A method and system for hotline early warning using intelligent label algorithm

Abstract

The present application provides a method and system for hotline early warning using an intelligent labeling algorithm, the method comprising the following steps: in response to receiving a hotline work order, obtaining hotline work order data; based on a pre-built intelligent labeling algorithm model, performing label recognition on the obtained hotline work order data, and labeling the hotline work order data according to the recognition result; inputting the labeled hotline work order data into a pre-built early warning rule judgment model to obtain data of multiple early warning categories; judging whether the data of multiple early warning categories meet the corresponding early warning condition thresholds, if the data of the early warning category meets the corresponding early warning condition thresholds, then generating early warning results for the corresponding early warning categories. The present application realizes automatic labeling of massive daily livelihood appeal case data, supports in-depth analysis, digs out the possibility of mass incidents, issues early warnings, reduces potential risks to the lowest level, reduces social public resource consumption, and reduces social and economic losses.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and system for performing hotline warning using an intelligent tag algorithm. Background Art

[0002] With the continuous development of urban economy and technology, hotline business platforms have been built and operated in various places. The number of work orders submitted by the public through hotlines has increased year by year, and cities are paying more and more attention to hotline requests.

[0003] With the increase in hotline work orders, a large amount of hotline work order data is generated. Among the large amount of hotline work order data, there are many public hot spots and work orders with high urgency. Currently, most of the on-site personnel use manual screening to find out the hot events that leaders are concerned about from the large number of work orders run every day, and then aggregate these work orders by type to form daily hot spots, providing support for professional departments to centrally handle similar hot issues.

[0004] Currently, most hotline services are mainly screened manually. First, each ticket is manually tagged with a topic, subject, and geography tag. Then, the tickets are aggregated by topic and subject to form the daily hot event results. The current method of processing hotline tickets still has the following shortcomings:

[0005] 1. Manual labeling of work orders will increase the burden on hotline system users, which is inefficient and prone to omissions in work order labeling. In addition, different people have different standards for understanding the same complaint, which leads to inconsistent labeling of the same work order by different people, and irregular processing of related work orders. In addition, manual aggregation of work orders will lead to a lag in warning results.

[0006] 2. In the course of business operations, it is not possible to classify warning information, resulting in the staff facing complicated warning information when handling warnings; the staff cannot quickly query and browse the relevant information of the warning, and cannot have an overall grasp of the warning situation, resulting in the entire warning analysis requiring a large amount of manual workload.

[0007] 3. When faced with mass and frequent problems, hot issues concerning people’s livelihood, new and sudden problems, and periodic recurring problems, they are often only dealt with passively after the fact, and are unable to achieve early detection, early attention, early deployment, and early control.

[0008] Therefore, the technical problem that urgently needs to be solved is: how to provide a method and system for hotline early warning using an intelligent labeling algorithm, to automatically label the massive amount of hotline work order data (i.e., people's livelihood case data) every day, to support in-depth analysis, to explore the possibility of mass incidents, to issue early warnings, to reduce potential risks to the lowest level, to reduce the consumption of social public resources, and to reduce social and economic losses. Summary of the invention

[0009] The purpose of this application is to provide a method and system for hotline warning using an intelligent labeling algorithm, to automatically label the massive amount of daily livelihood appeal case data, to support in-depth analysis, to uncover the possibility of mass incidents, to issue early warnings, to reduce potential risks to the lowest level, to reduce the consumption of social public resources, and to reduce social and economic losses.

[0010] To achieve the above-mentioned purpose, as the first aspect of the present application, the present application provides a method for hotline warning using an intelligent label algorithm, the method comprising the following steps: in response to receiving a hotline work order, obtaining hotline work order data; based on a pre-built intelligent label algorithm model, performing label recognition on the obtained hotline work order data, and labeling the hotline work order data according to the recognition result; inputting the labeled hotline work order data into a pre-built warning rule judgment model to obtain data of multiple warning categories; judging whether the data of multiple warning categories meet the corresponding warning condition thresholds, if the data of the warning category meets the corresponding warning condition thresholds, generating a warning result of the corresponding warning category, otherwise, there is no need to generate a warning result of the warning category.

[0011] The method for hotline warning using the smart label algorithm as described above, wherein the method for pre-building a smart label algorithm model includes the following steps: obtaining a training data set; performing feature extraction on the data in the training data set to obtain a training feature data set; and training the training feature data set based on the selected smart label algorithm to obtain a smart label algorithm model.

[0012] The method for hotline warning using the smart label algorithm as described above, wherein the method for pre-building a smart label algorithm model further comprises the following steps: evaluating the smart label algorithm model.

[0013] The method for hotline warning using the intelligent tagging algorithm as described above, wherein the tags include topic tags, subject tags and geographic tags.

[0014] The method for hotline warning using the intelligent tag algorithm as described above, wherein the warning categories include: high-frequency subject warning, high-incidence area warning, one person with multiple complaints warning, multiple people with the same complaint warning, emergency warning, sensitive complaint warning and repeated complaint warning.

[0015] The method for hotline warning using the smart tag algorithm as described above, wherein the method further includes: presetting a warning condition threshold for each warning category, and different warning categories correspond to different warning condition thresholds.

[0016] The method for hotline warning using the smart label algorithm as described above, wherein the smart label algorithm includes: neural network, logistic regression, support vector machine, naive Bayes classifier, decision tree or random forest.

[0017] In the method for hotline warning using the smart label algorithm as described above, the method for obtaining a training data set includes: selecting hotline work order data with known labels as original training data; preprocessing the original training data; and converting the preprocessed data into a machine learning format.

[0018] As a second aspect of the present application, the present application also provides a system for hotline warning using an intelligent label algorithm, characterized in that it is a method for executing the intelligent label algorithm for hotline warning, the system comprising: a first data acquisition module, used to acquire hotline work order data in response to receiving a hotline work order; a labeling module, used to perform label recognition on the acquired hotline work order data based on a pre-built intelligent label algorithm model, and label the hotline work order data according to the recognition result; a second data acquisition module, used to input the labeled hotline work order data into a pre-built warning rule judgment model to obtain data of multiple warning categories; a warning judgment module, used to judge whether the data of multiple warning categories meet the corresponding warning condition thresholds. If the data of the warning category meets the corresponding warning condition thresholds, a warning result of the corresponding warning category is generated; otherwise, there is no need to generate a warning result of the warning category.

[0019] The system for hotline warning using the intelligent label algorithm as described above, wherein the system also includes a display module for displaying detailed information on sensitive demand warnings.

[0020] The beneficial effects achieved by this application are as follows:

[0021] (1) Compared with the existing manual labeling method for related work orders, the solution proposed in this application can quickly and accurately identify the topic, subject, and geographic information of hotline work orders. This greatly reduces the workload of hotline system personnel in labeling human work orders and improves the accuracy.

[0022] (2) After the hotline work order of this application is completed and the information is automatically captured, it is automatically determined whether the hotline work order reaches the warning condition threshold, so that the warning work order can be automatically generated in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For those skilled in the art, other drawings can also be obtained based on these drawings.

[0024] Figure 1 This is a flow chart of a method for performing hotline warning using an intelligent tag algorithm according to an embodiment of the present application.

[0025] Figure 2 This application provides a flowchart of a method for hotline warning using an intelligent tag algorithm.

[0026] Figure 3 A schematic diagram of the system structure for hotline warning using an intelligent tag algorithm according to an embodiment of the present application.

[0027] Figure numerals: 10 - first data acquisition module; 20 - labeling module; 30 - second data acquisition module; 40 - early warning judgment module; 100 - system for hotline early warning using intelligent label algorithm. DETAILED DESCRIPTION

[0028] The following is a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0029] Embodiment 1

[0030] like Figure 1 As shown, the present application provides a method for performing hotline warning using an intelligent tag algorithm, the method comprising the following steps:

[0031] Step S1, in response to receiving a hotline work order, obtaining hotline work order data.

[0032] Specifically, citizens feedback their livelihood demands through the hotline business platform, and the livelihood demands reflect the suggestions and demands of the people. Hotline work order data refers to the livelihood demand case data. Hotline work order data refers to the problems and demands reflected by citizens received by government departments through telephone, Internet and other channels, as well as the handling of these problems and demands by relevant departments. These data can be used to analyze the needs and demands of citizens and provide decision-making support for government departments.

[0033] Step S2, based on the pre-built intelligent label algorithm model, label recognition is performed on the acquired hotline work order data, and labels are added to the hotline work order data according to the recognition result.

[0034] As a specific embodiment of the present invention, each time a piece of hotline work order data is obtained, the label of the obtained hotline work order data is promptly identified based on the pre-built intelligent label algorithm model, and the hotline work order data is labeled according to the identification result. There is no need to wait for obtaining other hotline work order data. The efficiency of hotline work order labeling is improved.

[0035] Specifically, tags include topic tags, subject tags, and geographic tags.

[0036] As a specific embodiment of the present invention, if label recognition is performed on the acquired hotline work order data based on a pre-built intelligent label algorithm model, if the recognition result is a topic label, the hotline work order is marked with a topic label; if the recognition result is a subject label, the hotline work order is marked with a subject label; if the recognition result is a geographic label, the hotline work order is marked with a geographic label.

[0037] As a specific embodiment of the present invention, based on a pre-built intelligent label algorithm model, after label recognition is performed on the acquired hotline work order data, the recognized label results are obtained. The accuracy of the recognized label results can also be checked manually, and erroneous label results can be corrected.

[0038] As a specific embodiment of the present invention, the method for pre-building a smart label algorithm model includes the following steps:

[0039] Step S210, obtaining a training data set.

[0040] Specifically, the method for obtaining the training data set includes: selecting hotline ticket data with known labels as original training data, preprocessing the original training data, such as removing duplicates, filling missing values, and detecting outliers, etc. Then converting the preprocessed data into a format suitable for machine learning, such as encoding categorical data into binary or one-hot encoding, and standardizing numerical data.

[0041] Step S220, extracting features from the data in the training data set to obtain a training feature data set.

[0042] Specifically, useful features are extracted from the training data set to improve the performance of the model. Common feature engineering methods include feature selection, feature expansion, and feature extraction.

[0043] Step S230: Based on the selected smart label algorithm, the training feature data set is trained to obtain a smart label algorithm model.

[0044] Specifically, the smart labeling algorithm may be a neural network, logistic regression, support vector machine (SVM), naive Bayes classifier, decision tree, random forest or gradient boosting tree (GBDT), etc. The type of smart labeling algorithm is not limited here and can be selected according to actual needs.

[0045] Step S240, evaluating the smart label algorithm model.

[0046] Specifically, after the smart label algorithm model is built, the smart label algorithm model is evaluated to determine its generalization ability. Common evaluation indicators include accuracy, precision, recall, F1 score, etc. Based on the evaluation results, the model with the best performance can be selected as the final smart label algorithm model.

[0047] Step S3, inputting the labeled hotline work order data into a pre-built warning rule judgment model to obtain data of multiple warning categories.

[0048] Among them, the early warning rule judgment model is used to count the data of hotline work orders, so as to obtain data corresponding to multiple early warning categories.

[0049] The warning rule judgment model is trained for the data types required for different warning categories in the warning rules, so that the warning rule model can identify the data corresponding to multiple warning categories of the hotline work order. Specifically, the warning rule judgment model is trained using existing methods.

[0050] As a specific embodiment of the present invention, the warning categories include: high-frequency subject warning, high-incidence area warning, one person multiple complaints warning, multiple people same complaint warning, emergency warning, sensitive complaint warning and repeated complaint warning, etc. Different warning categories correspond to different warning condition thresholds.

[0051] Step S4, determine whether the data of multiple warning categories meet the corresponding warning condition thresholds. If the data of the warning category meets the corresponding warning condition thresholds, generate a warning result for the corresponding warning category. Otherwise, there is no need to generate a warning result for the warning category.

[0052] As a specific embodiment of the present invention, a method for determining whether data of multiple warning categories meets corresponding warning condition thresholds is as follows:

[0053] ① High-frequency subject warning:

[0054] Specifically, for the same subject, within the specified warning period, if the number of hotline tickets for the same topic or subcategory reaches the warning condition threshold, a high-frequency subject warning event will be triggered.

[0055] ② Warning for high-incidence areas:

[0056] Specifically, for the same area, road (or other point of interest dimensions), within a specified warning period, if the number of hotline tickets for the same topic or subcategory reaches the warning condition threshold, a high-frequency subject warning event will be triggered.

[0057] ③ Warning of multiple complaints by one person:

[0058] Specifically, when a citizen (with the same caller number) calls multiple times (already dispatched) to reflect different demands (topics) within a certain period, and the duplicate flag generates a corresponding warning, a one-person-multiple-complaints warning will be generated.

[0059] ④ Warning for multiple people filing a complaint:

[0060] Specifically, within a certain period, if a certain number of citizens (with different caller numbers) call in the same area to reflect the same demand (topic), a multiple-complaint alert will be generated.

[0061] ⑤Emergency warning:

[0062] Specifically, if multiple citizens (with different caller numbers) report multiple identical demands (topics) in different areas within a certain period (such as 1 day, 3 days, or 1 week), and the topic is not on the TOP list of hot topics in the previous period, the "sudden hotspot" condition is triggered and a corresponding warning is generated. Different warning levels are given based on 1 day, 3 days, or 1 week.

[0063] ⑥Sensitive appeal warning:

[0064] Specifically, by mining the citizen demand data (i.e., hotline work order data) through the sensitive word algorithm, we found obvious negative words such as "threat", "run away", "rampant", "collapse", "major safety hazard", "major accident", "major loss", "labor-management dispute", "consumer dispute", etc., which are the conditions that trigger "sensitive demands", and then generate a sensitive demand warning.

[0065] The system supports displaying detailed information of sensitive appeal warnings, including the total number of warnings, warning lists, and can also filter or fuzzy search based on time periods.

[0066] ⑦Repeated complaint warning:

[0067] Specifically, if a citizen complains about the same incident multiple times and reaches the warning condition threshold (more than three times), and the incident has not been resolved, a repeated complaint warning event is generated.

[0068] As a specific embodiment of the present invention, a warning condition threshold value for each warning category is pre-set, and different warning categories correspond to different warning condition threshold values. When the data corresponding to the warning category reaches the corresponding warning condition threshold value, the warning is automatically triggered. The data of the warning condition threshold value for each warning category is not limited here. Those skilled in the art can set the warning condition threshold value according to actual needs.

[0069] like Figure 2As shown, this is a flowchart of a method for hotline warning using an intelligent label algorithm in the present application, the method comprising: obtaining work order information (i.e., hotline work order data), automatically labeling the work order information based on the intelligent label algorithm model, and manually correcting the automatic labeling results; inputting the labeled work order information into the warning rule judgment model for judgment, obtaining data on high-frequency subject warnings, high-incidence area warnings, one person with multiple complaints warnings, multiple people with the same complaint warnings, emergency warnings, sensitive claims warnings, and repeated complaint warnings, and judging whether the above-obtained data reaches the warning condition threshold. If so, a warning is issued; if not, no warning is issued, and finally a warning result is generated.

[0070] Embodiment 2

[0071] like Figure 3 As shown, the present application provides a system 100 for hotline warning using an intelligent tag algorithm, the system comprising:

[0072] A first data acquisition module 10 is used to acquire hotline work order data in response to receiving a hotline work order;

[0073] The labeling module 20 is used to perform label recognition on the acquired hotline work order data based on the pre-built intelligent label algorithm model, and label the hotline work order data according to the recognition result;

[0074] The second data acquisition module 30 is used to input the labeled hotline work order data into a pre-built warning rule judgment model to obtain data of multiple warning categories;

[0075] The warning judgment module 40 is used to judge whether the data of multiple warning categories meet the corresponding warning condition thresholds. If the data of the warning category meets the corresponding warning condition thresholds, a warning result of the corresponding warning category is generated. Otherwise, there is no need to generate a warning result of the warning category.

[0076] As a specific embodiment of the present invention, the system also includes a display module for displaying detailed information of sensitive demand warnings. The system supports displaying detailed information of sensitive demand warnings, which includes the total number of warnings, warning lists, and can be filtered or fuzzy queried according to time periods.

[0077] An embodiment of the present invention provides a processor for processing the above-mentioned smart tag algorithm to perform a hotline warning method.

[0078] In the embodiment of the present invention, the processor may be an integrated circuit chip having the ability to process signals. The processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0079] The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present invention can be directly embodied as a hardware decoding processor for execution, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The processor reads the information in the storage medium and completes the steps of the above method in combination with its hardware.

[0080] The storage medium may be a memory, which may be, for example, a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memory.

[0081] Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct RAM bus random access memory (DRRAM).

[0082] The beneficial effects achieved by this application are as follows:

[0083] (1) Compared with the existing manual labeling method of related work orders, the solution proposed in this application can quickly and accurately identify the topic, subject, and geographic information of hotline work orders. This greatly reduces the workload of hotline system personnel in labeling human work orders and improves the accuracy.

[0084] (2) After the hotline work order of this application is completed and the information is automatically captured, it is automatically determined whether the hotline work order reaches the warning condition threshold, so that the warning work order can be automatically generated in real time.

[0085] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0086] In the description of the present application, the word "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0087] The above description is only an embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A method for hotline warning using an intelligent tag algorithm, characterized in that: The method comprises the following steps: In response to receiving a hotline work order, obtaining hotline work order data; Based on the pre-built intelligent label algorithm model, the hotline work order data is labeled and labeled according to the identification results; the labels include topic labels, subject labels and geographic labels; Input the labeled hotline ticket data into the pre-built warning rule judgment model to obtain data of multiple warning categories; Among them, the warning rule judgment model is trained for the data types required for different warning categories in the warning rules, and the warning rule judgment model identifies the data corresponding to multiple warning categories of the hotline work order; Among them, the warning categories include: high-frequency subject warning, high-incidence area warning, one person multiple lawsuits warning, multiple people same lawsuits warning, emergency warning, sensitive appeal warning and repeated complaint warning; Determine whether the data of multiple warning categories meet the corresponding warning condition thresholds. If the data of the warning category meets the corresponding warning condition thresholds, generate a warning result of the corresponding warning category. Otherwise, there is no need to generate a warning result of the warning category. Among them, the method for judging whether the data of multiple warning categories meets the corresponding warning condition threshold is as follows: ① High-frequency subject warning: For the same subject, within the specified warning period, if the number of hotline tickets for the same topic or subcategory reaches the warning condition threshold, a high-frequency subject warning event will be triggered; ② High-incidence area warning: In the same area or road, within the specified warning period, if the number of hotline tickets for the same topic or subcategory reaches the warning condition threshold, a high-frequency subject warning event will be triggered; ③ One person multiple complaints warning: When a citizen calls to reflect different demands multiple times within a certain period, and the repeated flag generates corresponding warnings, a one person multiple complaints warning will be generated; ④Multiple people's complaint warning: If a certain number of citizens call in to express the same complaint in the same area within a certain period, a multiple people's complaint warning will be generated; ⑤ Emergency warning: Multiple citizens in different areas report multiple identical demands within a certain period, and the topic of the demand is not on the top list of hot topics in the previous period, triggering the "Emergency Hotspot" condition and generating a corresponding warning; ⑥Sensitive appeal warning: If negative words are found in the citizen appeal data through sensitive word algorithms, a sensitive appeal warning will be generated; ⑦ Repeated complaint warning: If a citizen complains about the same incident multiple times and reaches the warning condition threshold, and the incident has not been resolved, a repeated complaint warning event will be generated.

2. The method for hotline warning using the smart tag algorithm according to claim 1 is characterized in that: The method of pre-building a smart label algorithm model includes the following steps: Get the training data set; Perform feature extraction on the data in the training data set to obtain a training feature data set; Based on the selected smart labeling algorithm, the training feature data set is trained to obtain the smart labeling algorithm model.

3. The method for hotline warning using the smart tag algorithm according to claim 2 is characterized in that: The method for pre-building an intelligent label algorithm model also includes the following steps: Evaluate the smart labeling algorithm model.

4. The method for hotline warning using the smart tag algorithm according to claim 1 is characterized in that: Tags include topic tags, subject tags, and geo tags.

5. The method for hotline warning using the smart tag algorithm according to claim 1 is characterized in that: The warning categories include: high-frequency subject warning, high-incidence area warning, one person multiple lawsuits warning, multiple people same lawsuit warning, emergency warning, sensitive claims warning and repeated complaint warning.

6. The method for hotline warning using the smart tag algorithm according to claim 5 is characterized in that: The method further includes: presetting a warning condition threshold for each warning category, with different warning categories corresponding to different warning condition thresholds.

7. The method for hotline warning using the smart tag algorithm according to claim 2 is characterized in that: Smart labeling algorithms include: neural network, logistic regression, support vector machine, naive Bayes classifier, decision tree or random forest.

8. The method for hotline warning using the smart tag algorithm according to claim 2 is characterized in that: Methods for obtaining training data sets include: Select hotline ticket data with known labels as original training data; Preprocess the original training data; Convert the preprocessed data into a machine learning format.

9. A system for hotline warning using intelligent label algorithm, characterized in that: For executing the method according to any one of claims 1 to 8, the system comprises: A first data acquisition module, configured to acquire hotline work order data in response to receiving a hotline work order; The labeling module is used to identify labels of the acquired hotline work order data based on the pre-built intelligent labeling algorithm model, and label the hotline work order data according to the identification results; The second data acquisition module is used to input the labeled hotline work order data into the pre-built warning rule judgment model to obtain data of multiple warning categories; The warning judgment module is used to judge whether the data of multiple warning categories meet the corresponding warning condition thresholds. If the data of the warning category meets the corresponding warning condition thresholds, a warning result of the corresponding warning category is generated. Otherwise, there is no need to generate a warning result of the warning category.

10. The system for hotline warning using the intelligent label algorithm according to claim 9 is characterized in that: The system also includes a display module for displaying detailed information of sensitive appeal warnings.

Images