of websites is obtained firstly; and classifying the acquired network information according to the type of the source website and storing the network information into different corpora, so that all the network information is not mixed into one. And then calculating to obtain a target heat value according to different preset weights corresponding to each corpus and the heat value of each target data in each corpus. And finally, sequencing and displaying the target data according to the target heat value. The importance degree of the network information in different corpora is reflected through different preset weights corresponding to different corpora, so that the target heat value of the finally displayed target data has a higher reference value.
On the other hand, the embodiment of the present invention further provides an electronic device, which includes a memory, a processor, a bus, and a computer program that is stored in the memory and can be executed on the processor, and when the processor executes the program, the method for showing the network heat is implemented.
For example, fig. 16 shows a schematic physical structure diagram of an electronic device.
As shown in fig. 16, the electronic device may include: a processor (processor)1610, a communication Interface (Communications Interface)1620, a memory (memory)1630 and a communication bus 1640, wherein the processor 1610, the communication Interface 1620 and the memory 1630 communicate with each other via the communication bus 1640. Processor 1610 may call logic instructions in memory 1630 to perform the following method:
acquiring network information of different types of websites;
classifying the network information according to the type of the source website of the network information, and storing each type of network information into different corpora;
acquiring the occurrence frequency of the keywords of each piece of target data in each corpus, and calculating the intermediate heat value of each piece of target data in each corpus according to the frequency;
calculating a target heat value of each target data according to different preset weights and intermediate heat values corresponding to each corpus;
and sequencing and displaying the target data according to the target heat value.
In addition, the logic instructions in the memory 1630 may be implemented in software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes 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 invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to, when executed by a processor, perform the method for showing network heat provided in the foregoing embodiments, for example, including:
acquiring network information of different types of websites;
classifying the network information according to the type of the source website of the network information, and storing each type of network information into different corpora;
acquiring the occurrence frequency of the keywords of each piece of target data in each corpus, and calculating the intermediate heat value of each piece of target data in each corpus according to the frequency;
calculating a target heat value of each target data according to different preset weights and intermediate heat values corresponding to each corpus;
and sequencing and displaying the target data according to the target heat value.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for showing network heat is characterized by comprising the following steps:
acquiring network information of different types of websites;
classifying the network information according to the type of the source website of the network information, and storing each type of network information into different corpora;
acquiring the occurrence frequency of the keywords of each piece of target data in each corpus, and calculating the intermediate heat value of each piece of target data in each corpus according to the frequency;
calculating a target heat value of each piece of target data according to different preset weights corresponding to each corpus and the intermediate heat value;
and sequencing and displaying the target data according to the target heat value.
2. The method according to claim 1, wherein before obtaining the frequency of occurrence of the keyword of each piece of target data in each corpus and calculating the intermediate heat value of each piece of target data in each corpus according to the frequency, the method further comprises:
and filtering out corpora of the keywords which do not contain the target data in each corpus.
3. The method of claim 1, wherein the different types of websites comprise: a first type website containing news information; a second type of web site containing discussion information; at least two types of websites in a third type of website containing announcements or reports and a fourth type of website containing reports;
and the network information from the first type of website is stored in the news corpus, the network information from the second type of website is stored in the discussion corpus, the network information from the third type of website is stored in the announcement corpus, and the network information from the fourth type of website is stored in the research corpus.
4. The method of claim 3, wherein the preset weight corresponding to the research corpus is greater than the preset weight corresponding to the news corpus; the preset weight corresponding to the news corpus is larger than the weight corresponding to the discussion corpus, and the preset weight corresponding to the discussion corpus is larger than the preset weight corresponding to the announcement corpus.
5. The method of claim 3, wherein when the different types of websites include at least a first type of website;
after the sorting and presenting the target data by the target heat value, the method further comprises:
determining target corpora respectively associated with the target data in the news corpus according to the keywords of the target data;
obtaining a news emotion quantization value of the target corpus according to a pre-trained machine learning algorithm model;
determining the emotion type of the target corpus according to the news emotion quantization value and a preset emotion threshold range, wherein the emotion type comprises: good, empty and neutral;
after receiving a first input of a user, displaying a target corpus corresponding to the target data indicated by the first input and a corresponding emotion type.
6. The method of claim 3, wherein when the different types of websites include at least a third type of website;
after the sorting and presenting the target data by the target heat value, the method further comprises:
according to keywords of the target data, financial reports respectively associated with the target data in the bulletin corpus are determined;
according to a pre-trained machine learning algorithm model, carrying out reliability analysis on the financial report to obtain a quality score;
after receiving a second input of the user, displaying a financial report corresponding to the target data indicated by the second input and a corresponding quality score.
7. The method of claim 1, wherein the sorting and presenting the target data by the target heat value comprises:
sequencing the target data according to the sequence of the target heat values from large to small;
and displaying the sorted target data.
8. A device for showing network heat, the device comprising:
the acquisition module is used for acquiring network information of different types of websites;
the classification module is used for classifying the network information according to the type of the source website of the network information and storing each type of network information into different corpora;
the intermediate heat module is used for acquiring the frequency of the keywords of each piece of target data in each corpus and calculating the intermediate heat value of each stock and/or theme in each corpus according to the frequency;
the target heat value module is used for calculating a target heat value of each piece of target data according to different preset weights corresponding to each corpus and the intermediate heat value;
and the sequencing display module is used for sequencing and displaying the target data according to the target heat value.
9. An electronic device comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the method for demonstrating network heat according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the method for showing network heat according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911195321.0A CN111125561A (en) | 2019-11-28 | 2019-11-28 | Network heat display method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911195321.0A CN111125561A (en) | 2019-11-28 | 2019-11-28 | Network heat display method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111125561A true CN111125561A (en) | 2020-05-08 |
Family
ID=70497019
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911195321.0A Pending CN111125561A (en) | 2019-11-28 | 2019-11-28 | Network heat display method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111125561A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111966733A (en) * | 2020-08-18 | 2020-11-20 | 中国银行股份有限公司 | Hotspot knowledge generation method and device |
| CN112738227A (en) * | 2020-12-28 | 2021-04-30 | 广州金融科技股份有限公司 | Information heat evaluation method, computer equipment and storage medium |
| CN113921082A (en) * | 2021-10-27 | 2022-01-11 | 云舟生物科技（广州）有限公司 | Gene search weight adjustment method, computer storage medium, and electronic device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104077377A (en) * | 2014-06-25 | 2014-10-01 | 红麦聚信(北京)软件技术有限公司 | Method and device for finding network public opinion hotspots based on network article attributes |
| CN105243087A (en) * | 2015-09-09 | 2016-01-13 | 浙江网新恒天软件有限公司 | IT (Information Technology) information aggregation reading personalized recommendation method |
| CN105528465A (en) * | 2016-02-03 | 2016-04-27 | 天弘基金管理有限公司 | Credit status assessment method and device |
| KR20170037709A (en) * | 2015-09-25 | 2017-04-05 | 충북대학교 산학협력단 | Method and System for determination of social network hot topic in consideration of users influence and time |
| CN107463686A (en) * | 2017-08-10 | 2017-12-12 | 深圳市腾讯计算机系统有限公司 | A kind of method and device of calculating network public sentiment temperature |
| CN107656958A (en) * | 2017-06-09 | 2018-02-02 | 平安科技（深圳）有限公司 | A kind of classifying method and server of multi-data source data |
| CN107862603A (en) * | 2017-11-27 | 2018-03-30 | 北京艾信运通技术有限公司 | A kind of financial statement credibility evaluation method and device |
| CN109189934A (en) * | 2018-11-13 | 2019-01-11 | 平安科技（深圳）有限公司 | Public sentiment recommended method, device, computer equipment and storage medium |
| CN109960791A (en) * | 2017-12-25 | 2019-07-02 | 上海智臻智能网络科技股份有限公司 | Judge the method and storage medium, terminal of text emotion |
-
2019
- 2019-11-28 CN CN201911195321.0A patent/CN111125561A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104077377A (en) * | 2014-06-25 | 2014-10-01 | 红麦聚信(北京)软件技术有限公司 | Method and device for finding network public opinion hotspots based on network article attributes |
| CN105243087A (en) * | 2015-09-09 | 2016-01-13 | 浙江网新恒天软件有限公司 | IT (Information Technology) information aggregation reading personalized recommendation method |
| KR20170037709A (en) * | 2015-09-25 | 2017-04-05 | 충북대학교 산학협력단 | Method and System for determination of social network hot topic in consideration of users influence and time |
| CN105528465A (en) * | 2016-02-03 | 2016-04-27 | 天弘基金管理有限公司 | Credit status assessment method and device |
| CN107656958A (en) * | 2017-06-09 | 2018-02-02 | 平安科技（深圳）有限公司 | A kind of classifying method and server of multi-data source data |
| CN107463686A (en) * | 2017-08-10 | 2017-12-12 | 深圳市腾讯计算机系统有限公司 | A kind of method and device of calculating network public sentiment temperature |
| CN107862603A (en) * | 2017-11-27 | 2018-03-30 | 北京艾信运通技术有限公司 | A kind of financial statement credibility evaluation method and device |
| CN109960791A (en) * | 2017-12-25 | 2019-07-02 | 上海智臻智能网络科技股份有限公司 | Judge the method and storage medium, terminal of text emotion |
| CN109189934A (en) * | 2018-11-13 | 2019-01-11 | 平安科技（深圳）有限公司 | Public sentiment recommended method, device, computer equipment and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111966733A (en) * | 2020-08-18 | 2020-11-20 | 中国银行股份有限公司 | Hotspot knowledge generation method and device |
| CN112738227A (en) * | 2020-12-28 | 2021-04-30 | 广州金融科技股份有限公司 | Information heat evaluation method, computer equipment and storage medium |
| CN113921082A (en) * | 2021-10-27 | 2022-01-11 | 云舟生物科技（广州）有限公司 | Gene search weight adjustment method, computer storage medium, and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10748164B2 (en) | Analyzing sentiment in product reviews | |
| CN109325165B (en) | Network public opinion analysis method, device and storage medium | |
| CN103744981B (en) | System for automatic classification analysis for website based on website content | |
| CN107391493B (en) | Public opinion information extraction method and device, terminal equipment and storage medium | |
| US11709875B2 (en) | Prioritizing survey text responses | |
| CN110633373A (en) | Automobile public opinion analysis method based on knowledge graph and deep learning | |
| CN111125561A (en) | Network heat display method and device | |
| CN109993448A (en) | A kind of appraisal procedure and system of enterprise network public sentiment potential risk | |
| CN110490683B (en) | Offline collaborative multi-model hybrid recommendation method and system | |
| CN113495959B (en) | Financial public opinion identification method and system based on text data | |
| Kiran et al. | User specific product recommendation and rating system by performing sentiment analysis on product reviews | |
| CN105677902A (en) | Resume display method | |
| CN113901308A (en) | Knowledge graph-based enterprise recommendation method and recommendation device and electronic equipment | |
| CN110825974B (en) | Recommendation system content ordering method and device | |
| CN112862567A (en) | Exhibit recommendation method and system for online exhibition | |
| Hasanati et al. | Implementation of support vector machine with lexicon based for sentimenT ANALYSIS ON TWITter | |
| CN103294741A (en) | Similar document retrieval auxiliary device and similar document retrieval auxiliary method | |
| CN111062449A (en) | Prediction model training method, interestingness prediction device and storage medium | |
| CN113065975B (en) | Method, system and terminal for calculating focusing degree and evolution relation of network public sentiment topics | |
| CN111353803B (en) | Advertiser classification method and device and computing equipment | |
| CN114155057A (en) | Commodity recommendation system for electronic commerce platform | |
| CN112417858A (en) | Entity weight scoring method, system, electronic equipment and storage medium | |
| CN114153939A (en) | Text recognition method and device | |
| Irawaty et al. | Development of Youtube Sentiment Analysis Application using K-Nearest Neighbors (Nokia Case Study) | |
| CN110929123A (en) | E-commerce product competition analysis method and system |
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 |