Intelligent transaction risk prevention and control method and device based on emotion recognition

Abstract

The invention discloses a transaction risk intelligent prevention and control method and device based on emotion recognition, equipment and a medium, and the method comprises the steps: judging whether a transaction request of a user meets a recognition condition, obtaining video information of a preset question answered by the user if the transaction request meets the recognition condition, and recognizing a user image in the video information to obtain an expression recognition result; user voice in the video information is recognized to obtain a voice recognition result, the expression recognition result and the voice recognition result are comprehensively analyzed according to the emotion comprehensive analysis model to obtain a recognition result whether a transaction risk exists or not, and if the transaction risk exists, the transaction request is intercepted. According to the transaction risk intelligent prevention and control method based on emotion recognition, the user emotion is recognized by integrating the user image and the user voice, and the user expression and language are analyzed to judge whether the user emotion is stable so as to obtain the recognition result of whether the transaction risk exists; and the transaction requests with risks are intercepted, so that the security of the transfer transaction of the user is improved.

Description

Technical Field

[0001] The present invention relates to the field of smart financial technology, and in particular to a method and device for intelligently preventing and controlling transaction risks based on emotion recognition. Background Art

[0002] Financial institutions often face large-value transfer requests from users. However, some of these transactions carry certain risks, such as when a user receives a call from a stranger and is asked to transfer money. Financial institution staff typically question the user during the transfer and verify the account number. However, these staff members are unable to effectively identify the risks associated with this transaction, resulting in financial losses for the user after the transaction is completed. Therefore, existing technical methods suffer from an inability to accurately identify the risks of user transfer transactions. Summary of the Invention

[0003] The embodiments of the present invention provide a method and device for intelligent transaction risk prevention and control based on emotion recognition, aiming to solve the problem that existing technical methods cannot accurately identify the risks of user transfer transactions.

[0004] In a first aspect, an embodiment of the present invention provides a method for intelligently controlling transaction risks based on emotion recognition, wherein the method includes:

[0005] Upon receiving a transaction request input by a user, determining whether the transaction request meets a preset identification condition;

[0006] If the transaction request satisfies the identification condition, obtaining video information of the user answering preset questions;

[0007] Identify the user image in the video information according to a preset face recognition strategy to obtain a corresponding expression recognition result;

[0008] Recognize the user's voice in the video information according to a preset voice risk identification strategy to obtain a corresponding voice recognition result;

[0009] Performing a comprehensive analysis on the expression recognition result and the voice recognition result according to a preset comprehensive emotion analysis model to obtain an analysis result on whether there is a transaction risk;

[0010] If the analysis result indicates that there is a risk, the transaction request is intercepted.

[0011] In a second aspect, an embodiment of the present invention further provides an intelligent transaction risk prevention and control device based on emotion recognition, wherein the device is used to execute the intelligent transaction risk prevention and control method based on emotion recognition as described in the first aspect above, and the device includes:

[0012] a judgment unit, configured to, upon receiving a transaction request input by a user, judge whether the transaction request satisfies a preset identification condition;

[0013] A video information acquisition unit, configured to acquire video information of the user answering preset questions if the transaction request meets the identification condition;

[0014] An expression recognition result acquisition unit, configured to recognize the user image in the video information according to a preset face recognition strategy and obtain a corresponding expression recognition result;

[0015] A speech recognition result acquisition unit, configured to recognize the user's speech in the video information according to a preset speech risk identification strategy to obtain a corresponding speech recognition result;

[0016] A comprehensive analysis unit, configured to comprehensively analyze the expression recognition result and the speech recognition result according to a preset comprehensive emotion analysis model to obtain an analysis result of whether there is a transaction risk;

[0017] A request interception unit is configured to intercept the transaction request if the analysis result indicates that there is a risk.

[0018] In a third aspect, an embodiment of the present invention further provides a computer device, wherein the device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0019] Memory for storing computer programs;

[0020] The processor is configured to implement the steps of the method for intelligently preventing and controlling transaction risks based on emotion recognition as described in the first aspect above when executing the program stored in the memory.

[0021] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the method for intelligent prevention and control of transaction risks based on emotion recognition as described in the first aspect above are implemented.

[0022] The embodiments of the present invention provide a method, apparatus, device and medium for intelligent prevention and control of transaction risks based on emotion recognition. The method includes: determining whether a user's transaction request meets the recognition conditions, and if so, obtaining video information of the user answering preset questions, recognizing the user image in the video information to obtain an expression recognition result; recognizing the user voice in the video information to obtain a voice recognition result, and comprehensively analyzing the expression recognition result and the voice recognition result according to the comprehensive emotion analysis model to obtain an identification result of whether there is a transaction risk, and intercepting the transaction request if there is a transaction risk. The above-mentioned intelligent prevention and control method of transaction risks based on emotion recognition recognizes user emotions by comprehensively identifying user images and user voices, analyzes user expressions and language to determine whether the user emotions are stable to obtain an identification result of whether there is a transaction risk; and intercepts transaction requests that are at risk, thereby improving the security of user transfer transactions. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0024] Figure 1 A flowchart of a method for intelligently preventing and controlling transaction risks based on emotion recognition provided by an embodiment of the present invention;

[0025] Figure 2 A schematic block diagram of an intelligent transaction risk prevention and control device based on emotion recognition provided by an embodiment of the present invention;

[0026] Figure 3 It is a schematic block diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0028] It will be understood that when used in this specification and the appended claims, the terms “comprises” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0029] It should also be understood that the terms used in the present specification are only for the purpose of describing particular embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0030] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0031] The embodiments of the present invention provide a method for intelligently controlling transaction risks based on emotion recognition. This method is applied to a management server, which executes a stored software program to implement the method. The management server is a server configured within a financial institution for intelligently controlling transaction risks. The management server can be a cluster server. The management server can process user transaction requests. Users or financial institution staff can submit corresponding transaction requests to the management server through a transaction terminal, which can be a desktop computer, laptop computer, or automated teller machine (ATM).

[0032] like Figure 1 As shown, the method includes steps S110 to S160.

[0033] S110: If a transaction request input by a user is received, determine whether the transaction request meets a preset identification condition.

[0034] The management server can receive transaction requests input by users. Regardless of whether the transaction request is submitted by the user themselves or by staff, the transaction information (such as the transaction amount, transaction password, etc.) is entered by the user themselves, and the transaction request corresponds to the user. After receiving the transaction request, the management server can determine whether the transaction request meets the pre-set identification conditions. Specifically, the identification conditions can include a regulated transaction bank and a transaction amount threshold. The management server can then determine whether the receiving account in the transaction request belongs to a regulated transaction bank (such as an overseas bank or a non-state-owned bank) or whether the transaction amount in the transaction request exceeds the transaction amount threshold. If the receiving account belongs to a regulated transaction bank or the transaction amount exceeds the transaction amount threshold, the transaction request is determined to meet the identification conditions; otherwise, the transaction request is determined to not meet the identification conditions. If the identification conditions are not met, the transaction request is directly submitted.

[0035] S120: If the transaction request satisfies the identification condition, obtain video information of the user answering preset questions.

[0036] If the transaction request meets the recognition criteria, a pre-set question will be played, and the user will answer it. The user's image and audio of the answer will be captured to generate the corresponding video information, which will include the user's image and audio. The pre-set question may be "Describe the purpose of your transfer" or "Describe the recipient information of your transfer."

[0037] S130: Identify the user image in the video information according to a preset face recognition strategy to obtain a corresponding expression recognition result.

[0038] The user image contained in the video information is recognized through the face recognition strategy, and the corresponding expression recognition result is obtained by recognizing the user's expression information.

[0039] In a specific embodiment, step S130 includes sub-steps: extracting corresponding user facial features from the user image according to the facial feature extraction rules in the facial recognition strategy; identifying the user facial features according to the feature analysis model in the facial recognition strategy to obtain corresponding expression recognition results.

[0040] Specifically, user facial features can be extracted from user images according to the facial feature extraction rules in the facial recognition strategy. User images can be captured from continuous video frames of the video information according to the extraction interval set in the facial feature extraction rules. For example, if the extraction interval is set to 0.2 seconds, one image is extracted from the continuous video frames every 0.2 seconds as the user image. A partial portrait corresponding to the portrait template in the portrait feature extraction rules is extracted from the user image. The partial portrait contains only facial information by removing background information from the user image. Thus, a partial portrait can be extracted for each user image. Furthermore, a convolutional neural network is used in the facial feature extraction specifications to convolute each partial portrait, thereby converting the information contained in the partial portrait into a one-dimensional feature vector. For example, a 600×800 resolution partial portrait is converted into a 1×512 one-dimensional feature vector using a convolutional neural network. Each partial portrait can then be converted into a set of one-dimensional feature vectors, and the resulting multiple one-dimensional feature vectors are then combined to form the user facial features. Furthermore, the user's facial features can be comprehensively identified through the feature analysis model in the face recognition strategy to obtain expression recognition results.

[0041] In a specific embodiment, the feature analysis model in the face recognition strategy is used to identify whether the user's facial features pose a risk, and obtain a corresponding expression recognition result, including: inputting the user's facial features into the long short-term memory network in the feature analysis model to obtain an expression feature vector corresponding to the user's facial features; calculating the similarity value between the expression feature vector and a preset standard feature vector to obtain a corresponding expression recognition result.

[0042] The obtained user facial features can be input into the Long Short-Term Memory Network (LSTM) configured in the feature analysis model. The LSTM is a recurrent neural network (RNN). Based on the LSTM, the user facial features containing any number of one-dimensional feature vectors can be converted into a fixed-length vector. The fixed-length vector output by the LSTM is the expression feature vector. The process of the LSTM processing the input one-dimensional feature vector includes: ① Calculating the forget gate output information: f (t) =σ(W f ×h (t_1) +U f ×X (t)+ b f ), where f (t) is the forget gate parameter value, 0≤f (t) ≤1; σ is the activation function calculation symbol, σ can be specifically expressed as Then W f ×h (t_1) +U f ×X (t)+ b f The calculation result of x is used as the input activation function σ to calculate f (t) ;W f 、U f and b f are the parameter values ​​of the formula in this cell; h (t_1) is the output gate information of the previous cell; X (t) is the one-dimensional feature vector (1×M-dimensional vector) of the current cell. If the current cell is the first cell in the long short-term memory network, then h (t_1) =0. ② Calculate the input gate information: i (t) =σ(W i ×h (t_1) +U i ×X (t) +b i );a (t) =tanh(W a ×h (t-1) +U a ×X (t) +ba ), where i (t) is the input gate parameter value, 0≤i (t) ≤1;W i 、U i 、b i 、W a 、U a and b a are the parameter values ​​of the formula in this cell, a (t) is the calculated input gate vector value, a (t) is a 1×M-dimensional vector. ③ Update cell memory information: C (t) =C (t_1) ⊙f (t) +i (t) ⊙a (t) , C is the cell memory information accumulated in each calculation process, C (t) is the cell memory information output by the current cell, C (t_1) is the cell memory information output by the previous cell, ⊙ is a vector operator, C (t_1) ⊙f (t) The calculation process is to transform the vector C (t_1) Each dimension value in f (t) Multiply, the calculated vector dimension and vector C (t_1) The dimensions in are the same. ④ Calculate the output gate information: o (t) =σ(W o ×h (t_1) +U o ×X (t) +b o );h (t) =o (t) ⊙tanh(C (t) ), o (t) is the output gate parameter value, 0≤o (t) ≤1;W o 、U o and b o are the parameter values ​​of the formula in this cell, h (t) is the output gate information of this cell, h (t) is a 1×M-dimensional vector, h (t) As the current output, it is passed to the next moment at the same time. ⑤ Input each one-dimensional feature vector in the user's facial features into the long short-term memory network in sequence. Each time a one-dimensional feature vector is input, the cell memory information in the long short-term memory network can be updated once. After completing the input of all one-dimensional feature vectors, the output information of each cell is calculated in sequence: y (t) =σ(V×h (t)+c), where V and c are the parameters of the formula in this cell. Each cell calculates an output value. Combining the output information of N cells yields the memory network output for a piece of feature information. The memory network output for a piece of feature information is a 1×N-dimensional vector. This 1×N-dimensional feature vector corresponds to the expression feature vector. The number of dimensions of the resulting expression feature vector is unrelated to the number of one-dimensional feature vectors in the user's facial features and is only related to the number of cells in the long-short-term memory network.

[0043] Calculate the similarity between the expression feature vector and the standard feature vector, where the standard feature vector is the feature vector corresponding to the partial portrait of the user in a calm state. If the number of dimensions of the expression feature vector is equal to the number of dimensions of the standard feature vector, calculate the cosine similarity between the expression feature vector and the standard feature vector and perform normalization to obtain the corresponding similarity value. For example, if the cosine similarity value ranges from [-1, 1], the normalized similarity value will be in the range from [0, 1]. The long short-term memory network can be pre-trained before use. After pre-training, collect partial portraits of multiple users in a calm state and input them into the long short-term memory network. Obtain the output vector corresponding to each user, and calculate the average of the output vectors as the standard feature vector. A greater similarity between the expression feature vector and the standard feature vector indicates a calmer and more stable expression for the user. A smaller similarity between the expression feature vector and the standard feature vector indicates a more unstable expression for the user, potentially indicating panic or irritability.

[0044] S140: Recognize the user's voice in the video information according to a preset voice risk recognition strategy to obtain a corresponding voice recognition result.

[0045] To further increase the accuracy of user emotion recognition, the user voice in the video information can be recognized according to the voice analysis and recognition strategy. By recognizing the user voice, the corresponding voice recognition result is obtained. Combining the voice recognition result and the expression recognition result, comprehensive recognition of user emotions can be achieved.

[0046] In a specific embodiment, step S140 includes sub-steps: extracting corresponding basic feature parameters from the user voice according to the basic voice feature extraction rules of the voice risk identification strategy; performing text recognition on the user voice according to the text recognition model in the voice risk identification strategy to obtain corresponding text recognition results; performing combined recognition on the text recognition results and the basic feature parameters according to the combined recognition model in the voice risk identification strategy to obtain corresponding voice recognition results.

[0047] Specifically, the speech analysis and recognition strategy is configured with basic speech feature extraction rules, and corresponding basic feature parameters can be extracted from the user speech according to the basic speech feature extraction rules. According to the target frequency range set in the basic speech feature extraction rules, effective audio corresponding to the target frequency range is intercepted from the user speech, the number of peaks in the effective audio is extracted as the number of words, the duration of the effective audio is extracted as the speaking duration, and the ratio of the number of words to the speaking duration is calculated as the speaking rate parameter; the mean loudness of the effective audio is extracted as the loudness parameter; and the speaking rate parameter and the loudness parameter are obtained as the corresponding basic feature parameters.

[0048] Furthermore, text recognition is performed on the valid audio corresponding to the user's voice using a text recognition model, converting the voice information into corresponding text information as the corresponding text recognition result. The text recognition model is also a recognition model that converts audio information into text information. The text recognition result and basic feature parameters are combined and recognized using the combined recognition model in the voice risk identification strategy to obtain the voice recognition result.

[0049] In a specific embodiment, the text recognition result and the basic feature parameters are combined and recognized according to the combined recognition model in the speech risk recognition strategy to obtain a corresponding speech recognition result, including: performing disorder degree recognition on the basic feature parameters and the text recognition result according to the disorder degree recognition model in the combined recognition model to obtain the corresponding disorder degree; calculating the speech emotion coefficient between the basic feature parameters and the standard pronunciation feature parameters configured in the combined recognition model; and combining the disorder degree and the speech emotion coefficient into the speech recognition result.

[0050] Obtaining speech recognition results specifically includes performing disorder identification on the basic feature parameters and text recognition results based on a disorder identification model. Specifically, the speech rate parameter from the basic feature parameters is combined with the text recognition results and input into the disorder identification model. The disorder identification model includes multiple input nodes, an intermediate layer, and an output node. The intermediate layer contains one or more layers of intermediate nodes, with each layer of intermediate nodes consisting of multiple intermediate nodes arranged linearly. The first input node inputs the speech rate parameter, and each subsequent input node corresponds to a text character from the input text recognition result, and the output node outputs the corresponding disorder. The disorder degree can be used to reflect the degree of disorder in the user's speech. A higher disorder degree indicates a more disordered speech expression, while a lower disorder degree indicates a clearer speech expression. For example, fast speech, repeated words ("I, I, I want..."), and inconsistent expressions are all considered to indicate speech disorder. During the training process, multiple text segments with fast speech, repeated words, or inconsistent expressions can be used as training data to train the disorder identification model.

[0051] If the user's psychology fluctuates during the inquiry process, their speech speed and volume will change. In order to quantify the changes in the user's speech speed and volume, the corresponding voice emotion coefficient can be obtained. Specifically, the voice emotion coefficient between the basic feature parameters and the standard pronunciation feature parameters is calculated. The voice emotion coefficient is used to reflect the emotionality of the user's voice. The larger the voice emotion coefficient, the higher the user's voice is, and the smaller the voice emotion coefficient, the lower the user's voice is. For example, the formula for calculating the voice emotion coefficient can be expressed by formula (1):

[0052]

[0053] Q is the calculated voice emotion coefficient, Y s is the speech rate parameter in the basic feature parameter, Y h is the loudness parameter in the basic feature parameter, B s is the standard speaking speed parameter in the standard pronunciation feature parameter, B h is the standard loudness parameter in the standard pronunciation feature parameters, and e is the base of the natural logarithm.

[0054] By combining the obtained disorder degree with the voice emotion coefficient, the corresponding speech recognition result can be obtained.

[0055] S150: Perform a comprehensive analysis on the expression recognition result and the voice recognition result according to a preset comprehensive emotion analysis model to obtain an analysis result of whether there is a transaction risk.

[0056] By comprehensively analyzing the expression and voice recognition results using the comprehensive emotion analysis model, we can analyze the user's expressions and voice to determine whether the user's emotions are abnormal and thus determine whether there is a risk in the transaction. If the comprehensive analysis identifies abnormal emotions, the analysis results in the presence of transaction risk; if the comprehensive analysis shows no abnormal emotions, the analysis results in the absence of transaction risk.

[0057] In a specific embodiment, step S150 includes sub-steps: performing comprehensive calculation on the expression recognition result and the voice recognition result according to the comprehensive calculation rules in the comprehensive emotion analysis model to obtain a corresponding comprehensive emotion coefficient; judging whether the comprehensive emotion coefficient is within the coefficient range set by the comprehensive emotion analysis model to obtain an analysis result of whether there is a transaction risk.

[0058] The comprehensive emotion analysis model is configured with comprehensive calculation rules. The expression recognition results and speech recognition results can be comprehensively calculated according to the comprehensive calculation rules to obtain the corresponding comprehensive emotion coefficient. The comprehensive emotion coefficient is also a parameter value that characterizes whether the user's comprehensive emotion during the transfer operation is abnormal. The larger the comprehensive emotion coefficient, the more excited the user is; the smaller the comprehensive emotion coefficient, the more depressed the user is. The comprehensive calculation rule can be expressed by formula (2):

[0059]

[0060] Among them, Z is the comprehensive emotion coefficient, Q is the speech emotion coefficient in the speech recognition result, and its value is not less than zero, R is the disorder degree in the speech recognition result, and its value range is [0,1]; X is the similarity value in the expression recognition result, and its value range is [0,1].

[0061] It is further determined whether the comprehensive emotion coefficient is within the coefficient range set by the comprehensive emotion analysis model. For example, the coefficient range can be set to [0.6, 1.4]. If it is within the coefficient range, it is determined that the user emotion is normal, and the analysis result of no transaction risk is obtained; if it is not within the coefficient range, it is determined that the user emotion is abnormal, and the analysis result of the presence of transaction risk is obtained.

[0062] S160: If the analysis result indicates that there is a risk, intercept the transaction request.

[0063] If the analysis indicates a risk, the management server intercepts the transaction request and does not process it, causing the user's current transfer request to fail. By intercepting high-risk transaction requests, users can avoid financial losses caused by emotional transactions (such as those conducted under an emotional state due to fraud, coercion, etc.).

[0064] In a specific embodiment, after step S150, the method further includes the following steps: if the analysis result shows that there is no risk, submitting the transaction request.

[0065] If the analysis result shows that there is no risk, the transaction request can be submitted directly for processing. The settlement center will complete the corresponding transfer deduction upon receiving the transaction request.

[0066] In the intelligent transaction risk prevention and control method based on emotion recognition disclosed in the above embodiment, the method includes: determining whether the user's transaction request meets the identification conditions, and if so, obtaining video information of the user answering preset questions, identifying the user image in the video information to obtain an expression recognition result; identifying the user voice in the video information to obtain a voice recognition result, and comprehensively analyzing the expression recognition result and the voice recognition result according to the comprehensive emotion analysis model to obtain an identification result of whether there is a transaction risk, and intercepting the transaction request if there is a transaction risk. The above-mentioned intelligent transaction risk prevention and control method based on emotion recognition recognizes the user's emotions by comprehensively identifying the user's images and user voice, analyzes the user's expressions and language to determine whether the user's emotions are stable to obtain an identification result of whether there is a transaction risk; and intercepts transaction requests that are at risk, thereby improving the security of user transfer transactions.

[0067] The embodiment of the present invention also provides a transaction risk intelligent prevention and control device based on emotion recognition, which can be configured in a management server and is used to execute any embodiment of the transaction risk intelligent prevention and control method based on emotion recognition. Figure 2 , Figure 2 A schematic block diagram of an intelligent transaction risk prevention and control device based on emotion recognition provided by an embodiment of the present invention.

[0068] like Figure 2 As shown, the transaction risk intelligent prevention and control device 100 based on emotion recognition includes a judgment unit 110, a video information acquisition unit 120, an expression recognition result acquisition unit 130, a voice recognition result acquisition unit 140, a comprehensive analysis unit 150 and a request interception unit 160.

[0069] The judgment unit 110 is configured to judge whether a transaction request input by a user satisfies a preset identification condition upon receiving the transaction request.

[0070] The video information acquisition unit 120 is configured to acquire video information of the user answering preset questions if the transaction request satisfies the identification condition.

[0071] The expression recognition result acquisition unit 130 is configured to recognize the user image in the video information according to a preset face recognition strategy to obtain a corresponding expression recognition result.

[0072] The speech recognition result acquisition unit 140 is configured to recognize the user speech in the video information according to a preset speech risk recognition strategy to obtain a corresponding speech recognition result.

[0073] The comprehensive analysis unit 150 is used to perform a comprehensive analysis on the expression recognition result and the speech recognition result according to a preset comprehensive emotion analysis model to obtain an analysis result of whether there is a transaction risk.

[0074] The request interception unit 160 is configured to intercept the transaction request if the analysis result indicates that there is a risk.

[0075] The intelligent transaction risk prevention and control device based on emotion recognition provided in the embodiment of the present invention applies the above-mentioned intelligent transaction risk prevention and control method based on emotion recognition to determine whether the user's transaction request meets the identification conditions. If so, the video information of the user answering preset questions is obtained, and the user image in the video information is recognized to obtain the expression recognition result; the user voice in the video information is recognized to obtain the voice recognition result, and the expression recognition result and the voice recognition result are comprehensively analyzed according to the comprehensive emotion analysis model to obtain the recognition result of whether there is a transaction risk. If there is a transaction risk, the transaction request is intercepted. The above-mentioned intelligent transaction risk prevention and control method based on emotion recognition recognizes the user's emotions by comprehensively identifying the user's images and user voice, analyzes the user's expressions and language to determine whether the user's emotions are stable to obtain the recognition result of whether there is a transaction risk; and intercepts the transaction request with risks, thereby improving the security of user transfer transactions.

[0076] The above-mentioned transaction risk intelligent prevention and control device based on emotion recognition can be implemented in the form of a computer program. The computer program can be used in Figure 3 Runs on the computer equipment shown.

[0077] See also Figure 3 , Figure 3 is a schematic block diagram of a computer device provided by an embodiment of the present invention. The computer device may be a management server for executing the transaction risk intelligent prevention and control method based on emotion recognition to implement the transaction risk intelligent prevention and control based on emotion recognition.

[0078] See Figure 3 The computer device 500 includes a processor 502 , a memory, and a communication interface 505 connected via a communication bus 501 , wherein the memory may include a storage medium 503 and an internal memory 504 .

[0079] The storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, the processor 502 can execute the transaction risk intelligent prevention and control method based on emotion recognition. The storage medium 503 can be a volatile storage medium or a non-volatile storage medium.

[0080] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500.

[0081] The internal memory 504 provides an environment for the operation of the computer program 5032 in the storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute the intelligent transaction risk prevention and control method based on emotion recognition.

[0082] The communication interface 505 is used for network communication, such as providing data information transmission. Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device 500 to which the solution of the present invention is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0083] The processor 502 is configured to execute a computer program 5032 stored in the memory to implement the corresponding functions of the above-mentioned transaction risk intelligent prevention and control method based on emotion recognition.

[0084] Those skilled in the art will understand that Figure 3 The embodiment of the computer device shown in the figure does not constitute a limitation on the specific composition of the computer device. In other embodiments, the computer device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. For example, in some embodiments, the computer device may only include a memory and a processor. In such an embodiment, the structure and function of the memory and processor are the same as those in the figure. Figure 3 The embodiments shown are consistent and will not be described again here.

[0085] It should be understood that in the embodiment of the present invention, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0086] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium may be volatile or non-volatile. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps included in the aforementioned method for intelligent transaction risk prevention and control based on emotion recognition.

[0087] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0088] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, or units with the same function may be combined into one unit. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices or units, or may be an electrical, mechanical or other form of connection.

[0089] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the objectives of the embodiments of the present invention.

[0090] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0091] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a computer-readable storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned computer-readable storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk.

[0092] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A transaction risk intelligent prevention and control method based on emotion recognition, characterized in that: The method comprises: Upon receiving a transaction request input by a user, determining whether the transaction request satisfies a preset identification condition; If the transaction request satisfies the identification condition, obtaining video information of the user answering preset questions; Identify the user image in the video information according to a preset face recognition strategy to obtain a corresponding expression recognition result; Recognize the user's voice in the video information according to a preset voice risk identification strategy to obtain a corresponding voice recognition result; Performing a comprehensive analysis on the expression recognition result and the voice recognition result according to a preset comprehensive emotion analysis model to obtain an analysis result on whether there is a transaction risk; If the analysis result indicates that there is a risk, the transaction request is intercepted.

2. The method for intelligent transaction risk prevention and control based on emotion recognition according to claim 1 is characterized in that: The step of identifying the user image in the video information according to a preset face recognition strategy to obtain a corresponding expression recognition result includes: Extracting corresponding user facial features from the user image according to the facial feature extraction rules in the facial recognition strategy; The user's facial features are identified according to the feature analysis model in the face recognition strategy to obtain corresponding expression recognition results.

3. The method for intelligently controlling transaction risks based on emotion recognition according to claim 2 is characterized in that: The step of identifying whether the user's facial features present a risk based on the feature analysis model in the face recognition strategy and obtaining a corresponding expression recognition result includes: Inputting the user's facial features into the long short-term memory network in the feature analysis model to obtain an expression feature vector corresponding to the user's facial features; The similarity value between the expression feature vector and a preset standard feature vector is calculated to obtain a corresponding expression recognition result.

4. The method for intelligently controlling transaction risks based on emotion recognition according to claim 1, characterized in that: The step of recognizing the user voice in the video information according to the preset voice risk recognition strategy to obtain a corresponding voice recognition result includes: Extracting corresponding basic feature parameters from the user's voice according to the basic voice feature extraction rules of the voice risk identification strategy; Performing text recognition on the user's voice according to the text recognition model in the voice risk identification strategy to obtain a corresponding text recognition result; The text recognition result and the basic feature parameters are combined and recognized according to the combined recognition model in the speech risk recognition strategy to obtain a corresponding speech recognition result.

5. The method for intelligently controlling transaction risks based on emotion recognition according to claim 4 is characterized in that: The combining recognition of the text recognition result and the basic feature parameters according to the combined recognition model in the speech risk recognition strategy to obtain a corresponding speech recognition result includes: Performing disorder degree identification on the basic feature parameters and the text recognition result according to the disorder degree identification model in the combined recognition model to obtain corresponding disorder degrees; Calculating a speech emotion coefficient between the basic feature parameters and the standard pronunciation feature parameters configured in the combined recognition model; The disorder degree and the voice emotion coefficient are combined into the voice recognition result.

6. The transaction risk intelligent prevention and control method based on emotion recognition according to any one of claims 1 to 5, characterized in that: The comprehensive analysis of the expression recognition result and the speech recognition result based on the preset comprehensive emotion analysis model to obtain an analysis result of whether there is a transaction risk includes: Performing a comprehensive calculation on the expression recognition result and the speech recognition result according to the comprehensive calculation rules in the comprehensive emotion analysis model to obtain a corresponding comprehensive emotion coefficient; It is determined whether the comprehensive emotion coefficient is within the coefficient range set by the comprehensive emotion analysis model to obtain an analysis result of whether there is a transaction risk.

7. The method for intelligently controlling transaction risks based on emotion recognition according to claim 6 is characterized in that: The comprehensive analysis of the expression recognition result and the speech recognition result based on the preset comprehensive emotion analysis model to obtain an analysis result of whether there is a transaction risk includes: If the analysis result shows that there is no risk, the transaction request is submitted.

8. An intelligent transaction risk prevention and control device based on emotion recognition, characterized in that: The device is used to execute the transaction risk intelligent prevention and control method based on emotion recognition according to any one of claims 1 to 7, and the device includes: a judgment unit, configured to, upon receiving a transaction request input by a user, judge whether the transaction request satisfies a preset identification condition; A video information acquisition unit, configured to acquire video information of the user answering preset questions if the transaction request meets the identification condition; An expression recognition result acquisition unit, configured to recognize the user image in the video information according to a preset face recognition strategy and obtain a corresponding expression recognition result; A speech recognition result acquisition unit, configured to recognize the user's speech in the video information according to a preset speech risk identification strategy to obtain a corresponding speech recognition result; A comprehensive analysis unit, configured to comprehensively analyze the expression recognition result and the speech recognition result according to a preset comprehensive emotion analysis model to obtain an analysis result of whether there is a transaction risk; A request interception unit is configured to intercept the transaction request if the analysis result indicates that there is a risk.

9. A computer device, characterized in that: The device includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory for storing computer programs; The processor is configured to implement the steps of the method for intelligently preventing and controlling transaction risks based on emotion recognition according to any one of claims 1 to 7 when executing the program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the transaction risk intelligent prevention and control method based on emotion recognition as described in any one of claims 1 to 7 are implemented.

Images