Intelligent business guiding method and system

Abstract

The invention discloses an intelligent business guiding method and system, and relates to the technical field of intelligent guiding. The method comprises the following steps: acquiring attribute information of a business intelligent guidance system; according to the attribute information, combining with the business process to form a business process description file, and sending the business process description file to a development test environment; in the development test environment, according to the business process description file, configuration and development of the guide business are completed in a visual mode, and the guide business is tested; the development test environment deploys the guide business to a guide arrangement module of the central service layer on line; and the central service layer provides business guidance service for the business process of the business all-in-one machine based on a guidance arrangement module. According to the method provided by the embodiment of the invention, the guide business is developed and configured in a visual manner, so that guidance and help can be provided for the user in the process of operating the business all-in-one machine, and the user can complete self-service operation more quickly and more conveniently.

Description

Technical Field

[0001] The present invention relates to the field of intelligent guidance technology, and in particular to a business intelligent guidance method and system. Background Art

[0002] As offline business shrinks, financial companies are gradually promoting the construction of smart business halls and constantly introducing new technologies and service methods to improve the company's service efficiency and service quality. The construction of smart business halls has become an important means for companies to improve service levels and customer satisfaction.

[0003] At present, the self-service machines in the service halls of financial banks and other institutions lack automated and intelligent guidance, and many of them need to rely on manual guidance from hall managers. Some products that are equipped with digital humans to guide business operations mostly have fixed program steps written in advance, which is not conducive to scenarios where business processes need to be self-configured or changed. As a result, once the business process is changed, it has to be customized and developed again, which results in high development costs for the business party. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a business intelligent guidance method and system, which can provide users with a more intuitive and efficient guidance method.

[0005] In a first aspect, a business intelligent guidance method according to an embodiment of the present invention is applied to a business intelligent guidance system, wherein the business intelligent guidance system includes a device layer, a communication layer, a central service layer, and a development and testing environment, wherein the communication layer is respectively connected to the device layer and the central service layer for communication, wherein the device layer includes a business all-in-one machine and an edge AI server, the communication layer includes a central communication gateway, and the central service layer includes a guidance orchestration module; the business intelligent guidance method includes the following steps:

[0006] Acquire attribute information of the business intelligent guidance system; the attribute information includes address information of the central communication gateway, configuration information and access address of the business all-in-one machine, and address information of the edge AI server;

[0007] According to the attribute information, combined with the business process, a business process description file is formed, and the business process description file is sent to the development and testing environment;

[0008] On the development and testing environment, according to the business process description file, the configuration and development of the guidance service are completed in a visual manner, and the guidance service is tested;

[0009] The development and testing environment deploys the guidance service online to the guidance orchestration module of the central service layer; the guidance service includes a guidance service integration interface and a guidance speech model;

[0010] The central service layer provides business guidance services for the business process of the business machine based on the guidance orchestration module.

[0011] According to some embodiments of the present invention, the device layer further includes a user terminal, the communication layer further includes a cluster management module and a message middleware, and the service intelligent guidance method further includes:

[0012] Add the Dubbo microservice governance system based on the Zookeeper cluster to the communication layer through the cluster management module;

[0013] Providing asynchronous communication capability for the communication layer through the message middleware;

[0014] The communication layer also provides message push for the user terminal through the WebSocket protocol.

[0015] According to some embodiments of the present invention, the step of completing the configuration and development of the guidance service in a visual manner according to the business process description file on the development and testing environment, and testing the guidance service includes:

[0016] In the development and testing environment, a process file is created; the process file includes a start node;

[0017] In response to a selection operation on a configuration item of an interface of the development and testing environment, initially configuring the process file;

[0018] In response to the selection operation of the task item of the interface of the development and testing environment, a connection relationship between each task node and the start node is established, and a jump condition between each task node is configured, and an end node is connected at the last task node to complete the process configuration of the process file;

[0019] Use existing components or low-code platforms to configure the current page for each of the task nodes;

[0020] Configure the guidance words on the process file to complete the configuration and development of the guidance business;

[0021] The bootstrap service is tested.

[0022] According to some embodiments of the present invention, the further comprising:

[0023] Get the user's audio and video information;

[0024] The edge AI server identifies the user intention based on the audio and video information;

[0025] According to the user's intention, jump to and execute the business process corresponding to the corresponding task node.

[0026] According to some embodiments of the present invention, the business intelligence guidance method includes the following steps:

[0027] In the development and testing environment, an API baffle is set; the API baffle is used to prevent access to a preset interface or preset function of the business intelligent guidance system;

[0028] The API baffle is configured so that the access task in the actual environment is forwarded to the development and testing environment, so that the development and testing environment verifies and debugs the access task.

[0029] According to some embodiments of the present invention, the step of the development and testing environment deploying the guiding service online to the guiding orchestration module of the central service layer includes:

[0030] Establishing a corresponding publishing center for each version of the guiding service;

[0031] In the release center, a version number and a change log are set for each version, and a rollback mechanism is established;

[0032] When an error occurs in the published version of the boot service, the previous version of the boot service is returned through the rollback mechanism.

[0033] According to some embodiments of the present invention, the central service layer further includes an RPA module; and the business intelligence guidance method further includes the following steps:

[0034] Use Dubbo RPC mode to connect the guidance service with the business process; or,

[0035] The guiding business is connected to the business process through the RPA module.

[0036] According to some embodiments of the present invention, the step of upgrading the edge AI server is also included, and the step includes:

[0037] When the current version number of the edge AI server is less than the latest version number, read the update configuration table;

[0038] According to the update configuration table, determine whether to perform a strong update or a weak update on the edge AI server;

[0039] When the edge AI server is forced to update, a pop-up window will be displayed to prompt that it needs to be forced to update to the latest version;

[0040] When the edge AI server is weakly updated, a silent update is performed to update the edge AI server to the latest version.

[0041] According to some embodiments of the present invention, the central service layer further includes a compliance risk control module, and the business intelligent guidance method further includes:

[0042] Conduct risk monitoring of user behaviors through the compliance risk control module;

[0043] When abnormal behavior is detected, an alarm operation is performed.

[0044] In the second aspect, according to the business intelligent guidance system of an embodiment of the present invention, the business intelligent guidance system includes a device layer, a communication layer, a central service layer and a development and testing environment, the communication layer is communicated with the device layer and the central service layer respectively, the device layer includes a business all-in-one machine and an edge AI server, the central service layer includes a central communication gateway, and the central service layer includes a guidance orchestration module; the business intelligent guidance system is used to execute the business intelligent guidance method described in the embodiment of the first aspect.

[0045] The intelligent business guidance method and system according to the embodiments of the present invention have at least the following beneficial effects: by developing and configuring guidance services in a visual way, it is possible to provide guidance and assistance to users in the process of operating the business all-in-one machine, so that users can complete self-service operations faster and more conveniently. At the same time, the difficulty of developing guidance services is reduced, and it can better adapt to changes in business processes. The business all-in-one machine enhances the audio and video processing capabilities through the edge AI server, allowing the business all-in-one machine to have environmental adaptability, and at the same time enhances the UI rendering capabilities based on AI computing power to construct a smoother and more user-friendly self-service business processing environment.

[0046] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0048] Figure 1 A schematic diagram of the structure of a business intelligent guidance system according to an embodiment of the present invention;

[0049] Figure 2 A schematic diagram of the development process of the guidance service according to an embodiment of the present invention;

[0050] Figure 3A schematic diagram of a process for upgrading an edge AI server according to an embodiment of the present invention;

[0051] Figure 4 A schematic diagram after creating a process file according to an embodiment of the present invention;

[0052] Figure 5 This is a schematic diagram after adding a task node to the process file;

[0053] Figure 6 A schematic diagram of the business process for the final configuration;

[0054] Figure 7 A schematic diagram of the page configuration;

[0055] Figure 8 The present invention is a flowchart of the steps of the business intelligent guidance method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0056] Embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and are not to be construed as limitations on the present application. For the step numbers in the following embodiments, they are only provided for the convenience of explanation, and the order between the steps is not limited in any way, and the execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0057] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., and orientations or positional relationships indicated are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0058] The terms "first", "second", "third" and "fourth" etc. in the specification and claims of the present invention and the drawings are used to distinguish different objects, rather than to describe a specific order. 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 limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0059] Reference to "embodiments" in the present invention means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0060] As offline business shrinks, financial companies are gradually promoting the construction of smart business halls and constantly introducing new technologies and service methods to improve the company's service efficiency and service quality. The construction of smart business halls has become an important means for companies to improve service levels and customer satisfaction.

[0061] At present, the self-service machines in the service halls of financial banks and other institutions lack automated and intelligent guidance, and many of them need to rely on manual guidance from hall managers. Some products that are equipped with digital humans to guide business operations mostly have fixed program steps written in advance, which is not conducive to scenarios where business processes need to be self-configured or changed. As a result, once the business process is changed, it has to be customized and developed again, which results in high development costs for the business party.

[0062] To this end, the embodiments of the present invention provide a business intelligent guidance method and system, which develops and configures guidance services in a visual manner, thereby providing guidance and assistance to users in the process of operating the business all-in-one machine, allowing users to complete self-service operations faster and more conveniently. At the same time, the difficulty of developing guidance services is reduced, and it can better adapt to changes in business processes. The business all-in-one machine enhances the audio and video processing capabilities through the edge AI server, allowing the business all-in-one machine to have environmental adaptability, and at the same time enhances the UI rendering capabilities based on AI computing power to construct a smoother and more user-friendly self-service business processing environment.

[0063] The business intelligent guidance method and system according to the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0064] On the one hand, the embodiment of the present invention provides a business intelligent guidance system, such as Figure 1 As shown, the system includes a device layer 100, a communication layer 200, a central service layer 300 and a development and testing environment. The communication layer 200 is respectively communicated with the device layer 100 and the central service layer 300. The device layer 100 includes a business all-in-one machine 110 and an edge AI server 120. The communication layer 200 includes a central communication gateway 210, and the central service layer 300 includes a guidance orchestration module 310.

[0065] Specifically, Figure 1As shown, the business machine 110 is an intelligent device for users to handle business by themselves. Generally speaking, the business machine 110 includes devices such as a display screen, a camera, a card reader, a microphone, and a microservice client, which can shoot videos of operating users, read audio, read user information, and provide operation pages for users to operate business by themselves. In this example, in addition to the business machine 110, the device layer 100 is also provided with an edge AI server 120. The edge AI server 120 increases the audio and video processing capabilities of the business machine 110, so that the business machine 100 has environmental convenience capabilities, and at the same time, based on AI computing power, the UI rendering capability is enhanced to construct a smoother and more user-friendly self-service business handling environment. The edge AI server 120 includes an edge API gateway, and can help the system perform operations such as target detection, voice recognition, face recognition, and intelligent dialogue. At the same time, the edge AI server 120 also provides system management services and device communication services. In addition, in this example, the device layer 100 also includes a user terminal 130, which can be a mobile phone, a tablet, a laptop, a wearable smart device, etc. The user terminal 130 is provided with an APP, so that the user can receive system message pushes and review the execution results of the system, etc. It can be seen that the device layer 100 includes all edge devices, including the business all-in-one machine 110, the edge AI server 120, and the user terminal 130, etc.

[0066] The communication layer 200 is responsible for the communication and information transmission between the business all-in-one machine 110, the edge AI server 120, the user terminal 130 and the central service layer 300. In this example, the communication layer 200 includes a central communication gateway 210 (dubbo gateway), so that the communication layer 200 is compatible with the Dubbo microservice gateway, relying on the Dubbo microservice gateway to realize the conversion from the Http protocol to the Dubbo rpc protocol. At the same time, the central microservice is implemented using the Dubbo microservice framework, and can be seamlessly added to the Dubbo microservice governance system based on the Zookeeper cluster (i.e., the cluster management module 220). At the same time, the various layers and modules of the business intelligent guidance system require both synchronous and asynchronous communication. For this reason, the design of the communication layer 200 combines the microservice gateway (i.e., the central communication gateway) and the message middleware 230 (kafka), and the asynchronous communication requirements are realized based on the kafka message middleware 230 cluster; at the same time, the communication layer 200 also implements page message push through the WebSocket protocol to push messages to the user terminal 130.

[0067] The central service layer 300 includes various business services and management services that support the work of the device layer 100, as well as equipment monitoring management and configuration distribution. The management service is developed using the Dubbo RPC microservice architecture, which can be quickly built into microservices and connected to existing businesses. At the same time, the process orchestration platform and RPA platform are introduced to improve the development efficiency and flexibility of background services. Specifically, in this example, the central service layer 300 includes a guidance orchestration module 310, a compliance risk control module 320, a business system module 330 and an RPA module 340, among which the intelligent guidance orchestration service, compliance risk control service and RPA adaptation service are all developed using the Dubbo RPC microservice architecture and connected to the entire central microservice governance system according to the standard mode of Dubbo RPC.

[0068] The business intelligent guidance system according to the embodiment of the present invention is used to provide development, training, publishing and management capabilities for the realization of the intelligent guidance capabilities of the business machine 110. The business intelligent guidance system focuses on the development of intelligent guidance capabilities and builds the communication environment, business docking environment and AI capability docking, training, publishing and management environment required for intelligent guidance.

[0069] The business intelligent guidance system is a self-developed low-code development platform that provides the ability of rapid front-end development. It is installed and used in VSCODE in the form of plug-ins. Developers can design processes by dragging and connecting components without writing code, and each process node supports configuration access to business APIs and setting AI checkpoints, NLP capabilities, etc. There is also a corresponding development and testing environment. The development and testing environment is an environment used for testing. It usually simulates the basic architecture of the production environment, but on a smaller scale, which is convenient for developers to quickly verify the various functions and performance of their applications in a real environment. The development and testing environment has a baffle, which is used in the production environment to prevent high-risk operations or undeveloped functions from affecting the customer's experience, and to block access to certain specific interfaces or functions during actual operation. In the development and testing environment, in order to more conveniently verify whether the developed functions can run correctly in the actual environment, we usually need to configure the baffle appropriately so that the access in the production environment can be forwarded to the development and testing environment, so that developers can verify and debug the developed applications at any time in the development and testing environment, and further optimize them.

[0070] The business intelligent guidance system takes the business all-in-one machine 110 as the core, and uses the cloud, edge, and end collaborative working mode to realize the intelligent upgrade of self-service business. It adds an edge AI server 120 to enhance the audio and video processing capabilities of the business all-in-one machine 110, allowing the business all-in-one machine 110 to have environmental adaptability. At the same time, it enhances the UI rendering capability based on AI computing power to construct a smoother and more user-friendly self-service business processing environment.

[0071] The intelligent guidance function of the business intelligent guidance system provides user navigation and assistance for the business all-in-one machine 110, allowing users to complete self-service operations faster and more conveniently. The intelligent guidance function is based on intelligent conversation technology and cooperates with digital human technology to provide users with a more intuitive and friendly guidance method. At the same time, the intelligent guidance process combined with audio and video detection technology can respond more quickly to changes in the on-site operating environment.

[0072] The core of the intelligent guidance function is the following technical contents:

[0073] 1. NLP dialogue control management: NLP dialogue control technology needs to be managed, including dialogue logic design, semantic analysis, intent recognition, dialogue process management, etc.

[0074] 2. Risk management: It is necessary to effectively manage risk events that may occur during the transaction process, including real-time monitoring, early warning processing and risk situation analysis.

[0075] 3. AI-related service management: It is necessary to manage artificial intelligence-related services, including AI algorithm development, model training, effect evaluation, and online services. At the same time, it is necessary to manage and protect data to ensure data security and confidentiality.

[0076] 4. Intelligent guidance of digital human: The intelligent guidance function is based on intelligent conversation technology and cooperates with digital human technology to provide users with a more intuitive and friendly guidance method.

[0077] 5. Audio and video risk control: The intelligent guidance process cooperates with audio and video detection technology to conduct real-time risk monitoring and alarm services, and respond more quickly to changes in the on-site operating environment.

[0078] It should be noted that the business intelligent guidance system according to the embodiment of the present invention needs to meet the following requirements:

[0079] Low latency: The device response delay is controlled within 1-2 seconds, and the device operation meets high reliability and high safety requirements;

[0080] Voice dialogue: The business guidance process is realized through real-time dialogue between customers and digital people. The dialogue process is smooth and the business explanation is clear.

[0081] Remote operation and maintenance: Directly remotely control the business machine 110 and the edge AI server 120. The background server can initiate functions such as restarting, upgrading, and resetting the business machine 110 and the edge AI server 120.

[0082] The development process of the onboarding process is implemented in three stages:

[0083] 1. Online process editing and configuration:

[0084] By obtaining the central microservice address information, the device configuration information and access address of the business all-in-one machine 100, the AI ​​capability address information of the edge AI server 120, and the business interface address information online, combined with the actual business process, a business process description file is formed, and the file is downloaded and transferred to the development and testing environment.

[0085] 2. Offline process editing and testing:

[0086] Upload the business process description file in the development and testing environment, and complete the configuration, development and testing of the guided business based on the business process: use the low-code platform to generate a test page; use the low-code platform to generate a business process transition page; 3. Configure the guided speech.

[0087] The development and testing environment must meet the following requirements: business system API baffle, device access API baffle and guidance speech training platform. The testing process is: business process testing and guidance speech testing. The development and testing environment generates and deploys online, including: intelligent guidance business integration interface and guidance speech model.

[0088] 3. Guide the online deployment of business flows:

[0089] Each application independently releases a version using a single release center model. A dedicated release center is established and a dedicated person is responsible for version release to ensure the quality and stability of the version release. The content of each release involves: guided web page information, guided speech reasoning model; in this release center, version numbers, change logs and other information can be set for each independent version to facilitate management and tracking, and a rollback mechanism is established. After the version is released, if there is a problem, it needs to be rolled back in time. In the event of security issues or erroneous operations, the system can be quickly rolled back to reduce losses.

[0090] The development process of the guided process is as follows Figure 2 It should be noted that the business guidance process development is based on the visual process editing configuration mode. The transition form page can be quickly generated through the low-code platform. The process configuration page can configure the page jump information, digital human-guided corpus, and AI checkpoints for each node. After completing the relevant configuration, training and release can be carried out.

[0091] Since the boot process serves the business process, the development of the boot process is based on the business process, and the development process of the boot process is the business docking process. For business systems developed based on the Dubbo microservice architecture, you can directly use the Dubbo RPC mode to dock. For businesses that are not adapted to the Dubbo microservice architecture, use the microservice adaptation mode to complete business service docking. For business services that cannot be docked using the practical interface adaptation mode, use the RPA interface docking method to complete business service adaptation. The microservice adaptation mode development process is as follows:

[0092] 1. Define the Dubbo RPC interface based on the business service interface description;

[0093] 2. Create a Dubbo RPC adapter class and implement the corresponding interface;

[0094] 3. In the Dubbo configuration file, configure the implementation of the adapter class as a service provider;

[0095] 4. Release and deploy Dubbo microservices.

[0096] After the adaptation microservice is released, the interface provided by the adaptation microservice can be seen in the visual process editing interface.

[0097] During the use of the business intelligence guidance system, it is also necessary to upgrade the application deployment of the edge AI server 120. The upgrade deployment of the edge AI server 120 is divided into software deployment upgrade and AI capability model upgrade. The AI ​​capability model upgrade is performed in a silent update manner. After the background server issues an update instruction, the edge AI server 120 is silently updated in the background system after the bank branch goes off work. The deployment and upgrade of the application itself is implemented based on the software store, and the upgrade strategy is implemented based on the software upgrade strategy configured in the edge AI server 120. The process of the server obtaining the installation package and upgrade patch is as follows: Figure 3 shown.

[0098] On the other hand, based on the business intelligent guidance system of the above-mentioned embodiment, the embodiment of the present invention also proposes a business intelligent guidance method, such as Figure 8 As shown, the method comprises the following steps:

[0099] Step S100: Acquire attribute information of the business intelligent guidance system; the attribute information includes address information of the central communication gateway 210, configuration information and access address of the business all-in-one machine 110, and address information of the edge AI server 120;

[0100] Step S200: forming a business process description file based on the attribute information and the business process, and sending the business process description file to the development and testing environment;

[0101] Step S300: In the development and testing environment, according to the business process description file, the configuration and development of the guidance service are completed in a visual manner, and the guidance service is tested;

[0102] Step S400: the development and testing environment deploys the guidance service online to the guidance orchestration module 310 of the central service layer 300; the guidance service includes a guidance service integration interface and a guidance speech model;

[0103] Step S500 : the central service layer 300 provides business guidance services for the business process of the business machine 110 based on the guidance orchestration module 310 .

[0104] Specifically, by obtaining the central microservice address information, the device configuration information and access address of the business all-in-one machine 100, the AI ​​capability address information of the edge AI server 120, and the business interface address information online, combined with the actual business process, a business process description file is formed, and the file is downloaded and transferred to the development and testing environment.

[0105] Upload the business process description file in the development and testing environment, and complete the configuration, development and testing of the guided business based on the business process. Specifically, the above step S300 includes the following six steps:

[0106] (1) In the development and testing environment, create a process file; the process file includes a start node;

[0107] (2) in response to a selection operation on a configuration item of an interface of a development and testing environment, initially configuring a process file;

[0108] (3) In response to the selection operation of the task item in the interface of the development and testing environment, the connection relationship between each task node and the start node is established, and the jump conditions between each task node are configured, and the end node is connected at the last task node to complete the process configuration of the process file;

[0109] (4) Use existing components or low-code platforms to configure the current page for each task node;

[0110] (5) Configure guidance words in the process file to complete the configuration and development of guidance services;

[0111] (6) Test the boot service.

[0112] Specifically, after using the scaffolding to create the initial project, create a new process file in the src / process directory: demo.process. After the creation is completed, import the process file into the index.js file in the same directory. Enter the demo.process file, open it, and click the New button in the upper left corner of the editor to create a new process. After the creation is completed, there is a start node by default, such as Figure 4 As shown. In the configuration items of the process on the right, you can configure the name of the process and the trigger intention. After selecting the intention, it means that during the interaction with rasa, once rasa recognizes the user's intention, it will jump to the corresponding business process. Quality inspection skills are used to configure the AI ​​capabilities that the entire process will monitor when executing the current business process. After the new creation is completed, you can drag the task node on the left to add a new process node, or click the node, select the type of the next node on the right side of the node, double-click the task node, you can quickly give the node a name, and you can also give the task node a name or description on the right. When you need to execute different task nodes according to the situation, you need to add a gateway node after the node branch. After giving the name of the gateway node, you can create multiple different task nodes after the gateway node according to the situation. On the branch connection line, you can configure the jump conditions of the subsequent task nodes. You need to write some js code to cooperate with the previous task node configuration to jump. When the previous task node completes the jump, it will jump to the next task node that meets the conditions according to the jump conditions, such as Figure 5 When all process nodes are designed, an end node needs to be connected to the last node to indicate the end of the process, such as Figure 6 As shown. So far, a complete business process configuration is completed.

[0113] After the process is configured, you need to configure the current page at each task node. Currently, two page configuration methods are supported, namely, configuring existing components or using low-code to customize the page. To use existing components, you need to import the components into the project in advance and match the name when imported with the configured name. When using a low-code platform, Figure 7 As shown, select a task node in low code, click the mount page in the configuration bar on the right, a form configuration pop-up window will pop up, and you can start configuring the form. There is a component library on the left side of the form. You can click the content of the component library on the left and drag it to the middle area to create a component. At the same time, you can also select a form template to quickly use the pages that have been created before. Component settings are used to configure the style, form rules and other properties of each form component, and you can also write script code for some events of the component. Form settings are used to configure the properties, styles, events and other parameters of the entire form. Global methods used to control the style of the overall page and execution.

[0114] Then, you need to configure the guidance words on the process file to complete the configuration and development of the guidance business. The dialogue setting is used to configure what kind of words rasa needs to reply when executing to the business node, and whether it is necessary to interact with rasa. If you choose to need to reply, you need to cooperate with the subsequent configuration of the trigger intention on the node branch. After configuring this item, rasa will start recording after the broadcast is over. After recognizing the user's text, the content will be given to rasa to identify the intent. After the recognition is completed, it will jump to the process node corresponding to the branch of the recognized intent. After configuring the guidance words, when the user uses the business all-in-one machine 110 to handle business, the user's audio and video information can be obtained, and the edge AI server 120 identifies the user's intention based on the audio and video information; according to the user's intention, jump and execute the business process corresponding to the corresponding task node.

[0115] In addition, you can also configure which skills are required for the current page, including business, equipment, broadcast, risk control and other skills. The configured skills can be configured with relevant information in the management background system. After filling in the relevant parameters, the skill configuration is completed. After configuring the process and form, if you want to link with rasa, you also need to parse the xml file generated by the process. When the parsed json is packaged on the front-end deployment, call the background rasa publishing interface to generate the project file after rasa training is completed. Give the file to the rasa developer and deploy the corresponding rasa program:

[0116] 1. In the console of the current project directory, enter npm run build, use the webpack packager, and generate the rasa project file;

[0117] 2. After packaging is completed, find the rasa.tar.gz file under the front-end deployment package directory, copy it, and give it to the rasa developer.

[0118] Finally, the developed bootstrap service needs to be tested. The testing process is as follows:

[0119] 1. In the console of the current project directory, enter npm run serve to run the project

[0120] 2. Enter the business page path link in the browser and enter the business homepage. If the page appears, it means success.

[0121] 3. Enter the Digital Human path link in the browser and enter the Digital Human guidance page. If this page appears, it means success.

[0122] 4. Enter or speak the intention just configured on the digital human guidance page, such as transfer, and Rasa will recognize the user's intention and start the relevant business processing. The business homepage jumps to the first business node of the business process.

[0123] Furthermore, in some embodiments of the present invention, the business intelligence guidance method further includes the following steps:

[0124] The Dubbo microservice governance system based on the Zookeeper cluster is added to the communication layer 200 through the cluster management module 220;

[0125] Providing asynchronous communication capabilities for the communication layer 200 through the message middleware 230;

[0126] The communication layer 200 also provides message push for the user terminal 130 through the WebSocket protocol.

[0127] In this example, the communication layer 200 includes a central communication gateway 210 (dubbo gateway), so that the communication layer 200 is compatible with the Dubbo microservice gateway, relying on the Dubbo microservice gateway to realize the conversion from the Http protocol to the Dubbo rpc protocol. At the same time, the central microservice is implemented using the Dubbo microservice framework, and can be seamlessly added to the Dubbo microservice governance system based on the Zookeeper cluster (i.e., the cluster management module 220). At the same time, both synchronous and asynchronous communication are required between each layer and each module of the business intelligent guidance system. For this reason, the design of the communication layer 200 combines the microservice gateway (i.e., the central communication gateway) and the message middleware 230 (kafka), and the asynchronous communication requirement is realized based on the kafka message middleware 230 cluster; at the same time, the communication layer 200 also implements page message push through the WebSocket protocol to push messages to the user terminal 130.

[0128] Furthermore, the service intelligent guidance method of the embodiment of the present invention further includes the following steps:

[0129] In the development and testing environment, set up an API baffle; the API baffle is used to prevent access to the preset interface or preset function of the business intelligence guidance system;

[0130] Configure the API baffle to forward access tasks in the actual environment to the development and test environment so that the development and test environment can verify and debug the access tasks.

[0131] Specifically, the development and testing environment is an environment used for testing. It usually simulates the basic architecture of the production environment, but on a smaller scale, so that developers can quickly verify the various functions and performance of their applications in the real environment. The development and testing environment has a baffle API. The API baffle is used in the production environment to prevent high-risk operations or functions that have not yet been developed from affecting the customer experience, and to block access to certain specific interfaces or functions during actual operation. In the development and testing environment, in order to more conveniently verify whether the developed functions can run correctly in the actual environment, we usually need to configure the API baffle appropriately so that access in the production environment can be forwarded to the development and testing environment, so that developers can verify and debug the developed applications at any time in the development and testing environment, and further optimize them.

[0132] Further, in some embodiments of the present invention, when the development and testing environment guides the service to be deployed online to the guidance orchestration module 310 of the central service layer 300, it includes:

[0133] Establish a corresponding release center for each version of the guided business;

[0134] In the release center, set a version number and change log for each version, and establish a rollback mechanism;

[0135] When an error occurs in the released version of the boot service, the previous version of the boot service is returned through the rollback mechanism.

[0136] By independently releasing versions of each application, adopting a single release center model, establishing a dedicated release center, and having dedicated personnel responsible for version release, the quality and stability of version releases can be ensured. The content of each release involves: guided web page information, guided speech reasoning model; in this release center, version numbers, change logs and other information can be set for each independent version to facilitate management and tracking, and a rollback mechanism can be established. After the version is released, if there is a problem, it needs to be rolled back in time. In the event of security issues or erroneous operations, the system can be quickly rolled back to reduce losses.

[0137] Furthermore, in some embodiments of the present invention, a step of upgrading the edge AI server 120 is also included, and the step includes:

[0138] When the current version number of the edge AI server 120 is less than the latest version number, reading the update configuration table;

[0139] According to the update configuration table, determine whether to perform a strong update or a weak update on the edge AI server 120;

[0140] When the edge AI server 120 is forced to update, a pop-up window will be displayed to prompt that it is necessary to force update to the latest version;

[0141] When a weak update is performed on the edge AI server 120, a silent update is performed to update the edge AI server 120 to the latest version.

[0142] The upgrade deployment of the edge AI server 120 is divided into software deployment and upgrade and AI capability model upgrade. The AI ​​capability model upgrade is performed in a silent update mode. After the background server issues an update command, the edge AI server 120 is updated silently in the background system after the bank branch closes. The deployment and upgrade of the application itself is implemented based on the software store, and the upgrade strategy is implemented based on the software upgrade strategy configured in the edge AI server 120. The process of the server obtaining the installation package and upgrade patch is as follows: Figure 3 shown.

[0143] Furthermore, in some embodiments of the present invention, the business intelligence guidance method further includes:

[0144] Monitor user behavior risks through the compliance risk control module 320;

[0145] When abnormal behavior is detected, an alarm operation is performed.

[0146] For example, the system detects the behavior of financial managers operating APP on behalf of customers. If the system detects the behavior of operating on behalf of customers, it records it as an alarm and marks the time when the action occurred. The system detects the behavior of transferring money from POS machines on site. If the system detects the behavior of transferring money on site, it records it as an alarm and marks the time when the transfer occurred. After the identity of the person is determined through face recognition, the person's trajectory is tracked in the video, so that the identity of the person is obtained without the need for face detection in every frame (not every frame can obtain the face for recognition). The violation information detected by the system supports rapid data screening by time range, camera, and whether it is working time period; at the same time, the page will display the violation type, data source, alarm level, occurrence time, alarm content, review status and other related information of each violation record in detail.

[0147] The business intelligent guidance method and system according to the embodiments of the present invention have the following features:

[0148] 1. Digital Human Intelligent Guidance Voice Guidance Method for Business Processing: The intelligent guidance function provides user navigation and assistance for the business all-in-one machine 100, allowing users to complete self-service operations faster and more conveniently. The intelligent guidance function is based on intelligent conversation technology and cooperates with digital human technology to provide users with a more intuitive and friendly guidance method.

[0149] 2. Audio and video risk monitoring during business processing: The intelligent guidance process combined with audio and video detection technology can respond more quickly to changes in the on-site operating environment.

[0150] 3. Development and testing environment: Provides development, training, release and management capabilities for the realization of intelligent guidance capabilities in the business all-in-one machine 100. The development and testing environment focuses on the development of intelligent guidance capabilities and builds the communication environment, business docking environment and AI capability docking, training, release and management environment required for intelligent guidance.

[0151] 4. Visual configuration to guide business: Guide business operation steps through development and test environment configuration to quickly guide business configuration and deployment.

[0152] The business intelligent guidance system makes the use of the business all-in-one machine 100 simple and easy to understand. Customers can easily complete the operation process through the touch screen or other human-computer interaction methods; the interactive process and interactive interface of the business all-in-one machine 100 to assist customers in completing the business process have sufficient affinity, so that customers will not reject the use of self-service mode to complete business; when the customer completes the business operation on the smart self-service device, the smart self-service device can sense the customer's current status and environmental abnormalities, and respond in time to protect the customer's privacy and property safety; the smart self-service device can sense and evaluate the accompanying and assisting behavior of the staff and determine whether the staff's assisting behavior is compliant.

[0153] This business intelligent guidance method can support the construction of a business process from scratch, including the use of process editing, page editing, skill configuration, guidance script configuration and other functions in the development environment. In the background management, configure skill parameters, page templates, page intent, and support viewing log information during process operation.

[0154] The development process of the conversation guidance, business docking and compliance risk control functions of the business all-in-one machine 100 is simple, efficient and stable. It can quickly complete the business process while the self-service equipment is implemented, ensuring that the business guidance process is smooth and friendly. At the same time, it can efficiently use the self-service equipment software and hardware services to construct a safe and compliant self-service business operation environment.

[0155] Although specific embodiments are described herein, those of ordinary skill in the art will recognize that many other modifications or alternative embodiments are also within the scope of the present disclosure. For example, any of the functions and / or processing capabilities described in conjunction with a particular device or component may be performed by any other device or component. In addition, although various exemplary implementations and architectures have been described according to embodiments of the present disclosure, those of ordinary skill in the art will recognize that many other modifications to the exemplary implementations and architectures described herein are also within the scope of the present disclosure.

[0156] Some aspects of the present disclosure are described above with reference to the block diagram and flow chart of the system, method, system and / or computer program product according to exemplary embodiments.It should be understood that the combination of one or more blocks in the block diagram and flow chart and the blocks in the block diagram and flow chart can be realized by executing computer executable program instructions respectively.Equally, according to some embodiments, some blocks in the block diagram and flow chart may not need to be executed in the order shown, or may not need to be executed in full.In addition, additional components and / or operations beyond those components and / or operations shown in the blocks in the block diagram and flow chart may be present in certain embodiments.

[0157] Therefore, the blocks in the block diagrams and flow charts support the combination of devices for performing the specified functions, the combination of elements or steps for performing the specified functions, and the program instruction devices for performing the specified functions. It should also be understood that each block in the block diagrams and flow charts and the combination of blocks in the block diagrams and flow charts can be implemented by a special-purpose hardware computer system or a combination of special-purpose hardware and computer instructions that performs a specific function, element or step.

[0158] The program modules, applications, etc. described herein may include one or more software components, including, for example, software objects, methods, data structures, etc. Each such software component may include computer-executable instructions that, in response to execution, cause at least a portion of the functionality described herein (e.g., one or more operations of the illustrative methods described herein) to be performed.

[0159] Software components can be encoded with any of various programming languages. An exemplary programming language can be a low-level programming language, such as an assembly language associated with a specific hardware architecture and / or an operating system platform. The software component comprising assembly language instructions may need to be converted to executable machine code by an assembler before being executed by hardware architecture and / or platform. Another exemplary programming language can be a higher-level programming language, which can be transplanted across multiple architectures. The software component comprising a higher-level programming language may need to be converted to an intermediate representation by an interpreter or a compiler before execution. Other examples of programming languages ​​include but are not limited to macro languages, shells or command languages, job control languages, scripting languages, database queries or search languages ​​or report writing languages. In one or more exemplary embodiments, the software component comprising the instruction of one of the above-mentioned programming language examples can be directly executed by an operating system or other software components, without first being converted into another form.

[0160] Software components may be stored as files or other data storage structures. Software components of similar type or related functions may be stored together, such as in a specific directory, folder, or library. Software components may be static (e.g., preset or fixed) or dynamic (e.g., created or modified at execution time).

[0161] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of ordinary technicians in the relevant technical field without departing from the purpose of the present invention.

Claims

1. A business intelligence guidance method, characterized in that: Applied to a business intelligent guidance system, the business intelligent guidance system includes a device layer, a communication layer, a central service layer and a development and testing environment, the communication layer is respectively connected to the device layer and the central service layer for communication, the device layer includes a business all-in-one machine and an edge AI server, the communication layer includes a central communication gateway, and the central service layer includes a guidance orchestration module; the business intelligent guidance method includes the following steps: Acquire attribute information of the business intelligent guidance system; the attribute information includes address information of the central communication gateway, configuration information and access address of the business all-in-one machine, and address information of the edge AI server; According to the attribute information, combined with the business process, a business process description file is formed, and the business process description file is sent to the development and testing environment; On the development and testing environment, according to the business process description file, the configuration and development of the guidance service are completed in a visual manner, and the guidance service is tested; The development and testing environment deploys the guidance service online to the guidance orchestration module of the central service layer; the guidance service includes a guidance service integration interface and a guidance speech model; The central service layer provides business guidance services for the business process of the business machine based on the guidance orchestration module.

2. The business intelligent guidance method according to claim 1, characterized in that: The device layer also includes a user terminal, the communication layer also includes a cluster management module and a message middleware, and the business intelligent guidance method also includes: Add the Dubbo microservice governance system based on the Zookeeper cluster to the communication layer through the cluster management module; Providing asynchronous communication capability for the communication layer through the message middleware; The communication layer also provides message push for the user terminal through the WebSocket protocol.

3. The business intelligent guidance method according to claim 1, characterized in that: The step of completing the configuration and development of the guidance service in a visual manner according to the business process description file on the development and testing environment, and testing the guidance service includes: In the development and testing environment, a process file is created; the process file includes a start node; In response to a selection operation on a configuration item of an interface of the development and testing environment, initially configuring the process file; In response to the selection operation of the task item of the interface of the development and testing environment, a connection relationship between each task node and the start node is established, and a jump condition between each task node is configured, and an end node is connected at the last task node to complete the process configuration of the process file; Use existing components or low-code platforms to configure the current page for each of the task nodes; Configure the guidance words on the process file to complete the configuration and development of the guidance business; The bootstrap service is tested.

4. The business intelligent guidance method according to claim 3, characterized in that: Also includes: Get the user's audio and video information; The edge AI server identifies the user intention based on the audio and video information; According to the user's intention, jump to and execute the business process corresponding to the corresponding task node.

5. The business intelligent guidance method according to claim 1, characterized in that: The business intelligent guidance method comprises the following steps: In the development and testing environment, an API baffle is set; the API baffle is used to prevent access to a preset interface or preset function of the business intelligent guidance system; The API baffle is configured so that the access task in the actual environment is forwarded to the development and testing environment, so that the development and testing environment verifies and debugs the access task.

6. The business intelligent guidance method according to claim 1, characterized in that: The step of the development and testing environment deploying the guidance service online to the guidance orchestration module of the central service layer includes: Establishing a corresponding publishing center for each version of the guiding service; In the release center, a version number and a change log are set for each version, and a rollback mechanism is established; When an error occurs in the published version of the boot service, the previous version of the boot service is returned through the rollback mechanism.

7. The business intelligent guidance method according to claim 1, characterized in that: The central service layer also includes an RPA module; the business intelligent guidance method also includes the following steps: Use Dubbo RPC mode to connect the guidance service with the business process; or, The guiding business is connected to the business process through the RPA module.

8. The business intelligent guidance method according to claim 1, characterized in that: The step of upgrading the edge AI server is also included, which includes: When the current version number of the edge AI server is less than the latest version number, read the update configuration table; According to the update configuration table, determine whether to perform a strong update or a weak update on the edge AI server; When the edge AI server is forced to update, a pop-up window will be displayed to prompt that it needs to be forced to update to the latest version; When the edge AI server is weakly updated, a silent update is performed to update the edge AI server to the latest version.

9. The business intelligent guidance method according to claim 1, characterized in that: The central service layer also includes a compliance risk control module, and the business intelligent guidance method also includes: Conduct risk monitoring of user behaviors through the compliance risk control module; When abnormal behavior is detected, an alarm operation is performed.

10. A business intelligent guidance system, characterized in that: The business intelligent guidance system includes a device layer, a communication layer, a central service layer and a development and testing environment. The communication layer is communicated with the device layer and the central service layer respectively. The device layer includes a business all-in-one machine and an edge AI server. The central service layer includes a central communication gateway. The central service layer includes a guidance orchestration module. The business intelligent guidance system is used to execute the business intelligent guidance method as described in any one of claims 1 to 9.

Images