CN115221416A - Reputation risk positioning analysis method and system - Google Patents
Reputation risk positioning analysis method and system Download PDFInfo
- Publication number
- CN115221416A CN115221416A CN202210989980.7A CN202210989980A CN115221416A CN 115221416 A CN115221416 A CN 115221416A CN 202210989980 A CN202210989980 A CN 202210989980A CN 115221416 A CN115221416 A CN 115221416A
- Authority
- CN
- China
- Prior art keywords
- data
- matching degree
- public opinion
- reputation risk
- big data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a reputation risk positioning analysis method and a reputation risk positioning analysis system, which belong to the technical field of reputation risk management; wherein the method comprises the following steps: responding to the trigger signal, and acquiring public opinion research and judgment big data; carrying out first processing on the public opinion research big data to determine a plurality of interest correlators and first data corresponding to each interest correlator; second processing the first data to determine event causality; and generating and outputting a reputation risk analysis report according to the event causal relationship. The scheme of the invention can automatically and quickly acquire and analyze the public opinion research and judgment big data, further timely generate a reputation risk analysis report with higher reference value, greatly reduce the time consumption of the investigation process, enable enterprises to accurately know the causal consequence of the public opinion, and make quick and appropriate treatment in more time before the public opinion fermentation.
Description
Technical Field
The invention relates to the technical field of reputation risk management, in particular to a reputation risk positioning analysis method, a reputation risk positioning analysis system, electronic equipment and a computer storage medium.
Background
In the modern information society, it is very important for enterprises to discover and properly handle public sentiment in time.
The existing public opinion processing mainly relies on manpower to realize risk positioning, but the information quantity related to the occurrence of public opinion events is huge and the evolution speed is high, so that the traditional manpower risk positioning method is long in required time and high in difficulty, and the risk of reputation risk upgrading can be caused by overlong investigation time and the risk is evolved into a great reputation event.
Disclosure of Invention
In order to solve at least the technical problems in the background art, the invention provides a reputation risk localization analysis method, a reputation risk localization analysis system, an electronic device and a computer storage medium.
The invention provides a reputation risk positioning analysis method, which comprises the following steps:
responding to the trigger signal, and acquiring public opinion research and judgment big data;
performing first processing on the public opinion research and judgment big data to determine a plurality of interest correlators and first data corresponding to the interest correlators;
second processing the first data to determine event causality;
and generating and outputting a reputation risk analysis report according to the event causal relationship.
Further, the trigger signal is generated by:
receiving a risk analysis signal input by a user, and generating the trigger signal according to the risk analysis signal;
alternatively, the first and second electrodes may be,
the method comprises the steps of periodically obtaining public sentiment big data related to preset data, carrying out third processing on the public sentiment big data to obtain a plurality of negative topics, and generating a trigger signal when the development trend of any negative topic meets a first preset condition.
Further, the first processing of the big public opinion research and judgment data to determine a plurality of stakeholders comprises:
calculating first development trend data according to the public opinion research and judgment big data;
determining all related subjects from the public opinion research and judgment big data, and respectively calculating second development trend data according to the first data of each subject;
and calculating the matching degree of each second development trend data and the first development trend data, and taking a subject with the matching degree meeting a second preset condition as the interest-related person.
Further, the matching degree comprises a first matching degree and a plurality of second matching degrees;
the taking the subject with the matching degree meeting a second preset condition as the stakeholder includes:
calculating whether the first matching degree is larger than or equal to a first threshold value, and if so, taking the subject as the stakeholder;
if not, calculating whether each second matching degree is greater than or equal to a second threshold, and if at least one second matching degree greater than or equal to the second threshold exists, taking the subject as the stakeholder.
Further, the second threshold is determined by:
extracting a plurality of key nodes of the first development trend data, and determining a plurality of first section data and the corresponding relation between each first section data and each second section data in the second development trend data according to the key nodes;
calculating a third matching degree of the first section data and the corresponding second section data, and determining the second threshold value based on the third matching degree;
wherein the second threshold is inversely related to the third degree of matching.
Further, the first matching degree and the second matching degree are calculated through a first depth prediction model.
Further, the second processing the first data to determine event causality includes:
inputting the first data into a second depth prediction model, the second depth prediction model outputting the event causality;
the event cause and effect relationship comprises a stakeholder, a data matrix for describing event development and time calibration data of the data.
The invention provides a reputation risk positioning analysis system, which comprises an acquisition module, a processing module and a storage module, wherein the acquisition module is used for acquiring a reputation risk; the processing module is connected with the acquisition module and the storage module;
the storage module is used for storing executable computer program codes;
the acquisition module is used for acquiring public opinion research and judgment big data and transmitting the public opinion research and judgment big data to the processing module;
the processing module is configured to execute the method according to any one of the preceding claims by calling the executable computer program code in the storage module.
A third aspect of the present invention provides an electronic device comprising: a memory storing executable program code; a processor coupled with the memory; the processor calls the executable program code stored in the memory to perform the method of any of the preceding claims.
A fourth aspect of the invention provides a computer storage medium having stored thereon a computer program which, when executed by a processor, performs the method as set out in any one of the preceding claims.
Compared with the prior art, the reputation risk analysis method and device have the advantages that after the trigger signal of reputation risk analysis is received, relevant public opinion research and judgment big data can be automatically obtained, a plurality of interest correlators relevant to reputation risk are screened out, then event causal relations are determined according to the first data of the interest correlators, and finally a reputation risk analysis report is generated according to the event causal relations. Therefore, the scheme of the invention can automatically and quickly acquire and analyze the public opinion research and judgment big data, further generate a reputation risk analysis report with higher reference value in time, greatly reduce the time consumption of the investigation process, enable enterprises to accurately know the forecause and consequence of the public opinion, and make quick and appropriate treatment in more time before the public opinion fermentation.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a schematic flowchart of a reputation risk localization analysis method according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of a reputation risk localization analysis system according to an embodiment of the present invention.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, 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 terminology used in the embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the examples of this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and "a plurality" typically includes at least two.
It should be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
It should be understood that, although the terms first, second, third, etc. may be used in the embodiments of the present application to describe \8230; \8230, these \8230; should not be limited to these terms. These terms are used only to distinguish between 8230; and vice versa. For example, without departing from the scope of embodiments of the present application, a first of the methods may be used as 8230, a second of the methods may be used as 8230a first of the methods may be used as 8230a second of the methods may be used as 8230a third of the methods.
The words "if", as used herein may be interpreted as "at \8230; \8230whenor" when 8230; \8230when or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrases "if determined" or "if detected (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.
It is also noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a good or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such good or system. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in articles of commerce or systems including such elements.
Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Example one
Referring to fig. 1, fig. 1 is a schematic flowchart of a reputation risk localization analysis method according to an embodiment of the present invention. As shown in fig. 1, a reputation risk localization analysis method according to an embodiment of the present invention includes the following steps:
responding to the trigger signal, and acquiring public opinion research and judgment big data;
carrying out first processing on the public opinion research big data to determine a plurality of interest correlators and first data corresponding to each interest correlator;
second processing the first data to determine event causality;
and generating and outputting a reputation risk analysis report according to the event causal relationship.
In the embodiment of the invention, compared with the prior art, after receiving the trigger signal of reputation risk analysis, the method can automatically acquire related public opinion research and judgment big data, screen out a plurality of interest correlators related to reputation risk, then determine event causal relationship according to the first data of the interest correlators, and finally generate a reputation risk analysis report according to the event causal relationship. Therefore, the scheme of the invention can automatically and quickly acquire and analyze the public opinion research and judgment big data, further generate a reputation risk analysis report with higher reference value in time, greatly reduce the time consumption of the investigation process, enable enterprises to accurately know the forecause and consequence of the public opinion, and make quick and appropriate treatment in more time before the public opinion fermentation.
The public opinion research and judgment big data can comprise data of characters, videos and pictures, and can be acquired from the internet through a crawler technology.
Further, the trigger signal is generated by:
receiving a risk analysis signal input by a user, and generating the trigger signal according to the risk analysis signal;
alternatively, the first and second electrodes may be,
the method comprises the steps of periodically obtaining public sentiment big data related to preset data, carrying out third processing on the public sentiment big data to obtain a plurality of negative topics, and generating a trigger signal when the development trend of any negative topic meets a first preset condition.
In the embodiment of the invention, the triggering and starting of the reputation risk positioning analysis are realized through the two modes, namely manual triggering by a user and automatic triggering by a system. For the system automatic triggering mode, the system can periodically acquire public opinion big data related to a certain enterprise, extract negative topics from the public opinion big data, continuously analyze development trends of the negative topics, and automatically trigger reputation risk positioning analysis when the development trends rapidly rise (for example, topic popularity rises). For the manual triggering mode, the risk analysis signal input by the user includes risk analysis target data, such as data related to enterprise, data related to product, and data related to public opinion event, which can be used to guide the acquisition of big data related to public opinion research.
It should be noted that, for public opinion, usually, only negative information needs to be paid attention to, so the present invention presets several theme items as negative themes. The topic items may be respectively associated with related vocabularies such as enterprise public praise, product public praise, advertising, post-sale processing, and the like, for example, the vocabulary data set corresponding to the product public praise may include dead, stuck, slow, data lost, and the vocabulary data set corresponding to the post-sale processing may include untimely, bad attitude, unsolved, and the like.
Further, the first processing of the big public opinion research and judgment data to determine a plurality of stakeholders comprises:
calculating first development trend data according to the public opinion research and judgment big data;
determining all related subjects from the public opinion research and judgment big data, and respectively calculating second development trend data according to the first data of each subject;
and calculating the matching degree of each second development trend data and the first development trend data, and taking a subject with the matching degree meeting a second preset condition as the interest-related person.
In the embodiment of the invention, in order to screen out the interest relatives of certain public opinion data, the invention respectively calculates the development trend of the public opinion, namely the first development trend data, and the development trend data of each related main body in the public opinion, namely the second development trend data, and calculates the matching degree between the two, thereby accurately screening out the interest relatives in the public opinion event. The trend data refers to the discussion heat, and can be described by the data quantity related to the discussion frequency (original data or various processed equivalent data).
For the screening related to the subject, the term related to the public opinion research and judgment big data can be screened, then the term is subjected to statistical analysis, and potential stakeholders, namely all related subjects, can be screened according to the indexes such as the number of the term and the occurrence concentration of the term (taking time as a reference standard).
Further, the matching degree comprises a first matching degree and a plurality of second matching degrees;
the step of taking the subject with the matching degree meeting a second preset condition as the stakeholder includes:
calculating whether the first matching degree is greater than or equal to a first threshold value, and if so, taking the subject as the stakeholder;
if not, calculating whether each second matching degree is greater than or equal to a second threshold, and if at least one second matching degree greater than or equal to the second threshold exists, taking the subject as the stakeholder.
In the embodiment of the invention, the development of a public sentiment event mainly comprises single development and turning development, wherein the single development means that the main body of the public sentiment event does not obviously change, such as company A and company B are involved all the time; the transition refers to that the main body involved in different development stages of the public sentiment event (even the initial stage of the public sentiment development) is changed obviously, for example, the first stage involves company a and company B, and the second stage involves company a and company C. Aiming at the two situations, the invention adopts two matching degree calculation and analysis modes, namely, a first matching degree of overall matching of the public sentiment events and a second matching degree of local matching of the public sentiment events are calculated, matching analysis under the two situations is respectively calculated, and the corresponding subject can be used as a stakeholder as long as any matching is successful.
Further, the second threshold is determined by:
extracting a plurality of key nodes of the first development trend data, and determining a plurality of first section data and the corresponding relation between each first section data and each second section data in the second development trend data according to the key nodes;
calculating a third matching degree of the first section data and the corresponding second section data, and determining the second threshold value based on the third matching degree;
wherein the second threshold is inversely related to the third degree of matching.
In the embodiment of the invention, the first threshold is a fixed value and can be set based on an empirical value, and the second threshold is a non-fixed value and dynamically changes with different development stages of public sentiment. Specifically, the first development trend data is divided into a plurality of first section data based on the determined key nodes, the corresponding relation between the section data and each second section data of the second development trend data can be determined based on the time relation, then a third matching degree between the section data and each second section data is calculated respectively, the third matching degree refers to goodness of fit in time, for example, the closer the starting point of a certain second section data is to the starting point of a certain first section data, at this time, the higher the relevance between the main body and the section, namely the public sentiment development stage is, the higher the third matching degree is; and finally, determining the size of the second threshold value of different public sentiment development stages based on the negative correlation between the third matching degree and the second threshold value, wherein the higher the third matching degree is, the higher the correlation degree between the corresponding main subject and the public sentiment is (for example, the public sentiment event enters a new development stage just because of the occurrence of the main subject), and at the moment, turning down the second threshold value so as to avoid the main subject being mistakenly identified as a non-interest correlator.
Wherein, for the foregoing description that the third matching degree is determined based on the time distance from the starting point of the second section data to the starting point of the first section data, a further improvement is proposed herein:
judging whether the starting point of the second section data falls into the first section data or not, and if so, determining the third matching degree based on a first proportional relation; if not, determining the third matching degree based on a second proportional relation; wherein the first proportional relationship is weaker than the second proportional relationship.
In this modified mode, the corresponding first segment data and second segment data may not correspond to each other in the time of the start point and the end point completely, but may not correspond to each other in part of the time. In this regard, the present invention employs different scaling relationships to determine the third degree of matching. For the latter condition, the development of the public sentiment event enters a new stage after the occurrence of the corresponding main body, which indicates that the probability that the occurrence of the main body plays a greater role in the development of the public sentiment event is higher, and at this time, a greater proportional relation (such as a proportional coefficient) is adopted to determine a third matching degree; in the former case, the main body appears after the development of the public sentiment event enters a new stage, which means that the main body has a small probability of playing a great role in the development of the public sentiment event, for example, it may be only the reference/mention object of the public sentiment development stage, not the stakeholder, and then a small proportional relationship is used to determine the third matching degree.
Further, the first matching degree and the second matching degree are calculated through a first depth prediction model.
In the embodiment of the present invention, during the development of the public sentiment event, there are various situations of specific characteristics such as the occurrence time and the after-occurrence popularity of each related subject, for example, the subject D appears in the third stage of the public sentiment event, in which the popularity of the subject D is high, but the popularity of the public sentiment event itself may not be obviously different. Therefore, the matching degree of the main development trend data and the development trend data of the public sentiment event is difficult to calculate by using a definite functional relation or a calculation formula.
In view of the above practical difficulties, the present invention employs a depth prediction model to calculate the first degree of matching and the second degree of matching. The depth prediction model may be constructed by algorithms such as Neural Networks (Neural Networks), forward Neural Networks (FNNs), convolutional Neural Networks (CNNs), recurrent Neural Networks (RNNs), recurrent Neural Networks (Recurrent Neural Networks), auto Encoders (Auto Encoders), deep Belief Networks (Deep Belief Networks), and Restricted Boltzmann Machines (corrected Boltzmann Machines), generative adaptive Networks (generic adaptive Networks), graph Neural Networks (Graph Neural Networks), and the like, wherein the CNN and RNN algorithms are preferably used.
The invention trains the first depth prediction model in the following way:
1) A training data set is constructed. The training data in the training data set is obtained by crawling public opinion research and judgment big data in historical public opinion events, the training data exists in a data pair mode, namely < main body, research and judgment data >, the main body is an object appearing in the corresponding historical public opinion events, and all the main bodies are labeled based on manual analysis of the public opinions so as to establish the corresponding relation between the interest correlators and the research and judgment data.
2) And training the first depth prediction model by using the training data set, and finishing the training when the training result meets the specified condition. Wherein, the following loss function is adopted in the training process:
in the formula (I), the compound is shown in the specification,
is a loss function;
is the amount of training data that has been input to the first depth prediction model;
the distance of a front characteristic data matrix and a rear characteristic data matrix taking the appearance moment of the main body as a dividing point in the input training data is calculated;
the first distance between the characteristic data matrix at the appearance moment of the main body and the characteristic data matrix in a first time interval before the appearance moment is the first distance in the output result data corresponding to the input training data;
a second distance between the characteristic data matrix at the appearance moment of the main body and the characteristic data matrix in a second time interval after the appearance moment in the output result data corresponding to the input training data;
to adjust forCoefficients according to the amount of training data that has been input to the first depth prediction model
And determining the proportional relation with the total training data M.
The invention aims to train the first depth prediction model so that the first depth prediction model can be trained to establish a functional relation of the influence of each subject on the research and judgment data, namely the functional relation of the influence of the appearance of the subject on the development trend of the public sentiment. In the training process, input training data is judged data related to each subject (including data of a period of time before and after the subject appears), output data is data which is simulated and reconstructed based on a functional relation established by training, the output data has the same data structure and time node as the previously input training data, and if the difference between the input data and the output data is smaller, the training result is better. Wherein for the adjustment coefficient
According to the amount of training data input to the first depth prediction model
The proportional relation with the total quantity M of the training data is determined, the numerical value is similar to normal distribution, namely the numerical value in the early stage of training is larger, more training can be guided, the numerical value in the later stage of training becomes smaller, the training severity is reduced, unnecessary over-training can be finished in time, and therefore the balance between the training accuracy and the training rapidity is achieved.
Further, the second processing the first data to determine event causality includes:
inputting the first data into a second depth prediction model, the second depth prediction model outputting the event causality;
the event cause-and-effect relationship comprises a stakeholder, a data matrix for describing the event development and time calibration data of the data.
In the embodiment of the invention, similar to the matching degree situation, the causal relationship of the event is difficult to accurately describe by using the determined mathematical function, so the invention still adopts the trained deep prediction model to obtain the causal relationship of the public opinion event. The construction algorithm adopted by the second depth prediction model may be the same as the algorithm adopted by the first depth prediction model, or may also adopt an algorithm combining a neural network algorithm and an attention mechanism.
The event causal relationship output by the second depth prediction model comprises data related to the main body, namely the stakeholder and public sentiment event development, and time calibration data of the data. Examples are as follows:
the causal relationship of events output by the second depth prediction model is shown in the following table:
| t1 | t2 | t3 | t4 | t5 | t6 |
| A1 | A1 | A1 | A1 | ||
| A2 | A2 | A2 | |||
| A3 | A3 | A3 | |||
| A4 | A4 | A4 |
based on the above table, after the first and second processes, the starting point of the public sentiment event is the subject A1, and the subject A2 has a promoting effect on the development of the public sentiment event and finally causes the increase of participating subjects (i.e. A1, A3, A4 are all involved). Therefore, based on the causal relationship, a reputation risk analysis report can be generated, a main body solution structure of the report content may be "main body A1 (data loss) → main body A2 (data loss/unresolved) → main body A2 (crash/attitude difference) → main body A1/A2/A3/A4 (false promotion/attitude difference/data loss \8230;", and then the main body structure and a preset report template are combined to generate a complete reputation risk analysis report, and a method for automatically generating the report is relatively conventional and will not be described herein again. In addition, the above reports are only used for examples and are not used to limit the scope of the present invention, and the specific public sentiment events may involve more subjects and more development mainlines, and the above-mentioned scheme according to the present invention may be adapted.
Example two
Referring to fig. 2, fig. 2 is a schematic structural diagram of a reputation risk localization analysis system according to an embodiment of the present invention. As shown in fig. 2, a reputation risk localization analysis system according to an embodiment of the present invention includes an obtaining module 101, a processing module 102, and a storage module 103; the processing module 102 is connected to the obtaining module 101 and the storage module 103;
the storage module 103 is configured to store executable computer program codes;
the acquisition module 101 is configured to acquire public opinion research and judgment big data and transmit the public opinion research and judgment big data to the processing module 102;
the processing module 102 is configured to execute the method according to any one of the preceding items by calling the executable computer program code in the storage module 103.
The specific functions of the reputation risk positioning analysis system in this embodiment refer to the first embodiment, and since the system in this embodiment adopts all the technical solutions of the first embodiment, at least all the beneficial effects brought by the technical solutions of the first embodiment are achieved, and details are not repeated here.
EXAMPLE III
Referring to fig. 3, fig. 3 is an electronic device according to an embodiment of the present invention, including: a memory storing executable program code; a processor coupled with the memory; the processor calls the executable program code stored in the memory to execute the method according to the first embodiment.
Example four
The embodiment of the invention also discloses a computer storage medium, wherein a computer program is stored on the storage medium, and when the computer program is executed by a processor, the method in the first embodiment is executed.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It should be noted that the foregoing is only a preferred embodiment of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in more detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention.
Claims (10)
1. A reputation risk localization analysis method is characterized by comprising the following steps:
responding to the trigger signal, and acquiring public opinion research and judgment big data;
performing first processing on the public opinion research and judgment big data to determine a plurality of interest correlators and first data corresponding to the interest correlators;
second processing the first data to determine event causality;
and generating and outputting a reputation risk analysis report according to the event causal relationship.
2. The reputation risk localization analysis method according to claim 1, wherein: the trigger signal is generated by:
receiving a risk analysis signal input by a user, and generating the trigger signal according to the risk analysis signal;
alternatively, the first and second liquid crystal display panels may be,
the method comprises the steps of periodically obtaining public sentiment big data related to preset data, carrying out third processing on the public sentiment big data to obtain a plurality of negative topics, and generating a trigger signal when the development trend of any negative topic meets a first preset condition.
3. A reputation risk localization analysis method according to claim 1 or 2, characterized in that: the first processing of the public opinion research and judgment big data to determine a plurality of stakeholders comprises:
calculating first development trend data according to the public opinion research and judgment big data;
determining all related subjects from the public opinion research and judgment big data, and respectively calculating second development trend data according to the first data of each subject;
and calculating the matching degree of each second development trend data and the first development trend data, and taking a subject with the matching degree meeting a second preset condition as the interest-related person.
4. A reputation risk localization analysis method according to claim 3, characterized in that: the matching degree comprises a first matching degree and a plurality of second matching degrees;
the step of taking the subject with the matching degree meeting a second preset condition as the stakeholder includes:
calculating whether the first matching degree is greater than or equal to a first threshold value, and if so, taking the subject as the stakeholder;
if not, calculating whether each second matching degree is greater than or equal to a second threshold, and if at least one second matching degree greater than or equal to the second threshold exists, taking the subject as the stakeholder.
5. The reputation risk localization analysis method according to claim 4, wherein: the second threshold is determined by:
extracting a plurality of key nodes of the first development trend data, and determining a plurality of first section data and the corresponding relation between each first section data and each second section data in the second development trend data according to the key nodes;
calculating a third matching degree of the first section data and the corresponding second section data, and determining the second threshold value based on the third matching degree;
wherein the second threshold is inversely related to the third degree of matching.
6. The reputation risk localization analysis method according to claim 5, wherein: and the first matching degree and the second matching degree are calculated by a first depth prediction model.
7. A reputation risk localization analysis method according to claim 1 or 2 or 4 or 5 or 6, characterized in that: the second processing of the first data to determine event causality comprises:
inputting the first data into a second depth prediction model, the second depth prediction model outputting the event causality;
the event cause and effect relationship comprises a stakeholder, a data matrix for describing event development and time calibration data of the data.
8. A reputation risk positioning analysis system comprises an acquisition module, a processing module and a storage module; the processing module is connected with the acquisition module and the storage module;
the storage module is used for storing executable computer program codes;
the acquisition module is used for acquiring public opinion research and judgment big data and transmitting the public opinion research and judgment big data to the processing module;
the method is characterized in that: the processing module for executing the method according to any one of claims 1-7 by calling the executable computer program code in the storage module.
9. An electronic device, comprising: a memory storing executable program code; a processor coupled with the memory; the method is characterized in that: the processor calls the executable program code stored in the memory to perform the method of any of claims 1-7.
10. A computer storage medium having a computer program stored thereon, characterized in that: the computer program, when executed by a processor, performs the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210989980.7A CN115221416B (en) | 2022-08-18 | 2022-08-18 | Reputation risk positioning analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210989980.7A CN115221416B (en) | 2022-08-18 | 2022-08-18 | Reputation risk positioning analysis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115221416A true CN115221416A (en) | 2022-10-21 |
| CN115221416B CN115221416B (en) | 2023-01-17 |
Family
ID=83615288
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210989980.7A Active CN115221416B (en) | 2022-08-18 | 2022-08-18 | Reputation risk positioning analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115221416B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN110245792A (en) * | 2019-06-03 | 2019-09-17 | 北京清博大数据科技有限公司 | A kind of network public opinion prediction method, device, terminal and storage medium |
| CN110263238A (en) * | 2019-06-21 | 2019-09-20 | 浙江华坤道威数据科技有限公司 | A kind of public sentiment listening system based on big data |
| CN111241300A (en) * | 2020-01-09 | 2020-06-05 | 中信银行股份有限公司 | Public opinion early warning and risk propagation analysis method, system, equipment and storage medium |
| CN112734154A (en) * | 2020-11-16 | 2021-04-30 | 中山大学 | Multi-factor public opinion risk assessment method based on fuzzy number similarity |
| CN114741501A (en) * | 2022-01-21 | 2022-07-12 | 北京金堤科技有限公司 | Public opinion early warning method and device, readable storage medium and electronic equipment |
-
2022
- 2022-08-18 CN CN202210989980.7A patent/CN115221416B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN110245792A (en) * | 2019-06-03 | 2019-09-17 | 北京清博大数据科技有限公司 | A kind of network public opinion prediction method, device, terminal and storage medium |
| CN110263238A (en) * | 2019-06-21 | 2019-09-20 | 浙江华坤道威数据科技有限公司 | A kind of public sentiment listening system based on big data |
| CN111241300A (en) * | 2020-01-09 | 2020-06-05 | 中信银行股份有限公司 | Public opinion early warning and risk propagation analysis method, system, equipment and storage medium |
| CN112734154A (en) * | 2020-11-16 | 2021-04-30 | 中山大学 | Multi-factor public opinion risk assessment method based on fuzzy number similarity |
| CN114741501A (en) * | 2022-01-21 | 2022-07-12 | 北京金堤科技有限公司 | Public opinion early warning method and device, readable storage medium and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 刘雅姝: "多维视角的重大突发事件演变机理及应对策略研究", 《中国博士学位论文全文数据库社会科学Ⅰ辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115221416B (en) | 2023-01-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210232760A1 (en) | Optimization techniques for artificial intelligence | |
| US20220188521A1 (en) | Artificial intelligence-based named entity recognition method and apparatus, and electronic device | |
| US10216832B2 (en) | Underspecification of intents in a natural language processing system | |
| CN104951428B (en) | User's intension recognizing method and device | |
| US20210097410A1 (en) | Recommodation method, recommodation apparatus, electronic device and storage medium | |
| CN110619423A (en) | Multitask prediction method and device, electronic equipment and storage medium | |
| US10282420B2 (en) | Evaluation element recognition method, evaluation element recognition apparatus, and evaluation element recognition system | |
| CN109461446B (en) | Method, device, system and storage medium for identifying user target request | |
| US20200278976A1 (en) | Method and device for evaluating comment quality, and computer readable storage medium | |
| US20180107953A1 (en) | Content delivery method, apparatus, and storage medium | |
| CN113360711B (en) | Model training and executing method, device, equipment and medium for video understanding task | |
| CN115129848A (en) | Method, device, equipment and medium for processing visual question-answering task | |
| CN110717027B (en) | Multi-round intelligent question-answering method, system, controller and medium | |
| CN111931494B (en) | Method, apparatus, electronic device, and medium for generating prediction information | |
| CN113743522A (en) | Detection method and device for illegal behavior and electronic equipment | |
| CN110502635B (en) | Information quality evaluation method and device | |
| CN112995690A (en) | Live content item identification method and device, electronic equipment and readable storage medium | |
| CN115221416B (en) | Reputation risk positioning analysis method and system | |
| CN114970666A (en) | Spoken language processing method and device, electronic equipment and storage medium | |
| CN112788356B (en) | Live broadcast auditing method, device, server and storage medium | |
| CN111026991B (en) | Data display method and device and computer equipment | |
| CN114692778A (en) | Multi-modal sample set generation method, training method and device for intelligent inspection | |
| CN110852043B (en) | Text transcription method, device, equipment and storage medium | |
| CN109697260B (en) | Virtual currency detection method and device, computer equipment and storage medium | |
| CN116187094B (en) | Quality work prediction system based on real-time analysis of working conditions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 210 Liangjing Road, China (Shanghai) pilot Free Trade Zone, Pudong New Area, Shanghai, 201203 Patentee after: Shanghai Jinshida Software Technology Co.,Ltd. Address before: 210 Liangjing Road, China (Shanghai) pilot Free Trade Zone, Pudong New Area, Shanghai, 201203 Patentee before: Shanghai Kingstar Software Technology Co.,Ltd. |