Credit early warning method and device, storage medium and equipment

Abstract

The application discloses a credit early warning method and device, a storage medium and equipment, relates to the technical field of computer and data processing, and mainly aims to solve the problems of poor accuracy and low system processing efficiency of the existing credit early warning. The method comprises the following steps: obtaining student attribute characteristic information, timetable data and completed credit data of a student to be warned; determining a target course entity based on the student attribute characteristic information and the timetable data, and calling corresponding early warning threshold information based on the training type of the student, wherein the early warning threshold information comprises early warning rules and threshold limit information corresponding to different training types; matching the completed credit data, the target course entity and double constraint conditions, and generating counting information of the target course entity based on the matching result, wherein the double constraint conditions are used to represent two counting conditions required to be met simultaneously by the target course entity; and generating an early warning result of the counting information according to the early warning threshold information.

Description

Technical Field

[0001] This application relates to the field of computer and data processing technology, and in particular to a method, apparatus, storage medium and device for early warning of academic credits. Background Technology

[0002] With the rapid development of educational informatization, universities have generally introduced academic affairs management systems to assist in student training and teaching management. Credit early warning, as a crucial link in ensuring the quality of postgraduate teaching and standardizing degree awarding criteria, plays a core role in promptly identifying abnormalities in student credit completion, urging students to complete their required credits, and ensuring that the quality of training meets relevant standards.

[0003] Currently, credit warnings generally use a static tag and single threshold method for credit statistics. This means that academic staff enter basic course information into the system and manually hard-code fixed attribute tags for each course. Then, a standardized curriculum plan is statically distributed to students via computer, specifying the total credits and the minimum credit requirements for each course module. The system then aggregates and queries the database to summarize the credits earned by students according to the static tags. Finally, the summarized credits are compared with a preset single threshold. If the credits are lower than the threshold, a credit shortage warning is issued.

[0004] However, as the complexity of interdisciplinary and categorized training gradually increases, the credit statistics method using static labels and single thresholds lacks the ability to dynamically analyze the deep disciplinary attributes of courses, cannot identify the underlying disciplinary affiliation of interdisciplinary courses, and is prone to errors in credit classification. Furthermore, it cannot adapt to the parallel management of multiple training types such as academic and professional programs, and requires the independent deployment of multiple sets of business code for different training types, resulting in code redundancy, high maintenance costs, and problems such as false alarms and missed alarms. It cannot meet the needs of refined academic affairs management. Therefore, a credit early warning method is urgently needed to solve the above problems. Summary of the Invention

[0005] In view of this, this application provides a credit early warning method, device, storage medium and equipment, the main purpose of which is to solve the problems of poor accuracy and low system processing efficiency of existing credit early warning systems.

[0006] According to one aspect of this application, a method for early warning of academic credits is provided, including: Obtain student attribute characteristics, class schedule data, and completed credit data of students to be warned; The target course entity is determined based on the student attribute feature information and the timetable data, and the corresponding early warning threshold information is retrieved based on the student's training type. The early warning threshold information includes early warning rules and threshold limit information corresponding to different training types. Based on the completed credit data and the target course entity, a matching is performed with the dual constraints, and the counting information of the target course entity is generated based on the matching results. The dual constraints are used to characterize the two counting conditions that the target course entity needs to satisfy simultaneously. The warning result of the counting information is generated according to the warning threshold information.

[0007] Furthermore, before determining the target course entity based on the student attribute feature information and the timetable data, the method further includes: Obtain basic course data and perform character cleaning processing on the basic course data based on preset regular expression rules to obtain course strings; The course string is truncated based on a preset extraction step size to obtain the source subject feature code. This source subject feature code is then compared with the professional science code of the timetable data to obtain the comparison result; or, The course codes for the timetable data are determined based on a preset mapping dictionary table; Based on the comparison results or the course codes, a course data buffer pool is generated, which includes a buffer pool of courses from the same major and a buffer pool of interdisciplinary elective courses.

[0008] Furthermore, determining the target course entity based on the student attribute feature information and the timetable data includes: Based on the student attribute features and the timetable data, string matching is performed on the course data cache pool, and the course entities in the timetable data are identified based on the matching results to obtain target course entities with same-origin or different-origin identifiers.

[0009] Furthermore, the step of matching the completed credit data and the target course entity with the dual constraints, and generating the count information of the target course entity based on the matching results, includes: If the target course entity has a common origin identifier and the target course entity matches a core professional course, then count the common origin professional courses and the common origin core professional courses to generate the first count information. If the target course entity does not have a same-origin identifier, or the target course entity does not match a core professional course, then credit counting is performed based on the completed credit data to generate second counting information.

[0010] Furthermore, retrieving the corresponding early warning threshold information based on the student's training type includes: Read the student's file information and determine the training type based on the file information. The training type includes academic and engineering professional training. The system retrieves early warning threshold information matching the culture type from a preset threshold matrix library. The preset threshold matrix library stores early warning rules and threshold limit information corresponding to different culture types. The early warning rules are used to characterize the rule content for judging credit warnings, and the threshold limit information is used to define the limit range of the threshold size set in the early warning rules.

[0011] Furthermore, the early warning rules include course early warning rules and credit early warning rules set based on different threshold limit information, and the early warning result of generating the counting information according to the early warning threshold information includes: If the first counting information matches the course warning rule, a course warning count value is generated; If the second counting information matches the credit warning rule, a credit warning count value is generated; The difference between the course warning count and the credit warning count is calculated to generate a warning result.

[0012] Furthermore, the method also includes: The warning event is initiated according to the warning result, and the warning information corresponding to the warning event is output.

[0013] According to another aspect of this application, a credit early warning device is provided, comprising: The acquisition module is used to acquire student attribute characteristics, class schedule data, and completed credit data of students to be warned. The determination module is used to determine the target course entity based on the student attribute feature information and the timetable data, and to retrieve the corresponding early warning threshold information based on the student's training type. The early warning threshold information includes early warning rules and threshold limit information corresponding to different training types. The matching module is used to match the completed credit data and the target course entity with the dual constraints, and generate the count information of the target course entity based on the matching results. The dual constraints are used to characterize the two count conditions that the target course entity needs to satisfy simultaneously. The generation module is used to generate a warning result for the counting information according to the warning threshold information.

[0014] Furthermore, the device also includes: a processing module and a comparison module. The processing module is used to acquire basic course data and perform character cleaning processing on the basic course data based on preset regular expression rules to obtain course strings; The comparison module is used to truncate the course string based on a preset extraction step size to obtain the source subject feature code, and compare the source subject feature code with the professional science code of the timetable data to obtain a comparison result; or, determine the course code of the timetable data based on a preset mapping dictionary table. The generation module is used to generate a course data buffer pool based on the comparison results or the course code. The course data buffer pool includes a buffer pool of courses from the same major and a buffer pool of interdisciplinary elective courses.

[0015] Furthermore, the determining module is specifically used to perform string matching on the course data cache pool based on the student attribute feature information and the timetable data, and to identify the course entities in the timetable data based on the matching results, so as to obtain target course entities with same-origin identifiers or different-origin identifiers.

[0016] Furthermore, the matching module is specifically used to count the number of source courses and the number of source core courses if the target course entity has a source identifier and the target course entity matches a core professional course, thereby generating first counting information; if the target course entity does not have a source identifier or the target course entity does not match a core professional course, it counts credits based on the completed credit data, thereby generating second counting information.

[0017] Furthermore, the generation module is specifically used to read the student's file information and determine the training type based on the file information, the training type including academic and engineering professional; retrieve early warning threshold information matching the training type from a preset threshold matrix library, the preset threshold matrix library storing early warning rules and threshold limit information corresponding to different training types, the early warning rules being used to characterize the rule content of credit early warning judgment, and the threshold limit information being used to standardize the limit range of the threshold size set in the early warning rules.

[0018] Furthermore, the early warning rules include course early warning rules and credit early warning rules set based on different threshold limit information. The generation module is specifically used to generate a course early warning count value if the first counting information matches the course early warning rule; generate a credit early warning count value if the second counting information matches the credit early warning rule; and calculate the difference between the course early warning count value and the credit early warning count value to generate an early warning result.

[0019] Furthermore, the device also includes: The output module is used to initiate an early warning event according to the early warning result and output the early warning information corresponding to the early warning event.

[0020] According to another aspect of this application, a storage medium is provided, wherein at least one executable instruction is stored therein, the executable instruction causing a processor to perform an operation corresponding to the above-described credit warning method.

[0021] According to another aspect of this application, a terminal is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus; The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the above-mentioned credit warning method.

[0022] By employing the above technical solutions, the technical solutions provided in the embodiments of this application have at least the following advantages: This application provides a credit early warning method, apparatus, storage medium, and device. Compared with the prior art, the embodiments of this application obtain student attribute feature information, timetable data, and completed credit data of the student to be warned; determine the target course entity based on the student attribute feature information and timetable data, and retrieve the corresponding early warning threshold information based on the student's training type. The early warning threshold information includes early warning rules and threshold limit information corresponding to different training types; match the completed credit data and the target course entity with dual constraint conditions, and generate count information of the target course entity based on the matching result. The dual constraint conditions are used to characterize the two counting conditions that the target course entity needs to satisfy simultaneously; generate the early warning result of the count information according to the early warning threshold information, thereby achieving the purpose of credit early warning to meet different management needs, avoiding erroneous judgments caused by manual marking, and greatly reducing the cumbersomeness of code configuration, reducing system maintenance costs, and improving the accuracy of early warning through the configuration of dual constraint conditions and early warning threshold information, thus meeting the needs of refined academic affairs management.

[0023] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0024] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A flowchart of a credit early warning method provided in an embodiment of this application is shown; Figure 2 This illustration shows a flowchart of a course coding feature extraction and subject homology determination method provided in an embodiment of this application. Figure 3 This paper illustrates a flowchart of a polymorphic rule distribution and composite constraint matrix early warning calculation method provided in an embodiment of this application. Figure 4 This paper illustrates an architecture diagram of a multi-training type postgraduate credit early warning system provided in an embodiment of this application. Figure 5 This illustration shows a block diagram of a credit early warning device provided in an embodiment of this application; Figure 6 A schematic diagram of the structure of a terminal provided in an embodiment of this application is shown. Detailed Implementation

[0025] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] This application provides a method for early warning of academic credits, such as... Figure 1 As shown, the method includes: Step 101: Obtain the student attribute characteristics, class schedule data, and completed credit data of the students to be warned.

[0028] In this embodiment, the executing entity for credit warning can be a smart campus platform, providing campus data processing functions to students and teachers through multiple clients. Students can log in to the smart campus platform via a client to maintain relevant information, and teachers can log in via a client to enter credit and other information. This embodiment does not impose specific limitations. Student attribute information includes, but is not limited to, inherent entity attribute data such as student ID, training type, and subject code. Timetable data includes all courses for this student matched from the timetable database, represented as dictionary information. The timetable database stores course data for the entire school. Completed credit data refers to the grades of completed selected or required courses. This embodiment does not impose specific limitations.

[0029] It should be noted that the student attribute feature information, timetable data and completed credit data in the embodiments of this application can be stored in the memory of the smart campus platform so as to be retrieved after the credit warning judgment is triggered. The triggering of the credit warning method can be based on human command or based on the time node or scene node set by the system. This embodiment of the application does not make specific limitations.

[0030] Step 102: Determine the target course entity based on the student attribute feature information and the timetable data, and retrieve the corresponding early warning threshold information based on the student's training type.

[0031] In this embodiment, to identify courses requiring credit warnings, target course entities can be determined based on student attribute characteristics and timetable data. These target course entities are the objects requiring credit warnings, including but not limited to courses at different educational stages, such as required academic courses for graduate students and elective professional courses for undergraduate students. This embodiment does not impose specific limitations. Simultaneously, warning threshold information is retrieved based on the student's training type. This threshold information includes warning rules and threshold limit information corresponding to different training types. The warning rules characterize the content of the credit warning judgment, and the threshold limit information defines the limit range of the threshold size set in the warning rules. This limit can be set based on the specific needs of credit warnings, and this embodiment does not impose specific limitations.

[0032] In a specific implementation scenario, the smart campus platform at the current execution end can embed a polymorphic rule engine of a polymorphic rule router. This engine is responsible for distributing computing tasks, and its subordinates are equipped with pre-configured academic constraint matrices (threshold libraries) and engineering or professional constraint matrices (threshold libraries) as threshold limit information.

[0033] In another embodiment of this application, to further define and illustrate, before determining the target course entity based on the student attribute feature information and the timetable data, the method further includes: Obtain basic course data and perform character cleaning processing on the basic course data based on preset regular expression rules to obtain course strings; The course string is truncated based on a preset extraction step size to obtain the source subject feature code. This source subject feature code is then compared with the professional science code of the timetable data to obtain the comparison result; or, The course codes for the timetable data are determined based on a preset mapping dictionary table; A course data buffer pool is generated based on the comparison results or the course code.

[0034] To automatically match courses requiring early warning credits and thus improve the effectiveness of credit warnings, the current execution terminal pre-acquires all basic course data, which can be retrieved from the timetable database; this embodiment does not impose specific limitations. To ensure data validity, the basic course data is cleaned based on preset regular expression rules to obtain course strings. This character cleansing process includes, but is not limited to, removing suffix identifiers, special placeholders, and other interfering noise characters to obtain clean course strings.

[0035] In one example, the data cleaning and noise reduction module in the smart campus platform obtains the original unstructured course codes from the basic course data, such as the string "280216086001M2001". Then, the regular expression cleaning processor subroutine is activated. Based on preset regular expression rules, it actively scans and removes interfering noise characters such as combined class suffixes, special placeholders, and illegal spaces caused by scheduling, obtaining the clean version of the course code, i.e., the course string.

[0036] To ensure the effectiveness of course classification and the stability of system operation, the current execution end pre-builds a course data cache pool. At this time, the course data cache pool includes a cache pool of courses from the same major and a cache pool of interdisciplinary elective courses, so as to store the corresponding courses respectively.

[0037] In this embodiment, when reading basic course data, a cleaning function is automatically initiated to remove invalid characters, such as removing noise like class suffixes and illegal spaces. Then, string slicing with a specific extraction step size is performed to accurately extract feature intervals, generating a "source subject feature code" representing the underlying structure of the course. This feature code is then compared with the student's inherent corresponding major subject code using a high-priority string collision comparison. Based on the comparison Boolean value, the course is automatically mapped to either a same-source major course buffer pool or a cross-disciplinary elective course buffer pool. This approach replaces manual labeling with underlying string parsing, fundamentally solving the technical problems of inconsistent credit classification and high manual identification costs in cross-disciplinary elective courses.

[0038] In a specific embodiment of this application, the course string can be truncated based on a preset extraction step size to obtain the source subject feature code. The source subject feature code is then compared with the professional science code of the timetable data to obtain a comparison result, which is used to generate a course data buffer pool. In one example, the feature slicing module of the smart campus platform can truncate a specific interval of the cleaned pure code according to the positional distribution pattern of the Chinese legal subject code, at a fixed step size. For example, the 7th to 10th character sequence can be specified for extraction. This extracted short string is then encapsulated to generate a source subject feature code variable unique to the course entity. If the length of the cleaned pure code is abnormal, causing the truncation to exceed the limit or fail to match the preset regular expression, the system triggers an abnormal retry mechanism, or assigns a special unknown identifier, such as "Unknown," to the course and pushes it into a manual verification queue to ensure the robustness of the extraction process and the overall stability of the system operation.

[0039] In a specific embodiment of this application, the course codes of the timetable data are determined based on a preset mapping dictionary table, and a course data buffer pool is generated according to the course codes. In one example, all the complete original course codes that have appeared and their respective subjects can be pre-stored persistently in a relational database using hash mapping. When the smart campus platform performs source identification, it directly uses the full set of original course codes as the index (key) to query the dictionary table to obtain and compare subject classification information, thus ensuring high mapping stability when encountering irregular garbled course numbers.

[0040] In an example of generating a course data buffer pool based on comparison results, the specific subject code in the comparison results or course code is parsed to determine if they belong to the same category, so that they can be stored in the corresponding course data buffer pool. In a specific example, the attribute feature library is first read to accurately extract the pre-registered professional subject code of the currently warned target student. Then, the subject homology mapping collision detector is triggered, and the string comparison logic is executed in the arithmetic unit to determine whether the text values ​​of the source subject feature code in the course string and the extracted corresponding professional subject code are completely equal. If the comparison result is that they are consistent, the rule engine system assigns a boolean flag of type True to the course data object and points the course entity to the subject homology professional course buffer pool in the memory mapping pointer; if the comparison result is No, representing cross-disciplinary examination or selection from another college, the rule engine system assigns a false flag and downgrades the memory mapping of the course entity to a non-original or cross-disciplinary elective course buffer pool, such as Figure 2 As shown.

[0041] In another embodiment of this application, for further definition and explanation, the step of determining the target course entity based on the student attribute feature information and the timetable data includes: Based on the student attribute features and the timetable data, string matching is performed on the course data cache pool, and the course entities in the timetable data are identified based on the matching results to obtain target course entities with same-origin or different-origin identifiers.

[0042] To accurately match the course entities of students requiring early warning and achieve precise credit matching to meet the credit warning objectives for different course subjects, the current execution end performs string matching on the course data cache pool based on student attribute feature information and the timetable data. This involves matching each string in the course data against the course strings in the cache pool, based on the student's student ID, training type, and subject code from the student attribute feature information. Then, based on the matching results, the course entities in the timetable data are identified by marking whether they are from the same source, resulting in target course entities with either same-source or different-source identifiers.

[0043] In another embodiment of this application, for further definition and explanation, the step of retrieving the corresponding early warning threshold information based on the student's training type includes: Read the student's file information and determine the training type based on the file information; Retrieve early warning threshold information that matches the culture type from the preset threshold matrix library.

[0044] The training types in this embodiment include academic and engineering majors to adapt to the teaching scenarios of higher education institutions, thereby meeting the needs of credit warning scenarios. When the smart campus platform pre-configures warning threshold information, it first reads the student's file information and determines the training type based on the file information. At this time, the file information can be entered by the teacher and marked with the student's engineering major type or academic major type; this embodiment does not make specific limitations. In addition, the preset threshold matrix library stores warning rules and threshold limit information corresponding to different training types. The warning rules are used to characterize the rule content of credit warning judgment, and the threshold limit information is used to set the limit range of the threshold size in the standard warning rules. For example, the target total credit threshold must be greater than or equal to 30 points, and the individual threshold of public elective modules must be greater than or equal to 2 points, etc. This embodiment does not make specific limitations.

[0045] In another specific embodiment, for different training types, the smart campus platform obtains the polymorphic training type identifier of the current student entity by reading the header information of the personal file, such as defining the parameter: Type_Tag. The polymorphic rule router performs traffic routing and scheduling based on the characteristics of this parameter. This embodiment does not make specific limitations.

[0046] In one example, if the identifier is determined to be academic, the router executes branch A logic: actively schedules and mounts the academic constraint matrix library. This matrix sends a set of warning thresholds for academic standards to the system. For example, it forcibly sets the target total credit threshold to be greater than or equal to 30 credits, and the individual threshold for public elective modules to be greater than or equal to 2 credits. If the identifier is determined to be engineering or professional, the router executes branch B logic: schedules and mounts the engineering / professional constraint matrix library. The threshold sets sent to the system by this matrix not only include numerical differences, such as a total credit threshold requirement of greater than or equal to 25 credits, but also send additional module mandatory verification locks to the computing engine. For example, it forcibly verifies that the "Engineering Ethics" literacy course module under a specific tag must meet the standard; otherwise, it directly blocks the process.

[0047] This embodiment employs an independent polymorphic rule router in the core flow. By capturing the training type identifier (Type_Tag) embedded in the input data, different constraint matrices are dynamically attached using routing scheduling instructions. For example, academic constraint matrices or engineering constraint matrices with specific mandatory locks such as engineering ethics, data diversion and verification are achieved. This deeply decouples the early warning rule engine from the business control plane, solving the technical challenge of flexibly scaling the system when performing parallel accounting for multi-track postgraduate training. Moreover, this polymorphic routing architecture follows the Open / Closed Principle (OCP). When adding other training types in the future, such as Sino-foreign cooperative programs, only the corresponding constraint matrix configuration needs to be dynamically added and attached, without any modification to the underlying traversal and calculation engine source code, greatly reducing the system's iterative maintenance costs.

[0048] Step 103: Match the completed credit data and the target course entity with the dual constraints, and generate the count information of the target course entity based on the matching results.

[0049] In this embodiment of the application, the dual constraint condition is used to characterize the two counting conditions that the target course entity needs to satisfy simultaneously. That is, the two counting conditions are judged for the target course entity according to the completed credit data to obtain the result of whether they match. Then, the targeted counting information of the target course entity is generated based on the matching result.

[0050] In a specific implementation scenario, the smart campus platform at the current execution end serves as the core processing hub of the system. It includes a composite constraint operation matrix module, which has a two-dimensional accumulator dedicated to multi-dimensional conditional parallel processing of credits or course counts, as well as a subject homology mapping collision detector for processing mapping logic, so as to count the target course entities when matching double constraint conditions.

[0051] In another embodiment of this application, for further definition and explanation, the step of matching the completed credit data and the target course entity with the dual constraints, and generating the count information of the target course entity based on the matching result, includes: If the target course entity has a common origin identifier and the target course entity matches a core professional course, then count the common origin professional courses and the common origin core professional courses to generate the first count information. If the target course entity does not have a same-origin identifier, or the target course entity does not match a core professional course, then credit counting is performed based on the completed credit data to generate second counting information.

[0052] To improve the targeted credit prediction of course entities and meet the early warning requirements for different course credit constraints, the current execution end first determines the identifier carried by the target course entity. If the target course entity has a source identifier and matches a core professional course, then it counts both source professional courses and source core professional courses, generating the first count information. Conversely, if the target course entity does not have a source identifier or does not match a core professional course, then it counts credits based on completed credit data, generating the second count information.

[0053] In a specific example, the smart campus platform loads the completed course pool data with verified identities and initiates a two-dimensional traversal and accumulation engine for credits or course counts in the calculation engine layer. This engine does not perform a simple one-dimensional numerical addition but performs two-dimensional verification simultaneously in a single traversal. Specifically, the execution of the composite course count constraint logic includes: checking whether the currently extracted course entity simultaneously satisfies the following conditions: its course attribute belongs to the professional core course type and has a "same source" identifier of True. If both constraints are met, the system triggers a 2+2 parallel calculation mode with specific warning requirements, sending a control command to the concurrency counter. That is, within the same clock cycle, it drives the same-source professional course cumulative course count register to increment by 1, and simultaneously drives the same-source core course cumulative course count register to increment by 1. If the above two constraints are not met simultaneously, the concurrency counting module flow is bypassed, and the course data only performs the basic total credits or corresponding category credit value base accumulation operation.

[0054] When faced with high-priority dual constraints, such as the requirement for a specific number of professional and core courses to be completed simultaneously, the computational engine implemented in this application employs a 2+2 concurrent counting mechanism. It constructs a multi-dimensional synchronous statistical register, from total credits (Credit) to the number of courses (Count), simultaneously completing multi-channel logic and AND calculations through a single pass. Finally, the difference solver outputs the absolute value of the multi-dimensional operational difference (Gap) and the Boolean compliance parameter (is_pass). This breaks through the bottleneck of traditional single-summation comparison and successfully solves the technical problem that complex high-order cross-training constraints cannot be quickly and automatically verified using conventional SQL aggregation. Furthermore, from the perspective of low-level computer data processing, a single-pass two-dimensional traversal model can be used, effectively replacing the multiple cumbersome aggregation queries based on traditional relational databases. This reduces the time complexity of multi-constraint verification to linear time. This mechanism significantly reduces database I / O overhead and CPU and memory resource consumption during computation, significantly improving the execution efficiency of large-scale concurrent credit warning tasks across the entire university.

[0055] Step 104: Generate the warning result of the counting information according to the warning threshold information.

[0056] In this embodiment, after updating the counting information, it can be compared with the warning threshold information. When the counting information matches the warning rule and is greater than the threshold limit information, it indicates that a warning needs to be triggered. Therefore, a warning result can be generated. At this time, the smart campus platform at the current execution end is equipped with a warning system responsible for data visualization transformation and alarm issuance, such as a structured warning output module, which is used to encapsulate and output a panoramic warning panel, a gap analysis message, and a pass / fail (is_pass) Boolean value matrix. This embodiment does not impose specific limitations. In addition, the warning result in this embodiment includes warning or no warning. When issuing a warning, it can be done through SMS warning, email warning, etc. This embodiment does not impose specific limitations.

[0057] In another embodiment of this application, for further definition and explanation, the step of generating the warning result of the counting information according to the warning threshold information includes: If the first counting information matches the course warning rule, a course warning count value is generated; If the second counting information matches the credit warning rule, a credit warning count value is generated; The difference between the course warning count and the credit warning count is calculated to generate a warning result.

[0058] To achieve accurate credit warnings and meet multi-dimensional warning needs, rule-based judgments are performed on the first and second count information respectively. The warning rules include course warning rules and credit warning rules set based on different threshold limits. The course warning rule represents the rule for issuing a warning when the corresponding count of a course exceeds a preset threshold within a specific time period. The credit warning rule represents the rule for issuing a warning when the corresponding count of credits exceeds a preset threshold. The corresponding preset thresholds can be set based on warning needs, and this embodiment does not impose specific limitations. When the first count information matches a course warning rule once, a course warning count is performed, obtaining the corresponding count value. Similarly, when the second count information matches a credit warning rule once, a credit warning count is performed, obtaining the corresponding count value. Finally, the difference between the course warning count value and the credit warning count value is calculated to generate a warning result.

[0059] In a specific example, such as Figure 3As shown, after completing the matrix traversal of all timetable data under the student's file, the differential accounting and settlement and anomaly sorting stage begins. The engine performs difference value calculation on each sub-warning module, with the underlying formula set as follows: the target difference Gap equals the actual current completed value accumulated by the system (including credit warning count and course warning count) minus the threshold limit constrained by the rule. Then, the processor determines whether any warning sub-module's calculated difference Gap is less than 0, or whether a specific professional-specific mandatory lock verification bit has failed. If any of these abnormal states are detected, the final alarm event is triggered, writing the negative missing difference portion into the log memory area and forcibly assigning the warning module's status bit (i.e., the Boolean parameter: is_pass) to False, thus initiating the warning. If none of the above negative situations exist after traversing all modules, compliance is confirmed, and the system assigns the warning module's status bit to True.

[0060] In another embodiment of this application, for further definition and explanation, the steps also include: The warning event is initiated according to the warning result, and the warning information corresponding to the warning event is output.

[0061] In one specific embodiment, when the alert result is an alert, an alert event is initiated, such as an SMS alert or an email alert. Simultaneously, the alert information corresponding to the alert event is output; that is, the alert information may include, but is not limited to, alert count values, target course entities, etc., for students or teachers to view.

[0062] It should be noted that in the underlying module executing the above-mentioned credit warning program in this embodiment, all the processed and generated module-specific difference gap parameters and is_pass status bit attributes are combined into a panoramic object, and then packaged by the structured warning output module to generate a composite warning matrix with identification codes. Finally, it is output to the UI level to drive the front-end dynamic warning, at which point all accounting warning tasks end and exit. Furthermore, as the underlying physical support of the system architecture of this invention, the functional modules of the above-mentioned input layer, data preprocessing layer, core routing layer, computing engine layer, and output layer can be actually deployed in at least one computer device containing a processor and memory, such as... Figure 4 As shown. The memory is used to store computer program instructions. When the processor executes the instructions, it physically implements the aforementioned automated data processing processes, such as dynamic regularization cleaning, routing scheduling, concurrent accumulation counting, and multidimensional difference calculation.

[0063] This application provides a credit early warning method. Compared with the prior art, the embodiments of this application obtain student attribute feature information, timetable data, and completed credit data of the student to be warned; determine the target course entity based on the student attribute feature information and the timetable data, and retrieve the corresponding early warning threshold information based on the student's training type. The early warning threshold information includes early warning rules and threshold limit information corresponding to different training types; match the completed credit data and the target course entity with dual constraints, and generate count information of the target course entity based on the matching result. The dual constraints are used to characterize the two counting conditions that the target course entity needs to satisfy simultaneously; generate the early warning result of the count information according to the early warning threshold information, thereby achieving the purpose of credit early warning to meet different management needs, avoiding erroneous judgments caused by manual marking, and greatly reducing the cumbersomeness of code configuration, reducing system maintenance costs, and improving the accuracy of early warning through the configuration of dual constraints and early warning threshold information, thus meeting the needs of refined academic affairs management.

[0064] Furthermore, as a response to the above Figure 1 The implementation of the method shown in this application provides a credit early warning device, such as... Figure 5 As shown, the device includes: Module 21 is used to acquire student attribute characteristics, timetable data, and completed credit data of students to be warned. The determination module 22 is used to determine the target course entity based on the student attribute feature information and the timetable data, and to retrieve the corresponding early warning threshold information based on the student's training type. The early warning threshold information includes early warning rules and threshold limit information corresponding to different training types. The matching module 23 is used to match the completed credit data and the target course entity with the double constraint conditions, and generate the counting information of the target course entity based on the matching result. The double constraint conditions are used to characterize the two counting conditions that the target course entity needs to satisfy at the same time. The generation module is used to generate a warning result for the counting information according to the warning threshold information.

[0065] Furthermore, the device also includes: a processing module and a comparison module. The processing module is used to acquire basic course data and perform character cleaning processing on the basic course data based on preset regular expression rules to obtain course strings; The comparison module is used to truncate the course string based on a preset extraction step size to obtain the source subject feature code, and compare the source subject feature code with the professional science code of the timetable data to obtain a comparison result; or, determine the course code of the timetable data based on a preset mapping dictionary table. The generation module is used to generate a course data buffer pool based on the comparison results or the course code. The course data buffer pool includes a buffer pool of courses from the same major and a buffer pool of interdisciplinary elective courses.

[0066] Furthermore, the determining module is specifically used to perform string matching on the course data cache pool based on the student attribute feature information and the timetable data, and to identify the course entities in the timetable data based on the matching results, so as to obtain target course entities with same-origin identifiers or different-origin identifiers.

[0067] Furthermore, the matching module is specifically used to count the number of source courses and the number of source core courses if the target course entity has a source identifier and the target course entity matches a core professional course, thereby generating first counting information; if the target course entity does not have a source identifier or the target course entity does not match a core professional course, it counts credits based on the completed credit data, thereby generating second counting information.

[0068] Furthermore, the generation module is specifically used to read the student's file information and determine the training type based on the file information, the training type including academic and engineering professional; retrieve early warning threshold information matching the training type from a preset threshold matrix library, the preset threshold matrix library storing early warning rules and threshold limit information corresponding to different training types, the early warning rules being used to characterize the rule content of credit early warning judgment, and the threshold limit information being used to standardize the limit range of the threshold size set in the early warning rules.

[0069] Furthermore, the early warning rules include course early warning rules and credit early warning rules set based on different threshold limit information. The generation module is specifically used to generate a course early warning count value if the first counting information matches the course early warning rule; generate a credit early warning count value if the second counting information matches the credit early warning rule; and calculate the difference between the course early warning count value and the credit early warning count value to generate an early warning result.

[0070] Furthermore, the device also includes: The output module is used to initiate an early warning event according to the early warning result and output the early warning information corresponding to the early warning event.

[0071] This application provides a credit early warning device. Compared with the prior art, this application obtains student attribute feature information, timetable data, and completed credit data of the student to be warned; determines the target course entity based on the student attribute feature information and timetable data, and retrieves the corresponding early warning threshold information based on the student's training type. The early warning threshold information includes early warning rules and threshold limit information corresponding to different training types; matches the completed credit data and the target course entity with dual constraints, and generates count information of the target course entity based on the matching result. The dual constraints are used to characterize the two counting conditions that the target course entity needs to satisfy simultaneously; and generates an early warning result of the count information according to the early warning threshold information. This achieves the purpose of credit early warning to meet different management needs, avoids erroneous judgments caused by manual marking, and greatly reduces the cumbersomeness of code configuration, reduces system maintenance costs, and improves the accuracy of early warning through the configuration of dual constraints and early warning threshold information, thereby meeting the needs of refined academic affairs management.

[0072] According to one embodiment of this application, a storage medium is provided, the storage medium storing at least one executable instruction, which can execute the credit warning method in any of the above method embodiments.

[0073] Figure 6 The diagram shows a structural schematic of a terminal according to one embodiment of the present application. The specific embodiments of the present application do not limit the specific implementation of the terminal.

[0074] like Figure 6 As shown, the terminal may include: a processor 302, a communications interface 304, a memory 306, and a communications bus 308.

[0075] The processor 302, communication interface 304, and memory 306 communicate with each other via communication bus 308.

[0076] Communication interface 304 is used to communicate with other network elements such as clients or other servers.

[0077] The processor 302 is used to execute program 310, specifically to perform the relevant steps in the above-described embodiment of the credit warning method.

[0078] Specifically, program 310 may include program code that includes computer operation instructions.

[0079] Processor 302 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. The terminal includes one or more processors, which may be processors of the same type, such as one or more CPUs; or they may be processors of different types, such as one or more CPUs and one or more ASICs.

[0080] Memory 306 is used to store program 310. Memory 306 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0081] Specifically, program 310 can be used to cause processor 302 to perform the following operations: Obtain student attribute characteristics, class schedule data, and completed credit data of students to be warned; The target course entity is determined based on the student attribute feature information and the timetable data, and the corresponding early warning threshold information is retrieved based on the student's training type. The early warning threshold information includes early warning rules and threshold limit information corresponding to different training types. Based on the completed credit data and the target course entity, a matching is performed with the dual constraints, and the counting information of the target course entity is generated based on the matching results. The dual constraints are used to characterize the two counting conditions that the target course entity needs to satisfy simultaneously. The warning result of the counting information is generated according to the warning threshold information.

[0082] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0083] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for early warning of academic credits, characterized in that, include: Obtain student attribute characteristics, class schedule data, and completed credit data of students to be warned; The target course entity is determined based on the student attribute feature information and the timetable data, and the corresponding early warning threshold information is retrieved based on the student's training type. The early warning threshold information includes early warning rules and threshold limit information corresponding to different training types. Based on the completed credit data and the target course entity, a matching is performed with the dual constraints, and the counting information of the target course entity is generated based on the matching results. The dual constraints are used to characterize the two counting conditions that the target course entity needs to satisfy simultaneously. The warning result of the counting information is generated according to the warning threshold information.

2. The method according to claim 1, characterized in that, Before determining the target course entity based on the student attribute feature information and the timetable data, the method further includes: Obtain basic course data and perform character cleaning processing on the basic course data based on preset regular expression rules to obtain course strings; The course string is truncated based on a preset extraction step size to obtain the source subject feature code. This source subject feature code is then compared with the professional science code of the timetable data to obtain the comparison result; or, The course codes for the timetable data are determined based on a preset mapping dictionary table; Based on the comparison results or the course codes, a course data buffer pool is generated, which includes a buffer pool of courses from the same major and a buffer pool of interdisciplinary elective courses.

3. The method according to claim 2, characterized in that, The process of determining the target course entity based on the student attribute feature information and the timetable data includes: Based on the student attribute features and the timetable data, string matching is performed on the course data cache pool, and the course entities in the timetable data are identified based on the matching results to obtain target course entities with same-origin or different-origin identifiers.

4. The method according to claim 3, characterized in that, The process of matching the completed credit data and the target course entity with the dual constraints, and generating the count information of the target course entity based on the matching results, includes: If the target course entity has a common origin identifier and the target course entity matches a core professional course, then count the common origin professional courses and the common origin core professional courses to generate the first count information. If the target course entity does not have a same-origin identifier, or the target course entity does not match a core professional course, then credit counting is performed based on the completed credit data to generate second counting information.

5. The method according to claim 1, characterized in that, The step of retrieving the corresponding early warning threshold information based on the student's training type includes: Read the student's file information and determine the training type based on the file information. The training type includes academic and engineering professional training. The system retrieves early warning threshold information matching the culture type from a preset threshold matrix library. The preset threshold matrix library stores early warning rules and threshold limit information corresponding to different culture types. The early warning rules are used to characterize the rule content for judging credit warnings, and the threshold limit information is used to define the limit range of the threshold size set in the early warning rules.

6. The method according to claim 5, characterized in that, The early warning rules include course early warning rules and credit early warning rules set based on different threshold limit information. The early warning result of generating the counting information according to the early warning threshold information includes: If the first counting information matches the course warning rule, a course warning count value is generated; If the second counting information matches the credit warning rule, a credit warning count value is generated; The difference between the course warning count and the credit warning count is calculated to generate a warning result.

7. The method according to any one of claims 1-6, characterized in that, The method further includes: The warning event is initiated according to the warning result, and the warning information corresponding to the warning event is output.

8. A credit early warning device, characterized in that, include: The acquisition module is used to acquire student attribute characteristics, class schedule data, and completed credit data of students to be warned. The determination module is used to determine the target course entity based on the student attribute feature information and the timetable data, and to retrieve the corresponding early warning threshold information based on the student's training type. The early warning threshold information includes early warning rules and threshold limit information corresponding to different training types. The matching module is used to match the completed credit data and the target course entity with the dual constraints, and generate the count information of the target course entity based on the matching results. The dual constraints are used to characterize the two count conditions that the target course entity needs to satisfy simultaneously. The generation module is used to generate a warning result for the counting information according to the warning threshold information.

9. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method of claim 1.

10. A computer device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method of claim 1.

Images