An anti-fraud method, device, electronic device and storage medium

Abstract

The present application provides an anti-fraud method, device, electronic device and storage medium, which relates to the technical field of anti-fraud and is applied to smart glasses including a positioning device, a camera device and a recording device. It determines whether a user enters a specific place based on the position information obtained in real time by the positioning device and whether the captured content of the camera device contains specific words. After determining that the user enters the specific place, it recognizes the voice information obtained in real time by the recording device and matches the recognized voice information with multiple trained fraud models; determines a fraud scenario according to the matched fraud model, and gives a fraud risk reminder to the user based on the determined fraud scenario, and records the entire process through the images and sounds collected in real time by the camera device and the recording device to retain evidence, so as to achieve the effect of real-time protecting the property safety of the user and avoid on-site fraud other than telecommunications fraud.

Description

Technical Field

[0001] This application relates to the field of anti-fraud technology, and more specifically, to an anti-fraud method, device, electronic device, and storage medium. Background Art

[0002] The anti-fraud APP is an anti-telecom fraud application that helps users to warn of fraud information, quickly report fraud content, and enhance their awareness of prevention. The anti-fraud APP aims to publicize knowledge about preventing telecom network fraud crimes, improve the awareness and ability of the public to prevent telecom network fraud crimes, facilitate users to report telecom network fraud crimes, provide clues to telecom network fraud cases, reduce telecom network fraud cases, and reduce property losses.

[0003] However, the anti-fraud APP installed on mobile phones currently cannot provide real-time monitoring and cannot solve problems in non-telecom fraud scenarios. For example, when an elderly person goes to a bank to handle a deposit but is deceived into buying a wealth management product or insurance; when going to participate in an event and being sold high-priced health care products, and so on. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide an anti-fraud method, device, electronic device, and storage medium that can provide anti-fraud reminders in real time for on-site fraud scenarios of non-telecom fraud and retain evidence.

[0005] An anti-fraud method provided by an embodiment of this application is applied to smart glasses. The smart glasses include a positioning device and a recording device. The method includes:

[0006] Determine whether the user enters a specific place based on the location information obtained in real time by the positioning device;

[0007] After determining that the user enters a specific place, identify the voice information obtained in real time by the recording device, and match the identified voice information with multiple trained fraud models;

[0008] Determine the fraud scenario according to the matched fraud model, and give a fraud risk reminder to the user based on the determined fraud scenario.

[0009] In some embodiments, the smart glasses further include a camera device. The determining whether the user enters a specific place based on the location information obtained in real time by the positioning device includes:

[0010] If it is determined that the user does not enter a specific place, identify the captured content obtained in real time by the camera device, and determine whether the captured content contains specific words;

[0011] If the captured content contains specific words, determine that the user enters a specific place.

[0012] In some embodiments, the identifying the voice information acquired in real time based on the recording device and matching the identified voice information with a plurality of trained fraud models includes:

[0013] Uploading the voice information acquired by the recording device in real time to a server, and identifying the voice information through the server to determine whether the voice information contains sensitive words;

[0014] If it is determined that the voice information contains sensitive words, the sensitive words are matched with a plurality of trained fraud models.

[0015] In some embodiments, the fraud risk reminder is provided to the user in the following ways, including:

[0016] Providing text reminders through the screen of the smart glasses;

[0017] Or a voice reminder is given through a speaker of the smart glasses.

[0018] In some embodiments, after reminding the user of the fraud risk based on the determined fraud scenario, the method further includes:

[0019] The user's behavior process is recorded based on the recording device and the camera device.

[0020] In some embodiments, the fraud model is trained in the following manner, including:

[0021] Collect conversation information from various fraud scenarios and use it as samples;

[0022] The fraud model is trained through machine learning based on the samples.

[0023] In some embodiments, the specific place includes one or more of a financial management company and a healthcare merchant.

[0024] In some embodiments, an anti-fraud device is also provided, which is applied to smart glasses. The smart glasses include a positioning device and a recording device. The device includes:

[0025] A determination module, used to determine whether the user enters a specific place based on the location information obtained in real time by the positioning device;

[0026] A recognition module, which is used to recognize the voice information obtained in real time based on the recording device after determining that the user has entered a specific place, and match the recognized voice information with multiple trained fraud models;

[0027] A determination module is configured to determine a fraud scenario based on a matched fraud model, and give a fraud risk reminder to a user based on the determined fraud scenario.

[0028] In some embodiments, an electronic device is further provided, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device runs, the processor communicates with the memory through the bus. When the machine-readable instructions are executed by the processor, the steps of the anti-fraud method described in any one of the above are performed.

[0029] In some embodiments, a computer-readable storage medium is further provided. A computer program is stored on the computer-readable storage medium. When the computer program is run by a processor, the steps of the anti-fraud method described in any one of the above are performed.

[0030] An anti-fraud method, apparatus, electronic device, and storage medium according to the present application are applied to smart glasses. The smart glasses include a positioning device, a camera device, and a recording device. It is determined whether a user enters a specific place based on the position information obtained in real time by the positioning device; after determining that the user enters the specific place, the voice information obtained in real time by the recording device is recognized, and the recognized voice information is matched with a plurality of trained fraud models; a fraud scenario is determined according to the matched fraud model, and a fraud risk reminder is given to the user based on the determined fraud scenario, and images visible to the human eye are collected in real time through the camera device to retain evidence, thereby protecting the property safety of the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] To more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0032] Figure 1 Shows a flowchart of the anti-fraud method described in the embodiments of the present application;

[0033] Figure 2 Shows a schematic flowchart of determining whether a user enters a specific place described in the embodiments of the present application;

[0034] Figure 3 Shows a schematic flowchart of matching the recognized voice information with a plurality of trained fraud models described in the embodiments of the present application;

[0035] Figure 4 Shows a schematic flowchart of training the fraud model described in the embodiments of the present application;

[0036] Figure 5 shows a schematic structural diagram of the anti-fraud device described in the embodiments of the present application;

[0037] Figure 6 shows a schematic structural diagram of the electronic device described in the embodiments of the present application. Detailed implementation manners

[0038] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It should be understood that the accompanying drawings in the present application are only for the purposes of illustration and description, and are not used to limit the protection scope of the present application. In addition, it should be understood that the schematic drawings are not drawn in actual scale. The flowcharts used in the present application show operations implemented according to some embodiments of the present application. It should be understood that the operations in the flowchart may not be implemented in sequence, and steps without logical context relationships may be reversed or implemented simultaneously. In addition, those skilled in the art may add one or more other operations to the flowchart or remove one or more operations from the flowchart under the guidance of the content of the present application.

[0039] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application claimed, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present application.

[0040] It should be noted that the term "including" will be used in the embodiments of the present application to indicate the existence of the features stated thereafter, but does not exclude the addition of other features.

[0041] In the prior art, although anti-fraud APPs can prevent telecom fraud to a certain extent. For example, suspects pretend to be telecom, public security, and bank personnel through phone calls or text messages, claiming that the victim's home phone owes a huge amount of phone bills, the ID card has been stolen by others, the bank account has loopholes, and the package containing "drug-related" items cannot be delivered, etc., to intimidate the victim, and require the victim to transfer the funds in the bank card to a designated account for the so-called "fund protection" or "bank card upgrade" according to the instructions, thereby defrauding money; for example, the suspect steals the video of QQ friends during video chats, and then steals the QQ password by various methods, plays the friend's video images on QQ, pretends to be a friend to his relatives and friends and claims that he is in an emergency, and defrauds money by borrowing money, helping to pay, recharging, etc.; for example, the suspect posts attractive online part-time job information online, the work is easy and makes a lot of money. When the victim contacts him, the suspect will ask the victim to buy recharge cards, game point cards, etc. to help him brush his reputation, and promise to return the shopping principal and commission in time, luring the victim into being deceived, etc. These anti-fraud APPs can send messages to remind in time.

[0042] However, it does not work well for on-site fraud scenarios that are not telecommunications fraud. For example, they use various scams to sell so-called "special health products" based on the elderly's desire for good health; or they use insurance and financial management through sales and lobbying. The so-called scams often include "gift temptation", "hiring fraud", and "high-tech misleading". For example, they recognize "godfathers" and "godmothers", show false concern for the elderly, and use sweet words to coax the elderly into buying products. They give away soybean oil, paper towels, and even provide free travel. They take the opportunity to conduct physical examinations on customers, falsely claim that some customers have a great risk of cancer, and promote products that claim to cure cancer. So-called "experts" organize health lectures and physical examinations, and even go door-to-door to sell, conduct one-on-one "diagnosis and treatment", interpret physical examination reports, exaggerate the severity of physical examination results, scare consumers, and then propose solutions, so as to achieve the purpose of selling products at high prices. Or, in the name of holding public welfare activities such as "National Health Thousand Miles Tour", "Old People's Model Team", and "Sunset Red Tourism", they actually organize so-called "experts" to explain "health knowledge" and sell health products at high prices. Some businesses will take advantage of the empathy among patients and organize on-site statements by "patients".

[0043] And when they realize they have been cheated, they fail to trace back due to lack of evidence. Based on this, the present application provides an anti-fraud method, device, electronic device and storage medium, which can provide anti-fraud reminders for on-site fraud scenarios that are not telecommunications fraud in real time and retain evidence.

[0044] See the instruction manual Figure 1 The present application provides an anti-fraud method, which is applied to smart glasses, wherein the smart glasses include a positioning device and a recording device; the method includes the following steps:

[0045] S1. Determine whether the user enters a specific place based on the location information obtained in real time by the positioning device;

[0046] S2. After determining that the user enters a specific place, recognize the voice information obtained in real time by the recording device, and match the recognized voice information with multiple trained fraud models;

[0047] S3. Determine the fraud scenario according to the matched fraud model, and give a fraud risk reminder to the user based on the determined fraud scenario.

[0048] Among them, compared with the ordinary glasses in the prior art, the smart glasses are equipped with a photographing device, a recording device and a positioning device. Through the photographing device and the recording device, the information seen and heard by the wearer can be obtained in real time. Through the positioning device, the location information of the wearer can be obtained in real time. Specifically, in an embodiment, the photographing device may be a camera installed on the side of the lens, the recording device may be a conventional microphone, and the positioning device may be a conventional GPS chip.

[0049] In step S1, based on the location information of the wearer obtained in real time by the positioning device, determine whether the wearer enters a specific place. The specific place is a place that is often defrauded in reality, such as specific places like banks and health care product stores. These place information are determined based on the marked information on the map.

[0050] However, due to the defects of the map marked information, such as some remote places not being marked or the marked information not being updated in time, the location information of the wearer cannot be accurately obtained by the positioning device, and thus it cannot be accurately determined whether the wearer enters a specific place. Based on this, see the attached Figure 2 , determining whether the user enters a specific place based on the location information obtained in real time by the positioning device further includes the following steps:

[0051] S101. After determining that the user does not enter a specific place, recognize the shooting content obtained in real time by the imaging device, and determine whether the shooting content contains specific words;

[0052] S102. If the shooting content contains specific words, determine that the user enters a specific place.

[0053] Obtain the information seen by the shooter in real time through the imaging device, and then recognize the shooting content, such as OCR (Optical Character Recognition) recognition, to recognize the signs of merchants, goods, etc. When it contains specific words such as insurance, wealth management, and health care, it is also determined that the wearer enters a specific place.

[0054] Among them, OCR is optical character recognition, which is a technology for recognizing optical characters through image processing and pattern recognition technology. This should be a well-known technical means in this technical field and will not be elaborated here.

[0055] It should be noted that for smart glasses that support SIM cards, positioning can be completed through GPS. For those that do not support it, they can be connected to a mobile phone via Bluetooth, and the mobile phone provides continuous position updates.

[0056] In step S2, in one embodiment, when it is determined that the wearer enters a specific place, the smart glasses automatically enter the anti-fraud mode. In other embodiments, the smart glasses also support manual operation to turn on the anti-fraud mode. When the anti-fraud mode is turned on, the recording device of the smart glasses continuously records the voice information of the surrounding environment of the wearer, and recognizes the voice information, and then matches the recognized voice information with multiple trained fraud models. Specifically, see the attached Figure 3 The recognition of the voice information obtained in real time based on the recording device and the matching of the recognized voice information with multiple trained fraud models include:

[0057] S201. Upload the voice information obtained in real time by the recording device to the server, and the server recognizes the voice information to determine whether the voice information contains sensitive words;

[0058] S202. If it is determined that the voice information contains sensitive words, match the sensitive words with multiple trained fraud models.

[0059] That is, the smart glasses can communicate with the server through a wireless network or a mobile phone hotspot, upload the voice information obtained in real time by the recording device to the server, and the server converts the voice information obtained in real time by the recording device into text information, and then extracts the sensitive words in the text information. The sensitive words are words such as financial management and transfer, and then analyze these extracted sensitive words, that is, match them with multiple preset fraud models.

[0060] In addition, the server can also convert the voice information obtained in real time by the recording device into text information, and then perform semantic determination on the text information, and match the determined semantics with multiple preset fraud models.

[0061] In step S3, when a matching fraud model is found, the corresponding fraud scenario can be determined, such as health product promotion, financial product purchase and other scenarios, and the wearer is reminded for different scenarios. For example, for smart glasses with a screen or an optical engine, text reminders are given through the screen, "This transaction is recognized by the system as having a risk of being deceived. Please handle it carefully or interrupt the transaction." For smart glasses with a speaker, voice reminders are given.

[0062] Among them, the fraud model is trained in the following manner. Refer to the attached Figure 4 specification, including the following steps:

[0063] S301. Collect the conversation information in various fraud scenarios as samples;

[0064] S302. Train the fraud model based on the samples through machine learning.

[0065] That is, when training the fraud model, actual fraud cases collected are used as samples, and they are classified into different fraud scenario types by extracting features. This should be a well-known technical means to those skilled in the art and will not be elaborated here.

[0066] It should be noted that in other embodiments, for the algorithms of identifying voice information and matching the fraud model, in addition to being processed by the server, they can also be built into the smart glasses and directly determined by the smart glasses; or the voice information can be transmitted to the mobile phone in real time via Bluetooth, and the algorithms configured in the mobile phone or the corresponding APP can be used for determination.

[0067] Furthermore, after giving a fraud risk reminder to the user based on the determined fraud scenario, the following steps are further included:

[0068] Record the behavior process of the user based on the recording device and the imaging device.

[0069] That is, in addition to giving a fraud risk reminder to the wearer, images and sounds will be automatically recorded, and the entire transaction record will be recorded. If fraud is confirmed later, it can be provided to the police as evidence to protect the legitimate rights and interests of oneself.

[0070] Furthermore, the method further includes scanning the bar code of the transaction item based on the imaging device, uploading the collected bar code information to the server for query, and the server returns the actual price of the commodity and the commodity evaluation, and displays them on the screen of the smart glasses or gives a voice reminder, so that the wearer can make a correct judgment on the transaction commodity instead of blindly following the explanations of others.

[0071] Through an anti-fraud method of the present application, which is applied to smart glasses including a positioning device, a camera device, and a recording device, it is determined whether a user enters a specific place based on the position information obtained in real time by the positioning device and whether the captured content of the camera device contains specific words; after determining that the user enters the specific place, the voice information obtained in real time by the recording device is recognized, and the recognized voice information is matched with multiple trained fraud models; a fraud scenario is determined according to the matched fraud model, and a fraud risk reminder is given to the user based on the determined fraud scenario, and the entire process is recorded through the images and sounds collected in real time by the camera device and the recording device to retain evidence, so as to achieve the effect of ensuring the user's property safety in real time.

[0072] Based on the same inventive concept, an anti-fraud device is also provided in an embodiment of the present application. Since the principle of solving problems by the device in the embodiment of the present application is similar to that of the above anti-fraud method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be elaborated.

[0073] As Figure 5 shown, an embodiment of the present application also provides an anti-fraud device, which is applied to smart glasses. The smart glasses include a positioning device and a recording device; the device includes:

[0074] A determination module 501, configured to determine whether a user enters a specific place based on the position information obtained in real time by the positioning device; the specific place includes one or more of a financial management company and a health care merchant;

[0075] An identification module 502, configured to, after determining that the user enters the specific place, recognize the voice information obtained in real time by the recording device, and match the recognized voice information with multiple trained fraud models;

[0076] A determination module 503, configured to determine a fraud scenario according to the matched fraud model, and give a fraud risk reminder to the user based on the determined fraud scenario.

[0077] In some embodiments, the smart glasses further include a camera device. When the determination module 501 determines whether a user enters a specific place based on the position information obtained in real time by the positioning device, it is further configured to:

[0078] If it is determined that the user has not entered the specific place, the captured content obtained in real time by the camera device is recognized, and it is determined whether the captured content contains specific words;

[0079] If the captured content contains specific words, it is determined that the user enters the specific place.

[0080] In some embodiments, the recognition module 502 is configured to recognize the voice information obtained in real time based on the recording device, match the recognized voice information with multiple trained fraud models, and is further configured to:

[0081] Upload the voice information obtained in real time by the recording device to the server, recognize the voice information through the server, and determine whether the voice information contains sensitive words;

[0082] If it is determined that the voice information contains sensitive words, match the sensitive words with multiple trained fraud models.

[0083] In some embodiments, the device reminds the user of fraud risks in the following ways, including:

[0084] Perform text reminders through the screen of the smart glasses;

[0085] Or perform voice reminders through the speaker of the smart glasses.

[0086] In some embodiments, the device further includes a recording module, which is configured to record the user's behavior process based on the recording device and the imaging device after reminding the user of fraud risks based on the determined fraud scenario.

[0087] In some embodiments, the determination module 503 is further configured to train the fraud model in the following ways:

[0088] Collect the conversation information in various fraud scenarios as samples;

[0089] Train the fraud model based on the samples through machine learning.

[0090] A die-cutting and cutting control device described in this application includes a determination module 501, a recognition module 502, and a determination module 503, which is applied to smart glasses. The smart glasses include a positioning device, an imaging device, and a recording device. The determination module 501 determines whether the user enters a specific place based on the position information obtained in real time by the positioning device; after determining that the user enters a specific place, the recognition module 502 recognizes the voice information obtained in real time based on the recording device, and matches the recognized voice information with multiple trained fraud models; determine the fraud scenario according to the matched fraud model, and the determination module 503 reminds the user of fraud risks based on the determined fraud scenario, and records the images visible to the human eye in real time through the imaging device to retain evidence, thereby protecting the user's property safety.

[0091] Based on the same concept of the present invention, the specification appendix Figure 6As shown, the structure of an electronic device 600 provided by an embodiment of the present application. The electronic device 600 includes: at least one processor 601, at least one network interface 604 or other user interfaces 603, a memory 605, and at least one communication bus 602. The communication bus 602 is used to implement connection communication between these components. Optionally, the electronic device 600 includes a user interface 603, including a display (such as a touch screen, LCD, CRT, holographic imaging, or projector, etc.), a keyboard, or a pointing device (such as a mouse, trackball, touchpad, or touch screen, etc.).

[0092] The memory 605 may include a read-only memory and a random access memory, and provide instructions and data to the processor 601. A part of the memory 605 may also include a non-volatile random access memory (NVRAM).

[0093] In some embodiments, the memory 605 stores the following elements, executable modules, or data structures, or subsets thereof, or extended sets thereof:

[0094] An operating system 6051, containing various system programs for implementing various basic services and processing hardware-based tasks;

[0095] An application module 6052, containing various applications, such as a launcher, a media player, a browser, etc., for implementing various application services.

[0096] In the embodiment of the present application, by invoking the programs or instructions stored in the memory 605, the processor 601 is used to execute the steps of an anti-fraud method.

[0097] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it executes the steps in the anti-fraud method.

[0098] Specifically, the storage medium can be a general storage medium, such as a removable disk, a hard disk, etc. When the computer program on the storage medium runs, it can execute the above anti-fraud method, determine whether the user enters a specific place based on the location information obtained in real time by the positioning device and whether the captured content of the imaging device contains specific words; after determining that the user enters the specific place, identify the voice information obtained in real time based on the recording device, and match the identified voice information with multiple trained fraud models; determine the fraud scenario according to the matched fraud model, and give a fraud risk reminder to the user based on the determined fraud scenario, and record the entire process through the images and sounds collected in real time by the imaging and recording devices to retain evidence, so as to achieve the effect of real-time protecting the user's property safety and avoiding on-site fraud other than telecommunications fraud.

[0099] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the displayed or discussed coupling or direct coupling or communication connection between each other can be through some communication interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical or other form.

[0100] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be 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.

[0101] In addition, each functional unit in the embodiments provided in 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.

[0102] If a function 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 technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of this application. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0103] Finally, it should be noted that: The above embodiments are only specific implementation manners of this application, used to illustrate the technical solutions of this application, rather than limiting it. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: Any person skilled in the art within the technical scope disclosed in this application can still modify the technical solutions recorded in the foregoing embodiments, or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes, or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of this application. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. An anti-fraud method, characterized in that, Applied to smart glasses, the smart glasses include a positioning device and a recording device, and the method includes: Determining whether the user enters a specific place based on the location information obtained in real time by the positioning device; After determining that the user enters a specific place, recognizing the voice information obtained in real time by the recording device, and matching the recognized voice information with multiple trained fraud models; Determining a fraud scenario according to the matched fraud model, and giving a fraud risk reminder to the user based on the determined fraud scenario.

2. The anti-fraud method according to claim 1, characterized in that, The smart glasses further include a camera device. The determining whether the user enters a specific place based on the location information obtained in real time by the positioning device includes: After determining that the user does not enter a specific place, recognizing the captured content obtained in real time by the camera device, and determining whether the captured content contains specific words; If the captured content contains specific words, determining that the user enters a specific place.

3. The anti-fraud method according to claim 2, characterized in that, The recognizing the voice information obtained in real time by the recording device, and matching the recognized voice information with multiple trained fraud models includes: Uploading the voice information obtained in real time by the recording device to a server, and recognizing the voice information by the server to determine whether the voice information contains sensitive words; If it is determined that the voice information contains sensitive words, matching the sensitive words with multiple trained fraud models.

4. The anti-fraud method according to claim 3, wherein Giving a fraud risk reminder to the user in the following ways, including: Giving a text reminder through the screen of the smart glasses; Or giving a voice reminder through the speaker of the smart glasses.

5. The anti-fraud method according to claim 4, characterized in that, After giving a fraud risk reminder to the user based on the determined fraud scenario, it further includes: Recording the behavior process of the user based on the recording device and the camera device.

6. The anti-fraud method according to claim 5, characterized in that Training the fraud model in the following ways, including: Collecting conversation information in various fraud scenarios as samples; Training the fraud model through machine learning based on the samples.

7. The anti-fraud method according to claim 5, wherein The specific place includes one or more of a financial management company and a health care merchant.

8. An anti-fraud device, characterized in that, Applied to smart glasses, the smart glasses include a positioning device and a recording device, and the device includes: A determination module for determining whether the user enters a specific place based on the location information obtained in real time by the positioning device; An identification module for, after determining that the user enters a specific place, recognizing the voice information obtained in real time by the recording device, and matching the recognized voice information with multiple trained fraud models; A determination module for determining a fraud scenario according to the matched fraud model, and giving a fraud risk reminder to the user based on the determined fraud scenario.

9. An electronic device, characterized in that, Including: A processor, a memory and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device runs, the processor communicates with the memory through the bus. When the machine-readable instructions are executed by the processor, the steps of the anti-fraud method according to any one of claims 1 to 7 are executed.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, it executes the steps of the anti-fraud method according to any one of claims 1 to 7.

Images