Information interaction method and program product for power system

Abstract

The invention discloses an information interaction method and program product for a power system, and the method comprises the steps: displaying a target interaction interface in which a virtual object is displayed, and the virtual object is presented as first presentation information; in response to an information interaction request for the virtual object, target interaction information is obtained, the virtual object is presented in the form of second presentation information, and the target interaction information at least carries inquiry information associated with the electric power information; target response information corresponding to the target interaction information is generated based on a preset data interface and a power grid knowledge base, and the preset data interface is used for querying real-time operation associated data of a power system; third presentation information of the virtual object is generated according to the target response information, and the virtual object is presented on the target interaction interface through the third presentation information; the convenience and accuracy of information interaction of a power system are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and in particular to an information interaction method and program product for a power system. BACKGROUND

[0002] As a core infrastructure for guaranteeing people's livelihood and supporting the normal operation of society, the convenience and response efficiency of the power system are directly related to the power experience of users and the overall social operation efficiency. In daily operation, inquiries about power system-related knowledge and consultations on personal power information are often received.

[0003] Currently, information is obtained through methods such as user calls to artificial customer service telephone consultations or self-querying, which is cumbersome and difficult to obtain information. Moreover, it is limited by the uneven professional knowledge reserves and practical ability of artificial customer service personnel, which is prone to problems such as deviation in understanding user intent, slow response speed, inaccurate or mismatched answers, and seriously affects service efficiency and user experience. Therefore, an information interaction method is urgently needed to improve the convenience and accuracy of power system information interaction. SUMMARY

[0004] The present application provides an information interaction method and program product for a power system to solve the problem of difficult operation, slow artificial service response, unstable answer quality, and deviation in understanding intent in the process of users obtaining power system information, which leads to difficult information acquisition and poor interaction experience for users.

[0005] According to an aspect of the present application, an information interaction method for a power system is provided, which comprises:

[0006] displaying a target interaction interface, wherein a virtual object is displayed in the target interaction interface, and the virtual object is presented with first presentation information;

[0007] in response to an information interaction request for the virtual object, obtaining target interaction information, and presenting the virtual object with second presentation information, wherein the target interaction information at least carries inquiry information associated with power information;

[0008] generating target response information corresponding to the target interaction information based on a preset data interface and a power grid knowledge base, wherein the preset data interface is used to query real-time operation associated data of the power system;

[0009] generating third presentation information of the virtual object according to the target response information, and presenting the virtual object with the third presentation information in the target interaction interface.

[0010] According to another aspect of the present application, an information interaction device for a power system is provided, which comprises:

[0011] a first presentation module configured to display a target interactive interface, the target interactive interface having a virtual object displayed therein, and the virtual object being presented with first presentation information;

[0012] a second presentation module configured to, in response to an information interaction request for the virtual object, acquire target interaction information, and present the virtual object with second presentation information, wherein the target interaction information carries at least inquiry information associated with power information;

[0013] a target response information generation module configured to generate target response information corresponding to the target interaction information based on a preset data interface and a power grid knowledge base, wherein the preset data interface is used to query real-time operation related data of a power system;

[0014] a third presentation module configured to generate third presentation information of the virtual object according to the target response information, and present the virtual object with the third presentation information in the target interactive interface.

[0015] According to another aspect of the present application, an electronic device is provided, which comprises:

[0016] at least one processor; and

[0017] a memory connected to the at least one processor in communication; wherein

[0018] 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 to enable the at least one processor to execute the information interaction method for a power system according to any one of the embodiments of the present application.

[0019] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to implement the information interaction method for a power system according to any one of the embodiments of the present application when executed by the processor.

[0020] According to another aspect of the present application, the embodiments of the present disclosure further provide a computer program product comprising a computer program which, when executed by a processor, implements the information interaction method for a power system according to any one of the embodiments of the present disclosure.

[0021] The technical scheme of the embodiment of the present application firstly displays a target interactive interface, the target interactive interface has a virtual object displayed therein, and the virtual object is presented with first presentation information; abstract power information interaction is converted into concrete virtual object presentation, which is more intuitive than a text interface and reduces the operation threshold for power information interaction; then, in response to an information interaction request for the virtual object, target interaction information is acquired, and the virtual object is presented with second presentation information, wherein the target interaction information at least carries inquiry information associated with power information; the information interaction request is responded to in real time, the timeliness requirement for power information query is met, the interaction progress can be clearly perceived through feedback of the change of the second presentation information that the interaction request has been received; then, target response information corresponding to the target interaction information is generated based on a preset data interface and a power grid knowledge base, wherein the preset data interface is used to query real-time operation associated data of a power system; real-time power data is acquired in combination with the preset data interface, so that the target response information has real-time performance, accurately reflects the current operation state of the power system, and at the same time guarantees the professionalism and accuracy of the target response information according to the power grid knowledge base; finally, third presentation information of the virtual object is generated according to the target response information, and the virtual object is presented with the third presentation information in the target interactive interface; the response result is presented with the third presentation information, the consistency of the interaction process is maintained, the user experience is improved, the response information is converted into presentation information of the virtual object, complex power data is converted into a form that is easier to understand, the user can quickly grasp key information and more easily understand complex power response content, the problems of inefficient interaction and non-uniform information are effectively solved, and an efficient, accurate and friendly power information interaction experience is provided for the user.

[0022] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0024] Figure 1 is a flowchart of a power system information interaction method according to the first embodiment of the present application;

[0025] Figure 2 is a flowchart of a power system information interaction method according to the second embodiment of the present application;

[0026] Figure 3a is a flow chart of a method for information interaction for a power system according to an embodiment of the present application;

[0027] Figure 3b is a flow chart of a method for information interaction for a power system according to an embodiment of the present application;

[0028] Figure 4 is a structural schematic diagram of an information interaction device for a power system according to an embodiment of the present application;

[0029] Figure 5 is a structural schematic diagram of an electronic device implementing a method for information interaction for a power system according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to make the personnel in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0031] It should be noted that the terms "first", "second", "third", "target" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0032] It should be noted that the modification of "one" or "multiple" mentioned in the present disclosure is illustrative but not restrictive, and those skilled in the art should understand that unless otherwise explicitly indicated in the context, it should be understood as "one or more".

[0033] The names of the messages or information exchanged between the multiple devices in the embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of the messages or information.

[0034] It can be understood that, before using the technical solutions disclosed in the embodiments of the present disclosure, the type, use range, use scenario, etc. of the personal information involved in the present disclosure should be informed to the user and the authorization of the user should be obtained through appropriate means according to relevant laws and regulations.

[0035] For example, in response to receiving the active request of the user, the user is sent prompt information to explicitly prompt the user that the operation requested to be performed will require obtaining and using the personal information of the user. Thus, the user can voluntarily choose whether to provide the personal information to the software or hardware such as electronic device, application program, server or storage medium, etc. that performs the operation of the technical solutions of the present disclosure according to the prompt information.

[0036] As an optional but non-limiting implementation manner, in response to receiving the active request of the user, the manner of sending prompt information to the user may, for example, be the manner of pop-up window, and the prompt information may be presented in the form of text in the pop-up window. In addition, the pop-up window may also carry selection controls for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0037] It can be understood that the above notification and user authorization process is only illustrative and does not limit the implementation of the present disclosure, and other manners that meet the relevant laws and regulations can also be applied to the implementation of the present disclosure.

[0038] It can be understood that the data (including but not limited to the data itself, the acquisition or use of the data) involved in the present technical solution should comply with the requirements of the relevant laws and regulations and relevant provisions.

[0039] Embodiment one

[0040] Figure 1 A flowchart of an information interaction method for a power system is provided for the first embodiment of the present application. The present embodiment can be applied to information interaction of a power system based on virtual objects. The method can be performed by an information interaction device for a power system, which can be realized in the form of hardware and / or software. Optionally, the information interaction device for a power system is realized by an electronic device, which can be a mobile terminal, a PC terminal, or a server, etc. Figure 1 As shown in the figure, the method can specifically include:

[0041] S110, display a target interaction interface, the target interaction interface has a virtual object displayed therein, and the virtual object is presented with first presentation information.

[0042] In the embodiments of the present application, the target interactive interface can be understood as a visual interface that can be used for information interaction, and a virtual object is displayed on the target interactive interface to realize human-computer interaction. The virtual object can be understood as a digital object for information interaction, which can be obtained by 2D / 3D model rendering, and can present different presentation states according to the information interaction content to dynamically present and deliver power system related information.

[0043] The first presentation information can be the presentation state of the virtual object when it is initially displayed, that is, the default presentation form before any information interaction is triggered. For example, the first presentation information can include, but is not limited to, the initial mouth shape, expression and body movement of the virtual object, etc.

[0044] Optionally, before the information interaction is triggered, the target interactive interface can be displayed, and the virtual object can be presented with the first presentation information.

[0045] S120, in response to the information interaction request for the virtual object, obtaining target interactive information, and presenting the virtual object with second presentation information, wherein the target interactive information at least carries inquiry information associated with power information.

[0046] The information interaction request can be initiated for the virtual object, and is a request for triggering information interaction. The information interaction request can be triggered by inputting a text inquiry, a voice inquiry, a gesture operation, etc. For example, information such as "my home xx community is out of power, how did it happen" can be input by voice or text, which can trigger the information interaction request.

[0047] Optionally, in response to the information interaction request, the target interactive information is extracted from the information interaction request. Specifically, if the target interactive information is carried in the information interaction request, the target interactive information is directly extracted from the information interaction request; if the information interaction request is only used as an interaction trigger signal, the input content in the subsequent preset time period can be collected after the information interaction request is obtained, and the target interactive information is obtained based on the collected content.

[0048] The target interactive information can be the interaction content obtained in response to the information interaction request, and the target interactive information at least carries inquiry information associated with power information. The power information can be related information of the power system, such as power system operation, power service, equipment management, etc., for example, power failure information, real-time power operation data, etc.

[0049] Optionally, to adapt to diversified interactive output forms, the virtual object can realize bidirectional data format conversion of Speech-to-Text (STT) and Text-to-Speech (TTS), can convert voice input into text for analysis, or can convert generated text response information into voice for broadcasting, to adapt to information interaction requirements in different interactive scenarios and improve the flexibility and convenience of interaction.

[0050] The second presentation information can be a presentation form of the virtual object after responding to the information interaction request, for prompting that the information interaction request has been received. For example, the second presentation information can include, but is not limited to, various forms such as that the virtual object changes from static to dynamic, displays prompt text that is processing your request, and the like.

[0051] After obtaining the target interaction information, the virtual object can be presented in the second presentation information to realize real-time feedback of the information interaction request receiving state.

[0052] S130, generating target response information corresponding to the target interaction information based on a preset data interface and a power grid knowledge base, wherein the preset data interface is used to query real-time running associated data of the power system.

[0053] The preset data interface refers to an interface developed and configured in advance for interfacing various data storage modules of the power system. It can be used to query real-time running associated data of the power system to ensure the real-time nature of the response information. The real-time running associated data of the power system refers to data generated in real time during the operation of the power system and can be used to reflect the running state of the system, such as real-time running data of the power grid, device status, and operation and maintenance personnel location. The power grid knowledge base refers to a database storing knowledge related to the power system, which can include, but is not limited to, structured power industry regulation documents and unstructured historical fault handling documents, cases, and device parameter manuals, and the like. It provides professional knowledge support for the generation of target response information.

[0054] Optionally, the target interaction information can be processed, and real-time running associated data of the power system obtained in real time by the preset data interface and professional knowledge stored in the power grid knowledge base are analyzed and text is generated to determine the target response information corresponding to the target interaction information. The target response information refers to reply information corresponding to the target interaction information generated based on the real-time running associated data queried by the preset data interface and the stored knowledge in the power grid knowledge base. It can be an inquiry reply, operation content, result feedback, and the like for the target interaction information. For example, it is confirmed that tripping is caused by overload of the XX line, a repair work order is automatically generated, and the estimated power supply restoration time is 2 hours, and the like.

[0055] On the basis of the above scheme, optionally, the target interaction information includes power failure inquiry information, and the target response information includes power failure reply information and a fault repair work order; after the target response information corresponding to the target interaction information is generated based on the preset data interface and the power grid knowledge base, the method further includes: determining a fault repair operation according to the fault repair work order and the power grid knowledge base, calling the preset data interface to obtain available resources of the power system, generating a fault repair task according to the fault repair operation and the available resources, and distributing the fault repair task to a task performer of the fault repair task.

[0056] The power failure inquiry information can be inquiry content about a power failure, such as information about what happened when the power at home suddenly went out, when the power in the community will be restored, and the like. The power failure reply information can be reply content to the power failure inquiry information, such as information about a fault reason explanation, a temporary processing suggestion, and the like. The fault repair work order can be a standardized document recording fault information and repair requirements, which includes but is not limited to fault location, fault type, fault occurrence time, expected repair time limit, and the like. The fault repair operation can be a repair operation determined according to the fault repair work order and the power grid knowledge base. The fault repair task can be a specific task generated according to the fault repair operation requirement and the available resources, which can be assigned to a task performer. The task performer of the fault repair task can be a person responsible for performing the fault repair task.

[0057] The available resources can be various resources in the power system that can be used to perform the fault repair operation, such as maintenance personnel, maintenance vehicles, maintenance equipment, and the like, which can be queried through the preset data interface. Optionally, to improve the resource calling and business cooperation efficiency, various business functions that can be managed in the power system can be pre-packaged as standardized Application Programming Interface (API) tools for subsequent planning and calling. At the same time, permission and risk verification can be performed before tool calling when the target response information is executed.

[0058] Specifically, the corresponding power failure reply information and the failure repair work order can be determined based on the user failure inquiry information, the failure repair operation required for repairing the failure can be determined according to the failure repair work order, then the power grid real-time operation associated data can be obtained by calling the preset data interface, and the service resources available to the power system can be determined; according to the failure repair operation and the available resources, the optimal failure repair task is planned and generated by combining the optimization algorithm, and is distributed to the appropriate task performer. For example, when a power failure occurs in a certain cell, the power supply line related to the cell and the common failure type can be retrieved based on the power grid knowledge base, then the preset data interface is called, such as the address query power failure range tool, the real-time data acquisition and monitoring control system (Supervisory Control and Data Acquisition, SCADA) real-time alarm tool, if it is determined that there is a failure, the repair work order tool is called to generate the work order, the corresponding API is called according to the planned failure repair operation, and the real-time data such as whether there is a planned power failure and whether there is a line trip in the cell are obtained from the geographic information system (Geographic Information System, GIS) and the SCADA system, then the available resources such as the nearest repair team that can repair the failure are determined by comprehensively obtaining the real-time data, finally, the detailed failure repair task is generated and distributed to the corresponding repair team by combining the determined failure repair operation and the target interaction information, so as to realize the whole-process automatic processing from the failure inquiry to the task distribution, and improve the failure repair response speed and the scheduling efficiency.

[0059] On the basis of the above scheme, optionally, the target interaction information includes power failure inquiry information, and the target response information includes power failure reply information and a failure repair work order; after the target response information corresponding to the target interaction information is generated based on the preset data interface and the power grid knowledge base, the method further includes: calling a preset data interface to obtain failure repair execution information associated with the failure repair work order, determining fourth presentation information of the virtual object according to the failure repair execution information, and presenting the virtual object in the fourth presentation information on the target interaction interface.

[0060] Among them, the failure repair execution information can be repair progress data associated with the failure repair work order obtained by querying the preset data interface, such as failure repair work order number, estimated recovery time and the like. The fourth presentation information can be the presentation form of the virtual object generated according to the failure repair execution information, which is used to display the repair progress in real time.

[0061] Specifically, the preset data interface can be called to obtain fault repair execution information associated with the fault repair work order, and the fault repair execution information is converted into voice through TTS. Fourth presentation information is determined according to the fault repair execution information, and the virtual object is presented in the target interactive interface in the fourth presentation information, so as to realize the visual feedback of the repair progress.

[0062] Optionally, the GIS system can be used to update the position of the task performer in real time, and the mobile terminal such as the mobile phone APP of the repair personnel can be used to upload the repair operation record in real time, so as to ensure the real-time and accuracy of the fault repair execution information and provide data support for the accurate generation of the fourth presentation information.

[0063] The fault repair execution information is obtained through the preset data interface and converted into the fourth presentation information of the virtual object for display, so that the fault repair progress can be intuitively and real-timely understood, the perception of the service process is improved, and the transparency of information interaction is enhanced.

[0064] S140, generating third presentation information of the virtual object according to the target response information, and presenting the virtual object in the target interactive interface in the third presentation information.

[0065] The third presentation information can be the presentation form of the virtual object generated according to the target response information, and is used to deliver the target response information.

[0066] On the basis of the above scheme, the third presentation information includes object response audio and object response action; the third presentation information of the virtual object is generated according to the target response information, including: determining the object response audio and the object response action of the virtual object according to the target response information, and displaying the object response audio and the object response action based on the virtual object.

[0067] The object response audio can be audio content played by the virtual object generated according to the target response information. Optionally, the text content of the target response information can be converted into audio through TTS technology and played by the virtual object.

[0068] The object response action can be a limb action or expression of the virtual object generated according to the target response information. Optionally, the corresponding object response action can be generated according to the content or emotional tendency of the target response information. For example, when confirming the fault, the expression state of the virtual object can be changed to serious concern to show the importance of the fault problem; when the fault repair work order processing is successful, the tone state of the virtual object can be changed to relaxed affirmation; when waiting for fault repair execution information, the virtual object can present an animation simulating thinking and other presentation states.

[0069] Further, the object response audio and the object response action of the virtual object can be synchronously displayed based on the virtual object, and presented on the target interaction interface, realizing double information transmission of vision and hearing, improving information receiving efficiency and user interaction experience, reducing information acquisition difficulty, and the object response action of the virtual object can also make the abstract power response information concrete, helping users quickly understand the response content, and further optimizing the friendliness of the interaction experience and the information transmission efficiency.

[0070] The technical scheme of the embodiment of the application first displays a target interaction interface, the target interaction interface displays a virtual object, and the virtual object is presented with first presentation information; abstract power information interaction is converted into concrete virtual object presentation, which is more intuitive than a text interface and reduces the operation threshold of power information interaction; then, target interaction information is acquired in response to an information interaction request for the virtual object, and the virtual object is presented with second presentation information, wherein the target interaction information at least carries inquiry information associated with power information; the information interaction request is responded to in real time, the timeliness requirement of power information query is met, the interaction progress can be clearly perceived through the feedback of the change of the second presentation information that the interaction request has been received; then, target response information corresponding to the target interaction information is generated based on a preset data interface and a power grid knowledge base, wherein the preset data interface is used to query real-time operation associated data of a power system; the real-time power data is acquired by combining the preset data interface, so that the target response information has real-time performance and accurately reflects the current operation state of the power system, and the professional and accurate performance of the target response information is ensured according to the power grid knowledge base; finally, third presentation information of the virtual object is generated according to the target response information, and the virtual object is presented on the target interaction interface with the third presentation information; the response result is presented with the third presentation information, the consistency of the interaction process is maintained, the user experience is improved, the response information is converted into the presentation information of the virtual object, the complex power data is converted into a form that is easier to understand, the user can quickly grasp the key information and more easily understand the complex power response content, the problems of inefficient interaction and non-uniform information are effectively solved, and the user is provided with an efficient, accurate and friendly power information interaction experience.

[0071] Embodiment two

[0072] Figure 2A flowchart of an information interaction method for a power system is provided for the second embodiment of the present application, further describing the implementation of generating target response information corresponding to target interaction information. Optionally, the target response information corresponding to the target interaction information is generated based on the preset data interface and the power grid knowledge base, including: the target interaction information is analyzed by a preset decision layer to obtain a target interaction intent, the target power-related data corresponding to the target interaction intent is determined based on the preset data interface and the power grid knowledge base, and the target response information is generated according to the target power-related data. The specific implementation can be referred to the description of the present embodiment. Wherein, the same or similar technical features as the foregoing embodiments are not described herein. As shown in Figure 2 The method can specifically include:

[0073] S210, a target interaction interface is displayed, a virtual object is displayed in the target interaction interface, and the virtual object is presented with first presentation information.

[0074] S220, in response to an information interaction request for the virtual object, target interaction information is obtained, and the virtual object is presented with second presentation information, wherein the target interaction information carries at least inquiry information associated with power information.

[0075] S230, the target interaction information is analyzed by a preset decision layer to obtain a target interaction intent, the target power-related data corresponding to the target interaction intent is determined based on the preset data interface and the power grid knowledge base, and the target response information is generated according to the target power-related data, wherein the preset data interface is used to query real-time operation-related data of the power system.

[0076] In the embodiment of the present application, the preset decision layer can be understood as a functional module pre-built for analyzing target interaction information, which can extract the target interaction intent from the target interaction information to provide direction for subsequent data acquisition and response information generation. The target interaction intent can be the core purpose of interaction obtained by analyzing the preset decision layer, such as querying the power failure reason of a certain community, querying the electricity bill, etc. The target power-related data can be the power data directly related to the target interaction intent determined based on the preset data interface and the power grid knowledge base, such as the information of the power supply line related to a certain community, common fault types, etc.

[0077] Optionally, the preset decision layer can be a large language model (LLM) which has powerful natural language understanding and generation capabilities, can efficiently process fuzzy and colloquial target interaction information, and can improve the accuracy and efficiency of intent analysis.

[0078] Based on the above scheme, optionally, the target interaction information is parsed by the preset decision layer to obtain a target interaction intent, comprising: obtaining historical interaction information associated with the target interaction information by the preset decision layer and parsing the target interaction information according to the historical interaction information to obtain the target interaction intent.

[0079] Among them, the historical interaction information can be the information interaction record related to the current target interaction information, such as the previous inquiry information related to the power system and the feedback response information.

[0080] Specifically, the historical interaction information associated with the target interaction information can be queried by the preset decision layer, and the historical interaction information is used as a context reference basis to parse the target interaction information through context semantic analysis to accurately identify the target interaction intent. By combining the historical interaction information when parsing the target interaction information, the past interaction content can be combined to assist in understanding the current intent, avoiding the misjudgment of the intent caused by the incomplete interpretation of a single interaction information, improving the intent parsing efficiency and accuracy, and optimizing the user interaction experience.

[0081] Based on the above scheme, optionally, the target power-related data corresponding to the target interaction intent is determined based on the preset data interface and the power grid knowledge base, comprising: calling a preset data interface associated with the target interaction intent to obtain first power-related data corresponding to the target interaction intent from real-time operation-related data of the power system; determining a target query vector according to the target interaction intent, and querying the power grid knowledge base based on the target query vector to obtain second power-related data corresponding to the target interaction intent; and determining the target power-related data corresponding to the target interaction intent according to the first power-related data and the second power-related data.

[0082] Among them, the first power-related data can be the data directly related to the target interaction intent filtered from the real-time operation-related data of the power system after calling the preset data interface matching the target interaction intent, which guarantees the timeliness of the data. The second power-related data can be the relevant data of the target interaction intent queried in the power grid knowledge base based on the target query vector, which guarantees the professionalism of the data.

[0083] Optionally, the target interaction intent can be preprocessed, such as information parsing, error correction, and expansion, to obtain standardized target interaction information.

[0084] Specifically, the corresponding preset data interface can be matched according to the standardized target interaction intent, and then the preset data interface is called to filter the first power-related data corresponding to the target interaction intent from the real-time operation-related data of the power system.

[0085] The power grid knowledge base stores a plurality of power knowledge slices and target knowledge vectors corresponding to the power knowledge slices. When constructing the power grid knowledge base, each document in the power grid knowledge base can be subjected to preprocessing operations such as parsing, cleaning, and deduplication, and the document can be sliced according to paragraphs, sections, or fixed lengths to obtain power knowledge slices. Meanwhile, each power knowledge slice can be converted into a vector form according to a vector conversion model such as a Bidirectional Encoder Representations from Transformers (BERT) to generate a vector index and store it in the power grid knowledge base, thereby improving the efficiency and accuracy of subsequent retrieval.

[0086] To facilitate efficient comparison and query in the power grid knowledge base, the target interactive intent can be converted into a target query vector form that can be matched based on the same vector conversion model as the power knowledge slice conversion, ensuring consistency in the vector space.

[0087] Alternatively, the retrieval can be performed in the power grid database by using a Retrieval-Augmented Generation (RAG) technology. For professional problems in the power system, relevant information can be retrieved from the power grid database and provided as context to a preset decision layer, thereby ensuring the professionalism and accuracy of the response information.

[0088] Based on the above scheme, the power grid knowledge base can be queried based on the target query vector to obtain second power-related data corresponding to the target interactive intent, including determining the similarity between the target query vector and the target knowledge vector in the power grid knowledge base, determining a plurality of target knowledge slices from a plurality of power knowledge slices stored in the power grid knowledge base based on the similarity, and generating second power-related data corresponding to the target interactive intent based on the plurality of target knowledge slices.

[0089] Specifically, the similarity between the target query vector and the target knowledge vector in the power grid knowledge base can be calculated by using various vector similarity calculation methods such as cosine similarity and Euclidean distance, and the top K slices can be selected as the most relevant knowledge slices to the target interactive intent based on the similarity from high to low. The value of K can be flexibly set according to actual business needs, and the plurality of target knowledge slices can be combined into a coherent context text in a preset logical order such as document order or according to the similarity order. Finally, the target interactive intent and the constructed context text can be combined according to the prompt template format set by the preset decision layer to generate second power-related data corresponding to the target interactive intent.

[0090] Optionally, the retrieval accuracy can also be improved by multi-path retrieval. While the target query vector is similar to the target knowledge vector, keyword retrieval, semantic retrieval and other retrieval methods are performed in parallel. The retrieval results of the various retrieval methods are combined and de-duplicated. A preset similarity threshold is set. The retrieval results with a similarity higher than the preset similarity threshold are determined as the second power correlation data, which further improves the relevance of the second power correlation data to the target interaction intent while avoiding missed detection and false detection caused by a single retrieval method.

[0091] By screening the target knowledge slice from the power grid knowledge base, the association between the interaction intent and the knowledge slice can be accurately captured, and the reliability of the second power correlation data is further improved based on the professional knowledge in the power grid database.

[0092] On this basis, the first power correlation data and the second power correlation data can be combined to aggregate and integrate the target power correlation data corresponding to the target interaction intent. Meanwhile, the preset decision layer can be set to mark the specific knowledge source in the reference context when generating the target power correlation data, such as document name, chapter, etc., to improve the credibility and traceability of the target power correlation data.

[0093] By obtaining real-time operation correlation data through a preset data interface, it is ensured that the data can reflect the current state of the power grid, meet the timeliness requirement, and supplement historical cases, specifications and other professional information based on the power grid knowledge base, to realize dual support of real-time dynamic data and static professional knowledge, so that the finally determined target data is more comprehensive, avoiding the information one-sidedness caused by a single data source, and laying a foundation for subsequent generation of high-quality response information.

[0094] On the basis of the above scheme, optionally, the generating, according to the target power correlation data, of target response information corresponding to the target interaction information comprises: generating, according to the target power correlation data, initial response information corresponding to the target interaction information; and performing content filtering on the initial response information according to the target interaction information and a preset content filtering rule to obtain target response information, the preset content filtering rule being used to indicate the content in the initial response information that needs to be filtered out.

[0095] The initial response information can be response information generated directly according to the target power correlation data without filtering, which may contain redundant content, information with poor relevance to the target interaction intent, and information with non-standard expression, etc. The preset content filtering rule can be a rule preset for filtering the initial response information, which is used to indicate the content in the initial response information that needs to be filtered out, so as to improve the accuracy of the target response information.

[0096] Optionally, the preset content filtering rule can be a preset prompt engineering and an output filter, further, the initial response information can be constrained when generated by the preset decision layer through the prompt engineering, the role, responsibility and answer boundary of the virtual object are specified, the output specification of the response information such as the format, tone, content range and the like are specified, and the output filter is checked after the initial response information is generated, the ambiguous expressions, illegal operations or instructions and answers that do not conform to the industry specification are filtered out, so that the interaction process is reliable, the response information is compliant, and finally the target response information that is accurate and standard is obtained.

[0097] By combining the target interaction information and the preset filtering rule for content screening after generating the initial response information, the redundant information irrelevant to the current interaction is effectively eliminated, so that the final target response information is concise, focused and conforms to the industry specification, the power system data security is ensured, and the effectiveness and safety of information transmission are realized.

[0098] Optionally, feedback information for the target response information can be received, for negative feedback, specific problems can be recorded and reasons can be analyzed, if the retrieval deviation is further optimized, if the knowledge base information is lagging, the power grid knowledge base is updated. At the same time, a power grid knowledge base timing update strategy can also be set, and a vector index is regenerated to ensure the knowledge timeliness of the power grid knowledge base.

[0099] S240, generating third presentation information of the virtual object according to the target response information, and presenting the virtual object in the target interaction interface with the third presentation information.

[0100] The technical scheme of the embodiment of the application, by analyzing the target interaction information by the preset decision layer to obtain the target interaction intention, determining the target power-related data corresponding to the target interaction intention based on the preset data interface and the power grid knowledge base, and generating the target response information according to the target power-related data; by analyzing the target interaction information by the preset decision layer to determine the corresponding power-related data based on the preset data interface and the power grid knowledge base, the deviation caused by ambiguous information when directly matching data is avoided, the data acquisition is more targeted, the subsequent response information is aligned with the interaction intention, and the accuracy of the response information is improved.

[0101] Embodiment three

[0102] As an optional example of the embodiment of the application, the information interaction method for the power system of the application can specifically include:

[0103] 1. Multi-modal input and perception: receiving the request input by the user through voice or text, for example, "My home XX community is out of power, what's the matter?"

[0104] 2. Intention understanding and context analysis: Utilize the enhanced preset decision layer, combined with the dialogue history, accurately identify the user's intention as "fault repair and status query". The current conversation context, as well as cross-conversation user preferences, unfinished work orders, and other information can be obtained through the current interactive conversation.

[0105] 3. Information retrieval and tool planning:

[0106] a. The preset decision layer triggers the RAG process to retrieve information such as power supply lines, common fault types related to "XX small area" from the power grid knowledge base. Through RAG (Retrieval Augmented Generation) technology, the knowledge base of regulations, standards, equipment manuals, and historical cases in the power industry can be pre-processed as an external vector database. When answering professional questions, relevant information is retrieved from this database and provided as context to the preset decision layer, ensuring the professionalism and accuracy of the answers.

[0107] Through real-time data interfaces, integrate with the integrated platform of operation, distribution, and dispatch, GIS, SCADA, and other systems to obtain real-time operation data, equipment status, personnel location, and other information. Pre-set static knowledge base storage structure of industry standards and unstructured historical documents and cases.

[0108] b. The preset decision layer plans tool invocation sequence: [invoke "query power outage range by address" tool]->[invoke "get SCADA real-time alarm" tool]->[if confirmed fault, invoke "create rush repair work order" tool]. The preset decision layer dynamically plans and invokes these tools to execute specific business operations after understanding the interactive intention.

[0109] 4. Business tool execution and data acquisition: Call the corresponding API according to the planned sequence to obtain real-time data such as whether there is a planned power outage in the small area and whether there is a line trip from GIS and SCADA systems.

[0110] 5. Reasoning and decision-making and content generation: The preset decision layer integrates real-time data, retrieved knowledge, and user original questions to make inferences. For example, generate the decision: "Confirm that the trip is caused by XX line overload, and a rush repair work order NO.12345 has been automatically generated, with an estimated power restoration time of 2 hours."

[0111] Through prompt engineering and output filters, the generated content of the preset decision layer can be strictly constrained, filtering out uncertain, unsafe, or non-standard instructions and answers, ensuring the absolute reliability of the interaction process.

[0112] 6. Multimodal output and feedback: The generated text content is converted into speech through TTS and drives the virtual object to broadcast in a soothing and empathetic tone, while also displaying the ticket number and estimated recovery time on the screen.

[0113] Specific content executed by the preset decision layer:

[0114] 1. Dynamic knowledge injection mechanism based on RAG: According to user questions, real-time retrieval of the most relevant procedures, cases, and device parameters from the power grid knowledge base (vector database), and accurately provide them as context to the preset decision layer.

[0115] Process steps:

[0116] (1) Knowledge base construction:

[0117] Knowledge sources: regulations and documents, historical cases, and device parameter manuals in the power industry.

[0118] Knowledge preprocessing: document parsing (such as PDF parsing), cleaning, and deduplication.

[0119] Knowledge slicing: slice the document by paragraph, section, or fixed length, and generate vector representation (using models such as BERT), and store it in the vector database.

[0120] (2) User question processing:

[0121] In response to information interaction requests, receive user questions and perform necessary preprocessing (such as error correction and expansion).

[0122] Convert user questions into vector representation (use the same model).

[0123] Use vector similarity calculation (such as cosine similarity) to retrieve the most relevant knowledge slices from the vector database.

[0124] Multiple retrieval strategies can be used: for example, use keyword retrieval (such as BM25) and vector retrieval simultaneously, then merge the results. Set a threshold to only keep results with a similarity score higher than the threshold, ensuring relevance.

[0125] (3) Context construction:

[0126] Sort the retrieved knowledge slices by relevance (similarity score) and select the top K slices.

[0127] Combine these slices into a coherent context text in logical order (such as document order) or by relevance.

[0128] Combine the user question and the constructed context text according to the prompt template required by the preset decision layer.

[0129] (4) Preset decision layer Q&A:

[0130] Input the combined prompts into the preset decision layer, allowing it to generate answers based on the provided context.

[0131] The preset decision layer can be set to reference specific sources in the context (such as document name, chapter) when generating, improving credibility.

[0132] (5) Closed-loop feedback and optimization:

[0133] Collect user feedback on answers (such as likes, dislikes).

[0134] For negative feedback, record and analyze the reasons for optimization of retrieval strategies or knowledge base.

[0135] Regularly update the knowledge base and regenerate vector indexes to maintain the timeliness of knowledge.

[0136] 2. Abstract, encapsulate, and dynamically call business tools: Abstract the business functions of the business (query, create a work order, issue an instruction) into a set of tools that the preset decision layer can understand. According to the dialogue intent, automatically plan, sort, and execute these tools (for example: first check the power outage range -> then check the alarm information -> finally generate a work order).

[0137] 3. Multi-level security and compliance constraints:

[0138] Input constraints: Through prompt word engineering, solidify the role, responsibility, and answer boundary of virtual objects.

[0139] Process constraints: Perform permission and risk checks before tool invocation.

[0140] Output constraints: Post-process and filter the results generated by the preset decision layer, filtering out uncertain, unsafe, or unauthorized content.

[0141] Specific content executed by virtual objects:

[0142] Virtual objects can be responsible for multi-modal interaction with users. They can implement speech-to-text (STT) and text-to-speech (TTS) conversion, render virtual characters with affinity through 2D / 3D models, and generate corresponding lip movements, expressions, and body movements based on dialogue content.

[0143] 1. Virtual object multi-modal feedback based on business status: Driven by business execution status, generate virtual object expressions, tone, or action information. For example: when confirming a fault, the expression becomes "serious concern". When the work order processing is successful, the tone becomes "relaxed and affirmative". When waiting for system query, display "thinking" animation.

[0144] 2. End-to-end automatic closed loop of operation and deployment command: from the user's question, automatically complete fault analysis, work order generation, resource scheduling, progress tracking, and finally feedback to the user, without manual intervention to automatically make decisions and execute.

[0145] The steps are as follows:

[0146] 1. The user reports the fault through multiple channels (such as APP, voice, and SMS), and the fault interaction request is uniformly received.

[0147] 2. Automatic fault analysis: using power grid knowledge base and real-time data, automatically analyzing fault causes and scope.

[0148] 3. Automatically generate work orders: automatically create work orders according to the analysis results.

[0149] 4. Automatic resource scheduling: according to the work order requirements, available resources (personnel, vehicles, equipment) and optimization algorithms, automatically assign to the appropriate repair team.

[0150] 5. Automatic progress tracking: using GIS and mobile terminals to update the repair progress in real time.

[0151] 6. Automatic feedback to the user: through virtual objects, actively push the fault cause, estimated recovery time, progress, etc. to the user.

[0152] 7. Closed loop confirmation: after the fault is repaired, automatically confirm and archive the records.

[0153] The technical solution of the embodiment of the application first receives multi-modal input and context to identify the intention, accurately judges the user's intention, and lays the foundation for subsequent fault processing; then acquires real-time power grid data and retrieves relevant professional information in the power grid knowledge base to determine the fault cause, and plans the fault processing tools and processes, improves the accuracy and efficiency of fault cause determination based on real-time data and professional knowledge, and then determines the fault processing tools and processes to standardize the fault operation behavior and improve the fault processing efficiency; then, comprehensively reason and execute the real-time data, the retrieved knowledge, and the user's original question, drive the virtual object to perform multi-modal output and feedback, realize the rigor and reliability of fault processing mode decision through multi-source data, and improve the user information interaction experience based on virtual object feedback.

[0154] Embodiment four

[0155] Figure 4A structural schematic diagram of an information interaction device for a power system is provided for Embodiment Four of the present application. The device is used to execute the information interaction method for a power system provided by any of the above embodiments. The device and the information interaction method for a power system of each of the above embodiments belong to the same inventive concept. Details not described in the embodiment of the information interaction device for a power system can be referred to the above embodiments of the information interaction method for a power system. As shown in FIG. 4, the device includes a first presentation module 410, a second presentation module 420, a target response information generation module 430, and a third presentation module 440. Figure 4

[0156] The first presentation module 410 is configured to display a target interaction interface, the target interaction interface displays a virtual object, and the virtual object is presented with first presentation information. The second presentation module 420 is configured to, in response to an information interaction request for the virtual object, acquire target interaction information, and present the virtual object with second presentation information, wherein the target interaction information carries at least inquiry information associated with power information. The target response information generation module 430 is configured to generate target response information corresponding to the target interaction information based on a preset data interface and a power grid knowledge base, wherein the preset data interface is used to query real-time operation associated data of the power system. The third presentation module 440 is configured to generate third presentation information of the virtual object according to the target response information, and present the virtual object with the third presentation information in the target interaction interface

[0157] ​The technical scheme of the embodiment of the present application firstly displays a target interactive interface through the first presentation module 410, the target interactive interface has a virtual object displayed therein, and the virtual object is presented with first presentation information; abstract power information interaction is converted into concrete virtual object presentation, which is more intuitive than a text interface and reduces the operation threshold for power information interaction; then, the second presentation module 420 acquires target interactive information in response to an information interaction request for the virtual object and presents the virtual object with second presentation information, wherein the target interactive information at least carries inquiry information associated with power information; the information interaction request is responded to in real time, the timeliness requirement for power information query is met, the interaction progress can be clearly perceived through feedback of the change of the second presentation information that the interaction request has been received; then, the target response information generation module 430 generates target response information corresponding to the target interactive information based on a preset data interface and a power grid knowledge base, wherein the preset data interface is used to query real-time operation associated data of a power system; real-time power data is acquired in combination with the preset data interface, so that the target response information has real-time performance, accurately reflects the current operation state of the power system, and guarantees the professionalism and accuracy of the target response information according to the power grid knowledge base; finally, the third presentation module 440 generates third presentation information of the virtual object according to the target response information, and presents the virtual object with the third presentation information in the target interactive interface; the response result is presented with the third presentation information, the consistency of the interaction process is maintained, the user experience is improved, the response information is converted into presentation information of the virtual object, complex power data is converted into a form that is easier to understand, the user is helped to quickly grasp key information and more easily understand complex power response content, the problems of inefficient interaction and non-unified information are effectively solved, and an efficient, accurate and friendly power information interaction experience is provided for the user.

[0158] On the basis of the above scheme, optionally, the target response information generation module 430 comprises a target response information generation sub-module. The target response information generation sub-module is configured to analyze the target interactive information through a preset decision layer to obtain a target interaction intention, determine target power associated data corresponding to the target interaction intention based on a preset data interface and a power grid knowledge base, and generate target response information according to the target power associated data.

[0159] On the basis of the above scheme, optionally, the target response information generation submodule includes a first power correlation data acquisition unit, a second power correlation data acquisition unit, and a target power correlation data acquisition unit. The first power correlation data acquisition unit is configured to call a preset data interface associated with the target interaction intent to obtain first power correlation data corresponding to the target interaction intent from real-time operation correlation data of a power system. The second power correlation data acquisition unit is configured to determine a target query vector according to the target interaction intent, query the power grid knowledge base based on the target query vector, and obtain second power correlation data corresponding to the target interaction intent. The target power correlation data acquisition unit is configured to determine target power correlation data corresponding to the target interaction intent according to the first power correlation data and the second power correlation data.

[0160] On the basis of the above scheme, optionally, the power grid knowledge base stores a plurality of power knowledge slices and target knowledge vectors corresponding to the power knowledge slices. The second power correlation data acquisition unit includes a second power correlation data acquisition subunit. The second power correlation data acquisition subunit is configured to determine the similarity between the target query vector and the target knowledge vectors in the power grid knowledge base, determine a plurality of target knowledge slices from the plurality of power knowledge slices stored in the power grid knowledge base according to the similarity, and generate second power correlation data corresponding to the target interaction intent according to the plurality of target knowledge slices.

[0161] On the basis of the above scheme, optionally, the target response information generation submodule includes a target interaction intent acquisition unit. The target interaction intent acquisition unit is configured to obtain historical interaction information associated with the target interaction information through a preset decision layer, analyze the target interaction information according to the historical interaction information, and obtain a target interaction intent.

[0162] On the basis of the above scheme, optionally, the target interaction information includes power consumption failure inquiry information, and the target response information includes power consumption failure reply information and a failure repair work order. The device further includes a failure repair task generation module. The failure repair task generation module is configured to, after generating the target response information corresponding to the target interaction information based on the preset data interface and the power grid knowledge base, determine a failure repair operation according to the failure repair work order and the power grid knowledge base, call the preset data interface to obtain available resources of the power system, generate a failure repair task according to the failure repair operation and the available resources, and distribute the failure repair task to a task performer of the failure repair task.

[0163] On the basis of the above-mentioned scheme, optionally, the target interaction information includes power failure inquiry information, and the target response information includes power failure reply information and a failure repair work order; the device further comprises a fourth presentation module. The fourth presentation module is configured to, after the target response information corresponding to the target interaction information is generated based on the preset data interface and the power grid knowledge base, call the preset data interface to obtain failure repair execution information associated with the failure repair work order, determine fourth presentation information of the virtual object according to the failure repair execution information, and present the virtual object in the fourth presentation information on the target interaction interface.

[0164] On the basis of the above-mentioned scheme, optionally, the third presentation information includes object response audio and object response actions; and the third presentation module 440 comprises a virtual object response sub-module. The virtual object response sub-module is configured to determine object response audio and object response actions of the virtual object according to the target response information, and display the object response audio and the object response actions based on the virtual object.

[0165] On the basis of the above-mentioned scheme, optionally, the target response information generation sub-module comprises a target response information generation unit. The target response information generation unit is configured to generate initial response information corresponding to the target interaction information according to the target power association data, perform content screening on the initial response information according to the target interaction information and a preset content filtering rule to obtain target response information, and the preset content filtering rule is used to indicate the content that needs to be filtered out in the initial response information.

[0166] The information interaction device for a power system provided in the embodiments of the present application can execute the information interaction method for a power system provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0167] Embodiment five

[0168] Figure 5 A structural schematic diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smart phones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0169] As Figure 5As shown, the electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., connected to the at least one processor 11 in communication. The memory stores a computer program executable by the at least one processor 11, 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 loaded from the storage unit 18 into 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.

[0170] A plurality 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, a speaker, etc., a storage unit 18, such as a magnetic 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.

[0171] The processor 11 can be various general and / or special-purpose processing components having 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-purpose 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 performs various methods and processes described above, such as the information interaction method for a power system.

[0172] In some embodiments, the information interaction method for a power system can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto 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 information interaction method for a power system described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the information interaction method for a power system by any other appropriate means, such as by means of firmware.

[0173] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0174] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program

[0175] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0176] To provide for interaction with a user, the systems and techniques described here can 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 a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0177] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can 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.

[0178] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can 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 large management difficulty and weak business scalability in traditional physical host and VPS service.

[0179] In particular, the processes described above with reference to the flowcharts can be implemented as computer software programs in accordance with embodiments of the application. For example, embodiments of the application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program comprising program code for executing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication unit 19, or installed from the storage unit 18, or installed from the ROM 12. When the computer program is executed by the processor 11, the above-described functions defined in the methods of embodiments of the application are performed.

[0180] It should be understood that the various forms of flow shown above can be used to reorder, add, or remove steps. For example, the steps recited in the present application can be performed in parallel, in series, or in a different order, as long as the desired results of the claimed technical solution are achieved, which is not limited herein.

[0181] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for information interaction of a power system, characterized in that, The method comprises: displaying a target interaction interface, wherein a virtual object is displayed in the target interaction interface, and the virtual object is presented with first presentation information; in response to an information interaction request for the virtual object, obtaining target interaction information, and presenting the virtual object with second presentation information, wherein the target interaction information carries at least inquiry information associated with power information; generating target response information corresponding to the target interaction information based on a preset data interface and a power grid knowledge base, wherein the preset data interface is used to query real-time operation associated data of a power system; generating third presentation information of the virtual object according to the target response information, and presenting the virtual object with the third presentation information in the target interaction interface.

2. The information exchange method for power systems according to claim 1, characterized in that, The method of generating target response information corresponding to the target interaction information based on a preset data interface and a power grid knowledge base comprises: analyzing the target interaction information by a preset decision layer to obtain a target interaction intent, determining target power associated data corresponding to the target interaction intent based on a preset data interface and a power grid knowledge base, and generating target response information according to the target power associated data.

3. The information exchange method for power systems according to claim 2, characterized in that, The method of determining target power associated data corresponding to the target interaction intent based on a preset data interface and a power grid knowledge base comprises: calling a preset data interface associated with the target interaction intent to obtain first power associated data corresponding to the target interaction intent from real-time operation associated data of a power system; determining a target query vector according to the target interaction intent, and querying the power grid knowledge base based on the target query vector to obtain second power associated data corresponding to the target interaction intent; determining target power associated data corresponding to the target interaction intent according to the first power associated data and the second power associated data.

4. The information exchange method for power systems according to claim 3, characterized in that, The power grid knowledge base stores a plurality of power knowledge slices and target knowledge vectors corresponding to the power knowledge slices; The method of querying the power grid knowledge base based on the target query vector to obtain second power associated data corresponding to the target interaction intent comprises: determining the similarity between the target query vector and the target knowledge vectors in the power grid knowledge base, determining a plurality of target knowledge slices from a plurality of power knowledge slices stored in the power grid knowledge base according to the similarity, and generating second power associated data corresponding to the target interaction intent according to the plurality of target knowledge slices.

5. The information exchange method for power systems according to claim 2, wherein, The method of analyzing the target interaction information by a preset decision layer to obtain a target interaction intent comprises: obtaining historical interaction information associated with the target interaction information by a preset decision layer, and analyzing the target interaction information according to the historical interaction information to obtain a target interaction intent.

6. The information exchange method for power systems according to claim 1, wherein The target interaction information comprises power consumption fault inquiry information, and the target response information comprises power consumption fault reply information and a fault repair work order; after the method of generating target response information corresponding to the target interaction information based on a preset data interface and a power grid knowledge base, the method further comprises: According to the fault repair work order and the power grid knowledge base, a fault repair operation is determined, a preset data interface is called to obtain available resources of the power system, a fault repair task is generated according to the fault repair operation and the available resources, and the fault repair task is distributed to a task performer of the fault repair task.

7. The information exchange method for power systems according to claim 1, wherein The target interaction information includes power failure inquiry information, and the target response information includes power failure reply information and a fault repair work order. After the target response information corresponding to the target interaction information is generated based on the preset data interface and the power grid knowledge base, the method further includes: The fault repair execution information associated with the fault repair work order is called through the preset data interface, fourth presentation information of the virtual object is determined according to the fault repair execution information, and the virtual object is presented in the fourth presentation information on the target interaction interface.

8. The information exchange method for power systems according to claim 1, wherein The third presentation information includes object response audio and object response actions. The third presentation information of the virtual object is generated according to the target response information, including: The object response audio and the object response actions of the virtual object are determined according to the target response information, and the object response audio and the object response actions are displayed based on the virtual object.

9. The information exchange method for power systems according to claim 2, wherein, The target response information corresponding to the target interaction information is generated according to the target power association data, including: Initial response information corresponding to the target interaction information is generated according to the target power association data, and the initial response information is content-filtered according to the target interaction information and a preset content filtering rule to obtain target response information, the preset content filtering rule being used to indicate content that needs to be filtered out in the initial response information.

10. A computer program product comprising a computer program, characterized in that, The computer program, when executed by a processor, implements the information interaction method for a power system as claimed in any one of claims 1-9.

Images