A campus course display method, device and medium with wisdom encyclopedia

Abstract

The application discloses a campus course display method and device with wisdom encyclopedias and a medium, and relates to the technical field of wisdom campus. The method comprises the following steps: in response to the fact that a lower computer receives request data input by a student, the lower computer identifies the request data, generates a request text and a corresponding intention type label; the lower computer sends the request text and the intention type label to an upper computer; the upper computer processes corresponding resources based on the intention type label, and generates response information; and the upper computer sends the response information to the lower computer for display. According to the application, the lower computer identifies and generates a request text and an intention type label, and the upper computer generates response information according to the intention type label by calling corresponding resources, so that unified classification and differentiated response of multiple types of student requests are realized, the course display terminal has active interaction capability, and the limitation of the single function of the existing mode is changed.

Description

Technical Field

[0001] This invention relates to the field of smart campus technology, and in particular to a method, device and medium for displaying campus courses with a smart encyclopedia. Background Technology

[0002] With the development of educational informatization, campus course display systems have gradually replaced traditional paper timetables. Paper timetables require manual scheduling, printing, posting, and cleaning, resulting in poor real-time performance, requiring additional lighting at night for viewing, and failing to promptly reflect dynamic information such as temporary course changes or classroom adjustments. To address these issues, electronic real-time course display systems have emerged. These typically consist of a host computer management terminal and slave display terminals. The host computer is used by academic affairs administrators to schedule and publish courses, while the slave terminals are located at building entrances or classroom doors, displaying current course schedules, classroom availability, and temporary change notices to teachers and students. Such systems have improved the timeliness and accuracy of course information dissemination to a certain extent.

[0003] However, existing real-time course display systems still exhibit significant limitations in practical applications. On the host computer side, course scheduling relies heavily on manual operation by academic affairs staff. The scheduling process requires repeated verification of multiple constraints such as teachers, classrooms, and times, resulting in low efficiency and a high risk of conflicts and omissions. On the slave computer side, the display terminal's function is strictly limited to passively receiving and displaying course information, with a single output format and underutilized hardware resources. More importantly, existing systems only focus on the scheduling and display needs of public school courses, neglecting the interactive needs of students as individuals in areas such as knowledge expansion, psychological growth, campus safety assistance, and feedback. They lack the technical support for students' comprehensive development and personalized care. Summary of the Invention

[0004] This invention provides a method, device, and medium for displaying campus courses with a smart encyclopedia. The technical problem it aims to solve is: how to provide a method that can uniformly identify and classify various types of requests initiated by students, and call differentiated resources for response processing based on the classification results.

[0005] In a first aspect, embodiments of the present invention provide a method for displaying campus courses with a smart encyclopedia, comprising: In response to the lower-level machine receiving request data input by the student, the lower-level machine identifies the request data and generates request text and the intent type label corresponding to the request text; The lower-level machine sends the request text and the intent type label to the upper-level machine; The host computer receives the request text and the intent type tag, calls the resource corresponding to the intent type tag for processing based on the intent type tag, and generates response information. The host computer sends the response information to the slave computer, and the slave computer displays the response information on the display screen.

[0006] Optionally, the lower-level machine identifies the request data and generates a request text and an intent type tag corresponding to the request text, including: The lower-level machine performs speech recognition or text parsing on the request data to obtain the request text. The lower-level machine inputs the request text into the intent classification model to identify the intent type of the request text. The intent type includes at least one of the following: course query, school-based common knowledge query, encyclopedia knowledge query, psychological counseling and help, and campus problem feedback. The identified intent type is output as the intent type label.

[0007] Optionally, the step of calling the resource corresponding to the intent type tag based on the intent type tag for processing and generating response information includes: If the intent type tag is a course query or a school-based common knowledge query, then the pre-built course and school-based information database in the host computer is retrieved, and the first query result information is used as the response information. If the intent type tag is encyclopedia knowledge query, then the network encyclopedia knowledge base is searched online to obtain the second query result information as the response information; If the intent type label is psychological counseling and help-seeking, then the preset AI psychological counseling and advisor model is invoked to analyze the request text and generate third feedback information containing guidance or help-seeking instructions as the response information. If the intent type tag is campus issue feedback, then the feedback content in the request text is extracted, the feedback content is associated with the request text and stored, and a fourth feedback message indicating that the feedback content has been received is generated as the response information.

[0008] Optionally, the host computer sends the response information to the slave computer, including: The host computer sends the response information to the slave computer, and simultaneously sends the response information to the student terminal associated with the request. The student terminal includes a mobile phone or a smartwatch.

[0009] Optionally, the lower-level machine displays the response information on a display screen, including: The lower-level machine obtains the current working mode; If the current display mode is a weekday course, the response information will be displayed in a preset first area of ​​the display screen; If the current mode is a holiday with no or few classes, the response information will be displayed in a preset second area of ​​the display screen, and the area of ​​the preset second area is larger than that of the preset first area.

[0010] Optionally, the method further includes: The host computer performs data preprocessing on the set of request texts and intent type tags received within a preset time period; Machine learning algorithms are used to perform cluster analysis and classification model training on the preprocessed data; Based on the model obtained from the training, the psychological and behavioral characteristics, abilities, qualities, and growth needs of the student group were analyzed, and the analysis results were obtained. A student growth pattern analysis report is generated based on the analysis results.

[0011] Optionally, the method further includes a scheduling step, which includes: Receive input of teacher information, course information, class information, classroom information, and temporary changes; The system performs intelligent analysis on the teacher information, course information, class information, and classroom information to generate a preliminary course schedule. Identify teacher conflicts, classroom conflicts, and time conflicts in the preliminary course arrangement, fine-tune the preliminary course arrangement with conflicts, and generate an optimized final course arrangement.

[0012] Optionally, the pre-built course and school-based information database in the host computer stores the final course schedule, classroom usage information, teacher allocation information, and school-based general knowledge information.

[0013] Secondly, embodiments of the present invention also provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0014] Thirdly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the above-described method.

[0015] This invention provides a method, device, and medium for displaying campus courses with a smart encyclopedia. The method includes: responding to a lower-level computer receiving request data input by a student; the lower-level computer identifying the request data and generating request text and a corresponding intent type tag; the lower-level computer sending the request text and intent type tag to a higher-level computer; the higher-level computer receiving the request text and intent type tag, processing the data based on the intent type tag by calling the corresponding resource, and generating response information; the higher-level computer sending the response information to the lower-level computer, and the lower-level computer displaying the response information on a display screen. This invention, based on the lower-level computer identifying student request data and generating request text and intent type tags, and the higher-level computer processing the data based on the intent type tag and generating response information, achieves unified identification and classification of different types of student requests, as well as differentiated resource scheduling and response based on different classification results. As a result, the display terminal, which could only passively display fixed course information, has gained the ability to actively respond to multiple types of requests. This has changed the limitations of the existing method, which was limited by its single function and inability to adapt to students' personalized interaction needs. It has enriched the service dimensions of the campus information terminal without the need to add independent service channels. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A flowchart illustrating a method for displaying campus courses with a smart encyclopedia, provided as an embodiment of the present invention; Figure 2 A schematic diagram of the hardware architecture of a campus course display method with a smart encyclopedia provided in an embodiment of the present invention; Figure 3 A schematic diagram of the main data flow of a campus course display method with a smart encyclopedia provided in an embodiment of the present invention; Figure 4 This is a schematic block diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0020] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0021] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0022] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if [described condition or event] is detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once [described condition or event] is detected," or "in response to detection of [described condition or event]."

[0023] Please see Figure 1 This invention provides a method for displaying campus courses with a smart encyclopedia, aiming to solve the technical problem that existing campus course display systems have limited functionality, can only passively display course information, and cannot respond to students' personalized interaction needs.

[0024] Please see Figure 2 , Figure 2 This is a schematic diagram of the hardware architecture for a campus course display method with a smart encyclopedia, provided as an embodiment of the present invention. Figure 2As shown, the system includes a host computer and at least one slave computer. The host computer is equipped with a human-computer interface for receiving operation instructions from academic affairs administrators. Each slave computer is connected to a display screen and is equipped with a voice processing device for recognizing and processing students' voice input. Each slave computer is also equipped with a signal receiving and transmitting device for data communication with the host computer. Students' mobile phones can interact with both the host and slave computers through the signal receiving and transmitting devices.

[0025] Specifically, the method includes the following steps: S1, in response to the lower-level machine receiving request data input by the student, the lower-level machine identifies the request data and generates request text and the intent type label corresponding to the request text.

[0026] In practice, the lower-level machine refers to an interactive display terminal device deployed in the entrance hall of the teaching building, classroom doorway, or other public areas. The lower-level machine includes a processor, a display screen, a signal receiving and transmitting device, and an input acquisition component. The input acquisition component is used to capture request data initiated by students; for example, students can enter text questions by touching the virtual keyboard on the screen, or they can ask questions directly through a microphone.

[0027] Furthermore, after the lower-level machine receives the request data input by the student, its built-in processor performs recognition processing on the request data. The recognition processing includes: if the request data is a speech signal, the speech waveform is first converted into a text sequence using a speech recognition algorithm; if the request data is text input, the input text content is directly extracted. Regardless of the input format, the output of the recognition step is a request text representing the student's query intent.

[0028] Furthermore, the lower-level machine performs intent classification processing on the request text, mapping the request text to a preset intent category system, thereby generating an intent type label corresponding to the request text. The intent type label is used to characterize the student's intent in this request, such as course schedule inquiry, encyclopedic knowledge acquisition, psychological help requests, or feedback on campus issues. By uniformly converting inputs from different modalities into structured request text and intent type labels, subsequent processing flows can be performed in a standardized data format, improving the system's processing efficiency and scalability.

[0029] In some preferred embodiments, the lower-level machine identifies the request data and generates request text and an intent type label corresponding to the request text, including: the lower-level machine performs speech recognition or text parsing on the request data to obtain the request text; the lower-level machine inputs the request text into an intent classification model to identify the intent type of the request text, the intent type including at least one of course query, school-based common sense query, encyclopedia knowledge query, psychological counseling and help, and campus problem feedback; and outputs the identified intent type as the intent type label.

[0030] In specific implementation, the process by which the lower-level machine identifies the request data and generates request text and the corresponding intent type label further includes the following steps: The lower-level machine performs speech recognition or text parsing on the request data to obtain the request text. In one optional implementation, if a student initiates a request by inputting text via a virtual keyboard on a touchscreen, the lower-level machine directly uses the input string as the request text. If a student initiates a request via voice through a microphone, the lower-level machine calls a speech recognition engine to perform acoustic model matching and language model decoding on the acquired audio stream, converting the speech signal into a corresponding Chinese or foreign language text sequence, and using this text sequence as the request text.

[0031] Furthermore, the lower-level machine inputs the request text into the intent classification model to identify the intent type of the request text. It should be noted that the intent classification model is a machine learning model based on natural language processing. It can be built on a deep neural network and trained on a large corpus of text labeled with intent tags. This model can perform semantic analysis on the input request text, output the probability distribution of the text belonging to each preset intent category, and select the category with the highest probability value as the recognition result.

[0032] Furthermore, in this embodiment, the preset intent types include at least one of the following: course inquiry, school-based knowledge inquiry, encyclopedic knowledge inquiry, psychological counseling and assistance, and campus problem feedback. Specifically, the course inquiry category corresponds to students' needs to inquire about information such as course schedules, classroom locations, and instructors; the school-based knowledge inquiry category corresponds to students' needs to inquire about school-specific knowledge such as school history, motto, and regulations; the encyclopedic knowledge inquiry category corresponds to students' needs to explore extracurricular knowledge areas such as humanities, geography, science and technology, and history; the psychological counseling and assistance category corresponds to students' needs to seek guidance and help when encountering confusion, low mood, interpersonal communication difficulties, or experiencing school violence during their growth; and the campus problem feedback category corresponds to students' needs to report issues such as cafeteria food quality, damaged teaching facilities, and campus safety hazards to the school administration.

[0033] It should be noted that, considering the hardware resource constraints of the lower-level machine deployment environment, when the lower-level machine uses a low-computing-power processor such as a microcontroller, the intent classification model can adopt a lightweight design. In one specific implementation, the intent classification model is a compressed model based on MobileBERT or ALBERT-Tiny, with the number of parameters controlled within 10MB, which can run on memory-constrained embedded devices. In another specific implementation, the intent classification model uses a hybrid classifier based on keyword matching and a rule engine. It quickly matches the request text through a pre-built intent keyword dictionary and combines it with a small number of syntactic rules to determine the intent, thereby completing intent classification with almost no increase in computational load.

[0034] Through the aforementioned lightweight and hardware adaptation solutions, the lower-level machine of this invention can stably run the intent classification function on hardware platforms with different computing power levels, ensuring the universality and feasibility of the technical solution in various campus deployment scenarios.

[0035] S2, the lower-level machine sends the request text and the intent type label to the upper-level machine.

[0036] In practice, after identifying the request data and generating the request text and intent type label, the lower-level machine packages and sends the data to the upper-level machine through its configured signal receiving and transmitting device. The upper-level machine refers to a centralized management computer deployed in the school's academic affairs management department or data center, responsible for maintaining the school's course data, running AI algorithms, and coordinating communication with each lower-level machine. Furthermore, the lower-level machine and the upper-level machine can establish a communication connection through wired LAN, Wi-Fi network, or mobile communication network. The sent data packet must contain at least the original content of the request text, the identified intent type label, and the identifier of the lower-level machine that sent the request, so that the upper-level machine can distinguish the source of the request and accurately send a response back to the corresponding lower-level machine after generating it.

[0037] S3, the host computer receives the request text and the intent type tag, calls the resource corresponding to the intent type tag for processing based on the intent type tag, and generates response information.

[0038] In practice, after receiving the request text and intent type tag uploaded by the slave device, the host computer first parses the data packet and extracts the request text content and intent type tag value. The host computer is pre-configured with various resource processing modules, each of which is associated with one or more intent type tags.

[0039] For example, for queries involving course information or school-based knowledge, the host computer will retrieve resources from the local database; for queries involving extracurricular encyclopedic knowledge, it will retrieve online search resources; for queries involving requests for help with student psychological counseling, it will retrieve pre-built AI-powered psychological counseling models; and for queries involving feedback on campus facilities or management issues, it will retrieve information recording and forwarding resources. Based on the specific value of the received intent type tag, the host computer selects a matching processing resource from the above resource configuration, inputs the request text into that resource, executes the corresponding processing logic, and finally generates a response message for the request. The response message can be a descriptive text of a course schedule, a set of encyclopedic knowledge entries with images and text, a voice suggestion for psychological counseling, or a confirmation message indicating that feedback has been received.

[0040] This embodiment uses a differentiated resource invocation method based on intent type labels, enabling the host computer to provide targeted responses to different types of requests, thus avoiding the limitation of traditional course display systems that use the same processing method for all inputs.

[0041] In some preferred embodiments, the step of calling the resource corresponding to the intent type tag for processing based on the intent type tag to generate response information includes: if the intent type tag is a course query or a school-based common sense query, then retrieving the pre-built course and school-based information database in the host computer to obtain first query result information as the response information; if the intent type tag is an encyclopedia knowledge query, then retrieving the online encyclopedia knowledge base to obtain second query result information as the response information; if the intent type tag is psychological counseling and help-seeking, then calling the pre-built AI psychological counseling and advisor model to analyze the request text and generate third feedback information containing guidance or help-seeking instructions as the response information, wherein the help-seeking instructions include solutions to school violence; if the intent type tag is school problem feedback, then extracting the feedback content from the request text, associating and storing the feedback content with the request text, and generating fourth feedback information indicating that the feedback content has been received as the response information.

[0042] In specific implementation, if the intent type tag is a course query or a school-based common knowledge query, then the pre-built course and school-based information database in the host computer is retrieved to obtain the first query result information as the response information.

[0043] Specifically, the pre-built curriculum and school-based information database in the host computer is a structured or semi-structured data storage system, which stores the timetables of all classes in the school, the allocation of time slots for each classroom, the teaching arrangements of each teacher, the textbook information of each course, and school-based common knowledge information such as school history, school motto and rules, and departmental functions.

[0044] Furthermore, after receiving the request text, the host computer extracts keywords or entity information, such as course name, teacher's name, classroom number, or general knowledge keywords. Based on these keywords, it performs a matching search in the database, organizes the retrieved matching records into easily readable text or table format, and returns this as the first query result. For example, if a student asks which classroom the second period class will be in tomorrow afternoon, the host computer retrieves the corresponding course schedule from the database based on the student's class and current semester, generating a response containing the classroom number and course name.

[0045] Furthermore, if the intent type tag is an encyclopedia knowledge query, then an online encyclopedia knowledge base is searched online to obtain the second query result information as the response information. After recognizing the encyclopedia knowledge query intent, the host computer initiates a search request to one or more online encyclopedia knowledge bases via an internet interface. It should be noted that the online encyclopedia knowledge base can be a publicly available online encyclopedia, knowledge graph database, or an authorized third-party popular science content platform; this invention does not specifically limit this.

[0046] Furthermore, the host computer uses the core query object in the request text as search terms, such as Einstein, Tiangong space station, or photosynthesis, and sends it to the aforementioned knowledge base for matching queries. The search results returned by the knowledge base typically include term summaries, detailed descriptions, related image links, or video embedding codes. Further, the host computer performs format cleaning and content security filtering on the returned raw data, removing advertisements, inappropriate information, or redundant content unrelated to the query topic. The cleaned content is then organized into a second query result containing text, images, or video information, which serves as the response information.

[0047] Furthermore, if the intent type label is psychological counseling and help-seeking, a pre-built AI psychological counseling and advisor model is invoked to analyze the request text and generate third-party feedback information containing guidance or help-seeking instructions as the response information. The help-seeking instructions include suggestions for dealing with school violence. It should be noted that the AI ​​psychological counseling and advisor model is a large-scale language model specifically trained on psychological corpora, capable of understanding the emotional state, confusion, and help-seeking requests expressed by students in their request texts. The host computer inputs the request text into the model, which first generates sentiment analysis and problem identification results for the request text, and then generates a natural language response based on the basic principles of psychological counseling and the school safety response plan. The response may include words of emotional reassurance for the student, guidance suggestions for addressing learning anxiety or interpersonal problems, and the safest and most reliable coping steps and reporting channels when a student is identified as having experienced or witnessed school violence. By invoking this AI psychological counseling and advisor model, the host computer can provide immediate, anonymous, and professional initial support to students experiencing psychological distress or potential danger.

[0048] In one specific embodiment of the present invention, the pre-built AI psychological counseling and advisor model adopts a large-scale language model based on a Decoder-Only architecture, specifically a fine-tuned version of an open-source model such as ChatGLM, LLaMA, or Qwen. The basic components of this model include a network structure composed of multiple stacked Transformer decoders, each layer containing a masked multi-head self-attention mechanism and a feedforward neural network. The training method of the AI ​​psychological counseling and advisor model includes: using low-rank adaptation (LoRA) technology for efficient instruction fine-tuning of parameters on top of the basic pre-trained language model. During training, a constructed psychological counseling instruction dataset is used to optimize the model's ability to generate responses to user requests for help in a supervised learning manner. The optimization objective is to minimize the negative log-likelihood loss between the generated response and the reference response. The optimizer used is AdamW, with a learning rate set to 1e-4 and a LoRA rank set to 8. The training data sources include: anonymized dialogue data obtained from publicly available psychological counseling Q&A websites (with authorization), case Q&A dialogue data from psychology textbooks, and simulated help-seeking and guidance dialogue samples written by qualified school psychological counselors based on common psychological problems on campus. All data has undergone rigorous privacy anonymization and content security audits to ensure it does not contain any personally identifiable information. The dataset contains no fewer than 2,000 dialogue pairs.

[0049] Furthermore, if the intent type tag is "campus problem feedback," the feedback content is extracted from the request text, associated with and stored in relation to the request text, and a fourth feedback message indicating that the feedback content has been received is generated as the response information. Upon receiving such a request, the host computer extracts information from the request text, identifying elements such as the specific problem description, location, and involved facilities. Further, the host computer associates the feedback content with metadata such as the timestamp of the request and the location identifier of the slave device, storing them together in the background campus problem feedback record database. This database can be accessed and processed by administrators such as the school's logistics management department, security department, or principal's office. Furthermore, the host computer generates a brief confirmation message as the fourth feedback message, such as "Your problem has been received. The relevant school department will verify and process it as soon as possible. Thank you for your feedback." This confirmation message is returned to the slave device as response information, informing the student that their feedback has been successfully received by the system.

[0050] This embodiment, through detailed definition of the request data recognition process, intent classification model, and classification response generation logic, enables the system to accurately distinguish five typical student interaction needs and process them by calling differentiated resources such as local database retrieval, online encyclopedia retrieval, AI psychological model guidance, and feedback record storage, thereby achieving a refined response to students' personalized needs.

[0051] S4, the host computer sends the response information to the slave computer, and the slave computer displays the response information on the display screen.

[0052] In practice, after generating the response information, the host computer sends the response information back to the corresponding slave computer via the communication network according to the slave device identifier carried in the request data packet. Upon receiving the response information, the slave computer's processor parses the content format of the response information to determine its media type, such as plain text, static images, audio streams, or video streams. Further, the slave computer renders the parsed content onto its connected display screen for display. The display screen can be a liquid crystal display, a light-emitting diode display, or an organic light-emitting diode display, etc. If the response information contains audio content, the slave computer can also synchronously play the sound through built-in or external speakers. Through this process, the student's request receives intuitive and immediate visual or auditory feedback at the slave computer, realizing two-way intelligent interaction between humans and machines.

[0053] This embodiment converts student requests into request text and intent type tags, and the host computer calls corresponding resources to generate responses based on the differences in intent type tags. This enables the display terminal, which was originally only used to passively display course information, to actively respond to multiple types of student requests, providing a methodological basis for building a smart campus interactive platform that integrates course services, knowledge services, psychological services, and feedback services.

[0054] In some preferred embodiments, the host computer sends the response information to the slave computer, including: the host computer sends the response information to the slave computer and simultaneously sends the response information to a student terminal associated with the request, the student terminal including a mobile phone or a smartwatch.

[0055] In practice, during the process of the host computer sending the response information to the slave computer, the host computer also sends the response information to the student terminal associated with the request. The student terminal includes a mobile phone or a smartwatch. When a student initiates a request on the slave computer, the slave computer can obtain the student's identity identifier through an authentication method, such as the student completing the identity association by swiping their campus card, entering their student ID and password, or scanning a dynamic QR code on the screen.

[0056] Furthermore, when the lower-level device sends the request text and intent type label to the upper-level device, it also includes the aforementioned student identification. After generating the response information, the upper-level device, in addition to sending the response information back to the lower-level device via the communication network for display on the public screen, also queries the pre-stored student personal information database based on the student identification to obtain the student's bound mobile phone number or electronic watch device identifier. Furthermore, the upper-level device sends the response information to the student's mobile phone or electronic watch via SMS gateway, application push service, or Bluetooth communication module, in the form of text message, in-app notification, or data synchronization. After leaving the lower-level device, students can still view the course schedule, classroom change notifications, or encyclopedia summaries they just retrieved on their personal mobile terminals, avoiding the embarrassment of forgetting information due to a brief screen view and improving the persistence and convenience of information retrieval.

[0057] In some preferred embodiments, the lower-level machine displays the response information on the display screen, including: the lower-level machine obtains the current working mode; if the current mode is a weekday course display mode, the response information is displayed in a preset first area of ​​the display screen; if the current mode is a holiday mode with no or few classes, the response information is displayed in a preset second area of ​​the display screen, the area of ​​the preset second area being larger than the preset first area.

[0058] In specific implementation, the process of the lower-level machine displaying the response information on the display screen includes the step of the lower-level machine determining the current working mode. Specifically, the lower-level machine internally maintains a working mode status variable, which can automatically switch based on a system-preset schedule, or can be controlled in real time by the upper-level machine through remote commands. The working modes include at least two types: weekday course display mode and holiday no-class or low-class mode. When determining the working mode, the lower-level machine obtains the current system date and time and compares it with the pre-stored teaching calendar. If the current date belongs to a normal teaching weekday in the teaching calendar, it is determined that the current mode is weekday course display mode. If the current date belongs to a weekend, statutory holiday, or winter / summer vacation in the teaching calendar, it is determined that the current mode is holiday no-class or low-class mode.

[0059] Furthermore, if the current display mode is a weekday course display, the response information will be displayed in a preset first area of ​​the display screen. During normal teaching hours, the primary function of the lower-level computer display screen is to show teachers and students the current and subsequent course schedules, classroom occupancy status, temporary class rescheduling notices, and school promotional slogans. Therefore, in the weekday course display mode, most of the display screen is designated as the main area for displaying course information, while the area used to display AI question-and-answer response information is limited to a relatively small preset first area. This preset first area can be located on the right edge of the screen, the bottom banner, or a corner floating window, and its area does not exceed one-third of the total screen area to ensure that the prominence and integrity of the course information are not affected. For example, the results of a student's query about Einstein will be presented in this first area in the form of scrolling text or small graphic cards.

[0060] Furthermore, if the current mode is a holiday with no or few classes, the response information will be displayed in a preset second area of ​​the display screen, which is larger than the preset first area. During holidays or non-teaching periods, since there is almost no course schedule information to display, most or even all of the display area of ​​the lower-level machine's screen is idle or only used for looping school promotional videos. At this time, the lower-level machine will switch the display layout, expanding the display area of ​​the AI ​​Q&A response information to the preset second area. This preset second area can be expanded to the full screen or occupy most of the screen area, thereby enabling the display of encyclopedic knowledge content in a richer form, such as high-definition pictures, popular science short videos, or long text introductions. The display form of the response information on the display screen includes at least one of text, pictures, voice, and video. For example, a student's video query request about the Tiangong space station can, in holiday mode, directly play video footage of the space station traveling in space in an area occupying most of the screen area, supplemented by voice narration, temporarily transforming the lower-level machine into a campus popular science multimedia terminal.

[0061] Through the aforementioned working mode judgment and dynamic adjustment mechanism for the display area, this embodiment achieves on-demand allocation and efficient reuse of screen resources. On weekdays, the display primarily focuses on course content, supplemented by Q&A, to ensure teaching order; on holidays, Q&A content is elevated to the main display target, fully leveraging the science education value of the hardware device during non-teaching periods.

[0062] In some preferred embodiments, the method further includes: the host computer preprocessing the set of request texts and intent type tags received within a preset time period; using machine learning algorithms to perform cluster analysis and classification model training on the preprocessed data; based on the trained model, analyzing the psychological and behavioral characteristics, abilities, and growth needs of the student group to obtain analysis results; and generating a student growth pattern analysis report based on the analysis results.

[0063] In practice, the technical problem this embodiment aims to solve is: how to automatically mine the psychological and behavioral characteristics and developmental needs of students from daily interaction data without increasing the burden of questionnaires for teachers and students, thus providing data support for campus management and personalized education. The specific implementation method is as follows.

[0064] During daily communication with each slave device, the host computer continuously records the request text content, identified intent type tags, timestamps of the requests, the location of the slave device initiating the request, and associated student anonymization identifiers for each interaction. This data accumulates in the host computer's storage system as logs, forming a set of interaction data for a specific time period. The preset time period can be a semester, an academic year, or any analysis cycle specified by the system administrator. Furthermore, the host computer first performs data preprocessing operations on this set. Preprocessing includes, but is not limited to, removing stop words and punctuation marks from the request text, performing word segmentation and part-of-speech tagging, converting the text into numerical representations such as word vectors or sentence vectors, and performing one-hot encoding or tag encoding on the intent type tags, so that machine learning algorithms can directly process the data.

[0065] Furthermore, after data preprocessing, the host computer uses machine learning algorithms to perform cluster analysis and classification model training on the preprocessed data. Cluster analysis is used to discover the implicit topic distribution and behavioral patterns in student requests. For example, after vectorizing the request text, K-means clustering or hierarchical clustering algorithms can group semantically similar requests into the same cluster. By analyzing the high-frequency keywords of each cluster, topics that students are generally concerned about in a certain period can be discovered, such as exam anxiety, course selection guidance, space science, or cafeteria hygiene. Further, classification model training uses labeled intent type tags as supervision signals to train a more refined classifier of student psychological states or need types, enabling it to identify finer-grained psychological or cognitive states from request texts, such as expressions of mild anxiety, help-seeking signals, and expressions of curiosity and exploration.

[0066] Furthermore, based on the trained clustering and classification models, the host computer analyzes each newly received request data or the entire historical dataset, extracting characteristic indicators of the student group from multiple dimensions. For example, it statistically analyzes the distribution ratio and trends of various intent type tags over time, examines the frequency of key emotional words in psychological counseling and help-seeking requests, and identifies differences in request content between lower-level computers of different grades or regions. Through comprehensive analysis of these characteristics, the host computer can draw quantitative or qualitative conclusions about the psychological and behavioral characteristics, abilities and qualities, and current developmental needs of the student group.

[0067] Furthermore, the host computer organizes and summarizes the above analysis results, automatically generating a student growth pattern analysis report according to a preset report template. This report may include textual descriptions, statistical charts, and recommended measures, such as rankings of student concerns over a certain period, trend analysis of mental health assistance requests, distribution of campus problem feedback types and assessment of handling efficiency, and personalized counseling suggestions for specific student groups. This report can be used as a reference by the school's student affairs department, mental health center, academic affairs office, and logistics management department, providing data-driven decision-making support for developing more scientific student care policies, optimizing campus resource allocation, and promoting individualized education.

[0068] This embodiment utilizes unstructured text data generated from daily interactions for machine learning analysis, upgrading the lower-level computer display screen from a simple information output terminal to a seamless collection and analysis terminal for students' ideological dynamics. This replaces the traditional manual questionnaire survey method, achieving low-cost, high-efficiency, and sustainable insights into student group behavior.

[0069] In some preferred embodiments, the method further includes a scheduling step, which includes: receiving input teacher information, course information, class information, classroom information, and temporary change factors; performing intelligent analysis on the teacher information, course information, class information, and classroom information to generate a preliminary course schedule; identifying teacher conflicts, classroom conflicts, and time conflicts in the preliminary course schedule, fine-tuning the conflicting preliminary course schedule, and generating an optimized final course schedule. The pre-built course and school-based information database in the host computer stores the final course schedule, classroom usage information, teacher allocation information, and school-based general knowledge information.

[0070] In specific implementation, the technical problem to be solved in this embodiment is: how to efficiently generate a conflict-free course schedule on the host computer and use this course schedule as the data basis for the course query function in the aforementioned embodiments. The specific implementation method is as follows.

[0071] The method also includes a scheduling step. This step first receives input teacher information, course information, class information, classroom information, and temporary change factors. This information is entered by academic affairs administrators through a human-computer interaction interface on a host computer or imported from the school's existing academic affairs system. Teacher information includes teacher name, courses taught, and constraints on unschedulable time slots. Course information includes course name, course code, weekly class hour requirements, and requirements for combining or separating classes. Class information includes class name, number of students, and grade and major. Classroom information includes classroom number, building location, capacity, and whether multimedia equipment is provided. Temporary change factors include dynamic events such as temporary teacher leave, temporary classroom maintenance, and temporary occupancy for additional academic activities. All of the above information is categorized and stored in the host computer's storage unit in the form of structured data tables. For example, each record in the teacher information table contains a unique teacher identifier, name, and a set of unschedulable time slots; each record in the classroom information table contains a unique classroom identifier, capacity attributes, and multimedia equipment attributes.

[0072] Furthermore, the host computer performs a comprehensive analysis of the teacher information, course information, class information, and classroom information to generate a preliminary course schedule. This comprehensive analysis process is executed through item-by-item matching and constraint verification. First, the host computer iterates through all courses to be scheduled, determining the set of classes and teachers for each course. For each course, the host computer filters from the classroom information table a set of candidate classrooms with a capacity not less than the number of students in the class and that meet the course's multimedia equipment requirements. Further, within a preset teaching time grid, the host computer allocates a teaching time slot for the course that simultaneously meets the following conditions: the time slot is outside the teacher's unschedulable time slots, the time slot is available in the assigned course schedule of the class, and the time slot is available in the selected classroom's occupied time slots. Further, the host computer performs the above time slot allocation and classroom matching operations one by one according to a preset course priority order. The course priority is preset based on factors such as course nature, credit weight, or grade level, for example, required courses take precedence over elective courses, and higher-grade courses take precedence over lower-grade courses. The host computer assigns teaching time slots and classrooms to each course one by one according to the above priority order, until all courses have been assigned, thus forming a preliminary course schedule covering all classes, teachers and classrooms in the school.

[0073] Furthermore, the host computer identifies teacher conflicts, classroom conflicts, and time conflicts in the preliminary course schedule and makes minor adjustments to the conflicting preliminary course schedules. Due to the large number of courses to be scheduled and the potential for mutual constraints, the above item-by-item matching process may result in later-assigned courses failing to find completely free time slots or classrooms under the constraints of earlier assignments, thus generating conflicts. The host computer performs global conflict detection on the preliminary course schedule, detecting conflict types including: the same teacher assigned to two different classrooms in the same teaching time slot, the same class assigned to two different courses in the same teaching time slot, and the same classroom assigned to two different classes in the same teaching time slot. Furthermore, the host computer visually marks and displays the detected conflicts on a graphical interface, for example, highlighting conflicting course entries with a different color than normal entries and displaying a textual explanation of the conflict reason next to the entry. Furthermore, academic administrators can manually adjust the course schedule by observing the conflict markers on the graphical interface. Adjustment operations include: selecting a conflicting course entry and dragging it to another free teaching time slot, or clicking on the conflicting course entry and selecting a replacement classroom from a drop-down menu. Furthermore, upon receiving each adjustment operation, the host computer re-executes the aforementioned conflict detection logic in real time for the teachers, classes, classrooms, and time slots involved in the adjustment. If the detection result indicates that no new conflicts have been introduced, the adjustment operation is accepted and the course schedule data is updated; if the detection result indicates that new conflicts have been introduced, a prompt message is displayed on the graphical interface and the adjustment operation is rejected. Academic affairs administrators can repeatedly try different adjustment schemes until all conflicts are eliminated.

[0074] Furthermore, the host computer will use the course schedule that has been fine-tuned and confirmed to be conflict-free as the final course schedule, and store the final course schedule in the host computer's storage unit in the form of structured data.

[0075] Furthermore, the pre-built course and school-based information database in the host computer stores the final course schedule, classroom usage information, teacher allocation information, and school-based general knowledge information. This database is the data source retrieved in Embodiment 3 when the intent type tag is course query or school-based general knowledge query. The final course schedule data table records the course name, instructor, and classroom for each teaching class for each time slot each week. The classroom usage information table, generated based on the final course schedule, records the occupancy status of each classroom for each teaching time slot, including the teaching class information corresponding to the occupied time slot and the available time slot. The teacher allocation information table, also generated based on the final course schedule, records the teaching task allocation for each teacher for each teaching time slot. The school-based general knowledge information table stores general knowledge texts such as school history, school motto and regulations, and departmental function introductions. Since the final course schedule is stored after conflict detection and fine-tuning confirmation, the course-related data in this database is completely consistent with the actual arrangements of the academic affairs management department. When the lower-level computer sends a course query request to the host computer, the host computer can directly retrieve accurate and real-time course information as a response content by searching this database.

[0076] This embodiment details the complete data processing flow from receiving teacher, course, class, and classroom information, as well as temporary changes during the scheduling process, to matching each item to generate a preliminary course schedule, then to conflict detection and visual fine-tuning, and finally generating a conflict-free final course schedule and storing it in the database. This process replaces the traditional manual trial-and-error scheduling method with hierarchical constraint verification and visual conflict feedback, reducing human error and repetitive work. Simultaneously, the scheduling results serve as the underlying data support for the interactive system, ensuring that the course information queried by students on the lower-level computers accurately reflects the latest arrangements of the academic affairs management.

[0077] In some preferred embodiments, the lower-level machine includes a microcontroller, a digital signal processor, or a field-programmable gate array processor.

[0078] In practical implementation, the lower-level machine includes a microcontroller, a digital signal processor, or a field-programmable gate array (FPGA). In actual campus deployments, the lower-level machine can flexibly select different types of processor cores based on the functional requirements and budget constraints of the installation location. For edge nodes that only need to drive small displays, process simple voice wake-up words, and perform lightweight intent classification—for example, small-screen terminals deployed at the entrance of a single classroom to display the classroom's timetable and respond to simple text-based questions and answers—a low-power, low-cost microcontroller can be used as the main control chip. The microcontroller integrates a central processing unit core, read-only memory, random access memory, and input / output interfaces, enabling it to run a lightweight speech recognition engine and a simplified intent classification model.

[0079] Furthermore, for applications requiring high-definition voice input, driving large-size, high-resolution displays, and supporting smooth video playback, such as large-screen terminals deployed in the entrance hall of teaching buildings as campus information hubs, the lower-level machine can employ a digital signal processor (DSP). DSPs have dedicated hardware multipliers and accumulators and a Harvard bus architecture, making them particularly adept at processing real-time data streams such as voice and image signals. They can efficiently perform complex signal processing tasks such as voice noise reduction, echo cancellation, speech recognition, acoustic model inference, and video decoding, ensuring system response speed and smoothness under high-load scenarios.

[0080] Furthermore, in another alternative implementation, for high-end deployment scenarios requiring hardware acceleration for AI inference tasks, the lower-level machine can employ a Field-Programmable Gate Array (FPGA). An FPGA is a semi-custom circuit; users can configure the connections of its internal logic gates using a hardware description language, thereby implementing dedicated hardware acceleration circuits for specific algorithms. For example, some computational layers of a trained intent classification neural network model can be mapped to the logic units of an FPGA for parallel execution, thus completing intent recognition inference tasks with significantly lower power consumption and latency than general-purpose processors. This implementation is suitable for power-sensitive but computationally demanding uninterrupted operating environments.

[0081] This embodiment provides multiple processor hardware architecture options, enabling the lower-level machine of the present invention to be flexibly deployed according to specific application scenarios, meeting functional requirements while taking into account cost-effectiveness and energy consumption control.

[0082] Further, see Figure 3 , Figure 3 This is a schematic diagram of the main data flow of a campus course display method with a smart encyclopedia provided in an embodiment of the present invention. For example... Figure 3As shown, the data processing flow of the above method includes two parallel branches. The first branch is the student interaction branch, where students input their requests via voice or other means through a lower-level computer. After recognizing the requests, the lower-level computer directs them to either a course query path or an encyclopedia Q&A path based on the request type. In the course query path, the upper-level computer queries the course database to obtain information such as timetables and school-based general knowledge. In the encyclopedia Q&A path, the upper-level computer intelligently retrieves encyclopedic knowledge through the internet and filters the retrieved data, images, and audio content, removing useless or inappropriate information and generating useful information. The encyclopedia knowledge is displayed in various formats, including text, images, videos, and audio, and the content includes knowledge beneficial to students' physical and mental health, such as humanities, geography, science and technology, and inventions. The query results or encyclopedia knowledge are displayed on a display terminal or sent to students' mobile phones. The second branch is the course scheduling branch. The host computer collects data on teachers, courses, classes, classrooms, required resources, and potential variables. Based on historical evaluations, it performs preliminary course scheduling. Then, it uses machine learning algorithms to optimize the preliminary course arrangement, ensuring it meets all fixed and variable factors, and generates an optimized course scheduling plan. This optimized plan is then fed back to teachers and students for confirmation until the optimal course scheduling plan is generated. Furthermore, this method includes collecting, organizing, and preprocessing student questions. It analyzes and studies student questions using cluster analysis, classification models, and machine learning, and applies the research results to students, improving their needs and understanding, while also improving campus construction.

[0083] The technical effects of this invention are as follows.

[0084] Effect 1: Based on the technical features of the lower-level computer identifying student request data and generating request text and intent type tags, and the upper-level computer calling corresponding resources for processing and generating response information according to the intent type tags, this invention upgrades the traditional one-way course display terminal into a multimodal intelligent interactive platform integrating course query, encyclopedia Q&A, psychological counseling, and campus feedback. Students no longer need to obtain different services through different channels; they only need to interact with the same terminal once to receive differentiated response content tailored to their specific needs, greatly enriching the service content of the campus information terminal.

[0085] Secondly, based on intent type tags, requests are subdivided into course inquiry, school-based knowledge inquiry, encyclopedic knowledge inquiry, psychological counseling and assistance, and campus problem feedback. Response information is generated through methods such as searching local databases, searching online knowledge bases, calling AI psychological counseling and advisor models, and associating with stored feedback content. This invention achieves accurate classification of student request intents and highly adaptive resource scheduling. Each type of request is routed to the most suitable processing module, ensuring the professionalism and relevance of the response content. For example, psychological counseling requests receive professional guidance that conforms to psychological principles rather than simple keyword search results, and requests for assistance regarding campus violence receive specific guidance including proper handling steps rather than general comfort.

[0086] Thirdly, based on the technical feature of the host computer simultaneously sending response information to the lower-level computer's display screen and the student's mobile phone or smartwatch, this invention breaks through the information silo between the public display screen and the personal mobile terminal. Even if students leave after briefly viewing the screen, they can still access the query results on their personal devices at any time, avoiding information forgetting and repeated queries, thus improving the continuity of information services and user experience.

[0087] Fourthly, based on the technical feature of the lower-level machine determining the working mode and dynamically adjusting the size of the response information display area according to weekdays or holidays, this invention achieves time-division multiplexing and adaptive allocation of screen display resources. It ensures the priority display and prominence of timetable information on weekdays, and maximizes the use of idle screen area for displaying popular science content on holidays, thus tapping into the potential educational value of the device during non-teaching periods without increasing hardware investment.

[0088] Fifthly, based on the technical features of the host computer performing data preprocessing, cluster analysis, and classification model training on the request texts and intent type tag sets received within a preset time period, and generating a student growth pattern analysis report, this invention provides a seamless, low-cost, and sustainable means of gaining insights into student group behavior. Schools can extract high-value information about students' psychological dynamics, concerns, and developmental needs from daily interaction data without needing to conduct large-scale questionnaire surveys, providing objective data support for campus management and student affairs decision-making.

[0089] Effect Six: Based on the information received from the host computer, including teacher, course, class, and classroom information, as well as temporary changes, the system comprehensively analyzes and matches this information item by item to generate a preliminary course schedule. It identifies teacher, classroom, and time conflicts in the preliminary schedule, visually marks conflicting schedules, and allows for manual adjustments by academic affairs administrators. After each adjustment, a conflict check is performed in real time, and the system decides whether to accept or reject the adjustment based on the check results. Finally, a conflict-free final course schedule is generated and stored in the course and school-based information database. This invention transforms the scheduling process from manual trial-and-error scheduling to data-driven, constraint-checked scheduling. By decomposing the scheduling process into continuous data processing steps—information reception, item-by-item matching, conflict detection, visual fine-tuning interaction, and check feedback—academic affairs staff no longer need to maintain numerous constraints in their minds. They only need to make targeted adjustments to a limited number of conflict items detected by the system. Each adjustment is constrained by real-time conflict check, effectively avoiding the risk of introducing new conflicts during the adjustment process. This reduces the manpower and time consumption of scheduling work while ensuring the accuracy of the scheduling results. Meanwhile, the final course schedule generated through the above process is directly used as the data source for the course query function, ensuring that the course information queried by students through the lower-level machine is synchronized in real time and is accurate and consistent with the actual arrangements of the academic affairs management department.

[0090] Please see Figure 4 , Figure 4 This is a schematic block diagram of a computer device provided in an embodiment of this application. The computer device 500 can be a terminal or a server, wherein the server can be a standalone server or a server cluster composed of multiple servers.

[0091] The computer device 500 includes a processor 502, a memory, and a network interface 505 connected via a system bus 501. The memory may include a non-volatile storage medium 503 and internal memory 504.

[0092] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, it causes the processor 502 to execute a method for displaying campus courses with a smart encyclopedia.

[0093] The processor 502 provides computing and control capabilities to support the operation of the entire computer device 500.

[0094] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a method for displaying campus courses with a smart encyclopedia.

[0095] The network interface 505 is used for network communication with other devices. Those skilled in the art will understand that the above structure is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device 500 to which the present application is applied. A specific computer device 500 may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements.

[0096] The processor 502 is used to run a computer program 5032 stored in a memory to implement the steps of any of the above method embodiments.

[0097] It should be understood that in the embodiments of this application, the processor 502 may be a central processing unit (CPU), but it may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0098] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0099] Therefore, the present invention also provides a storage medium. This storage medium may be a computer-readable storage medium. The storage medium stores a computer program. When executed by a processor, the computer program causes the processor to perform the steps of any of the above-described method embodiments.

[0100] The storage medium is a physical, non-transient storage medium, such as a USB flash drive, external hard drive, read-only memory (ROM), magnetic disk, or optical disk, or any other physical storage medium capable of storing program code. The computer-readable storage medium can be non-volatile or volatile.

[0101] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0102] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0103] The steps in the method of this invention can be adjusted, merged, or reduced in order according to actual needs. The units in the device of this invention can be merged, divided, or reduced according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0104] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0105] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0106] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, this invention is also intended to include these modifications and variations as long as they fall within the scope of the claims and their equivalents.

[0107] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for displaying campus courses with an intelligent encyclopedia, characterized in that, include: In response to the lower-level machine receiving request data input by the student, the lower-level machine identifies the request data and generates request text and the intent type label corresponding to the request text; The lower-level machine sends the request text and the intent type label to the upper-level machine; The host computer receives the request text and the intent type tag, and calls the resource corresponding to the intent type tag for processing based on the intent type tag to generate response information; The host computer sends the response information to the slave computer, and the slave computer displays the response information on the display screen.

2. The campus course display method with intelligent encyclopedia according to claim 1, characterized in that, The lower-level machine identifies the request data and generates a request text and an intent type tag corresponding to the request text, including: The lower-level machine performs speech recognition or text parsing on the request data to obtain the request text. The lower-level machine inputs the request text into the intent classification model to identify the intent type of the request text. The intent type includes at least one of the following: course query, school-based common knowledge query, encyclopedia knowledge query, psychological counseling and help, and campus problem feedback. The identified intent type is output as the intent type label.

3. The campus course display method with intelligent encyclopedia according to claim 2, characterized in that, The process of calling the resource corresponding to the intent type tag based on the intent type tag to generate response information includes: If the intent type tag is a course query or a school-based common knowledge query, then the pre-built course and school-based information database in the host computer is retrieved, and the first query result information is used as the response information. If the intent type tag is encyclopedia knowledge query, then the network encyclopedia knowledge base is searched online to obtain the second query result information as the response information; If the intent type label is psychological counseling and help-seeking, then the preset AI psychological counseling and advisor model is invoked to analyze the request text and generate third feedback information containing guidance or help-seeking instructions as the response information. If the intent type tag is campus issue feedback, then the feedback content in the request text is extracted, the feedback content is associated with the request text and stored, and a fourth feedback message indicating that the feedback content has been received is generated as the response information.

4. The campus course display method with intelligent encyclopedia according to claim 1, characterized in that, The host computer sends the response information to the slave computer, including: The host computer sends the response information to the slave computer, and simultaneously sends the response information to the student terminal associated with the request. The student terminal includes a mobile phone or a smartwatch.

5. The campus course display method with intelligent encyclopedia according to claim 1, characterized in that, The lower-level machine displays the response information on the display screen, including: The lower-level machine obtains the current working mode; If the current display mode is a weekday course, the response information will be displayed in a preset first area of ​​the display screen; If the current mode is a holiday with no or few classes, the response information will be displayed in a preset second area of ​​the display screen, and the area of ​​the preset second area is larger than that of the preset first area.

6. The campus course display method with intelligent encyclopedia according to claim 1, characterized in that, The method further includes: The host computer performs data preprocessing on the set of request texts and intent type tags received within a preset time period; Machine learning algorithms are used to perform cluster analysis and classification model training on the preprocessed data; Based on the model obtained from the training, the psychological and behavioral characteristics, abilities, qualities, and growth needs of the student group were analyzed, and the analysis results were obtained. A student growth pattern analysis report is generated based on the analysis results.

7. The method for displaying campus courses with a smart encyclopedia according to any one of claims 1-6, characterized in that, The method further includes a scheduling step, which includes: Receive input of teacher information, course information, class information, classroom information, and temporary changes; The system performs intelligent analysis on the teacher information, course information, class information, and classroom information to generate a preliminary course schedule. Identify teacher conflicts, classroom conflicts, and time conflicts in the preliminary course arrangement, fine-tune the preliminary course arrangement with conflicts, and generate an optimized final course arrangement.

8. The campus course display method with intelligent encyclopedia according to claim 7, characterized in that, The pre-built course and school-based information database in the host computer stores the final course schedule, classroom usage information, teacher allocation information, and school-based general knowledge information.

9. A computer device, characterized in that, The computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, can implement the method as described in any one of claims 1-8.

Images