A publicity method, system, medium and electronic device for countering online fraud

Abstract

A publicity method, system, storage medium and electronic device for countering online fraud, which relates to the field of information technology. The method includes: obtaining a list of users to be called; determining the current called user in the list of users to be called, and determining a first fraud strategy based on the basic user information of the current called user, where the first fraud strategy includes a fraud type, a first fraud level, a first fraud script, and a first fraud tone; obtaining a first feedback result of the current called user on the first fraud plan, and calculating an anti-fraud score value of the current called user based on the first feedback result; when the anti-fraud score value is greater than a score threshold, adjusting the first fraud strategy to obtain a second fraud strategy; obtaining a second feedback result of the current called user on the second fraud plan, generating an anti-fraud publicity report based on the first feedback result and the second feedback result, and sending the anti-fraud publicity report to the current called user. Implementing the technical solution provided by this application can improve the effectiveness of anti-fraud publicity.

Description

Technical Field

[0001] This application relates to the field of information technology, and specifically relates to a publicity method, system, medium and electronic device for countering online fraud. Background Art

[0002] With the continuous innovation of telecommunications network fraud means, fraud scripts have become increasingly concealed and more deceptive, causing a large amount of property losses to the masses. In order to improve citizens' awareness and ability to prevent telecommunications network fraud, various forms have been adopted to carry out anti-fraud publicity and education work.

[0003] Currently, common anti-fraud publicity and education methods mainly include distributing publicity brochures, playing case videos, holding lectures, etc. Although these publicity methods can enable citizens to understand the basic routines and prevention key points of fraud, due to the lack of actual interactive experience, especially when facing a fraud process with different scripts setting traps layer by layer and pressing step by step, it is often difficult to make a correct judgment in a timely manner relying solely on the previously mastered prevention knowledge, resulting in difficulty in accurately identifying and effectively responding when encountering real fraud, and making the effectiveness of anti-fraud publicity relatively low. Summary of the Invention

[0004] This application provides a publicity method, system, storage medium and electronic device for countering online fraud, which can improve the effectiveness of anti-fraud publicity.

[0005] In a first aspect, this application provides a publicity method for countering online fraud, and the method includes:

[0006] Obtain a list of users to be called, where the list of users to be called includes at least one calling user;

[0007] Determine the current calling user in the list of users to be called, and determine a first fraud strategy based on the basic user information of the current calling user. The first fraud strategy includes fraud type, first fraud level, first fraud script, and first fraud tone;

[0008] Obtain the first feedback result of the current calling user on the first fraud plan, and calculate the anti-fraud score value of the current calling user based on the first feedback result;

[0009] When the anti-fraud score value is greater than the score threshold, adjust the first fraud strategy to obtain a second fraud strategy;

[0010] Obtain the second feedback result of the current calling user on the second fraud plan, generate an anti-fraud publicity report based on the first feedback result and the second feedback result, and send the anti-fraud publicity report to the current calling user.

[0011] By adopting the above technical solution, a first anti-fraud strategy is determined based on the basic information of the current calling user, and an anti-fraud score value is calculated according to the first feedback result of the user. When the anti-fraud score value is greater than the score threshold, the system can timely adjust the anti-fraud strategy to obtain a second anti-fraud strategy, and simulate the characteristics of setting traps layer by layer and pressing step by step in the real anti-fraud process through dynamic adjustment. At the same time, by analyzing the feedback results of the user on different anti-fraud strategies, a personalized anti-fraud publicity report is generated and sent to the user, enabling the user to experience the evolution of fraud scripts in the actual interaction process, improving the recognition ability and response ability to fraud characteristics, overcoming the problem that the existing anti-fraud publicity methods lack practical experience, resulting in users being difficult to identify and respond to fraud in a timely manner, and thus effectively improving the pertinence and effectiveness of anti-fraud publicity.

[0012] In the second aspect of the present application, a publicity system for countering online fraud is provided. The system includes:

[0013] A user information acquisition module for acquiring a call list to be called, where the call list to be called includes at least one calling user;

[0014] A first strategy determination module for determining the current calling user in the call list to be called, and determining a first anti-fraud strategy based on the user's basic information of the current calling user. The first anti-fraud strategy includes a fraud type, a first fraud level, a first fraud script, and a first fraud tone;

[0015] An anti-fraud score calculation module for obtaining a first feedback result of the current calling user on the first anti-fraud plan, and calculating an anti-fraud score value of the current calling user based on the first feedback result;

[0016] A second strategy determination module for adjusting the first anti-fraud strategy to obtain a second anti-fraud strategy when the anti-fraud score value is greater than the score threshold;

[0017] An anti-fraud publicity sending module for obtaining a second feedback result of the current calling user on the second anti-fraud plan, generating an anti-fraud publicity report based on the first feedback result and the second feedback result, and sending the anti-fraud publicity report to the current calling user.

[0018] In the third aspect of the present application, a computer storage medium is provided. The computer storage medium stores multiple instructions, and the instructions are suitable for being loaded and executed by a processor to perform the above method steps.

[0019] In the fourth aspect of the present application, an electronic device is provided, including: a processor and a memory; wherein, the memory stores a computer program, and the computer program is suitable for being loaded and executed by the processor to perform the above method steps.

[0020] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0021] Based on the basic information of the current calling user, the present application determines the first fraud strategy, calculates the anti-fraud score value according to the user's first feedback result. When the anti-fraud score value is greater than the score threshold, the system can timely adjust the fraud strategy to obtain the second fraud strategy, simulating the characteristics of setting traps layer by layer and pressing step by step in the real fraud process through dynamic adjustment. At the same time, by analyzing the feedback results of users on different fraud strategies, a personalized anti-fraud publicity report is generated and sent to the users, enabling the users to experience the evolution of fraud scripts in the actual interaction process, improving the recognition ability and response ability to fraud characteristics, overcoming the problem that the existing anti-fraud publicity methods lack practical experience, resulting in users being difficult to identify and respond to fraud in a timely manner, thereby effectively improving the pertinence and effectiveness of anti-fraud publicity. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a schematic flowchart of a method for publicizing anti-network fraud provided by an embodiment of the present application;

[0023] Figure 2 is a schematic block diagram of a system for publicizing anti-network fraud provided by an embodiment of the present application;

[0024] Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0025] Description of the reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0027] In the description of the embodiments of the present application, words such as "for example" or "for illustration" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "for example" or "for illustration" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of words such as "for example" or "for illustration" is intended to present relevant concepts in a specific manner.

[0028] In the description of the embodiments of the present application, the term "plurality" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "include", "comprise", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0029] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0030] Please refer to Figure 1 , and a flowchart of a method for promoting anti-fraud against online fraud is specifically proposed. This method can be implemented depending on a computer program, can be implemented depending on a single-chip microcomputer, or can run on an anti-fraud promotion system for online fraud. This computer program can be integrated in a computer device or can run as an independent tool-type application. Specifically, this method includes steps 10 to 50, and the above steps are as follows:

[0031] Step 10: Obtain a list of users to be called, and the list of users to be called includes at least one calling user.

[0032] In the embodiments of the present application, the list of users to be called refers to a list of target users who need to receive anti-fraud promotion, which contains information of at least one calling user. Each calling user corresponds to basic information for determining a first anti-fraud strategy, such as age, occupation type, and education level, etc. The list of users to be called can be sorted according to factors such as the user's location, age group, and occupation characteristics, etc., to facilitate the system to carry out anti-fraud promotion work in an orderly manner.

[0033] Specifically, in order to carry out targeted anti-fraud publicity, it is first necessary to obtain a waiting list. The waiting list can be obtained in the following ways: when a user actively signs up to participate in an anti-fraud publicity activity, the user voluntarily fills out a personal information registration form, including basic information such as contact information, age group, occupation type, and education level; or when anti-fraud publicity activities are carried out in communities, enterprises, etc., relevant staff collect the basic information of the participants and compile it into a list. The system imports the collected information into the database to form a waiting list containing at least one calling user. In order to facilitate the subsequent targeted anti-fraud publicity, the system will classify and organize the users in the waiting list, such as grouping them according to age groups, occupation types, etc., so that appropriate fraud strategies can be selected according to the characteristics of different groups. The waiting list obtained in this way not only ensures the legitimacy of the information source, but also lays the foundation for the subsequent personalized anti-fraud publicity, and also facilitates the system to carry out anti-fraud publicity work in an orderly manner according to the basic characteristics of the users.

[0034] Step 20: Determine the current calling user in the waiting-to-be-called list, and determine a first fraud strategy based on the basic user information of the current calling user. The first fraud strategy includes a fraud type, a first fraud level, a first fraud speech, and a first fraud tone.

[0035] Specifically, after obtaining the waiting list of calls, the system determines the calling user who needs to carry out anti-fraud publicity according to the preset call order. In order to ensure the pertinence and effectiveness of the anti-fraud publicity, the system will analyze the basic information of the current calling user, including age, occupation type and education level. First, the risk coefficient is calculated according to the basic information of the user. For example, for users with older age and lower education level, the risk coefficient is relatively high; while for users with younger age and higher education level, the risk coefficient is relatively low. Based on the calculated risk coefficient, the system determines the corresponding first fraud level. The higher the risk coefficient, the lower the corresponding first fraud level, so as to ensure that the user can accept and generate vigilance. At the same time, the system will select the most confusing fraud type according to the user's occupation type. For example, for corporate employees, business cooperation fraud may be selected; for students, part-time fraud may be selected. After determining the fraud type and the first fraud level, the system retrieves the matching first fraud speech and first fraud tone from the preset speech library. For example, for low-level fraud strategies, simpler and more direct speech and peaceful tone are selected; for high-level fraud strategies, more concealed and circuitous speech and strong tone are selected. Finally, the system integrates the first fraud level, fraud type, first fraud words and first fraud tone into a complete first fraud strategy. The first fraud strategy determined in this way not only takes into account the user's cognition and prevention ability, but also simulates the characteristics of real fraud, making anti-fraud publicity more targeted and effective.

[0036] Based on the above embodiments, as an alternative embodiment, the step of determining the first fraud strategy based on the basic user information of the current calling user may further include the following steps:

[0037] Step 201: Calculate a risk coefficient based on the basic information of the current calling user, where the basic information includes age, occupation type, and education level.

[0038] Specifically, according to the basic information actively provided by the current calling user, a preset calculation model is used to calculate the risk coefficient. The system first sets weight coefficients and quantization scores for the user's age, occupation type, and education level respectively. For example, age is divided into multiple intervals and different scores are assigned: 5 points for those over 50 years old, 4 points for those aged 35 - 50, 3 points for those aged 25 - 35, and 2 points for those under 25; education level is quantified as 1 point for postgraduate and above, 2 points for undergraduate, 3 points for junior college, and 4 points for high school and below; the occupation type is graded according to the sensitivity to fraud, such as 5 points for retirees, 4 points for self-employed individuals, 3 points for enterprise employees, 2 points for students, and 1 point for public servants. Then, the scores of each item are multiplied by the corresponding weights and summed to obtain the final risk coefficient.

[0039] Step 202: Determine the first fraud level based on the risk coefficient, and determine the fraud type according to the occupation type.

[0040] Specifically, based on the calculated risk coefficient, the system divides the fraud level into three levels: primary, intermediate, and advanced. The higher the risk coefficient, the lower the first fraud level adopted, so as to ensure that users can generate a preliminary sense of vigilance. At the same time, the system will select the most targeted fraud type according to the user's occupation type, such as business fraud for enterprise employees, job hunting fraud for students, and loan fraud for self-employed individuals, etc. Through this quantitative calculation method based on user characteristics, the system can scientifically evaluate the user's risk tolerance and select appropriate fraud levels and types, making the subsequent anti-fraud publicity more targeted and easily acceptable to users.

[0041] Step 203: Retrieve the first fraud script and the first fraud tone that match the fraud type and the first fraud level from the preset script library.

[0042] Specifically, in order to build a complete first fraud strategy, the system matches the speech and tone based on the pre-established speech library. First, a two-dimensional index table of fraud types and fraud levels is constructed in the speech library, and each index node stores a corresponding speech template set. For example, when the fraud type is business-related and the first fraud level is high-level, the system locates the corresponding speech template set through the index. In this set, each speech template is provided with a keyword label and an applicable scenario label. The system calculates the matching score between the label and the current scenario, and selects the speech template with the highest score as the first fraud speech. At the same time, the system establishes a tone feature mapping table corresponding to the fraud level in the tone parameter library, including speech speed parameters, intonation parameters, and modal particle parameters. The system extracts the corresponding tone parameter combination from the mapping table according to the current first fraud level to generate the first fraud tone.

[0043] Step 203: Integrate the first fraud level, fraud type, first fraud speech, and first fraud tone into a first fraud strategy.

[0044] Specifically, after completing the retrieval of the words and tone, the system integrates the first fraud level, fraud type, first fraud words and first fraud tone according to the preset organizational structure template. During integration, the system first uses the first fraud level and fraud type as the basic attributes of the strategy, then fills the template with the first fraud words, and finally superimposes the parameter configuration of the first fraud tone to form a structured first fraud strategy data package. Through this index-based precise matching and structured integration method, the system can quickly generate fraud strategies that meet actual scenarios and improve the authenticity and persuasiveness of anti-fraud propaganda.

[0045] Step 30: Obtain a first feedback result of the current calling user on the first fraud scheme, and calculate an anti-fraud score value of the current calling user based on the first feedback result.

[0046] Specifically, to evaluate the anti-fraud awareness level of the current calling user, the system needs to obtain and analyze the user's feedback on the first fraud scenario. The system records the response data of the user during the call through a preset feedback collection template, including information such as the user's voice reply content, reply duration, and changes in tone and intonation. Natural language processing technology is used to segment and semantically analyze the user's voice reply content, extract keywords, and match them with a preset awareness of prevention word library. For example, when words such as "verify", "check", and "untrustworthy" appear in the user's reply, it indicates that the user has a strong awareness of prevention. At the same time, the system will also analyze the user's reply duration. If the user can quickly identify fraud features and make a vigilant reply, it means that they have good recognition ability. In addition, the system uses voice feature analysis technology to identify changes in the user's tone and intonation. For example, when the user shows a suspicious or rejecting tone, it indicates that they have a strong recognition ability. Based on the above multi-dimensional feedback data, a preset scoring model is used to calculate the anti-fraud score value. Specifically, the scoring model sets weight coefficients for feedback indicators in different dimensions, and sums up the weighted scores of each item to obtain the final anti-fraud score value. Through this scoring mechanism based on the user's actual feedback, the system can objectively evaluate the user's anti-fraud awareness level and provide a targeted improvement basis for subsequent anti-fraud publicity.

[0047] Based on the above embodiments, as an alternative embodiment, the step of calculating the anti-fraud score value of the current calling user based on the first feedback result may further include the following steps:

[0048] Step 301: Analyze the first feedback result to obtain the call duration, answer keywords, and question frequency.

[0049] Specifically, to extract the key feature indicators of the user's anti-fraud awareness from the first feedback result, the system needs to analyze and process the feedback data. First, the first feedback result is separated into two parts: voice data and timestamp data. For the timestamp data, the system obtains the call duration by calculating the difference between the start timestamp and the end timestamp of the call. For the voice data, the system uses speech recognition technology to convert it into text data and analyzes it using natural language processing technology. The system pre-constructs a keyword library containing preventive words such as "investigation", "verify", and "evidence", and retrieves the quantity and distribution positions of the answer keywords through text matching. At the same time, the system analyzes the intonation features of the voice data, extracts acoustic feature parameters such as pitch, volume, and speech rate. When obvious changes in the voice parameters are detected, such as a sudden increase in volume or a significant increase in speech rate, the system marks it as a question, and the question frequency is obtained by accumulating the marked times. Through this multi-dimensional data analysis method, the system can convert unstructured feedback data into quantifiable evaluation indicators, providing an objective basis for subsequent anti-fraud awareness evaluation.

[0050] Step 302: Determine a basic score based on the call duration.

[0051] Specifically, the basic score is set according to the length of the call. The system pre-sets four duration intervals and corresponding basic scores: when the call duration is between 0 and 30 seconds, it indicates that the user is quick to detect fraud, and the basic score is set to 90 points; when the call duration is between 30 seconds and 2 minutes, it indicates that the user is slightly hesitant, and the basic score is set to 80 points; when the call duration is between 2 minutes and 5 minutes, it indicates that the user is not vigilant enough, and the basic score is set to 70 points; when the call duration exceeds 5 minutes, it indicates that the user is extremely likely to be defrauded, and the basic score is set to 60 points.

[0052] Step 303: Determine a vigilance score based on the answer keywords and the question frequency.

[0053] Specifically, after determining the basic score, the system further calculates the vigilance score. The system pre-sets the keyword scoring rules: each time a prevention keyword is identified, such as "verification" and "evidence", 2 points will be added; at the same time, the system adjusts the score according to the frequency of questioning: each time a valid question is detected, such as a sudden change in tone or speed, 3 points will be added. The system adds the keyword score and the questioning score to get the vigilance score. Through this method of determining the basic score based on duration, combined with the vigilance score of keywords and questioning frequency, the system can fully reflect the user's anti-fraud awareness level and provide targeted suggestions for subsequent anti-fraud education.

[0054] Step 304: Perform weighted calculation on the basic score and the vigilance score to obtain an anti-fraud score.

[0055] Specifically, in order to comprehensively evaluate the user's anti-fraud awareness level, the embodiment of the present application fuses the basic score and the vigilance score to obtain the final anti-fraud score. Specifically, the piecewise function calculation method is adopted, and the interval of the basic score is first determined: when the basic score is in the 90-point interval, it indicates that the user has a strong recognition ability, and 80% of the vigilance score is included in the final score; when the basic score is in the 80-point interval, it indicates that the user has a certain awareness of prevention, and 100% of the vigilance score is included in the final score; when the basic score is in the 70-point interval, it indicates that the user is not vigilant enough, and 120% of the vigilance score is included in the final score; when the basic score is in the 60-point interval, it indicates that the user is very easy to be defrauded, and 150% of the vigilance score is included in the final score. This step-by-step calculation method can give the user a greater vigilance score incentive when the user's basic prevention ability is weak. The system obtains the anti-fraud score through this calculation method, which not only reflects the user's basic recognition ability, but also fully considers the vigilance performance shown by the user during the call, making the scoring result more objective and reasonable. For example, when the user's basic score is 70 points and the vigilance score is 15 points, based on the calculation ratio of 120%, the final anti-fraud score is 70+18=88 points, which reflects that the user has improved the overall anti-fraud level through active questioning and prevention.

[0056] Step 40: When the anti-fraud score value is greater than the score threshold, the first fraud strategy is adjusted to obtain a second fraud strategy.

[0057] Specifically, in order to provide more targeted simulation training for users with strong awareness of prevention, the system needs to dynamically adjust the fraud strategy based on the user's anti-fraud score. Among them, the system pre-sets the score threshold to 85 points. When it is detected that the user's anti-fraud score exceeds this threshold, it indicates that the user has a strong anti-fraud awareness. Analyze the key points in the first fraud strategy that are recognized by the user, including suspicious terms, identity information, financial data and other elements. Based on these recognition points, the system extracts more concealed speech templates from the preset fraud strategy library and constructs the second fraud strategy by replacing key information nodes. For example, when the first fraud strategy is recognized by the user using "joint investigation by the public security, procuratorial and judicial organs", the second fraud strategy will adopt the method of "appointment for door-to-door verification"; when the specific amount of funds mentioned in the first fraud strategy is questioned, the second fraud strategy will gradually obtain information in a step-by-step manner. Through this strategy adjustment method based on user prevention performance, the system can simulate the speech upgrade process of real fraudsters, help users experience and identify more confusing fraud methods, and further enhance users' anti-fraud capabilities.

[0058] Based on the above embodiment, as an optional embodiment, when the anti-fraud score value is greater than the score threshold, the step of adjusting the first fraud strategy to obtain the second fraud strategy may also include the following steps:

[0059] Step 401: When the anti-fraud score value is greater than the score threshold, analyze the warning points in the first feedback result.

[0060] Specifically, to make the next round of simulated fraud more targeted and challenging, the system needs to determine a higher level of fraud level based on the user's warning performance. When the user's anti-fraud score value exceeds the preset threshold of 85 points, the system first conducts a in-depth analysis of the first feedback result and extracts the key nodes where the user shows vigilance. The system uses semantic analysis technology to identify the suspicious statements and preventive performances in the first feedback result and classifies them into different types of warning points such as identity verification, information verification, and fund confirmation.

[0061] Step 402: Determine the second fraud level based on each warning point, and the second fraud level is higher than the first fraud level.

[0062] Specifically, for each warning point, the system calculates its time position, duration, and number of repeated suspicions to generate a warning intensity value. For example, when the user questions the identity information at the beginning of the call and repeatedly verifies it many times, the intensity value of this warning point is relatively high; when the user only hesitates slightly when hearing about fund operations, the intensity value of this warning point is relatively low. The system determines the second fraud level based on the distribution of the intensity values of each warning point and in combination with the level of the first fraud strategy. Specifically, if the user has the highest warning intensity for identity information, the level is increased by two levels on the basis of the first fraud level; if the user has the highest warning intensity for fund operations, the level is increased by three levels. Through this way of increasing the level based on the analysis of warning points, the system can specifically increase the difficulty of fraud prevention for the user's stronger prevention links and make the training more effective.

[0063] Step 403: Based on the fraud type and the first fraud level, retrieve the second fraud script and the second fraud tone corresponding to the second fraud level from the preset script library.

[0064] Specifically, to maintain the coherence of the call and enhance the concealment of the fraud strategy, the system needs to dynamically adjust the content of the conversation and the tone characteristics in the current call context. First, the system retrieves the first set of conversation scripts from the preset conversation script library based on the current fraud type (such as impersonating public security, procuratorial, and judicial organs), and this first set of conversation scripts contains standard conversation script content related to the current case investigation. To ensure the continuity of the conversation scripts, the system conducts a content correlation analysis between the key elements (such as case number, involved amount, suspect information, etc.) in the currently used first fraud conversation script and the first set of conversation scripts, and screens out the conversation script content that can be naturally connected and logically echoed to form the second set of conversation scripts. For example, when the first fraud conversation script mentions that there are abnormal transactions in the user's bank account, the content screened in the second set of conversation scripts will focus on in-depth inquiries about this abnormal transaction or guide the user to verify the relevant transaction records. Subsequently, the system selects the final second fraud conversation script from the second set of conversation scripts based on the user's demonstrated points of vigilance and the second fraud level. At the same time, the system extracts the second fraud tone that matches the second fraud level from the preset tone parameter library, where the second fraud tone includes speech rate parameters (such as a fast speech rate in an emergency, a steady speech rate when verifying information), intonation parameters (such as a deep intonation for an authoritative tone, a gentle intonation when soothing emotions), and emotional parameters (such as seriousness, concern, oppression, etc.). The system smoothly transitions the selected tone parameters with the currently used first fraud tone to avoid sudden changes in tone. For example, when the user expresses doubts about the identity information, the system, while maintaining the original serious tone, gradually adjusts the speech rate and intonation to make the tone transition to a more oppressive and authoritative direction to form the final second fraud tone. Through this coordinated adjustment of the conversation script content and tone characteristics, the system can enhance the deception of the fraud strategy while ensuring the natural fluency of the entire call process.

[0065] Step 404: Integrate the second fraud level, the second fraud conversation script, and the second fraud tone into the second fraud strategy.

[0066] Specifically, the system integrates the selected second fraud conversation script template with the tone parameters to generate a second fraud strategy that includes a complete conversation script logic and tone control. Through this precise matching method based on type and level, the system can generate a fraud strategy that is more in line with the real scenario and more challenging, enabling users to experience a more realistic fraud prevention scenario during training.

[0067] Step 50: Obtain the second feedback result of the current called user on the second fraud plan, generate an anti-fraud publicity report based on the first feedback result and the second feedback result, and send the anti-fraud publicity report to the current called user.

[0068] Specifically, in order to help users deeply understand their own performance characteristics in the anti-fraud process and provide targeted improvement suggestions, the system needs to conduct a comprehensive analysis of the feedback results of users in the two rounds of fraud strategies. First, all the reaction information of the user when facing the second fraud strategy is recorded, including the content of the call, voice characteristics, and coping methods, etc., to form the second feedback result. The system compares and analyzes the second feedback result with the first feedback result obtained previously, and extracts the behavioral characteristics of the user in the two rounds of coping process. For example, the system analyzes whether the user can still remain vigilant when facing the upgraded fraud speech, whether he or she is shaken when encountering a more confusing fraud tone, and whether he or she can maintain a sense of prevention under escalating pressure. Based on these analysis results, the system generates an anti-fraud publicity report containing personalized evaluations and improvement suggestions. The report first shows the specific performance of the user in the two rounds of testing, including the identification of vigilance points, the adoption of preventive measures, and the trend of changes in psychological state. Subsequently, the report provides detailed descriptions of the advantages and disadvantages shown by the user, for example, affirming the vigilance points that can be maintained at all times, and proposing improvement suggestions for the links that were neglected in the second round. Finally, the report provides prevention points and practical skills based on the typical characteristics of this type of fraud and the latest fraud methods. The system sends the anti-fraud publicity report to the user through SMS, email and other contact methods reserved by the user, so that the user can timely understand the current status of his or her anti-fraud ability and strengthen the prevention awareness in a targeted manner. Through this two-round feedback-based analysis and reporting mechanism, the system can help users establish a more comprehensive and lasting anti-fraud awareness and improve their ability to deal with real fraud.

[0069] Based on the above embodiment, as an optional embodiment, the step of generating an anti-fraud publicity report based on the first feedback result and the second feedback result may further include the following steps:

[0070] Step 501: Determine a change value of the alertness level of the current calling user based on the first feedback result and the second feedback result.

[0071] Specifically, in order to accurately evaluate the user's anti-fraud ability and provide personalized anti-fraud guidance, the system needs to conduct a quantitative analysis of the user's performance in the two rounds of fraud response process. The system first calculates the change value of the degree of vigilance based on the first feedback result and the second feedback result. The change value reflects the change in the user's awareness of prevention when facing the upgraded fraud strategy. The system uses a preset calculation model to compare the user's various indicators in the two rounds of feedback (such as the number of suspicious points identified, the timeliness of taking preventive measures, the firmness of resisting inducement, etc.) to obtain a quantitative change value of the degree of vigilance.

[0072] Step 502: Determine the anti-fraud awareness level based on the vigilance level change value.

[0073] Specifically, the system matches the change value of the vigilance level in a preset anti-fraud awareness level table to determine the user's anti-fraud awareness level. The level table divides the change value of the vigilance level into multiple intervals. For example, when the change value is greater than 0.8, it is determined as a high-level anti-fraud awareness; when the change value is between 0.3 and 0.8, it is determined as a medium-level anti-fraud awareness; when the change value is less than 0.3, it is determined as a low-level anti-fraud awareness.

[0074] Step 503: Determine an anti-fraud publicity report based on the anti-fraud awareness level and the type of fraud. The anti-fraud publicity report includes fraud characteristics and anti-fraud suggestions.

[0075] Specifically, after determining the anti-fraud awareness level, the system combines the current type of fraud and retrieves the corresponding report template from a preset anti-fraud publicity template library. This template contains targeted descriptions of fraud characteristics and anti-fraud suggestions for different anti-fraud awareness levels and types of fraud. For example, for users who show a low-level anti-fraud awareness in impersonating public security, procuratorial, and judicial frauds, the system will highlight the basic characteristics of this type of fraud (such as false call numbers, use of professional terms, etc.) and basic prevention methods in the report; for users who show a high-level anti-fraud awareness, it will introduce deeper changes in fraud techniques and advanced prevention skills. Through this personalized report generation mechanism based on quantitative analysis, the system can help users better understand their own anti-fraud capabilities and obtain more targeted improvement suggestions.

[0076] Based on the above embodiments, as an optional embodiment, the step of determining the change value of the vigilance level of the current calling user based on the first feedback result and the second feedback result may further include the following steps:

[0077] Step 5011: Extract the call key parameters from the first feedback result and the second feedback result respectively. The call key parameters include call duration, number of questions, and number of risk point identifications.

[0078] Specifically, from the call records of the first feedback result, the key parameters of the call are extracted through voice recognition and semantic analysis technology. The key parameters of the call include call duration, number of questions and number of risk point identification. Among them, the call duration parameter is obtained by calculating the duration from the user answering the call to hanging up the call, which reflects the user's resistance time during the fraud process; the number of questions parameter is obtained by identifying the frequency of the user's questioning or doubting statements during the call, such as the system detecting questioning words such as "this can't be a fraud" and "why do you do this" and accumulating their occurrence times; the number of risk point identification parameters is obtained by detecting the frequency of users pointing out suspicious information or seeing through fraudulent tricks, such as the number of times users mentioned "formal departments will not allow transfers" and "identity information needs to be verified" and other expressions of prevention awareness. The system uses the same extraction method to obtain the corresponding key parameters of the call from the second feedback result. Through this standardized parameter extraction mechanism, the system can convert the user's performance in two rounds of calls into quantifiable and comparable data indicators, providing an objective basis for the subsequent calculation of the change value of the degree of vigilance. For example, when the system finds that the number of questions raised by the user in the second round of calls has increased significantly, it means that the user's awareness of prevention has improved; when the number of risk point identifications has decreased, it indicates that the user may have become less vigilant when facing upgraded fraud strategies. Through this data-based analysis based on key parameters, the system can more accurately evaluate the changing trend of the user's anti-fraud ability.

[0079] Step 5012: Calculate the change rate of the call duration and the density change rate of the number of inquiries corresponding to the call duration.

[0080] Specifically, to accurately evaluate the changes in the anti-fraud performance of users during two rounds of calls, the system needs to perform standardized calculations and comparative analyses on the extracted key call parameters. First, calculate the change rate of call duration, that is, the ratio of the difference between the second-round call duration and the first-round call duration to the first-round call duration. This change rate reflects the change in the response time of users when facing upgraded fraud strategies. For example, when the first-round call duration is 10 minutes and the second-round is 15 minutes, the call duration change rate is 0.5, indicating that the user extended the prevention time in the second round. Subsequently, the system calculates the density change rate of the number of questions. That is, divide the number of questions in each of the two rounds of calls by the corresponding call duration to obtain the question density, and then calculate the change ratio of the two-round question densities. This density calculation method can eliminate the influence brought by the difference in call duration and more accurately reflect the actual change in the user's question frequency. For example, when there are 5 questions (density 0.5 questions / minute) in the first-round 10-minute call and 12 questions (density 0.8 questions / minute) in the second-round 15-minute call, the question density change rate is 0.6, indicating that the user increased the question frequency in the second round. Similarly, the system calculates the growth rate of the number of risk point identifications, that is, divide the ratio of the number of risk point identifications in the second round to the call duration minus the corresponding ratio in the first round, and then divide by the ratio in the first round. This calculation method can accurately reflect the improvement or decline in the user's risk identification ability. For example, when 0.3 risk points are identified per minute in the first round and it is increased to 0.5 risk points per minute in the second round, the growth rate is 0.67, indicating a significant improvement in the user's risk identification ability. Through this standardized change rate calculation mechanism, the system can objectively evaluate the changes in the anti-fraud performance of users in calls of different durations and provide reliable data support for subsequent vigilance level evaluations.

[0081] Step 5013: Statistically calculate the growth rate of the number of risk point identifications in the corresponding call duration.

[0082] Specifically, calculate the growth rate of the number of risk point identifications in the corresponding call duration, that is, divide the number of risk point identifications in the second-round call by its call duration to obtain the identification frequency per unit time, and then compare and calculate it with the identification frequency per unit time of the first-round call. For example, when 3 risk points are identified in the first-round 10-minute call (frequency 0.3 times / minute) and 8 risk points are identified in the second-round 15-minute call (frequency 0.53 times / minute), the system calculates the growth rate of 0.77 by calculating (0.53 - 0.3) / 0.3, indicating a significant improvement in the user's risk identification ability.

[0083] Step 5014: Calculate the change value of the vigilance level based on the change rate of call duration, density change rate, and growth rate.

[0084] Specifically, in order to more accurately evaluate the change in the user's vigilance level, the embodiments of the present application adopt a composite calculation method that takes into account the correlation and non-linear characteristics between indicators. Specifically, the system uses the following calculation formula to determine the change value of the vigilance level: Change value of vigilance level = arctanh(α×R) × [1 + β×(1 - e (-γ×D)) × sqrt(1 + δ×L 2 ), where R is the change rate of call duration, D is the change rate of suspicion density, and L is the growth rate of risk point identification; α, β, γ, δ are adjustment coefficients, taking values of 0.8, 0.6, 0.9, and 0.7 respectively. In this formula, the arctanh function is used to handle the saturation effect of the change in call duration, that is, when the change in call duration is too large, its impact on the vigilance level will tend to be stable; the exponential decay term (1 - e (-γ×D) ) reflects the non-linear impact of the change in suspicion density on the vigilance level, reflecting the marginal diminishing effect of the improvement in the suspicion ability; the square term sqrt(1 + δ×L 2 ) emphasizes the importance of the risk point identification ability, and will make a greater contribution when the identification ability is significantly improved. For example, when R = 0.5, D = 0.6, I = 0.77, the system first calculates arctanh(0.8×0.5) = 0.549, then calculates [1 + 0.6×(1 - e (-0.9×0.6) )] = 1.296, and finally calculates sqrt(1 + δ×L 2 ) = 1.336. The three items are multiplied to obtain the final change value of the vigilance level of 0.952. This calculation formula can more accurately depict the change characteristics of the user's anti-fraud ability, taking into account the interaction and non-linear influence between various indicators, and providing a more scientific quantitative basis for the subsequent determination of the anti-fraud awareness level.

[0085] Please refer to Figure 2 , which is a schematic diagram of the modules of a publicity system for countering online fraud provided by the embodiments of the present application. Among them, the system includes:

[0086] A user information acquisition module, configured to acquire a to-be-called list, where the to-be-called list includes at least one called user;

[0087] A first strategy determination module, configured to determine the current called user in the to-be-called list, and determine a first fraud strategy based on the basic user information of the current called user. The first fraud strategy includes a fraud type, a first fraud level, a first fraud script, and a first fraud tone;

[0088] An anti-fraud score calculation module, configured to acquire a first feedback result of the current called user on the first fraud plan, and calculate an anti-fraud score value of the current called user based on the first feedback result;

[0089] A second strategy determination module, configured to adjust the first fraud prevention strategy to obtain a second fraud prevention strategy when the fraud prevention score value is greater than a score threshold;

[0090] An anti-fraud publicity sending module, configured to obtain a second feedback result of the current calling user on the second fraud prevention plan, generate an anti-fraud publicity report based on the first feedback result and the second feedback result, and send the anti-fraud publicity report to the current calling user.

[0091] Optionally, the first strategy determination module is further configured to calculate a risk coefficient based on the basic information of the current calling user, where the basic information includes age, occupation type, and education level;

[0092] Determine a first fraud level based on the risk coefficient, and determine a fraud type according to the occupation type;

[0093] Retrieve a first fraud prevention script and a first fraud prevention tone that match the fraud type and the first fraud level from a preset script library;

[0094] Integrate the first fraud level, fraud type, first fraud prevention script, and first fraud prevention tone into the first fraud prevention strategy.

[0095] Optionally, the fraud prevention score calculation module is further configured to parse the first feedback result to obtain a call duration, response keywords, and suspicion frequency;

[0096] Determine a basic score based on the call duration;

[0097] Determine a vigilance score based on the response keywords and the suspicion frequency;

[0098] Perform weighted calculation on the basic score and the vigilance score to obtain the fraud prevention score value.

[0099] Optionally, when the fraud prevention score value is greater than the score threshold, the second strategy determination module is further configured to analyze the vigilance points in the first feedback result;

[0100] Determine a second fraud level based on each of the vigilance points, where the second fraud level is higher than the first fraud level;

[0101] Retrieve a second fraud prevention script and a second fraud prevention tone corresponding to the second fraud level from a preset script library based on the fraud type and the first fraud level;

[0102] Integrate the second fraud level, second fraud prevention script, and second fraud prevention tone into the second fraud prevention strategy.

[0103] Optionally, the second policy determination module is further configured to retrieve a first set of scripts corresponding to the fraud type from a preset script library, and screen out a second set of scripts related to the first fraud script from the first set of scripts;

[0104] Based on the warning points, screen out a second fraud script and a second fraud tone corresponding to the second fraud level from the second set of scripts.

[0105] Optionally, the anti-fraud publicity sending module is further configured to determine a change value of the vigilance level of the current calling user based on the first feedback result and the second feedback result;

[0106] Determine the anti-fraud awareness level based on the change value of the vigilance level;

[0107] Determine an anti-fraud publicity report based on the anti-fraud awareness level and the fraud type, where the anti-fraud publicity report includes fraud characteristics and anti-fraud suggestions.

[0108] Optionally, the anti-fraud publicity sending module is further configured to extract call key parameters from the first feedback result and the second feedback result respectively, where the call key parameters include call duration, number of questions, and number of risk point identifications;

[0109] Calculate the change rate of the call duration and the density change rate of the number of questions corresponding to the call duration;

[0110] Statistically calculate the growth rate of the number of risk point identifications corresponding to the call duration;

[0111] Calculate the change value of the vigilance level based on the change rate of the call duration, the density change rate, and the growth rate.

[0112] It should be noted that: when the system provided in the above embodiment realizes its functions, only the above-mentioned division of each functional module is used for illustration. In actual application, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process can be seen in the method embodiment, which will not be elaborated here.

[0113] The embodiment of the present application also provides a computer storage medium, which can store multiple instructions, and the instructions are suitable for being loaded and executed by a processor to execute an anti-fraud publicity method for countering online fraud in the above embodiment. The specific execution process can refer to the specific description in the above embodiment, which will not be elaborated here.

[0114] Please refer to Figure 3 The present application also discloses an electronic device. Figure 3It is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0115] Among them, the communication bus 302 is used to realize the connection and communication between these components.

[0116] Among them, the user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may further include a standard wired interface and a wireless interface.

[0117] Among them, the network interface 304 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0118] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts within the entire server. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling data stored in the memory 305, it executes various functions of the server and processes data. Optionally, the processor 301 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 301 may integrate a combination of one or several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.; the GPU is responsible for the rendering and drawing of the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above modem may not be integrated into the processor 301 and may be implemented separately by a single chip.

[0119] Among them, the memory 305 may include a Random Access Memory (RAM), or may also include a Read-Only Memory. Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area can store the data involved in the above-mentioned method embodiments. Optionally, the memory 305 may also be at least one storage device located far from the aforementioned processor 301. Refer to Figure 3 , in the memory 305 as a computer storage medium, it may include an operating system, a network communication module, a user interface module, and an application program for a method of promoting anti-network fraud.

[0120] In Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program for a method of promoting anti-network fraud stored in the memory 305. When executed by one or more processors 301, the electronic device 300 is caused to execute one or more of the methods as described in the above embodiments. It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0121] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0122] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some service interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0123] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0124] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0125] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present application. And the aforementioned memory includes: various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0126] The above are only exemplary embodiments of the present disclosure and should not be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will easily think of other implementation schemes of the present disclosure after considering the specification and the disclosure of the practical truth.

[0127] The present application aims to cover any variations, uses, or adaptive changes of the present disclosure. These variations, uses, or adaptive changes follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A propaganda method for countering online fraud, characterized in that: The method comprises: Acquire a waiting-to-call list, wherein the waiting-to-call list includes at least one calling user; Determine a current calling user in the waiting-to-call list, and determine a first fraud strategy based on basic user information of the current calling user, wherein the first fraud strategy includes a fraud type, a first fraud level, a first fraud speech, and a first fraud tone; Obtaining a first feedback result of the current calling user on a first fraud scheme, and calculating an anti-fraud score value of the current calling user based on the first feedback result; When the anti-fraud score is greater than a score threshold, the first fraud strategy is adjusted to obtain a second fraud strategy; obtaining a second feedback result of the current calling user on the second fraud scheme, Extracting key call parameters from the first feedback result and the second feedback result respectively, wherein the key call parameters include call duration, number of inquiries, and number of risk point identifications; Calculate the change rate of the call duration and the density change rate of the number of inquiries corresponding to the call duration; Counting the growth rate of the number of risk point identifications in the corresponding call duration; Calculate the alertness level change value based on the call duration change rate, density change rate and growth rate; Determining the anti-fraud awareness level based on the vigilance level change value; An anti-fraud publicity report is determined based on the anti-fraud awareness level and the fraud type, the anti-fraud publicity report including fraud characteristics and anti-fraud suggestions, and the anti-fraud publicity report is sent to the current calling user.

2. The propaganda method for countering online fraud according to claim 1 is characterized in that: The determining of the first fraud strategy based on the basic user information of the current calling user includes: Calculating a risk factor based on basic information of the current calling user, the basic information including age, occupation type and education level; Determining a first fraud level based on the risk factor, and determining a fraud type based on the occupation type; Retrieving a first fraudulent speech and a first fraudulent tone that match the fraud type and the first fraud level from a preset speech library; The first fraud level, fraud type, first fraud speech and first fraud tone are integrated into the first fraud strategy.

3. The propaganda method for countering online fraud according to claim 1 is characterized in that: The calculating the anti-fraud score value of the current calling user based on the first feedback result includes: Analyze the first feedback result to obtain call duration, answer keywords and question frequency; Determine a basic score based on the call duration; Determining a vigilance score based on the answer keywords and the questioning frequency; The basic score and the vigilance score are weighted and calculated to obtain an anti-fraud score.

4. The propaganda method for countering online fraud according to claim 1 is characterized in that: When the anti-fraud score is greater than a score threshold, adjusting the first fraud strategy to obtain a second fraud strategy includes: When the anti-fraud score is greater than the score threshold, analyzing the warning points in the first feedback result; Determining a second fraud level based on each of the vigilance points, wherein the second fraud level is higher than the first fraud level; Based on the fraud type and the first fraud level, retrieve a second fraud speech and a second fraud tone corresponding to the second fraud level from a preset speech library; The second fraud level, the second fraud words and the second fraud tone are integrated into the second fraud strategy.

5. The propaganda method for countering online fraud according to claim 4 is characterized in that: The method of retrieving a second fraud speech and a second fraud tone corresponding to the second fraud level from a preset speech library based on the fraud type and the first fraud level includes: Retrieving a first speech set corresponding to the fraud type from a preset speech library, and selecting a second speech set related to the first fraud speech from the first speech set; Based on the vigilance point, the second fraud speech and the second fraud tone corresponding to the second fraud level are screened out from the second speech set.

6. A system for countering online fraud for implementing the method for countering online fraud as claimed in claim 1, characterized in that: The system comprises: A user information acquisition module, used to acquire a waiting-to-call list, wherein the waiting-to-call list includes at least one calling user; A first strategy determination module, used to determine a current calling user in the waiting-to-call list, and determine a first fraud strategy based on basic user information of the current calling user, wherein the first fraud strategy includes a fraud type, a first fraud level, a first fraud speech, and a first fraud tone; an anti-fraud score calculation module, configured to obtain a first feedback result of the current calling user on the first fraud scheme, and calculate an anti-fraud score value of the current calling user based on the first feedback result; A second strategy determination module, configured to adjust the first fraud strategy to obtain a second fraud strategy when the anti-fraud score value is greater than a score threshold; An anti-fraud publicity sending module is used to obtain the second feedback result of the current calling user on the second fraud scheme, generate an anti-fraud publicity report based on the first feedback result and the second feedback result, and send the anti-fraud publicity report to the current calling user.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 5.

8. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-5.

Images