Smart terminal service system for power industry

Abstract

The invention provides an intelligent terminal service system for the power industry, and the system comprises an interaction module which is used for obtaining interaction information inputted by a user; the instruction identification module is used for inputting the interaction information into a preset identification model to identify the operation instruction to obtain a classification result corresponding to the operation instruction; according to a classification result corresponding to the operation instruction, dividing the operation instruction into a corresponding service component; the classification result at least comprises a business handling instruction or a service query instruction; and the instruction execution module is used for calling the corresponding business logic parameters through the corresponding standardized interfaces according to the identified operation instructions and executing the corresponding business logic actions to obtain corresponding execution results. According to the method, through virtual human voice interaction, traditional static menu page clicking is replaced, and by means of large model and business component packaging, user intention recognition and business handling are achieved, the system use threshold is lowered, and the service satisfaction degree is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system automation, and in particular to an intelligent terminal business system for the power industry. Background Art

[0002] With the deepening of the digital transformation of the power industry, the upgrade of traditional power grids to smart grids has become a trend. Digitalization has promoted the integration and analysis of power data, and provided a technical basis and data support for the application of virtual humans and large models. The development of artificial intelligence technology has brought new productivity to the power industry, achieving more efficient data analysis, prediction and decision support. In addition, the power industry is facing the pressure of falling electricity prices, so reducing costs and increasing efficiency have become important tasks for power grid companies. Through digitalization and artificial intelligence, power companies can optimize resource allocation, reduce waste, and improve operational efficiency.

[0003] The smart terminal business system has many functions, complicated menus, and high usage costs. It has a high learning cost and is not user-friendly for new and elderly users. Summary of the invention

[0004] The purpose of the present invention is to propose a smart terminal business system for the power industry to solve the technical problems of how to realize user intention recognition and business processing, lower the threshold for system use, and improve service satisfaction.

[0005] On the one hand, a smart terminal business system for the power industry is provided, comprising:

[0006] An interaction module, used to obtain interaction information input by a user; wherein the interaction information at least includes instruction information or voice communication information;

[0007] The instruction recognition module is used to input the interaction information into a preset recognition model to recognize the operation instruction, and obtain the classification result corresponding to the operation instruction; and classify the operation instruction into the corresponding business component according to the classification result corresponding to the operation instruction; the classification result at least includes a business processing instruction or a service query instruction; the business component at least includes a business processing component or a service query component; the business component sets the preset business logic parameters and provides the corresponding standardized interface;

[0008] The instruction execution module is used to call the corresponding business logic parameters through the corresponding standardized interface according to the identified operation instructions, and execute the corresponding business logic actions to obtain the corresponding execution results.

[0009] Preferably, the business handling instruction includes at least a payment inquiry sub-instruction, a bill printing sub-instruction and a transfer sub-instruction.

[0010] Preferably, the service query instruction includes at least an electricity balance and bill query sub-instruction, an information query sub-instruction, a satisfaction feedback submission sub-instruction, and a customer service contact and consultation sub-instruction.

[0011] Preferably, the business processing component at least includes packaging payment business process parameters, printing business process parameters, transfer business process parameters and corresponding execution interfaces.

[0012] Preferably, the service query component at least includes encapsulated query service logic parameters, feedback service logic parameters, customer service logic parameters and corresponding execution interfaces.

[0013] Preferably, the interaction module is also used to, if no matching operation instruction is found in the initial identification, continue to obtain new interaction information input by the user and identify the new interaction information until an operation instruction is identified or an exit instruction input by the user is received.

[0014] Preferably, the instruction recognition module is specifically used to determine the corresponding text information based on the interaction information, and perform intention recognition through a preset text language processing model; if an operation instruction is recognized, the corresponding business component is called to perform the instruction operation, and the instruction result text is returned to the text language processing model; if a response text is recognized, the response text is returned to the text language processing service model.

[0015] Preferably, the instruction execution module is also used to obtain satisfaction information input by the user after outputting the execution result; if the satisfaction information is satisfactory, end the current dialogue with the user; if the satisfaction information is unsatisfactory, continue the dialogue until the user's satisfaction information is satisfactory or an exit instruction input by the user is received.

[0016] In summary, the implementation of the embodiments of the present invention has the following beneficial effects:

[0017] The smart terminal business system for the power industry provided by the present invention replaces the clicks on traditional static menu pages through virtual human voice interaction, and realizes user intention recognition and business processing with the help of large models and business component encapsulation, thereby lowering the threshold for system use and improving service satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying creative labor, other drawings obtained based on these drawings still belong to the scope of the present invention.

[0019] Figure 1Schematic diagram of a smart terminal business system for the power industry in an embodiment of the present invention.

[0020] Figure 2 This is a logical schematic diagram of a smart terminal business system for the power industry in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention will be further described in detail below with reference to the accompanying drawings.

[0022] like Figure 1 and Figure 2 FIG. 1 is a schematic diagram of an embodiment of a smart terminal service system for the power industry provided by the present invention. In this embodiment, it includes:

[0023] The interactive module is used to obtain the interactive information input by the user; wherein the interactive information at least includes instruction information or voice communication information; it can be understood that the user communicates with the virtual person through the dialogue interface of the smart terminal. The virtual person service converts the user's voice into text and sends it to the big model for instruction recognition.

[0024] The instruction recognition module is used to input the interactive information into the preset recognition model to recognize the operation instruction and obtain the classification result corresponding to the operation instruction; and the operation instruction is divided into the corresponding business component according to the classification result corresponding to the operation instruction; the classification result at least includes the business handling instruction or the service query instruction; the business component at least includes the business handling component or the service query component; the business component sets the preset business logic parameters and provides the corresponding standardized interface; it is understandable that in the smart terminal system, the operation instruction is finely classified, mainly including two categories: business handling instructions and service query instructions. After the classification is completed, the big model is specially trained for each type of instruction to ensure the accuracy and efficiency of instruction recognition. According to the classification result of the operation instruction, the business component is correspondingly divided into the business handling component and the service query component. Each component implements the specific business logic internally and provides a standardized interface for the virtual person to call quickly. The big model (recognition model) parses the text according to the training results and identifies the corresponding operation instruction; the setting of the recognition model can be an AI algorithm model, which at least includes a speech-to-text component, a language big model and a text-to-speech component, etc., which belongs to the conventional setting in this field and will not be repeated here.

[0025] In one embodiment, the business handling instructions at least include payment inquiry sub-instructions, bill printing sub-instructions and transfer sub-instructions. The service inquiry instructions at least include electricity balance and bill inquiry sub-instructions, information inquiry sub-instructions, satisfaction feedback submission sub-instructions and customer service contact and consultation sub-instructions. Business handling instructions: subdivided into payment inquiry, bill printing, transfer and other specific sub-instructions. Service inquiry instructions: subdivided into electricity balance and bill inquiry, information inquiry (such as service outlets, policy interpretation), satisfaction feedback submission, customer service contact and consultation and other specific sub-instructions.

[0026] In one embodiment, the business processing component at least includes encapsulating payment business process parameters, printing business process parameters, transfer business process parameters and corresponding execution interfaces. The service query component at least includes encapsulating query service logic parameters, feedback service logic parameters, customer service service logic parameters and corresponding execution interfaces. Business processing component: encapsulates payment, printing, transfer and other business processes, and provides a one-click entry and execution method. Service query component: encapsulates query, feedback, customer service and other service logics to ensure the immediacy and accuracy of information acquisition and feedback.

[0027] In one embodiment, the instruction recognition module is also used to, if no matching operation instruction is found in the initial recognition, continue to obtain new interaction information input by the user and recognize the new interaction information until the operation instruction is recognized or the exit instruction input by the user is received. The instruction recognition module is specifically used to determine the corresponding text information according to the interaction information, and perform intention recognition through a preset text language processing model; if the operation instruction is recognized, the corresponding business component is called to perform the instruction operation, and the instruction result text is returned to the text language processing model; if the response text is recognized, the response text is returned to the text language processing service model. It can be understood that the user performs voice or text input at the business hall terminal, and the business hall processes the input into text. If the input is voice, the business hall terminal calls the algorithm component through the virtual human service to convert the voice into text and return the text to the virtual human service. If the input is text, it is directly sent to the virtual human service. The virtual human calls the text language processing service for intention recognition after receiving the text. If the operation instruction is recognized, the business hall system service is directly called to perform the instruction operation, and the instruction result text is returned to the text language processing service. If the response text is recognized, it is directly returned to the text language processing service. The text language processing service receives the text result content and calls the text-to-speech component, which is then played by the virtual person.

[0028] The instruction execution module is used to call the corresponding business logic parameters through the corresponding standardized interface according to the identified operation instructions, and execute the corresponding business logic actions to obtain the corresponding execution results.

[0029] In one embodiment, the instruction execution module is further used to obtain the satisfaction information input by the user after outputting the execution result; if the satisfaction information is satisfactory, the current dialogue with the user is terminated; if the satisfaction information is unsatisfactory, the dialogue is continued until the user's satisfaction information is satisfactory or an exit instruction input by the user is received. Once the accurate instruction is identified, the virtual person will call the corresponding business component method, perform specific business operations, and feedback the results to the user. If the user is satisfied with the result, the current dialogue is terminated; if not, the system will continue the dialogue until the user is satisfied or the user actively exits.

[0030] In summary, the implementation of the embodiments of the present invention has the following beneficial effects:

[0031] The smart terminal business system for the power industry provided by the present invention replaces the clicks on traditional static menu pages through virtual human voice interaction, and realizes user intention recognition and business processing with the help of large models and business component encapsulation, thereby lowering the threshold for system use and improving service satisfaction.

[0032] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A smart terminal business system for the power industry, characterized in that: include: An interaction module, used to obtain interaction information input by a user; wherein the interaction information at least includes instruction information or voice communication information; The instruction recognition module is used to input the interaction information into a preset recognition model to recognize the operation instruction, and obtain the classification result corresponding to the operation instruction; and classify the operation instruction into the corresponding business component according to the classification result corresponding to the operation instruction; the classification result at least includes a business processing instruction or a service query instruction; the business component at least includes a business processing component or a service query component; the business component sets the preset business logic parameters and provides the corresponding standardized interface; The instruction execution module is used to call the corresponding business logic parameters through the corresponding standardized interface according to the identified operation instructions, and execute the corresponding business logic actions to obtain the corresponding execution results.

2. The system according to claim 1, characterized in that The business handling instruction at least includes a payment inquiry sub-instruction, a bill printing sub-instruction and a transfer sub-instruction.

3. The system according to claim 2, characterized in that The service inquiry instruction at least includes an electricity balance and bill inquiry sub-instruction, an information inquiry sub-instruction, a satisfaction feedback submission sub-instruction, and a customer service contact and consultation sub-instruction.

4. The system according to claim 3, characterized in that The business processing component at least includes packaging payment business process parameters, printing business process parameters, transfer business process parameters and corresponding execution interfaces.

5. The system according to claim 4, characterized in that The service query component at least includes encapsulating query service logic parameters, feedback service logic parameters, customer service logic parameters and corresponding execution interfaces.

6. The system according to claim 5, characterized in that The instruction recognition module is also used to, if no matching operation instruction is found in the initial recognition, continue to obtain new interaction information input by the user and recognize the new interaction information until an operation instruction is recognized or an exit instruction input by the user is received.

7. The system according to claim 6, characterized in that The instruction recognition module is specifically used to determine the corresponding text information based on the interaction information, and perform intent recognition through a preset text language processing model; if an operation instruction is recognized, the corresponding business component is called to perform the instruction operation, and the instruction result text is returned to the text language processing model; if a response text is recognized, the response text is returned to the text language processing service model.

8. The system according to claim 7, characterized in that The instruction execution module is also used to obtain satisfaction information input by the user after outputting the execution result; if the satisfaction information is satisfactory, end the current dialogue with the user; if the satisfaction information is unsatisfactory, continue the dialogue until the user's satisfaction information is satisfactory or an exit instruction input by the user is received.

Images