Call risk prompting method and device

Abstract

The invention discloses a call risk prompting method and device, and belongs to the technical field of electronic equipment. The call risk prompting method comprises the following steps: acquiring call data in a call process of a user; identifying feature information of the call data; wherein the feature information comprises at least one of keyword feature information, voice feature information, behavior feature information and equipment interaction feature information; determining a score corresponding to each piece of feature information in the feature information according to a feature information scoring model; determining a risk score corresponding to the call according to the score corresponding to each piece of feature information; and prompting a call risk according to a prompt mode corresponding to the risk score.

Description

Technical Field

[0001] The present application belongs to the technical field of electronic equipment, and specifically relates to a call risk warning method and device. Background Art

[0002] In order to ensure the safety of users' property, some calls are usually intercepted before users answer the call, such as marketing calls, fraud calls, etc.

[0003] In the related art, when intercepting calls, a method based on number location identification and number tag library comparison is usually used to intercept calls.

[0004] However, the method of intercepting calls based on number location identification and number tag library comparison is to intercept calls before they are answered. If some calls are not intercepted and users answer the calls, it may cause property losses to users. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to provide a call risk warning method and device thereof, which can solve the problem that risk warnings cannot be provided during a call.

[0006] In a first aspect, an embodiment of the present application provides a call risk prompting method, comprising:

[0007] Get the call data of the user during the call;

[0008] Identify characteristic information of call data; wherein the characteristic information includes at least one of the following: keyword characteristic information, voice characteristic information, behavior characteristic information, and device interaction characteristic information;

[0009] Determine, according to the feature information scoring model, a score corresponding to each feature information in the feature information;

[0010] Determine the risk score corresponding to the call based on the score corresponding to each feature information;

[0011] The call risk is indicated according to the prompt method corresponding to the risk score.

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

[0013] The acquisition module is used to obtain the call data of the user during the call;

[0014] An identification module, configured to identify characteristic information of call data; wherein the characteristic information includes at least one of the following: keyword characteristic information, voice characteristic information, behavior characteristic information, and device interaction characteristic information;

[0015] determining module, configured to determine a score corresponding to each feature information in the feature information according to a feature information score model; and determine a risk score corresponding to the call according to the score corresponding to each feature information.

[0016] prompting module, configured to prompt the call risk according to a prompt mode corresponding to the risk score.

[0017] In a third aspect, an electronic device is provided, which includes a processor and a memory. The memory stores programs or instructions executable on the processor. When the programs or instructions are executed by the processor, the steps of the call risk prompting method provided in the embodiments of the present application are implemented.

[0018] In a fourth aspect, a readable storage medium is provided, which stores programs or instructions. When the programs or instructions are executed by a processor, the steps of the call risk prompting method provided in the embodiments of the present application are implemented.

[0019] In a fifth aspect, a chip is provided, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is configured to execute programs or instructions, and implement the steps of the call risk prompting method provided in the embodiments of the present application.

[0020] In a sixth aspect, a computer program product is provided, which is stored in a storage medium. The program product is executed by at least one processor to implement the steps of the call risk prompting method provided in the embodiments of the present application.

[0021] In the embodiments of the present application, the call data in the call process of a user is obtained; the feature information of the call data is identified; wherein the feature information includes at least one of the following: keyword feature information, voice feature information, behavior feature information, and device interaction feature information; the score corresponding to each feature information in the feature information is determined according to a feature information score model; the risk score corresponding to the call is determined according to the score corresponding to each feature information; and the call risk is prompted according to the prompt mode corresponding to the risk score. In this way, the call risk can be prompted in the call process. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 is a flowchart of the call risk prompting method provided in the embodiments of the present application;

[0023] Figure 2 is a schematic diagram of the reply suggestion provided in the embodiments of the present application;

[0024] Figure 3 is a structural schematic diagram of the call risk prompting device provided in the embodiments of the present application;

[0025] Figure 4 is a structural schematic diagram of an electronic device provided by an embodiment of the present application.

[0026] Figure 5 is a hardware structural schematic diagram of an electronic device implementing an embodiment of the present application. DETAILED DESCRIPTION

[0027] The technical solutions in the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all of them. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art belong to the scope of protection of the present application.

[0028] The terms “first”, “second”, and the like in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than that illustrated or described herein, and the objects distinguished by “first”, “second”, and the like are generally of a kind and are not limited in number, for example, the first object can be one or more. In addition, “and / or” in the specification and claims indicates at least one of the connected objects, and the character “ / ” generally indicates that the objects before and after are in an “or” relationship.

[0029] The call risk prompting method and device provided by the embodiments of the present application will be described in detail below with reference to the drawings, through specific embodiments and their application scenarios.

[0030] Figure 1 is a flow schematic diagram of a call risk prompting method provided by an embodiment of the present application; the call risk prompting method can include the following steps:

[0031] Step 101: Obtain call data in a user call process;

[0032] In some possible implementations of the embodiments of the present application, after the answering party user answers the call of the calling party user, the call data in the call process between the answering party user and the calling party user can be obtained in real time.

[0033] In some possible implementations of the embodiments of the present application, during the call process between the answering party user and the calling party user, a control for triggering the obtaining of the call data in the user call process can be displayed on the call interface of the electronic device used by the answering party user, and the call data in the user call process is obtained after the user clicks the control.

[0034] Step 102: identifying feature information of the call data; wherein the feature information comprises at least one of keyword feature information, voice feature information, behavior feature information, and device interaction feature information.

[0035] The keyword feature information refers to the appearance of specific keywords in the call data, such as keywords such as time-limited collection, loan, and high yield. The voice feature information refers to whether the emotional response of the caller user is abnormal, for example, the caller user always has stable or consistent emotions. The behavior feature information includes requesting a transfer, installing software or remote assistance, and the called user not actively interacting. The device interaction feature information refers to opening certain specific applications (Apps), such as bank Apps.

[0036] In some possible implementations of the embodiments of the present application, the keyword feature information of the call data can be identified by a natural language processing (NPL) model. The voice feature information, behavior feature information, and device interaction feature information in the call data can be identified by a voiceprint anomaly and artificial intelligence (AI) detection model.

[0037] In some possible implementations of the embodiments of the present application, the NPL model in the embodiments of the present application can perform dialogue identification and semantic understanding on the call data, support identification of various risk dialogue templates, such as semantic structures of financial fraud, social induction, and sales promotion, and identify related expressions such as sales and fraud through keyword matching and semantic similarity matching. When identifying the behavior feature information, the speaking order of the caller user, the stability of the speech speed are analyzed, and the behavior graph matching is performed in combination with the structured risk behavior chain to find the complete fraud behavior path. When identifying the voice feature information, it can be detected whether the caller user has the following abnormalities: emotional smoothing, no natural pause, extremely low sound speed change rate, and abnormal stable speech rhythm.

[0038] In some possible implementations of the embodiments of the present application, before step 102, the call risk prompting method provided by the embodiments of the present application can further include updating the natural language processing model used to identify the feature information of the call data by using historical call records.

[0039] In some possible implementations of the embodiments of the present application, after the called user authorizes, the electronic device stores the text corresponding to the local historical call records in a desensitized manner, only retains non-sensitive fragments such as keywords, sentence structures, and dialogue sequences for training; and automatically labels part of the call fragments as high-risk samples by using pre-defined high-risk sample labeling rules. The high-risk sample labeling rules include hitting risk keywords and activating behavior chains.

[0040] In some possible implementations of the embodiments of the present application, the sample marking rule may include, but is not limited to, at least one of the following: a keyword rule, a behavior chain rule, and an auxiliary judgment rule.

[0041] Among them, the keyword rule means that if more than two keywords are hit in a paragraph, the paragraph will be marked as a risky segment, or if at least one high-risk word and action instruction appears in a continuous semantic segment, the continuous semantic segment will be marked as a risky segment. Keywords include, rebate, account abnormality, specially invited user, serious consequences of not handling, etc. The behavior chain rule means that if multiple typical fraud actions are identified to occur continuously in a single call, a high-risk behavior chain judgment will be triggered. For example: if any two of the following behavior actions appear in a call, the call will be marked as a high-risk behavior chain, and behavior actions include "verify identity", "obtain card number verification code", "guide to install APP", "screen sharing" and "transfer". The auxiliary judgment rule refers to the hesitant statements of the user on the answering side, for example, the appearance of question semantics such as "really", "I don't understand", "Are you serious?", etc., which can be used as signs of being deceived to assist in analysis.

[0042] The user on the receiving end can also actively report that the call is "fraud", "sales promotion" or "normal" to generate manually labeled samples to improve data quality.

[0043] During periods of idle time, the NPL model is updated. When updating the NPL model, the semantic recognition layer of the NPL model updates the local word embedding vector space to enhance the recognition of new semantic structures, such as recognizing "zero down payment loan" as "loan" and "security verification code" as "verification code." For the speech pattern recognition layer of the NPL model, the structured speech analysis module extracts new speech templates and adds them to the speech risk template library. For keywords, recent high-frequency risk terms can be added.

[0044] After each NPL model update, the performance of the updated NPL is evaluated. If the accuracy of the NPL model decreases or the fluctuation exceeds the standard, the model will be rolled back to the previous version of the NPL model, and the pre-updated NPL model will be used when identifying the characteristic information of the call data. If the accuracy of the NPL model does not decrease and the fluctuation does not exceed the standard, the updated NPL model will be used when identifying the characteristic information of the call data. The user on the receiving end can pause the NPL model update at any time or set the NPL model update to "manual update only" mode. When the user on the receiving end sets the NPL model update to "manual update only" mode, the NPL model will only be updated when the user's NPL model update instruction is received.

[0045] Step 103: Determine the score corresponding to each feature information in the feature information according to the feature information scoring model;

[0046] In some possible implementations of the embodiments of the present application, the form of the feature information scoring model in the embodiments of the present application includes but is not limited to a table, a text and the like. Exemplarily, the feature information scoring model in the embodiments of the present application is described below by taking the form of the table as an example.

[0047] Exemplarily, the feature information scoring model in the embodiments of the present application can be as shown in Table 1.

[0048] Table 1

[0049]

[0050] Exemplarily, it is assumed that only one “loan” keyword exists in the call data, and no other keywords exist, and the score corresponding to the “sales / financial keyword identification” is 3.

[0051] Exemplarily, it is assumed that one “loan” keyword, one “time-limited collection” keyword and one “verification code” keyword exist in the call data, and no other keywords exist, and the score corresponding to the “sales / financial keyword identification” is 6, and the score corresponding to the “fraud term / fraud trick term” is 15.

[0052] Exemplarily, it is assumed that only one “loan” keyword, one “time-limited collection” keyword and one “verification code” keyword exist in the call data, and no other keywords exist, and the call opens a bank APP, the score corresponding to the “sales / financial keyword identification” is 6, the score corresponding to the “fraud term / fraud trick term” is 15, and the score corresponding to the device interaction feature information is 10.

[0053] Step 104: determining the risk score corresponding to the call according to the score corresponding to each feature information;

[0054] In some possible implementations of the embodiments of the present application, step 104 can include: determining the risk weight corresponding to each feature information according to the preference information of the user; and performing weighted summation on the score corresponding to each feature information according to the risk weight corresponding to each feature information, to obtain the risk score corresponding to the call.

[0055] In some possible implementations of the embodiments of the present application, the user can set the preference information, for example, set a preference scene, and increase the weight corresponding to the preference scene on the basis of the default weight, and reduce the weight corresponding to a non-preference scene on the basis of the default weight.

[0056] Exemplarily, the user sets “fraud” as the preference scene, and the weight corresponding to the “fraud term / fraud trick term” is increased from 1.5 to 1.7, and the weight corresponding to the “sales / financial keyword identification” is reduced from 1.0 to 0.7.

[0057] For example, assuming that only one "loan" keyword is detected in the call data, no other keywords are detected, and no other behavioral feature information, voice feature information, and device interaction feature information is detected, the score corresponding to the "promotion / financial keyword recognition" is 3, and the risk score corresponding to the call is: 1*3=3.

[0058] For example, assuming that only one "loan" keyword, one "time-limited receipt" keyword, and one "verification code" keyword are detected in the call data, no other keywords are detected, and a bank class APP is opened in the call, the score corresponding to the "promotion / financial keyword recognition" is 6, the score corresponding to the "fraud term / fraud routine term" is 15, and the score corresponding to the device interaction feature information is 10, and the risk score corresponding to the call is: 1*6+1.5*15+1.3*10=41.5.

[0059] In some possible implementations of the embodiments of the present application, step 104 can include: determining the risk score corresponding to the call according to the sensitive coefficient of the user and the score corresponding to each feature information; wherein the sensitive coefficient is set by the user or determined according to the attribute information of the user.

[0060] In some possible implementations of the embodiments of the present application, the value range of the sensitive coefficient in the embodiments of the present application can be 0.5 to 1.5.

[0061] In some possible implementations of the embodiments of the present application, when the sensitive coefficient of the user is set by the user, the user can select a sensitive coefficient from the value range of the sensitive coefficient described above as the sensitive coefficient thereof.

[0062] In some possible implementations of the embodiments of the present application, the attribute information in the embodiments of the present application includes but is not limited to age, education, number of times of experiencing fraud, number of times of answering fraud calls, and the like.

[0063] In some possible implementations of the embodiments of the present application, the higher the age of the user, the greater the sensitive coefficient of the user can be, the higher the education of the user, the smaller the sensitive coefficient of the user can be, the more times the user experiences fraud, the smaller the sensitive coefficient of the user can be, and the more times the user answers fraud calls, the smaller the sensitive coefficient of the user can be.

[0064] When the risk score corresponding to the call is determined according to the sensitive coefficient of the user and the score corresponding to each feature information, the score corresponding to each feature information can be weighted and summed by using the risk weight corresponding to each feature information, and then the sum value is multiplied by the sensitive coefficient of the user to obtain the risk score corresponding to the call.

[0065] Step 105: prompting the call risk according to the prompt mode corresponding to the risk score.

[0066] In some possible implementations of the embodiments of the present application, different risk scores correspond to different risk levels, and different risk levels correspond to different prompt manners.

[0067] For example, a risk score of 0-30 (inclusive) corresponds to a low risk, a risk score of 30 (exclusive) -70 (inclusive) corresponds to a medium risk, and a risk score greater than 70 corresponds to a high risk.

[0068] For example, the prompt manner corresponding to the low risk is that the dynamic risk indicator displayed on the screen is green, the prompt manner corresponding to the medium risk is that the dynamic risk indicator displayed on the screen is yellow, and the prompt manner corresponding to the high risk is that the dynamic risk indicator displayed on the screen is red.

[0069] In some possible implementations of the embodiments of the present application, the risk can also be prompted through vibration of the electronic device.

[0070] For example, the prompt manner corresponding to the low risk is that the electronic device vibrates at a first vibration frequency, the prompt manner corresponding to the medium risk is that the electronic device vibrates at a second vibration frequency, and the prompt manner corresponding to the high risk is that the electronic device vibrates at a third vibration frequency. The first vibration frequency is less than the second vibration frequency, and the second vibration frequency is less than the third vibration frequency.

[0071] In some possible implementations of the embodiments of the present application, the risk can also be prompted through sound. When the risk is prompted through sound, a bone conduction earphone or a microphone array can be used to prompt the risk.

[0072] For example, the prompt manner corresponding to the low risk is that a short sound prompt that only the user can perceive is sent through the bone conduction earphone or the microphone array, such as playing a “pay attention to safety” phrase or emitting a short prompt sound, without affecting normal communication.

[0073] In some possible implementations of the embodiments of the present application, when the call risk is prompted, a wearable device can also be used to prompt the risk.

[0074] When the call risk is prompted in combination with the wearable device, the risk prompt information can be displayed on the electronic device, and the call risk can be prompted through vibration of the wearable device. At this time, even if the user does not look at the screen of the electronic device, the user can also perceive the call risk.

[0075] In the embodiment of the present application, the call data in the user call process is obtained, and the feature information of the call data is identified, wherein the feature information includes at least one of the following: keyword feature information, voice feature information, behavior feature information, and device interaction feature information; the score corresponding to each feature information in the feature information is determined according to a feature information scoring model; the risk score corresponding to the call is determined according to the score corresponding to each feature information; and the call risk is prompted according to the prompt mode corresponding to the risk score. In this way, the call risk can be prompted during the call.

[0076] In some possible implementations of the embodiment of the present application, after the call risk is prompted, the user can also input a voice instruction or double-click the screen, and the electronic device gives a reply suggestion. For example, the user asks in a whisper during the call "Is this true?", the electronic device analyzes the call context and quickly gives a suggestion through a floating window text. For another example, the user double-clicks the screen to activate the deep analysis mode, and the electronic device will analyze the call structure, intent and emotion of the incoming call party in detail, and provide a safe reply suggestion. Exemplarily, as shown in Figure 2 Figure 2 is a schematic diagram of a reply suggestion provided by the embodiment of the present application. In Figure 2 , the reply suggestion is "The large model analyzes that the current call party has a transfer inducement, and the user can continue to ask "XXX question" for further verification".

[0077] In some possible implementations of the embodiment of the present application, the call risk prompting method provided by the embodiment of the present application further includes: receiving a first input of a user in a call process; and performing a call processing corresponding to the first input.

[0078] In some possible implementations of the embodiment of the present application, different call processing can be set for different inputs. The first input in the embodiment of the present application includes but is not limited to voice input, operation input, etc. The voice input is a trigger sentence recorded by the user himself, and the operation input is a series of actions defined by the user. Exemplarily, the operation input is a shaking input of the user shaking the electronic device, or a sliding input of the user sliding the screen with three fingers.

[0079] Exemplarily, the input and call processing corresponding relationship is shown in Table 2.

[0080] Table 2

[0081]

[0082] Exemplarily, when the user inputs "remember this number" by voice, the incoming call number is included in the trusted white list, and the risk is no longer prompted; when the user shakes the electronic device, the current call prompt is closed.

[0083] ​The call risk warning method provided in the embodiment of the present application can be executed by a call risk warning device. In the embodiment of the present application, the call risk warning device executing the call risk warning method is taken as an example to illustrate the call risk warning device provided in the embodiment of the present application.

[0084] Figure 3 Schematic diagram of the structure of the call risk warning device provided in an embodiment of the present application. The call risk warning device 300 may include:

[0085] Acquisition module 301, used to obtain call data of the user during the call;

[0086] Identification module 302, configured to identify characteristic information of call data; wherein the characteristic information includes at least one of the following: keyword characteristic information, voice characteristic information, behavior characteristic information, and device interaction characteristic information;

[0087] Determination module 303, configured to determine a score corresponding to each feature information in the feature information according to the feature information scoring model; and determine a risk score corresponding to the call according to the score corresponding to each feature information;

[0088] The prompt module 304 is configured to prompt the call risk according to a prompt method corresponding to the risk score.

[0089] In an embodiment of the present application, call data from a user during a call is obtained; feature information of the call data is identified; wherein the feature information includes at least one of the following: keyword feature information, voice feature information, behavior feature information, and device interaction feature information; a score corresponding to each feature information in the feature information is determined based on a feature information scoring model; a risk score corresponding to the call is determined based on the score corresponding to each feature information; and a call risk is indicated based on a prompt method corresponding to the risk score. In this way, a call risk prompt can be provided during the call.

[0090] In some possible implementations of the embodiment of the present application, the determining module 303 is specifically configured to:

[0091] Determine the risk weight corresponding to each feature information based on the user's preference information

[0092] Based on the risk weight corresponding to each feature information, the scores corresponding to each feature information are weighted and summed to obtain the risk score corresponding to the call.

[0093] In some possible implementations of the embodiment of the present application, the determining module 303 is specifically configured to:

[0094] The risk score corresponding to the call is determined based on the user's sensitivity coefficient and the score corresponding to each feature information; wherein the sensitivity coefficient is set by the user or determined based on the user's attribute information.

[0095] In some possible implementation of the embodiments of the present application, the call risk prompting apparatus 300 further includes:

[0096] an updating module, configured to update a natural language processing model used to identify feature information of the call data by using the historical call record.

[0097] In some possible implementation of the embodiments of the present application, the call risk prompting apparatus 300 further includes:

[0098] a receiving module, configured to receive a first input of the user in the call process;

[0099] an executing module, configured to execute a call processing corresponding to the first input.

[0100] The call risk prompting apparatus in the embodiments of the present application can be an electronic device, or a component in the electronic device, for example, an integrated circuit or a chip. The electronic device can be a terminal, or other devices than the terminal. For example, the electronic device can be a mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted electronic device, a Mobile Internet Device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), and the like, or a server, a Network Attached Storage (NAS), a personal computer (PC), a television (TV), a teller machine, or a self-service machine, and the like, and the embodiments of the present application are not limited thereto.

[0101] The call risk prompting apparatus in the embodiments of the present application can be an apparatus with an operating system. The operating system can be an Android operating system, an iOS operating system, or other possible operating systems, and the embodiments of the present application are not limited thereto.

[0102] The call risk prompting apparatus provided in the embodiments of the present application can implement each process of the call risk prompting method embodiment, and details are not described herein again to avoid repetition. Figures 1 to 2

[0103] Optionally, as Figure 4 ​As shown, the embodiments of the present application further provide an electronic device 400, comprising a processor 401 and a memory 402, wherein the memory 402 stores programs or instructions executable on the processor 401, and the programs or instructions are executed by the processor 401 to implement each step of the call risk prompting method provided by the embodiments of the present application and achieve the same technical effects. To avoid repetition, details are not described herein.

[0104] Figure 5 FIG. 1 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present application.

[0105] The electronic device 500 includes, but is not limited to, a radio frequency unit 501, a network module 502, an audio output unit 503, an input unit 504, a sensor 505, a display unit 506, a user input unit 507, an interface unit 508, a memory 509, and a processor 510, etc.

[0106] Those skilled in the art can understand that the electronic device 500 can further include a power supply (such as a battery) for supplying power to each component, and the power supply can be logically connected to the processor 510 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system. Figure 5 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and the electronic device can include more or fewer components than shown, or combine certain components, or different component arrangements, which are not described herein.

[0107] The processor 510 is configured to: obtain call data in a user call process; identify feature information of the call data; wherein the feature information includes at least one of the following: keyword feature information, voice feature information, behavior feature information, and device interaction feature information; determine a score corresponding to each feature information in the feature information according to a feature information score model; determine a risk score corresponding to the call according to the score corresponding to each feature information; and prompt a call risk according to a prompt mode corresponding to the risk score.

[0108] In the embodiments of the present application, the call data in the user call process is obtained; the feature information of the call data is identified; wherein the feature information includes at least one of the following: keyword feature information, voice feature information, behavior feature information, and device interaction feature information; a score corresponding to each feature information in the feature information is determined according to a feature information score model; a risk score corresponding to the call is determined according to the score corresponding to each feature information; and a call risk is prompted according to a prompt mode corresponding to the risk score. In this way, the call risk can be prompted during the call process.

[0109] In some possible implementations of the embodiments of the present application, the processor 510 is specifically configured to:

[0110] According to the preference information of the user, determine the risk weight corresponding to each feature information.

[0111] According to the risk weight corresponding to each feature information, the scores corresponding to each feature information are weighted and summed to obtain the risk score corresponding to the call.

[0112] In some possible implementations of the embodiments of the present application, the processor 510 is specifically configured to:

[0113] According to the sensitivity coefficient of the user and the score corresponding to each feature information, determine the risk score corresponding to the call; wherein, the sensitivity coefficient is set by the user or determined according to the attribute information of the user.

[0114] In some possible implementations of the embodiments of the present application, the processor 510 is further configured to:

[0115] Update the natural language processing model used to identify the feature information of the call data by using the historical call record.

[0116] In some possible implementations of the embodiments of the present application, the user input unit 507 is configured to:

[0117] Receive the first input of the user during the call;

[0118] The processor 510 is further configured to: execute the call processing corresponding to the first input.

[0119] It should be understood that in the embodiments of the present application, the input unit 504 can include a graphics processor (GPU) 5041 and a microphone 5042. The graphics processor 5041 processes image data of a still picture or a video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 506 can include a display panel 5061, which can be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 507 includes at least one of a touch panel 5071 and other input devices 5072. The touch panel 5071 is also called a touch screen. The touch panel 5071 can include a touch detection device and a touch controller. The other input devices 5072 can include, but are not limited to, a physical keyboard, function keys (such as volume control keys, on-off keys, etc.), trackballs, mice, joysticks, and the like, which will not be described here.

[0120] The memory 509 can be used to store software programs and various data. The memory 509 can mainly include a first storage area storing programs or instructions and a second storage area storing data, wherein the first storage area can store an operating system, application programs or instructions required by at least one function (such as a sound playing function, an image playing function, etc.), and the like. In addition, the memory 509 can include a volatile memory or a non-volatile memory, or the memory 509 can include both a volatile memory and a non-volatile memory. The non-volatile memory can be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a Random Access Memory (RAM), a Static RAM (SRAM), a Dynamic RAM (DRAM), a Synchronous DRAM (SDRAM), a Double Data Rate SDRAM (DDR SDRAM), an Enhanced SDRAM (ESDRAM), a Synch link DRAM (SLDRAM), and a Direct Rambus RAM (DRRAM). The memory 509 in the embodiments of the present application includes but is not limited to these and any other suitable types of memory.

[0121] The processor 510 can include one or more processing units; optionally, the processor 510 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and an application program, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 510.

[0122] The embodiments of the present application also provide a readable storage medium, and the readable storage medium stores programs or instructions, which are executed by a processor to implement various processes of the call risk prompting method embodiments provided by the embodiments of the present application and achieve the same technical effects. To avoid repetition, details are not described herein.

[0123] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes a computer readable storage medium, such as a computer readable only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0124] The chip provided in the embodiments of the present application includes a processor and a communication interface. The communication interface is coupled with the processor. The processor is configured to execute programs or instructions, implement various processes of the call risk prompting method provided in the embodiments of the present application, and achieve the same technical effects. To avoid repetition, details are not described herein.

[0125] It should be understood that the chip mentioned in the embodiments of the present application can also be referred to as a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0126] The embodiments of the present application also provide a computer program product. The program product is stored in a storage medium. The program product is executed by at least one processor to implement various processes of the call risk prompting method provided in the embodiments of the present application, and achieve the same technical effects. To avoid repetition, details are not described herein.

[0127] It should be noted that, in this document, the term "comprising" or "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that processes, methods, articles or devices including a series of elements not only include those elements, but also include other elements not explicitly listed, or include elements inherent to such processes, methods, articles or devices. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to the order of performing functions as shown or discussed, but can also include performing functions in a substantially simultaneous manner or in a reverse order, for example, the described method can be performed in an order different from that described, and various steps can also be added, omitted or combined. In addition, the feature information described with reference to some examples can be combined in other examples.

[0128] Through the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned example methods can be realized by means of software and a necessary general hardware platform, and of course, can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a computer software product in essence or in the form of a part that contributes to the prior art, which is stored in a storage medium (such as a ROM / RAM, a magnetic disk, or an optical disk) and includes a plurality of instructions for causing a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application.

[0129] The embodiments of the present application are described above in combination with the drawings, but the present application is not limited to the above-mentioned specific embodiments, and the above-mentioned specific embodiments are only illustrative and not restrictive. Those skilled in the art can make many forms under the inspiration of the present application without departing from the scope of the present application and the scope protected by the claims.

Claims

1. A call risk reminder method, characterized in that: The method comprises: Get the call data of the user during the call; Identify feature information of the call data; wherein the feature information includes at least one of the following: keyword feature information, voice feature information, behavior feature information, and device interaction feature information; Determining a score corresponding to each feature information in the feature information according to a feature information scoring model; Determining a risk score corresponding to the call based on the score corresponding to each feature information; The call risk is prompted according to the prompt method corresponding to the risk score.

2. The method according to claim 1, characterized in that Determining a risk score corresponding to the call according to the score corresponding to each feature information includes: Determining the risk weight corresponding to each feature information according to the user's preference information; According to the risk weight corresponding to each feature information, the score corresponding to each feature information is weighted and summed to obtain the risk score corresponding to the call.

3. The method according to claim 1, characterized in that Determining a risk score corresponding to the call according to the score corresponding to each feature information includes: The risk score corresponding to the call is determined according to the user's sensitivity coefficient and the score corresponding to each feature information; wherein the sensitivity coefficient is set by the user or determined according to the user's attribute information.

4. The method according to any one of claims 1 to 3, characterized in that Before identifying the characteristic information of the call data, the method further includes: The natural language processing model used to update and identify the feature information of the call data is used by using the historical call records.

5. The method according to any one of claims 1 to 3, characterized in that The method further comprises: receiving a first input from the user during the call; Execute call processing corresponding to the first input.

6. A call risk warning device, characterized in that: The device comprises: The acquisition module is used to obtain the call data of the user during the call; an identification module, configured to identify characteristic information of the call data; wherein the characteristic information includes at least one of the following: keyword characteristic information, voice characteristic information, behavior characteristic information, and device interaction characteristic information; a determination module, configured to determine a score corresponding to each piece of feature information in the feature information according to a feature information scoring model; and determine a risk score corresponding to the call according to the score corresponding to each piece of feature information; The prompt module is used to prompt the call risk according to the prompt method corresponding to the risk score.

7. The device according to claim 6, characterized in that The determining module is specifically configured to: Determine the risk weight corresponding to each feature information based on the user's preference information According to the risk weight corresponding to each feature information, the score corresponding to each feature information is weighted and summed to obtain the risk score corresponding to the call.

8. The device according to claim 6, characterized in that The determining module is specifically configured to: The risk score corresponding to the call is determined according to the user's sensitivity coefficient and the score corresponding to each feature information; wherein the sensitivity coefficient is set by the user or determined according to the user's attribute information.

9. The device according to any one of claims 6 to 8, characterized in that The device further comprises: An updating module is used to update a natural language processing model used to identify characteristic information of the call data using historical call records.

10. The device according to any one of claims 6 to 8, characterized in that The device further comprises: A receiving module, configured to receive a first input from the user during the call; An execution module is used to execute the call processing corresponding to the first input.

Images