Smart park knowledge question-answering method and device based on large language model

Abstract

The invention relates to a smart park knowledge question-answering method and device based on a large language model, electronic equipment and a storage medium, relates to the technical field of large language models, and can perform automatic abnormality diagnosis on park equipment in combination with multi-dimensional data to improve the intelligent degree of a park. The method comprises the steps of displaying a first sub-page in response to a triggering operation on an equipment abnormal function in a knowledge question-answer page of a smart park, and displaying a second sub-page in response to a problem input by a user in the first sub-page for inquiring an abnormal reason of target equipment in the smart park, retrieving real-time equipment parameters and historical maintenance records of the target equipment in a knowledge base and acquiring data of environmental sensors around the target equipment; on the basis of the problem, the equipment parameter, the historical maintenance record and the data of the environment sensor, constructing a cue word; and inputting the cue word into the large language model to obtain an abnormality diagnosis report for the target equipment, and displaying the abnormality diagnosis report on the first sub-page.

Description

Technical Field

[0001] The present disclosure relates to the field of natural language processing technology, and in particular to a method, device, electronic device and storage medium for answering questions in a smart park knowledge based on a large language model. Background Art

[0002] A park is a comprehensive area formed through spatial aggregation, centered around a specific function. It typically encompasses facilities such as offices, production, R&D, warehousing, and lifestyle services, serving the collaborative operations of businesses, institutions, or individuals. Common types include industrial parks (such as manufacturing bases), science and technology parks (such as innovative business incubators), logistics parks (such as warehousing and transportation hubs), and campus parks (such as universities or corporate headquarters). Their core value lies in reducing operating costs, improving collaborative efficiency, and providing a vehicle for regional economic development through resource concentration and functional complementarity.

[0003] However, traditional parks are centered around physical space and rely mainly on manual management and basic information technology. Their operating models are relatively rigid, data interoperability among systems is poor, and there are problems such as delayed service responses, making it difficult to meet the needs of modern enterprises for efficiency and intelligence. Summary of the Invention

[0004] To overcome the problems existing in the related art, the embodiments of the present disclosure provide an XX method, apparatus, electronic device, storage medium, and program product to solve the defects in the related art.

[0005] According to a first aspect of an embodiment of the present disclosure, a method for answering questions about a smart park knowledge based on a large language model is provided, comprising: Displaying a smart park knowledge question and answer page based on the large language model on a terminal device, wherein the smart park knowledge question and answer page is used for users to ask questions related to the smart park in at least one of images, voice, and text; In response to a triggering operation of a device abnormality function in the smart campus knowledge question and answer page, a first subpage is displayed for the user to inquire about the device abnormality, and in response to a question entered by the user in the first subpage about the cause of the abnormality of a target device in the smart campus, real-time device parameters and historical maintenance records of the target device are retrieved from a knowledge base, as well as data from environmental sensors surrounding the target device; Constructing prompt words based on the question of the cause of the abnormality of the target device, the device parameters, the historical maintenance records, and the data of the environmental sensors, wherein the prompt words are used to prompt the large language model to generate an abnormality diagnosis report for the target device based on the question of the cause of the abnormality of the target device, the device parameters, the historical maintenance records, and the data of the environmental sensors; The prompt word is input into the large language model to obtain an abnormality diagnosis report for the target device, and the abnormality diagnosis report is displayed on the first sub-page.

[0006] In one embodiment, the method further comprises: In response to a triggering operation on a maintenance operation function in the smart park knowledge question and answer page, displaying a second sub-page for the user to ask questions about maintenance operations; In response to a maintenance operation question regarding abnormal operation of the target qua device input by the user in the second sub-page, obtaining physiological information of the user from the user's wearable device and obtaining environmental information of the user's environment through a sensor on the terminal device; determining the stress state of the user based on the physiological information and the environmental information, and, if the stress state indicates that the user is in a high-stress state, generating, using the large language model and the abnormality diagnosis report, the maintenance operation question, the physiological information, and the environmental information, operation step information for instructing the user to perform abnormal maintenance on the target device; The operation step information is displayed on the second sub-page, and the operation step information is played in the form of voice.

[0007] In one embodiment, the method further comprises: In response to a triggering operation of a visitor function on the smart park knowledge question and answer page, a third sub-page for visitors is displayed, and in response to an input operation by the user on the third sub-page, emotion recognition is performed on content corresponding to the input operation to obtain first emotion information of the user, wherein the content includes voice content and / or text content; Acquiring the user's facial expression and body language through a camera on the terminal device, and identifying the user's second emotion information based on the expression and the body language; determining target emotion information of the user according to the first emotion information and the second emotion information, and determining a visitor type of the user according to the target emotion information; The large language model is used to generate introduction information of the smart park and smart park guidance information for the user according to the visitor type, and the introduction information and the smart park guidance information are displayed on the third sub-page.

[0008] In one embodiment, generating the introduction information of the smart park and the smart park guidance information for the user according to the visitor type by using the large language model includes: When the visitor type characterizes the user as a hurried visitor, first introduction information of the smart park and first smart park guidance information for the user are generated by the large language model, wherein the first smart park guidance information is navigation information generated by the large language model for guiding the user to a first location, and the first location is the location in the park that the user desires to reach, as determined by the large language model based on content corresponding to the input operation; When the visitor type characterizes that the user is a leisure visitor, the second introduction information of the smart park and the second smart park guidance information for the user are generated by the large language model, wherein the content of the second introduction information is more than the first introduction information, and the second smart park guidance information is navigation information generated by the large language model for guiding the user to a second location, and the second location is the park location of the user that is predicted by the large language model to be of interest to the user.

[0009] In one embodiment, displaying a smart park knowledge question and answer page based on a large language model on a terminal device includes: In response to a vehicle user scanning a QR code at a target entrance of the smart park, a smart park knowledge question and answer page based on a large language model is displayed on a terminal device held by the vehicle user; The method further comprises: In response to a triggering operation on a parking function in the smart park knowledge question and answer page, displaying a fourth sub-page for the vehicle user to ask questions about park parking; In response to a parking navigation question input by the vehicle user on the fourth sub-page, querying the underground parking lot information of the smart park for a vacant parking space closest to the target park location using the large language model based on the target park location in the parking navigation question, and generating parking navigation information based on the vacant parking space and the location of the target entrance using the large language model; The parking guidance information is displayed on the fourth sub-page and played in the form of voice.

[0010] In one embodiment, the method further comprises: In response to a triggering operation on an emergency drill function in the smart park knowledge question and answer page, displaying a fifth sub-page for the user to ask questions about the emergency drill; In response to a question inquiring about an emergency drill plan input by the user on the fifth subpage, real-time environmental information of the smart park and real-time operating information of equipment in the smart park are determined through sensors in the smart park, real-time meteorological information of the smart park is determined through a meteorological data interface, and real-time video of the smart park is obtained from a camera in the smart park. Based on the real-time video, real-time crowd flow information and real-time traffic information of the smart park are determined. The real-time environmental information includes the temperature and / or humidity of the smart park. Generate an emergency drill plan for the smart park based on the real-time environmental information, the real-time operation information, the real-time weather information, the real-time crowd flow information, and the real-time traffic information through the large language model; The emergency drill plan is displayed on the fifth sub-page.

[0011] In one embodiment, the method further comprises: In response to a triggering operation on a work status function in the smart park knowledge question and answer page, displaying a sixth sub-page for the user to inquire about the work status of staff in the smart park; In response to a question entered on the sixth subpage asking about the work status of a specific staff member, acquiring a facial expression and body language of the specific staff member through a camera at the specific staff member, and identifying third emotion information of the specific staff member based on the facial expression and the body language using the large language model; When the third emotion information indicates that the specific staff member is in a low mood, generating an emotion regulation suggestion through the large language model, wherein the emotion regulation suggestion includes a recommended relaxing place within a preset range and / or music for soothing the mood; The emotion regulation suggestion is displayed on the sixth sub-page, and the emotion regulation suggestion is sent to the terminal device held by the specific staff member.

[0012] According to a second aspect of an embodiment of the present disclosure, a smart park knowledge question-answering device based on a large language model is provided, comprising: A first display module is configured to display a smart park knowledge question and answer page based on a large language model on a terminal device, wherein the smart park knowledge question and answer page is configured to allow a user to ask questions related to the smart park in at least one of images, voice, and text; a second display module, configured to, in response to a triggering operation of a device abnormality function in the smart campus knowledge question and answer page, display a first sub-page for the user to inquire about the device abnormality, and, in response to a question entered by the user in the first sub-page regarding the cause of the abnormality of a target device in the smart campus, retrieve the real-time device parameters and historical maintenance records of the target device from a knowledge base, and obtain data from environmental sensors surrounding the target device; a construction module, configured to construct prompt words based on the question of the cause of the abnormality of the target device, the device parameters, the historical maintenance records, and the data of the environmental sensors, wherein the prompt words are used to prompt the large language model to generate an abnormality diagnosis report for the target device based on the question of the cause of the abnormality of the target device, the device parameters, the historical maintenance records, and the data of the environmental sensors; The third display module is configured to input the prompt word into the large language model, obtain an abnormality diagnosis report for the target device, and display the abnormality diagnosis report on the first sub-page. According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory and a processor, wherein the memory is used to store computer instructions that can be executed on the processor, and the processor is used to implement any one of the methods described in the first aspect when executing the computer instructions.

[0013] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method described in any one of the first aspects is implemented.

[0014] The technical solutions provided by the embodiments of the present disclosure may have the following beneficial effects: The large language model-based smart campus knowledge Q&A method provided in the embodiments of the present disclosure supports users asking questions related to smart campuses using at least one of image, voice, and text input. This supports multimodal input, thereby improving input accuracy and, consequently, the accuracy of the knowledge Q&A results. Furthermore, the smart campus knowledge Q&A page provides a device anomaly function. In response to a user's input on the first subpage corresponding to the device anomaly function, the function retrieves the target device's real-time device parameters and historical maintenance records from the knowledge base, as well as data from the environmental sensors surrounding the target device. The large language model then combines this multi-dimensional data (i.e., real-time device parameters, historical maintenance records, and environmental sensor data) to generate an anomaly diagnosis report for the target device, thereby improving the accuracy of anomaly diagnosis and the accuracy of the campus knowledge Q&A results. Furthermore, the large language model enables automatic anomaly diagnosis of campus equipment, eliminating the need for on-site manual anomaly diagnosis. This improves the efficiency of campus anomaly diagnosis and, consequently, enhances the intelligence of the smart campus. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0016] Figure 1 This is a flowchart of a method for answering questions in a smart park knowledge based on a large language model, according to an exemplary embodiment of the present disclosure; Figure 2 1 is a schematic structural diagram of a smart park knowledge question-answering device based on a large language model according to an exemplary embodiment of the present disclosure; Figure 3 It is a structural block diagram of an electronic device shown in an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0017] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0018] The terms used in this disclosure are for the purpose of describing specific embodiments only and are not intended to limit the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0019] It should be understood that although the terms first, second, third, etc. may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining."

[0020] As mentioned in the background technology, traditional parks are centered on physical space and rely mainly on manual management and basic information technology. Their operating models are relatively rigid, data interoperability among systems is poor, and there are problems such as delayed service responses, making it difficult to meet the needs of modern enterprises for efficiency and intelligence.

[0021] For example, the inventors discovered that in traditional industrial parks, equipment fault diagnosis often requires manual on-site diagnosis. First, reaching the site of the equipment failure takes a long time in large industrial parks. Second, manual diagnosis often relies on on-site inspections of the equipment based on experience. Consequently, traditional industrial park equipment fault diagnosis is inefficient and cannot meet the demands of modern enterprises for efficiency and intelligence.

[0022] Based on this, in the first aspect, at least one embodiment of the present disclosure provides a method for answering questions in a smart park based on a large language model. Figure 1 , which shows the process of the method, including steps S101 to S104.

[0023] In step S101, a smart park knowledge question and answer page based on a large language model is displayed on a terminal device, wherein the smart park knowledge question and answer page is used for users to ask questions related to smart parks in at least one of the following ways: pictures, voice, and text.

[0024] In step S102, in response to the triggering operation of the device abnormality function in the smart park knowledge question and answer page, a first sub-page is displayed for the user to ask questions about the device abnormality, and in response to the question entered by the user in the first sub-page asking about the cause of the abnormality of the target device in the smart park, the real-time device parameters and historical maintenance records of the target device are retrieved from the knowledge base, and the data of the environmental sensors around the target device are obtained.

[0025] For example, the knowledge base is used to store the real-time device parameters and historical maintenance records of each device in the smart park. The environmental sensors around the target device can be, for example, wind pressure sensors, humidity sensors, temperature sensors, etc., which are not limited in the embodiments of the present disclosure.

[0026] For example, in the disclosed embodiment, a user can upload a picture of a device failure, then extract the image features through the ResNet-50 structure, search the vector library, associate the video clips of the device maintenance, and obtain the historical maintenance record of the device.

[0027] In step S103, a prompt word is constructed based on the question of the cause of the abnormality of the target device, the device parameters, the historical maintenance records, and the data from the environmental sensors. The prompt word is used to prompt the large language model to generate an abnormality diagnosis report for the target device based on the question of the cause of the abnormality of the target device, the device parameters, the historical maintenance records, and the data from the environmental sensors.

[0028] In step S104, the prompt word is input into the large language model to obtain an abnormality diagnosis report for the target device, and the abnormality diagnosis report is displayed on the first sub-page.

[0029] It should be understood that the smart park knowledge question and answer page in the embodiment of the present disclosure provides multiple functions for the smart park, such as equipment abnormality function, maintenance operation function, visitor function, parking function, emergency drill function, and working status function. The embodiment of the present disclosure does not limit this. The following text will provide detailed examples for each of the aforementioned functions.

[0030] For example, in the device anomaly function, in response to a user's voice query on the first sub-page, "Possible reasons for insufficient airflow from the air conditioner in Building 3," the knowledge base retrieves the air conditioner's real-time device parameters and historical maintenance records, as well as data from the environmental sensors surrounding the air conditioner. A prompt word is then constructed based on the question, "Possible reasons for insufficient airflow from the air conditioner in Building 3," the device parameters, historical maintenance records, and environmental sensor data. Finally, the prompt word is input into the large language model, generating an anomaly diagnostic report for the target device: "Probability of filter clogging 72%, immediate cleaning recommended."

[0031] As a result, the large language model can combine multi-dimensional data (i.e., real-time device parameters, historical maintenance records, and environmental sensor data) to generate anomaly diagnosis reports for target devices, thereby improving the accuracy of anomaly diagnosis and the accuracy of knowledge-based Q&A results. Furthermore, the large language model can automatically diagnose anomalies in devices within the park, eliminating the need for manual on-site diagnosis. This improves the efficiency of park anomaly diagnosis and, in turn, enhances the intelligence level of the smart park. Furthermore, it supports multimodal user input, improving input accuracy and, in turn, the accuracy of knowledge-based Q&A results.

[0032] In one embodiment, in response to the triggering operation of the maintenance operation function in the smart park knowledge question and answer page, a second sub-page for the user to ask maintenance operation questions can be displayed; in response to the maintenance operation questions regarding the abnormal operation of the target device input by the user in the second sub-page, the user's physiological information is obtained from the user's wearable device, and the environmental information of the user's environment is obtained through the sensor on the terminal device; the user's stress state is determined based on the physiological information and the environmental information, and when the stress state indicates that the user is in a high-pressure state, the large language model is used to generate operation step information for instructing the user to perform abnormal maintenance on the target device based on the abnormal diagnosis report, the maintenance operation questions, the physiological information and the environmental information; the operation step information is displayed in the second sub-page, and the operation step information is played in the form of voice.

[0033] The user's stress state may be a numerical value representing the degree of stress, and correspondingly, a high-pressure state may be when the numerical value is higher than a preset threshold.

[0034] It should be understood that fault repair in traditional campuses often relies on the experience of maintenance personnel. If the maintenance personnel are under stress, the repair effect may be affected. However, in the disclosed embodiments, the maintenance personnel's stress state can be identified. If the maintenance personnel are under stress, the large language model can be used to assist the maintenance personnel in fault repair, thereby ensuring the repair effect.

[0035] For example, in response to a maintenance worker entering a maintenance operation question regarding an abnormal air conditioner operation on the second sub-page, physiological information (such as heart rate information) is obtained from the maintenance worker's wristband, and environmental information (such as noise decibels, workspace lighting, and temperature) of the maintenance worker's environment is obtained through sensors on the terminal device. Based on the physiological and environmental information, the maintenance worker's stress state is then determined. If the stress state indicates that the maintenance worker is under high pressure, the large language model is used to generate operational steps to instruct the maintenance worker to perform abnormal air conditioner repairs based on the air conditioner's abnormality diagnosis report, maintenance operation question, physiological information, and environmental information.

[0036] For example, if an abnormality diagnosis report indicates that the air conditioner's fan bearing has failed, the generated operation step information may be: "Now you need: ① An Allen wrench with a blue handle (on the second layer of the tool kit) ② A red torque gauge (with a yellow label). Note! The current screws are fixed with anti-loosening glue. First, turn them clockwise 15° to break the glue layer. Now loosen the first screw (located at 3 o'clock on the north side). Insert the feeler gauge into the bearing gap. When the 0.3mm thin sheet cannot be inserted, the clearance meets the standard. Now start the inspection. When the inspection is completed, say "Inspection completed." The operation step information generated by the large language model can include spatial positioning descriptions and feature identifiers, decompose compound actions, provide spatial orientation guidance to maintenance personnel, quantify operation standards, and add voice confirmation nodes. In combination with voice playback, it can better assist maintenance personnel in fault repair and improve maintenance results.

[0037] Continuing with the above example, if no action is taken within a preset time (e.g., 30 seconds) after a voice prompt for a specific step, a flashing graphic reminder can be automatically displayed (e.g., a red arrow pointing to the part to be operated can be displayed on the maintenance technician's glasses). Alternatively, if a tool is incorrectly used (e.g., using an 8mm wrench to tighten a 10mm screw), a large language model can be used to generate a prompt: "Stop! This screw requires a 10mm wrench. The correct tool is on the third shelf of the tool cart behind you to the left"), and this prompt can be played back via voice.

[0038] In one embodiment, in response to the triggering operation of the visitor function in the smart park knowledge question and answer page, a third sub-page for visitors can be displayed, and in response to the user's input operation in the third sub-page, emotion recognition is performed on the content corresponding to the input operation to obtain the user's first emotion information, wherein the content includes voice content and / or text content; the user's facial expression and body language are obtained through the camera on the terminal device, and the user's second emotion information is identified based on the expression and the body language; the user's target emotion information is determined based on the first emotion information and the second emotion information, and the user's visitor type is determined based on the target emotion information; the introduction information of the smart park and the smart park guidance information for the user are generated according to the visitor type through the large language model, and the introduction information and the smart park guidance information are displayed on the third sub-page.

[0039] That is to say, when a visitor enters the park, the reception method can be quickly adjusted based on the visitor's input content, expression and body language.

[0040] In one embodiment, the large language model is used to generate introduction information of the smart park and smart park guidance information for the user according to the visitor type, including: when the visitor type characterizes that the user is a hurried visitor, the large language model is used to generate first introduction information of the smart park and first smart park guidance information for the user, wherein the first smart park guidance information is navigation information generated by the large language model for guiding the user to a first location, and the first location is the park location that the user expects to arrive at, determined by the large language model according to the content corresponding to the input operation; when the visitor type characterizes that the user is a leisure visitor, the large language model is used to generate second introduction information of the smart park and second smart park guidance information for the user, wherein the content of the second introduction information is more than the first introduction information, and the second smart park guidance information is navigation information generated by the large language model for guiding the user to a second location, and the second location is the park location that the user is interested in predicted by the large language model.

[0041] This means that for visitors who appear to be in a hurry, the large language model can be used to concisely provide key information and quick guidance services; for visitors with more time, the large language model can be used to provide more detailed park introductions and interactive experience recommendations. This allows for different reception methods to be automatically provided for different visitors, improving visitor reception effectiveness.

[0042] For example, the first introduction information might include the name of the smart campus, the approximate location and purpose of major functional areas (such as offices, leisure areas, and exhibition areas), and the direction and distance to important facilities near the visitor's current location, such as restrooms, elevators, and exits. For example, the large language model might generate the following first introduction information: "You are currently at the main entrance of the smart campus. The office building reception is 50 meters ahead. There is a café on the left side of the building, restrooms on the right, and the elevator is located in the center of the office building lobby." For example, the first smart park guidance information can enable visitors to reach their destination most conveniently, and can also provide some key node signs or reference objects to help visitors quickly locate, such as, "Please go straight along this main road, turn left at the second intersection, and the conference room you want to go to is 100 meters ahead. You will see a large fountain as a sign on the way." In addition, the first smart park guidance information can be displayed in a concise and clear manner, such as displaying a route map on the terminal device screen, or providing direction and distance through voice prompts, which is not limited in this embodiment of the present disclosure.

[0043] For example, in addition to the typical park layout and functional areas, the secondary introduction could also include background information such as the park's development history, design philosophy, advanced technologies employed, and awards received. For example, this could explain how the park utilizes intelligent energy management systems to achieve energy conservation and emission reduction, or how the park's buildings are designed and constructed with green environmental protection concepts. It could also showcase the park's corporate culture and employee activities, giving visitors a more comprehensive understanding of the park's overall situation.

[0044] For example, the second smart park guidance information can be guidance information for personalized interactive experience projects recommended by the large language model based on the visitor's interests and time. For example, if the visitor is interested in technology, they can be recommended to visit the intelligent robot R&D center in the park to watch the demonstration and operation of the robot, or even personally experience simple interactive communication with the robot. Or they can be recommended to participate in science and technology lectures, innovation workshops and other activities held in the park, so that visitors can deeply participate in and feel the scientific and technological atmosphere and innovation capabilities of the park. For visitors who like culture and art, art exhibitions and creative studio visits in the park can be recommended, and some interactive art creation experiences such as pottery making and painting creation can also be provided. It should be understood that if the visitor is entering the park for the first time, the visitor's interests can be predicted based on the interests and hobbies of most visitors. If the visitor is not entering the park for the first time, the visitor's interests can be predicted based on the visitor's historical visit information.

[0045] In one embodiment, the display of the smart park knowledge question and answer page based on the large language model on the terminal device includes: in response to the vehicle user's QR code scanning operation on the target entrance of the smart park, displaying the smart park knowledge question and answer page based on the large language model on the terminal device held by the vehicle user. Accordingly, in response to the triggering operation of the parking function in the smart park knowledge question and answer page, a fourth sub-page for the vehicle user to ask questions about the park parking problem can be displayed; in response to the parking navigation question input by the vehicle user in the fourth sub-page, based on the target park location in the parking navigation question, the large language model is used to query the underground parking lot information of the smart park for the nearest vacant parking space to the target park location, and the large language model is used to generate parking navigation information based on the vacant parking space and the location of the target entrance; the parking navigation information is displayed on the fourth sub-page, and the parking navigation information is played in the form of voice.

[0046] It's understandable that first-time users often face difficulties finding parking, primarily due to the park's vast size. Finding a parking space can be challenging, and even once you've found one, it can be difficult to locate an available space. Furthermore, park parking lots are often underground, where positioning signals are weak. Conventional navigation software doesn't work in these areas. Therefore, even if a companion gets out first and finds a vacant space, you might still be unable to navigate to it.

[0047] In the disclosed embodiment, users can scan the QR code at the entrance to the Smart Park to access the Smart Park Q&A page. Within this page, users can further trigger the parking function, thereby querying for available parking spaces on the fourth sub-page corresponding to the parking function. After finding available parking spaces, a large language model can be used to generate parking navigation information based on the location of the available parking spaces and the target entrance. This parking navigation information can be displayed on the fourth sub-page as an image showing the navigation path, or as a voice message that includes landmarks along the way.

[0048] For example, the parking navigation information may be: "Hello! Welcome to the underground parking lot. Please follow the following route to the vacant parking space: Go straight for 50 meters from the entrance: turn left at the first intersection, and you will see a yellow sign for "Area A Elevator Entrance" on the left wall; after passing the elevator entrance: continue straight for about 100 meters, and pay attention to the green fire hydrant (numbered F-03) on the right column; turn right at the green fire hydrant: enter the Area B passage, there is a blue arrow marked "B2-08" on the ground, go in the direction of the arrow; after passing two rows of columns: there is a fluorescent sign for "Charging Pile Area" hanging on the top in front, turn left to reach the parking space (numbered B2-12)".

[0049] In one embodiment, in response to the triggering operation of the emergency drill function in the smart park knowledge question and answer page, a fifth sub-page for the user to ask emergency drill questions can be displayed; in response to the questions about the emergency drill plan entered by the user on the fifth sub-page, the real-time environmental information of the smart park and the real-time operation information of the equipment in the smart park are determined through the sensors in the smart park, the real-time meteorological information of the smart park is determined through the meteorological data interface, and the real-time video of the smart park is obtained from the camera in the smart park, and based on the real-time video, the real-time crowd information and real-time traffic information of the smart park are determined, wherein the real-time environmental information includes the temperature and / or humidity of the smart park; an emergency drill plan for the smart park is generated based on the real-time environmental information, the real-time operation information, the real-time meteorological information, the real-time crowd information and the real-time traffic information through the large language model; and the emergency drill plan is displayed on the fifth sub-page.

[0050] In other words, a large language model can be used to automatically generate emergency drill plans for a smart park by combining real-time environmental information, weather information, crowd flow information, traffic information, and real-time operational information about the park's equipment. This reduces the manpower and time required to generate these plans. Furthermore, because these plans are generated based on real-time park information, they can be dynamically adjusted, improving their practicality.

[0051] In one embodiment, in response to the triggering operation of the work status function in the smart park knowledge question and answer page, a sixth sub-page for the user to inquire about the work status of the staff in the smart park can be displayed; in response to the question about the work status of a specific staff member input in the sixth sub-page, the facial expression and body language of the specific staff member are obtained through the camera at the specific staff member, and the third emotional information of the specific staff member is identified according to the facial expression and the body language through the large language model; when the third emotional information represents that the specific staff member is depressed, the large language model generates an emotional adjustment suggestion, wherein the emotional adjustment suggestion includes a recommended relaxation place within a preset range and / or music for soothing emotions; the emotional adjustment suggestion is displayed on the sixth sub-page, and the emotional adjustment suggestion is sent to the terminal device held by the specific staff member.

[0052] It should be understood that facial expressions and body language can be converted into text and then input into a large language model, which can then identify the emotional information of specific staff members. If this emotional information indicates that a specific staff member is feeling depressed, the large language model can further generate emotional adjustment suggestions, such as recommending a nearby relaxing place or playing soothing music. This allows for deep emotional interaction with park staff through multiple modalities such as voice and expression, enhancing the park's intelligence.

[0053] According to the second aspect of the embodiment of the present disclosure, a smart park knowledge question answering device 200 based on a large language model is provided. Figure 2 , the device 200 includes: A first display module 201 is configured to display a smart park knowledge question and answer page based on a large language model on a terminal device, wherein the smart park knowledge question and answer page is configured to allow users to ask questions related to the smart park in at least one of images, voice, and text; The second display module 202 is configured to, in response to a triggering operation of a device abnormality function in the smart campus knowledge question and answer page, display a first sub-page for the user to inquire about the device abnormality, and, in response to a question entered by the user in the first sub-page regarding the cause of the abnormality of a target device in the smart campus, retrieve the real-time device parameters and historical maintenance records of the target device from a knowledge base, and obtain data from environmental sensors surrounding the target device; A construction module 203 is configured to construct prompt words based on the question of the cause of the abnormality of the target device, the device parameters, the historical maintenance records, and the data from the environmental sensors, wherein the prompt words are used to prompt the large language model to generate an abnormality diagnosis report for the target device based on the question of the cause of the abnormality of the target device, the device parameters, the historical maintenance records, and the data from the environmental sensors; The third display module 204 is configured to input the prompt word into the large language model, obtain an abnormality diagnosis report for the target device, and display the abnormality diagnosis report on the first sub-page.

[0054] In some embodiments of the present disclosure, the apparatus 200 further includes a maintenance operation module configured to: In response to a triggering operation on a maintenance operation function in the smart park knowledge question and answer page, displaying a second sub-page for the user to ask questions about maintenance operations; In response to a maintenance operation question regarding abnormal operation of the target device input by the user in the second sub-page, obtaining physiological information of the user from the wearable device of the user, and obtaining environmental information of the environment in which the user is located through a sensor on the terminal device; determining the stress state of the user based on the physiological information and the environmental information, and, if the stress state indicates that the user is in a high-stress state, generating, using the large language model and the abnormality diagnosis report, the maintenance operation question, the physiological information, and the environmental information, operation step information for instructing the user to perform abnormal maintenance on the target device; The operation step information is displayed on the second sub-page, and the operation step information is played in the form of voice.

[0055] In some embodiments of the present disclosure, the apparatus 200 further includes a visitor module configured to: In response to a triggering operation of a visitor function on the smart park knowledge question and answer page, a third sub-page for visitors is displayed, and in response to an input operation by the user on the third sub-page, emotion recognition is performed on content corresponding to the input operation to obtain first emotion information of the user, wherein the content includes voice content and / or text content; Acquiring the user's facial expression and body language through a camera on the terminal device, and identifying the user's second emotion information based on the expression and the body language; determining target emotion information of the user according to the first emotion information and the second emotion information, and determining a visitor type of the user according to the target emotion information; The large language model is used to generate introduction information of the smart park and smart park guidance information for the user according to the visitor type, and the introduction information and the smart park guidance information are displayed on the third sub-page.

[0056] In some embodiments of the present disclosure, the visitor module is specifically configured to: When the visitor type characterizes the user as a hurried visitor, first introduction information of the smart park and first smart park guidance information for the user are generated by the large language model, wherein the first smart park guidance information is navigation information generated by the large language model for guiding the user to a first location, and the first location is the location in the park that the user desires to reach, as determined by the large language model based on content corresponding to the input operation; When the visitor type characterizes that the user is a leisure visitor, the second introduction information of the smart park and the second smart park guidance information for the user are generated by the large language model, wherein the content of the second introduction information is more than the first introduction information, and the second smart park guidance information is navigation information generated by the large language model for guiding the user to a second location, and the second location is the park location of the user that is predicted by the large language model to be of interest to the user.

[0057] In some embodiments of the present disclosure, the first display module 201 is specifically configured to: In response to a vehicle user scanning a QR code at a target entrance of the smart park, a smart park knowledge question and answer page based on a large language model is displayed on a terminal device held by the vehicle user; The device 200 further includes a parking module for: In response to a triggering operation on a parking function in the smart park knowledge question and answer page, displaying a fourth sub-page for the vehicle user to ask questions about park parking; In response to a parking navigation question input by the vehicle user on the fourth sub-page, querying the underground parking lot information of the smart park for a vacant parking space closest to the target park location using the large language model based on the target park location in the parking navigation question, and generating parking navigation information based on the vacant parking space and the location of the target entrance using the large language model; The parking guidance information is displayed on the fourth sub-page and played in the form of voice.

[0058] In some embodiments of the present disclosure, the apparatus 200 further includes an emergency drill module for: In response to a triggering operation on an emergency drill function in the smart park knowledge question and answer page, displaying a fifth sub-page for the user to ask questions about the emergency drill; In response to a question inquiring about an emergency drill plan input by the user on the fifth subpage, real-time environmental information of the smart park and real-time operating information of equipment in the smart park are determined through sensors in the smart park, real-time meteorological information of the smart park is determined through a meteorological data interface, and real-time video of the smart park is obtained from a camera in the smart park. Based on the real-time video, real-time crowd flow information and real-time traffic information of the smart park are determined. The real-time environmental information includes the temperature and / or humidity of the smart park. Generate an emergency drill plan for the smart park based on the real-time environmental information, the real-time operation information, the real-time weather information, the real-time crowd flow information, and the real-time traffic information through the large language model; The emergency drill plan is displayed on the fifth sub-page.

[0059] In some embodiments of the present disclosure, the apparatus 200 further includes a working status module configured to: In response to a triggering operation on a work status function in the smart park knowledge question and answer page, displaying a sixth sub-page for the user to inquire about the work status of staff in the smart park; In response to a question entered on the sixth subpage asking about the work status of a specific staff member, acquiring a facial expression and body language of the specific staff member through a camera at the specific staff member, and identifying third emotion information of the specific staff member based on the facial expression and the body language using the large language model; When the third emotion information indicates that the specific staff member is in a low mood, generating an emotion regulation suggestion through the large language model, wherein the emotion regulation suggestion includes a recommended relaxing place within a preset range and / or music for soothing the mood; The emotion regulation suggestion is displayed on the sixth sub-page, and the emotion regulation suggestion is sent to the terminal device held by the specific staff member.

[0060] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the first aspect related to the method, and will not be elaborated here.

[0061] According to the third aspect of the embodiment of the present disclosure, please refer to the attached Figure 3 , which exemplarily shows a block diagram of an electronic device, the electronic device 700 may include: a processor 701, a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input / output (I / O) interface 704, and a communication component 705.

[0062] The processor 701 is configured to control the overall operation of the electronic device 700 to complete all or part of the steps in any of the aforementioned methods. The memory 702 is configured to store various types of data to support the operation of the electronic device 700. This data may include, for example, instructions for any application or method operating on the electronic device 700, as well as application-related data, such as the aforementioned abnormality diagnosis report, operation procedure information, smart campus introduction information, smart campus guidance information, etc. The memory 702 may be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 702 or transmitted via the communication component 705. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules. The above-mentioned other interface modules may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more thereof, so the corresponding communication component 705 may include: a Wi-Fi module, a Bluetooth module, an NFC module.

[0063] In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform any of the above methods.

[0064] In another exemplary embodiment, a computer-readable storage medium including program instructions is further provided, wherein the program instructions, when executed by a processor, implement the steps of any of the above methods. For example, the computer-readable storage medium may be the memory 702 including the program instructions, and the program instructions may be executed by the processor 701 of the electronic device 700 to perform any of the above methods.

[0065] In another exemplary embodiment, a computer program product is further provided. The computer program product includes a computer program that can be executed by a processor. When the computer program is executed by the processor, the steps of any of the above methods are implemented.

[0066] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings. However, the present disclosure is not limited to the specific details of the above embodiments. Within the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the scope of protection of the present disclosure.

[0067] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0068] In addition, the various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A knowledge question-answering method for a smart park based on a large language model, characterized by: include: Displaying a smart park knowledge question and answer page based on the large language model on a terminal device, wherein the smart park knowledge question and answer page is used for users to ask questions related to the smart park in at least one of images, voice, and text; In response to a triggering operation of a device abnormality function in the smart campus knowledge question and answer page, a first subpage is displayed for the user to inquire about the device abnormality, and in response to a question entered by the user in the first subpage about the cause of the abnormality of a target device in the smart campus, real-time device parameters and historical maintenance records of the target device are retrieved from a knowledge base, as well as data from environmental sensors surrounding the target device; Constructing prompt words based on the question of the cause of the abnormality of the target device, the device parameters, the historical maintenance records, and the data of the environmental sensors, wherein the prompt words are used to prompt the large language model to generate an abnormality diagnosis report for the target device based on the question of the cause of the abnormality of the target device, the device parameters, the historical maintenance records, and the data of the environmental sensors; The prompt word is input into the large language model to obtain an abnormality diagnosis report for the target device, and the abnormality diagnosis report is displayed on the first sub-page.

2. The smart park knowledge question-answering method according to claim 1, characterized in that: The method further comprises: In response to a triggering operation on a maintenance operation function in the smart park knowledge question and answer page, displaying a second sub-page for the user to ask questions about maintenance operations; In response to a maintenance operation question regarding abnormal operation of the target device input by the user in the second sub-page, obtaining physiological information of the user from the wearable device of the user, and obtaining environmental information of the environment in which the user is located through a sensor on the terminal device; determining the stress state of the user based on the physiological information and the environmental information, and, if the stress state indicates that the user is in a high-stress state, generating, using the large language model and the abnormality diagnosis report, the maintenance operation question, the physiological information, and the environmental information, operation step information for instructing the user to perform abnormal maintenance on the target device; The operation step information is displayed on the second sub-page, and the operation step information is played in the form of voice.

3. The smart park knowledge question-answering method according to claim 1 or 2, characterized in that: The method further comprises: In response to a triggering operation of a visitor function on the smart park knowledge question and answer page, a third sub-page for visitors is displayed, and in response to an input operation by the user on the third sub-page, emotion recognition is performed on content corresponding to the input operation to obtain first emotion information of the user, wherein the content includes voice content and / or text content; Acquiring the user's facial expression and body language through a camera on the terminal device, and identifying the user's second emotion information based on the expression and the body language; determining target emotion information of the user according to the first emotion information and the second emotion information, and determining a visitor type of the user according to the target emotion information; The large language model is used to generate introduction information of the smart park and smart park guidance information for the user according to the visitor type, and the introduction information and the smart park guidance information are displayed on the third sub-page.

4. The smart park knowledge question-answering method according to claim 3, characterized in that: The generating, based on the visitor type, introduction information of the smart park and smart park guidance information for the user using the large language model includes: When the visitor type characterizes the user as a hurried visitor, first introduction information of the smart park and first smart park guidance information for the user are generated by the large language model, wherein the first smart park guidance information is navigation information generated by the large language model for guiding the user to a first location, and the first location is the location in the park that the user desires to reach, as determined by the large language model based on content corresponding to the input operation; When the visitor type characterizes that the user is a leisure visitor, the second introduction information of the smart park and the second smart park guidance information for the user are generated by the large language model, wherein the content of the second introduction information is more than the first introduction information, and the second smart park guidance information is navigation information generated by the large language model for guiding the user to a second location, and the second location is the park location of the user that is predicted by the large language model to be of interest to the user.

5. The smart park knowledge question-answering method according to claim 1 or 2, characterized in that: The display of the smart park knowledge question and answer page based on the large language model on the terminal device includes: In response to a vehicle user scanning a QR code at a target entrance of the smart park, a smart park knowledge question and answer page based on a large language model is displayed on a terminal device held by the vehicle user; The method further comprises: In response to a triggering operation on a parking function in the smart park knowledge question and answer page, displaying a fourth sub-page for the vehicle user to ask questions about park parking; In response to a parking navigation question input by the vehicle user on the fourth sub-page, querying the underground parking lot information of the smart park for a vacant parking space closest to the target park location using the large language model based on the target park location in the parking navigation question, and generating parking navigation information based on the vacant parking space and the location of the target entrance using the large language model; The parking guidance information is displayed on the fourth sub-page and played in the form of voice.

6. The smart park knowledge question-answering method according to claim 1 or 2, characterized in that: The method further comprises: In response to a triggering operation on an emergency drill function in the smart park knowledge question and answer page, displaying a fifth sub-page for the user to ask questions about the emergency drill; In response to a question inquiring about an emergency drill plan input by the user on the fifth subpage, real-time environmental information of the smart park and real-time operating information of equipment in the smart park are determined through sensors in the smart park, real-time meteorological information of the smart park is determined through a meteorological data interface, and real-time video of the smart park is obtained from a camera in the smart park. Based on the real-time video, real-time crowd flow information and real-time traffic information of the smart park are determined. The real-time environmental information includes the temperature and / or humidity of the smart park. Generate an emergency drill plan for the smart park based on the real-time environmental information, the real-time operation information, the real-time weather information, the real-time crowd flow information, and the real-time traffic information through the large language model; The emergency drill plan is displayed on the fifth sub-page.

7. The smart park knowledge question-answering method according to claim 1 or 2, characterized in that: The method further comprises: In response to a triggering operation on a work status function in the smart park knowledge question and answer page, displaying a sixth sub-page for the user to inquire about the work status of staff in the smart park; In response to a question entered on the sixth subpage asking about the work status of a specific staff member, acquiring a facial expression and body language of the specific staff member through a camera at the specific staff member, and identifying third emotion information of the specific staff member based on the facial expression and the body language using the large language model; When the third emotion information indicates that the specific staff member is in a low mood, generating an emotion regulation suggestion through the large language model, wherein the emotion regulation suggestion includes a recommended relaxing place within a preset range and / or music for soothing the mood; The emotion regulation suggestion is displayed on the sixth sub-page, and the emotion regulation suggestion is sent to the terminal device held by the specific staff member.

8. A knowledge question-answering device for a smart park based on a large language model, characterized in that: include: A first display module is configured to display a smart park knowledge question and answer page based on a large language model on a terminal device, wherein the smart park knowledge question and answer page is configured to allow a user to ask questions related to the smart park in at least one of images, voice, and text; a second display module, configured to, in response to a triggering operation of a device abnormality function in the smart campus knowledge question and answer page, display a first sub-page for the user to inquire about the device abnormality, and, in response to a question entered by the user in the first sub-page regarding the cause of the abnormality of a target device in the smart campus, retrieve the real-time device parameters and historical maintenance records of the target device from a knowledge base, and obtain data from environmental sensors surrounding the target device; a construction module, configured to construct prompt words based on the question of the cause of the abnormality of the target device, the device parameters, the historical maintenance records, and the data of the environmental sensors, wherein the prompt words are used to prompt the large language model to generate an abnormality diagnosis report for the target device based on the question of the cause of the abnormality of the target device, the device parameters, the historical maintenance records, and the data of the environmental sensors; The third display module is configured to input the prompt word into the large language model, obtain an abnormality diagnosis report for the target device, and display the abnormality diagnosis report on the first sub-page.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, wherein the memory is used to store computer instructions that can be executed on the processor, and the processor is used to implement the steps of the method according to any one of claims 1 to 7 when executing the computer instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images