Fraud prediction method, prediction device, mobile device and storage medium

Abstract

The embodiment of the present application provides a fraud prediction method, a prediction device, a mobile device, and a storage medium. The fraud prediction method is applied to a mobile device and is characterized by comprising: obtaining content to be detected in the mobile device; and determining the fraud probability of the content to be detected based on a fraud prediction model. The fraud prediction method provided in the embodiment of the present application can predict the fraud probability through a fraud prediction model, thereby improving the intelligence level of fraud prediction.

Description

Technical Field

[0001] The present invention relates to the field of computer security technology, and in particular to a fraud prediction method, a prediction device, a mobile device, and a storage medium. Background Art

[0002] With the rapid development of information technology, telecommunications fraud is also constantly evolving and escalating. Telecommunications fraud not only causes economic losses to victims, but also affects social harmony and stability. Therefore, anti-telecommunications fraud is particularly important.

[0003] In the related art, telecom operators can reduce the spread of fraudulent information by filtering and intercepting suspicious calls and text messages. However, this method relies on the setting of blacklists and whitelists, and blacklists and whitelists are usually lagging behind. In addition, non-phone or non-text fraud, such as fraud in application software or fraud in web pages, is usually difficult to detect. Summary of the invention

[0004] The embodiments of the present application provide a fraud prediction method, a prediction device, a mobile device, and a storage medium, which can predict the probability of fraud through a fraud prediction model, thereby improving the intelligence level of fraud prediction.

[0005] In a first aspect, an embodiment of the present application provides a fraud prediction method, which is applied to a mobile device, comprising: obtaining content to be detected in the mobile device; and determining the fraud probability of the content to be detected based on a fraud prediction model.

[0006] In some implementations, the acquiring the content to be detected in the mobile device includes: acquiring a display interface of the mobile device at a preset frequency, and acquiring the content to be detected in the display interface.

[0007] In some implementations, the fraud prediction model includes a text recognition model and a content recognition model; determining the fraud probability of the content to be detected based on the fraud prediction model includes: performing text recognition on the content to be detected based on the text recognition model to obtain the text to be detected, and performing content recognition on the text to be detected based on the content recognition model to obtain the fraud probability.

[0008] In some implementations, the content recognition model includes a first recognition model and a second recognition model, and the computational complexity of the first recognition model is smaller than that of the second recognition model.

[0009] In some implementations, performing content recognition on the text to be detected based on the content recognition model to obtain the fraud probability includes: obtaining a first fraud probability of the text to be detected based on the first recognition model; and when the first fraud probability is less than a first threshold or greater than a second threshold, using the first fraud probability as the fraud probability, or when the first fraud probability is greater than or equal to the first threshold and less than or equal to the second threshold, obtaining the fraud probability of the text to be detected based on the second recognition model.

[0010] In some implementations, the fraud prediction model includes a first prediction model and a second prediction model, and the computational complexity of the first prediction model is less than that of the second prediction model.

[0011] In some implementations, determining the fraud probability of the content to be detected based on the fraud prediction model includes: obtaining a second fraud probability of the content to be detected based on the first prediction model; and when the second fraud probability is less than a first threshold or greater than a second threshold, using the second fraud probability as the fraud probability, or when the second fraud probability is greater than or equal to the first threshold and less than or equal to the second threshold, obtaining the fraud probability of the content to be detected based on the second prediction model.

[0012] In a second aspect, an embodiment of the present application provides a prediction device, the device comprising:

[0013] An acquisition module, used to acquire the content to be detected in the mobile device; and

[0014] A determination module is used to determine the fraud probability of the content to be detected based on a fraud prediction model.

[0015] In a third aspect, an embodiment of the present application provides a mobile device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the operations in the method described in the first aspect when executing the computer program.

[0016] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the operations in the method described in the first aspect are implemented.

[0017] In summary, the embodiments of the present application provide a fraud prediction method, a prediction device, a mobile device, and a storage medium. The fraud prediction method, applied to a mobile device, comprises: obtaining content to be detected in the mobile device; and determining the fraud probability of the content to be detected based on a fraud prediction model. The beneficial effect of the present application is that the fraud probability is predicted by the fraud prediction model, thereby improving the intelligence level of fraud prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of this specification, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 A schematic diagram showing a flow chart of a fraud prediction method provided by some embodiments of the present application;

[0020] Figure 2 A schematic diagram of a process for determining a fraud probability provided by some embodiments of the present application is shown;

[0021] Figure 3 A schematic diagram of a process of multi-level content identification provided by some embodiments of the present application is shown;

[0022] Figure 4 A schematic diagram of a process of multi-level fraud prediction provided by some embodiments of the present application is shown;

[0023] Figure 5 A schematic diagram showing the structure of a prediction device provided in some embodiments of the present application is shown;

[0024] Figure 6 A schematic diagram of the structure of a mobile device provided in some embodiments of the present application is shown. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in this application to clearly and completely describe the technical solutions in this application. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments in the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0026] Although the present application shows a logical sequence in the flow charts, in some cases, the operations shown or described may be performed in a different order than that shown in the drawings.

[0027] Figure 1A schematic flow chart of a fraud prediction method provided by some embodiments of the present application is shown. The fraud prediction method can be applied to mobile devices, including, but not limited to, smart phones, tablet computers, smart watches, game consoles or similar devices. The specific process of the fraud prediction method can be as follows:

[0028] S101: Acquire content to be detected in a mobile device.

[0029] The content to be detected may be an object used to determine the probability of fraud. The content to be detected may be in various forms, such as images, texts, or voices.

[0030] In some embodiments, the content to be detected may be an image. For example, the fraud prediction method may obtain an image displayed on a display interface of a mobile device. For example, the fraud method may obtain an image in a multimedia message or rich media communication received by a mobile device.

[0031] In some embodiments, the content to be detected may be text. For example, the fraud prediction method may obtain text messages received by a mobile device. For example, the fraud prediction method may obtain chat texts in an instant messaging software or social media software in a mobile device.

[0032] In some embodiments, the content to be detected may be voice. For example, the fraud prediction method may obtain voice of a mobile device during a telephone communication. For example, the fraud prediction method may obtain voice of an instant messaging software or social media software of a mobile device in real-time voice communication or voice messages.

[0033] S102: Determine the fraud probability of the content to be detected based on the fraud prediction model.

[0034] Among them, the fraud prediction model can be a trained machine learning model or a deep learning model. Before operation S102, the fraud prediction method can also include fine-tuning the pre-trained model to obtain a trained fraud prediction model. The fraud prediction model can include one or more models. For example, different models or the same model can be used to obtain the fraud probability for different types of content to be detected. For example, one model or multiple models can be used to obtain the fraud probability for the same type of content to be detected. The training method of the fraud prediction model will be introduced in conjunction with specific embodiments later.

[0035] Among them, the fraud probability can be used to evaluate the possibility that the content to be detected contains fraudulent information. The greater the fraud probability, the higher the possibility of containing fraudulent information, and the smaller the fraud probability, the lower the possibility of containing fraudulent information. The fraud probability can be a probability value of continuous distribution. For example, the fraud probability can be any probability value in the range of 0% to 100%. The fraud probability can also be a probability rating of discrete distribution. For example, the fraud probability can be divided into three ratings of high, medium and low. The fraud probability can also be a judgment of whether it is a fraud. For example, the fraud probability can be divided into a high fraud probability, which is considered to be a fraud, and a low fraud probability, which is considered not to be a fraud.

[0036] In some embodiments, after obtaining the probability of fraud, corresponding operations can be performed according to the probability of fraud. For example, the corresponding operation can be to generate reminders of different risk levels according to the probability of fraud. When the probability of fraud is in the first probability interval, the risk level is low, and only a pop-up reminder is performed. When the probability of fraud is in the second probability interval, a confirmation dialog box pops up, and the user needs to confirm before the dialog box can be closed. When the probability of fraud is in the third probability interval, the risk level is high, and the user needs to pass the security question and answer to remove the usage restrictions. Of course, the probability interval or reminder method can be preset by the fraud prediction method, or set by the user. For example, the corresponding operation can be to block the message according to the probability of fraud. For another example, the corresponding operation can be to restrict the user's behavior according to the probability of fraud, such as transfer transactions.

[0037] The fraud prediction method provided in some embodiments of the present application can be applied to a mobile device to obtain the content to be detected in the mobile device, and determine the fraud probability of the content to be detected based on a fraud prediction model. The fraud prediction method provided in some embodiments of the present application predicts the fraud probability through a fraud prediction model, thereby improving the intelligence level of fraud prediction.

[0038] As mentioned above, the content to be detected may be in the form of an image. In some embodiments, obtaining the content to be detected in the mobile device in operation S101 may include:

[0039] The display interface of the mobile device is obtained at a preset frequency, and the content to be detected in the display interface is obtained.

[0040] Wherein, obtaining the display interface of the mobile device may be when the mobile device is in a screen-on state, obtaining the display interface at a preset frequency. Obtaining the content to be detected in the display interface may be obtaining an image of the entire display interface, or obtaining an image of a partial area in the display interface. For example, the fraud prediction method in some embodiments may determine the position of the message pop-up window according to the user setting or the model of the mobile device, and obtain an image of the message pop-up window area.

[0041] The preset frequency may be set in the fraud prediction method or set by the user. The preset frequency may be a fixed frequency or an adjustable frequency. For example, the fraud prediction method in some embodiments may adjust the preset frequency according to the battery level or power consumption of the mobile phone.

[0042] In some embodiments, a fraud prediction model for performing fraud prediction on the to-be-detected content in the form of an image may include a text recognition model and a content recognition model. Figure 2 A schematic diagram of a process for determining a fraud probability provided by some embodiments of the present application is shown. Determining the fraud probability of the content to be detected based on the fraud prediction model may include:

[0043] S201 , performing text recognition on the content to be detected based on a text recognition model to obtain the text to be detected.

[0044] The content to be detected may be an image to be detected, and the text recognition model may be used to recognize text in the image to be detected. The text recognition model may be one or more models.

[0045] In some embodiments, the text recognition model can be a model in which a text detection model and a character recognition model are cascaded. Among them, the text detection model can be used to detect the text area in the image to be detected, and then the text area image is input into the character recognition model, and the characters in the text area image, that is, the text to be detected, are output. The text detection model can use a general target detection model, such as the YOLO series model, the SSD model, the Faster R-CNN model, or an improved model based on these models. The text detection model can also be a special detection model for the text field, such as the EAST detection model (Efficient and Accurate Scene Text Detector) and the CTPN model (Column Proposal Networks).

[0046] In some embodiments, the text recognition model may be an end-to-end text recognition model, which may directly output the text to be detected based on the input image to be detected.

[0047] S202: Perform content recognition on the text to be detected based on the content recognition model to obtain a fraud probability.

[0048] Among them, the content recognition model can be used to analyze and understand the text to be detected to obtain the probability of fraud.

[0049] In some embodiments, the content identification model may be a natural language processing model, which may be a bag of words model (BoW), an N-gram model, a hidden Markov model (HMM), a recurrent neural network (RNN), or a Transformer model.

[0050] In order to obtain better prediction results in the task of fraud prediction, the content recognition pre-training model can be fine-tuned using data from the fraud prediction field. To this end, a training sample set and a test sample set can be constructed. Each sample is a piece of text content. A sample can correspond to a label, which is used to indicate whether there is fraud information in the sample. For example, when there is fraud information in the sample, the corresponding label is 1, and when there is no fraud content in the sample, the corresponding label is 0.

[0051] In some embodiments, the text in character form needs to be converted into a feature vector first and then input into the content recognition pre-training model. The model parameters are continuously adjusted according to the difference between the output result of the training sample after passing through the content recognition pre-training model and the label to obtain a trained content recognition model.

[0052] The training process of the content recognition model can be performed on the server. The trained content recognition model can be stored in a mobile device or a cloud device. Based on the trained content recognition model, the text to be detected or the feature vector of the text to be detected can be input into the content recognition model to output the fraud probability.

[0053] Some embodiments of the present application provide a fraud prediction method that, when predicting the fraud probability of content to be detected in image form, first extracts text from the image to be detected, and then performs content recognition on the extracted text to determine the fraud probability.

[0054] In order to increase the speed of fraud prediction, in some embodiments, a multi-level recognition model can be used to predict the probability of fraud. For example, the content recognition model may include a first recognition model and a second recognition model, wherein the computational complexity of the first recognition model is less than that of the second recognition model. For the same input data and the same computing device, the time spent on reasoning using the first recognition model is less than the time spent on reasoning using the second recognition model. Moreover, at least on the test sample set, the accuracy or recall rate of the first recognition model is lower than that of the second recognition model.

[0055] Figure 3The flowchart of multi-level content recognition provided by some embodiments of the present application is shown. In which, based on the content recognition model, content recognition is performed on the text to be detected to obtain the fraud probability, which may specifically include:

[0056] S301. Obtain a first fraud probability of a text to be detected based on a first recognition model.

[0057] The first fraud probability can be used to make a preliminary judgment on whether the text to be detected contains fraud information, and determine whether it is necessary to use the second recognition model for further prediction based on the preliminary judgment result.

[0058] S302: When the first fraud probability is less than the first threshold or greater than the second threshold, the first fraud probability is used as the fraud probability.

[0059] When the first fraud probability is relatively small or relatively large, it can be considered that the result obtained by the first recognition model is relatively credible, that is, the first fraud probability can be used as the fraud probability.

[0060] S303: When the first fraud probability is greater than or equal to the first threshold and less than or equal to the second threshold, obtain the fraud probability of the text to be detected based on the second recognition model.

[0061] When the first fraud probability is in the middle zone, it can be considered that the first recognition model is difficult to judge whether the text to be detected contains fraud information. At this time, the second recognition model can be used for further prediction to obtain the fraud probability.

[0062] It should be noted that the first recognition model and the second recognition model can be stored together in a mobile device; or the first recognition model and the second recognition model can be stored together in a cloud device; or the first recognition model can be stored in a mobile device and the second recognition model can be stored in a cloud device.

[0063] The fraud prediction method provided by some embodiments of the present application can improve the prediction speed of fraud probability by using a multi-level content recognition model. In the case where the result obtained by using the lightweight first recognition model is relatively credible, only a few cases require the use of the second recognition model for secondary judgment.

[0064] In other embodiments, the fraud prediction model for predicting fraud on the content to be detected in the form of an image may be an end-to-end image semantic understanding model. The image semantic understanding model may receive input in the form of an image and analyze and understand whether there is fraud information in the input image to be detected.

[0065] Similarly, in order to obtain better prediction results, a training sample set and a test sample set can be constructed. Each sample is an image. A sample can correspond to a label, and the label is used to indicate whether there is fraudulent information in the sample. For example, when there is fraudulent information in the sample, the corresponding label is 1, and when there is no fraudulent content in the sample, the corresponding label is 0. For another example, when there is fraudulent information in the sample, the corresponding label can be what type of fraud is happening in the image, and when there is no fraudulent content in the sample, the corresponding label can be nothing happened. The model parameters are continuously adjusted according to the difference between the output results of the training samples after passing through the image semantic understanding model and the labels to obtain a trained image semantic understanding model.

[0066] Similarly, the training process of the image semantic understanding model can be performed on the server. The trained image semantic understanding model can be stored in a mobile device or a cloud device. Based on the trained image semantic understanding model, the image to be detected can be input into the image semantic understanding model to output the fraud probability.

[0067] It is understandable that for other forms of content to be detected, the fraud prediction model can be other models that match the input form. For example, for content to be detected in text form, the content recognition model described above can be used as a fraud prediction model to predict the probability of fraud. For example, for content to be detected in voice form, a voice recognition model can be used as a fraud prediction model to predict the probability of fraud.

[0068] Similar to the two-stage (text recognition + content recognition) fraud prediction, the single-stage fraud prediction can also use a multi-level fraud prediction model to predict the probability of fraud. In some embodiments, the fraud prediction model may include a first prediction model and a second prediction model, wherein the computational complexity of the first prediction model is less than that of the second prediction model. For the same input data and the same computing device, the time spent on reasoning using the first prediction model is less than the time spent on reasoning using the second prediction model. Moreover, at least on the test sample set, the accuracy or recall rate of the first prediction model is lower than that of the second prediction model.

[0069] Figure 4 A schematic diagram of a multi-level fraud prediction process provided by some embodiments of the present application is shown. Determining the fraud probability of the content to be detected based on the fraud prediction model may specifically include:

[0070] S401. Obtain a second fraud probability of the content to be detected based on the first prediction model.

[0071] The first prediction model may be a model for predicting the fraud probability of the content to be detected in the form of images, texts, or voices, etc. The second fraud probability may be used to make a preliminary judgment on whether the content to be detected contains fraud information, and to determine whether the second prediction model needs to be used for further prediction based on the preliminary judgment result.

[0072] S402: When the second fraud probability is less than the first threshold or greater than the second threshold, the second fraud probability is used as the fraud probability.

[0073] When the second fraud probability is smaller or larger, it can be considered that the result obtained by the first prediction model is more credible, that is, the second fraud probability can be used as the fraud probability.

[0074] S403: When the second fraud probability is greater than or equal to the first threshold and less than or equal to the second threshold, obtain the fraud probability of the content to be detected based on the second prediction model.

[0075] When the second fraud probability is in the middle zone, it can be considered that the first prediction model is difficult to judge whether the content to be detected contains fraud information. At this time, the second prediction model can be used for further prediction to obtain the fraud probability.

[0076] It should be noted that the first prediction model and the second prediction model can be stored together in a mobile device; or the first prediction model and the second prediction model can be stored together in a cloud device; or the first prediction model can be stored in a mobile device and the second prediction model can be stored in a cloud device.

[0077] The fraud prediction method provided by some embodiments of the present application can improve the prediction speed of fraud probability by using a multi-level fraud prediction model. In the case where the result obtained by using the lightweight first prediction model is relatively credible, only a few cases require the use of the second prediction model for secondary judgment.

[0078] Figure 5 The schematic diagram of the structure of the prediction device provided by some embodiments of the present application is shown. The prediction device 500 can be applied to a mobile device, and specifically may include:

[0079] The acquisition module 501 may be used to acquire the content to be detected in the mobile device.

[0080] The determination module 502 may be used to determine the fraud probability of the content to be detected based on the fraud prediction model.

[0081] In some embodiments of the present application, the acquisition module 501 may first acquire the content to be detected in the mobile device. Next, the determination module 502 may determine the fraud probability of the content to be detected based on the fraud prediction model. The prediction device 500 provided in some embodiments of the present application may predict the fraud probability through the fraud prediction model, thereby improving the intelligence level of fraud prediction.

[0082] In some embodiments, the determination acquisition module 501 may include a first acquisition unit and a second acquisition unit. The first acquisition unit may be used to acquire the display interface of the mobile device at a preset frequency. The second acquisition unit may be used to acquire the content to be detected in the display interface.

[0083] In some embodiments, the determination module 502 may include a text recognition unit and a content recognition unit. The text recognition unit may be used to perform text recognition on the content to be detected based on the text recognition model to obtain the text to be detected. The content recognition unit may be used to perform content recognition on the text to be detected based on the content recognition model to obtain the fraud probability.

[0084] In some embodiments, the content recognition unit may include a first recognition subunit and a second recognition subunit. The first recognition subunit may be used to obtain a first fraud probability of the text to be detected based on a first recognition model. The second recognition subunit may be used to use the first fraud probability as the fraud probability when the first fraud probability is less than a first threshold or greater than a second threshold, or to obtain the fraud probability of the text to be detected based on the second recognition model when the first fraud probability is greater than or equal to the first threshold and less than or equal to the second threshold.

[0085] In some embodiments, the determination module 502 may include a first prediction unit and a second prediction unit. The first prediction unit may be used to obtain a second fraud probability of the content to be detected based on the first prediction model. The second prediction unit may be used to use the first fraud probability as the fraud probability when the second fraud probability is less than the first threshold or greater than the second threshold, or to obtain the fraud probability of the content to be detected based on the second prediction model when the second fraud probability is greater than or equal to the first threshold and less than or equal to the second threshold.

[0086] In addition, the present application also provides a mobile device, Figure 6 The following is a schematic diagram of the structure of a mobile device provided by some embodiments of the present application. The mobile device 600 includes, but is not limited to, a smart phone, a tablet computer, a smart watch, a game console or a similar device. Specifically:

[0087] The mobile device 600 may include one or more processors 601 of processing cores, one or more computer-readable storage media memories 602 and other components. Those skilled in the art will appreciate that Figure 6 The structure of the mobile device 600 shown in the figure does not constitute a limitation on the mobile device 600, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0088] The processor 601 is the control center of the mobile device 600. It uses various interfaces and lines to connect various parts of the entire mobile device 600. By running or executing software programs and / or modules stored in the memory 602 and calling data stored in the memory 602, it executes various functions of the mobile device 600 and processes data, thereby monitoring the mobile device 600 as a whole. Optionally, the processor 601 may include one or more processing cores; preferably, the processor 601 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 601.

[0089] The memory 602 can be used to store software programs and modules. The processor 601 executes various functional applications and data processing by running the software programs and modules stored in the memory 602. The memory 602 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the mobile device 600, etc. In addition, the memory 602 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 602 may also include a memory controller to provide the processor 601 with access to the memory 602.

[0090] Specifically in this embodiment, the processor 601 in the mobile device 600 will load the executable files corresponding to the processes of one or more applications into the memory 602 according to the following instructions, and the processor 601 will run the applications stored in the memory 602, thereby implementing the operations in any fraud prediction method provided in the embodiments of the present application.

[0091] The specific process of the mobile device 600 executing the fraud prediction method can be referred to Figures 2 to 5 The description in , this application will not be repeated here.

[0092] Those skilled in the art will appreciate that all or part of the operations in the various methods of the above embodiments may be accomplished through instructions, or through instruction-controlled related hardware. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0093] To this end, the present application provides a computer-readable storage medium having a computer program stored thereon, which can be loaded by a processor to execute the operations in any fraud prediction method provided in the present application.

[0094] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0095] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0096] Since the instructions stored in the computer-readable storage medium can execute the operations in any fraud prediction method provided in the present application, the beneficial effects that can be achieved by any fraud prediction method provided in the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0097] It should be noted that the fraud prediction method provided in the embodiment of the present application strictly follows the principle of user privacy protection in the process of data acquisition and prediction. Before collecting any personal information, a clear and detailed information description will be provided to the user, including but not limited to the data type, collection purpose, scope of use and storage period. The user must indicate that he has read and understood the above information through clear and affirmative actions (such as clicking a confirmation button or turning on a function switch), and voluntarily authorize data collection and specific use purposes.

[0098] The above is a detailed introduction to a fraud prediction method, prediction device, mobile device and storage medium provided by the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A fraud prediction method, applied to a mobile device, characterized in that: include: Acquire the content to be detected in the mobile device; Determining the fraud probability of the content to be detected based on a fraud prediction model, the fraud prediction model includes a first prediction model and a second prediction model for predicting the fraud probability, the computational complexity of the first prediction model is smaller than that of the second prediction model, and the time spent on reasoning using the first prediction model for the same input data is smaller than the time spent on reasoning using the second prediction model; The determining the fraud probability of the content to be detected based on the fraud prediction model includes: Obtaining a second fraud probability of the content to be detected based on the first prediction model; When the second fraud probability is less than the first threshold or greater than the second threshold, the second fraud probability is used as the fraud probability; or when the second fraud probability is greater than or equal to the first threshold and less than or equal to the second threshold, the fraud probability of the content to be detected is obtained based on the second prediction model, and the fraud probability is used to evaluate the possibility that the content to be detected contains fraudulent information; wherein, the greater the fraud probability, the higher the possibility that the content to be detected contains fraudulent information; the smaller the fraud probability, the lower the possibility that the content to be detected contains fraudulent information.

2. The method according to claim 1, characterized in that in, The obtaining of the content to be detected in the mobile device includes: The display interface of the mobile device is obtained at a preset frequency, and the content to be detected in the display interface is obtained.

3. The method according to claim 2, characterized in that in, The fraud prediction model includes a text recognition model and a content recognition model; The step of determining the fraud probability of the content to be detected based on the fraud prediction model includes: Perform text recognition on the content to be detected based on the text recognition model to obtain the text to be detected, The content recognition model is used to perform content recognition on the text to be detected to obtain the fraud probability.

4. The method according to claim 3, characterized in that in, The content recognition model includes a first recognition model and a second recognition model, and the computational complexity of the first recognition model is smaller than that of the second recognition model.

5. The method according to claim 4, characterized in that in, The performing content recognition on the text to be detected based on the content recognition model to obtain the fraud probability includes: Obtaining a first fraud probability of the text to be detected based on the first recognition model; When the first fraud probability is less than a first threshold or greater than a second threshold, the first fraud probability is used as the fraud probability; or when the first fraud probability is greater than or equal to the first threshold and less than or equal to the second threshold, the fraud probability of the text to be detected is obtained based on the second recognition model.

6. A prediction device, characterized in that: The device comprises: An acquisition module, used for acquiring the content to be detected in the mobile device; A determination module is used to determine the fraud probability of the content to be detected based on a fraud prediction model, the fraud prediction model includes a first prediction model and a second prediction model for predicting the fraud probability, the calculation amount of the first prediction model is smaller than that of the second prediction model, and the time spent on reasoning using the first prediction model for the same input data is smaller than the time spent on reasoning using the second prediction model; the determination of the fraud probability of the content to be detected based on the fraud prediction model includes: obtaining a second fraud probability of the content to be detected based on the first prediction model; when the second fraud probability is less than a first threshold or greater than a second threshold, using the second fraud probability as the fraud probability, or when the second fraud probability is greater than or equal to the first threshold and less than or equal to the second threshold, obtaining the fraud probability of the content to be detected based on the second prediction model, the fraud probability is used to evaluate the possibility that the content to be detected contains fraud information; wherein, the greater the fraud probability, the higher the possibility that the content to be detected contains fraud information; the smaller the fraud probability, the lower the possibility that the content to be detected contains fraud information.

7. A mobile device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the operations in the method according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the operations in the method according to any one of claims 1 to 5 are implemented.

Images