Methods, devices, equipment, and storage media for analyzing event data in government systems

Abstract

This application provides a method, apparatus, device, and storage medium for analyzing event data in a government affairs system. The method includes: acquiring event data when new event data is detected being updated in the government affairs system's database; calculating an event score based on the event data and a pre-configured risk hot word automatic perception model; and determining whether the event corresponding to the event data will evolve into a public opinion event based on the event score and preset public opinion event judgment conditions. The method of this application, by calculating the event score corresponding to the event data through a configured risk hot word automatic perception model and combining it with preset public opinion judgment conditions, can accurately determine whether a related event will evolve into a public opinion event.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, device and storage medium for analyzing event data in a government system. Background Technology

[0002] With the rapid development of information technology, online incidents, sensitive topics, and social events in the government sector have become increasingly common. Government departments need to promptly grasp the information dynamics, risk development, and spread of these events.

[0003] In related technologies, government departments can use public opinion monitoring tools to monitor relevant events. However, these tools are based on human experience and have low accuracy in analyzing and predicting relevant events, making it difficult to accurately determine whether an event will escalate into a public opinion crisis. Summary of the Invention

[0004] This application provides a method, apparatus, equipment, and storage medium for analyzing event data in a government affairs system, which can accurately determine whether a related event will evolve into a public opinion event.

[0005] Firstly, this application provides a method for analyzing event data in a government affairs system, including:

[0006] When it is detected that new event data has been updated in the database of the government affairs system, the event data is retrieved;

[0007] Based on the event data and the pre-configured risk hot word automatic perception model, an event score is calculated. The event score is used to indicate the likelihood that the event corresponding to the event data will evolve into a public opinion event. The risk hot word automatic perception model is used to calculate the comprehensive score of the part of speech, level of detail, and frequency of occurrence of risk hot words in the event data.

[0008] Based on the event score and preset public opinion event judgment conditions, it is determined whether the event corresponding to the event data will evolve into a public opinion event.

[0009] In one possible implementation, the step of calculating the event score based on the event data and a pre-configured risk hot word automatic perception model includes:

[0010] The event data was segmented using a forward longest matching word segmentation algorithm to obtain multiple event keywords.

[0011] The event keywords are input into the risk hot word automatic perception model to calculate the event score.

[0012] In one possible implementation, the automatic risk hot word perception model includes a hidden Markov algorithm, a word length calculation algorithm, and a word frequency calculation algorithm;

[0013] Accordingly, the step of inputting the multiple event keywords into the risk hot word automatic perception model and calculating the event score includes:

[0014] Based on the multiple event keywords and the preset feature library of hot words for government risk, the Hidden Markov algorithm is used to calculate the part-of-speech scores of the multiple event keywords.

[0015] Based on the multiple event keywords and the preset government risk hot word feature library, the word length calculation algorithm is used to calculate the detail score of the event data;

[0016] Based on the multiple event keywords and the feature library of government risk hot words, the word frequency score of risk hot words among the multiple event keywords is calculated using the word frequency calculation algorithm.

[0017] The event score is calculated based on the preset weights of each type of score, the part-of-speech score, the detail score, and the word frequency score;

[0018] The government affairs risk hot word feature library stores key digital indicators of multiple public opinion events, including event type, event occurrence time, event address type, event sensitivity, and event level.

[0019] In one possible implementation, the word length calculation algorithm is the longest common prefix algorithm, and the word frequency calculation algorithm is the TF-IDF model algorithm.

[0020] In one possible implementation, the calculation of the event score based on the preset weights of each type score, the part-of-speech score, the detail score, and the word frequency score includes:

[0021] The event score is obtained by weighting the part-of-speech score, the detail score, and the word frequency score according to the weight of each type score.

[0022] In one possible implementation, the criteria for judging public opinion events include: events with an event score greater than a preset score threshold will evolve into public opinion events;

[0023] Accordingly, determining whether the event corresponding to the event data will evolve into a public opinion event based on the event score and preset public opinion event judgment conditions includes:

[0024] If the event score is greater than the score threshold, it is determined that the event corresponding to the event data will evolve into a public opinion event.

[0025] If the event score is less than or equal to the score threshold, it is determined that the event corresponding to the event data will not evolve into a public opinion event.

[0026] In one possible implementation, the method further includes:

[0027] After receiving event information from other devices in the government affairs system, the database of the government affairs system is probed and compared based on the event information to determine whether new event data associated with the event information has been updated in the database.

[0028] Secondly, this application provides an analysis device for event data in a government affairs system, comprising:

[0029] The acquisition module is used to acquire the event data when it is detected that new event data has been updated in the database of the government affairs system;

[0030] The first processing module is used to calculate an event score based on the event data and a pre-configured risk hot word automatic perception model. The event score is used to indicate the likelihood that the event corresponding to the event data will evolve into a public opinion event. The risk hot word automatic perception model is used to calculate the comprehensive score of the part of speech, level of detail, and frequency of occurrence of risk hot words in the event data.

[0031] The second processing module is used to determine whether the event corresponding to the event data will evolve into a public opinion event based on the event score and preset public opinion event judgment conditions.

[0032] In one possible implementation, the first processing module is specifically used for:

[0033] The event data was segmented using a forward longest matching word segmentation algorithm to obtain multiple event keywords.

[0034] The event keywords are input into the risk hot word automatic perception model to calculate the event score.

[0035] In one possible implementation, the automatic risk hot word perception model includes a hidden Markov algorithm, a word length calculation algorithm, and a word frequency calculation algorithm;

[0036] Accordingly, the first processing module is specifically used for:

[0037] Based on the multiple event keywords and the preset government risk hot word feature library, the hidden Markov algorithm is used to calculate the part-of-speech scores of the multiple event keywords.

[0038] Based on the multiple event keywords and the preset government risk hot word feature library, the word length calculation algorithm is used to calculate the detail score of the event data;

[0039] Based on the multiple event keywords and the feature library of government risk hot words, the word frequency score of risk hot words among the multiple event keywords is calculated using the word frequency calculation algorithm.

[0040] The event score is calculated based on the preset weights of each type of score, the part-of-speech score, the detail score, and the word frequency score;

[0041] The government affairs risk hot word feature library stores key digital indicators of multiple public opinion events, including event type, event occurrence time, event address type, event sensitivity, and event level.

[0042] In one possible implementation, the word length calculation algorithm is the longest common prefix algorithm, and the word frequency calculation algorithm is the TF-IDF model algorithm.

[0043] In one possible implementation, the first processing module is specifically used for:

[0044] The event score is obtained by weighting the part-of-speech score, the detail score, and the word frequency score according to the weight of each type score.

[0045] In one possible implementation, the criteria for judging public opinion events include: events with an event score greater than a preset score threshold will evolve into public opinion events;

[0046] Accordingly, the second processing module is specifically used for:

[0047] If the event score is greater than the score threshold, it is determined that the event corresponding to the event data will evolve into a public opinion event.

[0048] If the event score is less than or equal to the score threshold, it is determined that the event corresponding to the event data will not evolve into a public opinion event.

[0049] In one possible implementation, the apparatus further includes a third processing module, the third processing module being used for:

[0050] After receiving event information from other devices in the government affairs system, the database of the government affairs system is probed and compared based on the event information to determine whether new event data associated with the event information has been updated in the database.

[0051] Thirdly, this application provides an electronic device, including: a processor, a memory, and an interaction interface;

[0052] The memory stores computer-executed instructions;

[0053] The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any of the first aspects.

[0054] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, are used to implement the method described in any of the first aspects.

[0055] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the first aspects.

[0056] This application provides a method, apparatus, device, and storage medium for analyzing event data in a government affairs system. It can acquire event data when new event data is detected updated in the database of the government affairs system. Based on the event data and a pre-configured automatic risk hot word perception model, an event score is calculated. Based on the event score and preset public opinion event judgment conditions, it is determined whether the event corresponding to the event data will evolve into a public opinion event. In the above process, the event score corresponding to the event data is calculated through the configured automatic risk hot word perception model, and combined with the preset public opinion judgment conditions, it is possible to accurately determine whether the relevant event will evolve into a public opinion event. Attached Figure Description

[0057] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0058] Figure 1 A schematic diagram illustrating the application scenarios provided in the embodiments of this application;

[0059] Figure 2 A flowchart illustrating a method for analyzing event data in a government system, provided as an embodiment of this application;

[0060] Figure 3 A flowchart illustrating another method for analyzing event data in a government system provided in this application embodiment;

[0061] Figure 4 A schematic diagram illustrating the execution process of an event data analysis method in a government system, provided as an embodiment of this application;

[0062] Figure 5 A schematic diagram of the structure of an event data analysis device in a government system provided in this application embodiment;

[0063] Figure 6 A schematic diagram of the structure of another event data analysis device in a government system provided in this application embodiment;

[0064] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0065] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0066] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0067] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0068] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0069] It should be noted that the method, apparatus, equipment and storage medium for analyzing event data in a government system provided in this application can be used in the field of artificial intelligence technology, or in any field other than artificial intelligence technology. The application field of the method, apparatus, equipment and storage medium for analyzing event data in a government system provided in this application is not limited.

[0070] To facilitate understanding, the following will be combined with... Figure 1 The application scenarios applicable to the embodiments of this application will be described.

[0071] Figure 1 This is a schematic diagram illustrating an application scenario provided in an embodiment of this application. Please refer to [link / reference]. Figure 1 Event data can be input into the risk hot word automatic perception model. The model calculates an event score for the event data and compares this score with preset public opinion event judgment criteria to determine whether the event data corresponds to a public opinion event. For example, if the public opinion event judgment criterion is that the event score is greater than 60, then the event corresponding to that score is a public opinion event. Alternatively, event data can be input into the risk hot word automatic perception model. If the model calculates an event score of 80, and this score is compared with preset public opinion event judgment criteria, then the event data can be confirmed as a public opinion event.

[0072] In related technologies, government departments can use public opinion monitoring tools to monitor relevant events. However, these tools are based on human experience and have low accuracy in analyzing and predicting relevant events, making it difficult to accurately determine whether an event will escalate into a public opinion crisis.

[0073] In this embodiment, event data can be acquired when new event data is detected in the database of the government affairs system. Based on the event data and a pre-configured automatic risk keyword perception model, an event score is calculated. Based on the event score and preset public opinion event judgment conditions, it is determined whether the event corresponding to the event data will evolve into a public opinion event. By calculating the event score corresponding to the event data through the configured automatic risk keyword perception model and combining it with preset public opinion judgment conditions, it is possible to accurately determine whether a related event will evolve into a public opinion event.

[0074] The technical solutions shown in this application will now be described in detail through specific embodiments. It should be noted that the following embodiments may exist independently or in combination with each other; for the same or similar content, the description will not be repeated in different embodiments.

[0075] Figure 2 This is a flowchart illustrating a method for analyzing event data in a government affairs system, as provided in an embodiment of this application. Please refer to [link / reference]. Figure 2 The method may include:

[0076] S101. When new event data is detected to have been updated in the database of the government affairs system, retrieve the event data.

[0077] The executing entity in this application embodiment can be an electronic device or an event data analysis device in a government affairs system installed in an electronic device. The event data analysis device in a government affairs system can be implemented through software or a combination of software and hardware. For ease of understanding, the following description uses an electronic device as the executing entity.

[0078] Electronic devices can retrieve new event data from the database of the government system. Specifically, the database of the government system can store multiple events and the event data corresponding to each event. Whenever a new event and its corresponding event data are updated to the database of the government system, the electronic device can retrieve the event data of that event from the database of the government system.

[0079] Optionally, event data could be a message received by the government system that may have a significant impact and attract the attention of a large number of users.

[0080] For example, the government system's database currently contains Event 1 and its corresponding event data 1. Event 1 is no longer attracting attention and will not escalate into a public opinion event. A new Event 2 and its corresponding event data 2 are then updated to the government system's database. Event 2 could be: "Natural Disaster Event," and event data 2 could be: "City N in coastal Province M was affected by a typhoon. The typhoon had a wide impact area, causing 5 million yuan in losses." Electronic devices can retrieve event data 2 from the government system's database.

[0081] S102. Calculate the event score based on the event data and the pre-configured risk hot word automatic perception model.

[0082] To obtain the event score corresponding to the event data, the event data can be input into a pre-configured risk hot word automatic perception model. The model then calculates the event score. Specifically, a forward longest matching word segmentation algorithm can be used to segment the event data, obtaining multiple event keywords. These keywords are then input into the risk hot word automatic perception model to calculate the event score. The event score indicates the likelihood that the event corresponding to the event data will evolve into a public opinion event. The risk hot word automatic perception model calculates a comprehensive score based on the part-of-speech, level of detail, and frequency of occurrence of risk hot words in the event data.

[0083] The forward longest matching word segmentation algorithm can be used to segment event data and remove some useless modal particles from the segmentation results, such as modal particles like "le" and "de", thereby obtaining multiple event keywords. When segmenting event data, it is possible to scan the event data from left to right and use left points, right points, and word points to segment the event data. Find the position of each word in the event data where it does not match any other word on the far right. Here, the left point and the right point represent words in the event data, and the word point represents the word itself.

[0084] For example, the event data 2 is: "Coastal M Province N City has suffered from the impact of a typhoon. The impact of this typhoon is large, causing a loss of 5 million yuan." Using the forward longest matching word segmentation algorithm to segment event data 2, the segmentation result can be: "Coastal, M Province, N City, suffered, le, typhoon impact, this time, typhoon impact, scope, large, caused, le, 5 million yuan, loss". After removing some useless modal particles, the corresponding keywords for multiple events 2 can be: "M Province, N City, suffered, typhoon impact, caused, 5 million yuan, loss". After obtaining multiple event 2 keywords, the multiple event 2 keywords can be input into the risk hot word automatic perception model to calculate the event score. Here, the event score can be 60 points.

[0085] S103. Determine whether the event corresponding to the event data will evolve into a public opinion event according to the event score and the preset public opinion event judgment conditions.

[0086] When calculating the event score through the risk hot word automatic perception model, it is possible to determine whether the event corresponding to the event data will evolve into a public opinion event according to the preset public opinion judgment conditions. In specific implementation, the judgment conditions for public opinion events can be preset, and the judgment conditions for public opinion events are compared with the calculated event score, and whether the event corresponding to the event data will evolve into a public opinion event is determined through the comparison result.

[0087] In a specific implementation manner, the public opinion event judgment conditions include: an event with an event score greater than the preset score threshold will evolve into a public opinion event. Correspondingly, determining whether the event corresponding to the event data will evolve into a public opinion event according to the event score and the preset public opinion event judgment conditions includes the following two situations.

[0088] Situation 1: If the event score is greater than the score threshold, it is determined that the event corresponding to the event data will evolve into a public opinion event;

[0089] For example, if the preset criteria for judging public opinion events are: the preset score threshold is 50 points, and the risk hot word automatic perception model calculates the event score corresponding to event data 2 as 60 points, since the calculated event score is greater than the preset score threshold, then event data 2: "N city in coastal province M was affected by a typhoon. The typhoon had a wide impact area and caused a loss of 5 million yuan." The corresponding event 2: "natural disaster event" will evolve into a public opinion event.

[0090] Scenario 2: If the event score is less than or equal to the score threshold, then the event corresponding to the event data will not evolve into a public opinion event.

[0091] For example, if the preset criteria for judging public opinion events are: the preset score threshold is 50 points, and the risk hot word automatic perception model calculates the event score corresponding to event data 2 as 40 points, since the calculated event score is less than the preset score threshold, then it can be confirmed that event data 2: "City N in coastal province M was affected by a typhoon. The typhoon had a wide impact area and caused a loss of 5 million yuan", and the corresponding event 2: "natural disaster event" will not evolve into a public opinion event.

[0092] In this embodiment, event data can be acquired when new event data is detected in the database of the government affairs system. Based on the event data and a pre-configured automatic risk keyword perception model, an event score is calculated. Then, based on the event score and preset public opinion event judgment conditions, it is determined whether the event corresponding to the event data will evolve into a public opinion event. During the judgment process, the configured automatic risk keyword perception model calculates the event score corresponding to the event data, and by comparing the results with the preset public opinion event judgment conditions, it is possible to accurately determine whether the relevant event will evolve into a public opinion event.

[0093] Below, in Figure 2 Based on the illustrated embodiments, combined with Figure 3 The analysis methods for the above event data will be explained in detail.

[0094] Figure 3 For a flowchart illustrating another method for analyzing event data in a government system provided in this application embodiment, please refer to [link / reference]. Figure 3 The method may include:

[0095] S201. After receiving event information sent by other devices in the government affairs system, the database of the government affairs system is probed and compared according to the event information to determine whether the database has been updated with new event data associated with the event information.

[0096] After receiving event information from other devices in the government system, electronic devices can perform probe-style access and comparison of the government system's database based on the event information. If the access results show that the government system's database has updated event data, the updated event data can be compared with the event information sent by other devices. If the comparison results show that the updated event data is related to the event information, it can be determined whether the database has been updated with new event data related to the event information.

[0097] Optionally, the event information may include multiple event data. For example, event information 1 may include event data 1, event data 2, and event data 3.

[0098] After receiving event information 1 from other devices in the government system, the electronic device receives event information 1, which includes event data 1, event data 2, and event data 3. The government system's database can be probed and compared based on event information 1. If the access result shows that the government system's database has updated event data 3, then the updated event data 3 can be compared with event information 1 sent by other devices. If the comparison result shows that the updated event data 3 is related to event information 1, then it can be determined whether a new event data 3 associated with event information 1 has been updated in the database.

[0099] S202. When it is detected that new event data has been updated in the database of the government affairs system, retrieve the event data.

[0100] It should be noted that the specific execution process of step S202 can be found in the specific execution process of step S101, and will not be repeated here.

[0101] S203. The event data is segmented using the forward longest matching word segmentation algorithm to obtain multiple event keywords.

[0102] After obtaining the event data, the forward longest matching word segmentation algorithm can be used to segment the event data and obtain multiple event keywords from the segmentation results.

[0103] For example, if event data 3 is: "A tiger escaped from the zoo and fled to village D in district C of city B in province A", then the matching result after using the forward longest matching word segmentation algorithm can be: "A province, city B, district C, have, tiger, from, zoo, escape, escape, to, village D". The corresponding keywords for multiple events 3 can be: "A province, city B, district C, tiger, zoo, escape, village D".

[0104] S204. Based on multiple event keywords and a pre-set feature library of hot words for government risk, the Hidden Markov algorithm is used to calculate the part-of-speech scores of multiple event keywords.

[0105] When obtaining multiple event keywords using the forward longest matching word segmentation algorithm, a pre-set government risk hot word feature library can be used to perform part-of-speech tagging on the multiple event keywords, achieve semantic classification, and calculate the part-of-speech scores of the multiple event keywords.

[0106] Hidden Markov algorithms can generate hidden and observed states through a random process and determine the state transition probability distribution based on the dependencies between states, thereby describing the process of randomly generating observation sequences from hidden Markov chains. They can also tag keywords with part-of-speech tags to achieve semantic classification.

[0107] In one specific implementation, the government affairs risk hot word feature library stores key digital indicators of multiple public opinion events, including event type, event occurrence time, event address type, event sensitivity, and event level.

[0108] Optionally, the key numerical indicators in the government affairs risk hot word feature database may include: number of deaths, number of seriously injured, number of slightly injured, number of missing persons, number of trapped persons, number of poisoned persons, economic and property losses, etc.; event types may include: social security, public health, natural disasters, public opinion events, etc.; the event occurrence time may be specified down to the year, month, and day; the event location type may include: district / county, city, province; event sensitivity may include: general, insensitive, sensitive; and the event level may be divided into 5 levels, with the severity of the event gradually increasing from the lowest to the highest.

[0109] For example, using the forward longest matching word segmentation algorithm, multiple event keywords are obtained as follows: "Province A, City B, District C, Tiger, Zoo, Escape, Village D". A Hidden Markov Model (HMM) algorithm can be used to perform part-of-speech tagging on these keywords, achieving semantic classification. The calculated part-of-speech score for these multiple event keywords can be 70 points. Specifically, "Province A, City B, District C, Village D" is tagged with part-of-speech tags to classify it as an event address type, resulting in part-of-speech score 1 (75 points). "Tiger, Escape" is tagged with part-of-speech tags to classify it as social security, resulting in part-of-speech score 2 (70 points). "Tiger escaping from the zoo" can be classified as a sensitive event of public concern, resulting in part-of-speech score 3 (65 points). Therefore, the total part-of-speech score for these multiple event keywords is 70 points, which can be the average of multiple different types of part-of-speech scores.

[0110] S205. Based on multiple event keywords and a pre-set database of hot words for government risk, a word length calculation algorithm is used to calculate the level of detail score of the event data.

[0111] When using the forward longest matching word segmentation algorithm to obtain multiple event keywords, a word length calculation algorithm can be used in conjunction with a pre-set government risk hot word feature library to calculate the level of detail score of the event data.

[0112] In one specific implementation, the word length calculation algorithm is the Longest Common Prefix (LCP) algorithm, which can calculate the detail score of event data by comparing a preset government risk hot word feature library with multiple event keywords.

[0113] For example, the pre-defined hot word feature database for government risks contains the detailed address of the keyword "zoo" in event data 3. The detailed address can be: Province A, City B, District C, and the corresponding street. If the keyword in event data 3 only contains "Province A", the detailed score of event data 3 can be calculated as 10 points using the longest common prefix algorithm; if the keyword in event data 3 contains "Province A, City B", the detailed score can be calculated as 30 points; and if the keyword in event data 3 contains "Province A, City B, District C", the detailed score can be calculated as 60 points.

[0114] S206. Based on multiple event keywords and the feature library of government risk hot words, a word frequency calculation algorithm is used to calculate the word frequency score of risk hot words among multiple event keywords.

[0115] When multiple event keywords are obtained using the forward longest matching word segmentation algorithm, and these multiple event keywords appear in the government risk hot word feature library, a pattern matching algorithm can be used to calculate the number of times the keywords appear in the event data. The keywords are then sorted from highest to lowest frequency to find the most frequent words. Finally, a word frequency calculation algorithm is used to calculate the word frequency score of the risk hot words among the multiple event keywords.

[0116] In one specific implementation, the term frequency calculation algorithm is the TF-IDF (term frequency–inverse document frequency) model algorithm. The TF-IDF model algorithm can be used for information retrieval and data mining. If a word appears frequently in one event but rarely in other events, it is considered to have good category discrimination ability. By calculating the TF-IDF value, the importance of keywords to a set of events can be measured.

[0117] For example, event data 3 is: "A tiger escaped from the zoo in District C, City B, Province A, and fled to Village D." The keywords for multiple events in event 3 are: "Province A, City B, District C, tiger, zoo, escape, Village D." Using a pattern matching algorithm, the keyword "escape" appears twice in event data 3. The keywords are then sorted from highest to lowest frequency, and the word "escape" is identified as the most frequent. The TF-IDF model algorithm is used. The calculation process is as follows: Event data 2 has a total of 12 words, and the word "escape" appears twice. Therefore, the word frequency of "escape" in event data 2 is 2 / 12 = 0.17. The method for calculating event frequency is to divide the total number of events in the event set by the number of events in which the word "escape" appears. If the word "escape" appears in 1000 events, and the total number of events is 10,000,000, its reverse file frequency is log(10,000,000 / 1000) = 4, and the final calculated word frequency score can be 0.17 * 4 = 0.68.

[0118] S207. Based on the preset weights of each type of score, part-of-speech score, detail score, and word frequency score, the event score is calculated.

[0119] When obtaining different types of event data scores using Hidden Markov Models, word length calculation algorithms, and word frequency calculation algorithms, the event score can be obtained by multiplying the score of each type by a pre-defined weight. In specific implementations, the part-of-speech score, detail score, and word frequency score can be weighted and summed according to the weight of each type score to obtain the event score.

[0120] Optionally, a weight can be preset for each type of score. The preset weight can be determined based on the empirical weighting method to determine the weight of each algorithm. Each algorithm can be evaluated, and the weight can be determined based on the evaluation results.

[0121] It should be noted that when calculating the event scores by pre-setting the weights of the Hidden Markov algorithm, word length calculation algorithm, and word frequency calculation algorithm, the calculated scores can range from 0 to 100.

[0122] For example, if the weights of the Hidden Markov Model (HMM) algorithm are preset to 0.7, the weight of the word length calculation algorithm to 0.2, and the weight of the word frequency calculation algorithm to 0.1, the HMM calculates a part-of-speech score of 70 for multiple event keywords; the word length calculation algorithm calculates a detail score of 60 for the event data; and the word frequency calculation algorithm calculates a frequency score of 0.68 for risk hot words among multiple event keywords. Combining the preset weights of each type of score with the corresponding score for each type, the event score is 61.

[0123] S208. Based on the event score and the preset public opinion event judgment conditions, determine whether the event corresponding to the event data will evolve into a public opinion event.

[0124] It should be noted that the specific execution process of step S208 can be found in the specific execution process of step S103, and will not be repeated here.

[0125] In this embodiment, after receiving event information from other devices in the government affairs system, a probe-style access and comparison is performed on the database of the government affairs system based on the event information to determine whether new event data associated with the event information has been updated in the database. When new event data is detected to have been updated in the database of the government affairs system, the event data is acquired, and the event data is segmented using a forward longest matching word segmentation algorithm to obtain multiple event keywords. Based on the multiple event keywords and a preset government affairs risk hot word feature library, a Hidden Markov algorithm is used to calculate the part-of-speech scores of the multiple event keywords; based on the multiple event keywords and the preset government affairs risk hot word feature library, a word length calculation algorithm is used to calculate the detail score of the event data; based on the multiple event keywords and the government affairs risk hot word feature library, a word frequency calculation algorithm is used to calculate the word frequency score of the risk hot words among the multiple event keywords; based on the preset weights of each type of score, the part-of-speech score, the detail score, and the word frequency score, the event score is calculated. Based on the event score and preset public opinion event judgment conditions, it is determined whether the event corresponding to the event data will evolve into a public opinion event. During the judgment process, the event score corresponding to the event data is calculated by the configured risk hot word automatic perception model. Combined with the preset public opinion event judgment conditions, the results can be compared to accurately determine whether the relevant event will evolve into a public opinion event.

[0126] To further understand the analysis methods for event data, the execution process of the analysis methods for event data in the relevant government systems will be further explained.

[0127] Figure 4 This is a schematic diagram illustrating the execution process of a method for analyzing event data in a government system, provided as an embodiment of this application. Please refer to [link / reference]. Figure 4 When new event data is updated in the government affairs system's database, the event data can be retrieved. A forward longest matching word segmentation algorithm is used to segment the event data, resulting in multiple event keywords. Based on these keywords and a pre-defined database of government risk hot words, a Hidden Markov Model, word length calculation algorithm, and TF-IDF model algorithm are used to obtain part-of-speech scores, detail scores, and word frequency scores. Then, by applying pre-defined weights to each type of score in a weighted algorithm, an event score is calculated. Based on the event score and pre-defined public opinion event judgment conditions, it is determined whether the event corresponding to the event data will evolve into a public opinion event.

[0128] It should be noted that the execution process of the event data analysis method provided in this application embodiment can refer to the event data analysis method provided in the above embodiment.

[0129] Figure 5 This is a schematic diagram of the structure of an event data analysis device in a government affairs system, provided as an embodiment of this application. Please refer to [link / reference]. Figure 5 The event data analysis device 10 in the government system includes:

[0130] The acquisition module 11 is used to acquire the event data when it is detected that new event data has been updated in the database of the government affairs system;

[0131] The first processing module 12 is used to calculate an event score based on the event data and a pre-configured risk hot word automatic perception model. The event score is used to indicate the likelihood that the event corresponding to the event data will evolve into a public opinion event. The risk hot word automatic perception model is used to calculate the comprehensive score of the part of speech, level of detail, and frequency of occurrence of risk hot words in the event data.

[0132] The second processing module 13 is used to determine whether the event corresponding to the event data will evolve into a public opinion event based on the event score and preset public opinion event judgment conditions.

[0133] The event data analysis device in the government system provided in this application embodiment can execute the technical solution shown in the above embodiment. Its implementation principle and beneficial effects are similar and will not be repeated here.

[0134] In one possible implementation, the first processing module 12 is specifically used for:

[0135] The event data was segmented using a forward longest matching word segmentation algorithm to obtain multiple event keywords.

[0136] The event keywords are input into the risk hot word automatic perception model to calculate the event score.

[0137] In one possible implementation, the automatic risk hot word perception model includes a hidden Markov algorithm, a word length calculation algorithm, and a word frequency calculation algorithm;

[0138] Accordingly, the first processing module 12 is specifically used for:

[0139] Based on the multiple event keywords and the preset government risk hot word feature library, the hidden Markov algorithm is used to calculate the part-of-speech scores of the multiple event keywords.

[0140] Based on the multiple event keywords and the preset government risk hot word feature library, the word length calculation algorithm is used to calculate the detail score of the event data;

[0141] Based on the multiple event keywords and the feature library of government risk hot words, the word frequency score of risk hot words among the multiple event keywords is calculated using the word frequency calculation algorithm.

[0142] The event score is calculated based on the preset weights of each type of score, the part-of-speech score, the detail score, and the word frequency score;

[0143] The government affairs risk hot word feature library stores key digital indicators of multiple public opinion events, including event type, event occurrence time, event address type, event sensitivity, and event level.

[0144] In one possible implementation, the word length calculation algorithm is the longest common prefix algorithm, and the word frequency calculation algorithm is the TF-IDF model algorithm.

[0145] In one possible implementation, the first processing module 12 is specifically used for:

[0146] The event score is obtained by weighting the part-of-speech score, the detail score, and the word frequency score according to the weight of each type score.

[0147] In one possible implementation, the criteria for judging public opinion events include: events with an event score greater than a preset score threshold will evolve into public opinion events;

[0148] Accordingly, the second processing module 13 is specifically used for:

[0149] If the event score is greater than the score threshold, it is determined that the event corresponding to the event data will evolve into a public opinion event.

[0150] If the event score is less than or equal to the score threshold, it is determined that the event corresponding to the event data will not evolve into a public opinion event.

[0151] Figure 6 This is a schematic diagram of the structure of another event data analysis device in a government affairs system provided in an embodiment of this application. Figure 5 Based on the illustrated embodiments, please refer to Figure 6 The event data analysis device 10 in the government affairs system further includes: a third processing module 14, which is used for:

[0152] After receiving event information from other devices in the government affairs system, the database of the government affairs system is probed and compared based on the event information to determine whether new event data associated with the event information has been updated in the database.

[0153] The event data analysis device in the government system provided in this application embodiment can execute the technical solution shown in the above embodiment. Its implementation principle and beneficial effects are similar and will not be repeated here.

[0154] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Please refer to... Figure 7 The electronic device 20 may include a processor 21, a memory 22, and an interface 24. Exemplarily, the processor 21, the memory 22, and the interface 24 are interconnected via a bus 23.

[0155] The memory 22 stores computer-executed instructions;

[0156] The processor 21 executes the computer execution instructions stored in the memory 22, causing the processor 21 to perform the method provided in the above method embodiments.

[0157] Accordingly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method provided in any of the above method embodiments.

[0158] Accordingly, embodiments of this application may also provide a computer program product, including a computer program, which, when executed by a processor, can implement the method provided in any of the above method embodiments.

[0159] All or part of the steps in the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable memory. When the program is executed, it performs the steps of the above-described method embodiments; and the aforementioned memory (storage medium) includes: read-only memory (ROM), random access memory (RAM), flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disk, and any combination thereof.

[0160] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processing unit of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processing unit of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0161] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0162] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0163] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0164] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0165] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for analyzing event data in a government affairs system, characterized in that, include: When it is detected that new event data has been updated in the database of the government affairs system, the event data is retrieved; The event data is segmented using a forward longest matching word segmentation algorithm to obtain multiple event keywords. These event keywords are then input into an automatic risk hot word perception model to calculate an event score. The event score indicates the likelihood that the event corresponding to the event data will evolve into a public opinion event. The automatic risk hot word perception model is used to calculate a comprehensive score of the part of speech, level of detail, and frequency of occurrence of risk hot words in the event data. Based on the event score and the preset public opinion event judgment conditions, it is determined whether the event corresponding to the event data will evolve into a public opinion event; The automatic risk hot word perception model includes a hidden Markov algorithm, a word length calculation algorithm, and a word frequency calculation algorithm. Accordingly, the step of inputting the multiple event keywords into the risk hot word automatic perception model and calculating the event score includes: Based on the multiple event keywords and the preset government risk hot word feature library, the hidden Markov algorithm is used to calculate the part-of-speech scores of the multiple event keywords. Based on the multiple event keywords and the preset government risk hot word feature library, the word length calculation algorithm is used to calculate the detail score of the event data; Based on the multiple event keywords and the feature library of government risk hot words, the word frequency score of risk hot words among the multiple event keywords is calculated using the word frequency calculation algorithm. The event score is calculated based on the preset weights of each type of score, the part-of-speech score, the detail score, and the word frequency score; The government affairs risk hot word feature library stores key digital indicators of multiple public opinion events, including event type, event occurrence time, event address type, event sensitivity, and event level.

2. The method according to claim 1, characterized in that, The word length calculation algorithm is the longest common prefix algorithm, and the word frequency calculation algorithm is the TF-IDF model algorithm.

3. The method according to claim 2, characterized in that, The event score is calculated based on the preset weights of each type score, the part-of-speech score, the detail score, and the word frequency score, including: The event score is obtained by weighting the part-of-speech score, the detail score, and the word frequency score according to the weight of each type score.

4. The method according to claim 1 or 2, characterized in that, The criteria for judging public opinion events include: events with an event score greater than a preset score threshold will evolve into public opinion events; Accordingly, determining whether the event corresponding to the event data will evolve into a public opinion event based on the event score and preset public opinion event judgment conditions includes: If the event score is greater than the score threshold, it is determined that the event corresponding to the event data will evolve into a public opinion event. If the event score is less than or equal to the score threshold, it is determined that the event corresponding to the event data will not evolve into a public opinion event.

5. The method according to claim 1 or 2, characterized in that, The method further includes: After receiving event information from other devices in the government affairs system, the database of the government affairs system is probed and compared based on the event information to determine whether new event data associated with the event information has been updated in the database.

6. An analysis device for event data in a government affairs system, characterized in that, include: The acquisition module is used to acquire the event data when it is detected that new event data has been updated in the database of the government affairs system; The first processing module is used to segment the event data using a forward longest matching word segmentation algorithm to obtain multiple event keywords; input the multiple event keywords into a risk hot word automatic perception model to calculate an event score, the event score being used to indicate the likelihood of the event corresponding to the event data evolving into a public opinion event; the risk hot word automatic perception model is used to calculate the part-of-speech, level of detail, and frequency of occurrence of risk hot words in the event data as a comprehensive score. The second processing module is used to determine whether the event corresponding to the event data will evolve into a public opinion event based on the event score and preset public opinion event judgment conditions. The automatic risk hot word perception model includes a hidden Markov algorithm, a word length calculation algorithm, and a word frequency calculation algorithm. The first processing module is specifically used to calculate the part-of-speech scores of the multiple event keywords based on the multiple event keywords and the preset government risk hot word feature library, using the hidden Markov algorithm. Based on the multiple event keywords and the preset government risk hot word feature library, the word length calculation algorithm is used to calculate the detail score of the event data; Based on the multiple event keywords and the feature library of government risk hot words, the word frequency score of risk hot words among the multiple event keywords is calculated using the word frequency calculation algorithm. The event score is calculated based on the preset weights of each type of score, the part-of-speech score, the detail score, and the word frequency score; The government affairs risk hot word feature library stores key digital indicators of multiple public opinion events, including event type, event occurrence time, event address type, event sensitivity, and event level.

7. An electronic device, characterized in that, include: Processor, memory, and interaction interface; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions that, when executed by a processor, are used to implement the method described in any one of claims 1 to 5.

Images