Online public opinion dynamic monitoring method and device and readable medium

Abstract

The invention relates to a network public opinion dynamic monitoring method and device and a readable medium, belongs to the field of public opinion management and control, and solves the problem that a current network public opinion monitoring mode is unreasonable. The method comprises the steps that a network publishing carrier and historical publishing data of network publishing media in the network publishing carrier are acquired; determining a network publishing carrier and a public opinion control level of network publishing media in the network publishing carrier based on the historical publishing data; executing a corresponding monitoring method based on the public opinion management and control level network publishing carrier and network publishing media in the network publishing carrier; collecting real-time publishing data of the network messages published by the network publishing carrier and the network publishing media in real time, and analyzing the published network messages in combination with the real-time publishing data; the published network message is subjected to public opinion monitoring according to the message analysis result, the public opinion situation of the network message is analyzed according to the public opinion monitoring result, and timely early warning and accurate management and control of the network public opinions are achieved by setting the adaptive monitoring method.

Description

Technical Field

[0001] The present invention belongs to the technical field of public opinion management, and specifically relates to a method, a device and a readable medium for dynamically monitoring network public opinion. Background Art

[0002] Internet public opinion refers to the popular online opinions on different social issues. It is a form of social public opinion. It is the public's opinions and views on certain hot and focal issues in real life that are spread through the Internet. Internet public opinion is a diversified collection of various popular online public opinions. Internet public opinion is a collection of the expression, dissemination and interaction of the emotions, attitudes, opinions and views of the majority of netizens, with the Internet as the carrier and events as the core.

[0003] In the prior art, the monitoring and early warning of online public opinion usually sets a unified monitoring standard, that is, the same control criteria and control methods are set in major online publishing carriers or online publishing platforms. Therefore, it is easy to have problems such as waste of public opinion supervision resources on a certain platform or insufficient public opinion monitoring resources on a certain platform, and the allocation of online public opinion supervision resources is unreasonable. For this reason, the present invention proposes a method, device and readable medium for dynamic monitoring of online public opinion. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention aims to provide a method, device and readable medium for dynamically monitoring network public opinion.

[0005] The technical problems to be solved by the present invention are: How to achieve timely warning and accurate control of online public opinion based on differentiated online public opinion monitoring methods.

[0006] In the first aspect, in order to achieve the above-mentioned purpose, the present invention adopts the following technical solutions: A method for dynamic monitoring of network public opinion, the method is as follows: Step S1, obtaining the historical publishing data of the network publishing carrier and the network publishing media in the network publishing carrier; Step S2: determining the public opinion control level of the network publishing carrier and the network publishing media in the network publishing carrier based on the historical publishing data; Step S3: Based on the public opinion control level, the network publishing carrier and the network publishing media within the network publishing carrier implement corresponding monitoring measures; Step S4: monitoring public opinion according to the monitoring method, collecting real-time publishing data of network messages published by network publishing carriers and network publishing media in real time when network messages are published, and analyzing the published network messages in combination with the real-time publishing data; Among them, the real-time release data includes the network release carrier, network release media, release time and key words of the network message; Step S5: monitoring the public opinion of the published online message based on the message analysis result, and analyzing the public opinion situation of the online message based on the public opinion monitoring result; Step S6: Control network information based on public opinion trends.

[0007] Furthermore, the historical release data includes the number of times false information is released on the network release carrier, as well as the number of media broadcasts, media forwardings and media clicks of the false information; the number of media releases of false information by network release media on the network release carrier, as well as the number of media broadcasts, media forwardings and media clicks of the false information released by the network release media.

[0008] Furthermore, in this example, step S2 includes the following sub-steps: Step S21, obtaining the media publishing times ZFCio of false information published by the network publishing media in the network publishing carrier, where i is the serial number of the network publishing carrier, and o is the serial number of the network publishing media in the network publishing carrier; Step S22, then obtaining the media playback volume ZBLio, media forwarding volume ZZFio and media click volume ZDJio of the false information released by the network publishing media in the network publishing carrier; Step S23: Calculate the media monitoring value ZJCio of the network publishing media in the network publishing carrier through a formula, the specific formula is as follows: ZJCio=ZFCio×a1+ZBLio×a2+ZZFio×a3+ZDJio×a4; where a1, a2, a3 and a4 are weight coefficients; Step S24: compare the media monitoring value with the media monitoring threshold. If the media monitoring value is greater than or equal to the media monitoring threshold, the corresponding network publishing media is recorded as public opinion monitoring media. If the media monitoring value is less than the media monitoring threshold, no operation is performed. Step S25, counting the number of public opinion monitoring media in the network publishing carrier, and recording it as the number of public opinion monitoring media ZTi; Step S26, obtaining the carrier publishing times PFCi of the false message in the network publishing carrier, as well as the carrier broadcast volume PBLi, carrier forwarding volume PZFi and carrier click volume PDJi of the false message; Step S27, calculate the carrier control value PGi of the network publishing carrier by the formula PGi=ZTi×b1+PFCi×b2+(PBLi+PZFi+PDJi)×b3; wherein b1, b2, and b3 are all weight coefficients, and b1>b2>b3; Step S28, compare the carrier control value with the carrier control threshold, and determine whether the public opinion control level of the network publishing carrier is the third public opinion control level, the second public opinion control level or the first public opinion control level; among which, the control strength of the third public opinion control level is lower than the control strength of the second public opinion control level, and the control strength of the second public opinion control level is lower than the control strength of the first public opinion control level.

[0009] Furthermore, the step S3 includes the following sub-steps: Step S31: If it is the first public opinion control level, the third monitoring method is implemented on the network publishing carrier and the network publishing media in the network publishing carrier; Step S32: If it is the second public opinion control level, the second monitoring method is implemented on the network publishing carrier and the network publishing media in the network publishing carrier; Step S33: If it is the third public opinion control level, the first monitoring method is implemented on the network publishing carrier and the network publishing media in the network publishing carrier.

[0010] Furthermore, the first monitoring method is specifically: extracting keywords n3 times from the published titles and message contents of network messages; The second monitoring method is specifically: extracting keywords n2 times from the message content of the network message; The third monitoring method is as follows: extract keywords n1 times from the title of the online message; 0<n1<n2<n3, n1, n2 and n3 are all positive integers; Among them, the control intensity of the public opinion control level is directly proportional to the control intensity of the monitoring method, that is, the higher the level of public opinion control, the greater the control intensity of the monitoring method.

[0011] Furthermore, the analysis process of the network message in step S4 is specifically as follows: Step S41, marking the currently analyzed network message as a monitored network message, obtaining a keyword group of the monitored network message and recording it as the monitored keyword group, searching for network messages published by multiple authoritative publishing carriers in the same network publishing carrier based on the monitored keyword group and recording it as the compared network message; Step S42, extracting a plurality of comparison keyword groups from the comparison network messages; Step S43, comparing a set of monitoring keyword groups with a set of comparison keyword groups corresponding to the comparison network messages one by one; Step S44: if the monitoring keyword group does not match all the comparison keyword groups in the comparison network message, then the unmatched monitoring keyword group is compared again with the comparison keyword group corresponding to the other group of comparison network messages one by one. When the unmatched monitoring keyword group matches any one of the comparison keyword groups in the other group of comparison network messages, the comparison is continued until all the monitoring keyword groups obtain matching comparison keyword groups in the other group of comparison network messages. At this time, no operation is performed. When the unmatched monitoring keyword group still does not match all the comparison keyword groups in the other group of comparison network messages, the monitoring network message is recorded as a false message. Step S45: If the monitoring keyword group matches any one of the comparison keyword groups in the comparison network message, the next monitoring keyword group is compared with any one of the comparison keyword groups in the comparison network message. When any monitoring keyword group does not match all the comparison keyword groups in the comparison network message, the unmatched monitoring keyword group is compared again with the comparison keyword groups corresponding to the other group of comparison network messages one by one. If the unmatched monitoring keyword group matches any one of the comparison keyword groups in the other group of comparison network messages, the comparison is continued until all the monitoring keyword groups are matched with the comparison keyword groups in the other group of comparison network messages. At this time, no operation is performed. When the unmatched monitoring keyword group also does not match all the comparison keyword groups in the other group of comparison network messages, the monitoring network message is recorded as a false message.

[0012] Furthermore, the step S5 includes the following sub-steps: Step S51, obtaining the public opinion change data of the network message, obtaining the initial playback volume, initial forwarding volume and initial click volume of the network message at the time of release, and the real-time playback volume, real-time forwarding volume and real-time click volume of the network message at the current time; Step S52: If the real-time playback volume is equal to the initial playback volume, the real-time forwarding volume is equal to the initial forwarding volume, and the real-time click volume is equal to the initial click volume, no operation is performed; If the real-time playback volume is not equal to the initial playback volume, the real-time forwarding volume is not equal to the initial forwarding volume, or the real-time click volume is not equal to the initial click volume, proceed to the next step; In reality, the initial playback volume, initial forwarding volume, and initial click volume are definitely minimum values, and the real-time playback volume, real-time forwarding volume, and real-time click volume can only be increasing; Step S53: Calculate the increase rate of the broadcast of the network message by a formula, the specific formula is: Play increase rate = (real-time play volume - initial play volume) / (current time - release time); Step S54: Similarly, the forwarding increase rate and click increase rate of the network message are calculated by the formula; Step S55: When the play increase rate, forwarding increase rate and click increase rate are all less than or equal to the corresponding rate thresholds, a public opinion normal signal is generated; When any of the playback increase rate, forwarding increase rate or click increase rate is greater than the corresponding rate threshold, a public opinion control signal is generated.

[0013] Furthermore, the step S6 includes the following sub-steps: Step S61: When a public opinion control signal is received, control measures are implemented on the corresponding network publishing carriers and network publishing media. The control measures are to remove the network messages that need to be controlled from the network publishing carriers and punish the network publishing media that published the corresponding network messages. Step S62: When a normal public opinion signal is received, no operation is performed.

[0014] In a second aspect, the present invention further adopts a computer device, the computer device comprising: A memory storing a computer program; The processor is communicatively connected to the memory, and when the computer program is executed by the processor, a method for dynamically monitoring network public opinion is implemented.

[0015] In a third aspect, the present invention also adopts a computer-readable storage medium on which a computer program is stored, characterized in that when the program is executed by a processor, a method for dynamically monitoring network public opinion is implemented.

[0016] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. The present invention obtains historical publishing data of network publishing carriers and network publishing media in network publishing carriers, determines the public opinion control level of network publishing carriers and network publishing media in network publishing carriers in combination with the historical publishing data, and implements corresponding monitoring methods based on the public opinion control level for network publishing carriers and network publishing media in network publishing carriers. By setting adaptive public opinion monitoring methods for different network publishing carriers, network publishing platforms and network publishing media, dynamic monitoring of network public opinion is achieved; 2. The present invention monitors public opinion based on a monitoring method. When online messages are released, the present invention collects real-time release data of online messages released by online release carriers and online release media in real time, analyzes the released online messages in combination with the real-time release data, monitors public opinion on the released online messages based on the message analysis results, analyzes the public opinion situation of the online messages based on the public opinion monitoring results, and realizes timely early warning and timely control of online public opinion. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0018] Figure 1 is a flow chart of the method of the present invention; Figure 2 is a flowchart of the sub-steps corresponding to step S3 in the present invention; Figure 3 It is a step flow chart of the sub-steps corresponding to step S5 in the present invention; Figure 4 It is a schematic diagram of the structure of the computer device in the present invention. DETAILED DESCRIPTION

[0019] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Embodiment 1: See also Figure 1-Figure 2 As shown, the technical solution provided by the present invention is: a method for dynamic monitoring of online public opinion, which is used to dynamically monitor and dynamically monitor network messages released by different network publishing carriers and different network publishing media in network publishing carriers, and timely warn and timely control false network messages to avoid the malicious fermentation of false network messages. The method is specifically as follows: Step S1, obtaining the historical publishing data of the network publishing carrier and the network publishing media in the network publishing carrier; It should be specifically noted that the historical release data include the number of media releases of false information in online release carriers, as well as the media playback volume, media forwarding volume and media click volume of false information; the number of media releases of false information by online release media in online release carriers, as well as the media playback volume, media forwarding volume and media click volume of false information released by online release media; among which, the media playback volume, media forwarding volume and media click volume are respectively included in the carrier playback volume, carrier forwarding volume and carrier click volume.

[0021] Step S2: determining the public opinion control level of the network publishing carrier and the network publishing media in the network publishing carrier based on the historical publishing data; In this example, step S2 includes the following sub-steps: Step S21, obtaining the media publishing times ZFCio of false information published by the network publishing media in the network publishing carrier, where i is the serial number of the network publishing carrier, and o is the serial number of the network publishing media in the network publishing carrier; Step S22, then obtaining the media playback volume ZBLio, media forwarding volume ZZFio and media click volume ZDJio of the false information released by the network publishing media in the network publishing carrier; Step S23: After removing the dimension, the media monitoring value ZJCio of the network publishing media in the network publishing carrier is calculated by the formula, and the specific formula is as follows: ZJCio=ZFCio×a1+ZBLio×a2+ZZFio×a3+ZDJio×a4; where a1, a2, a3 and a4 are weight coefficients; Step S24: compare the media monitoring value with the media monitoring threshold. If the media monitoring value is greater than or equal to the media monitoring threshold, the corresponding network publishing media is recorded as public opinion monitoring media. If the media monitoring value is less than the media monitoring threshold, no operation is performed. Step S25, counting the number of public opinion monitoring media in the network publishing carrier, and recording it as the number of public opinion monitoring media ZTi; Step S26, obtaining the carrier publishing times PFCi of the false message in the network publishing carrier, as well as the carrier broadcast volume PBLi, carrier forwarding volume PZFi and carrier click volume PDJi of the false message; Step S27, after removing the dimension, the carrier control value PGi of the network publishing carrier is calculated by the formula PGi=ZTi×b1+PFCi×b2+(PBLi+PZFi+PDJi)×b3; wherein b1, b2, and b3 are all weight coefficients, and b1>b2>b3; Step S28: If the carrier control value is less than or equal to the first carrier control threshold, the public opinion control level of the network publishing carrier is the third public opinion control level; If the carrier control value is greater than the first carrier control threshold and less than or equal to the second carrier control threshold, the public opinion control level of the network publishing carrier is the second public opinion control level; If the carrier control value is greater than the second carrier control threshold, the public opinion control level of the network publishing carrier is the first public opinion control level; It is understandable that the first carrier control threshold is lower than the second carrier control threshold, the control intensity of the third public opinion control level is lower than the control intensity of the second public opinion control level, and the control intensity of the second public opinion control level is lower than the control intensity of the first public opinion control level.

[0022] Step S3: Based on the public opinion control level, the network publishing carrier and the network publishing media within the network publishing carrier implement corresponding monitoring measures; In this embodiment, step S3 includes the following sub-steps: Step S31: If it is the first public opinion control level, the third monitoring method is implemented on the network publishing carrier and the network publishing media in the network publishing carrier; Step S32: If it is the second public opinion control level, the second monitoring method is implemented on the network publishing carrier and the network publishing media in the network publishing carrier; Step S33: If it is the third public opinion control level, the first monitoring method is implemented on the network publishing carrier and the network publishing media in the network publishing carrier; The first monitoring method is as follows: extracting keywords n3 times from the title and content of online messages; The second monitoring method is specifically: extracting keywords n2 times from the message content of the network message; The third monitoring method is as follows: extract keywords from the titles of online messages n1 times; keyword extraction is a mature technology in the prior art and will not be described in detail here, 0<n1<n2<n3, n1, n2 and n3 are all positive integers; Among them, the control intensity of the public opinion control level is directly proportional to the control intensity of the monitoring method, that is, the higher the level of public opinion control, the greater the control intensity of the monitoring method.

[0023] Embodiment 2: Figure 3 As shown, as a further solution of the first embodiment, when the network publishing carrier and the network publishing media are monitored according to the monitoring method set in the first embodiment; Step S4: monitoring public opinion according to the monitoring method, collecting real-time publishing data of network messages published by network publishing carriers and network publishing media in real time when network messages are published, and analyzing the published network messages in combination with the real-time publishing data; Specifically, the real-time release data includes the network release carrier, network release media, release time and keyword phrases of the network message; The analysis process of the network message in step S4 is specifically as follows: Step S41, marking the currently analyzed network message as a monitored network message, obtaining a keyword group of the monitored network message and recording it as the monitored keyword group, searching for network messages published by multiple authoritative publishing carriers in the same network publishing carrier based on the monitored keyword group and recording it as the compared network message; The authoritative network release carrier is specifically an official media. In this embodiment, in order to facilitate comparison and analysis, two groups of authoritative release carriers are preferably used, that is, one group of authoritative release carriers corresponds to one group of comparison network messages; Step S42, extracting a plurality of comparison keyword groups from the comparison network messages; Step S43, comparing a set of monitoring keyword groups with a set of comparison keyword groups corresponding to the comparison network messages one by one; Step S44: if the monitoring keyword group does not match all the comparison keyword groups in the comparison network message, then the unmatched monitoring keyword group is compared again with the comparison keyword group corresponding to the other group of comparison network messages one by one. When the unmatched monitoring keyword group matches any one of the comparison keyword groups in the other group of comparison network messages, the comparison is continued until all the monitoring keyword groups obtain matching comparison keyword groups in the other group of comparison network messages. At this time, no operation is performed. When the unmatched monitoring keyword group still does not match all the comparison keyword groups in the other group of comparison network messages, the monitoring network message is recorded as a false message. Step S45: If the monitoring keyword group matches any one of the comparison keyword groups in the comparison network message, the next monitoring keyword group is compared with any one of the comparison keyword groups in the comparison network message. When any monitoring keyword group does not match all the comparison keyword groups in the comparison network message, the unmatched monitoring keyword group is compared again with the comparison keyword groups corresponding to the other group of comparison network messages one by one. If the unmatched monitoring keyword group matches any one of the comparison keyword groups in the other group of comparison network messages, the comparison is continued until all the monitoring keyword groups are matched with the comparison keyword groups in the other group of comparison network messages. At this time, no operation is performed. When the unmatched monitoring keyword group also does not match all the comparison keyword groups in the other group of comparison network messages, the monitoring network message is recorded as a false message.

[0024] Step S5: monitoring the public opinion of the published online message based on the message analysis result, and analyzing the public opinion situation of the online message based on the public opinion monitoring result; The step S5 comprises the following sub-steps: Step S51, obtaining the public opinion change data of the network message, obtaining the initial playback volume, initial forwarding volume and initial click volume of the network message at the time of release, and the real-time playback volume, real-time forwarding volume and real-time click volume of the network message at the current time; Step S52: If the real-time playback volume is equal to the initial playback volume, the real-time forwarding volume is equal to the initial forwarding volume, and the real-time click volume is equal to the initial click volume, no operation is performed; If the real-time playback volume is not equal to the initial playback volume, the real-time forwarding volume is not equal to the initial forwarding volume, or the real-time click volume is not equal to the initial click volume, proceed to the next step; In reality, the initial playback volume, initial forwarding volume, and initial click volume are definitely minimum values, and the real-time playback volume, real-time forwarding volume, and real-time click volume can only be increasing; Step S53: Calculate the increase rate of the broadcast of the network message by a formula, the specific formula is: Play increase rate = (real-time play volume - initial play volume) / (current time - release time); Step S54: Similarly, the forwarding increase rate and click increase rate of the network message are calculated by the formula; Step S55: When the play increase rate, forwarding increase rate and click increase rate are all less than or equal to the corresponding rate thresholds, a public opinion normal signal is generated; When any of the playback increase rate, forwarding increase rate or click increase rate is greater than the corresponding rate threshold, a public opinion control signal is generated.

[0025] Step S6: Control network information based on public opinion trends, specifically: Step S61: When receiving a public opinion control signal, control measures are implemented on the corresponding network publishing carriers and network publishing media. The control measures are to remove the network information that needs to be controlled in the network publishing carriers, and punish the network publishing media that publishes the corresponding network information. The punishment includes but is not limited to long-term account blocking, short-term account blocking, fixed-term prohibition of network information publishing, permanent prohibition of network information publishing, etc. Step S62: When a normal public opinion signal is received, no operation is performed; In this application, if corresponding calculation formulas appear, the above calculation formulas are all dimensionless and take their numerical calculations. The weight coefficients, proportional coefficients and other coefficients in the formulas are set to a result value obtained by quantifying each parameter. The size of the weight coefficient and the proportional coefficient can be determined as long as it does not affect the proportional relationship between the parameter and the result value.

[0026] Embodiment three: Figure 4 The structural diagram of a computer device is illustrated, and the computer device may include: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus. The processor may call the logic instructions in the memory to execute a method for dynamic monitoring of online public opinion, which includes: obtaining the historical release data of the network release carrier and the network release media in the network release carrier; determining the public opinion control level of the network release carrier and the network release media in the network release carrier based on the historical release data; based on the public opinion control level, the network release carrier and the network release media in the network release carrier execute corresponding monitoring methods; public opinion monitoring is performed according to the monitoring method, and when the network message is released, the real-time release data of the network message released by the network release carrier and the network release media is collected in real time, and the released network message is analyzed in combination with the real-time release data; public opinion monitoring is performed on the released network message according to the message analysis result, and the public opinion situation of the network message is analyzed according to the public opinion monitoring result.

[0027] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0028] Embodiment 4: The present application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute a method for dynamically monitoring online public opinion provided by the above methods, which includes: obtaining historical release data of online publishing carriers and online publishing media in the online publishing carriers; determining the public opinion control level of the online publishing carriers and the online publishing media in the online publishing carriers based on the historical release data; based on the public opinion control level, the online publishing carriers and the online publishing media in the online publishing carriers execute corresponding monitoring methods; public opinion monitoring is performed according to the monitoring methods, and when online messages are released, real-time release data of online messages released by the online publishing carriers and online publishing media are collected in real time, and the released online messages are analyzed in combination with the real-time release data; public opinion monitoring is performed on the released online messages according to the message analysis results, and the public opinion situation of the online messages is analyzed according to the public opinion monitoring results.

[0029] Embodiment 5: The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute a method for dynamically monitoring network public opinion provided above, the method comprising: obtaining historical release data of a network publishing carrier and a network publishing media in the network publishing carrier; determining the public opinion control level of the network publishing carrier and the network publishing media in the network publishing carrier based on the historical release data; based on the public opinion control level, the network publishing carrier and the network publishing media in the network publishing carrier execute a corresponding monitoring method; performing public opinion monitoring according to the monitoring method, and when a network message is released, collecting real-time release data of the network message released by the network publishing carrier and the network publishing media in real time, and analyzing the released network message in combination with the real-time release data; performing public opinion monitoring on the released network message based on the message analysis result, and analyzing the public opinion situation of the network message based on the public opinion monitoring result.

[0030] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0031] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0032] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for dynamic monitoring of network public opinion, characterized in that: The specific methods for dynamic monitoring of online public opinion are as follows: Step S1, obtaining the historical publishing data of the network publishing carrier and the network publishing media in the network publishing carrier; Step S2: determining the public opinion control level of the network publishing carrier and the network publishing media in the network publishing carrier based on the historical publishing data; Step S3: Based on the public opinion control level, the network publishing carrier and the network publishing media within the network publishing carrier implement corresponding monitoring measures; Step S4: monitoring public opinion according to the monitoring method, collecting real-time publishing data of network messages published by network publishing carriers and network publishing media in real time when network messages are published, and analyzing the published network messages in combination with the real-time publishing data; Among them, the real-time release data includes the network release carrier, network release media, release time and key words of the network message; Step S5: monitoring the public opinion of the published online message based on the message analysis result, and analyzing the public opinion situation of the online message based on the public opinion monitoring result; Step S6: Control network information based on public opinion trends.

2. A method for dynamic monitoring of network public opinion according to claim 1, characterized in that: The historical release data include the number of media releases of false information in online release media, as well as the media playback volume, media forwarding volume and media click volume of false information; the number of media releases of false information by online release media in online release media, as well as the media playback volume, media forwarding volume and media click volume of false information released by online release media.

3. A method for dynamic monitoring of network public opinion according to claim 2, characterized in that: In this example, step S2 includes the following sub-steps: Step S21, obtaining the media publishing times ZFCio of false information published by the network publishing media in the network publishing carrier, where i is the serial number of the network publishing carrier, and o is the serial number of the network publishing media in the network publishing carrier; Step S22, then obtaining the media playback volume ZBLio, media forwarding volume ZZFio and media click volume ZDJio of the false information released by the network publishing media in the network publishing carrier; Step S23: Calculate the media monitoring value ZJCio of the network publishing media in the network publishing carrier through a formula, the specific formula is as follows: ZJCio=ZFCio×a1+ZBLio×a2+ZZFio×a3+ZDJio×a4; where a1, a2, a3 and a4 are weight coefficients; Step S24: compare the media monitoring value with the media monitoring threshold. If the media monitoring value is greater than or equal to the media monitoring threshold, the corresponding network publishing media is recorded as public opinion monitoring media. If the media monitoring value is less than the media monitoring threshold, no operation is performed. Step S25, counting the number of public opinion monitoring media in the network publishing carrier, and recording it as the number of public opinion monitoring media ZTi; Step S26, obtaining the carrier publishing times PFCi of the false message in the network publishing carrier, as well as the carrier broadcast volume PBLi, carrier forwarding volume PZFi and carrier click volume PDJi of the false message; Step S27, calculate the carrier control value PGi of the network publishing carrier by the formula PGi=ZTi×b1+PFCi×b2+(PBLi+PZFi+PDJi)×b3; wherein b1, b2, and b3 are all weight coefficients, and b1>b2>b3; Step S28, compare the carrier control value with the carrier control threshold, and determine whether the public opinion control level of the network publishing carrier is the third public opinion control level, the second public opinion control level or the first public opinion control level; among which, the control strength of the third public opinion control level is lower than the control strength of the second public opinion control level, and the control strength of the second public opinion control level is lower than the control strength of the first public opinion control level.

4. A method for dynamic monitoring of network public opinion according to claim 3, characterized in that: The step S3 includes the following sub-steps: Step S31: If it is the first public opinion control level, the third monitoring method is implemented on the network publishing carrier and the network publishing media in the network publishing carrier; Step S32: If it is the second public opinion control level, the second monitoring method is implemented on the network publishing carrier and the network publishing media in the network publishing carrier; Step S33: If it is the third public opinion control level, the first monitoring method is implemented on the network publishing carrier and the network publishing media in the network publishing carrier.

5. A method for dynamic monitoring of network public opinion according to claim 4, characterized in that: The first monitoring method is as follows: extract keywords n3 times from the title and content of online messages; The second monitoring method is specifically: extracting keywords n2 times from the message content of the network message; The third monitoring method is as follows: extract keywords n1 times from the title of the online message; 0<n1<n2<n3, n1, n2 and n3 are all positive integers; Among them, the control intensity of the public opinion control level is directly proportional to the control intensity of the monitoring method, that is, the higher the level of public opinion control, the greater the control intensity of the monitoring method.

6. A method for dynamic monitoring of network public opinion according to claim 1, characterized in that: The analysis process of the network message in step S4 is specifically as follows: Step S41, marking the currently analyzed network message as a monitored network message, obtaining a keyword group of the monitored network message and recording it as the monitored keyword group, searching for network messages published by multiple authoritative publishing carriers in the same network publishing carrier based on the monitored keyword group and recording it as the compared network message; Step S42, extracting a plurality of comparison keyword groups from the comparison network messages; Step S43, comparing a set of monitoring keyword groups with a set of comparison keyword groups corresponding to the comparison network messages one by one; Step S44: if the monitoring keyword group does not match all the comparison keyword groups in the comparison network message, then the unmatched monitoring keyword group is compared again with the comparison keyword group corresponding to the other group of comparison network messages one by one. When the unmatched monitoring keyword group matches any one of the comparison keyword groups in the other group of comparison network messages, the comparison is continued until all the monitoring keyword groups obtain matching comparison keyword groups in the other group of comparison network messages. At this time, no operation is performed. When the unmatched monitoring keyword group still does not match all the comparison keyword groups in the other group of comparison network messages, the monitoring network message is recorded as a false message. Step S45: If the monitoring keyword group matches any one of the comparison keyword groups in the comparison network message, the next monitoring keyword group is compared with any one of the comparison keyword groups in the comparison network message. When any monitoring keyword group does not match all the comparison keyword groups in the comparison network message, the unmatched monitoring keyword group is compared again with the comparison keyword groups corresponding to the other group of comparison network messages one by one. If the unmatched monitoring keyword group matches any one of the comparison keyword groups in the other group of comparison network messages, the comparison is continued until all the monitoring keyword groups are matched with the comparison keyword groups in the other group of comparison network messages. At this time, no operation is performed. When the unmatched monitoring keyword group also does not match all the comparison keyword groups in the other group of comparison network messages, the monitoring network message is recorded as a false message.

7. A method for dynamic monitoring of network public opinion according to claim 6, characterized in that: The step S5 comprises the following sub-steps: Step S51, obtaining the public opinion change data of the network message, obtaining the initial playback volume, initial forwarding volume and initial click volume of the network message at the time of release, and the real-time playback volume, real-time forwarding volume and real-time click volume of the network message at the current time; Step S52: If the real-time playback volume is equal to the initial playback volume, the real-time forwarding volume is equal to the initial forwarding volume, and the real-time click volume is equal to the initial click volume, no operation is performed; If the real-time playback volume is not equal to the initial playback volume, the real-time forwarding volume is not equal to the initial forwarding volume, or the real-time click volume is not equal to the initial click volume, proceed to the next step; In reality, the initial playback volume, initial forwarding volume, and initial click volume are definitely minimum values, and the real-time playback volume, real-time forwarding volume, and real-time click volume can only be increasing; Step S53: Calculate the increase rate of the broadcast of the network message by a formula, the specific formula is: Play increase rate = (real-time play volume - initial play volume) / (current time - release time); Step S54: Similarly, the forwarding increase rate and click increase rate of the network message are calculated by the formula; Step S55: When the play increase rate, forwarding increase rate and click increase rate are all less than or equal to the corresponding rate thresholds, a public opinion normal signal is generated; When any of the playback increase rate, forwarding increase rate or click increase rate is greater than the corresponding rate threshold, a public opinion control signal is generated.

8. A method for dynamic monitoring of network public opinion according to claim 7, characterized in that: The step S6 comprises the following sub-steps: Step S61: When a public opinion control signal is received, control measures are implemented on the corresponding network publishing carriers and network publishing media. The control measures are to remove the network messages that need to be controlled from the network publishing carriers and punish the network publishing media that published the corresponding network messages. Step S62: When a normal public opinion signal is received, no operation is performed.

9. A computer device, characterized in that: The computer device comprises: A memory storing a computer program; A processor is communicatively connected to the memory, and when the computer program is executed by the processor, the method for dynamically monitoring network public opinion described in any one of claims 1-8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for dynamically monitoring network public opinion described in any one of claims 1 to 8 is implemented.

Images