Method and device for monitoring hot public opinion, electronic equipment and storage medium
By screening and analyzing the heat-affecting parameters of public opinion data and calculating hotspot indicators, the problem of misjudging public opinion hotspots has been solved, and more accurate hotspot early warning and decision support have been achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ANHUI IFLYTEK INTELLIGENT SYST
- Filing Date
- 2026-01-07
- Publication Date
- 2026-05-29
Smart Images
Figure CN122114900A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, electronic device, and storage medium for monitoring trending public opinion. Background Technology
[0002] The needs of the people are often collected through various channels and platforms. However, these channels and platforms only provide fragmented and incomplete analyses, making it difficult to present a comprehensive picture of public sentiment. Swift action on public opinion requires a comprehensive approach that "observes" public opinion, "understands" people's livelihoods, and "gathers" public sentiment. Therefore, it is necessary to aggregate fragmented information for a more comprehensive analysis.
[0003] In related technologies, a hotspot analysis model based on keyword matching is mainly used, which triggers an alert when the number of work orders containing keywords reaches a threshold. However, this method only considers the keywords in the work orders, and keywords may not reflect the overall situation of the event itself, thus easily leading to misjudgments. Summary of the Invention
[0004] This application provides a method, device, electronic device, and storage medium for monitoring trending public opinion, in order to solve the problem that trending public opinion is easily misjudged in the prior art.
[0005] According to a first aspect of the embodiments of this application, a method for monitoring trending public opinion is provided, comprising: Acquire public opinion data to be monitored, which includes public opinion elements and public opinion content. The public opinion elements include key attribute information used to describe the public opinion data to be monitored. From the public opinion data to be monitored, target public opinion data that meets the preset hotspot filtering conditions are selected; The public opinion heat influence parameter of the target public opinion data is determined based on the public opinion elements and the public opinion content. The public opinion heat influence parameter is used to represent the degree of influence of the target public opinion data on the public opinion heat. Hotspot indicators are determined based on the public opinion heat impact parameters of the target public opinion data, and the hotspot indicators are used to represent the heat of public opinion indicated by the target public opinion data; When the hot spot indicator exceeds a preset indicator threshold, an early warning message is generated.
[0006] Optionally, obtain the public opinion data to be monitored, including: Obtain raw public opinion data, which includes public opinion content, time of occurrence, and location of occurrence; Based on the content of the public opinion, the subject of the public opinion, the information prompts, and the category of the public opinion in the original public opinion data are determined. The original public opinion data, including the content of the public opinion, the time of occurrence of the public opinion, the location of occurrence of the public opinion, the subject of the public opinion, the public opinion prompt information, and the category of the public opinion, is identified as the public opinion data to be monitored.
[0007] Optionally, based on the public opinion content, the public opinion subject, public opinion alert information, and public opinion category of the original public opinion data are determined, including: Extract the initial subject from the public opinion content, and determine the public opinion subject corresponding to the initial subject according to the preset subject mapping library; The public opinion content is extracted based on pre-configured prompts to obtain the public opinion prompt information; A pre-trained classification model is used to determine the classification category of the public opinion content, thus obtaining the public opinion category.
[0008] Optionally, the preset hotspot filtering conditions include a preset time period and / or a preset regional range; the public opinion elements include the time and / or location of the public opinion data to be monitored. From the monitored public opinion data, target public opinion data that meets preset hotspot filtering conditions are selected, including: From the public opinion data to be monitored, the public opinion data whose occurrence time is within the preset time period and / or whose location is within the preset area are determined as the target public opinion data.
[0009] Optionally, the public opinion elements include the time of occurrence of the public opinion, the location of the occurrence of the public opinion, the public opinion prompt information, the subject of the public opinion, and the category of the public opinion data to be monitored; Determining the public opinion heat impact parameters of the target public opinion data based on the aforementioned public opinion elements and content includes: Based on the time of the occurrence of the public opinion event, a first data volume of the target public opinion data within a preset time period is determined, and the submission rate of the target public opinion data is determined based on the first data volume. Semantic extraction is performed on the public opinion category, public opinion prompt information, and public opinion content to obtain a semantic vector, and the semantic vector is normalized to obtain the semantic proportion of the target public opinion data; Determine the textual features of the target public opinion data based on the content of the public opinion; Based on the location of the public opinion event, a second data volume of the target public opinion subject is determined within a preset area, and the spatial subject characteristics of the target public opinion data are determined based on the second data volume, wherein the target public opinion subject is any one of the public opinion subjects; The spatial clustering characteristics of the target public opinion data are determined based on the location where the public opinion occurred; The submission rate, semantic proportion, text features, spatial subject features, and spatial clustering features are determined as the parameters affecting public opinion heat.
[0010] Optionally, the spatial subject characteristics of the target public opinion data are determined based on the second data volume, including: The spatial subject density is determined based on the second data volume and the preset area range. The spatial subject density is used to indicate the density of the target public opinion data corresponding to the target public opinion subject within the preset area range. The spatial subject alignment value is determined based on the third data volume and the total number of the public opinion subjects. The spatial subject alignment value is used to indicate the subject coverage of the target public opinion subject. The third data volume is the data volume of public opinion subjects other than the target public opinion subject.
[0011] Optionally, the parameters affecting public opinion heat include: the submission rate, semantic proportion, text features, spatial subject features, and spatial clustering features of the target public opinion data; The hotspot indicators determined by the public opinion heat impact parameters based on the target public opinion data include: Based on the submission rate and the spatial subject characteristics, determine the hotspot spatiotemporal indicators of the target public opinion data; Based on the semantic proportion, text features, spatial subject features, and spatial clustering features, the hot topic public opinion indicators of the target public opinion data are determined. The hot topic indicators are determined based on the hot topic spatiotemporal indicators and the hot topic public opinion indicators.
[0012] According to a second aspect of the embodiments of this application, a monitoring device for trending public opinion is provided, comprising: The acquisition unit is used to acquire public opinion data to be monitored. The public opinion data to be monitored includes public opinion elements and public opinion content. The public opinion elements include key attribute information used to describe the public opinion data to be monitored. The filtering unit is used to filter target public opinion data that meets preset hotspot filtering conditions from the public opinion data to be monitored. The first determining unit is used to determine the public opinion heat influence parameter of the target public opinion data based on the public opinion elements and the public opinion content. The public opinion heat influence parameter is used to represent the degree of influence of the target public opinion data on the public opinion heat. The second determining unit is used to determine hot spot indicators based on the public opinion heat influence parameters of the target public opinion data, wherein the hot spot indicators are used to represent the heat of public opinion indicated by the target public opinion data; The early warning unit is used to generate early warning information when the hot spot indicator exceeds a preset indicator threshold.
[0013] According to a third aspect of the embodiments of this application, an electronic device is provided, including a memory and a processor; The memory is connected to the processor and is used to store programs; The processor is used to implement the method for monitoring trending public opinion as described in the first aspect by running the program in the memory.
[0014] According to a fourth aspect of the embodiments of this application, a storage medium is provided, on which a computer program is stored, and when the computer program is run by a processor, it implements the method for monitoring hot public opinion as described in the first aspect.
[0015] According to a fifth aspect of the embodiments of this application, a computer program product is provided, including computer program instructions, which, when executed by a processor, cause the processor to perform the hot topic monitoring method as described in the first aspect.
[0016] Compared with the prior art, the technical solution provided in this application has the following advantages: The method provided in this application acquires public opinion data to be monitored, which includes public opinion elements and public opinion content. The public opinion elements include key attribute information used to describe the public opinion data to be monitored. From the public opinion data to be monitored, target public opinion data that meets preset hotspot filtering conditions is selected. Based on the public opinion elements and the public opinion content, a public opinion heat impact parameter of the target public opinion data is determined, which represents the degree of influence of the target public opinion data on the public opinion heat. Based on the public opinion heat impact parameter of the target public opinion data, a hotspot index is determined, which represents the heat of the public opinion indicated by the target public opinion data. When the hotspot index is greater than a preset index threshold, an early warning information is generated. Thus, by utilizing the public opinion elements and public opinion content of the public opinion data to be monitored, a public opinion heat impact parameter affecting the public opinion heat is determined, and a hotspot index is determined based on this parameter. This utilizes all the information of the public opinion data to be monitored for hotspot analysis, thereby ensuring the accuracy of hotspot early warning. Attached Figure Description
[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.
[0018] Figure 1 A flowchart illustrating a method for monitoring trending public opinion in an embodiment of this application.
[0019] Figure 2 A flowchart is provided for another embodiment of this application to illustrate a method for monitoring trending public opinion.
[0020] Figure 3 This is a structural diagram of an electronic device provided in an embodiment of this application. Detailed Implementation
[0021] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0022] Exemplary Implementation Environment The method for monitoring trending public opinion according to embodiments of this application can be executed by electronic devices such as terminal devices or servers. Terminal devices can be user equipment (UE), mobile devices, user terminals, terminals, cellular phones, cordless phones, personal digital assistants (PDAs), handheld devices, computing devices, in-vehicle devices, wearable devices, etc. Servers can be independent physical servers, server clusters composed of multiple physical servers, or cloud servers capable of cloud computing. This method can be implemented by a processor calling computer-readable program instructions stored in memory. This application uses the execution of a server-based method for monitoring trending public opinion as an example for explanation, but does not limit the scope of the application.
[0023] Exemplary methods Please see Figure 1 In one exemplary embodiment, a method for monitoring trending public opinion is provided, including: Step 101: Obtain the public opinion data to be monitored.
[0024] The public opinion data to be monitored includes public opinion elements and public opinion content. The public opinion elements include key attribute information used to describe the public opinion data to be monitored. In some embodiments, the public opinion data to be monitored can be determined from public opinion data obtained from different channels and platforms (such as grid event platforms, specific channel platforms, or event data manually imported by relevant personnel). Public opinion data obtained from channel platforms may contain some interfering data; therefore, the public opinion data obtained from channel platforms can be filtered to ensure that the data participating in the monitoring of hot topic public opinion is all valid data.
[0025] Furthermore, the raw public opinion data obtained from the channel platform can be preprocessed to obtain public opinion data that meets the needs of hot topic public opinion monitoring.
[0026] In one optional embodiment, acquiring the public opinion data to be monitored includes: Obtain raw public opinion data, which includes public opinion content, time of occurrence, and location of occurrence; Based on the content of the public opinion, the subject of the public opinion, the information prompts, and the category of the public opinion in the original public opinion data are determined. The original public opinion data, including the content of the public opinion, the time of occurrence of the public opinion, the location of occurrence of the public opinion, the subject of the public opinion, the public opinion prompt information, and the category of the public opinion, is identified as the public opinion data to be monitored.
[0027] In some embodiments, the acquired raw public opinion data undergoes preprocessing processes such as event classification, event subject extraction, event description, and geographic information determination to obtain the public opinion data to be monitored. Through these preprocessing processes, more public opinion elements can be identified from the raw data, providing more data features for subsequent monitoring of trending public opinion and improving the accuracy of early warning results. It is understood that after preprocessing the raw public opinion data, the resulting public opinion data to be monitored can be identified as preprocessed data. This facilitates subsequent identification of the public opinion data to be monitored based on this identification, thereby completing data filtering.
[0028] Among them, public opinion content refers to the entire content of the original public opinion data.
[0029] The subject of public opinion can be the core object that triggers or is directly related to public opinion, such as individuals, organizations, groups, or products; it is the "focus" of public opinion. For example, if a brand of mobile phones experiences widespread battery swelling, the manufacturer of that brand is the subject of public opinion.
[0030] Public opinion alerts are condensed and refined versions of the core content of public opinion, enabling the rapid dissemination of key information. For example, regarding the issue of bulging mobile phone batteries, the alert might read, "Users have complained about bulging batteries in a certain brand of mobile phone."
[0031] Public opinion categories are classifications of public opinion based on preset dimensions (such as sentiment, event type, scope of impact, etc.) to facilitate subsequent statistical analysis and targeted handling. For example, complaint types, exposure types, etc.
[0032] In one optional embodiment, determining the public opinion subject, public opinion alert information, and public opinion category of the original public opinion data based on the public opinion content includes: Extract the initial subject from the public opinion content, and determine the public opinion subject corresponding to the initial subject according to the preset subject mapping library; The public opinion content is extracted based on pre-configured prompts to obtain the public opinion prompt information; A pre-trained classification model is used to determine the classification category of the public opinion content, thus obtaining the public opinion category.
[0033] In some embodiments, prompts can be pre-set, and the feature collection capabilities of large models can be used to obtain the initial subject corresponding to the public opinion event in the public opinion content. Different users may use different names for the same public opinion subject, leading to differences in the initial subjects extracted from different work orders for the same public opinion subject. Therefore, a pre-set subject mapping library can be used to unify different initial subjects belonging to the same public opinion subject. For example, if the public opinion content is data related to complaints about excessive noise from Company A's production, the initial subject might be Company A, Limited Liability Company A, etc. To ensure consistency of the public opinion subject, all of these different initial subjects can be mapped to the same public opinion subject, namely Company A, for subsequent data processing.
[0034] The public opinion content is extracted based on pre-configured prompts to obtain the public opinion prompt information; Prompt words can be preset, and the summarizing capabilities of large models can be used to extract time-related descriptions from public opinion content to obtain public opinion prompts.
[0035] Pre-processed sample data can be used to train a classification model, resulting in a classification model. Then, public opinion content can be input into this model, which classifies the content to obtain the corresponding public opinion category. The sample data includes sample public opinion content and its corresponding classification category.
[0036] The time of occurrence of public opinion in the public opinion data to be monitored and the location of occurrence of public opinion can be the time of work order upload and the location of the uploading device, or it can be extracted from the time and location of public opinion content.
[0037] Step 102: Select target public opinion data that meets the preset hotspot filtering conditions from the public opinion data to be monitored.
[0038] In some embodiments, by setting preset hotspot filtering conditions, target public opinion data can be filtered from the public opinion data to be monitored. This can reduce information redundancy, improve the efficiency of public opinion processing, capture key public opinion in a timely manner, and reduce the probability of risk spread when monitoring public opinion hotspots.
[0039] The occurrence of public opinion hotspots is often related to the time and location of the event. Therefore, preset time periods and / or preset area ranges can be set as preset hotspot filtering conditions to filter the public opinion data to be monitored.
[0040] In an optional embodiment, the public opinion elements include the time and / or location of the public opinion event to be monitored; From the monitored public opinion data, target public opinion data that meets preset hotspot filtering conditions are selected, including: From the public opinion data to be monitored, the public opinion data whose occurrence time is within the preset time period and / or whose location is within the preset area are determined as the target public opinion data.
[0041] In some embodiments, when filtering target public opinion data, the public opinion data to be monitored that occurs within the preset time period and / or occurs within the preset area can be used as the target public opinion data. This can achieve accurate spatiotemporal positioning of public opinion, making public opinion analysis more focused on the scenario, responding more promptly, and making decisions more realistic, thus avoiding the inefficiency caused by generalized analysis.
[0042] Step 103: Determine the public opinion heat impact parameters of the target public opinion data based on the public opinion elements and the public opinion content.
[0043] The public opinion heat influence parameter is used to represent the degree of influence of the target public opinion data on public opinion heat.
[0044] In some embodiments, by describing the key attribute information and content of the target public opinion data, the public opinion heat impact parameters of the target public opinion data are determined. This enables a more accurate assessment of public opinion hotspots, a precise grasp of key public opinion variables, and a more evidence-based approach to decision-making, thereby improving the efficiency of responding to hot public opinion events.
[0045] In an optional embodiment, the public opinion elements include the time of occurrence of the public opinion, the location of the occurrence of the public opinion, the public opinion prompt information, the subject of the public opinion, and the category of the public opinion data to be monitored; Determining the public opinion heat impact parameters of the target public opinion data based on the aforementioned public opinion elements and content includes: Based on the time of the occurrence of the public opinion event, a first data volume of the target public opinion data within a preset time period is determined, and the submission rate of the target public opinion data is determined based on the first data volume. Semantic extraction is performed on the public opinion category, public opinion prompt information, and public opinion content to obtain a semantic vector, and the semantic vector is normalized to obtain the semantic proportion of the target public opinion data; Determine the textual features of the target public opinion data based on the content of the public opinion; Based on the location of the public opinion event, a second data volume of the target public opinion subject is determined within a preset area, and the spatial subject characteristics of the target public opinion data are determined based on the second data volume, wherein the target public opinion subject is any one of the public opinion subjects; The spatial clustering characteristics of the target public opinion data are determined based on the location where the public opinion occurred; The submission rate, semantic proportion, text features, spatial subject features, and spatial clustering features are determined as the parameters affecting public opinion heat.
[0046] In some embodiments, the preset time period can be set according to the actual situation, for example, by day, week or month, or it can be a specified time range.
[0047] The submission rate is obtained by statistically analyzing the first quantity of target public opinion data within a preset time period, calculating the difference between this first quantity and the historical average, and then calculating the ratio of this difference to the duration of the preset time period. The historical average can be the average quantity of target public opinion data over the previous few time periods.
[0048] Using the language processing capabilities of Natural Language Processing (NLP), based on public opinion content, public opinion categories, and public opinion prompts, semantic vectors for each public opinion category are extracted, and each semantic vector is normalized to obtain the semantic proportion.
[0049] Different public opinion content typically includes various word frequencies. Word frequency weights are pre-configured for each word frequency to obtain the word frequency weights in the public opinion content. A large model is used to perform sentiment analysis on the public opinion content to determine the sentiment polarity of the public opinion content. Based on the public opinion content, the text length of the public opinion content is determined. By calculating the product of word frequency weights and sentiment polarity, and the ratio of this product to the text length, the sum of the aforementioned ratios of each target public opinion data is the text feature.
[0050] By statistically analyzing the target public opinion subjects within a preset area (e.g., a specified square kilometer range) based on the location of the public opinion occurrence in the target public opinion data, a second data volume is obtained. Based on this second data volume, the spatial subject characteristics of the target public opinion data corresponding to the target public opinion subject are calculated.
[0051] In one optional embodiment, determining the spatial subject characteristics of the target public opinion data based on the second data volume includes: The spatial subject density is determined based on the second data volume and the preset area range. The spatial subject density is used to indicate the density of the target public opinion data corresponding to the target public opinion subject within the preset area range. The spatial subject alignment value is determined based on the third data volume and the total number of the public opinion subjects. The spatial subject alignment value is used to indicate the subject coverage of the target public opinion subject. The third data volume is the data volume of public opinion subjects other than the target public opinion subject.
[0052] In some embodiments, the preset area can be set according to actual conditions, for example, 1 square kilometer. The spatial entity density is calculated by calculating the ratio of the second data volume to the preset area. Thus, the spatial entity density can represent the density of a certain target public opinion entity within the preset area.
[0053] By calculating the ratio of the third data volume to the total number, and calculating the difference between 1 and the ratio, the spatial subject alignment value is obtained, thereby determining the subject coverage rate of the target public opinion subject within the preset area.
[0054] By calculating the spatial subject density and spatial subject alignment values, we can determine the density of a specific target public opinion subject within a specific area, thereby accurately grasping the spatial distribution pattern of public opinion and providing key evidence for early warning of subsequent hot public opinion events.
[0055] For each public opinion category, there will be multiple public opinion subjects. The target public opinion data within each category can be grouped according to the public opinion subject. Based on the location of the public opinion occurrence of all target public opinion data within a group, the coordinates of the center point are obtained. A geofencing area is determined with a radius set at the center point for geofencing filtering. The total number of target public opinion subjects within the geofencing area is determined using the location of the public opinion occurrence. A fourth number of target public opinion data including these subjects and a fifth number of target public opinion subjects not within the geofencing area are also determined. Then, by calculating a first ratio of the fourth number to the total number and a second ratio of the fifth number to the total number, and calculating the difference between 1 and these ratios, the product of the first ratio and the difference is determined as the spatial clustering feature.
[0056] The first ratio represents the core cluster density of the target public opinion subject within the geofenced area. A higher core cluster density indicates a larger number of target public opinion subjects within the geofenced area, and a more concentrated discussion surrounding that target public opinion subject. The second ratio represents the cross-regional conflict rate of the target public opinion subject, determining whether relevant public opinion data targeting the target public opinion subject exists outside the geofenced area.
[0057] The radius can be adjusted based on the region type where the target public opinion data is located. For example, a smaller radius (e.g., 2 kilometers) can be set in densely populated areas, while a larger radius (e.g., 5 kilometers) can be set in sparsely populated areas. By setting geofence filters, clustering parameters are dynamically adjusted to eliminate cross-regional noisy data.
[0058] Step 104: Determine hotspot indicators based on the public opinion heat impact parameters of the target public opinion data.
[0059] The hotspot index is used to represent the popularity of the public opinion indicated by the target public opinion data; In some embodiments, hotspot indicators are calculated using hotspot impact parameters that affect the popularity of public opinion, which can help analyze whether there are any major hotspots in the target public opinion data.
[0060] In an optional embodiment, the public opinion heat influence parameters include: the submission rate, semantic proportion, text features, spatial subject features, and spatial clustering features of the target public opinion data; The hotspot indicators determined by the public opinion heat impact parameters based on the target public opinion data include: Based on the submission rate and the spatial subject characteristics, determine the hotspot spatiotemporal indicators of the target public opinion data; Based on the semantic proportion, text features, spatial subject features, and spatial clustering features, the hot topic public opinion indicators of the target public opinion data are determined. The hot topic indicators are determined based on the hot topic spatiotemporal indicators and the hot topic public opinion indicators.
[0061] In some embodiments, since the submission rate and the spatial subject features can reflect the distribution of the target public opinion data in time and space, hotspot spatiotemporal indicators can be determined based on these two factors. Semantic proportion, text features, spatial subject features, and spatial clustering features can reflect public opinion characteristics in the events themselves within the target public opinion data. Therefore, hotspot public opinion indicators can be calculated based on these features, and then hotspot indicators can be obtained by calculating hotspot spatiotemporal indicators and hotspot public opinion indicators.
[0062] Furthermore, the hotspot indicator H can be calculated as follows: H = f(S, T, L) × (α·W + β·EA + γ·SC); f(S,T,L)= exp(S·T) / √L; Where exp(S·T) represents the exponential function for calculating the dot product of S and T, and √L represents the arithmetic square root of L.
[0063] Where T represents submission rate, S represents semantic proportion, W represents text features, L represents spatial subject density, EA represents spatial subject alignment value, and SC represents spatial clustering features. α, β, and γ are preset weight coefficients, where α ranges from 0.48 to 0.52, β ranges from 0.2 to 0.3, and γ ranges from 0.2 to 0.3, with a sum of 1.
[0064] Step 105: If the hot spot indicator is greater than the preset indicator threshold, generate an early warning message.
[0065] In some embodiments, the public opinion elements and content of the public opinion data to be monitored are used to determine the public opinion heat influence parameters that affect the public opinion heat, and hot spot indicators are determined based on these parameters. Hot spot analysis is carried out using all the information of the public opinion data to be monitored, thereby ensuring the accuracy of hot spot early warning.
[0066] For spatially denoised grouped data, when the rate of change of H value over time exceeds a preset threshold (e.g., 0.8), early warning information can be generated by summarizing hot topics, extracting hot topic descriptions, summarizing handling results, suggesting disposal measures, and providing early warning predictions for the corresponding public opinion data through the large model summarization capabilities. This will prompt relevant personnel to handle the hot topic in a timely manner.
[0067] Understandably, to improve the efficiency of monitoring public opinion hotspots, the data volume can be calculated for each filtered and grouped data. If the data volume is less than a preset value, it indicates that the amount of public opinion data corresponding to that event is small and does not possess the characteristics of becoming a public opinion hotspot. Therefore, such data is excluded from the scope of hot events and is not monitored. The preset value can be set according to the actual situation, for example, it can be set to 5.
[0068] For the monitoring methods of trending public opinion in this application, please refer to [link / reference]. Figure 2 By collecting public opinion events from different channels, the collected raw public opinion data undergoes preprocessing processes such as public opinion classification, event subject extraction, event description, and geographic information determination. The preprocessed data is then marked as preprocessed to obtain public opinion data to be monitored. This data is then grouped and filtered to achieve hotspot aggregation, and finally, hotspot indicators are calculated from the data.
[0069] To normalize multimodal subjects, a two-factor subject alignment mechanism based on text description and latitude / longitude coordinates is established, normalizing heterogeneous expressions of public opinion subjects and significantly improving accuracy compared to traditional methods. Dynamic radius geofencing technology is employed, automatically adjusting the clustering radius based on region type (e.g., 1.5km for commercial areas and 0.8km for residential areas), adaptively clustering spatially and improving spatial noise filtering efficiency. In the preprocessing, classification, and early warning stages, NLP capabilities are injected into the large model, enabling dynamic adjustment of semantic similarity thresholds through fine-tuning, resulting in significantly improved case grouping accuracy compared to rule engines. By setting up a three-dimensional coupled analysis system H=f(S,T,L)×(α·NLP+β·EA+γ·SC), the spatial dimension L and dynamic weight coefficients (α,β,γ) are introduced into the analysis framework, addressing the shortcomings of traditional two-dimensional models in identifying geographically related events.
[0070] Exemplary device Accordingly, this application also provides a monitoring device for trending public opinion, including: The acquisition unit is used to acquire public opinion data to be monitored. The public opinion data to be monitored includes public opinion elements and public opinion content. The public opinion elements include key attribute information used to describe the public opinion data to be monitored. The filtering unit is used to filter target public opinion data that meets preset hotspot filtering conditions from the public opinion data to be monitored. The first determining unit is used to determine the public opinion heat influence parameter of the target public opinion data based on the public opinion elements and the public opinion content. The public opinion heat influence parameter is used to represent the degree of influence of the target public opinion data on the public opinion heat. The second determining unit is used to determine hot spot indicators based on the public opinion heat influence parameters of the target public opinion data, wherein the hot spot indicators are used to represent the heat of public opinion indicated by the target public opinion data; The early warning unit is used to generate early warning information when the hot spot indicator exceeds a preset indicator threshold.
[0071] Optionally, the acquisition unit is specifically used for: Obtain raw public opinion data, which includes public opinion content, time of occurrence, and location of occurrence; Based on the content of the public opinion, the subject of the public opinion, the information prompts, and the category of the public opinion in the original public opinion data are determined. The original public opinion data, including the content of the public opinion, the time of occurrence of the public opinion, the location of occurrence of the public opinion, the subject of the public opinion, the public opinion prompt information, and the category of the public opinion, is identified as the public opinion data to be monitored.
[0072] Optionally, based on the public opinion content, the public opinion subject, public opinion alert information, and public opinion category of the original public opinion data are determined, including: Extract the initial subject from the public opinion content, and determine the public opinion subject corresponding to the initial subject according to the preset subject mapping library; The public opinion content is extracted based on pre-configured prompts to obtain the public opinion prompt information; A pre-trained classification model is used to determine the classification category of the public opinion content, thus obtaining the public opinion category.
[0073] Optionally, the preset hotspot filtering conditions include a preset time period and / or a preset regional range; the public opinion elements include the time and / or location of the public opinion data to be monitored. The filtering unit is specifically used for: From the public opinion data to be monitored, the public opinion data whose occurrence time is within the preset time period and / or whose location is within the preset area are determined as the target public opinion data.
[0074] Optionally, the public opinion elements include the time of occurrence of the public opinion, the location of the occurrence of the public opinion, the public opinion prompt information, the subject of the public opinion, and the category of the public opinion data to be monitored; The first determining unit is specifically used for: Based on the time of the occurrence of the public opinion event, a first data volume of the target public opinion data within a preset time period is determined, and the submission rate of the target public opinion data is determined based on the first data volume. Semantic extraction is performed on the public opinion category, public opinion prompt information, and public opinion content to obtain a semantic vector, and the semantic vector is normalized to obtain the semantic proportion of the target public opinion data; Determine the textual features of the target public opinion data based on the content of the public opinion; Based on the location of the public opinion event, a second data volume of the target public opinion subject is determined within a preset area, and the spatial subject characteristics of the target public opinion data are determined based on the second data volume, wherein the target public opinion subject is any one of the public opinion subjects; The spatial clustering characteristics of the target public opinion data are determined based on the location where the public opinion occurred; The submission rate, semantic proportion, text features, spatial subject features, and spatial clustering features are determined as the parameters affecting public opinion heat.
[0075] Optionally, the spatial subject characteristics of the target public opinion data are determined based on the second data volume, including: The spatial subject density is determined based on the second data volume and the preset area range. The spatial subject density is used to indicate the density of the target public opinion data corresponding to the target public opinion subject within the preset area range. The spatial subject alignment value is determined based on the third data volume and the total number of the public opinion subjects. The spatial subject alignment value is used to indicate the subject coverage of the target public opinion subject. The third data volume is the data volume of public opinion subjects other than the target public opinion subject.
[0076] Optionally, the parameters affecting public opinion heat include: the submission rate, semantic proportion, text features, spatial subject features, and spatial clustering features of the target public opinion data; The second determining unit is specifically used for: Based on the submission rate and the spatial subject characteristics, determine the hotspot spatiotemporal indicators of the target public opinion data; Based on the semantic proportion, text features, spatial subject features, and spatial clustering features, the hot topic public opinion indicators of the target public opinion data are determined. The hot topic indicators are determined based on the hot topic spatiotemporal indicators and the hot topic public opinion indicators.
[0077] The hot topic monitoring device provided in this embodiment belongs to the same application concept as the hot topic monitoring method provided in the above embodiments of this application. It can execute the method provided in any of the above embodiments of this application and has the corresponding functional modules and beneficial effects of the method. Technical details not described in detail in this embodiment can be found in the specific processing content of the hot topic monitoring method provided in the above embodiments of this application, and will not be repeated here.
[0078] The functions implemented by each unit in the above-mentioned monitoring device for trending public opinion can be implemented by the same or different processors, and this application embodiment does not limit this.
[0079] It should be understood that each unit in the above device can be implemented by a processor calling software. For example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of each unit in the device. The processor can be a general-purpose processor, such as a CPU or microprocessor, and the memory can be internal or external to the device. Alternatively, the units in the device can be implemented as hardware circuits. By designing the hardware circuits, some or all of the unit functions can be implemented. The hardware circuits can be understood as one or more processors. For example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units are implemented by designing the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a PLD, such as an FPGA, which can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files to implement the functions of some or all of the above units. All units in the above device can be implemented entirely by a processor calling software, entirely by hardware circuits, or partially by a processor calling software with the remaining parts implemented by hardware circuits.
[0080] In this application embodiment, a processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and execution capabilities, such as a CPU, microprocessor, GPU, or DSP. In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented as an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the processor loading instructions to implement the functions of some or all of the above units. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, or DPU.
[0081] As can be seen, each unit in the above device can be one or more processors (or processing circuits) configured to implement the above methods, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.
[0082] Furthermore, the units in the above devices can be integrated in whole or in part, or they can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a System-on-Chip (SoC). The SoC may include at least one processor for implementing any of the above methods or implementing the functions of the units in the device. The at least one processor may be of different types, such as CPU and FPGA, CPU and artificial intelligence processor, CPU and GPU, etc.
[0083] Exemplary electronic devices Another embodiment of this application also provides an electronic device, see [link to relevant documentation] Figure 3 As shown, the device includes: Memory 300 and processor 310; The memory 300 is connected to the processor 310 and is used to store programs; The processor 310 is used to implement the hot topic monitoring method disclosed in any of the above embodiments by running the program stored in the memory 300.
[0084] Specifically, the monitoring equipment for the aforementioned hot public opinion issues may also include: a bus, a communication interface 320, an input device 330, and an output device 340.
[0085] The processor 310, memory 300, communication interface 320, input device 330, and output device 340 are interconnected via a bus. Among them: A bus can include a pathway for transmitting information between various components of a computer system.
[0086] The processor 310 can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present invention. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.
[0087] Processor 310 may include a main processor, as well as a baseband chip, modem, etc.
[0088] The memory 300 stores a program that executes the technical solution of this invention, and may also store an operating system and other key business functions. Specifically, the program may include program code, which includes computer operation instructions. More specifically, the memory 300 may include read-only memory (ROM), other types of static storage devices capable of storing static information and instructions, random access memory (RAM), other types of dynamic storage devices capable of storing information and instructions, disk storage, flash memory, etc.
[0089] Input device 330 may include a device for receiving user input data and information, such as a keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor.
[0090] Output device 340 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.
[0091] The communication interface 320 may include a device that uses any transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.
[0092] The processor 310 executes the program stored in the memory 300 and calls other devices, which can be used to implement the various steps of any of the hot public opinion monitoring methods provided in the above embodiments of this application.
[0093] Exemplary computer program products and storage media In addition to the methods and devices described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the monitoring methods for hot public opinion according to various embodiments of this application as described in any of the above embodiments of this specification.
[0094] The computer program product can be written in any combination of one or more programming languages to perform the operations of the embodiments of this application. The programming languages include object-oriented programming languages such as Java and C++, as well as conventional procedural programming languages such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.
[0095] Furthermore, embodiments of this application may also be storage media storing a computer program, which is executed by a processor through steps in the hot topic monitoring method according to various embodiments of this application described above. Specifically, the following steps can be implemented: Acquire public opinion data to be monitored, which includes public opinion elements and public opinion content. The public opinion elements include key attribute information used to describe the public opinion data to be monitored. From the public opinion data to be monitored, target public opinion data that meets the preset hotspot filtering conditions are selected; The public opinion heat influence parameter of the target public opinion data is determined based on the public opinion elements and the public opinion content. The public opinion heat influence parameter is used to represent the degree of influence of the target public opinion data on the public opinion heat. Hotspot indicators are determined based on the public opinion heat impact parameters of the target public opinion data, and the hotspot indicators are used to represent the heat of public opinion indicated by the target public opinion data; When the hot spot indicator exceeds a preset indicator threshold, an early warning message is generated.
[0096] For the foregoing method embodiments, in order to simplify the description, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.
[0097] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For apparatus embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.
[0098] The steps in the methods of the various embodiments of this application can be adjusted, merged, or deleted in order according to actual needs, and the technical features described in each embodiment can be replaced or combined.
[0099] The modules and sub-modules in the apparatus and terminal in the various embodiments of this application can be merged, divided, and deleted according to actual needs.
[0100] It should be understood that the disclosed terminals, devices, and methods can be implemented in other ways, given the several embodiments provided in this application. For example, the terminal embodiments described above are merely illustrative. For instance, the division of modules or sub-modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple sub-modules or modules may be combined or integrated into another module, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.
[0101] The modules or submodules described as separate components may or may not be physically separate. The components that constitute a module or submodule may or may not be physical modules or submodules; that is, they may be located in one place or distributed across multiple network modules or submodules. Some or all of the modules or submodules can be selected to achieve the purpose of this embodiment's solution, depending on actual needs.
[0102] Furthermore, the functional modules or sub-modules in the various embodiments of this application can be integrated into one processing module, or each module or sub-module can exist physically separately, or two or more modules or sub-modules can be integrated into one module. The integrated modules or sub-modules described above can be implemented in hardware or in the form of software functional modules or sub-modules.
[0103] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0104] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software unit executed by a processor, or a combination of both. The software unit can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.
[0105] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one subject or operation from another, and do not necessarily require or imply any such actual relationship or order between these subjects or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0106] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for monitoring trending public opinion, characterized in that, include: Acquire public opinion data to be monitored, which includes public opinion elements and public opinion content. The public opinion elements include key attribute information used to describe the public opinion data to be monitored. From the public opinion data to be monitored, target public opinion data that meets the preset hotspot filtering conditions are selected; The public opinion heat influence parameter of the target public opinion data is determined based on the public opinion elements and the public opinion content. The public opinion heat influence parameter is used to represent the degree of influence of the target public opinion data on the public opinion heat. Hotspot indicators are determined based on the public opinion heat impact parameters of the target public opinion data, and the hotspot indicators are used to represent the heat of public opinion indicated by the target public opinion data; When the hot spot indicator exceeds a preset indicator threshold, an early warning message is generated.
2. The method according to claim 1, characterized in that, Obtain the public opinion data to be monitored, including: Obtain raw public opinion data, which includes public opinion content, time of occurrence, and location of occurrence; Based on the content of the public opinion, the subject of the public opinion, the information prompts, and the category of the public opinion in the original public opinion data are determined. The original public opinion data, including the content of the public opinion, the time of occurrence of the public opinion, the location of occurrence of the public opinion, the subject of the public opinion, the public opinion prompt information, and the category of the public opinion, is identified as the public opinion data to be monitored.
3. The method according to claim 2, characterized in that, Based on the content of the public opinion, the subject of the public opinion, the public opinion alert information, and the public opinion category of the original public opinion data are determined, including: Extract the initial subject from the public opinion content, and determine the public opinion subject corresponding to the initial subject according to the preset subject mapping library; The public opinion content is extracted based on pre-configured prompts to obtain the public opinion prompt information; A pre-trained classification model is used to determine the classification category of the public opinion content, thus obtaining the public opinion category.
4. The method according to claim 1, characterized in that, The preset hotspot filtering conditions include a preset time period and / or a preset area range; the public opinion elements include the time and / or location of the public opinion data to be monitored. From the monitored public opinion data, target public opinion data that meets preset hotspot filtering conditions are selected, including: From the public opinion data to be monitored, the public opinion data whose occurrence time is within the preset time period and / or whose location is within the preset area are determined as the target public opinion data.
5. The method according to claim 1, characterized in that, The public opinion elements include the time of occurrence of the public opinion, the location of the public opinion, the public opinion prompt information, the subject of the public opinion, and the category of the public opinion data to be monitored; Determining the public opinion heat impact parameters of the target public opinion data based on the aforementioned public opinion elements and content includes: Based on the time of the occurrence of the public opinion event, a first data volume of the target public opinion data within a preset time period is determined, and the submission rate of the target public opinion data is determined based on the first data volume. Semantic extraction is performed on the public opinion category, public opinion prompt information, and public opinion content to obtain a semantic vector, and the semantic vector is normalized to obtain the semantic proportion of the target public opinion data; Determine the textual features of the target public opinion data based on the content of the public opinion; Based on the location of the public opinion event, a second data volume of the target public opinion subject is determined within a preset area, and the spatial subject characteristics of the target public opinion data are determined based on the second data volume, wherein the target public opinion subject is any one of the public opinion subjects; The spatial clustering characteristics of the target public opinion data are determined based on the location where the public opinion occurred; The submission rate, semantic proportion, text features, spatial subject features, and spatial clustering features are determined as the parameters affecting public opinion heat.
6. The method according to claim 5, characterized in that, Based on the second data volume, the spatial subject characteristics of the target public opinion data are determined, including: The spatial subject density is determined based on the second data volume and the preset area range. The spatial subject density is used to indicate the density of the target public opinion data corresponding to the target public opinion subject within the preset area range. The spatial subject alignment value is determined based on the third data volume and the total number of the public opinion subjects. The spatial subject alignment value is used to indicate the subject coverage of the target public opinion subject. The third data volume is the data volume of public opinion subjects other than the target public opinion subject.
7. The method according to claim 1 or 5, characterized in that, The parameters affecting public opinion heat include: the submission rate, semantic proportion, text features, spatial subject features, and spatial clustering features of the target public opinion data; The hotspot indicators determined by the public opinion heat impact parameters based on the target public opinion data include: Based on the submission rate and the spatial subject characteristics, determine the hotspot spatiotemporal indicators of the target public opinion data; Based on the semantic proportion, text features, spatial subject features, and spatial clustering features, the hot topic public opinion indicators of the target public opinion data are determined. The hot topic indicators are determined based on the hot topic spatiotemporal indicators and the hot topic public opinion indicators.
8. A monitoring device for trending public opinion, characterized in that, include: The acquisition unit is used to acquire public opinion data to be monitored. The public opinion data to be monitored includes public opinion elements and public opinion content. The public opinion elements include key attribute information used to describe the public opinion data to be monitored. The filtering unit is used to filter target public opinion data that meets preset hotspot filtering conditions from the public opinion data to be monitored. The first determining unit is used to determine the public opinion heat influence parameter of the target public opinion data based on the public opinion elements and the public opinion content. The public opinion heat influence parameter is used to represent the degree of influence of the target public opinion data on the public opinion heat. The second determining unit is used to determine hot spot indicators based on the public opinion heat influence parameters of the target public opinion data, wherein the hot spot indicators are used to represent the heat of public opinion indicated by the target public opinion data; The early warning unit is used to generate early warning information when the hot spot indicator exceeds a preset indicator threshold.
9. An electronic device, characterized in that, Including memory and processor; The memory is connected to the processor and is used to store programs; The processor is used to implement the method for monitoring hot public opinion as described in any one of claims 1 to 7 by running the program in the memory.
10. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the method for monitoring trending public opinion as described in any one of claims 1 to 7.