Transaction instruction generation method and device, equipment, medium and program product

Abstract

The invention provides a transaction instruction generation method and device, equipment, a medium and a program product, which can be applied to the field of information technology or financial science and technology. The method comprises the following steps: in response to a received transaction operation of a target user, obtaining to-be-transacted information and historical transaction information of the target user; determining a transaction risk level of the transaction operation based on the to-be-transacted information and the historical transaction information; under the condition that the transaction risk level is larger than a first preset threshold value, a voice interaction problem is generated based on the to-be-transacted information, the voice interaction problem is generated based on voice corpus data input by a first user, and the first user and a target user have an association relationship; the voice interaction problem characterization is used for determining a problem for a reason of the transaction operation; and in response to received reply information of the target user for the voice interaction problem, generating a target instruction for controlling the transaction operation based on the reply information.

Description

Technical Field

[0001] The present disclosure relates to the field of information technology or financial technology, and more specifically to a transaction instruction generation method, device, equipment, medium and program product. Background Art

[0002] With the advancement of technology, especially the application of mobile payment and other technologies, consumers can conveniently conduct various consumer transactions through mobile phones and other terminal devices, which not only improves the shopping experience, but also broadens consumer choices. However, in some cases, the risk control system of relevant institutions will be triggered to control transactions. Rigid restrictions on user transactions will reduce users' favorability towards relevant institutions, reduce user experience and thus cause user complaints. Summary of the invention

[0003] In view of the above problems, the present disclosure provides a transaction instruction generation method, apparatus, device, medium and program product.

[0004] According to a first aspect of the present disclosure, a transaction instruction generation method is provided, comprising: in response to receiving a transaction operation of a target user, obtaining information to be traded and historical transaction information of the target user; determining a transaction risk level of the transaction operation based on the information to be traded and the historical transaction information; in a case where the transaction risk level is greater than a first predetermined threshold, generating a voice interaction question based on the information to be traded, wherein the voice interaction question is generated based on voice corpus data input by a first user, the first user and the target user have an associated relationship, and the voice interaction question represents a question for determining a reason for the transaction operation; in response to received reply information of the target user to the voice interaction question, generating a target instruction for controlling the transaction operation based on the reply information.

[0005] According to an embodiment of the present disclosure, the above-mentioned response is to the reply information received from the target user to the above-mentioned voice interaction question, and a target instruction for controlling the above-mentioned transaction operation is generated based on the above-mentioned reply information, including: determining the emotional state of the above-mentioned target user based on the reply information of the above-mentioned voice interaction question; and generating a target instruction for controlling the above-mentioned transaction operation when the above-mentioned emotional state is a preset emotional state.

[0006] According to an embodiment of the present disclosure, the above-mentioned reply information based on the above-mentioned voice interaction question determines the emotional state of the above-mentioned target user, including: preprocessing the above-mentioned reply information to obtain preprocessed reply information; inputting the above-mentioned preprocessed reply information into a trained emotion cause recognition model to obtain an emotion cause clause, and the above-mentioned emotion cause clause is the sub-voice data that causes emotional fluctuations in the above-mentioned preprocessed reply information; and determining the emotional state of the above-mentioned target user based on the above-mentioned emotion cause clause.

[0007] According to an embodiment of the present disclosure, the generation of voice interaction questions based on the transaction information includes: generating text interaction data based on a preset question and answer template and the transaction information; inputting the text interaction data into a speech synthesis model to obtain the voice interaction questions, wherein the speech synthesis model is trained based on the speech corpus data of the first user.

[0008] According to an embodiment of the present disclosure, the above method also includes: when the above emotional state is a joyful state and the above emotional reason sentence includes a preset risk control text, terminating the above transaction operation.

[0009] According to an embodiment of the present disclosure, the above-mentioned transaction information includes a transaction amount and a transaction time, the above-mentioned historical transaction information includes a historical transaction frequency, and the above-mentioned determination of the transaction risk level of the above-mentioned transaction operation based on the above-mentioned pending transaction information and the above-mentioned historical transaction information includes: determining the usual transaction time period of the above-mentioned target user based on the above-mentioned historical transaction frequency; when the above-mentioned transaction time is not within the usual time period of the above-mentioned target user, and the above-mentioned transaction amount is greater than a first preset risk amount, determining the above-mentioned transaction risk level as a first transaction risk level, and the above-mentioned first transaction risk level is greater than the above-mentioned first predetermined threshold value.

[0010] According to an embodiment of the present disclosure, the above-mentioned historical transaction information also includes risk control terminated transaction data, and the above-mentioned method also includes: when the above-mentioned transaction amount is greater than the second risk preset amount, and the number of the above-mentioned risk control terminated transaction data is greater than the preset risk control terminated transaction number, the above-mentioned transaction risk is determined as the first transaction risk level, wherein the above-mentioned second preset risk amount is less than the above-mentioned first preset risk amount.

[0011] A second aspect of the present disclosure provides a transaction instruction generation device, including: an acquisition module, for acquiring information to be traded and historical transaction information of the target user in response to receiving a transaction operation of a target user; a determination module, for determining a transaction risk level of the transaction operation based on the information to be traded and the historical transaction information; a generation module, for generating a voice interaction question based on the information to be traded when the transaction risk level is greater than a first predetermined threshold, wherein the voice interaction question is generated based on voice corpus data input by a first user, the first user and the target user have an associated relationship, and the voice interaction question represents a question for determining a cause for the transaction operation; and a control module, for generating a target instruction for controlling the transaction operation based on the reply information received from the target user for the voice interaction question.

[0012] According to an embodiment of the present disclosure, the above-mentioned control module includes: an emotional state determination submodule, which is used to determine the emotional state of the above-mentioned target user based on the reply information of the above-mentioned voice interaction question; and a transaction control submodule, which is used to generate a target instruction for controlling the above-mentioned transaction operation when the above-mentioned emotional state is a preset emotional state.

[0013] According to an embodiment of the present disclosure, the above-mentioned emotional state determination submodule includes: a preprocessing unit, used to preprocess the above-mentioned reply information to obtain preprocessed reply information; a model input unit, used to input the above-mentioned preprocessed reply information into a trained emotion cause recognition model to obtain an emotion cause clause, and the above-mentioned emotion cause clause is the sub-voice data that causes emotional fluctuations in the above-mentioned preprocessed reply information; an emotional state determination unit, used to determine the emotional state of the above-mentioned target user based on the above-mentioned emotion cause clause.

[0014] According to an embodiment of the present disclosure, the above-mentioned generation module includes: a text interaction data generation sub-module, used to generate text interaction data based on a preset question and answer template and the above-mentioned transaction information; a model input sub-module, used to input the above-mentioned text interaction data into a speech synthesis model to obtain the above-mentioned speech interaction question, wherein the above-mentioned speech synthesis model is trained based on the speech corpus data of the above-mentioned first user.

[0015] According to an embodiment of the present disclosure, the above-mentioned device also includes: when the above-mentioned emotional state is a joyful state and the above-mentioned emotional reason words include a preset risk control text, controlling the above-mentioned transaction operation.

[0016] According to an embodiment of the present disclosure, the above-mentioned transaction information includes a transaction amount and a transaction time, the above-mentioned historical transaction information includes a historical transaction frequency, and the above-mentioned determination module includes: a habitual transaction time period determination submodule, used to determine the habitual transaction time period of the above-mentioned target user based on the above-mentioned historical transaction frequency; a transaction risk level determination submodule, used to determine the above-mentioned transaction risk level as a first transaction risk level when the above-mentioned transaction time is not within the habitual time period of the above-mentioned target user and the above-mentioned transaction amount is greater than a first preset risk amount, and the above-mentioned first transaction risk level is greater than the above-mentioned first predetermined threshold value.

[0017] According to an embodiment of the present disclosure, the above-mentioned historical transaction information also includes risk control terminated transaction data, and the above-mentioned device also includes: a second transaction risk level determination submodule, which is used to determine the above-mentioned transaction risk as the first transaction risk level when the above-mentioned transaction amount is greater than the second risk preset amount and the number of the above-mentioned risk control terminated transaction data is greater than the preset risk control terminated transaction number, wherein the above-mentioned second preset risk amount is less than the above-mentioned first preset risk amount.

[0018] A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0019] The fourth aspect of the present disclosure further provides a computer-readable storage medium having a computer program or instructions stored thereon, which implements the steps of the above method when the above computer program or instructions are executed by a processor.

[0020] The fifth aspect of the present disclosure further provides a computer program product, including a computer program or instructions, which implement the steps of the above method when the above computer program or instructions are executed by a processor.

[0021] According to the embodiments of the present disclosure, the transaction risk level of the transaction operation is determined by obtaining the information to be traded and the historical transaction information of the target user. When the transaction risk level is greater than a predetermined threshold value of the first transaction, a voice interaction question of the first user is generated according to the information to be traded to obtain the user's reply information, and then the transaction operation is controlled. This can reduce the user's resistance and improve the user experience. The transaction operation can be further controlled by question-and-answer method, thereby ensuring the user's fund security. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0023] Figure 1 The application scenario diagram of the transaction instruction generation method and device according to the embodiment of the present disclosure is schematically shown;

[0024] Figure 2 A flowchart of a method for generating a transaction instruction according to an embodiment of the present disclosure is schematically shown;

[0025] Figure 3 A schematic diagram schematically shows a BiLSTM model structure according to an embodiment of the present disclosure;

[0026] Figure 4 A schematic diagram of an AM-BiLSTM model according to an embodiment of the present disclosure is schematically shown;

[0027] Figure 5 The structure block diagram of the transaction instruction generating device according to the embodiment of the present disclosure is schematically shown;

[0028] Figure 6 A block diagram of an electronic device suitable for implementing a transaction instruction generating method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0029] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0030] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0031] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0032] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0033] It should be noted that the transaction instruction generation method, device, equipment, medium and program product disclosed in the present invention can be used in the field of financial technology, and can also be used in any field other than the field of financial technology. The present disclosure does not limit the application field of the transaction instruction generation method, device, equipment, medium and program product.

[0034] In the technical solution of the present disclosure, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0035] In the scenario of using personal information for automated decision-making, the methods, devices, and systems provided by the embodiments of the present disclosure provide users with corresponding operation portals for users to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating a person's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs, and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge and skills, and have reached a certain level of professionalism.

[0036] With the continuous upgrading of the transaction system, users can conveniently conduct various transactions through mobile banking, such as credit card swiping, transfers, recharges and payments, etc. However, some transactions will trigger the risk control indicators of relevant institutions and thus restrict user transactions. Rigid restrictions on customer transactions will reduce the user experience.

[0037] In view of this, an embodiment of the present disclosure provides a transaction instruction generation method, in response to receiving a transaction operation of a target user, obtaining information to be traded and historical transaction information of the target user; determining a transaction risk level of the transaction operation based on the information to be traded and the historical transaction information; when the transaction risk level is greater than a first predetermined threshold, generating a voice interaction question based on the information to be traded, wherein the voice interaction question is generated based on voice corpus data entered by a first user, the first user and the target user have an associated relationship, and the voice interaction question represents a question used to determine the cause of the transaction operation; in response to received reply information of the target user to the voice interaction question, controlling the transaction operation based on the reply information.

[0038] Figure 1 The application scenario diagram of the transaction instruction generation method and device according to the embodiments of the present disclosure is schematically shown.

[0039] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0040] The user can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0041] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0042] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0043] It should be noted that the transaction instruction generation method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the transaction instruction generation device provided in the embodiment of the present disclosure can generally be set in the server 105. The transaction instruction generation method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the transaction instruction generation device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0044] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0045] The following will be based on Figure 1 The scene described by Figure 2~Figure 4 The transaction instruction generating method of the disclosed embodiment is described in detail.

[0046] Figure 2 The flowchart of the transaction instruction generation method according to the embodiment of the present disclosure is schematically shown.

[0047] like Figure 2 As shown, the transaction instruction generating method of this embodiment includes operations S210 to S240.

[0048] In operation S210, in response to receiving a transaction operation of a target user, to-be-transacted information and historical transaction information of the target user are acquired.

[0049] According to an embodiment of the present disclosure, the above-mentioned pending transaction information may be, for example, data such as transaction amount, transaction time, and transaction type.

[0050] In operation S220, a transaction risk level of the transaction operation is determined based on the pending transaction information and the historical transaction information.

[0051] In operation S230, when the transaction risk level is greater than a first predetermined threshold, a voice interaction question is generated based on the transaction information.

[0052] The voice interaction question is generated based on the voice corpus data input by the first user, the first user and the target user have an association relationship, and the voice interaction question representation is a question used to determine the cause of the transaction operation.

[0053] According to an embodiment of the present disclosure, the above-mentioned voice interaction questions can also be pre-entered by the first user. The first user first binds the identity identifier of the target user who needs to be prompted. After approval by the relevant agency, the correspondence between the identity identifier of the target user and the voice interaction questions is recorded in the database. When it is monitored that the transaction risk level is greater than the first predetermined threshold, the voice interaction questions are played to the target user.

[0054] Exemplarily, when the target user's transfer operation triggers the first predetermined threshold, a voice interaction question may be played to the target user through the terminal device, such as "Who are you trading with? The transaction amount is quite large, what is it for?".

[0055] In operation S240, in response to the received reply information of the target user to the voice interaction question, a target instruction for controlling the transaction operation is generated based on the reply information.

[0056] According to an embodiment of the present disclosure, the above-mentioned control transaction operation may, for example, terminate the transaction operation or suspend the transaction operation and notify the first user.

[0057] According to the embodiments of the present disclosure, sensitive words may be detected in the reply information to determine whether to control the transaction operation, and whether to control the transaction operation may also be determined based on the emotional state in the reply information, and the present application does not impose any restrictions on this.

[0058] According to the embodiments of the present disclosure, the transaction risk level of the transaction operation is determined by obtaining the information to be traded and the historical transaction information of the target user. When the transaction risk level is greater than a predetermined threshold value of the first transaction, a voice interaction question of the first user is generated according to the information to be traded to obtain the user's reply information, and then the transaction operation is controlled. This can reduce the user's resistance and improve the user experience. The transaction operation can be further controlled by question-and-answer method, thereby ensuring the user's fund security.

[0059] According to an embodiment of the present disclosure, in response to reply information received from the target user to a voice interaction question, a target instruction for controlling the transaction operation is generated based on the reply information, including: determining the emotional state of the target user based on the reply information to the voice interaction question; and generating a target instruction for controlling the transaction operation when the emotional state is a preset emotional state.

[0060] According to an embodiment of the present disclosure, the above-mentioned preset emotional state may be, for example, an emotional state such as anxiety, worry, anger, sadness, etc.

[0061] According to an embodiment of the present disclosure, the above-mentioned reply information based on the voice interaction question determines the emotional state of the target user, including: preprocessing the reply information to obtain preprocessed reply information; inputting the preprocessed reply information into a trained emotion cause recognition model to obtain an emotion cause clause, the emotion cause clause being the sub-voice data that causes emotional fluctuations in the preprocessed reply information; and determining the emotional state of the target user based on the emotion cause clause.

[0062] According to the embodiments of the present disclosure, the emotion recognition of the target user's reply information can be performed through a deep learning model. The above deep learning model regards the emotion cause recognition task as a classification problem, and can be modeled through a bidirectional long short-term memory network and an attention mechanism and the training results can be classified through a softmax function to obtain the emotion cause recognition result.

[0063] According to the embodiment of the present disclosure, when the reply information is text information, the reply information can be segmented and POS tagged by a segmentation tool, and nouns and verbs in each clause can be extracted and their number can be counted. When the reply information is voice information, the voice information can be converted into text information and then the corresponding preprocessing operation can be performed.

[0064] According to the embodiment of the present disclosure, character vector training can be performed after preprocessing to obtain a vector for each character, and the extracted clause features are fused with the clause itself to obtain a sentence vector representation of each clause.

[0065] According to an embodiment of the present disclosure, the sentence vector of each clause can be input into a trained emotion cause recognition model. The emotion cause recognition model can be, for example, an AM-BiLSTM (attention model and bi-directional long short-term memory) model.

[0066] Figure 3 A schematic diagram of a BiLSTM model structure according to an embodiment of the present disclosure is schematically shown.

[0067] like Figure 3 As shown in the figure, the BiLSTM (bi-directional long short-term memory) in the aforementioned model is composed of two LSTM (long short-term memory) stacked up and down in reverse, and the output is jointly determined by the two LSTMs. When a clause is input into the input layer of the model, the model will perform operations in the forward and backward directions respectively, which can not only preserve the past semantic information of the clause, but also take into account the future semantic information of the clause, thereby making better use of the contextual information of the clause.

[0068] Figure 4 A schematic diagram of an AM-BiLSTM model according to an embodiment of the present disclosure is schematically shown.

[0069] like Figure 4 As shown, the input text sequence "ABCDEFGH" can be first segmented to obtain the text after segmentation. The input text sequence here is only for illustration, and the present disclosure does not limit this. Then, the text after segmentation is converted into a word embedding vector (that is, the above-mentioned sentence vector representation) and input into the Bi-LSTM model, and the output data is obtained through the self-attention mechanism to obtain the emotion cause recognition result.

[0070] According to the embodiments of the present disclosure, attention data can be calculated by calculating the clauses output by the bidirectional long short-term memory network, so as to focus on the important information in the data, amplify the important information, and selectively ignore the unimportant data, so as to better represent the text information and make the trained model have better performance.

[0071] According to the embodiments of the present disclosure, by identifying the target user's reply information to voice interaction questions and determining the target user's emotional state, the user's transaction operations can be controlled in a timely manner when the user's emotional state is not a preset emotional state to avoid losses. In addition, by inputting the reply information into a trained emotion reason recognition model, the emotion reason clause that causes the emotional fluctuation is obtained. The user's emotional state is determined through the clause, which reduces the amount of data processing, speeds up emotion recognition, and further ensures the safety of user funds.

[0072] According to an embodiment of the present disclosure, the method further includes: when the emotional state is a joyful state and the emotion-causing sentence includes a preset risk control text, controlling the transaction operation.

[0073] According to the embodiments of the present disclosure, in general, for abnormal transactions, the target users all have negative emotions such as anxiety and worry, but there may be abnormal transactions in which the users have positive emotions. When the user's emotional state is a joyful state, the transaction reason can be further determined based on the determined emotional reason clause, and an abnormal transaction reason database is preset in the database. When the emotional reason clause contains data stored in the abnormal transaction reason database, the transaction can be considered to be an abnormal transaction and the transaction operation can be controlled.

[0074] According to the embodiments of the present disclosure, after determining the user's emotional state, a secondary detection is performed on the transaction operations corresponding to the joy state that does not belong to the preset emotional state. When the preset risk text is included in the emotional reason clause, the transaction operations are controlled, thereby further ensuring the safety of user funds.

[0075] According to an embodiment of the present disclosure, the above-mentioned generation of voice interaction questions based on transaction information includes: generating text interaction data based on a preset question and answer template and transaction information; inputting the text interaction data into a speech synthesis model to obtain voice interaction questions, wherein the speech synthesis model is trained based on the speech corpus data of the first user.

[0076] According to an embodiment of the present disclosure, after a first user enters expected voice data, voice data having the first user's speaking characteristics can be generated through voice cloning technology in a voice synthesis model, and the target user can be reminded through the voice data.

[0077] Exemplarily, the above-mentioned preset question and answer template can be "You transferred XX yuan, who is it for?", where XX can be the transaction amount in the transaction information. The preset question and answer template can also be "It's XXX o'clock, what are you going to do with so much money", where XXX can be the transaction time in the transaction information.

[0078] According to an embodiment of the present disclosure, the above-mentioned transaction information includes the transaction amount and the transaction time, the historical transaction information includes the historical transaction frequency, and the transaction risk level of the transaction operation is determined based on the pending transaction information and the historical transaction information, including: determining the target user's usual transaction time period based on the historical transaction frequency; when the transaction time is not within the target user's usual time period and the transaction amount is greater than the first preset risk amount, determining the transaction risk level as the first transaction risk level, and the first transaction risk level is greater than the first predetermined threshold.

[0079] According to an embodiment of the present disclosure, the above-mentioned historical transaction information also includes risk control terminated transaction data, and the method also includes: when the transaction amount is greater than the second risk preset amount, and the number of risk control terminated transaction data is greater than the preset risk control terminated transaction number, the transaction risk is determined as the first transaction risk level, wherein the second preset risk amount is less than the first preset risk amount.

[0080] According to an embodiment of the present disclosure, the above-mentioned risk control suspension transaction data may be data on the number of times the target user triggered a risk control risk and had his transaction suspended.

[0081] For example, when the first preset risk amount is set to RMB 50,000, the second preset risk amount is set to RMB 30,000, and the usual transaction time period determined based on the historical transaction frequency is from 9 a.m. to 12 p.m., when the target user performs a transaction operation of RMB 60,000 at 5 p.m., the transaction operation can be considered an abnormal transaction operation, determined to be the first transaction risk level, and the transfer transaction can be controlled; when the target user's risk control terminated transaction data is 4 times, and the preset risk control terminated transaction number is 3, and the target user's transaction amount is RMB 40,000, the transaction can also be determined as the first transaction risk level, and the transfer transaction can be controlled.

[0082] According to an embodiment of the present disclosure, a second predetermined threshold is further set in the system, and the second predetermined threshold is smaller than the first predetermined threshold. When it is determined that the transaction risk level is greater than the second predetermined threshold but less than the first risk threshold, a voice prompt can be given to the target user, and the above voice prompt can be pre-entered by the first user; a third predetermined threshold can also be set in the system, and the third predetermined threshold is greater than the first predetermined threshold. When it is determined that the transaction risk level is greater than the third predetermined threshold, the transfer operation can be directly terminated.

[0083] According to the embodiment of the present disclosure, after the transaction operation is controlled, if the target user wants to continue the transaction, he or she may contact the relevant institution through the terminal and continue the above transaction operation after verification by the relevant personnel.

[0084] According to the embodiments of the present disclosure, by analyzing transaction information and historical transaction information to determine the transaction risk level, potential high-risk transactions can be identified, so that corresponding measures can be taken to control the transactions, and by considering the target users' usual time periods, more targeted risk management can be provided to reduce interference with normal transactions; by setting different risk levels and thresholds, the system can more accurately control transaction risks and improve transaction security.

[0085] Based on the above transaction instruction generation method, the present disclosure also provides a transaction instruction generation device. Figure 5 The device is described in detail.

[0086] Figure 5 The structural block diagram of the transaction instruction generating device according to the embodiment of the present disclosure is schematically shown.

[0087] like Figure 5 As shown, the transaction instruction generating device 500 of this embodiment includes an acquisition module 510 , a determination module 520 , a generation module 530 and a control module 540 .

[0088] The acquisition module 510 is used to obtain the pending transaction information and the historical transaction information of the target user in response to receiving the transaction operation of the target user. In one embodiment, the acquisition module 510 can be used to perform the operation S210 described above, which will not be repeated here.

[0089] The determination module 520 is used to determine the transaction risk level of the transaction operation based on the pending transaction information and the historical transaction information. In one embodiment, the determination module 520 can be used to perform the operation S220 described above, which will not be described in detail here.

[0090] The generation module 530 is used to generate a voice interaction question based on the transaction information when the transaction risk level is greater than the first predetermined threshold, wherein the voice interaction question is generated based on the voice corpus data entered by the first user, the first user and the target user have an association relationship, and the voice interaction question represents a question used to determine the reason for the transaction operation. In one embodiment, the generation module 530 can be used to perform the operation S230 described above, which will not be repeated here.

[0091] The control module 540 is used to generate a target instruction for controlling the transaction operation based on the reply information received from the target user to the voice interaction question. In one embodiment, the control module 540 can be used to perform the operation S240 described above, which will not be repeated here.

[0092] According to an embodiment of the present disclosure, the above-mentioned control module includes: an emotional state determination submodule, which is used to determine the emotional state of the above-mentioned target user based on the reply information of the above-mentioned voice interaction question; and a transaction control submodule, which is used to generate a target instruction for controlling the above-mentioned transaction operation when the above-mentioned emotional state is a preset emotional state.

[0093] According to an embodiment of the present disclosure, the above-mentioned emotional state determination submodule includes: a preprocessing unit, used to preprocess the above-mentioned reply information to obtain preprocessed reply information; a model input unit, used to input the above-mentioned preprocessed reply information into a trained emotion cause recognition model to obtain an emotion cause clause, and the above-mentioned emotion cause clause is the sub-voice data that causes emotional fluctuations in the above-mentioned preprocessed reply information; an emotional state determination unit, used to determine the emotional state of the above-mentioned target user based on the above-mentioned emotion cause clause.

[0094] According to an embodiment of the present disclosure, the above-mentioned generation module includes: a text interaction data generation sub-module, used to generate text interaction data based on a preset question and answer template and the above-mentioned transaction information; a model input sub-module, used to input the above-mentioned text interaction data into a speech synthesis model to obtain the above-mentioned speech interaction question, wherein the above-mentioned speech synthesis model is trained based on the speech corpus data of the above-mentioned first user.

[0095] According to an embodiment of the present disclosure, the above-mentioned device also includes: when the above-mentioned emotional state is a joyful state and the above-mentioned emotional reason words include a preset risk control text, controlling the above-mentioned transaction operation.

[0096] According to an embodiment of the present disclosure, the above-mentioned transaction information includes a transaction amount and a transaction time, the above-mentioned historical transaction information includes a historical transaction frequency, and the above-mentioned determination module includes: a habitual transaction time period determination submodule, used to determine the habitual transaction time period of the above-mentioned target user based on the above-mentioned historical transaction frequency; a transaction risk level determination submodule, used to determine the above-mentioned transaction risk level as a first transaction risk level when the above-mentioned transaction time is not within the habitual time period of the above-mentioned target user and the above-mentioned transaction amount is greater than a first preset risk amount, and the above-mentioned first transaction risk level is greater than the above-mentioned first predetermined threshold value.

[0097] According to an embodiment of the present disclosure, the above-mentioned historical transaction information also includes risk control terminated transaction data, and the above-mentioned device also includes: a second transaction risk level determination submodule, which is used to determine the above-mentioned transaction risk as the first transaction risk level when the above-mentioned transaction amount is greater than the second risk preset amount and the number of the above-mentioned risk control terminated transaction data is greater than the preset risk control terminated transaction number, wherein the above-mentioned second preset risk amount is less than the above-mentioned first preset risk amount.

[0098] According to an embodiment of the present disclosure, any multiple modules among the acquisition module 510, the determination module 520, the generation module 530 and the control module 540 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the acquisition module 510, the determination module 520, the generation module 530 and the control module 540 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation modes of software, hardware and firmware or in any appropriate combination of any of them. Alternatively, at least one of the acquisition module 510, the determination module 520, the generation module 530 and the control module 540 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be performed.

[0099] Figure 6 A block diagram of an electronic device suitable for implementing a transaction instruction generating method according to an embodiment of the present disclosure is schematically shown.

[0100] like Figure 6 As shown, the electronic device 600 according to an embodiment of the present disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 to a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include an onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0101] In RAM 603, various programs and data required for the operation of electronic device 600 are stored. Processor 601, ROM 602 and RAM 603 are connected to each other via bus 604. Processor 601 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 602 and / or RAM 603. It should be noted that the program can also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0102] According to an embodiment of the present disclosure, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to the bus 604. The electronic device 600 may further include one or more of the following components connected to the input / output (I / O) interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 608 including a hard disk, etc.; and a communication portion 609 including a network interface card such as a LAN card, a modem, etc. The communication portion 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output (I / O) interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage portion 608 as needed.

[0103] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0104] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, it may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 602 and / or RAM 603 described above and / or one or more memories other than ROM 602 and RAM 603.

[0105] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the transaction instruction generation method provided by the embodiment of the present disclosure.

[0106] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 601. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0107] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 609, and / or installed from a removable medium 611. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0108] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, apparatus, module, unit, etc. described above can be implemented by a computer program module.

[0109] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0110] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0111] It will be appreciated by those skilled in the art that the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations or combinations are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0112] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for generating a transaction instruction, characterized in that: The method comprises: In response to receiving a transaction operation of a target user, obtaining information to be traded and historical transaction information of the target user; Determining a transaction risk level of the transaction operation based on the pending transaction information and the historical transaction information; In the case where the transaction risk level is greater than a first predetermined threshold, generating a voice interaction question based on the pending transaction information, wherein the voice interaction question is generated based on voice corpus data input by a first user, the first user and the target user have an associated relationship, and the voice interaction question represents a question used to determine a reason for the transaction operation; In response to the received reply information of the target user to the voice interaction question, a target instruction for controlling the transaction operation is generated based on the reply information.

2. The method according to claim 1, characterized in that The step of generating a target instruction for controlling the transaction operation based on the response information received from the target user to the voice interaction question includes: Determining the emotional state of the target user based on the response information of the voice interaction question; In a case where the emotional state is a preset emotional state, a target instruction for controlling the transaction operation is generated.

3. The method according to claim 2, characterized in that The determining the emotional state of the target user based on the reply information of the voice interaction question includes: Preprocessing the reply information to obtain preprocessed reply information; Inputting the pre-processed reply information into a trained emotion cause recognition model to obtain an emotion cause clause, wherein the emotion cause clause is sub-voice data causing emotion fluctuations in the pre-processed reply information; An emotional state of the target user is determined based on the emotional reason clause.

4. The method according to claim 1, characterized in that: The generating of voice interaction questions based on the transaction information includes: Generate text interaction data based on a preset question and answer template and the transaction information; The text interaction data is input into a speech synthesis model to obtain the speech interaction problem, wherein the speech synthesis model is trained based on the speech corpus data of the first user.

5. The method according to claim 3, characterized in that: The method further comprises: When the emotional state is a joyful state and the emotional reason sentence includes a preset risk control text, the transaction operation is controlled.

6. The method according to claim 1, characterized in that The transaction information includes a transaction amount and a transaction time, the historical transaction information includes a historical transaction frequency, and determining the transaction risk level of the transaction operation based on the pending transaction information and the historical transaction information includes: Determining a customary transaction time period of the target user based on the historical transaction frequency; When the transaction time is not within the target user's usual time period and the transaction amount is greater than a first preset risk amount, the transaction risk level is determined to be a first transaction risk level, and the first transaction risk level is greater than the first predetermined threshold.

7. The method according to claim 6, characterized in that The historical transaction information also includes risk control aborted transaction data, and the method further includes: When the transaction amount is greater than the second preset risk amount and the number of risk control terminated transaction data is greater than the preset risk control terminated transaction number, the transaction risk is determined as the first transaction risk level, wherein the second preset risk amount is less than the first preset risk amount.

8. A transaction instruction generating device, characterized in that: The device comprises: An acquisition module, configured to acquire, in response to receiving a transaction operation of a target user, information to be traded and historical transaction information of the target user; A determination module, configured to determine a transaction risk level of the transaction operation based on the pending transaction information and the historical transaction information; a generating module, configured to generate a voice interaction question based on the to-be-transacted information when the transaction risk level is greater than a first predetermined threshold, wherein the voice interaction question is generated based on voice corpus data input by a first user, the first user and the target user are associated, and the voice interaction question represents a question for determining a reason for the transaction operation; The control module is used to respond to the received reply information of the target user to the voice interaction question and control the transaction operation based on the reply information.

9. An electronic device, comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images