CN117787994A - Transaction method and device based on intelligent teller machine, storage medium and electronic equipment - Google Patents

Abstract

The application discloses a transaction method, a device, a storage medium and electronic equipment based on an intelligent teller machine, wherein the method is applied to the field of artificial intelligence, the field of financial science and technology or other technical fields, and comprises the following steps: acquiring biological information of a target object through target equipment to obtain target biological information; the target biological information is sent to a virtual object, and the virtual object responds to an instruction triggered by the target object through a target artificial intelligent model; under the condition that the virtual object receives a target transaction instruction triggered by the target object, verifying the identity information of the target object through the target biological information to obtain a verification result; and carrying out transaction according to the target transaction instruction under the condition that the verification result indicates that verification is passed. According to the method and the device, the problem that the response speed of the intelligent teller machine is low when the intelligent teller machine which is arranged in a centralized mode in the related technology is communicated with and traded with a client is solved.

Description

Transaction method and device based on intelligent teller machine, storage medium and electronic equipment

Technical Field

The present application relates to the field of artificial intelligence, financial science and technology, or other technical fields, and in particular, to a transaction method, device, storage medium, and electronic apparatus based on an intelligent teller machine.

Background

With the development of virtual technology, the metauniverse technology gradually develops and matures, and more fields gradually start to use the metauniverse technology. Meta space (Metaverse) is a virtual, interconnected network space composed of multiple virtual worlds, is a highly interactive virtual world, and combines multiple technical means such as artificial intelligence, virtual reality technology, 3D drawing, cryptocurrency, etc. In the financial field, users can interact with other people in the virtual world through meta-universe techniques, create virtual assets, and experience various virtual scenes.

In the prior art, a financial institution maps a website teller in a meta universe through a virtual technology and a meta universe technology, and an avatar in the website teller machine interacts with a customer through an artificial intelligence algorithm or model. However, in the prior art, because the artificial intelligence algorithm or model deployed in each website teller machine is deployed in a centralized manner, the data received and collected by each website teller machine is required to be sent to a headquarter of a financial institution for calculation through a network, and then the calculated data is transmitted to each website teller machine through the network by the headquarter for display to a customer, so that the response rate of the teller machine in response to a customer instruction is low, and the customer experience is reduced.

Aiming at the problem that the response speed of the intelligent teller machine is slower when the intelligent teller machine is communicated and traded with a client through centralized deployment in the related technology, no effective solution is proposed at present.

Disclosure of Invention

The main purpose of the application is to provide a transaction method, a device, a storage medium and electronic equipment based on an intelligent teller machine, so as to solve the problem that the response speed of the intelligent teller machine is slower when the intelligent teller machine is communicated and transacted with a customer through centralized deployment in the related technology.

To achieve the above object, according to one aspect of the present application, there is provided a transaction method based on an intelligent teller machine, wherein the intelligent teller machine at least includes: the method comprises the steps of enabling target equipment and a virtual object, wherein the target equipment is wearable virtual reality equipment, and the virtual object is a three-dimensional model of a bank teller in a finger universe, and the method comprises the following steps: acquiring biological information of a target object through the target equipment to obtain target biological information; the target biological information is sent to the virtual object, wherein the virtual object responds to an instruction triggered by the target object through a target artificial intelligent model, and the target artificial intelligent model is an artificial intelligent model with a reduced code rear edge deployed in a preset teller machine; under the condition that the virtual object receives a target transaction instruction triggered by the target object, verifying the identity information of the target object through the target biological information to obtain a verification result; and under the condition that the verification result indicates that verification is passed, carrying out transaction according to the target transaction instruction.

Further, before the virtual object responds to the target object triggered instruction by the target artificial intelligence model, the method further comprises: replacing a data type in a preset artificial intelligent model with a preset data type to obtain a first artificial intelligent model, wherein the preset artificial intelligent model is used for generating reply information for responding to the target object according to the target biological information; removing redundant parameters and redundant network layers from the first artificial intelligent model through pruning technology to obtain a second artificial intelligent model; updating the preset artificial intelligent model by adopting the second artificial intelligent model to obtain the target artificial intelligent model; and deploying the target artificial intelligence model in the preset teller machine, wherein the preset teller machine is a teller machine of a banking website of a financial institution.

Further, the target biological information is voice information of the target object, and the instruction that the virtual object responds to the target object trigger through the target artificial intelligence model comprises: converting the voice information of the target object into text information through a voice recognition technology to obtain target text information; inputting the target text information into the target artificial intelligent model for calculation to obtain text reply information; converting the text reply information into voice information through the voice recognition technology to obtain voice reply information; responding to the command triggered by the target object according to the voice reply information.

Further, before the virtual object receives the target transaction instruction triggered by the target object, the method further comprises: receiving data information of the target object; inputting the data information of the target object into a preset recommendation model for calculation to obtain target recommendation information, wherein the preset recommendation model is used for generating recommendation information of financial products or financial services; and sending the target recommendation information to the target equipment.

Further, the target biological information is eye feature information of the target object, and the instructions for the virtual object to respond to the target object trigger through the target artificial intelligence model comprise: extracting an eyeball fixation point of the target object from the eye feature information of the target object; calculating the eyeball fixation point through a preset algorithm to obtain an interested coordinate of the target object, wherein the interested coordinate refers to a coordinate of an interested region of the target object in a meta universe; and after receiving the target recommendation information, displaying the target recommendation information on the interested coordinates so as to respond to the instruction triggered by the target object.

Further, verifying the identity information of the target object through the target biological information, and obtaining a verification result comprises: processing the eye feature information to obtain target iris information of the target object; acquiring preset iris information of the target object in a financial institution; and comparing the target iris information with the preset iris information to obtain the verification result.

Further, before sending the target biological information to the virtual object, the method further comprises: constructing a virtual three-dimensional model according to data information of a first object to obtain a target three-dimensional model, wherein the first object is a bank teller of a financial institution; and importing the target three-dimensional model into the meta universe by adopting a virtual reality technology, and configuring a preset interaction algorithm and a control algorithm for the target three-dimensional model to obtain the virtual object.

To achieve the above object, according to another aspect of the present application, there is provided a transaction apparatus based on an intelligent teller machine, including at least: target equipment and virtual object, wherein, target equipment is wearing formula virtual reality equipment, virtual object is the three-dimensional model of bank teller in the finger element universe, and the device includes: the acquisition unit is used for acquiring biological information of a target object through the target equipment to obtain target biological information; the response unit is used for sending the target biological information to the virtual object, wherein the virtual object responds to an instruction triggered by the target object through a target artificial intelligent model, and the target artificial intelligent model is an artificial intelligent model with a reduced code rear edge deployed in a preset teller machine; the verification unit is used for verifying the identity information of the target object through the target biological information under the condition that the virtual object receives a target transaction instruction triggered by the target object, so as to obtain a verification result; and the transaction unit is used for carrying out transaction according to the target transaction instruction under the condition that the verification result indicates that verification is passed.

Further, the apparatus further comprises: the replacing unit is used for replacing the data type in the preset artificial intelligent model by adopting the preset data type before the virtual object responds to the instruction triggered by the target object through the target artificial intelligent model to obtain a first artificial intelligent model, wherein the preset artificial intelligent model is used for generating reply information for responding to the target object according to the target biological information; the rejecting unit is used for rejecting the redundancy parameters and the redundancy network layer from the first artificial intelligent model through pruning technology to obtain a second artificial intelligent model; the updating unit is used for updating the preset artificial intelligent model by adopting the second artificial intelligent model to obtain the target artificial intelligent model; the deployment unit is used for deploying the target artificial intelligence model in the preset teller machine, wherein the preset teller machine is a teller machine of a banking website of a financial institution.

Further, the target biological information is voice information of the target object, and the response unit includes: the first conversion subunit is used for converting the voice information of the target object into text information through a voice recognition technology to obtain target text information; the first calculation subunit is used for inputting the target text information into the target artificial intelligent model for calculation to obtain text reply information; the second conversion subunit is used for converting the text reply information into voice information through the voice recognition technology to obtain voice reply information; and the response subunit is used for responding to the instruction triggered by the target object according to the voice reply information.

Further, the apparatus further comprises: the receiving unit is used for receiving the data information of the target object before the virtual object receives the target transaction instruction triggered by the target object; the computing unit is used for inputting the data information of the target object into a preset recommendation model for computing to obtain target recommendation information, wherein the preset recommendation model is used for generating recommendation information of financial products or financial services; and the sending unit is used for sending the target recommendation information to the target equipment.

Further, the target biological information is ocular feature information of the target subject, and the response unit includes: an extraction subunit, configured to extract an eye gaze point of the target object from eye feature information of the target object; the second calculation subunit is used for calculating the eyeball fixation point through a preset algorithm to obtain the interested coordinate of the target object, wherein the interested coordinate refers to the coordinate of the interested region of the target object in the universe; and the display subunit is used for displaying the target recommendation information on the interested coordinates after receiving the target recommendation information so as to respond to the instruction triggered by the target object.

Further, the verification unit includes: the processing subunit is used for processing the eye feature information to obtain target iris information of the target object; the acquisition subunit is used for acquiring preset iris information of the target object in a financial institution; and the comparison subunit is used for comparing the target iris information with the preset iris information to obtain the verification result.

Further, the apparatus further comprises: the construction unit is used for constructing a virtual three-dimensional model according to the data information of a first object before the target biological information is sent to the virtual object to obtain a target three-dimensional model, wherein the first object is a bank teller of a financial institution; the configuration unit is used for importing the target three-dimensional model into the meta universe by adopting a virtual reality technology, and configuring a preset interaction algorithm and a control algorithm for the target three-dimensional model to obtain the virtual object.

To achieve the above object, according to one aspect of the present application, there is provided a computer readable storage medium, including a stored computer program, wherein a device in which the computer readable storage medium is located is controlled to perform the transaction method based on the intelligent teller machine according to any one of the above when the computer program is run.

To achieve the above object, according to one aspect of the present application, there is provided an electronic device including one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement any one of the above-described smart teller machine-based transaction methods.

Through the application, the following steps are adopted: acquiring biological information of a target object through the target equipment to obtain target biological information; the target biological information is sent to the virtual object, wherein the virtual object responds to an instruction triggered by the target object through a target artificial intelligent model, and the target artificial intelligent model is an artificial intelligent model with a reduced code rear edge deployed in a preset teller machine; under the condition that the virtual object receives a target transaction instruction triggered by the target object, verifying the identity information of the target object through the target biological information to obtain a verification result; under the condition that the verification result indicates that verification is passed, the transaction is carried out according to the target transaction instruction, and the problem that the response speed of the intelligent teller machine is slower when the intelligent teller machine is communicated and transacted with a client through centralized deployment in the related technology is solved. The related codes of the artificial intelligence technology are reduced, the edge of the artificial intelligence model can be deployed into each website teller machine of the financial institution, the data volume required to be transmitted when each website teller machine responds to a client instruction is reduced, the response speed of the teller machine is improved, the working efficiency of a teller is improved, the client experience is improved, and meanwhile, the transaction safety of a client is improved by carrying out identity verification before the client transaction.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application, illustrate and explain the application and are not to be construed as limiting the application. In the drawings:

FIG. 1 is a flow chart of a transaction method based on a smart teller machine according to one embodiment of the present application;

FIG. 2 is a schematic diagram of an alternative intelligent teller machine-based transaction method provided in accordance with an embodiment of the present application;

fig. 3 is a schematic diagram of a transaction device based on a smart teller machine according to a second embodiment of the present application;

fig. 4 is a schematic diagram of a transaction electronic device based on an intelligent teller machine according to a fifth embodiment of the present application.

Detailed Description

It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

It should be noted that the processing method, the device, the storage medium, and the method and the device for determining electronic equipment of the present application may be used in the financial science and technology field in the interaction process of the website teller machine and the client, so that the response rate of the teller machine is improved, and may also be used in any field other than the financial science and technology field, where the application fields of the processing method, the device, the storage medium, and the method and the device for electronic equipment of the present application are not limited.

It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, user information stored by a financial institution, etc.) and the data (including, but not limited to, data used for analysis, stored data, displayed data, information related to a user stored by a financial institution, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the relevant laws and regulations and standards of the related area, and are provided with corresponding operation entries for the user to select authorization or rejection.

In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the present application described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

For convenience of description, the following will describe some terms or terms related to the embodiments of the present application:

super division of digital people: digital human superintegration is a virtual technology aimed at creating a digital version similar to a human in the real world. By using a large amount of data and algorithms, a digital person can mimic the characteristics of a human in terms of language, behavior, appearance, emotion, etc., forming a virtual individual that is nearly identical to a human. Super-splitting means that the digital person can be duplicated into multiple entities to accomplish different tasks.

Meta universe: meta space (Metaverse) is a virtual, interconnected network space composed of multiple virtual worlds, is a highly interactive virtual world, and combines multiple technical means such as artificial intelligence, virtual reality technology, 3D drawing, cryptocurrency, etc. Through meta-universe technology, users can interact with other people in the virtual world, create virtual assets, and experience various virtual scenes.

Example 1

The invention will be described with reference to preferred implementation steps, and fig. 1 is a flowchart of a transaction method based on a smart teller machine according to an embodiment of the present application, and as shown in fig. 1, the method includes the following steps:

Step S101, acquiring biological information of a target object through target equipment to obtain target biological information.

In the first embodiment, in order to interact with a customer (i.e., the target object described above), it is necessary to collect target biometric information of the customer by a target device configured in the intelligent teller machine, so that friendly interaction with the customer is achieved by performing analysis processing on the target biometric information. The intelligent teller machine is deployed in each website of the financial institution and interacts with the customer by adopting an artificial intelligence technology. The target device refers to a wearable virtual reality device, such as a virtual reality helmet. Biological information of the target object, such as voice information, eye feature information, etc., can be acquired by a built-in sensor of the target device.

Step S102, the target biological information is sent to the virtual object, wherein the virtual object responds to an instruction triggered by the target object through a target artificial intelligent model, and the target artificial intelligent model is an artificial intelligent model with a reduced code rear edge deployed in a preset teller machine.

After the target biological information is collected in the first embodiment, interaction with the client is completed through the virtual object, that is, a client-triggered instruction, for example, a client-triggered communication instruction, a transaction instruction, and the like, is responded. The virtual object refers to super-splitting of digital people of a financial institution website teller, and the virtual object can answer questions posed by clients through a target artificial intelligence model.

Step S103, under the condition that the virtual object receives a target transaction instruction triggered by the target object, verifying the identity information of the target object through the target biological information to obtain a verification result.

In the first embodiment, when a customer needs to conduct a transaction, the target biometric information of the customer can be verified, and the identity of the customer is identified, for example, fingerprint verification, voiceprint verification, password verification, iris verification, etc., so as to obtain a verification result, if the collected target biometric information is consistent with the biometric information retained in the financial institution, the verification result is confirmed to be passed, and if the collected target biometric information is inconsistent with the biometric information retained in the financial institution, the verification result is confirmed to be failed.

Step S104, when the verification result indicates that the verification is passed, the transaction is carried out according to the target transaction instruction.

In the first embodiment, when the verification result is that the verification is passed, the transaction instruction initiated by the client is allowed to be executed continuously, and the target transaction instruction triggered by the client is executed and completed, so as to ensure that the client carries out safe transaction and avoid property loss.

In summary, in the transaction method based on the intelligent teller machine provided in the first embodiment of the present application, the target device collects the biological information of the target object to obtain the target biological information; the method comprises the steps of sending target biological information to a virtual object, wherein the virtual object responds to an instruction triggered by the target object through a target artificial intelligent model, and the target artificial intelligent model is an artificial intelligent model with a reduced code rear edge deployed in a preset teller machine; under the condition that the virtual object receives a target transaction instruction triggered by the target object, verifying the identity information of the target object through the target biological information to obtain a verification result; under the condition that the verification result indicates that verification is passed, the transaction is carried out according to the target transaction instruction, and the problem that the response speed of the intelligent teller machine is lower when the intelligent teller machine is communicated with and transacted with a client through centralized deployment in the related technology is solved. The related codes of the artificial intelligence technology are reduced, the edge of the artificial intelligence model can be deployed into each website teller machine of the financial institution, the data volume required to be transmitted when each website teller machine responds to a client instruction is reduced, the response speed of the teller machine is improved, the working efficiency of a teller is improved, the client experience is improved, and meanwhile, the transaction safety of a client is improved by carrying out identity verification before the client transaction.

Optionally, in the transaction method based on the intelligent teller machine according to the first embodiment of the present application, before the virtual object responds to the instruction triggered by the target object through the target artificial intelligence model, the method further includes: replacing a data type in a preset artificial intelligent model with a preset data type to obtain a first artificial intelligent model, wherein the preset artificial intelligent model is used for generating reply information for responding to a target object according to target biological information; removing redundant parameters and redundant network layers from the first artificial intelligent model through pruning technology to obtain a second artificial intelligent model; updating a preset artificial intelligent model by adopting a second artificial intelligent model to obtain a target artificial intelligent model; the target artificial intelligence model is deployed in a preset teller machine, wherein the preset teller machine is a teller machine of a banking website of a financial institution.

In the prior art, a target artificial intelligence model for interacting with clients is mostly arranged in a financial institution headquarter in a centralized way, and the teller machines of all the websites carry out data transmission with the target artificial intelligence model of the headquarter through a network, so that the response speed of the teller machines of all the websites is low. In the first embodiment, in order to reduce network transmission and improve response efficiency, the target artificial intelligent model may be compressed by technical means such as quantization and pruning, so as to implement deployment of the target artificial intelligent model at each website teller machine terminal at the edge side, avoid tedious operations during data transmission, and improve response speed.

Specifically, a low-precision data type (namely the preset data type) is adopted to replace the data type in the preset artificial intelligent model, so that a first artificial intelligent model is obtained. A low precision data type refers to a data type, e.g., an integer type, that uses a smaller number of bits to represent data. In deep learning, 32-bit or 64-bit floating point numbers are typically used to represent model parameters and intermediate computation results, while low-precision data types may use fewer numbers of bits to represent data, thereby reducing storage space and computing resource consumption. The preset artificial intelligent model is a model which is trained in advance and interacted with a client, can receive voice information and eye characteristic information (namely target biological information) of the client, and generates reply information for replying the client to broadcast to the client or display to the client through virtual reality equipment.

And then removing redundant parameters and layers in the first artificial intelligent model through pruning technology to obtain a second artificial intelligent model. Pruning techniques achieve further compression of the size and computational complexity of the first artificial intelligence model by evaluating the importance of the weight parameters and network layers (e.g., convolutional layers) in the first artificial intelligence model, and then deleting the weight parameters and network layers of lower importance. At this time, whether the model parameter file size of the second artificial intelligent model is deployed in a website teller machine or not can be evaluated, for example, if the model parameter file is smaller than 4G, it is confirmed that the second artificial intelligent model can be operated on the internal memory of the teller machine terminal; meanwhile, whether the computing resources of the automatic teller machine meet the operation requirements can be evaluated, for example, hardware resources used by the automatic teller machine terminal are relatively deficient, a high-performance GPU display card is not available, and the model pruning processing supports the CPU operation through the two-core four-wire process (Two Cores Four Threads,2C 4T).

And finally, updating a preset artificial intelligent model by adopting a second artificial intelligent model to obtain a target artificial intelligent model, converting the target artificial intelligent model into machine learning compiling codes which can be operated on the edge-side teller machine terminals, and deploying the compiled machine learning codes on all the teller machine terminals at the edge side of the financial institution so as to infer and predict.

The size and the computational complexity of the preset artificial intelligent model are reduced to the level acceptable by the terminal of the edge side teller machine by using the technical means of low-precision data type replacement, pruning and the like, so that the network transmission quantity and the network bandwidth cost are reduced, the response efficiency is improved, and the effect of improving the customer experience is achieved.

Optionally, in the transaction method based on the intelligent teller machine according to the first embodiment of the present application, the target biometric information is voice information of a target object, and the instruction that the virtual object triggers by responding to the target object through the target artificial intelligence model includes: converting the voice information of the target object into text information through a voice recognition technology to obtain target text information; inputting the target text information into a target artificial intelligent model for calculation to obtain text reply information; converting the text reply information into voice information through a voice recognition technology to obtain voice reply information; responding to the command triggered by the target object according to the voice reply information.

In the first embodiment, in order to perform friendly interaction with a client, the target device may collect the voice information of the client (i.e. the target object) as target biological information, then identify the voice information output by the client through a voice recognition technology, obtain target text information, generate text reply information of the target text information through a target artificial intelligent model, and finally convert the text reply information into audio data, i.e. the voice reply information is broadcasted to the client, respond to the voice information output by the client, i.e. respond to a voice interaction instruction sent by the client, and complete the interaction with the client. The voice information of the client is converted into the target text information in a text form through the voice recognition technology, the transaction intention, the transaction information input and the like of the client can be recognized, the client requirement can be better known, meanwhile, the reply information is generated through the target artificial intelligence model, the problem raised by the client can be responded in time, the working efficiency is improved, friendly interaction with the client is completed, and the client experience is improved.

Optionally, in the transaction method based on the intelligent teller machine according to the first embodiment of the present application, before the virtual object receives the target transaction instruction triggered by the target object, the method further includes: receiving data information of a target object; inputting the data information of the target object into a preset recommendation model for calculation to obtain target recommendation information, wherein the preset recommendation model is used for generating recommendation information of financial products or financial services; and sending the target recommendation information to the target equipment.

In the first embodiment, personalized services can be developed in combination with personalized information such as occupation, income, age, and the like, which are reserved in a financial institution by a customer. Specifically, related data information stored in a financial institution by a customer is acquired and received, past transaction records, customer demands, consumption characteristics and the like of the customer are integrated through a preset recommendation model, and target recommendation information for the customer is generated, so that a function of pushing related services meeting the demands of the user is realized. By inputting the data information of the client into the preset recommendation model, personalized recommendation service can be provided for the client, and the experience of the client is improved.

Optionally, in the transaction method based on the intelligent teller machine according to the first embodiment of the present application, the target biometric information is eye feature information of a target object, and the instruction that the virtual object triggers by responding to the target object through the target artificial intelligent model includes: extracting an eyeball fixation point of a target object from eye feature information of the target object; calculating an eyeball fixation point through a preset algorithm to obtain an interested coordinate of a target object, wherein the interested coordinate refers to a coordinate of an interested region of the target object in a meta universe; and after receiving the target recommendation information, displaying the target recommendation information on the interested coordinates to respond to the instruction triggered by the target object.

In the first embodiment, when the customer speaks the financial product or the financial service of interest to the customer or after the target recommendation information for the customer is generated, the financial product, the financial service or the target recommendation information can be presented to the customer through the target device in response to the interactive instruction issued by the customer.

Specifically, the movement direction of the eye mind of the customer can be recorded through the built-in sensor of the virtual reality helmet (namely the target equipment) worn by the customer, the eye feature information of the customer is collected, and the gazing position of the eyeballs of the customer, namely the eyepoint of gaze, is collected and extracted according to the eye feature information of the customer; then, calculating coordinates of an interested region of the client in the virtual universe by adopting a preset algorithm to obtain the interested coordinates; finally, target recommendation information generated by the financial products, financial services or preset recommendation models of interest of the clients is displayed at the positions of the coordinates of interest, so that the clients can see the target recommendation information.

By capturing the eye gaze point of the customer and calculating the interested coordinates of the customer, the information of the recommendation of the financial products, financial services or targets can be displayed to the customer, so that the interaction with the customer is facilitated, and the experience of the customer is improved.

Optionally, in the transaction method based on the intelligent teller machine provided in the first embodiment of the present application, verifying the identity information of the target object through the target biometric information, and obtaining the verification result includes: processing the eye feature information to obtain target iris information of a target object; acquiring preset iris information of a target object in a financial institution; and comparing the target iris information with preset iris information to obtain a verification result.

In the first embodiment, after a customer issues a transaction instruction (for example, a login instruction, a transfer instruction, a fund purchase instruction, etc.), eye feature information of the customer can be obtained through a target device, iris information of the customer is extracted to obtain target iris information, and then the iris technology is used for identifying with preset iris information of the customer which is reserved in a financial institution. Identity authentication is performed through iris recognition, so that the safety and convenience of customer transaction are improved.

Optionally, in the transaction method based on the intelligent teller machine according to the first embodiment of the present application, before the target biometric information is sent to the virtual object, the method further includes: constructing a virtual three-dimensional model according to the data information of a first object to obtain a target three-dimensional model, wherein the first object refers to a bank teller of a financial institution; and importing the target three-dimensional model into the meta universe by adopting a virtual reality technology, and configuring a preset interaction algorithm and a control algorithm for the target three-dimensional model to obtain the virtual object.

In the first embodiment, the virtual object refers to super-personal digital corresponding to a website teller in the financial institution. The super-body of the digital person is a virtual person which utilizes a deep neural network to carry out image synthesis and is highly simulated, and is a kind of digital body. The method has high-efficiency content output and content production capacity, can quickly reproduce the image of the real person, and can highly restore the looks, expressions and behaviors of the person. The virtual objects can communicate with the client in the meta universe to navigate the client, for example, introduce and display various business scenes. The virtual objects can correspond to the network point teller in the meta-universe one by one, simulate the way that the teller provides service for the client in the real scene, and guide the client to perform relevant business operation.

Specifically, three-dimensional modeling software may be employed to construct a virtual three-dimensional model of the teller (i.e., the target three-dimensional model described above); then, a virtual reality technology is adopted to import the target three-dimensional model into the meta universe, and corresponding action voices (namely the preset interaction algorithm and the control algorithm) are configured for the target three-dimensional model, so that a virtual object corresponding to the teller is constructed.

By constructing a virtual three-dimensional model of a teller and mapping the three-dimensional model into a virtual universe by adopting a virtual reality technology, interaction between a virtual object and a client can be realized, the time of the teller is saved, and the effect of improving the working efficiency is achieved.

Optionally, in the first embodiment, the flow of the interaction between the scheme and the customer through the intelligent teller machine may be as shown in fig. 2, and first, the customer needs to wear the virtual reality helmet; then, the client interacts with a virtual object corresponding to a website teller in the meta universe, the virtual object generates reply information for replying to the client through a target artificial intelligent model, performs voice interaction and eye interaction with the client, and responds to an instruction sent by the client; finally, before receiving the transaction instruction sent by the client, verifying the identity information of the client through iris technology, and executing the transaction instruction of the client under the condition that the identity information passes verification.

It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.

Example two

The second embodiment of the present application also provides a transaction device based on an intelligent teller machine, and it should be noted that the transaction device based on an intelligent teller machine in the second embodiment of the present application may be used to execute the transaction method based on an intelligent teller machine provided in the first embodiment of the present application. The following describes a transaction device based on an intelligent teller machine according to a second embodiment of the present application.

Fig. 3 is a schematic diagram of a transaction device based on a smart teller machine according to a second embodiment of the present application. As shown in fig. 3, the apparatus includes: an acquisition unit 301, a response unit 302, a verification unit 303 and a transaction unit 304.

Specifically, the acquisition unit 301 is configured to acquire biological information of a target object through a target device, so as to obtain target biological information.

And a response unit 302, configured to send the target biological information to the virtual object, where the virtual object responds to the instruction triggered by the target object through a target artificial intelligent model, and the target artificial intelligent model is an artificial intelligent model with a reduced code trailing edge deployed in a preset teller machine.

And the verification unit 303 is configured to verify the identity information of the target object through the target biological information to obtain a verification result when the virtual object receives the target transaction instruction triggered by the target object.

And a transaction unit 304, configured to perform a transaction according to the target transaction instruction if the verification result indicates that verification is passed.

According to the transaction device based on the intelligent teller machine provided by the second embodiment of the present application, the collection unit 301 collects the biological information of the target object through the target device, so as to obtain the target biological information; the response unit 302 sends the target biological information to the virtual object, wherein the virtual object responds to an instruction triggered by the target object through a target artificial intelligent model, and the target artificial intelligent model is an artificial intelligent model with a reduced code rear edge deployed in a preset teller machine; the verification unit 303 verifies the identity information of the target object through the target biological information under the condition that the virtual object receives the target transaction instruction triggered by the target object, so as to obtain a verification result; the transaction unit 304 performs a transaction according to the target transaction instruction when the verification result indicates that the verification is passed, so that the problem of slow response speed of the intelligent teller machine when the intelligent teller machine is communicated with and transacted with the client through the intelligent teller machine which is intensively deployed in the related art is solved. The related codes of the artificial intelligence technology are reduced, the edge of the artificial intelligence model can be deployed into each website teller machine of the financial institution, the data volume required to be transmitted when each website teller machine responds to a client instruction is reduced, the response speed of the teller machine is improved, the working efficiency of a teller is improved, the client experience is improved, and meanwhile, the transaction safety of a client is improved by carrying out identity verification before the client transaction.

Optionally, in the transaction device based on an intelligent teller machine according to the second embodiment of the present application, the device further includes: the replacing unit is used for replacing the data type in the preset artificial intelligent model by adopting the preset data type before the virtual object responds to the instruction triggered by the target object through the target artificial intelligent model to obtain a first artificial intelligent model, wherein the preset artificial intelligent model is used for generating reply information for responding to the target object according to the target biological information; the rejecting unit is used for rejecting redundant parameters and redundant network layers from the first artificial intelligent model through pruning technology to obtain a second artificial intelligent model; the updating unit is used for updating the preset artificial intelligent model by adopting the second artificial intelligent model to obtain a target artificial intelligent model; the deployment unit is used for deploying the target artificial intelligent model in a preset teller machine, wherein the preset teller machine is a teller machine of a banking website of a financial institution.

Optionally, in the transaction device based on an intelligent teller machine according to the second embodiment of the present application, the target biometric information is voice information of a target object, and the response unit 302 includes: the first conversion subunit is used for converting the voice information of the target object into text information through a voice recognition technology to obtain target text information; the first calculation subunit is used for inputting the target text information into the target artificial intelligent model for calculation to obtain text reply information; the second conversion subunit is used for converting the text reply information into voice information through a voice recognition technology to obtain voice reply information; and the response subunit is used for responding to the instruction triggered by the target object according to the voice reply information.

Optionally, in the transaction device based on an intelligent teller machine according to the second embodiment of the present application, the device further includes: the receiving unit is used for receiving the data information of the target object before the virtual object receives the target transaction instruction triggered by the target object; the computing unit is used for inputting the data information of the target object into a preset recommendation model for computing to obtain target recommendation information, wherein the preset recommendation model is used for generating recommendation information of financial products or financial services; and the sending unit is used for sending the target recommendation information to the target equipment.

Optionally, in the transaction device based on the intelligent teller machine according to the second embodiment of the present application, the target biometric information is eye feature information of the target object, and the response unit 302 includes: an extraction subunit, configured to extract an eye gaze point of the target object from the eye feature information of the target object; the second calculation subunit is used for calculating the eye gaze point through a preset algorithm to obtain the interested coordinate of the target object, wherein the interested coordinate refers to the coordinate of the interested region of the target object in the universe; and the display subunit is used for displaying the target recommendation information on the interested coordinates after receiving the target recommendation information so as to respond to the instruction triggered by the target object.

Optionally, in the transaction device based on an intelligent teller machine according to the second embodiment of the present application, the verification unit 303 includes: the processing subunit is used for processing the eye feature information to obtain target iris information of a target object; the acquisition subunit is used for acquiring preset iris information of the target object in the financial institution; and the comparison subunit is used for comparing the target iris information with preset iris information to obtain a verification result.

Optionally, in the transaction device based on an intelligent teller machine according to the second embodiment of the present application, the device further includes: the construction unit is used for constructing a virtual three-dimensional model according to the data information of a first object before sending the target biological information to the virtual object to obtain a target three-dimensional model, wherein the first object refers to a bank teller of a financial institution; the configuration unit is used for importing the target three-dimensional model into the meta universe by adopting a virtual reality technology, and configuring a preset interaction algorithm and a control algorithm for the target three-dimensional model to obtain the virtual object.

The transaction device based on the intelligent teller machine comprises a processor and a memory, wherein the acquisition unit 301, the response unit 302, the verification unit 303, the transaction unit 304 and the like are all stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.

The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more than one, and the response rate of the teller machine is improved by adjusting kernel parameters.

The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.

A third embodiment of the present invention provides a computer-readable storage medium having a program stored thereon, which when executed by a processor, implements a transaction method based on an intelligent teller machine.

The fourth embodiment of the invention provides a processor, which is used for running a program, wherein the program runs to execute a transaction method based on an intelligent teller machine.

As shown in fig. 4, a fifth embodiment of the present invention provides an electronic device, where the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the following steps when executing the program: acquiring biological information of a target object through target equipment to obtain target biological information; the method comprises the steps of sending target biological information to a virtual object, wherein the virtual object responds to an instruction triggered by the target object through a target artificial intelligent model, and the target artificial intelligent model is an artificial intelligent model with a reduced code rear edge deployed in a preset teller machine; under the condition that the virtual object receives a target transaction instruction triggered by the target object, verifying the identity information of the target object through the target biological information to obtain a verification result; and carrying out transaction according to the target transaction instruction under the condition that the verification result indicates that verification is passed.

The processor also realizes the following steps when executing the program: before the virtual object responds to the instruction triggered by the target object through the target artificial intelligence model, the method further comprises the following steps: replacing a data type in a preset artificial intelligent model with a preset data type to obtain a first artificial intelligent model, wherein the preset artificial intelligent model is used for generating reply information for responding to a target object according to target biological information; removing redundant parameters and redundant network layers from the first artificial intelligent model through pruning technology to obtain a second artificial intelligent model; updating a preset artificial intelligent model by adopting a second artificial intelligent model to obtain a target artificial intelligent model; the target artificial intelligence model is deployed in a preset teller machine, wherein the preset teller machine is a teller machine of a banking website of a financial institution.

The processor also realizes the following steps when executing the program: the target biological information is voice information of a target object, and the instruction of the virtual object to respond to the target object trigger through the target artificial intelligent model comprises the following steps: converting the voice information of the target object into text information through a voice recognition technology to obtain target text information; inputting the target text information into a target artificial intelligent model for calculation to obtain text reply information; converting the text reply information into voice information through a voice recognition technology to obtain voice reply information; responding to the command triggered by the target object according to the voice reply information.

The processor also realizes the following steps when executing the program: before the virtual object receives the target transaction instruction triggered by the target object, the method further comprises the following steps: receiving data information of a target object; inputting the data information of the target object into a preset recommendation model for calculation to obtain target recommendation information, wherein the preset recommendation model is used for generating recommendation information of financial products or financial services; and sending the target recommendation information to the target equipment.

The processor also realizes the following steps when executing the program: the target biological information is eye feature information of a target object, and the instruction of the virtual object to respond to the target object trigger through the target artificial intelligent model comprises the following steps: extracting an eyeball fixation point of a target object from eye feature information of the target object; calculating an eyeball fixation point through a preset algorithm to obtain an interested coordinate of a target object, wherein the interested coordinate refers to a coordinate of an interested region of the target object in a meta universe; and after receiving the target recommendation information, displaying the target recommendation information on the interested coordinates to respond to the instruction triggered by the target object.

The processor also realizes the following steps when executing the program: verifying the identity information of the target object through the target biological information, wherein the obtaining of the verification result comprises the following steps: processing the eye feature information to obtain target iris information of a target object; acquiring preset iris information of a target object in a financial institution; and comparing the target iris information with preset iris information to obtain a verification result.

The processor also realizes the following steps when executing the program: the method further comprises, before sending the target biological information to the virtual object: constructing a virtual three-dimensional model according to the data information of a first object to obtain a target three-dimensional model, wherein the first object refers to a bank teller of a financial institution; and importing the target three-dimensional model into the meta universe by adopting a virtual reality technology, and configuring a preset interaction algorithm and a control algorithm for the target three-dimensional model to obtain the virtual object.

The device herein may be a server, PC, PAD, cell phone, etc.

The present application also provides a computer program product adapted to perform, when executed on a data processing device, a program initialized with the method steps of: acquiring biological information of a target object through target equipment to obtain target biological information; the method comprises the steps of sending target biological information to a virtual object, wherein the virtual object responds to an instruction triggered by the target object through a target artificial intelligent model, and the target artificial intelligent model is an artificial intelligent model with a reduced code rear edge deployed in a preset teller machine; under the condition that the virtual object receives a target transaction instruction triggered by the target object, verifying the identity information of the target object through the target biological information to obtain a verification result; and carrying out transaction according to the target transaction instruction under the condition that the verification result indicates that verification is passed.

When executed on a data processing device, is further adapted to carry out a program initialized with the method steps of: before the virtual object responds to the instruction triggered by the target object through the target artificial intelligence model, the method further comprises the following steps: replacing a data type in a preset artificial intelligent model with a preset data type to obtain a first artificial intelligent model, wherein the preset artificial intelligent model is used for generating reply information for responding to a target object according to target biological information; removing redundant parameters and redundant network layers from the first artificial intelligent model through pruning technology to obtain a second artificial intelligent model; updating a preset artificial intelligent model by adopting a second artificial intelligent model to obtain a target artificial intelligent model; the target artificial intelligence model is deployed in a preset teller machine, wherein the preset teller machine is a teller machine of a banking website of a financial institution.

When executed on a data processing device, is further adapted to carry out a program initialized with the method steps of: the target biological information is voice information of a target object, and the instruction of the virtual object to respond to the target object trigger through the target artificial intelligent model comprises the following steps: converting the voice information of the target object into text information through a voice recognition technology to obtain target text information; inputting the target text information into a target artificial intelligent model for calculation to obtain text reply information; converting the text reply information into voice information through a voice recognition technology to obtain voice reply information; responding to the command triggered by the target object according to the voice reply information.

When executed on a data processing device, is further adapted to carry out a program initialized with the method steps of: before the virtual object receives the target transaction instruction triggered by the target object, the method further comprises the following steps: receiving data information of a target object; inputting the data information of the target object into a preset recommendation model for calculation to obtain target recommendation information, wherein the preset recommendation model is used for generating recommendation information of financial products or financial services; and sending the target recommendation information to the target equipment.

When executed on a data processing device, is further adapted to carry out a program initialized with the method steps of: the target biological information is eye feature information of a target object, and the instruction of the virtual object to respond to the target object trigger through the target artificial intelligent model comprises the following steps: extracting an eyeball fixation point of a target object from eye feature information of the target object; calculating an eyeball fixation point through a preset algorithm to obtain an interested coordinate of a target object, wherein the interested coordinate refers to a coordinate of an interested region of the target object in a meta universe; and after receiving the target recommendation information, displaying the target recommendation information on the interested coordinates to respond to the instruction triggered by the target object.

When executed on a data processing device, is further adapted to carry out a program initialized with the method steps of: verifying the identity information of the target object through the target biological information, wherein the obtaining of the verification result comprises the following steps: processing the eye feature information to obtain target iris information of a target object; acquiring preset iris information of a target object in a financial institution; and comparing the target iris information with preset iris information to obtain a verification result.

When executed on a data processing device, is further adapted to carry out a program initialized with the method steps of: the method further comprises, before sending the target biological information to the virtual object: constructing a virtual three-dimensional model according to the data information of a first object to obtain a target three-dimensional model, wherein the first object refers to a bank teller of a financial institution; and importing the target three-dimensional model into the meta universe by adopting a virtual reality technology, and configuring a preset interaction algorithm and a control algorithm for the target three-dimensional model to obtain the virtual object.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims (10)

1. The transaction method based on the intelligent teller machine is characterized in that the intelligent teller machine at least comprises the following steps: target equipment and virtual object, wherein, target equipment is wearing formula virtual reality equipment, virtual object is the three-dimensional model of bank teller in the finger element universe, includes:

acquiring biological information of a target object through the target equipment to obtain target biological information;

the target biological information is sent to the virtual object, wherein the virtual object responds to an instruction triggered by the target object through a target artificial intelligent model, and the target artificial intelligent model is an artificial intelligent model with a reduced code rear edge deployed in a preset teller machine;

under the condition that the virtual object receives a target transaction instruction triggered by the target object, verifying the identity information of the target object through the target biological information to obtain a verification result;

and under the condition that the verification result indicates that verification is passed, carrying out transaction according to the target transaction instruction.

2. The method of claim 1, wherein prior to the virtual object responding to the target object triggered instruction by the target artificial intelligence model, the method further comprises:

Replacing a data type in a preset artificial intelligent model with a preset data type to obtain a first artificial intelligent model, wherein the preset artificial intelligent model is used for generating reply information for responding to the target object according to the target biological information;

removing redundant parameters and redundant network layers from the first artificial intelligent model through pruning technology to obtain a second artificial intelligent model;

updating the preset artificial intelligent model by adopting the second artificial intelligent model to obtain the target artificial intelligent model;

and deploying the target artificial intelligence model in the preset teller machine, wherein the preset teller machine is a teller machine of a banking website of a financial institution.

3. The method of claim 1, wherein the target biometric information is voice information of the target object, and wherein the instructions for the virtual object to respond to the target object trigger by the target artificial intelligence model comprise:

converting the voice information of the target object into text information through a voice recognition technology to obtain target text information;

inputting the target text information into the target artificial intelligent model for calculation to obtain text reply information;

Converting the text reply information into voice information through the voice recognition technology to obtain voice reply information;

responding to the command triggered by the target object according to the voice reply information.

4. The method of claim 1, wherein prior to the virtual object receiving the target transaction instruction triggered by the target object, the method further comprises:

receiving data information of the target object;

inputting the data information of the target object into a preset recommendation model for calculation to obtain target recommendation information, wherein the preset recommendation model is used for generating recommendation information of financial products or financial services;

and sending the target recommendation information to the target equipment.

5. The method of claim 4, wherein the target biometric information is ocular feature information of the target subject, and wherein the instructions by which the virtual subject responds to the target subject trigger by the target artificial intelligence model comprise:

extracting an eyeball fixation point of the target object from the eye feature information of the target object;

calculating the eyeball fixation point through a preset algorithm to obtain an interested coordinate of the target object, wherein the interested coordinate refers to a coordinate of an interested region of the target object in a meta universe;

And after receiving the target recommendation information, displaying the target recommendation information on the interested coordinates so as to respond to the instruction triggered by the target object.

6. The method of claim 5, wherein verifying the identity information of the target object with the target biometric information comprises:

processing the eye feature information to obtain target iris information of the target object;

acquiring preset iris information of the target object in a financial institution;

and comparing the target iris information with the preset iris information to obtain the verification result.

7. The method of claim 1, wherein prior to transmitting the target biological information to the virtual object, the method further comprises:

constructing a virtual three-dimensional model according to data information of a first object to obtain a target three-dimensional model, wherein the first object is a bank teller of a financial institution;

and importing the target three-dimensional model into the meta universe by adopting a virtual reality technology, and configuring a preset interaction algorithm and a control algorithm for the target three-dimensional model to obtain the virtual object.

8. A transaction device based on an intelligent teller machine, comprising:

the acquisition unit is used for acquiring biological information of a target object through the target equipment to obtain target biological information;

the response unit is used for sending the target biological information to the virtual object, wherein the virtual object responds to an instruction triggered by the target object through a target artificial intelligent model, and the target artificial intelligent model is an artificial intelligent model with a reduced code rear edge deployed in a preset teller machine;

the verification unit is used for verifying the identity information of the target object through the target biological information under the condition that the virtual object receives a target transaction instruction triggered by the target object, so as to obtain a verification result;

and the transaction unit is used for carrying out transaction according to the target transaction instruction under the condition that the verification result indicates that verification is passed.

9. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored computer program, wherein the computer program, when run, controls a device in which the computer readable storage medium is located to perform the intelligent teller machine based transaction method according to any of claims 1 to 7.

10. An electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the intelligent teller machine-based transaction method of any of claims 1-7.