Power consumer public opinion risk early warning method and related device
Through automated public opinion data collection and analysis, key texts are identified and risk assessment coefficients are calculated, the problem of slow processing speed in the power industry's public opinion control is solved, and timely warning and response to public opinion risks in the power industry is achieved.
Patent Information
- Application Number
- CN202411227983.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-09-03
AI Technical Summary
The power industry lacks automation tools in public opinion control, resulting in slow processing speed and inability to respond to emerging public opinion threats in a timely manner.
Through automated public opinion data collection and analysis, key texts are identified and risk assessment coefficients are calculated based on their frequency, preliminary and in-depth risk assessments are conducted, and corresponding alarm signals are issued to achieve timely early warning of public opinion risks.
It has achieved rapid identification and timely response to public opinion risks in the power industry, and improved the efficiency and accuracy of public opinion processing.
Smart Images

Figure CN119089893A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of public opinion risk management, and specifically relates to a method and related devices for early warning of public opinion risks for power users. Background Art
[0002] The power industry is in a stage of rapid development. In the process of optimizing and reforming the power structure, issues such as power supply and demand contradictions, environmental protection and sustainable development have received great attention from public opinion. How to accurately grasp the social situation and public opinion, and the power public opinion work faces new challenges. The extensive use of instant messaging tools such as Weibo has brought information release and public communication into the "self-media" era. The network spreads quickly and has a wide range of influence. The power public opinion management faces new challenges.
[0003] At present, the control of public opinion mainly relies on manual data collection and analysis. The process from data collection and analysis to risk assessment lacks effective automated tools, resulting in slow processing speed and inability to respond to emerging public opinion threats in a timely manner. Summary of the invention
[0004] In view of this, the present invention aims to provide a method and related devices for early warning of public opinion risks for power users, which can obtain risk assessment through automated public opinion data collection and analysis, and perform further alarm processing based on the assessment results, so as to respond to emerging public opinion threats in a timely manner.
[0005] In order to achieve the above object, the technical solution provided by the present invention is as follows:
[0006] In a first aspect, the present invention provides a method for early warning of public opinion risks of power users, comprising the following steps:
[0007] Obtain text data containing public opinion content in the power industry;
[0008] Identify preset key texts from text data, and determine the risk assessment coefficient of the current text data based on the frequency of occurrence of the key texts. The key texts are texts that reflect public opinion content, and there is a positive correlation between the size of the risk assessment coefficient and the frequency.
[0009] Conduct a preliminary risk assessment of the current risk based on the risk assessment coefficient, and issue a first-class warning signal when the preliminary risk assessment result indicates that a risk has occurred;
[0010] Generate a risk assessment coefficient prediction sequence based on all risk assessment coefficients within the time period of the current text data, and input it into the pre-trained prediction model to obtain the risk assessment prediction coefficient;
[0011] Conduct in-depth risk assessment of current risks based on risk assessment prediction coefficients, and issue a second-class warning signal indicating the severity of the risk based on the in-depth risk assessment results;
[0012] Based on the first and second type of warning signals, early warning is issued for the current public opinion situation.
[0013] Furthermore, the preset key text is identified from the text data, including:
[0014] Based on the basic recognition dictionary, key texts are identified from the text data, and the frequencies of occurrence of all key texts in the text data are counted. The basic recognition dictionary includes preset key texts and corresponding weights.
[0015] Furthermore, the risk assessment coefficient of the current text data is determined according to the frequency of occurrence of the key text, including:
[0016] The weight corresponding to the key text is combined with the frequency of occurrence to obtain a comprehensive weight;
[0017] The risk assessment coefficient is obtained by summing up the comprehensive weights of all key texts.
[0018] Furthermore, identifying a preset key text from the text data also includes:
[0019] Divide the text data into several simple sentences;
[0020] Based on the comprehensive recognition dictionary, the predicate key text is recognized from a plurality of simple sentences, and the front part of the predicate key text in the simple sentence is used as the subject part to be recognized, and the rear part is used as the object part to be recognized, and the comprehensive recognition dictionary includes the subject key text, the predicate key text and the object key text and the corresponding weights;
[0021] Traverse the subject part to be identified and the object part to be identified, select simple sentences containing subject key text, predicate key text and object key text at the same time, and count the frequency of occurrence of the corresponding key text.
[0022] Furthermore, the risk assessment coefficient of the current text data is determined according to the frequency of occurrence of the key text, including:
[0023] The corresponding weights and occurrence frequencies of the subject key text, predicate key text and object key text in each screened simple sentence are integrated to obtain the comprehensive weight of each simple sentence;
[0024] The risk assessment coefficient is obtained by summing up the comprehensive weights of all simple sentences.
[0025] Further, the initial risk assessment includes:
[0026] The risk assessment coefficient is compared with the preset risk threshold. If it exceeds the preset risk threshold, it is assessed as a risk.
[0027] Further, in-depth risk assessment includes:
[0028] The risk assessment prediction coefficient is matched with the preset risk level to obtain the risk prediction level. Each risk level corresponds to a risk assessment prediction coefficient range and an alarm signal.
[0029] In a second aspect, the present invention provides a power user public opinion risk early warning device, comprising
[0030] A public opinion data collection unit, used to obtain text data containing public opinion content in the power industry;
[0031] The topic extraction unit is used to identify preset key texts from the text data and determine the risk assessment coefficient of the current text data according to the frequency of occurrence of the key texts. The key texts are texts that reflect the content of public opinion, and there is a positive correlation between the size of the risk assessment coefficient and the frequency.
[0032] The risk determination unit is used to conduct a preliminary risk assessment of the current risk based on the risk assessment coefficient;
[0033] The risk level prediction unit is used to generate a risk assessment coefficient prediction sequence based on all risk assessment coefficients within the time period of the current text data, and input it into the pre-trained prediction model to obtain the risk assessment prediction coefficient; it is also used to perform in-depth risk assessment on the current risk based on the risk assessment prediction coefficient;
[0034] The risk processing unit is used to issue a first-class warning signal when the preliminary risk assessment result indicates that a risk has occurred; and is also used to issue a second-class warning signal indicating the severity of the risk according to the in-depth risk assessment result;
[0035] The early warning unit is used to warn the current public opinion situation based on the first type of warning signal and the second type of warning signal.
[0036] Accordingly, the present invention provides a computer device, the device comprising a processor and a memory:
[0037] The memory is used to store the computer program and send the instructions of the computer program to the processor;
[0038] The processor executes a method for early warning of public opinion risks of power users as described in the first aspect according to the instructions of the computer program.
[0039] Accordingly, the present invention provides a computer-readable storage medium having a computer program stored thereon, and the computer program is executed by a processor as in a method for early warning of public opinion risks of power users according to the first aspect.
[0040] In summary, the present invention provides a method and related device for early warning of public opinion risk of power users, including obtaining text data containing public opinion content in the power industry; identifying preset key texts from the text data, and determining the risk assessment coefficient of the current text data according to the frequency of occurrence of the key texts, wherein the key texts are texts reflecting the content of public opinion, and the size of the risk assessment coefficient is positively correlated with the frequency; performing a preliminary risk assessment on the current risk according to the risk assessment coefficient, and issuing a first-class alarm signal when the preliminary risk assessment result is that a risk occurs; generating a risk assessment coefficient prediction sequence based on all risk assessment coefficients within the time period of the current text data, and inputting it into a pre-trained prediction model to obtain a risk assessment prediction coefficient; performing a deep risk assessment on the current risk according to the risk assessment prediction coefficient, and issuing a second-class alarm signal for indicating the severity of the risk according to the deep risk assessment result; and issuing an early warning of the current public opinion situation based on the first-class alarm signal and the second-class alarm signal. The present invention obtains a risk assessment through automated public opinion data collection and analysis, and performs further alarm processing based on the assessment result, so as to respond to new public opinion threats in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0042] Figure 1 A flowchart of a method for early warning of public opinion risks of power users provided by an embodiment of the present invention;
[0043] Figure 2 A flow chart of determining a risk determination coefficient based on a comprehensive recognition dictionary provided by an embodiment of the present invention;
[0044] Figure 3 A block diagram of a power user public opinion risk early warning device provided by an embodiment of the present invention;
[0045] Figure 4 A block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0046] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0047] See also Figure 1 This embodiment provides a method for early warning of public opinion risks of power users, comprising the following steps:
[0048] S11: Obtain text data containing public opinion content in the power industry.
[0049] It should be noted that this step collects public opinion text data related to the power industry, such as collecting text data from the latest information, articles and Internet discussion content released by the power industry. The text content can be directly copied from power industry websites and discussion websites (such as Weibo, forums, etc.) and stored based on this to form the text to be processed.
[0050] S12: Identify preset key texts from the text data, and determine the risk assessment coefficient of the current text data based on the frequency of occurrence of the key texts. The key texts are texts that reflect the content of public opinion, and there is a positive correlation between the size of the risk assessment coefficient and the frequency.
[0051] It should be noted that this step identifies keywords or phrases related to public opinion and quantifies the risk level based on their frequency of occurrence. Natural language processing techniques (such as TF-IDF, word frequency statistics, etc.) can be used to analyze the text and find key texts related to public opinion.
[0052] S13: Conduct a preliminary risk assessment on the current risk based on the risk assessment coefficient, and issue a first-class warning signal when the preliminary risk assessment result indicates that a risk has occurred.
[0053] It should be noted that this step conducts a preliminary risk assessment based on the risk assessment coefficient, quickly determines the public opinion risk level based on the frequency of keyword occurrence, and makes an immediate response. The first type of warning signal has the characteristics of rapid response so that timely action can be taken.
[0054] S14: Generate a risk assessment coefficient prediction sequence based on all risk assessment coefficients within the time period of the current text data, and input it into a pre-trained prediction model to obtain a risk assessment prediction coefficient.
[0055] It should be noted that this step uses historical data to predict future public opinion trends and prepare countermeasures in advance. By establishing time intervals and time periods T, repeating the previous steps, and obtaining the risk assessment coefficients K at fixed time intervals of time period T, the risk assessment coefficient prediction sequence can be obtained: , based on the time series algorithm, predict the future risk determination data trend and obtain the risk assessment prediction coefficient K 预测 .
[0056] S15: Conduct an in-depth risk assessment on the current risk based on the risk assessment prediction coefficient, and issue a second type of warning signal to indicate the severity of the risk based on the in-depth risk assessment result.
[0057] It should be noted that this step further evaluates the severity of public opinion risks based on the predicted results and issues more detailed warnings. The second type of warning signal contains specific risk levels, which can be matched with specific response measures, thereby accurately handling risks.
[0058] S16: Issue an early warning of the current public opinion situation based on the first type of warning signal and the second type of warning signal.
[0059] It should be noted that this step integrates the information of immediate warning and forecast warning to form a complete public opinion warning mechanism. Combining the immediate warning signal with the forecast warning signal, the overall situation of public opinion risk can be comprehensively evaluated, and warning notifications can be sent to relevant personnel accordingly.
[0060] This embodiment provides a method for early warning of public opinion risks for power users, which obtains risk assessment through automated public opinion data collection and analysis, and performs further alarm processing based on the assessment results, so as to respond to new public opinion threats in a timely manner.
[0061] In some embodiments, identifying a preset key text from the text data includes:
[0062] Based on the basic recognition dictionary, key texts are identified from the text data, and the frequencies of occurrence of all key texts in the text data are counted. The basic recognition dictionary includes preset key texts and corresponding weights.
[0063] It should be noted that the key text can be a keyword or a key word. The following is an example of a basic recognition dictionary:
[0064]
[0065] In a further embodiment, the risk assessment coefficient of the current text data is determined according to the frequency of occurrence of the key text, including:
[0066] S21: The weight corresponding to the key text is integrated with the frequency of occurrence to obtain a comprehensive weight;
[0067] S22: The comprehensive weights of all key texts are summed up to obtain the risk assessment coefficient.
[0068] Here are some examples (take Weibo blog excerpts as an example):
[0069] “#Grid maintenance complaints# I’m speechless! The recent power outages due to grid maintenance have lasted too long! The food in my refrigerator has gone bad, and I have to rely on my phone for lighting at night. Maintenance work is important, but we, the innocent users, should not be forced to pay for long power outages! I hope the power company can pay attention to this issue and stop us from paying for the “dark times”! @Power company, don’t be too ridiculous! Come and take a look at these complaining netizens!”
[0070] For this blog post, based on the keywords / keywords contained in the recognition dictionary, the above keywords / keywords are identified, and the keywords and their frequencies are recorded as follows:
[0071]
[0072] Multiply the recognition frequency of keywords and key words by the corresponding weights, and finally add them up to get the risk assessment coefficient. The details are as follows:
[0073]
[0074] in, represents the risk assessment coefficient, represents the weight of the i-th keyword / keyword, Indicates the frequency of the i-th keyword / keyword.
[0075] In some embodiments, identifying a preset key text from the text data further includes:
[0076] S31: Divide the text data into a number of simple sentences, which may be divided by punctuation marks.
[0077] S32: Identify predicate key texts from several simple sentences based on a comprehensive recognition dictionary, and use the front part of the predicate key text in the simple sentence as the subject part to be recognized, and the rear part as the object part to be recognized. The comprehensive recognition dictionary includes the subject key text, the predicate key text and the object key text as well as corresponding weights.
[0078] This step first identifies whether the simple sentence contains the predicate in the comprehensive recognition dictionary. If it does, the part before the predicate is regarded as the subject to be recognized, and the part after the predicate is regarded as the object to be recognized.
[0079] S33: traverse the subject to be identified part and the object to be identified part, select simple sentences containing subject key text, predicate key text and object key text at the same time, and count the frequency of occurrence of corresponding key text.
[0080] This step performs subject and object recognition, specifically traversing the subject and object parts to be recognized to check whether there are subjects and objects in the comprehensive recognition dictionary. If both exist, the corresponding weights of the subject, predicate and object recognized based on the current simple sentence are accumulated to calculate the comprehensive weight of the simple sentence; if at least one does not exist, the next simple sentence is recognized. Obtain each simple sentence and perform subject, predicate and object recognition on it until all simple sentences are traversed.
[0081] It should be noted that the comprehensive recognition dictionary includes three items: "subject", "predicate" and "object", and each item has a corresponding weight; the example is as follows:
[0082]
[0083]
[0084]
[0085] The following is a simple example to illustrate the above steps:
[0086] "I'm speechless! The power company has been cutting off electricity for too long! The food in my refrigerator has gone bad, and I have to rely on my phone for lighting at night. Maintenance work is important, but we, the innocent users, should not be forced to pay for long power outages! I hope the power grid can pay attention to the problem of always cutting off electricity in our community! @power company, don't be too ridiculous! Come and take a look at these complaining netizens!"
[0087] First, the above sentence is divided into simple sentences by punctuation marks (in this example, exclamation mark, period, question mark, semicolon, and ellipsis are used as separators). The above paragraph is processed as follows:
[0088] 1. I am speechless!
[0089] 2. The power company (subject) has cut off (predicate) electricity (object) for too long recently!
[0090] 3. The food in the refrigerator at home has gone bad, and I have to rely on my mobile phone for lighting at night.
[0091] 4. Maintenance work is important, but we cannot let innocent users like us pay for long-term power outages!
[0092] 5. I hope the power grid (subject) can pay attention to the problem of power outages (predicate) in our neighborhood (object)!
[0093] 6. @Electricity Company, don’t be too outrageous!
[0094] 7. Come and take a look at these complaining netizens! "
[0095] Then, the subject, predicate and object in the above simple sentences are identified, the above "electricity" and "grid" are subjects, "stop" is the predicate and "electricity" is the object. It can be seen that the above simple sentences 2 and 5 are the sentences that need to be screened out.
[0096] In a further embodiment, the risk assessment coefficient of the current text data is determined according to the frequency of occurrence of the key text, including:
[0097] S41: The corresponding weights and occurrence frequencies of the subject key text, the predicate key text and the object key text in each screened simple sentence are integrated to obtain a comprehensive weight of each simple sentence;
[0098] S42: The comprehensive weights of all simple sentences are summed up to obtain a risk assessment coefficient.
[0099] Based on the example of the above embodiment, the weights of simple sentences 2 and 5 are calculated. The weight of a simple sentence is the subject weight + the predicate weight + the object weight. Then the weights of simple sentences 2 and 5 are added together to obtain the risk determination coefficient. The process of determining the risk assessment coefficient based on the comprehensive recognition dictionary is as follows: Figure 2 shown.
[0100] In some embodiments, the preliminary risk assessment includes:
[0101] The risk assessment coefficient is compared with the preset risk threshold. If it exceeds the preset risk threshold, it is assessed as a risk.
[0102] It should be noted that a risk threshold is set, and the risk assessment coefficient is compared with the risk threshold. If the risk threshold is exceeded, it is assessed as a current risk and the first warning signal of "current risk" is issued.
[0103] In some embodiments, the in-depth risk assessment includes:
[0104] The risk assessment prediction coefficient is matched with the preset risk level to obtain the risk prediction level. Each risk level corresponds to a risk assessment prediction coefficient range and an alarm signal.
[0105] It should be noted that based on K 预测 Take risk level prediction as an example, as follows:
[0106]
[0107] Above , , The judgment threshold can be designed and adjusted according to actual needs. There is no limitation here. The risk levels of "low", "medium" and "high" are only examples. In actual applications, more levels can be set as needed, and corresponding judgment thresholds can be designed based on the levels.
[0108] A separate alarm signal is set for each risk prediction level, namely the second alarm signal, the third alarm signal, ..., the mth alarm signal, corresponding to the m-1 risk prediction levels (i.e., the second type of alarm signal). For example, the risk levels are divided into "low", "medium", and "high" as mentioned above, and the second alarm signal, the third alarm signal, and the fourth alarm signal are matched.
[0109] Based on the same inventive concept, the embodiment of the present application also provides a power user public opinion risk warning device for implementing the power user public opinion risk warning method involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in the power user public opinion risk warning device embodiment provided below can refer to the limitations of the power user public opinion risk warning method above, and will not be repeated here.
[0110] See also Figure 3 This embodiment provides a power user public opinion risk early warning device, including
[0111] The public opinion data collection unit is used to obtain text data of public opinion content in the power industry. Specifically, the latest information, documents and Internet discussion content released by the power industry are collected, mainly for collecting text data. The text content obtained from the power industry website and discussion website (such as Weibo, forum, etc.) can be directly copied and stored based on this.
[0112] The topic extraction unit is used to identify the preset key text from the text data, and determine the risk assessment coefficient of the current text data according to the frequency of the key text. The key text is the text that reflects the content of public opinion, and the size of the risk assessment coefficient is positively correlated with the frequency. Specifically, this unit mainly outputs the risk assessment coefficient, including the current risk assessment coefficient and the historical risk assessment coefficient (the current risk assessment coefficient and the historical risk assessment coefficient are obtained in the same way, and the difference between the two is only the difference in the time dimension, that is, the risk assessment coefficient obtained at the current time is the current risk assessment coefficient. When the risk assessment coefficient at the next moment is output, the risk assessment coefficient at the previous moment and before is the historical risk assessment coefficient).
[0113] The extraction process of the topic extraction unit is as follows:
[0114] Constructing a recognition dictionary, wherein the recognition dictionary includes keywords, key words and their corresponding weights;
[0115] Get the text content, traverse the text content and identify keywords, key words and their corresponding frequencies.
[0116] The risk determination unit is used to conduct a preliminary risk assessment of the current risk based on the risk assessment coefficient.
[0117] The risk level prediction unit is used to generate a risk assessment coefficient prediction sequence based on all risk assessment coefficients within the time period of the current text data, and input it into a pre-trained prediction model to obtain the risk assessment prediction coefficient; it is also used to perform in-depth risk assessment on the current risk based on the risk assessment prediction coefficient.
[0118] Specifically, the unit obtains the real-time output data and historical output data of the risk determination unit, predicts the future risk determination data trend based on the time series algorithm, and predicts the risk level based on the predicted risk determination data. The time series algorithm can be ARIMA algorithm, Prophet algorithm, etc.
[0119] The risk processing unit is used to send out a first type of alarm signal when the preliminary risk assessment result indicates that a risk has occurred; it is also used to send out a second type of alarm signal indicating the severity of the risk according to the in-depth risk assessment result. The unit sets a risk processing method for each risk level, receives the risk level output from the risk level prediction unit, selects the corresponding risk processing method for processing, including sending a first alarm signal to the terminal. In addition, it can also receive the current risk determination coefficient of the risk determination unit and compare it with the set threshold. If it exceeds the set threshold, a second alarm signal is sent.
[0120] The early warning unit is used to warn the current public opinion situation based on the first type of warning signal and the second type of warning signal.
[0121] In addition, the above device may also include a data preprocessing unit and a terminal.
[0122] The data preprocessing unit serves as an intermediate unit between the public opinion data collection unit and the topic extraction unit, and plays the role of further processing the data. Its main purpose is to make the data more standardized. This unit can be set as needed and can be omitted.
[0123] The terminal includes a management terminal and an execution terminal. The management terminal is used to access the above units and has the influencing data of changing the process data of the above units, such as the judgment threshold, weight, recognition dictionary content, etc. The execution terminal is mainly connected to the risk processing unit and is used to receive data (such as alarm signals) from the risk processing unit.
[0124] This embodiment completes data collection, processing and analysis through the public opinion data collection unit, data preprocessing unit and topic extraction unit, and finally further calculates the risk assessment coefficient through the risk determination unit based on the output result of the topic extraction unit, so as to assess whether there is a risk at present and predict whether there will be a risk in the future, wherein the prediction of whether there will be a risk in the future is specifically realized through the time series algorithm in the risk level prediction unit. In addition, the present invention is also designed with a risk processing unit, which provides the response methods and strategies for each risk level, including sending an alarm signal to the terminal. Based on this, the technical solution of the present invention is sufficient to solve the problem that the control of public opinion mainly relies on manual data collection and analysis, and the processing speed is slow.
[0125] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0126] Reference Figure 4 An embodiment of the present invention further provides a computer device, including: a memory and a processor and a computer program stored in the memory. When the computer program is executed on the processor, the power user public opinion risk warning method as described in any one of the above methods is implemented.
[0127] The computer device may be a desktop computer, a notebook, a PDA, a cloud server or other computing device. The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that Figure 4 It is only an example of a computer device and does not constitute a limitation of the computer device. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.
[0128] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0129] In some embodiments, the memory may be an internal storage unit of the computer device, such as a hard disk or memory of the computer device. In other embodiments, the memory may also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device. Further, the memory may include both an internal storage unit and an external storage device of the computer device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory may also be used to temporarily store data that has been output or is to be output.
[0130] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for early warning of public opinion risks of power users as described in any one of the above methods is implemented.
[0131] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, USB flash drive, mobile hard disk, disk or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.
[0132] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0133] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0134] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0135] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for early warning of public opinion risks of power users, characterized in that: The steps include: Obtain text data containing public opinion content in the power industry; Identify a preset key text from the text data, and determine a risk assessment coefficient of the current text data according to the frequency of occurrence of the key text, wherein the key text is a text reflecting the content of the public opinion, and there is a positive correlation between the magnitude of the risk assessment coefficient and the frequency; Conduct a preliminary risk assessment on the current risk based on the risk assessment coefficient, and issue a first-class warning signal when the preliminary risk assessment result indicates that a risk has occurred; Generate a risk assessment coefficient prediction sequence based on all risk assessment coefficients within the time period of the current text data, and input it into the pre-trained prediction model to obtain the risk assessment prediction coefficient; Conducting a deep risk assessment on the current risk based on the risk assessment prediction coefficient, and issuing a second type of warning signal indicating the severity of the risk based on the deep risk assessment result; Based on the first type of alarm signal and the second type of alarm signal, an early warning of the current public opinion situation is issued.
2. The method for early warning of public opinion risk of power users according to claim 1 is characterized in that: Identifying a preset key text from the text data includes: Key texts are identified from the text data based on a basic recognition dictionary, and the frequencies of occurrence of all the key texts in the text data are counted. The basic recognition dictionary includes preset key texts and corresponding weights.
3. The method for early warning of public opinion risk of power users according to claim 2 is characterized in that: Determining the risk assessment coefficient of the current text data according to the frequency of occurrence of the key text includes: The weight corresponding to the key text is integrated with the frequency of occurrence to obtain a comprehensive weight; The risk assessment coefficient is obtained by summing up the comprehensive weights of all the key texts.
4. The method for early warning of public opinion risk of power users according to claim 1 is characterized in that: Identifying a preset key text from the text data also includes: Dividing the text data into a plurality of simple sentences; Recognize predicate key texts from a plurality of simple sentences based on a comprehensive recognition dictionary, and use the front part of the predicate key text in the simple sentence as the subject to be recognized part, and the rear part as the object to be recognized part, wherein the comprehensive recognition dictionary includes the subject key text, the predicate key text and the object key text and corresponding weights; The subject to-be-recognized part and the object to-be-recognized part are traversed to select simple sentences containing the subject key text, the predicate key text and the object key text at the same time, and the frequency of occurrence of the corresponding key text is counted.
5. The method for early warning of public opinion risk of power users according to claim 4 is characterized in that: Determining the risk assessment coefficient of the current text data according to the frequency of occurrence of the key text includes: The corresponding weights and occurrence frequencies of the subject key text, the predicate key text and the object key text in each of the screened simple sentences are merged to obtain a comprehensive weight of each of the simple sentences; The risk assessment coefficient is obtained by summing up the comprehensive weights of all the simple sentences.
6. The method for early warning of public opinion risk of power users according to claim 1 is characterized in that: The initial risk assessment includes: The risk assessment coefficient is compared with a preset risk threshold, and if it exceeds the preset risk threshold, it is assessed as a risk.
7. The method for early warning of public opinion risk of power users according to claim 1 is characterized in that: The in-depth risk assessment includes: The risk assessment prediction coefficient is matched with a preset risk level to obtain a risk prediction level, and each risk level corresponds to a risk assessment prediction coefficient range and an alarm signal.
8. A power user public opinion risk early warning device, characterized in that: include A public opinion data collection unit, used to obtain text data containing public opinion content in the power industry; A topic extraction unit, used to identify a preset key text from the text data, and determine a risk assessment coefficient of the current text data according to the frequency of occurrence of the key text, wherein the key text is a text reflecting the content of the public opinion, and there is a positive correlation between the size of the risk assessment coefficient and the frequency; A risk determination unit, used to perform a preliminary risk assessment on the current risk according to the risk assessment coefficient; A risk level prediction unit is used to generate a risk assessment coefficient prediction sequence based on all risk assessment coefficients within the time period of the current text data, and input it into a pre-trained prediction model to obtain a risk assessment prediction coefficient; It is also used to perform an in-depth risk assessment of the current risk based on the risk assessment prediction coefficient; The risk processing unit is used to issue a first-class warning signal when the preliminary risk assessment result indicates that a risk has occurred; It is also used to issue a second type of warning signal indicating the severity of the risk based on the results of the in-depth risk assessment; An early warning unit is used to issue an early warning on the current public opinion situation based on the first type of warning signal and the second type of warning signal.
9. A computer device, characterized in that: The device comprises a processor and a memory: The memory is used to store a computer program and send instructions of the computer program to the processor; The processor executes a method for early warning of public opinion risks for power users as described in any one of claims 1 to 7 according to instructions of the computer program.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor according to a method for early warning of public opinion risks for power users as described in any one of claims 1-7.
Citation Information
Patent Citations
Public opinion early warning method and device based on recurrent neural network algorithm, terminal and medium
CN109800302A
Data analysis method, device and system based on public opinion analysis
CN111581945A
Risk assessment method and system
CN113642867A
Network public opinion early warning method integrated with correlation analysis and storm suppression mechanism
CN115934808A
Enterprise public opinion analysis method and apparatus, and electronic device and medium
WO2021217843A1
