CN111027310A - Text influence evaluation method, device, equipment and readable medium - Google Patents
Text influence evaluation method, device, equipment and readable medium Download PDFInfo
- Publication number
- CN111027310A CN111027310A CN201911066611.5A CN201911066611A CN111027310A CN 111027310 A CN111027310 A CN 111027310A CN 201911066611 A CN201911066611 A CN 201911066611A CN 111027310 A CN111027310 A CN 111027310A
- Authority
- CN
- China
- Prior art keywords
- text
- information
- target
- score
- determining
- 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
Abstract
The embodiment of the invention discloses a method, a device, equipment and a medium for evaluating text influence, wherein the method comprises the following steps: acquiring evaluation data of a text to be evaluated under a preset evaluation index, wherein the evaluation index comprises at least one of an information source index, an information entropy index and/or a timeliness index; respectively determining sub-influence scores corresponding to the text to be evaluated under the evaluation index according to the evaluation data, wherein the sub-influence scores comprise at least one of information source scores, information entropy scores and/or aging scores; and determining the target influence score of the text to be evaluated according to the sub-influence scores. The method improves the accuracy of text influence assessment in public opinion analysis.
Description
Technical Field
The invention relates to the technical field of computer processing, in particular to a method, a device, equipment and a readable medium for determining text influence.
Background
With the development and wide application of internet technology, how to quickly extract key information concerned by a user from massive information of the internet determines the utilization efficiency of the internet information.
On one hand, information of each dimension with wider and more comprehensive text needs to be mined; on the other hand, the amount of data is large and cluttered, making it difficult to quickly obtain critical information.
Particularly, when a hot event occurs, the public sentiment information generated on the internet is exploded, and users such as the related interest parties of the event need to spend a lot of time to screen the key information in the public sentiment event of interest. Therefore, the influence of various texts reflecting public sentiment needs to be analyzed, and the key information with large influence is preferentially pushed to the user, so that the cost for obtaining the key information is saved for the user, and the decision efficiency is improved.
However, most of the current public opinion text influence calculation is performed based on the content contained in the text, and the influence of the text is rarely evaluated by using other relevant attributes of the text, such as release time, release source and the like, so that a certain deviation exists in the evaluation result of the text influence, and the accuracy and efficiency of obtaining target information by a user are reduced.
Disclosure of Invention
In view of the above, it is necessary to provide a method, an apparatus, a computer device and a readable medium for evaluating influence of a text in view of the above problems.
A method for evaluating influence of a text, the method comprising:
acquiring evaluation data of a text to be evaluated under a preset evaluation index, wherein the evaluation index comprises at least one of an information source index, an information entropy index and/or a timeliness index;
respectively determining sub-influence scores corresponding to the text to be evaluated under the evaluation index according to the evaluation data, wherein the sub-influence scores comprise at least one of information source scores, information entropy scores and/or aging scores;
and determining the target influence score of the text to be evaluated according to the sub-influence scores.
The evaluation data comprises information source parameter data of the text to be evaluated;
determining the information source score of the text to be evaluated according to the evaluation data, wherein the step comprises the following steps of:
determining at least two information source parameter information in the publishing website information, the originating website information and/or the author information of the text to be evaluated according to the information source parameter data;
determining a sub-information source score corresponding to each information source parameter information;
and determining the information source score of the text to be evaluated according to the sub information source score.
The determining of the sub-source score corresponding to each source parameter information includes:
respectively determining a target ranking list score, a target forwarding transshipment score and a target expert score corresponding to each information source parameter information as information source influence related scores;
and determining the sub-information source score corresponding to each information source parameter information according to the information source influence related score.
Determining a sub-information source score corresponding to each information source parameter information according to the information source influence related score, wherein the determining comprises the following steps:
respectively obtaining the score of each information source parameter information on at least one ranking list as a sub-ranking list score corresponding to each information source parameter information;
and determining a target ranking list score corresponding to each information source parameter information according to the sub-ranking list scores.
The determining the target ranking list score, the target forwarding transshipment score and the target expert score corresponding to each information source parameter information respectively as information source influence related scores comprises the following steps:
determining a corresponding target event according to the text to be evaluated;
acquiring the occurrence time of the target event, and determining a target evaluation time interval according to the occurrence time;
respectively acquiring forwarding and transshipping data of each information source parameter information in the target evaluation time interval, wherein the forwarding and transshipping data comprises the total text release number and the text forwarded and transshipping number corresponding to the information source parameter information;
and determining a target forwarding transshipment score corresponding to each information source parameter information according to the forwarding transshipment data.
After determining the corresponding target event according to the text to be evaluated, the method further comprises the following steps:
acquiring the release time of the text to be evaluated, and determining the time interval between the release time and the occurrence time of a target event as target aging information;
and determining the aging score of the text to be evaluated according to the target aging information.
The determining sub-influence scores corresponding to the text to be evaluated under the evaluation index according to the evaluation data further includes:
determining a corresponding target field according to the text to be evaluated;
determining at least one target keyword of the target field;
determining the number of the target keywords contained in the text to be evaluated and the occurrence frequency of at least one contained target keyword;
and determining the information entropy score of the text to be evaluated according to the number of the target keywords and the corresponding occurrence times.
An apparatus for evaluating influence of a text, the apparatus comprising:
an acquisition unit: the method comprises the steps of obtaining evaluation data of a text to be evaluated under a preset evaluation index, wherein the evaluation index comprises at least one of an information source index, an information entropy index and/or a timeliness index;
a first determination unit: the evaluation data are used for respectively determining sub-influence scores corresponding to the text to be evaluated under the evaluation index according to the evaluation data, wherein the sub-influence scores comprise at least one of information source scores, information entropy scores and/or aging scores;
a second determination unit: and the target influence score of the text to be evaluated is determined according to the sub-influence scores.
A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of:
acquiring evaluation data of a text to be evaluated under a preset evaluation index, wherein the evaluation index comprises at least one of an information source index, an information entropy index and/or a timeliness index;
respectively determining sub-influence scores corresponding to the text to be evaluated under the evaluation index according to the evaluation data, wherein the sub-influence scores comprise at least one of information source scores, information entropy scores and/or aging scores;
and determining the target influence score of the text to be evaluated according to the sub-influence scores.
A computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of:
acquiring evaluation data of a text to be evaluated under a preset evaluation index, wherein the evaluation index comprises at least one of an information source index, an information entropy index and/or a timeliness index;
respectively determining sub-influence scores corresponding to the text to be evaluated under the evaluation index according to the evaluation data, wherein the sub-influence scores comprise at least one of information source scores, information entropy scores and/or aging scores;
and determining the target influence score of the text to be evaluated according to the sub-influence scores.
In the embodiment of the invention, firstly, the evaluation data of the text to be evaluated under the preset evaluation index comprising at least one of the information source index, the information entropy index and/or the timeliness index is obtained. And respectively determining at least one of the information source score, the information entropy score and/or the aging score corresponding to the text to be evaluated under each evaluation index as a sub-influence score according to the evaluation data. And finally, determining the target influence score of the text to be evaluated according to the sub-influence scores.
Compared with the prior art that the influence of the semantic information contained in the text is judged only based on the semantic information contained in the text, the text related attribute characteristics such as the author of the text, the time of text release, the authority of the source of the text release and the like are ignored. The attributes play a decisive role in the influence of the text in public opinion analysis, so that the problem of low accuracy of judgment of the influence is caused.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Wherein:
FIG. 1 shows a flow diagram of a method for evaluation of text impact in one embodiment;
FIG. 2 illustrates a flow diagram for determining a source score for a text to be evaluated in one embodiment;
FIG. 3 is a flow diagram that illustrates the determination of sub-source scores for each item of source parametric information, in one embodiment;
FIG. 4 illustrates a flow diagram for determining a target forwarding transshipment score in one embodiment;
FIG. 5 illustrates a flow diagram that determines a target leaderboard score in one embodiment;
FIG. 6 illustrates a flow diagram for determining a target age score in one embodiment;
FIG. 7 illustrates a flow diagram for determining a target information entropy score, in one embodiment;
FIG. 8 is a block diagram showing a configuration of an apparatus for evaluating influence of a text in one embodiment;
FIG. 9 is a diagram illustrating an internal structure of a computer device in one embodiment.
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 only a part of the embodiments of the present invention, and not all of the embodiments. 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.
The invention provides a text influence evaluation method, and in one embodiment, the text influence evaluation method can be realized based on a computer terminal such as a smart phone or a PC terminal.
Referring to fig. 1, an embodiment of the present invention provides a method for evaluating influence of a text.
FIG. 1 shows a flow diagram of a method for evaluation of text impact in one embodiment. The method for evaluating influence of text in the present invention at least includes steps S1022 to S1026 shown in fig. 1, which are described in detail as follows:
in step S1022, evaluation data of the text to be evaluated under a preset evaluation index is obtained, where the evaluation index includes at least one of an information source index, an information entropy index, and/or a timeliness index.
First, the text to be evaluated in the present invention may be a text carrier that includes news reports, self-media articles, postings on social networks, etc. that serve as alternative public opinion (e.g. some hot social events) analysis to disseminate relevant information to the public.
The source refers to a source of text information, such as an author of the text, a mechanism (including an originating mechanism and a reprinting mechanism) for distributing the text, and the like, and correspondingly, the evaluation data may be all text data distributed by a certain news media mechanism (as a source) in the past six months.
In step S1024, sub-influence scores corresponding to the text to be evaluated under the evaluation index are respectively determined according to the evaluation data, where the sub-influence scores include at least one of an information source score, an information entropy score, and/or an aging score.
First, it is easily understood that the source score, the information entropy score and/or the aging score correspond to the source index, the information entropy index and/or the aging index in the foregoing step S1022, respectively.
The determination process of the above sub-influence scores will be described below with respect to the above three indexes.
First, before determining the information source score, information source parameter data of the text to be evaluated needs to be acquired as evaluation data, and a specific process for determining the information source score of the text to be evaluated according to the evaluation data may include steps S1032-S1036 as shown in fig. 2. FIG. 2 illustrates a flow diagram for determining a source score for text to be evaluated in one embodiment.
In step S1032, at least two information source parameter information of the post website information, the originating website information, and/or the author information of the text to be evaluated are determined according to the information source parameter data.
The source parameter values here are publishing source items of the text to be evaluated, such as a publishing website, an originating website, an author, and the like of the text to be evaluated.
In step S1034, a sub-source score corresponding to each piece of source parameter information is determined.
Still further, step S1034 may include steps S1042-S1044 as shown in FIG. 3. FIG. 3 is a flow diagram that illustrates the determination of sub-source scores for each item of source parametric information, in one embodiment.
In step S1042, a target ranking list score, a target forwarding transshipment score, and a target expert score corresponding to each information source parameter information are respectively determined as information source influence related scores.
First, the process of determining the target forwarding reprint score in step S1042 may include steps S1052-S1058 shown in fig. 4. FIG. 4 illustrates a flow diagram for determining a target forwarding transshipment score in one embodiment.
In step S1052, a corresponding target event is determined according to the text to be evaluated.
Specifically, the text to be evaluated may be a news text entitled "company a completes an a + round financing with a value of 6000 ten thousand", and the corresponding target event may be that company a completes the a + round financing. The specific determination process may be that the text to be evaluated is subjected to natural language processing and matched with an event entry in a preset public opinion event database to determine.
In addition, in an alternative embodiment, a certain public opinion event to be analyzed may be determined as a target event (for example, a company issues a new product, a policy in a certain field is released or starts to be implemented, and the like), and then a text related to the target event (for example, news reporting the policy, a self-media article reading the policy) is obtained as the text to be evaluated to evaluate the influence, so that the information with the greatest influence in the public opinion information constituting the target event may be screened out and pushed to the relevant users as key information, and the like.
In step S1054, the occurrence time of the target event is acquired, and a target evaluation time interval is determined according to the occurrence time.
For example, in the embodiment where the target event is that company a completes the a + round of financing, the occurrence time of the event may be beijing time 10/30: 00 in 2019, and the speed and range of information dissemination decreases with the elapse of the occurrence time based on the principle of propaganda, and the primary characteristic of the news report is timeliness, so that the target evaluation time interval may be determined to be within 48 hours after the target event occurs, i.e., the time interval from 10/30: 00 in 2019 to 12/10/30: 00 in 2019.
In step S1056, forwarding and transshipping data of each information source parameter information in the target evaluation time interval is respectively obtained, where the forwarding and transshipping data includes a total number of text releases and a number of text forwarded and transshipped corresponding to the information source parameter information.
First, the reason for determining the influence of the sources based on the amount of text being forwarded and relayed by the sources is that some opinion leaders (i.e., KOL: KeyOpinion Leader) often appear (either spontaneously or due to being closer to the source of information distribution) in the course of information dissemination among a large audience of information (also public opinion participants and manufacturers). Information is typically first processed and distributed via these opinion leaders to a broader audience that is remote from the source of the information.
Therefore, the larger the forwarded amount is in proportion to the amount of all texts issued by the source, that is, the more speaking right and the more focused degree of the source subject in the public opinion composition of the relevant hot events can be considered as an opinion leader in a certain audience range.
In step S1058, a target forwarding transshipment score corresponding to each information source parameter information is determined according to the forwarding transshipment data.
In an optional embodiment, the target forwarding and transshipping score determination may be performed according to a ratio of a total number of texts issued by a certain source in the forwarding and transshipping data to a number of texts to be forwarded and transshipped therein, and further, different weights are assigned to the target evaluation time interval according to a distance from an occurrence time of the target event, that is, a ratio value of a number of texts to be forwarded and transshipped in a time closer to the occurrence time of the target event is larger than a ratio value of a number of texts to be forwarded and transshipped farther from the occurrence time of the target event in a calculation ratio of the target forwarding and transshipping score.
It should be noted that, considering that some hot public sentiment events may have temporal and spatial specificity, such as a major public sentiment event occurring in a small public area with less attention or a remote area, the source of the main stream media with greater attention may not be the first mechanism for monitoring and reporting the public sentiment event, but the main stream media generally has larger text reading flow and huge number of stable audiences, so reporting of the hot sentiment event in the general main stream area is generally most timely, authoritative and influential.
Therefore, in an optional embodiment, in addition to using a preset time length from a certain specific target event occurrence time as a target evaluation interval, the transferred and forwarded conditions of each information source can be obtained at regular intervals, so that the transferred and forwarded scores of each large information source in the daily period without a large hotspot event are monitored.
Second, in another alternative embodiment, the step of determining the target leaderboard score in step S1042 may include steps S1062-S1064 shown in FIG. 5. FIG. 5 illustrates a flow diagram that determines a target leaderboard score in one embodiment.
In step S1062, respectively obtaining a score of each information source parameter information on at least one ranking list as a sub-ranking list score corresponding to each information source parameter information.
The reason for obtaining the score of at least one ranking list is that in practical application, the emphasis points of different ranking lists are different, and if the ranking list is ranked according to the flow number, the searched amount, the reverse link number and the like of the information source, the scoring basis of other ranking lists is indexes such as the mobile client data, the subscription number and whether the information source is original or not. Therefore, it is necessary to combine the consideration indexes of the ranking lists to obtain the scores corresponding to the information sources from multi-aspect comprehensive evaluation.
In S1064, determining a target ranking list score corresponding to each item of information source parameter information according to the sub-ranking list scores.
For example, when determining the ranking list score of the originating website of the text to be evaluated, that is, the source parameter of the B website, the corresponding sub-ranking list score of the B website on each ranking list may be obtained first, and the following scores may be obtained respectively: if the score corresponding to the B website on the flow chart is 57 scores, the score corresponding to the B website on the subscription chart is 70 scores, and the score corresponding to the B website on the content original chart is 80 scores.
Here, since the methods of data statistics and score calculation on the respective leaderboards are different, it is difficult to directly compare and count the scores of the leaderboards because the scores of the leaderboards are different, for example, a certain leaderboard may be fully divided into 10 scores, while another leaderboard may be fully divided into 100 scores.
Therefore, in an optional embodiment, after each sub-leaderboard score is obtained, the sub-leaderboard scores may be converted in a certain proportion, so that all the sub-leaderboard scores may be unified into a preset score interval, and thus calculation operations such as summing up the converted sub-leaderboard scores may be performed directly.
In an optional embodiment, a certain weight coefficient may be further allocated to each ranking board (such as the above-mentioned traffic ranking board, subscription ranking board, and the like), each sub-ranking board score is multiplied by a preset weight corresponding to the sub-ranking board score, and finally, a target ranking board score corresponding to each source parameter (such as an author, an originating website) ranking board index is determined.
Meanwhile, in step S0142, the expert scoring for forming one of the target information source scores may be performed by obtaining a preset information source analyst having abundant actual working experience in a specific field as a scoring expert to score each information source for each information source in the field.
Specifically, the information source analyst may be invited to score each information source in the form of a questionnaire, a scoring range is set in a preset score interval, and target expert scores corresponding to each information source are finally obtained through weighting.
In step S1044, a sub-source score corresponding to each item of source parameter information is determined according to the source influence correlation score.
After the target forwarding and transshipment score, the target ranking list score and the target expert score corresponding to the B website are determined through the foregoing steps, the sub-source score corresponding to the source parameter of the B website can be calculated according to the weighting coefficients corresponding to the influence-related scores of the three sources. And the calculation process of the sub-source scores corresponding to the source parameters such as the author and the forwarding website is similar.
In step S1036, an information source score of the text to be evaluated is determined according to the sub information source scores.
Considering that the sub-source scores of a text to be evaluated on the source parameters may not be consistent, for example, the author of a text may not be a normal traffic or a relatively well-known author, the sub-source score corresponding to the author item may be relatively low, and since the B site where the text is initially published may be relatively authoritative news media, the sub-source score corresponding to the parameter of the original web site may be relatively high.
Therefore, the corresponding information source score can be calculated by integrating the weighting of each information source parameter of the text to be evaluated according to the preset weight.
Continuing back to the description of step S1024, wherein the step of determining the target age score may include steps S1072-S1074 as shown in FIG. 6. FIG. 6 illustrates a flow diagram for determining a target age score in one embodiment.
In step S1072, the release time of the text to be evaluated is obtained, and the time interval between the release time and the occurrence time of the target event is determined as target aging information.
Similar to the process of determining the target event in step S1052, the target event here may be an event that triggers a public opinion information dissemination process, such as C company releasing a new product, D quarter fund rate down-regulation, and the like.
In step S1074, the aging score of the text to be evaluated is determined according to the target aging information.
It is easy to understand that timeliness is a key factor for public opinion hotspot events. The timeliness of information release and acquisition is guaranteed, public sentiment information can be provided for market participants in time, and important basis is provided for operation decision. Therefore, the shorter the interval between the publishing time of the text of a certain source and the occurrence time of the target event is, the higher the corresponding timeliness score is.
Meanwhile, determining the target information entropy scores other than the target source score (refer to fig. 4 and 5) and the target aging score (refer to fig. 6) in step S1024 may include steps S1082 to S1088 as shown in fig. 7. FIG. 7 illustrates a flow diagram for determining a target information entropy score, in one embodiment.
First, briefly explaining the concept of information entropy, based on shannon's information theory, the information entropy in the embodiment of the present invention refers to the size of the information amount contained in the text, and the larger the information entropy is, the more information it contains (reveals), the greater the degree of information uncertainty it reduces.
In step S1082, a corresponding target area is determined according to the text to be evaluated.
The determination of the target area here is similar to the process of determining the target event in step S1052.
In step S1084, at least one target keyword of the target domain is determined.
If the determined target field is the scientific and technical financial field, the corresponding target keyword can be the sixth world internet congress, the 5G mobile phone terminal network access test and the like.
In step S1086, the number of the target keywords included in the text to be evaluated and the occurrence number of at least one included target keyword are determined.
In step S1088, a target information entropy score of the text to be evaluated is determined according to the number of the target keywords and the corresponding occurrence times.
In combination with the above description of the definition of the information entropy, the larger the number of keywords appearing in the text, that is, the larger the information entropy, that is, the higher the score of the content dimension. Therefore, the proportional coefficients of the number of keywords of the target field in the text to be evaluated, the number of keywords of all preset fields contained in the text and the proportional coefficients of the number of times that a specific keyword appears in all the target field keywords contained in the text to be evaluated can be determined, and finally, the corresponding information entropy score is determined according to the two proportional coefficients and a preset calculation formula.
In step S1026, a target influence score of the text to be evaluated is determined according to the sub-influence scores.
Specifically, the target influence value of the text to be evaluated can be calculated in a manner that preset weights corresponding to three sub-influence values, namely the target information source value, the information entropy value and the aging value, are multiplied and then added respectively.
FIG. 8 is a block diagram showing a configuration of an apparatus for evaluating influence of text in one embodiment.
Referring to fig. 8, a text influence evaluation device 1090 according to an embodiment of the present invention includes: an acquisition unit 1092, a second connection unit 1094, a second determination unit 1096.
Wherein, the obtaining unit 1092: the method comprises the steps of obtaining evaluation data of a text to be evaluated under a preset evaluation index, wherein the evaluation index comprises at least one of an information source index, an information entropy index and/or a timeliness index;
the first determination unit 1094: the evaluation data are used for respectively determining sub-influence scores corresponding to the text to be evaluated under the evaluation index according to the evaluation data, wherein the sub-influence scores comprise at least one of information source scores, information entropy scores and/or aging scores;
the second determination unit 1096: and the target influence score of the text to be evaluated is determined according to the sub-influence scores.
FIG. 9 is a diagram illustrating an internal structure of a computer device in one embodiment. The computer device may specifically be a terminal, and may also be a server. As shown in fig. 9, the computer device includes a processor, a memory, and a calculation module, a communication module, which are connected by a system bus. Wherein the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program which, when executed by the processor, causes the processor to implement the method for assessing influence of text. The internal memory may also have a computer program stored therein, which when executed by the processor, causes the processor to perform the method for assessing the influence of the text. Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is proposed, comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of:
acquiring evaluation data of a text to be evaluated under a preset evaluation index, wherein the evaluation index comprises at least one of an information source index, an information entropy index and/or a timeliness index;
respectively determining sub-influence scores corresponding to the text to be evaluated under the evaluation index according to the evaluation data, wherein the sub-influence scores comprise at least one of information source scores, information entropy scores and/or aging scores;
and determining the target influence score of the text to be evaluated according to the sub-influence scores.
In one embodiment, a computer-readable storage medium is proposed, in which a computer program is stored which, when executed by a processor, causes the processor to carry out the steps of:
acquiring evaluation data of a text to be evaluated under a preset evaluation index, wherein the evaluation index comprises at least one of an information source index, an information entropy index and/or a timeliness index;
respectively determining sub-influence scores corresponding to the text to be evaluated under the evaluation index according to the evaluation data, wherein the sub-influence scores comprise at least one of information source scores, information entropy scores and/or aging scores;
and determining the target influence score of the text to be evaluated according to the sub-influence scores.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for evaluating influence of a text, the method comprising:
acquiring evaluation data of a text to be evaluated under a preset evaluation index, wherein the evaluation index comprises at least one of an information source index, an information entropy index and/or a timeliness index;
respectively determining sub-influence scores corresponding to the text to be evaluated under the evaluation index according to the evaluation data, wherein the sub-influence scores comprise at least one of information source scores, information entropy scores and/or aging scores;
and determining the target influence score of the text to be evaluated according to the sub-influence scores.
2. The method of claim 1, wherein the evaluation data comprises source parameter data of the text to be evaluated;
determining the information source score of the text to be evaluated according to the evaluation data, wherein the step comprises the following steps of:
determining at least two information source parameter information in the publishing website information, the originating website information and/or the author information of the text to be evaluated according to the information source parameter data;
determining a sub-information source score corresponding to each information source parameter information;
and determining the information source score of the text to be evaluated according to the sub information source score.
3. The method of claim 2, wherein determining the sub-source score corresponding to each source parameter information comprises:
respectively determining a target ranking list score, a target forwarding transshipment score and a target expert score corresponding to each information source parameter information as information source influence related scores;
and determining the sub-information source score corresponding to each information source parameter information according to the information source influence related score.
4. The method of claim 3, wherein the determining a sub-source score corresponding to each source parameter information according to the source influence correlation score comprises:
respectively obtaining the score of each information source parameter information on at least one ranking list as a sub-ranking list score corresponding to each information source parameter information;
and determining a target ranking list score corresponding to each information source parameter information according to the sub-ranking list scores.
5. The method of claim 3, the determining a target leaderboard score, a target forwarding referral score, a target expert score, respectively, for each source parameter information as source impact-related scores, comprising:
determining a corresponding target event according to the text to be evaluated;
acquiring the occurrence time of the target event, and determining a target evaluation time interval according to the occurrence time;
respectively acquiring forwarding and transshipping data of each information source parameter information in the target evaluation time interval, wherein the forwarding and transshipping data comprises the total text release number and the text forwarded and transshipping number corresponding to the information source parameter information;
and determining a target forwarding transshipment score corresponding to each information source parameter information according to the forwarding transshipment data.
6. The method of claim 5, after determining a corresponding target event from the text to be evaluated, further comprising:
acquiring the release time of the text to be evaluated, and determining the time interval between the release time and the occurrence time of a target event as target aging information;
and determining the aging score of the text to be evaluated according to the target aging information.
7. The method according to claim 1, wherein the determining sub-influence scores of the text to be evaluated under the evaluation index according to the evaluation data further comprises:
determining a corresponding target field according to the text to be evaluated;
determining at least one target keyword of the target field;
determining the number of the target keywords contained in the text to be evaluated and the occurrence frequency of at least one contained target keyword;
and determining the information entropy score of the text to be evaluated according to the number of the target keywords and the corresponding occurrence times.
8. An apparatus for evaluating influence of a text, the apparatus comprising:
an acquisition unit: the method comprises the steps of obtaining evaluation data of a text to be evaluated under a preset evaluation index, wherein the evaluation index comprises at least one of an information source index, an information entropy index and/or a timeliness index;
a first determination unit: the evaluation data are used for respectively determining sub-influence scores corresponding to the text to be evaluated under the evaluation index according to the evaluation data, wherein the sub-influence scores comprise at least one of information source scores, information entropy scores and/or aging scores;
a second determination unit: and the target influence score of the text to be evaluated is determined according to the sub-influence scores.
9. A readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the method according to any one of claims 1 to 7.
10. A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911066611.5A CN111027310A (en) | 2019-11-04 | 2019-11-04 | Text influence evaluation method, device, equipment and readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911066611.5A CN111027310A (en) | 2019-11-04 | 2019-11-04 | Text influence evaluation method, device, equipment and readable medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111027310A true CN111027310A (en) | 2020-04-17 |
Family
ID=70200811
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911066611.5A Pending CN111027310A (en) | 2019-11-04 | 2019-11-04 | Text influence evaluation method, device, equipment and readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111027310A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112000676A (en) * | 2020-07-14 | 2020-11-27 | 微民保险代理有限公司 | Vehicle information updating method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101409634A (en) * | 2007-10-10 | 2009-04-15 | 中国科学院自动化研究所 | Quantitative analysis tools and method for internet news influence based on information retrieval |
| US20160098738A1 (en) * | 2014-10-06 | 2016-04-07 | Chunghwa Telecom Co., Ltd. | Issue-manage-style internet public opinion information evaluation management system and method thereof |
| CN106484733A (en) * | 2015-09-01 | 2017-03-08 | 中国科学院计算技术研究所 | News clue personalized push method and system |
| CN108229769A (en) * | 2016-12-12 | 2018-06-29 | 上海看榜信息科技有限公司 | A kind of new media Brand Evaluation system |
-
2019
- 2019-11-04 CN CN201911066611.5A patent/CN111027310A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101409634A (en) * | 2007-10-10 | 2009-04-15 | 中国科学院自动化研究所 | Quantitative analysis tools and method for internet news influence based on information retrieval |
| US20160098738A1 (en) * | 2014-10-06 | 2016-04-07 | Chunghwa Telecom Co., Ltd. | Issue-manage-style internet public opinion information evaluation management system and method thereof |
| CN106484733A (en) * | 2015-09-01 | 2017-03-08 | 中国科学院计算技术研究所 | News clue personalized push method and system |
| CN108229769A (en) * | 2016-12-12 | 2018-06-29 | 上海看榜信息科技有限公司 | A kind of new media Brand Evaluation system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112000676A (en) * | 2020-07-14 | 2020-11-27 | 微民保险代理有限公司 | Vehicle information updating method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhao et al. | Seismic: A self-exciting point process model for predicting tweet popularity | |
| Noss et al. | Comparison of density estimation methods for mammal populations with camera traps in the K aa‐I ya del G ran C haco landscape | |
| US10664872B2 (en) | Systems and methods for generating network intelligence through real-time analytics | |
| Ghosh et al. | On sampling the wisdom of crowds: Random vs. expert sampling of the twitter stream | |
| CN105431844B (en) | Third party for search system searches for application | |
| Janko et al. | Examining the link between crime and unemployment: A time-series analysis for Canada | |
| US20160321261A1 (en) | System and method of providing a content discovery platform for optimizing social network engagements | |
| CN111311136A (en) | Wind control decision method, computer equipment and storage medium | |
| KR20210118452A (en) | Real-time event detection for social data streams | |
| CN108462888A (en) | The intelligent association analysis method and system of user's TV and internet behavior | |
| Mahata et al. | From chirps to whistles: discovering event-specific informative content from twitter | |
| CN102833111A (en) | Visual hyper text transfer protocol (HTTP) data supervising method and device | |
| Li et al. | Understanding video sharing propagation in social networks: Measurement and analysis | |
| CN113869931A (en) | Advertisement putting strategy determining method and device, computer equipment and storage medium | |
| Vasiloudis et al. | Predicting session length in media streaming | |
| EP3857406A1 (en) | Multi-tier scalable media analysis | |
| Permana et al. | Perception analysis of the Indonesian society on twitter social media on the increase in BPJS kesehatan contribution in the Covid 19 pandemic era | |
| Hu et al. | Predicting key events in the popularity evolution of online information | |
| CN109933709B (en) | Public opinion tracking method and device for video text combined data and computer equipment | |
| CN111062202A (en) | Method, device and equipment for evaluating influence of information source and readable medium | |
| CN111027310A (en) | Text influence evaluation method, device, equipment and readable medium | |
| Overbey et al. | Structure and prominence in Twitter networks centered on contentious politics | |
| Rafail et al. | Local receptivity climates and the dynamics of media attention to protest | |
| Chua et al. | Rumor retransmission on Twitter: message characteristics, user characteristics and retransmission outcomes | |
| US10601749B1 (en) | Trends in a messaging platform |
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 |