Automatic business handling method, device and equipment and storage medium

Abstract

The invention discloses an automatic business handling method and device, equipment and a storage medium. The method comprises the following steps: acquiring historical business handling information of a user on different types of equipment; performing optimization learning training on the large language model based on the historical business handling information to obtain a target large language model, and deploying the target large language model to the autonomous business handling equipment; and obtaining a current user service handling operation, and generating current operation guide information corresponding to the current user service handling operation based on the current user service handling operation and the target large language model so as to guide the user to handle the service. According to the embodiment of the invention, the user is guided to handle the business by acquiring the operation for handling the business, generating the operation guide information corresponding to the business handling operation based on the target large language model and interacting with the user in the interaction area, so that the problem that the business handling needs to be guided by manual intervention can be solved; the business handling efficiency and accuracy are improved, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automated business processing, and in particular to an automated business processing method, device, equipment and storage medium. Background Art

[0002] With the development of intelligence, more and more users hope to realize the self-service handling of business online or based on autonomous business handling equipment. At present, although there are corresponding self-service handling equipment, the equipment still needs to intervene in the user to know how to handle the business, that is, there are many businesses that can be handled on the existing autonomous equipment or terminal display interface, but it is not clear what content on the display interface needs to be triggered for a specific business, that is, it is necessary to try to trigger different controls many times to determine whether the business you want to handle can be completed. There are problems such as unchanged business handling, low automation, low business handling efficiency and poor user experience. In addition, based on the staff guiding users to handle the corresponding business on the autonomous equipment according to customer needs, there is a need for manual labor in the process of handling, and there is a problem of high labor costs. Summary of the invention

[0003] In view of this, the present invention provides an automated business processing method, device, equipment and storage medium, which can solve the problem in the prior art that manual intervention is required to guide users in handling business, improve the efficiency and accuracy of business processing, and thus improve the user experience.

[0004] According to one aspect of the present invention, an embodiment of the present invention provides an automated service handling method, the method comprising:

[0005] Obtain the user's historical business handling information on different types of devices;

[0006] Based on the historical business handling information, the large language model is optimized and trained to obtain a trained target large language model, and the target large language model is deployed to the autonomous business handling device; wherein the target large language model is a large language model that can guide business handling;

[0007] The current user business handling operation is obtained, and based on the current user business handling operation and the target large language model, current operation guidance information corresponding to the current user business handling operation is generated in the interactive area to guide the user to handle business.

[0008] According to another aspect of the present invention, an embodiment of the present invention further provides an automated service processing device, the device comprising:

[0009] The information acquisition module is used to obtain the user's historical business handling information on different types of devices;

[0010] A model integration module, used to optimize the learning and training of the large language model based on the historical business handling information, obtain a trained target large language model, and deploy the target large language model to an autonomous device or APP for autonomous business handling; wherein the target large language model is a large language model that can guide business handling;

[0011] The business handling guidance module is used to obtain the current user's business handling operation, and generate current operation guidance information corresponding to the current user's business handling operation in the interactive area based on the current user's business handling operation and the target large language model to guide the user to handle the business.

[0012] According to another aspect of the present invention, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0013] at least one processor; and

[0014] a memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the automated business processing method described in any embodiment of the present invention.

[0016] According to another aspect of the present invention, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the automated business processing method described in any embodiment of the present invention when executed.

[0017] According to another aspect of the present invention, an embodiment of the present invention further provides a computer program product, characterized in that the computer program product includes a computer program, and when the computer program is executed by a processor, it implements the automated business processing method described in any embodiment of the present invention.

[0018] The technical effect of the present invention is that the large language model is optimized and learned through historical business processing information to obtain a trained target large language model, and the target large language model is deployed in an autonomous business processing device to obtain operations for processing business, generate operation guidance information corresponding to the text information based on the target ChatGPT, and interact with the user in the interactive area to guide the user in processing business. This can solve the problem in the prior art that manual intervention is required to guide users in processing business, improve the efficiency and accuracy of business processing, and thus improve the user experience.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 A flowchart of an automated business handling method provided by one embodiment of the present invention;

[0022] Figure 2 A flowchart of another automated business handling method provided by an embodiment of the present invention;

[0023] Figure 3 A schematic diagram of an interface display of an autonomous business handling device provided by an embodiment of the present invention;

[0024] Figure 4 A structural block diagram of an automated business processing device provided by an embodiment of the present invention;

[0025] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] In one embodiment, Figure 1 A flowchart of an automated business processing method provided for one embodiment of the present invention. This embodiment can be applied to situations where users are guided to handle business independently. The method can be executed by an automated business processing device. The automated business processing device can be implemented in the form of hardware and / or software. The automated business processing device can be configured in an electronic device.

[0029] like Figure 1 As shown, the automated business handling method in this embodiment includes the following specific steps:

[0030] S110. Obtain the user's historical business handling information on different types of devices.

[0031] Among them, different types of equipment can be understood as different types of equipment information that can handle business independently. The equipment may include but is not limited to independent business handling equipment, web-based APPs in the financial field, and other business handling equipment in the financial industry.

[0032] In this embodiment, different devices have different operations when users handle services. Even for the same type of service, different devices have different operation steps and controls. The historical service handling information in this embodiment at least includes: device information corresponding to historical services, historical service information of services handled under the device information, text description information corresponding to each historical service information, service handling operation steps, click controls corresponding to each service handling operation step, and control description information corresponding to the click control. The historical service information refers to the relevant financial services handled by the user before.

[0033] In this embodiment, historical business information of businesses handled by users on business handling devices in the financial industry such as autonomous business handling devices, web-based APPs in the financial field, text description information corresponding to each historical business information, business handling operation steps, click controls corresponding to each business handling operation step, and control description information corresponding to the click controls are obtained.

[0034] S120, optimizing learning and training the large language model based on historical business processing information to obtain a trained target large language model, and deploying the target large language model to the autonomous business processing device.

[0035] The large language model in this embodiment can be a ChatGPT model, and the target large language model is the target ChatGPT model, which can be understood as a chat generation pre-trained transformation model. The target large language model is a large language model that can guide business handling. Autonomous business handling equipment can include but is not limited to autonomous equipment or APP that can handle autonomous business.

[0036] In this embodiment, the historical business handling information corresponding to each of the multiple devices can be used as a training sample set to optimize the learning and training of the large language model, obtain the trained target large language model, and deploy the target large language model to the autonomous business handling device. It can be understood that for each processable business, the text description, operation steps, click control identification and control description information of the current processable business are learned based on the ChatGPT model to obtain the target ChatGPT model that can guide the business handling, and the target ChatGPT model is integrated into the autonomous device or APP that can handle the business autonomously. At the same time, in order to improve the interactivity with the user, the intelligent question and answer display area can be displayed in the display interface.

[0037] In some embodiments, the historical business processing information can be first preprocessed to convert it into a sample set for model training. The sample set uses the historical business information of the business processed under the device information as the context, and the text description information corresponding to the historical business information, the business processing operation steps, the click controls corresponding to each business processing operation step, and the control description information corresponding to the click control as the target. Learning and training are performed through pre-training, supervised learning, and reinforcement learning. Through the Transformer neural network structure and large-scale corpus training, powerful natural language processing capabilities are achieved. Through continuous optimization and iteration, the model performance of the ChatGPT model is continuously improved, and it can generate more natural and accurate answers.

[0038] In this embodiment, after the training is completed, the target ChatGPT model needs to be deployed to the autonomous business handling device to guide the user to perform business handling operations in the future. Specifically, the deployment method may include packaging the dependent library corresponding to the target ChatGPT model using a specified language instruction to form an application package software corresponding to the ChatGPT model that can guide business handling, and deploying the application package software in an autonomous device or APP for autonomous business handling.

[0039] S130, obtaining the current user's business handling operation, and generating current operation guidance information corresponding to the current user's business handling operation in the interactive area based on the current user's business handling operation and the target large language model to guide the user to handle the business.

[0040] The current user service handling operation refers to the service handling operation being performed by the user. The interactive area refers to the area in the interface of the autonomous service handling device that guides the user to perform operations.

[0041] In this embodiment, the current operation guidance information may include, but is not limited to, the current click control corresponding to the current text information, the current control description information corresponding to the current click control, and at least one currently optimizable text description information corresponding to the current control description information displayed in a preset area of ​​the intelligent question and answer display area. It should be noted that the preset area includes at least two sub-areas; the contents of at least two sub-areas are dynamically updated; at least two sub-areas include a first sub-area and a second sub-area; wherein the first sub-area is used to display the business description, and the second sub-area is used to display the next operation description.

[0042] In this embodiment, the operation for handling the business is obtained, and after the operation is converted into text information, the operation guidance information corresponding to the text information is generated based on the large language model, and the user is interacted with in the interactive area to guide the user to handle the business. It can be understood that the trigger operation of the user on the display interface can be converted into corresponding text, and the text is used as the input of the large language model, so that the large language model can output the buttons that the user can operate and guide the user to automatically handle the business.

[0043] In this embodiment, in the specific application process, the user can edit the text description of the business to be handled in the intelligent question and answer display area. The target ChatGPT model can output a click control corresponding to the text description, and display at least one optimizable text description in the preset area of ​​the intelligent question and answer display area. If the user triggers the optimizable text description, the click control corresponding to the optimizable text description is determined based on the target ChatGPT model; if the user triggers the click control, the control description information corresponding to the click control is retrieved, and the next triggerable control is determined according to the control description information, the click control, and the historical text description (the historical text description includes all the text descriptions and control description information when entering the current page from the homepage), and the corresponding display is performed.

[0044] The technical solution of the embodiment of the present invention optimizes the learning and training of the ChatGPT model through historical business processing information to obtain a trained target ChatGPT model, and deploys the target ChatGPT model to an autonomous business processing device to obtain operations for processing business, generates operation guidance information corresponding to text information based on the target ChatGPT model, and interacts with users in an interactive area to guide users in processing business. This can solve the problem in the prior art that manual intervention is required to guide users in processing business, improve the efficiency and accuracy of business processing, and thus improve user experience.

[0045] In one embodiment, Figure 2 A flow chart of another automated business processing method provided for an embodiment of the present invention. Based on the above embodiments, this embodiment optimizes learning and training of a large language model based on historical business processing information to obtain a trained target large language model, and deploys the target large language model to an autonomous business processing device, and generates current operation guidance information corresponding to the current user business processing operation in an interactive area based on the current user business processing operation and the target large language model, so as to further refine the guidance of users in handling business.

[0046] like Figure 2 As shown, the automated business handling method in this embodiment may specifically include the following steps:

[0047] S210: Obtain the user's historical business handling information on different types of devices.

[0048] S220. Perform data preprocessing on historical business handling information to convert it into a sample set for model training; wherein the sample set uses the historical business information of the business handled under the device information as context, and uses the text description information corresponding to the historical business information, the business handling operation steps, the click controls corresponding to each business handling operation step, and the control description information corresponding to the click control as targets.

[0049] In this embodiment, data preprocessing is performed on historical business handling information to convert it into a sample set for model training; wherein, the data preprocessing methods may include but are not limited to removing unique attributes, processing missing values, attribute encoding, data standardization and regularization, feature selection, and principal component analysis. Three methods for processing missing values ​​in this embodiment: directly using features containing missing values; deleting features containing missing values ​​(this method is effective when the attributes containing missing values ​​contain a large number of missing values ​​and only contain a very small number of valid values); missing value completion. Common missing value completion methods: mean interpolation, same-mean interpolation, modeling prediction, high-dimensional mapping, multiple interpolation, maximum likelihood estimation, compressed sensing, and matrix completion.

[0050] In this embodiment, the historical business information of the business handled under the device information is used as the context, and the text description information corresponding to the historical business information, the business handling operation steps, the click controls corresponding to each business handling operation step, and the control description information corresponding to the click control are input as targets into the large language model for training.

[0051] S230: input the sample set into the large language model, and perform unsupervised training on the large language model using an unsupervised learning method to optimize model parameters.

[0052] In this embodiment, the historical business information of the business handled under the device information is used as the context, and the text description information corresponding to the historical business information, the business handling operation steps, the click controls corresponding to each business handling operation step, and the control description information corresponding to the click control are input into the ChatGPT model as the target, and the ChatGPT model is unsupervisedly trained using an unsupervised learning method, and the model parameters are optimized by maximum likelihood estimation. During training, optimizers (such as Adam) and learning rate schedulers can be used to accelerate convergence and improve model performance.

[0053] S240, using a reinforcement learning method to repeatedly adjust the generated text results according to the feedback information to adjust the model parameters and obtain a trained target large language model.

[0054] In this embodiment, the generated text information is repeatedly adjusted according to the feedback information using reinforcement learning to adjust and optimize the model parameters to obtain the trained target ChatGPT model. At the same time, during the training process, evaluation indicators (such as perplexity, etc.) can be used to monitor the performance of the model and adjust and optimize the model parameters. Through multiple iterative training, the generation ability and conversation quality of the model are continuously improved. After the model training is completed, fine-tuning can be performed to adapt the model to specific downstream conversation tasks or task sets, and optimized according to actual needs. Finally, the trained large language model is deployed to the target environment for real-time application and generation of conversations.

[0055] S250. Use preset language instructions to package the target large language model to form an application package software corresponding to the large language model that can guide business processing, and deploy the application package software in an autonomous device or APP for autonomous business processing.

[0056] Among them, the preset language instructions include Python programming instructions. Of course, in addition to Python programming instructions, languages ​​such as C and C++ can also be used, which is not limited in this embodiment.

[0057] In this embodiment, Python programming instructions are used to package the dependent libraries corresponding to the target ChatGPT model to form an application package software corresponding to the ChatGPT model that can guide business processing, and the application package software is deployed in an autonomous device or APP for autonomous business processing.

[0058] S260: Obtain the current user service handling operation, and convert the current user service handling operation into current text information.

[0059] In this embodiment, the current user business processing operation is obtained and converted into current text information. The specific conversion method can be text generated according to the operation clicked by the user, or it can be other methods in the prior art, which is not limited in this embodiment.

[0060] S270. Generate current operation guidance information corresponding to the current text information based on the target large language model; wherein the current operation guidance information at least includes: the current click control corresponding to the current text information, the current control description information corresponding to the current click control, and at least one current optimizable text description information corresponding to the current control description information displayed in a preset area of ​​the intelligent question and answer display area.

[0061] In this embodiment, current operation guidance information corresponding to the current text information is generated based on the target large language model; wherein the current operation guidance information includes at least: the current click control corresponding to the current text information, the current control description information corresponding to the current click control, and at least one current optimizable text description information corresponding to the current control description information displayed in a preset area of ​​the intelligent question and answer display area.

[0062] In this embodiment, after generating the current operation guidance information corresponding to the current text information based on the target large language model, it also includes: in response to the user triggering the operation of the current optimizable text description information, generating the current optimized click control corresponding to the current optimizable text description information according to the target large language model; in response to the user triggering the operation of the current optimized click control, calling the current control description information corresponding to the current optimized click control; obtaining all the historical click controls of the user before the operation of triggering the current optimized click control, and determining the next triggerable control according to the current control description information and the historical click control, and displaying the next triggerable control; wherein the next triggerable control includes the first next triggerable control corresponding to the current optimized click control, the second next triggerable control, until the last triggerable control of the user's business handling. It can be understood that if the user triggers the optimizable text description, the click control corresponding to the optimizable text description continues to be determined based on the large language model. If the user triggers the click control, the control description information corresponding to the click control is called. According to the control description information, the click control and the historical text description (the historical text description includes all the text descriptions and control description information when entering the current page from the homepage), the next triggerable control is determined and displayed.

[0063] In one embodiment, the preset area includes at least two sub-areas; the contents of at least two sub-areas are dynamically updated; the at least two sub-areas include a first sub-area and a second sub-area; wherein the first sub-area is used to display a business description, and the second sub-area is used to display a description of the next operation; at least two sub-areas in the preset area are slidable sub-areas.

[0064] In this embodiment, the control description information, clicked controls, and historical text descriptions are processed based on the target ChatGPT model, and the description text of the preset area can be updated. The preset area may include at least two sub-areas. The contents of at least two sub-areas are dynamically updated. One of the at least two sub-areas is used to display the business description, and the other sub-area is used to display the next operation description. In this embodiment, at least two sub-areas in the preset area can slide, so that multiple description information can be displayed.

[0065] The technical solution of the embodiment of the present invention inputs a sample set into a large language model, and uses an unsupervised learning method to perform unsupervised training on the large language model to optimize model parameters, uses a reinforcement learning method to repeatedly adjust the generated text results according to feedback information to adjust and optimize the model parameters, so as to obtain a trained target large language model, uses preset language instructions to package the target large language model to form an application package software corresponding to the large language model that can guide business handling and deploys it in an autonomous device or APP for autonomous business handling, converts the current user business handling operation into current text information, and generates current operation guidance information corresponding to the current text information based on the target large language model, which can further solve the problem of needing manual intervention to guide business handling, improve the efficiency and accuracy of business handling, and improve user experience. Based on the displayed information in the intelligent question and answer area, the user is guided to handle the corresponding business, and the technical effect of improving the guidance and efficiency of business handling is improved.

[0066] For example, to better understand the interface display diagram of the autonomous business handling device, Figure 3 A schematic diagram of an interface display of an autonomous business handling device provided by an embodiment of the present invention, such as Figure 3 As shown, the display interface includes a main interface, an intelligent question and answer area, a preset area, and a text input area. At least two sub-areas in the preset area can slide, so that multiple description information can be displayed. Based on the displayed information in the intelligent question and answer area, the user is guided to handle the corresponding business, which improves the technical effect of the guidance and efficiency of business handling.

[0067] In one embodiment, Figure 4 This is a structural block diagram of an automated service handling device provided in one embodiment of the present invention. The device is suitable for guiding users to handle services independently. The device can be implemented by hardware / software. It can be configured in an electronic device to implement an automated service handling method in an embodiment of the present invention.

[0068] like Figure 4 As shown, the device includes: an information acquisition module 410, a model integration module 420 and a business handling guidance module 430;

[0069] The information acquisition module 410 is used to acquire the historical business handling information of the user on different types of devices;

[0070] The model integration module 420 is used to optimize the learning and training of the large language model based on the historical business handling information to obtain a trained target large language model, and deploy the target large language model to an autonomous device or APP for autonomous business handling; wherein the target large language model is a large language model that can guide business handling;

[0071] The business handling guidance module 430 is used to obtain the current user's business handling operation, and generate current operation guidance information corresponding to the current user's business handling operation in the interactive area based on the current user's business handling operation and the target large language model to guide the user to handle the business.

[0072] In the embodiment of the present invention, the module integration module optimizes the learning and training of the large language model based on the historical business processing information to obtain the trained target large language model, and deploys the target large language model to the autonomous business processing device. The business processing guidance module obtains the operations for processing the business, generates operation guidance information corresponding to the text information based on the target ChatGPT, and interacts with the user in the interactive area to guide the user to process the business. This can solve the problem in the prior art that manual intervention is required to guide the user to process the business, improve the efficiency and accuracy of business processing, and thus improve the user experience.

[0073] In one embodiment, the historical business processing information includes at least: device information corresponding to the historical business processing, historical business information of the business processed under the device information, text description information corresponding to each historical business information, business processing operation steps, click controls corresponding to each of the business processing operation steps, and control description information corresponding to the click controls.

[0074] In one embodiment, the model integration module 420 includes:

[0075] A sample set determination unit, configured to perform data preprocessing on the historical business handling information to convert it into a sample set for model training; wherein the sample set uses the historical business information of the business handled under the device information as context, and uses the text description information corresponding to the historical business information, the business handling operation steps, the click controls corresponding to each of the business handling operation steps, and the control description information corresponding to the click controls as targets;

[0076] A training unit, used for inputting the sample set into the large language model, and performing unsupervised training on the large language model in an unsupervised learning manner to optimize model parameters;

[0077] The optimization unit is used to repeatedly adjust the generated text results according to the feedback information using a reinforcement learning method to adjust the model parameters and obtain a trained target large language model.

[0078] In one embodiment, the model integration module 420 includes:

[0079] The integrated unit is used to use preset language instructions to package the target large language model to form an application package software corresponding to the large language model that can guide business processing, and deploy the application package software in an autonomous device or APP for autonomous business processing.

[0080] In one embodiment, the business handling module 430 includes:

[0081] A conversion unit, used to convert the current user service handling operation into current text information;

[0082] A guidance unit, used to generate current operation guidance information corresponding to the current text information based on the target large language model; wherein the current operation guidance information at least includes: a current click control corresponding to the current text information, current control description information corresponding to the current click control, and at least one current optimizable text description information corresponding to the current control description information displayed in a preset area of ​​the intelligent question and answer display area.

[0083] In one embodiment, after the current operation guidance information corresponding to the current text information is generated based on the target large language model, at least one of the following is further included:

[0084] In response to a user triggering an operation of currently optimizable text description information, generating a current optimization click control corresponding to the currently optimizable text description information according to the target large language model;

[0085] In response to the user triggering the operation of the current click control corresponding to the current text information, calling the current control description information corresponding to the current click control;

[0086] Acquire all historical click controls of the user before the operation of triggering the current click control, determine the next triggerable control according to the current control description information and the historical click controls, and display the next triggerable control.

[0087] In one embodiment, the preset area includes at least two sub-areas; the contents of the at least two sub-areas are dynamically updated; the at least two sub-areas include a first sub-area and a second sub-area; wherein the first sub-area is used to display a service description, and the second sub-area is used to display a next operation description;

[0088] At least two sub-areas in the preset area are slidable sub-areas.

[0089] The automated service processing device provided in the embodiment of the present invention can execute the automated service processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0090] In one embodiment, Figure 5 A schematic diagram of the structure of an electronic device provided for an embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0091] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0092] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0093] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as an automated business handling method.

[0094] In some embodiments, the automated business handling method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the automated business handling method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the automated business handling method in any other appropriate manner (e.g., by means of firmware).

[0095] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0096] The computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable automated business processing device, so that when the computer programs are executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer programs may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0097] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0098] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0099] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0100] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0101] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0102] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An automated business handling method, characterized in that: The method comprises: Obtain the user's historical business handling information on different types of devices; Based on the historical business handling information, the large language model is optimized and trained to obtain a trained target large language model, and the target large language model is deployed to the autonomous business handling device; wherein the target large language model is a large language model that can guide business handling; The current user business handling operation is obtained, and based on the current user business handling operation and the target large language model, current operation guidance information corresponding to the current user business handling operation is generated in the interactive area to guide the user to handle business.

2. The method according to claim 1, characterized in that: The historical business processing information at least includes: device information corresponding to the historical processing business, historical business information of the business processed under the device information, text description information corresponding to each historical business information, business processing operation steps, click controls corresponding to each of the business processing operation steps, and control description information corresponding to the click controls.

3. The method according to claim 2, characterized in that The optimizing learning and training of the large language model based on the historical business handling information to obtain a trained target large language model includes: Performing data preprocessing on the historical business handling information to convert it into a sample set for model training; wherein the sample set uses the historical business information of the business handled under the device information as context, and uses the text description information corresponding to the historical business information, the business handling operation steps, the click controls corresponding to each of the business handling operation steps, and the control description information corresponding to the click controls as targets; Inputting the sample set into the large language model, and performing unsupervised training on the large language model by using an unsupervised learning method to optimize model parameters; The generated text results are repeatedly adjusted according to the feedback information using reinforcement learning to adjust the model parameters and obtain the trained target large language model.

4. The method according to claim 1, characterized in that: The step of deploying the target large language model to the autonomous business processing device includes: The target large language model is packaged using preset language instructions to form an application package software corresponding to the large language model that can guide business handling, and the application package software is deployed in an autonomous device or APP for autonomous business handling.

5. The method according to claim 1, characterized in that The generating, in the interactive area, current operation guidance information corresponding to the current user service handling operation based on the current user service handling operation and the target large language model includes: Converting the current user service handling operation into current text information; Based on the target large language model, current operation guidance information corresponding to the current text information is generated; wherein, the current operation guidance information at least includes: the current click control corresponding to the current text information, the current control description information corresponding to the current click control, and at least one current optimizable text description information corresponding to the current control description information displayed in a preset area of ​​the smart question and answer display area.

6. The method according to claim 5, characterized in that After the current operation guidance information corresponding to the current text information is generated based on the target large language model, the method further includes at least one of: In response to a user triggering an operation of currently optimizable text description information, generating a current optimization click control corresponding to the currently optimizable text description information according to the target large language model; In response to the user triggering the operation of the current click control corresponding to the current text information, calling the current control description information corresponding to the current click control; Acquire all historical click controls of the user before the operation of triggering the current click control, determine the next triggerable control according to the current control description information and the historical click controls, and display the next triggerable control.

7. The method according to claim 5, characterized in that The preset area includes at least two sub-areas; the contents of the at least two sub-areas are dynamically updated; the at least two sub-areas include a first sub-area and a second sub-area; wherein the first sub-area is used to display a service description, and the second sub-area is used to display a next operation description; At least two sub-areas in the preset area are slidable sub-areas.

8. An automated business handling device, characterized in that: include: The information acquisition module is used to obtain the user's historical business handling information on different types of devices; A model integration module, used to optimize the learning and training of the large language model based on the historical business handling information, obtain a trained target large language model, and deploy the target large language model to an autonomous device or APP for autonomous business handling; wherein the target large language model is a large language model that can guide business handling; The business handling guidance module is used to obtain the current user's business handling operation, and generate current operation guidance information corresponding to the current user's business handling operation in the interactive area based on the current user's business handling operation and the target large language model to guide the user to handle the business.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the automated business processing method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the automated business processing method according to any one of claims 1 to 7 when executed.

Images