CN114417830A - Risk evaluation method, device, equipment and computer readable storage medium - Google Patents
Risk evaluation method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN114417830A CN114417830A CN202210100199.XA CN202210100199A CN114417830A CN 114417830 A CN114417830 A CN 114417830A CN 202210100199 A CN202210100199 A CN 202210100199A CN 114417830 A CN114417830 A CN 114417830A
- Authority
- CN
- China
- Prior art keywords
- event
- public sentiment
- public
- risk
- risk evaluation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application provides a risk evaluation method, a risk evaluation device, risk evaluation equipment and a computer-readable storage medium. The risk evaluation method comprises the steps of obtaining public sentiment events of risk evaluation objects in a preset time period; determining public sentiment events with the attention degree greater than or equal to a preset attention degree threshold value as first public sentiment events, and determining public sentiment events with the attention degree smaller than the preset attention degree threshold value as second public sentiment events; classifying the second public opinion event based on the attention degree to obtain a plurality of grades of the second public opinion event; determining the second public sentiment event with the occurrence probability larger than a preset probability threshold value as a third public sentiment event in each level of the second public sentiment event; and evaluating the risk value of the risk evaluation object based on the first public sentiment event and the third public sentiment event. According to the method and the device, the determined risk value can be more accurate.
Description
Technical Field
The present application belongs to the field of computer technologies, and in particular, to a risk evaluation method, apparatus, device, and computer-readable storage medium.
Background
With the progress of society, the economy of society is rapidly developing. With the rapid development of economy, the economic exchange between different individuals is also becoming more intimate.
In the current economic transaction, the risk value of the economic transaction object is reference data which cannot be ignored in the process of the economic transaction. In the process of determining the risk value of the economic object, the public sentiment event is also an indispensable important influence factor.
In the current process of determining the risk value of the economic transaction object through the public sentiment event, the adopted public sentiment event is single, so that the risk value determined through the single public sentiment event is not accurate.
Disclosure of Invention
The embodiment of the application provides a risk evaluation method, a risk evaluation device, a risk evaluation equipment and a computer storage medium, so that the determined risk value is more accurate.
In a first aspect, an embodiment of the present application provides a risk evaluation method, including:
acquiring public sentiment events of risk evaluation objects in a preset time period;
determining public sentiment events with the attention degree greater than or equal to a preset attention degree threshold value as first public sentiment events, and determining public sentiment events with the attention degree smaller than the preset attention degree threshold value as second public sentiment events;
classifying the second public opinion event based on the attention degree to obtain a plurality of grades of the second public opinion event;
determining the second public sentiment event with the occurrence probability larger than a preset probability threshold value as a third public sentiment event in each level of the second public sentiment event;
and evaluating the risk value of the risk evaluation object based on the first public sentiment event and the third public sentiment event.
In some embodiments, after determining the second public sentiment event with the occurrence probability greater than a preset probability threshold as the third public sentiment event, the method further comprises: determining a first weight value corresponding to each level of public sentiment events in the second public sentiment events based on a first preset rule;
weighting the third public opinion event based on the first weight value to obtain a first weighting result;
evaluating the risk value of the risk evaluation object based on the first public sentiment event and the third public sentiment event, specifically comprising:
and evaluating the risk value of the risk evaluation object based on the first public sentiment event and the first weighting result.
In some embodiments, after determining the second public sentiment event with the occurrence probability greater than a preset probability threshold as the third public sentiment event, the method further comprises:
classifying the third public sentiment event to obtain a first system public sentiment event and a first individual public sentiment event;
weighting the first system public opinion event and the first individual public opinion event respectively based on a predetermined system risk factor and an individual risk factor to obtain a second weighting result;
evaluating the risk value of the risk evaluation object based on the first public sentiment event and the third public sentiment event, specifically comprising:
and evaluating the risk value of the risk evaluation object based on the first public sentiment event and the second weighting result.
In some embodiments, after determining a public opinion event with a degree of attention greater than or equal to a preset degree of attention threshold as a first public opinion event, the method further comprises:
classifying the first public opinion event based on a preset classification rule to obtain a plurality of grades of the first public opinion event;
determining a second weight value corresponding to each level of public sentiment events in the first public sentiment events based on a second preset rule;
weighting the first public sentiment event based on the second weight value to obtain a third weighting result;
evaluating the risk value of the risk evaluation object based on the first public sentiment event and the third public sentiment event, specifically comprising:
and evaluating the risk value of the risk evaluation object based on the third weighting result and the third public sentiment event.
In some embodiments, after determining a public opinion event with a degree of attention greater than or equal to a preset degree of attention threshold as a first public opinion event, the method further comprises:
classifying the first public sentiment event to obtain a second system public sentiment event and a second individual public sentiment event;
weighting the second system public opinion event and the second individual public opinion event respectively based on a predetermined system risk factor and an individual risk factor to obtain a fourth weighting result;
evaluating the risk value of the risk evaluation object based on the first public sentiment event and the third public sentiment event, specifically comprising:
and evaluating the risk value of the risk evaluation object based on the fourth weighting result and the third public sentiment event.
In some embodiments, the evaluating the risk value of the risk evaluation object based on the first public sentiment event and the third public sentiment event specifically includes:
and inputting the first public sentiment event and the target public sentiment event into the trained risk evaluation model to obtain a risk value of the target risk evaluation object.
In a second aspect, an embodiment of the present application provides a risk assessment apparatus, including:
the acquisition module is used for acquiring public sentiment events of the risk evaluation object in a preset time period;
the first determining module is used for determining the public sentiment event of which the attention degree is greater than or equal to a preset attention degree threshold value as a first public sentiment event, and determining the public sentiment event of which the attention degree is less than the preset attention degree threshold value as a second public sentiment event;
the first grading module is used for grading the second public opinion event based on the attention degree to obtain a plurality of grades of the second public opinion event;
the second determining module is used for determining the second public sentiment event of which the occurrence probability is greater than a preset probability threshold value as a third public sentiment event in each level of the second public sentiment event;
and the evaluation module is used for evaluating the risk value of the risk evaluation object based on the first public sentiment event and the third public sentiment event.
In some embodiments, the risk assessment device further comprises:
the third determining module is used for determining a first weight value corresponding to each level of public sentiment events in the second public sentiment events based on the first preset rule after the second public sentiment events with the occurrence probability larger than the preset probability threshold are determined as the third public sentiment events;
the first weighting module is used for weighting the third public opinion event based on the first weight value to obtain a first weighting result;
the first evaluation module specifically comprises:
and the first evaluation unit is used for evaluating the risk value of the risk evaluation object based on the first public sentiment event and the first weighting result.
In some embodiments, the risk assessment device further comprises:
the first classification module is used for classifying a third public opinion event after the second public opinion event with the occurrence probability larger than a preset probability threshold is determined as the third public opinion event to obtain a first system public opinion event and a first individual public opinion event;
the second weighting module is used for weighting the first system public opinion event and the first individual public opinion event respectively based on a predetermined system risk factor and an individual risk factor to obtain a second weighting result;
the first evaluation module specifically comprises:
and the second evaluation unit is used for evaluating the risk value of the risk evaluation object based on the first public sentiment event and the second weighting result.
In some embodiments, the risk assessment device further comprises:
the second grading module is used for grading the first public sentiment event based on a preset grading rule after the public sentiment event of which the attention degree is greater than or equal to a preset attention degree threshold value is determined as the first public sentiment event, so as to obtain a plurality of grades of the first public sentiment event;
the fourth determining module is used for determining a second weight value corresponding to each level of public sentiment events in the first public sentiment events based on a second preset rule;
the third weighting module is used for weighting the first public sentiment event based on the second weight value to obtain a third weighting result;
the first evaluation module specifically comprises:
and the third evaluation unit is used for evaluating the risk value of the risk evaluation object based on the third weighting result and the third public sentiment event.
In some embodiments, the risk assessment device further comprises:
the second classification module is used for classifying the first public sentiment event after the public sentiment event of which the attention degree is greater than or equal to the preset attention degree threshold is determined as the first public sentiment event, so as to obtain a second system public sentiment event and a second individual public sentiment event;
the fourth weighting module is used for weighting the second system public opinion event and the second individual public opinion event respectively based on the predetermined system risk factor and the individual risk factor to obtain a fourth weighting result;
the first evaluation module specifically comprises:
and the fourth evaluation unit is used for evaluating the risk value of the risk evaluation object based on the fourth weighting result and the third public sentiment event.
In some embodiments, the first evaluation module specifically comprises:
and the fifth evaluation unit is used for inputting the first public sentiment event and the target public sentiment event into the trained risk evaluation model to obtain the risk value of the target risk evaluation object.
In a third aspect, an embodiment of the present application provides an electronic device, including: a processor and a memory storing computer program instructions;
the steps of the risk assessment method as in any of the embodiments of the first aspect are implemented when the processor executes the computer program instructions.
In a fourth aspect, the present application provides a computer-readable storage medium, on which computer program instructions are stored, and when executed by a processor, the computer program instructions implement the steps of the risk assessment method in any one of the embodiments of the first aspect.
In a fifth aspect, the present application provides a computer program product, and instructions in the computer program product, when executed by a processor of an electronic device, enable the electronic device to perform the risk assessment method as in any one of the embodiments of the first aspect.
After public opinions of a risk evaluation object in a preset time period are obtained, the public opinion events with the attention degree greater than or equal to the attention degree threshold value are determined as first public opinion events, and the public opinion events with the attention degree smaller than the attention degree threshold value are determined as second public opinion events. And then, classifying the second public sentiment event according to the attention degree to obtain a plurality of grades of the second public sentiment event, determining the second public sentiment event with the occurrence probability larger than a preset probability threshold value in each grade of the second public sentiment event as a third public sentiment event, and then evaluating the risk value of the risk evaluation object according to the first public sentiment event and the third public sentiment event. The public sentiment events are classified into a first public sentiment event and a second public sentiment event according to the attention threshold, and then the second public sentiment event is screened according to the occurrence probability, so that a third public sentiment event is screened. And then evaluating the risk value of the risk evaluation object according to the first public sentiment event and the third public sentiment event, so that the public sentiments with different attention degrees and different occurrence probabilities are adopted in the process of evaluating the risk of the risk evaluation object according to the public sentiments, and further, the risk evaluation of the risk evaluation object through the public sentiments with different attention degrees and different occurrence probabilities can be more accurate.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart diagram illustrating one embodiment of a risk assessment method provided herein;
FIG. 2 is a schematic structural diagram of an embodiment of a risk assessment device provided herein;
fig. 3 is a schematic hardware structure diagram of an embodiment of an electronic device provided in the present application.
Detailed Description
Features and exemplary embodiments of various aspects of the present application will be described in detail below, and in order to make objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are intended to be illustrative only and are not intended to be limiting. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present application by illustrating examples thereof.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
In the current process of using public sentiment events to carry out risk evaluation on risk evaluation objects, the public sentiment events with higher attention are generally adopted, but the public sentiment events have concealment and accumulation, and some public sentiment events with lower attention often cause larger risks after long-term accumulation. Therefore, the risk evaluation of the risk evaluation object using the public sentiment event is not accurate at present.
In order to solve the problems of the prior art, embodiments of the present application provide a risk evaluation method, apparatus, device, and computer-readable storage medium.
First, a risk evaluation method provided in the embodiment of the present application is described below.
Fig. 1 shows a schematic flow chart of an embodiment of a risk assessment method provided by the present application. As shown in fig. 1, the method may include the steps of:
s110, acquiring public sentiment events of risk evaluation objects in a preset time period;
s120, determining a public sentiment event of which the attention degree is greater than or equal to a preset attention degree threshold value as a first public sentiment event, and determining a public sentiment event of which the attention degree is less than the preset attention degree threshold value as a second public sentiment event;
s130, classifying the second public opinion event based on the attention degree to obtain a plurality of grades of the second public opinion event;
s140, in each level of the second public sentiment event, determining the second public sentiment event of which the occurrence probability is greater than a preset probability threshold value as a third public sentiment event;
and S150, evaluating the risk value of the risk evaluation object based on the first public sentiment event and the third public sentiment event.
Therefore, after public opinions of the risk evaluation object in a preset time period are acquired, the public opinion events with the attention degree greater than or equal to the attention degree threshold value are determined as first public opinion events, and the public opinion events with the attention degree smaller than the attention degree threshold value are determined as second public opinion events. And then, classifying the second public sentiment event according to the attention degree to obtain a plurality of grades of the second public sentiment event, determining the second public sentiment event with the occurrence probability larger than a preset probability threshold value in each grade of the second public sentiment event as a third public sentiment event, and then evaluating the risk value of the risk evaluation object according to the first public sentiment event and the third public sentiment event. The public sentiment events are classified into a first public sentiment event and a second public sentiment event according to the attention threshold, and then the second public sentiment event is screened according to the occurrence probability, so that a third public sentiment event is screened. And then evaluating the risk value of the risk evaluation object according to the first public sentiment event and the third public sentiment event, wherein the public sentiments with different attention degrees and different occurrence probabilities are adopted in the process of evaluating the risk of the risk evaluation object according to the public sentiments, and further, the risk evaluation of the risk evaluation object through the public sentiments with different attention degrees and different occurrence probabilities can be more accurate.
In some embodiments, in S110, the preset time period may include a current time period or a historical time period. The public sentiment events may include news events associated with the operation of the risk assessment object and may also include news events associated with the risk value of the risk assessment object.
In some embodiments, the risk evaluation device may identify and search public sentiment events based on Natural Language Processing (NLP) to obtain the public sentiment events within a preset time period.
In some embodiments, the attention may include a click rate, a search amount, or a collection amount of public opinion events for the public within a preset time period in S120. The first public sentiment event may include a public sentiment event with a higher degree of attention. The second public sentiment event may include a public sentiment event with a lower degree of attention. The first public opinion event and the second public opinion event can be distinguished based on a user-defined attention threshold.
In some embodiments, the second public sentiment event may further include a noisy public sentiment event deviating from a reference value, wherein the reference value may include a reference value currently used in an evaluation process of a risk value of a risk evaluation object based on the public sentiment event.
In some embodiments, ranking the second public opinion event based on the degree of attention size in S130 may include dividing the second public opinion event into a plurality of levels based on correspondence of the degree of attention set by the user to the second public opinion event of different levels.
In some embodiments, in S140, after obtaining a plurality of levels of the second public opinion events, the risk evaluation device may screen the second public opinion events according to a preset probability threshold in each level of the second public opinion events. In some specific examples, in each level, a second public sentiment event with an occurrence probability greater than a preset probability threshold in the level may be determined as a third public sentiment event in the level.
In some embodiments, S150 may specifically include:
and inputting the first public sentiment event and the third public sentiment event into the trained risk evaluation model to obtain a risk value of the target risk evaluation object.
In some embodiments, the risk assessment method may further comprise, before S150:
and training the risk evaluation model based on multiple groups of training samples to obtain the trained risk evaluation model. Wherein each set of training samples may include: historical first public sentiment events and historical third public sentiment events and historical risk values corresponding to the historical first public sentiment events and the historical third public sentiment events;
in some embodiments, training the risk assessment model based on the sets of training samples may include:
for each group of training samples, the following steps are respectively carried out:
inputting each group of training samples into a risk evaluation model to obtain a predicted risk value corresponding to a historical first public sentiment event and a historical third public sentiment event;
determining a loss function value of the risk evaluation model according to the predicted risk value and the historical risk value;
and under the condition that the loss function value does not meet the training stopping condition, adjusting model parameters of the risk evaluation model, training the risk evaluation model after parameter adjustment by using the training sample until the training stopping condition is met, and obtaining the trained risk evaluation model.
Here, the training stop condition may include a condition set by a user, and for example, the training stop condition may include that the loss function value is less than a certain threshold or the number of training iterations reaches a certain specific value.
Therefore, the trained risk evaluation model can determine the risk value of the risk evaluation object more accurately in the subsequent determination of the risk value of the risk evaluation object by training the risk evaluation model in advance. In some embodiments, in order to make the risk assessment of the risk assessment object more accurate, after S120, the risk assessment method may further include:
classifying the first public opinion event based on a preset classification rule to obtain a plurality of grades of the first public opinion event;
determining a second weight value corresponding to each level of public sentiment events in the first public sentiment events based on a second preset rule;
and weighting the first public opinion event based on the second weight value to obtain a third weighting result.
In some embodiments, the preset rating rules may include user-defined rating rules.
In some specific examples, the first public opinion event can be classified according to the attention degree size, and the obtained multiple levels of the first public opinion event can be obtained.
In some embodiments, the second preset rule may include correspondence between public sentiment events of different levels and different weight values, which are set by a user in a customized manner.
In some specific examples, the weight value positively correlated to the attention degree may be determined according to the attention degree of the public sentiment events of different levels.
In some embodiments, the second weight value may include a plurality of weight values, and the first public sentiment event may include a plurality of levels of the first public sentiment event. Weighting the first public opinion event based on the second weight value may include:
and taking the product of the second weight values and the public sentiment events of the first public sentiment events corresponding to the second weight values as a third weighting result.
In some embodiments, the risk evaluation device may determine the acquired public opinion events as the first public opinion event and the second public opinion event based on a degree of attention threshold value set by a user.
In some embodiments, after obtaining the third weighting result, the step S140 may specifically include:
and evaluating the risk value of the risk evaluation object based on the third weighting result and the third public sentiment event.
Therefore, the first public sentiment event obtained after the public sentiment events are classified according to the attention threshold is divided into a plurality of levels of the first public sentiment event based on a second preset rule, and then the first public sentiment event after classification is weighted respectively according to a preset weight value to obtain a third weighting result. And then evaluating the risk value of the risk evaluation object according to the third weighting result and the third public sentiment event. The first public opinion event is divided into a plurality of levels, the first public opinion event after the levels are divided is weighted, the risk evaluation object is subjected to risk evaluation by using the weighting result, the utilized public opinion event is more accurate, the data volume is larger, and further, the risk evaluation on the risk evaluation object is more accurate in the risk evaluation process of the risk evaluation object by using the public opinion event.
In some embodiments, in order to make the risk assessment of the risk assessment object more accurate, after S120, the risk assessment method may further include:
classifying the first public sentiment event to obtain a second system public sentiment event and a second individual public sentiment event;
and respectively weighting the second system public opinion event and the second individual public opinion event based on the predetermined system risk factor and the predetermined individual risk factor to obtain a fourth weighting result.
In some embodiments, the first public opinion event may be divided into a second system public opinion event and a second individual public opinion event based on risk concepts in system risk or economics. The dividing of the first public opinion event into the second system public opinion event and the second individual public opinion event based on the risk concept in the system risk science or the economics is a conventional technical means in the art, and is not described herein again.
In some embodiments, the second system public sentiment event may include a public sentiment event existing in a majority of individuals in the same kind of system where the risk assessment object is located as the risk assessment object. The second individual public sentiment event may include a public sentiment event in which the risk evaluation object exists alone in the same kind of system as the risk evaluation object in which the risk evaluation object is located.
In some specific examples, the system risk is a risk existing in a system where the risk evaluation object is located, and the individual risk is a risk existing only in the risk evaluation object alone in the system where the risk evaluation object is located, so that the system risk factor may be set to be larger than the individual risk factor.
In some embodiments, the risk evaluation device may classify the first public opinion event to obtain a second system public opinion event and a second individual public opinion event, and then weight the classified second system public opinion event and the second individual public opinion event respectively based on a predetermined system risk factor and an individual risk factor to obtain a fourth weighted result.
In some embodiments, after obtaining the fourth weighting result, the step S140 may include:
and evaluating the risk value of the risk evaluation object based on the fourth weighting result and the third public sentiment event.
Therefore, the first public opinion event is classified according to the difference between the system and the individual to obtain a second system public opinion event and a second individual public opinion event, and then the second system public opinion event and the second individual public opinion event are weighted respectively according to a preset system risk factor and an individual risk factor to obtain a fourth weighting result. And then evaluating the risk value of the risk evaluation object according to the fourth weighting result and the third public sentiment event. Since the first public sentiment event is classified into the second system public sentiment event and the second individual public sentiment event, then the second system public sentiment event and the second individual public sentiment event are weighted, in the process of risk evaluation of the risk evaluation object according to the public sentiments, the corresponding weight values of the first public sentiment events of different types are determined, then the risk value of the risk evaluation object is evaluated, and the risk evaluation of the risk evaluation object through the public sentiment events of different attention degrees and different occurrence probabilities can be more accurate.
In some embodiments, after S140, the risk assessment method may further include:
determining a first weight value corresponding to each level of public sentiment events in the second public sentiment events based on a first preset rule;
weighting the third public opinion event based on the first weight value to obtain a first weighting result;
evaluating the risk value of the risk evaluation object based on the first public sentiment event and the third public sentiment event, specifically comprising:
and evaluating the risk value of the risk evaluation object based on the first public sentiment event and the first weighting result.
In some embodiments, the first preset rule may include a rule set by a user in a self-defined manner, in some specific examples, the second public opinion event is classified into a plurality of levels according to the attention degree, so that the attention degree corresponding to each level is different, and the first weight value corresponding to each level may be set according to the attention degree, for example, the weight value corresponding to each level of the second public opinion is positively correlated to the first weight value.
In some embodiments, the risk evaluation device may set, after acquiring the second public opinion event, a first preset rule according to user definition to set each level of the second public opinion event after ranking, to a first weight value corresponding to each level.
In some embodiments, the third public sentiment event may include a plurality of levels of the third public sentiment event obtained by ranking in the above step, and a weight value corresponding to each level has been established in the above step.
In some embodiments, a product of the third public sentiment event corresponding to each level and the first weight value corresponding to the low level may be used as the first weighting result.
In some embodiments, after obtaining the first weighting result, the step S140 may specifically include:
and evaluating the risk value of the risk evaluation object based on the first public sentiment event and the first weighting result.
Therefore, corresponding weight values are set for a plurality of levels of the second public sentiment event obtained after grading, and then the weighting result of the third public sentiment event corresponding to each level and the weight values is used as reference data for evaluating the risk evaluation object. Since the third public sentiment event with higher occurrence probability in the second public sentiment events and the weighted value corresponding to the third public sentiment event are used as the reference data for risk evaluation of the risk evaluation object, screening of the third public sentiment event with higher occurrence probability in the second public sentiment events with lower attention is substantially completed, and then the third public sentiment event with higher occurrence probability in the first public sentiment event with higher attention and the second public sentiment event with lower attention is used as the reference data for risk evaluation of the risk evaluation object, the quantity of the parameter data can be increased in the process of risk evaluation of the risk evaluation object, and the types of the reference data are enriched. Further, the risk evaluation value of the risk evaluation object based on a larger number and a richer variety can be made more accurate.
In some embodiments, in order to make the risk assessment value of the risk assessment target more accurate, after S140, the risk assessment method may further include:
classifying the third public sentiment event to obtain a first system public sentiment event and a first individual public sentiment event;
weighting the first system public opinion event and the first individual public opinion event respectively based on a predetermined system risk factor and an individual risk factor to obtain a second weighting result;
evaluating the risk value of the risk evaluation object based on the first public sentiment event and the third public sentiment event, specifically comprising:
and evaluating the risk value of the risk evaluation object based on the first public sentiment event and the second weighting result.
In some embodiments, the method for classifying the third public sentiment event into the first system public sentiment event and the first physical public sentiment event may be the same as the method for classifying the first public sentiment event into the second system public sentiment event and the second physical public sentiment event in the above steps, and will not be described herein again.
In some embodiments, the system risk factor and the individual risk factor in this embodiment are the same as the system risk factor and the individual risk factor in the above steps, and are not described herein again.
In some embodiments, after obtaining the second weighting result, the S140 may include:
and evaluating the risk value of the risk evaluation object based on the first public sentiment event and the second weighting result.
Therefore, the third public opinion event is classified according to the difference between the system and the individual to obtain a first system public opinion event and a first individual public opinion event, and then the first system public opinion event and the first individual public opinion event are weighted respectively according to a preset system risk factor and an individual risk factor to obtain a fourth weighting result. And then evaluating the risk value of the risk evaluation object according to the second weighting result and the first public sentiment event. Since the third public sentiment event is classified into the first system public sentiment event and the first individual public sentiment event, then the first system public sentiment event and the first individual public sentiment event are weighted, in the process of risk evaluation of the risk evaluation object according to the public sentiments, the third public sentiment events of different types are determined with corresponding weight values, then the risk value of the risk evaluation object is evaluated, and the risk evaluation of the risk evaluation object through the public sentiment events of different attention degrees and different occurrence probabilities can be more accurate.
It should be noted that the application scenarios described in the foregoing disclosure are for more clearly illustrating the technical solutions of the embodiments of the disclosure, and do not constitute a limitation of the technical solutions provided in the embodiments of the disclosure, and as a person of ordinary skill in the art knows new application scenarios, the technical solutions provided in the embodiments of the disclosure are also applicable to similar technical problems.
Based on the same inventive concept, the embodiment of the present application further provides a risk evaluation device, and the risk evaluation device provided by the embodiment of the present application is described in detail below with reference to fig. 2.
Fig. 2 is a schematic structural diagram of an embodiment of a risk assessment apparatus 200 provided in the present application, and as shown in fig. 2, the apparatus may include:
an obtaining module 201, configured to obtain a public sentiment event of a risk evaluation object within a preset time period;
a first determining module 202, configured to determine a public sentiment event of which the attention degree is greater than or equal to a preset attention degree threshold as a first public sentiment event, and determine a public sentiment event of which the attention degree is less than the preset attention degree threshold as a second public sentiment event;
the first grading module 203 is used for grading the second public opinion event based on the attention degree to obtain a plurality of grades of the second public opinion event;
a second determining module 204, configured to determine, in each level of the second public sentiment event, the second public sentiment event of which the occurrence probability is greater than a preset probability threshold as a third public sentiment event;
and the evaluation module 205 is used for evaluating the risk value of the risk evaluation object based on the first public sentiment event and the third public sentiment event.
After public opinions of the risk evaluation object in a preset time period are obtained, the public opinion events with the attention degree being larger than or equal to the attention degree threshold value are determined as first public opinion events, and the public opinion events with the attention degree being smaller than the attention degree threshold value are determined as second public opinion events. And then, classifying the second public sentiment event according to the attention degree to obtain a plurality of grades of the second public sentiment event, determining the second public sentiment event with the occurrence probability larger than a preset probability threshold value in each grade of the second public sentiment event as a third public sentiment event, and then evaluating the risk value of the risk evaluation object according to the first public sentiment event and the third public sentiment event. The public sentiment events are classified into a first public sentiment event and a second public sentiment event according to the attention threshold, and then the second public sentiment event is screened according to the occurrence probability, so that a third public sentiment event is screened. And then evaluating the risk value of the risk evaluation object according to the first public sentiment event and the third public sentiment event, so that the public sentiments with different attention degrees and different occurrence probabilities are adopted in the process of evaluating the risk of the risk evaluation object according to the public sentiments, and further, the risk evaluation of the risk evaluation object through the public sentiments with different attention degrees and different occurrence probabilities can be more accurate.
In some embodiments, in order to make the risk evaluation value of the risk evaluation target more accurate, the risk evaluation device may further include:
the third determining module may be configured to determine, after determining a second public sentiment event with an occurrence probability greater than a preset probability threshold as a third public sentiment event, a first weight value corresponding to each level of public sentiment events in the second public sentiment event based on a first preset rule;
the first weighting module may be configured to weight the third public opinion event based on the first weight value to obtain a first weighting result;
the first evaluation module may specifically include:
the first evaluation unit may be configured to evaluate a risk value of the risk evaluation object based on the first public opinion event and the first weighting result.
Therefore, corresponding weight values are set for a plurality of levels of the second public sentiment event obtained after grading, and then the weighting result of the third public sentiment event corresponding to each level and the weight values is used as reference data for evaluating the risk evaluation object. Since the third public sentiment event with higher occurrence probability in the second public sentiment events and the weighted value corresponding to the third public sentiment event are used as the reference data for risk evaluation of the risk evaluation object, screening of the third public sentiment event with higher occurrence probability in the second public sentiment events with lower attention is substantially completed, and then the third public sentiment event with higher occurrence probability in the first public sentiment event with higher attention and the second public sentiment event with lower attention is used as the reference data for risk evaluation of the risk evaluation object, the quantity of the parameter data can be increased in the process of risk evaluation of the risk evaluation object, and the types of the reference data are enriched. Further, the risk evaluation value of the risk evaluation object based on a larger number and a richer variety can be made more accurate.
In some embodiments, in order to make the risk evaluation value of the risk evaluation object more accurate, the risk evaluation device may further include:
the first classification module is used for classifying a third public opinion event after determining the second public opinion event with the occurrence probability greater than a preset probability threshold as the third public opinion event to obtain a first system public opinion event and a first individual public opinion event;
the second weighting module is used for weighting the first system public opinion event and the first individual public opinion event respectively based on a predetermined system risk factor and an individual risk factor to obtain a second weighting result;
the first evaluation module may specifically include:
and the second evaluation unit can be used for evaluating the risk value of the risk evaluation object based on the first public sentiment event and the second weighting result.
Therefore, the third public opinion event is classified according to the difference between the system and the individual to obtain a first system public opinion event and a first individual public opinion event, and then the first system public opinion event and the first individual public opinion event are weighted respectively according to a preset system risk factor and an individual risk factor to obtain a fourth weighting result. And then evaluating the risk value of the risk evaluation object according to the second weighting result and the first public sentiment event. Since the third public sentiment event is classified into the first system public sentiment event and the first individual public sentiment event, then the first system public sentiment event and the first individual public sentiment event are weighted, in the process of risk evaluation of the risk evaluation object according to the public sentiments, the third public sentiment events of different types are determined with corresponding weight values, then the risk value of the risk evaluation object is evaluated, and the risk evaluation of the risk evaluation object through the public sentiment events of different attention degrees and different occurrence probabilities can be more accurate.
In some embodiments, in order to make the risk assessment of the risk assessment object more accurate, the risk assessment apparatus may further include:
the second grading module is used for grading the first public opinion event based on a preset grading rule to obtain a plurality of grades of the first public opinion event after the public opinion event with the attention degree greater than or equal to the preset attention degree threshold is determined as the first public opinion event;
the fourth determining module may be configured to determine, based on a second preset rule, a second weight value corresponding to each level of public sentiment events in the first public sentiment events;
the third weighting module may be configured to weight the first public opinion event based on the second weight value to obtain a third weighting result;
the first evaluation module may specifically include:
and the third evaluation unit can be used for evaluating the risk value of the risk evaluation object based on the third weighting result and the third public opinion event.
Therefore, the first public sentiment event obtained after the public sentiment events are classified according to the attention threshold is divided into a plurality of levels of the first public sentiment event based on a second preset rule, and then the first public sentiment event after classification is weighted respectively according to a preset weight value to obtain a third weighting result. And then evaluating the risk value of the risk evaluation object according to the third weighting result and the third public sentiment event. The first public opinion event is divided into a plurality of levels, the first public opinion event after the levels are divided is weighted, the risk evaluation object is subjected to risk evaluation by using the weighting result, the utilized public opinion event is more accurate, the data volume is larger, and further, the risk evaluation on the risk evaluation object is more accurate in the risk evaluation process of the risk evaluation object by using the public opinion event.
In some embodiments, in order to make the risk assessment of the risk assessment object more accurate, the risk assessment apparatus may further include:
the second classification module is used for classifying the first public sentiment event after the public sentiment event of which the attention degree is greater than or equal to the preset attention degree threshold is determined as the first public sentiment event to obtain a second system public sentiment event and a second individual public sentiment event;
the fourth weighting module may be configured to weight the second system public opinion event and the second individual public opinion event respectively based on a predetermined system risk factor and an individual risk factor, so as to obtain a fourth weighting result;
the first evaluation module may specifically include:
and the fourth evaluation unit can be used for evaluating the risk value of the risk evaluation object based on the fourth weighting result and the third public opinion event.
Therefore, the first public opinion event is classified according to the difference between the system and the individual to obtain a second system public opinion event and a second individual public opinion event, and then the second system public opinion event and the second individual public opinion event are weighted respectively according to a preset system risk factor and an individual risk factor to obtain a fourth weighting result. And then evaluating the risk value of the risk evaluation object according to the fourth weighting result and the third public sentiment event. Since the first public sentiment event is classified into the second system public sentiment event and the second individual public sentiment event, then the second system public sentiment event and the second individual public sentiment event are weighted, in the process of risk evaluation of the risk evaluation object according to the public sentiments, the corresponding weight values of the first public sentiment events of different types are determined, then the risk value of the risk evaluation object is evaluated, and the risk evaluation of the risk evaluation object through the public sentiment events of different attention degrees and different occurrence probabilities can be more accurate.
In some embodiments, the first evaluation module may specifically include:
and the fifth evaluation unit can be used for inputting the first public opinion event and the target public opinion event into the trained risk evaluation model to obtain the risk value of the target risk evaluation object.
Therefore, the trained risk evaluation model can determine the risk value of the risk evaluation object more accurately in the subsequent determination of the risk value of the risk evaluation object by training the risk evaluation model in advance.
Fig. 3 shows a hardware structure diagram of an embodiment of the electronic device provided in the present application.
The electronic device 300 may comprise a processor 301 and a memory 302 in which computer program instructions are stored.
Specifically, the processor 301 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.
The memory may include Read Only Memory (ROM), Random Access Memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical/tangible memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software comprising computer-executable instructions and when the software is executed (e.g., by one or more processors), it is operable to perform operations described with reference to the methods according to an aspect of the application.
The processor 301 implements any of the risk assessment methods in the above embodiments by reading and executing computer program instructions stored in the memory 302.
In some examples, electronic device 300 may also include a communication interface 303 and a bus 310. As shown in fig. 3, the processor 301, the memory 302, and the communication interface 303 are connected via a bus 310 to complete communication therebetween.
The communication interface 303 may be mainly used for implementing communication between modules, apparatuses, units and/or devices in the embodiments of the present application.
Illustratively, as the payment terminal, the electronic device 300 may be a mobile phone, a tablet computer, a notebook computer, a palm top computer, a vehicle-mounted electronic device, an ultra-mobile personal computer (UMPC), a netbook or a Personal Digital Assistant (PDA), and the like. As the code scanning terminal, the electronic device 300 may be a Point of sale (POS), a code scanner, or the like.
The electronic device may execute the risk evaluation method in the embodiment of the present application, so as to implement the risk evaluation method and apparatus described in conjunction with fig. 1 to 2.
In addition, in combination with the risk evaluation method in the foregoing embodiments, the embodiments of the present application may be implemented by providing a computer-readable storage medium. The computer readable storage medium having stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement any of the risk assessment methods in the above embodiments. Examples of computer-readable storage media include non-transitory computer-readable storage media such as portable disks, hard disks, Random Access Memories (RAMs), Read Only Memories (ROMs), erasable programmable read only memories (EPROMs or flash memories), portable compact disk read only memories (CD-ROMs), optical storage devices, magnetic storage devices, and so forth.
It is to be understood that the present application is not limited to the particular arrangements and instrumentality described above and shown in the attached drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions or change the order between the steps after comprehending the spirit of the present application.
The functional blocks shown in the above structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the present application are programs or code segments that may be used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
Aspects of the present application are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware for performing the specified functions or acts, or combinations of special purpose hardware and computer instructions.
As will be apparent to those skilled in the art, for convenience and brevity of description, the specific working processes of the systems, modules and units described above may refer to corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered within the scope of the present application.
Claims (10)
1. A method of risk assessment, the method comprising:
acquiring public sentiment events of risk evaluation objects in a preset time period;
determining public sentiment events with the attention degree greater than or equal to a preset attention degree threshold value as first public sentiment events, and determining public sentiment events with the attention degree smaller than the preset attention degree threshold value as second public sentiment events;
classifying the second public opinion event based on the attention degree to obtain a plurality of grades of the second public opinion event;
determining the second public sentiment event with the occurrence probability larger than a preset probability threshold value as a third public sentiment event in each level of the second public sentiment event;
and evaluating the risk value of the risk evaluation object based on the first public sentiment event and the third public sentiment event.
2. The method of claim 1, wherein after determining the second public sentiment event with the occurrence probability greater than a preset probability threshold as a third public sentiment event, the method further comprises:
determining a first weight value corresponding to each level of public sentiment events in the second public sentiment events based on a first preset rule;
weighting the third public opinion event based on the first weight value to obtain a first weighting result;
the evaluating the risk value of the risk evaluation object based on the first public sentiment event and the third public sentiment event specifically comprises:
and evaluating the risk value of the risk evaluation object based on the first public sentiment event and the first weighting result.
3. The method of claim 1, wherein after determining the second public sentiment event with the occurrence probability greater than a preset probability threshold as a third public sentiment event, the method further comprises:
classifying the third public sentiment event to obtain a first system public sentiment event and a first individual public sentiment event;
weighting the first system public opinion event and the first individual public opinion event respectively based on a predetermined system risk factor and an individual risk factor to obtain a second weighting result;
the evaluating the risk value of the risk evaluation object based on the first public sentiment event and the third public sentiment event specifically comprises:
and evaluating the risk value of the risk evaluation object based on the first public sentiment event and the second weighting result.
4. The method of claim 1, wherein after the determining of the public sentiment event with the attention degree greater than or equal to the preset attention degree threshold as the first public sentiment event, the method further comprises:
classifying the first public opinion event based on a preset classification rule to obtain a plurality of grades of the first public opinion event;
determining a second weight value corresponding to each level of public sentiment events in the first public sentiment events based on a second preset rule;
weighting the first public opinion event based on the second weight value to obtain a third weighting result;
the evaluating the risk value of the risk evaluation object based on the first public sentiment event and the third public sentiment event specifically comprises:
and evaluating the risk value of the risk evaluation object based on the third weighting result and the third public sentiment event.
5. The method of claim 1, wherein after the determining of the public sentiment event with the attention degree greater than or equal to the preset attention degree threshold as the first public sentiment event, the method further comprises:
classifying the first public sentiment event to obtain a second system public sentiment event and a second individual public sentiment event;
weighting the second system public opinion event and the second individual public opinion event respectively based on a predetermined system risk factor and an individual risk factor to obtain a fourth weighting result;
the evaluating the risk value of the risk evaluation object based on the first public sentiment event and the third public sentiment event specifically comprises:
and evaluating the risk value of the risk evaluation object based on the fourth weighting result and the third public sentiment event.
6. The method of claim 1, wherein the evaluating the risk value of the risk assessment object based on the first and third public sentiment events comprises:
and inputting the first public sentiment event and the third public sentiment event into a trained risk evaluation model to obtain a risk value of the target risk evaluation object.
7. A risk assessment device, characterized in that the device comprises:
the first acquisition module is used for acquiring public sentiment events of the risk evaluation object within a preset time period;
the determining module is used for determining a public opinion event with the attention degree greater than or equal to a preset attention degree threshold value as a first public opinion event, and determining a public opinion event with the attention degree smaller than the preset attention degree threshold value as a second public opinion event;
the first grading module is used for grading the second public opinion event based on the attention degree to obtain a plurality of grades of the second public opinion event;
the second determining module is used for determining the second public sentiment event of which the occurrence probability is greater than a preset probability threshold value as a third public sentiment event in each level of the second public sentiment event;
and the evaluation module is used for evaluating the risk value of the risk evaluation object based on the first public sentiment event and the third public sentiment event.
8. An electronic device, characterized in that the device comprises: a processor, and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the risk assessment method of any one of claims 1-6.
9. A computer-readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the risk assessment method of any one of claims 1-6.
10. A computer program product, wherein instructions in the computer program product, when executed by a processor of an electronic device, cause the electronic device to perform the risk assessment method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210100199.XA CN114417830A (en) | 2022-01-27 | 2022-01-27 | Risk evaluation method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210100199.XA CN114417830A (en) | 2022-01-27 | 2022-01-27 | Risk evaluation method, device, equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114417830A true CN114417830A (en) | 2022-04-29 |
Family
ID=81279312
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210100199.XA Pending CN114417830A (en) | 2022-01-27 | 2022-01-27 | Risk evaluation method, device, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114417830A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117390602A (en) * | 2023-12-11 | 2024-01-12 | 深圳市瑞迅通信息技术有限公司 | Information security risk evaluation method and system |
-
2022
- 2022-01-27 CN CN202210100199.XA patent/CN114417830A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117390602A (en) * | 2023-12-11 | 2024-01-12 | 深圳市瑞迅通信息技术有限公司 | Information security risk evaluation method and system |
| CN117390602B (en) * | 2023-12-11 | 2024-03-29 | 深圳市瑞迅通信息技术有限公司 | Information security risk evaluation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108280542B (en) | User portrait model optimization method, medium and equipment | |
| CN109982367B (en) | Complaint prediction method, device, equipment and storage medium for internet users of mobile terminals | |
| CN104702492A (en) | Garbage message model training method, garbage message identifying method and device thereof | |
| CN111861486A (en) | Abnormal account identification method, device, equipment and medium | |
| CN114417830A (en) | Risk evaluation method, device, equipment and computer readable storage medium | |
| CN114549136A (en) | Method, device and equipment for evaluating credit of supply chain user and computer storage medium | |
| CN111245815B (en) | Data processing method and device, storage medium and electronic equipment | |
| CN111353015B (en) | Crowd-sourced question recommendation method, device, equipment and storage medium | |
| CN115310735A (en) | Method, device, equipment and storage medium for identifying business district boundary | |
| CN112214675A (en) | Method, device and equipment for determining user machine purchasing and computer storage medium | |
| CN113112102A (en) | Priority determination method, device, equipment and storage medium | |
| CN114547101B (en) | Data quality evaluation method, device, equipment and storage medium for data center | |
| CN116308373A (en) | Data processing method, device, equipment and computer storage medium | |
| CN114547133B (en) | Multi-dimensional dataset-based conversational attribution analysis method, device and equipment | |
| CN117273932A (en) | Method, device, equipment, medium and product for processing remittance transaction | |
| CN115879959A (en) | Channel complaint risk determination method, device, equipment, medium and product | |
| CN115878873A (en) | Method, device and equipment for determining characteristics of abnormal user and storage medium | |
| CN115359330A (en) | Data processing method, device, equipment and storage medium | |
| CN116701803A (en) | Page conversion rate determination method, device, equipment and computer storage medium | |
| CN115392934A (en) | Method, device and equipment for evaluating credit of commercial tenant and computer storage medium | |
| CN114866433A (en) | User service perception evaluation method, device, equipment and computer storage medium | |
| CN117093845A (en) | Model training method, data processing method, device, equipment, medium and product | |
| CN115859169A (en) | Feature extraction method, device, equipment, readable storage medium and program product | |
| CN114996590A (en) | Classification method, classification device, classification equipment and storage medium | |
| CN115907955A (en) | Grading card model construction method, device, equipment, storage medium and product |
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 |