Anti-fraud wristband control method and intelligent anti-fraud wristband

Abstract

The present application is applicable to the technical field of anti-fraud bracelets, and in particular, to an anti-fraud bracelet control method and a smart anti-fraud bracelet. The anti-fraud bracelet control method is applied to the smart anti-fraud bracelet, and the smart anti-fraud bracelet is connected to the mobile terminal for communication. The anti-fraud bracelet control method includes: receiving call messages from the mobile terminal in real time; wherein the call message methods include telephone communication, SMS communication, and face-to-face conversation; analyzing the call messages to identify key content; when the key content meets the fraud conditions, providing scene reminders in the form of call messages. The method monitors and analyzes the communication content between the user and the contact in real time, identifies potential fraudulent behavior, and adopts different reminder methods according to the communication information method, which can effectively prevent users from suffering economic losses or other forms of damage, and take effective reminders in response to different scenarios, thereby improving fraud identification capabilities and improving the real-time, accuracy, and effectiveness of alarms.

Description

Technical Field

[0001] The present application belongs to the technical field of anti-fraud bracelets, and in particular relates to an anti-fraud bracelet control method and a smart anti-fraud bracelet. Background Art

[0002] With the rapid development of information technology, fraud methods have become increasingly diverse and complex. From traditional telephone fraud to today's social media fraud, fraudsters are constantly updating their methods. In particular, people at home are in a relaxed state and are relatively less vigilant against fraud, so they have become the main target of fraudsters. Although home is a warm haven, it has also become a place where fraud incidents frequently occur. According to statistics, as of 2023, home and door-to-door fraud cases accounted for about 34% of total fraud cases, which reflects the severity of the fraud problem in the home environment.

[0003] As cybersecurity issues become more and more prominent, the economic losses caused by fraud incidents are also increasing year by year. It is estimated that by 2024, the size of the global cybersecurity market has exceeded US$180 billion, and is expected to further grow to nearly US$315 billion by 2029. This trend shows that the demand for technology to prevent fraud is increasing, and society urgently needs an effective tool that can help people identify and prevent fraud.

[0004] Although some anti-fraud tools or applications currently available on the market can provide protection to a certain extent, they lack certain real-time and portability, and cannot meet the needs of users to prevent fraud anytime and anywhere. Summary of the invention

[0005] The embodiments of the present application provide an anti-fraud bracelet control method and a smart anti-fraud bracelet, which can solve the problem that some anti-fraud tools or applications currently available on the market lack certain real-time and portability and cannot meet the needs of users to prevent fraud anytime and anywhere.

[0006] In a first aspect, an embodiment of the present application provides an anti-fraud bracelet control method, the anti-fraud bracelet control method is applied to a smart anti-fraud bracelet, the smart anti-fraud bracelet is communicatively connected to a mobile terminal, and the anti-fraud bracelet control method includes:

[0007] Receiving the call message of the mobile terminal in real time; wherein the call message includes telephone communication, SMS communication and face-to-face conversation;

[0008] Analyze the call messages to identify key content;

[0009] When the key content meets the fraud conditions, a scenario reminder is provided in the form of the call message.

[0010] The above technical solutions in the embodiments of the present application have at least the following technical effects:

[0011] The anti-fraud bracelet control method provided by the present application first receives call messages including telephone communications, text message communications, and face-to-face conversations from a mobile terminal in real time; then analyzes the call messages to identify key content; when the key content meets the fraud conditions, a scene reminder is made according to the call message. This method monitors and analyzes the communication content between the user and the contact in real time, identifies potential fraudulent behavior, and adopts different reminder methods according to the communication information. It can effectively prevent users from suffering economic losses or other forms of damage, and take effective reminders in response to different scenarios, thereby improving the ability to identify fraud and improving the real-time, accuracy and effectiveness of the alarm.

[0012] In a possible implementation manner of the first aspect, analyzing the call message to identify key content includes:

[0013] Analyze the call message to obtain the communication frequency and specific words; wherein the communication frequency is used to reflect the number of times and intervals of contact between the contact and the user, and the specific words are used to reflect phrases or short sentences related to fraud;

[0014] An analysis is performed based on the communication frequency and the specific vocabulary to obtain key content.

[0015] In a possible implementation manner of the first aspect, the analyzing according to the communication frequency and the specific vocabulary to obtain key content includes:

[0016] Performing combination analysis between the specific words to obtain the degree of word connection of key contents;

[0017] Analyze the sentence structures corresponding to the specific words to obtain sentiment tendency information;

[0018] The intimacy information of the key content is obtained by analyzing the communication frequency and the emotional tendency information; wherein the intimacy information is used to reflect the intimacy between the contact person and the user.

[0019] In a possible implementation of the first aspect, performing a combination analysis on the specific words to obtain a degree of word connection of key content includes:

[0020] Screening the multiple specific words to determine sensitive words;

[0021] Calculating the correlation values ​​of the sensitive words and other specific words respectively;

[0022] The average of the plurality of association values ​​is calculated to obtain the degree of vocabulary connection of the key content.

[0023] In a possible implementation of the first aspect, analyzing the sentence structures corresponding to the multiple specific words to obtain the sentiment tendency information includes:

[0024] Analyze the sentence structure where the specific vocabulary is located to obtain emotional vocabulary; wherein the emotional vocabulary includes vocabulary that contacts emotional intentions and attitudes;

[0025] Analyzing the sentiment words and the specific words to obtain a sentence polarity value; wherein the sentence polarity value is used to reflect the sentiment tendency of the sentence;

[0026] Filter out the maximum value among multiple sentence polarity values ​​to obtain sentiment tendency information.

[0027] In a possible implementation of the first aspect, the analyzing according to the communication frequency and the emotional tendency information to obtain the intimacy information of the key content includes:

[0028] Analyze according to the communication frequency to obtain the intimacy weight;

[0029] The intimacy weight is weighted on the emotional tendency information to obtain the intimacy information of the key content.

[0030] In a possible implementation manner of the first aspect, when the key content meets the fraud condition, the method includes:

[0031] When the degree of vocabulary connection of the key content is greater than or equal to a first preset degree, the fraud condition is met;

[0032] and / or, when the degree of vocabulary connection of the key content is less than the first preset degree and greater than the second preset degree, assigning a value according to the intimacy information to obtain an additional value;

[0033] The added value is summed with the degree of vocabulary connection to obtain a total added value;

[0034] When the total additional value is greater than or equal to the first preset level, the fraud condition is met.

[0035] In a possible implementation of the first aspect, the performing a scene reminder according to the call message includes:

[0036] When the call message is in the form of telephone communication, a vibration reminder and a light reminder are performed; when the call message is in the form of text message communication, a light reminder and a voice reminder are performed; when the call message is in the form of face-to-face conversation, a vibration reminder and a sound reminder are performed.

[0037] In a possible implementation manner of the first aspect, after performing the scene reminder according to the call message, the method further includes:

[0038] The control device receives feedback information;

[0039] Sending a help message to another mobile terminal based on the feedback information;

[0040] The receiving feedback information comprises:

[0041] Receiving a triggering electrical signal from the smart anti-fraud bracelet;

[0042] And / or, after the scene reminder exceeds the preset time, obtaining the re-communication information; wherein the re-communication information is used to reflect the conversation information between the user and the contact after the scene reminder is issued;

[0043] Calculating the relevance between the second communication information and the communication information;

[0044] When the correlation is greater than a preset threshold, feedback information is generated.

[0045] In a second aspect, an embodiment of the present application provides an anti-fraud bracelet control device, comprising:

[0046] An acquisition module, used for receiving the call information of the mobile terminal in real time; wherein the call information includes telephone communication, SMS communication and face-to-face conversation;

[0047] An analysis module, used to analyze the call message and identify key content;

[0048] The reminder module is used to provide a scene reminder in the form of the call message when the key content meets the fraud condition.

[0049] In the third aspect, an embodiment of the present application provides a smart anti-fraud bracelet, comprising a ring band, a scene reminder device and a control device, wherein the scene reminder device and the control device are arranged on the ring band, and the control device is electrically connected to the scene reminder device. The control device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the method described in any one of the first aspects above is implemented.

[0050] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the above-mentioned first aspects is implemented.

[0051] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on a smart anti-fraud bracelet, the smart anti-fraud bracelet executes the anti-fraud bracelet control method described in any one of the first aspects above.

[0052] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0054] Figure 1 It is a flowchart of the anti-fraud bracelet control method provided in an embodiment of the present application;

[0055] Figure 2 It is a schematic diagram of the implementation flow of the anti-fraud bracelet control method provided in the embodiment of the present application;

[0056] Figure 3 It is a structural diagram of a smart anti-fraud bracelet provided in an embodiment of the present application;

[0057] Figure 4 It is a structural schematic diagram of the anti-fraud wristband control device provided in an embodiment of the present application;

[0058] Figure 5 It is a structural schematic diagram of the control device of the smart anti-fraud bracelet provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0060] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0061] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0062] As used in the specification of this application and the appended claims, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrase "if it is determined" or "if the described condition or event is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce the described condition or event is detected" or "in response to detecting the described condition or event" depending on the context.

[0063] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0064] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0065] With the rapid development of information technology, fraud methods have become increasingly diverse and complex. From traditional telephone fraud to today's social media fraud, fraudsters are constantly updating their methods. In particular, people at home are in a relaxed state and are relatively less vigilant against fraud, so they have become the main target of fraudsters. Although home is a warm haven, it has also become a place where fraud incidents frequently occur. According to statistics, as of 2023, home and door-to-door fraud cases accounted for about 34% of total fraud cases, which reflects the severity of the fraud problem in the home environment.

[0066] As cybersecurity issues become more and more prominent, the economic losses caused by fraud incidents are also increasing year by year. It is estimated that by 2024, the size of the global cybersecurity market has exceeded US$180 billion, and is expected to further grow to nearly US$315 billion by 2029. This trend shows that the demand for technology to prevent fraud is increasing, and society urgently needs an effective tool that can help people identify and prevent fraud.

[0067] Although some anti-fraud tools or applications currently available on the market can provide protection to a certain extent, they lack certain real-time and portability, and cannot meet the needs of users to prevent fraud anytime and anywhere.

[0068] To solve the above problems, the embodiments of the present application provide an anti-fraud bracelet control method and a smart anti-fraud bracelet. In this method, call messages including telephone communications, text message communications, and face-to-face conversations from a mobile terminal are first received in real time; then the call messages are analyzed to identify key content; when the key content meets the fraud conditions, a scenario reminder is made in the form of a call message. This method identifies potential fraudulent behavior by real-time monitoring and analyzing the content of communications between users and contacts, and adopts different reminder methods according to the form of communication information. It can effectively prevent users from suffering economic losses or other forms of damage, and take effective reminders in response to different scenarios, thereby improving fraud identification capabilities and improving the real-time, accuracy and effectiveness of alarms.

[0069] The anti-fraud bracelet control method provided in the embodiment of the present application can be applied to a smart anti-fraud bracelet. In this case, the smart anti-fraud bracelet is the executor of the anti-fraud bracelet control method provided in the embodiment of the present application. The embodiment of the present application does not impose any restrictions on the specific type of the smart anti-fraud bracelet.

[0070] For example, the smart anti-fraud bracelet may include a ring belt, a scene reminder device and a control device, wherein the scene reminder device and the control device are arranged on the ring belt, and the control device is electrically connected to the scene reminder device. The scene reminder device is used to remind the user. The scene reminder device includes an adjustment device, a light-emitting device, a voice device and a vibration device. The adjustment device is arranged on the ring belt to control the contraction of the ring belt, such as a small motor or memory metal, etc., but not limited to this. The light-emitting device is arranged on the ring belt to emit a warning light, such as an LED lamp or other types of light sources. The voice device is arranged on the ring belt to issue a voice or sound reminder, and the voice device can be a voice output device such as a small speaker. The vibration device is arranged on the ring belt to generate vibration, and the vibration device can be a vibration motor, piezoelectric ceramics, etc., but not limited to this. The control device monitors and controls the entire scene reminder process. The control device can be a microcontroller (MCU), a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), a low-power Bluetooth (BLE) chip, etc.

[0071] In order to better understand the anti-fraud bracelet control method provided in the embodiment of the present application, the specific implementation process of the anti-fraud bracelet control method provided in the embodiment of the present application is exemplarily introduced below.

[0072] Figure 1 and Figure 2A schematic flow chart of an anti-fraud bracelet control method provided in an embodiment of the present application is shown. The anti-fraud bracelet control method is applied to a smart anti-fraud bracelet, which is communicatively connected to a mobile terminal. The anti-fraud bracelet control method includes:

[0073] S100, receiving a call message from a mobile terminal in real time; wherein the call message includes telephone communication, SMS communication and face-to-face conversation.

[0074] It is understood that the mobile terminal can be a device with communication and recording functions, such as a mobile phone, a tablet, a smart watch, etc. The SMS communication method can be the communication of an application in the mobile terminal, such as operator SMS, WeChat, shopping software, etc. During a face-to-face conversation, the mobile terminal obtains the recording permission and can obtain the communication content between the user and the interlocutor in real time.

[0075] S200, analyzing the call message to identify key content.

[0076] It can be understood that when the call message is in the form of telephone communication or text message communication, the communication text can be directly analyzed. When the call message is in the form of face-to-face conversation, the voice can be converted into text through voice recognition technology, and then the text content can be further analyzed.

[0077] For example, the call message text can be input into the learning model, and the learning model then outputs the corresponding key content; the key content can also be obtained by matching the call message text with the anti-fraud database, etc., but not limited to this. The learning model is trained by multiple sets of training data, and each set of training data in the multiple sets of training data includes call message text and labels for representing key content. The training process of the learning model is: collect a large number of call message text samples, add labels to each sample, and the label content is the key content of the corresponding text sample; then divide the data set into a training set (for example, 70%), a verification set (for example, 15%) and a test set (for example, 15%) in proportion, and train, verify and test the learning model. The anti-fraud database refers to a database containing key content corresponding to different call message texts. These data can be obtained through laboratory experiments, on-site measurements and monitoring, and previous experience. After obtaining, the collected data is sorted, classified and archived, useful information and rules are extracted, and the relevant data is saved in the database to form an anti-fraud database.

[0078] In a possible implementation, in step S200, analyzing the call message to identify key content includes:

[0079] S210, analyzing the call information to obtain the communication frequency and specific words; wherein the communication frequency is used to reflect the number of times and intervals of contact between the contact and the user, and the specific words are used to reflect phrases or short sentences related to fraud.

[0080] It is understood that the analysis period of the number of times and intervals of contact between the contact and the user can be statistically analyzed from the total time from the first contact between the contact and the user to the current communication. Phrases or phrases related to fraud may include direct words such as "transfer", "winning", "verification code", "account", and indirect words such as "legal issues", "authentication", "activation", and "authorization".

[0081] For example, the interval in the communication frequency can be calculated by calculating the average interval according to the number of contacts in the total time from the first contact between the contact and the user to the current communication; or a preset time period can be selected from the total time from the first contact between the contact and the user to the current communication, such as the last six months or one year, to calculate the average interval in the preset time period, etc., but not limited to this. Specific vocabulary can be obtained by inputting call information into a learning model, and the learning model outputs the corresponding specific vocabulary; or the call information can be matched with an anti-fraud database to obtain the corresponding specific vocabulary, etc., but not limited to this.

[0082] S220, analyzing based on the communication frequency and specific words to obtain key content.

[0083] Exemplarily, the potential purpose of the contact can be obtained by analyzing the degree of connection between specific words and the expectations expressed in the sentences in which each specific word appears, and then the degree of intimacy between the contact and the user can be obtained by combining the communication frequency analysis to obtain the key content; the communication frequency and specific words can also be input into the learning model, and the learning model outputs the corresponding key content, etc., but not limited to this.

[0084] With this setting, through multi-level in-depth analysis of call messages, it can not only identify specific words related to fraud, but also judge the behavior patterns of contacts by calculating the frequency and interval of contact, and further infer potential purposes by analyzing the degree of connection between specific words and the expectations expressed. It also evaluates the intimacy between the contact and the user based on the frequency of communication, thereby comprehensively judging the true intention of the call content, effectively improving the accuracy and reliability of the smart anti-fraud bracelet in identifying potential fraudulent behaviors.

[0085] In a possible implementation, in step S220, analysis is performed based on the communication frequency and specific words to obtain key content, including:

[0086] S221, performing combination analysis between specific words to obtain the degree of word connection of key contents.

[0087] It can be understood that the degree of vocabulary connection is used to reflect the frequency of occurrence of idiomatic language between specific words in fraudulent behavior. The higher the frequency of occurrence, the greater the degree of vocabulary connection. For example, all specific words can be input into the learning model, and the learning model outputs the degree of vocabulary connection between specific words; specific words can also be matched in the anti-fraud database to obtain the corresponding degree of vocabulary connection, etc., but not limited thereto.

[0088] In a possible implementation, in step S221, specific words are combined and analyzed to obtain the degree of word connection of key contents, including:

[0089] S2211, screening multiple specific words to determine sensitive words.

[0090] It is understood that sensitive words are used to reflect the specific words that appear most frequently in all fraudulent behaviors. For example, multiple specific words can be input into a learning model, and the learning model outputs the corresponding sensitive words. Alternatively, multiple specific words can be matched with an anti-fraud database to obtain the corresponding sensitive words, etc., but not limited thereto.

[0091] S2212, respectively calculating the correlation values ​​between the sensitive words and other specific words.

[0092] It can be understood that the association value is used to reflect the number or frequency of other specific words appearing when sensitive words appear in fraudulent behavior. The higher the number or frequency of appearance, the greater the association value. Exemplarily, the mutual information value between sensitive words and specific words can be calculated. The higher the mutual information value, the closer the relationship between the two, and then the mutual information value is converted into an association value; the LLR value of sensitive words and specific words can also be calculated. LLR is used to measure whether the co-occurrence of sensitive words and specific words is significantly higher than the level of random co-occurrence. The larger the LLR value, the more significant the correlation between the two, and then the LLR value is converted into an association value, and so on. Calculation methods, but not limited to this.

[0093] S2213, calculating the average of multiple correlation values ​​to obtain the degree of vocabulary connection of key contents.

[0094] Exemplarily, all calculated association values ​​can be aggregated to form an association value list. For example, if the sensitive word "transfer" and the specific words "verification code", "account", "winning" and so on are respectively calculated with association values, a list containing these association values ​​is formed, and the average value (mean) of these association values ​​is calculated to obtain a comprehensive vocabulary connection degree index. If the calculated mean is high, it indicates that there is a high degree of connection between the sensitive word and other specific words, indicating that there may be a high risk of fraud. If the calculated mean is low, it indicates that the connection between the sensitive word and other specific words is weak, indicating that there may be a low risk of fraud.

[0095] In this way, by calculating the average of multiple correlation values, the degree of lexical connection of key content can reflect the overall closeness of the connection between sensitive words and other specific words. This indicator helps to comprehensively evaluate whether there is potential fraud risk in the content of calls or text messages.

[0096] S222, analyzing the sentence structures corresponding to the multiple specific words to obtain sentiment tendency information.

[0097] For example, by analyzing the sentence structure corresponding to specific words, words representing emotions can be obtained. By analyzing the connection between specific words and words representing emotions, the intention of the contact person can be known, thereby obtaining emotional tendency information. Alternatively, the sentence containing the specific words can be input into a learning model, and the learning model outputs the corresponding emotional tendency information, and so on, but not limited to this.

[0098] In a possible implementation, in step S222, the sentence structures corresponding to the multiple specific words are analyzed to obtain sentiment tendency information, including:

[0099] S2221, analyzing the sentence structure in which the specific vocabulary is located to obtain sentiment vocabulary; wherein the sentiment vocabulary includes vocabulary that relates to the emotional intention and attitude of the contact.

[0100] It can be understood that, first, the sentence structure of the specific vocabulary can be analyzed through natural language processing technology (such as dependency syntax analysis, component syntax analysis, etc.), the sentence components such as subject, predicate, object, etc. can be identified, and the context of the specific vocabulary in the sentence, including the context of the preceding and following texts, can be analyzed to better understand its meaning. Then the sentence containing the specific vocabulary can be matched with the sentiment dictionary to find out the vocabulary containing sentiment tendencies. The sentiment dictionary can include positive sentiment words (such as "thank you" and "satisfied") and negative sentiment words (such as "threat" and "intimidation"). Sentiment analysis algorithms (such as rule-based methods, machine learning-based methods, etc.) are used to extract sentiment words from sentences. These algorithms can identify the sentiment tendencies of sentences and mark out key sentiment words.

[0101] S2222, analyzing the sentiment words and the specific words to obtain a sentence polarity value; wherein the sentence polarity value is used to reflect the sentiment tendency of the sentence.

[0102] It can be understood that after obtaining the sentiment words, the sentiment intensity and sentiment polarity between the specific words corresponding to the sentences where each sentiment word is located are calculated respectively. The sentiment intensity is used to quantify the strength of the sentiment tendency. The sentiment polarity includes positive, negative or neutral. Among them, positive means that the sentiment tendency of the sentence is positive, and there is a great possibility that there is no fraud. Neutral means that the sentiment tendency of the sentence is peaceful, and there may be no fraud. Negative means that the sentiment tendency of the sentence is negative, and there may be fraud.

[0103] S2223, filter out the maximum value among multiple sentence polarity values ​​to obtain sentiment tendency information.

[0104] It can be understood that the maximum value is selected from multiple sentence polarity values ​​to reflect the strongest emotional tendency in the entire call or text message content, and the emotional tendency information of the maximum value is used to reflect the most representative emotional tendency in the entire call or text message content. If the maximum value is positive, it means that the overall emotional tendency is positive; if it is negative, it means that the overall emotional tendency is negative; if it is neutral, it means that the emotional tendency is neutral.

[0105] With this setting, the sentiment dictionary and sentiment analysis algorithm are combined to extract sentiment words, calculate sentiment intensity and polarity, and finally screen out the maximum value among multiple sentence polarity values ​​to reflect the overall sentiment tendency. This can comprehensively and accurately evaluate the sentiment tendency in the call or text message content, improve detection accuracy, enhance recognition ability, and quantify the strength of sentiment tendency, ultimately achieving effective identification and early warning of potential fraudulent behavior.

[0106] S223, analyzing the communication frequency and the emotional tendency information to obtain the intimacy information of the key content; wherein the intimacy information is used to reflect the intimacy between the contact person and the user.

[0107] For example, the degree of understanding between the user and the contact can be first determined by the communication frequency, and then the emotional tendency information is weighted by the degree of understanding, that is, if the communication frequency is higher, the degree of understanding between the user and the contact is higher, and the emotional tendency information is positive, the intimacy is higher; if the communication frequency is lower, the degree of understanding between the user and the contact is lower, and the emotional tendency information is negative, the intimacy is lower, and so on. The communication frequency and emotional tendency information can also be input into the learning model, and the learning model then outputs the corresponding intimacy information, etc., but not limited to this.

[0108] In a possible implementation, in step S223, the intimacy information of the key content is obtained by analyzing the communication frequency and the emotional tendency information, including:

[0109] S2231, analyze according to the communication frequency to obtain the intimacy weight.

[0110] It is understandable that different communication frequencies may correspond to different intimacy weights, and the intimacy weight is calculated based on the communication frequency characteristics. For example, the more contacts there are and the shorter the average contact interval is, the higher the intimacy weight is; conversely, the weight is lower. Exemplarily, the communication frequency can be input into a learning model, and the learning model obtains the corresponding intimacy weight; the communication frequency can also be matched in an anti-fraud database to obtain the corresponding intimacy weight, and so on, but is not limited to this.

[0111] S2232, weighting the emotional tendency information with the intimacy weight to obtain the intimacy information of the key content.

[0112] It can be understood that intimacy information = intimacy weight × sentence polarity value. For example, the total number of contacts is large (20 times) and the average contact interval is short (2 days), so the intimacy weight is high. Assuming the intimacy weight is 0.8, the sentiment polarity value (negative) and the intimacy weight (0.8) are weighted. Assuming the sentiment polarity value is -0.7 (negative), the weighted sentiment tendency value is -0.56 (0.8×-0.7), and the final intimacy information of the key content is -0.56, indicating that although the contacts are more frequent, the intimacy information is still biased towards negative due to the negative sentiment tendency, but affected by the intimacy weight, its intimacy is slightly greater than the sentiment polarity value.

[0113] With this setting, by quantifying the communication frequency characteristics and emotional tendency information and performing weighted processing, the objective quantification of intimacy information can be achieved, thereby improving the scientificity and reliability of the evaluation; the intimacy between the contact and the user is comprehensively evaluated from multiple dimensions, making the evaluation results more comprehensive and accurate.

[0114] S300, when the key content meets the fraud conditions, the scenario reminder is given in the form of call message.

[0115] It can be understood that scenario reminder refers to the use of intelligent anti-fraud rings to send signals to remind users. Whether the key content meets the fraud conditions can be determined by judging whether the vocabulary connection degree and intimacy information of the key content meet the preset conditions; the key content can also be input into the learning model, and the learning model outputs the judgment result, etc., but not limited to this.

[0116] In a possible implementation, in step S300, when the key content meets the fraud condition, the following steps are performed:

[0117] S301, when the degree of vocabulary connection of the key content is greater than or equal to the first preset degree, it meets the fraud condition.

[0118] It can be understood that the first preset degree value is a pre-set value used to reflect the degree value of reaching the fraud condition, which can be set manually or obtained from the anti-fraud database, etc., but is not limited to this. When the vocabulary connection degree is greater than or equal to the first preset degree, it means that the content of the communication between the contact person and the fraud content during the communication process is consistent with the fraud content during the fraud. At this time, there is no need to consider the intimacy information. Even if the intimacy degree reflected by the intimacy information is very large, it may be because the fraudster has stolen the contact information of the user's contact person (for example, the mobile phone number is temporarily lost and stolen by the fraudster, the communication application such as WeChat is stolen by the fraudster, etc.), or the contact person has joined a fraud gang and then communicated with the user.

[0119] S302: When the vocabulary connection degree of the key content is less than the first preset degree and greater than the second preset degree, a value is assigned according to the intimacy information to obtain an additional value.

[0120] It can be understood that the second preset degree value is a pre-set value, which can be set manually or obtained from an anti-fraud database, etc., but is not limited to this. Different intimacy corresponds to different added values. The higher the degree of intimacy reflected by the intimacy information, the smaller the added value. Exemplarily, the intimacy information can be input into a learning model, and the learning model outputs the corresponding added value; the intimacy information can also be matched with the anti-fraud database to obtain the corresponding added value, etc., but is not limited to this.

[0121] S303, summing the added value and the vocabulary connection degree to obtain the total added value.

[0122] It can be understood that total added value = added value + degree of vocabulary connection.

[0123] S304: When the total added value is greater than or equal to the first preset level, the fraud condition is met.

[0124] It can be understood that when the degree of lexical connection of the key content is less than the first preset degree and greater than the second preset degree, it indicates that it may be a potential fraudulent behavior. Combined with the intimacy analysis, it is further confirmed whether it is a fraudulent behavior. When the total added value is greater than or equal to the first preset degree, it is confirmed that it meets the fraudulent conditions and is a fraudulent behavior.

[0125] Such a setting achieves refined recognition and judgment of potential fraudulent behaviors, improves the accuracy and reliability of fraudulent behavior identification by combining multi-level thresholds with intimacy information, and can dynamically adjust the evaluation criteria under different degrees of lexical connection, so as to more effectively identify possible fraud risks and avoid false alarms or omissions caused by a single threshold, ensuring that the smart anti-fraud bracelet can still operate efficiently and provide reliable early warning services in complex environments.

[0126] In a possible implementation, in step S300, performing a scene reminder according to the call message includes:

[0127] When the call message is sent via telephone, vibration reminder and light reminder are used; when the call message is sent via SMS, light reminder and voice reminder are used; when the call message is sent via face-to-face conversation, vibration reminder and sound reminder are used.

[0128] It can be understood that voice reminder refers to the broadcast through preset voice content, and sound effect reminder refers to playing preset sound effects to attract the user's attention.

[0129] This setting ensures that users can be effectively reminded of potential fraud risks in various scenarios by adopting different reminder methods according to different communication methods. The combination of multiple reminder methods such as vibration, light, voice and sound effects not only ensures the reminder effect, but also takes into account the user experience and privacy protection in different scenarios, so that the smart anti-fraud bracelet can provide timely and effective warnings in various situations, thereby improving the safety of users.

[0130] In a possible implementation, in step S300, after the scene reminder is performed according to the call message, the anti-fraud bracelet control method further includes:

[0131] S400: The control device receives feedback information.

[0132] It can be understood that the feedback information is used to indicate the user's response to the reminder issued by the smart anti-fraud bracelet.

[0133] In a possible implementation, in step S400, the control device receives feedback information, including:

[0134] S410a, receiving a triggering electrical signal from the smart anti-fraud bracelet.

[0135] It is understood that the trigger signal is triggered after the user receives the reminder, indicating that the user has noticed the potential fraud and wants to take further measures through the smart anti-fraud bracelet. This trigger signal can be manually triggered by the user, such as pressing a button on the smart anti-fraud bracelet or confirming through a touch screen.

[0136] Optionally, in step S400, the control device receives feedback information, further comprising:

[0137] S410b, after the scene reminder exceeds the preset time, obtain the re-communication information; wherein the re-communication information is used to reflect the conversation information between the user and the contact after the scene reminder is issued.

[0138] It is understood that the preset time is a preset value, which can be set manually or obtained from an anti-fraud database, etc., but is not limited thereto. The communication information can be obtained in a similar manner to the acquisition of the call information in step 100.

[0139] S420b, calculating the correlation between the second communication information and the communication information.

[0140] It can be understood that the relevance is used to reflect the reproducibility of the content of the re-communication information and the communication information, that is, if the content of the re-communication information is the same or similar to the content of the communication information, the higher the relevance. The re-communication information and the communication information can be input into the learning model, and the learning model outputs the corresponding relevance; the re-communication information and the communication information can also be compared by a semantic similarity algorithm, and the relevance can be obtained by comparing the overlap of the words appearing in the communication content.

[0141] S430b: When the correlation is greater than a preset threshold, feedback information is generated.

[0142] It can be understood that when the relevance is greater than the preset threshold, it means that the user did not receive the scene reminder or ignored the scene reminder, or was unable to stop communicating with the contact about the fraud topic, and so on.

[0143] With such a setting, by calculating the correlation between the re-communication information and the original communication information, it is possible to accurately identify whether the user continues to face potential risks. When the correlation is greater than the preset threshold, feedback information can be generated in a timely manner to prompt the user to take further measures; the relevance of the re-communication information is comprehensively evaluated to improve the accuracy and reliability of the evaluation.

[0144] S500: Sending a help message to another mobile terminal based on the feedback information.

[0145] It is understandable that the user of the other mobile terminal can be the user's emergency contact, or the police, etc., but not limited thereto. By generating feedback information and sending a help message to the other mobile terminal, it is ensured that the user can get help in time when facing potential risks, thereby improving the responsiveness and security of the system.

[0146] With such a setting, by receiving call messages from mobile terminals in real time and issuing scene reminders according to the methods of call messages (telephone communication, SMS communication and face-to-face conversation), an instant early warning of potential fraudulent behavior is achieved. Specifically, the communication frequency and specific words are obtained by analyzing the call messages, and then the key content is identified. The degree of word connection is obtained by combining and analyzing the specific words, and the emotional tendency information is obtained by analyzing the sentence structure. The intimacy information reflecting the degree of intimacy between the contact person and the user is obtained by combining the communication frequency and emotional tendency information. When the key content meets the preset fraud conditions, corresponding scene reminder measures are taken according to different communication methods, such as vibration reminders and light reminders for telephone communication, light reminders and voice reminders for SMS communication, and vibration reminders and sound reminders for face-to-face conversations. It can also wake up users by receiving feedback information and sending a help message to another mobile terminal when necessary, ensuring that users can get help in time when facing potential risks. At the same time, it can generate feedback information by calculating the correlation between the second communication information and the original communication information when the correlation exceeds the preset threshold, so that it can more accurately evaluate whether the content of the second communication still has potential fraud risks, thereby improving the response speed and recognition accuracy of the smart anti-fraud bracelet in different communication scenarios, and effectively preventing users from suffering from fraudulent behaviors due to ignoring reminders or being unable to stop communicating. Ultimately, it realizes all-round protection of user communication security, improves the responsiveness and security of the system, ensures that timely and effective early warning services can be provided in a variety of communication methods, and significantly improves user experience and sense of security.

[0147] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0148] Corresponding to the anti-fraud wristband control method described in the above embodiment, the embodiment of the present application also provides an anti-fraud wristband control device, and each module of the device can implement each step of the anti-fraud wristband control method. Figure 4 A structural block diagram of an anti-fraud bracelet control device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0149] Reference Figure 4 , the anti-fraud bracelet control device comprises:

[0150] The acquisition module is used to receive the call information of the mobile terminal in real time; wherein the call information includes telephone communication, SMS communication and face-to-face conversation;

[0151] An analysis module is used to analyze call messages and identify key content;

[0152] The reminder module is used to provide scenario reminders based on call messages when the key content meets the fraud conditions.

[0153] It should be noted that the information interaction, execution process and other contents between the above-mentioned modules are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0154] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above modules is used as an example for illustration. In actual applications, the above functions can be assigned to different modules as needed, that is, the internal structure of the device can be divided into different modules to complete all or part of the functions described above. The modules in the embodiment can be integrated into a processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the modules in the above device can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0155] The present application also provides a smart anti-fraud bracelet. Figure 3 As shown, it includes an endless belt 10, a scene reminder device 20 and a control device 6, wherein the scene reminder device 20 includes an adjustment device 201, a light emitting device 202, a voice device 203 and a vibration device 204. The scene reminder device and the control device are arranged on the endless belt, and the control device is electrically connected to the scene reminder device. Figure 5 This is a schematic diagram of the structure of a control device 6 provided in an embodiment of the present application. Figure 5 As shown, the control device 6 of this embodiment includes: at least one processor 60 ( Figure 5 Only one is shown), at least one memory 61 ( Figure 5 Only one is shown in the figure) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, the control device 6 implements the steps in any of the above-mentioned anti-fraud bracelet control method embodiments, or implements the functions of the modules in the above-mentioned device embodiments.

[0156] Exemplarily, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 62 in the control device 6.

[0157] The control device 6 may be a microcontroller (MCU), a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a low-power Bluetooth (BLE) chip, etc. The control device 6 may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that Figure 5 It is only an example of the control device 6 and does not constitute a limitation on the control device 6. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, buses, etc.

[0158] The processor 60 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0159] In some embodiments, the memory 61 may be an internal storage unit of the control device 6, such as a hard disk or memory of the control device 6. In other embodiments, the memory 61 may also be an external storage device of the control device 6, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the control device 6. Further, the memory 61 may also include both an internal storage unit and an external storage device of the control device 6. The memory 61 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 61 may also be used to temporarily store data that has been output or is to be output.

[0160] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0161] An embodiment of the present application provides a computer program product. When the computer program product is run on a smart anti-fraud bracelet, the smart anti-fraud bracelet implements the steps in any of the above method embodiments.

[0162] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the smart anti-fraud bracelet, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk.

[0163] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0164] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0165] In the embodiments provided in the present application, it should be understood that the disclosed smart anti-fraud bracelet and anti-fraud bracelet control device can be implemented in other ways. For example, the anti-fraud bracelet control device embodiment described above is only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0166] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0167] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for controlling an anti-fraud bracelet, characterized in that: The anti-fraud bracelet control method is applied to a smart anti-fraud bracelet, and the smart anti-fraud bracelet is communicatively connected with a mobile terminal. The anti-fraud bracelet control method includes: Receiving the call message of the mobile terminal in real time; wherein the call message includes telephone communication, SMS communication and face-to-face conversation; Analyze the call messages to identify key content; When the key content meets the fraud conditions, a scene reminder is provided according to the method of the call message; The step of analyzing the call message and identifying key content includes: Analyze the call message to obtain the communication frequency and specific words; wherein the communication frequency is used to reflect the number of times and intervals of contact between the contact and the user, and the specific words are used to reflect phrases or short sentences related to fraud; Analyze the communication frequency and the specific words to obtain key content; The analysis is performed based on the communication frequency and the specific words to obtain key contents, including: Performing combination analysis on the specific words to obtain the degree of word connection; Analyze the sentence structures corresponding to the specific words to obtain sentiment tendency information; Analyze the communication frequency and the emotional tendency information to obtain intimacy information; wherein the intimacy information is used to reflect the intimacy between the contact person and the user; When the key content meets the fraud conditions, it includes: When the degree of vocabulary connection is greater than or equal to a first preset degree, the fraud condition is met; When the vocabulary connection degree is less than the first preset degree and greater than the second preset degree, assigning a value according to the intimacy information to obtain an additional value; The added value and the degree of vocabulary connection are summed to obtain a total added value; When the total additional value is greater than or equal to the first preset level, the fraud condition is met.

2. The anti-fraud bracelet control method according to claim 1, characterized in that: The combining and analyzing the specific words to obtain the degree of word connection includes: Screening the multiple specific words to determine sensitive words; Calculating the correlation values ​​of the sensitive words and other specific words respectively; The average of the plurality of association values ​​is calculated to obtain the degree of vocabulary connection.

3. The anti-fraud bracelet control method according to claim 2, characterized in that: The analyzing the sentence structures corresponding to the plurality of specific words to obtain the sentiment tendency information includes: Analyze the sentence structure where the specific vocabulary is located to obtain emotional vocabulary; wherein the emotional vocabulary includes vocabulary that contacts emotional intentions and attitudes; Analyzing the sentiment words and the specific words to obtain a sentence polarity value; wherein the sentence polarity value is used to reflect the sentiment tendency of the sentence; Filter out the maximum value among multiple sentence polarity values ​​to obtain sentiment tendency information.

4. The anti-fraud bracelet control method according to claim 3, characterized in that: The analyzing according to the communication frequency and the emotional tendency information to obtain the intimacy information includes: Analyze according to the communication frequency to obtain the intimacy weight; The intimacy weight is weighted on the emotional tendency information to obtain intimacy information.

5. The anti-fraud bracelet control method according to claim 1, characterized in that: The scene reminder according to the call message includes: When the call message is in the form of telephone communication, a vibration reminder and a light reminder are performed; when the call message is in the form of text message communication, a light reminder and a voice reminder are performed; when the call message is in the form of face-to-face conversation, a vibration reminder and a sound reminder are performed.

6. The anti-fraud bracelet control method according to claim 1, characterized in that: After the scene reminder is performed according to the call message, the method further includes: The control device receives feedback information; Sending a help message to another mobile terminal based on the feedback information; The receiving feedback information comprises: Receiving a triggering electrical signal from the smart anti-fraud bracelet; And / or, after the scene reminder exceeds the preset time, obtaining the re-communication information; wherein the re-communication information is used to reflect the conversation information between the user and the contact after the scene reminder is issued; Calculating the relevance between the second communication information and the communication information; When the correlation is greater than a preset threshold, feedback information is generated.

7. A smart anti-fraud bracelet, characterized in that: It includes an annular belt, a scene reminder device and a control device, wherein the scene reminder device and the control device are arranged on the annular belt, the control device is electrically connected to the scene reminder device, the control device includes a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the method according to any one of claims 1 to 6 when executing the computer program.

Images