CN-122022583-A - Method, system, electronic equipment and storage medium for generating associated knowledge point skill capability complex test questions

CN122022583ACN 122022583 ACN122022583 ACN 122022583ACN-122022583-A

Abstract

The invention discloses a method for generating a compound test question of related knowledge point skill capability, which comprises the following steps of determining initial grasping degree weights of all knowledge points according to basic examination scores and determining corresponding weak knowledge points, triggering a subsequent flow when a core knowledge point of an accepted order is the weak knowledge point or technical standard information of the weak knowledge point is updated, determining difficulty values of the compound test question according to the weak knowledge point and the initial grasping degree weights of the related knowledge points, generating the compound test question through a large language model, determining the review adaption degree according to the number of the knowledge points in knowledge review information, transmitting the knowledge review information meeting the conditions and the compound test question to a terminal of a resident person, and acquiring a review result of the compound test question and updating the weights. The invention can effectively improve the professional ability of the personnel in residence, and improve the fine management and continuous optimization of the whole service quality of the platform. The invention also discloses a system, electronic equipment and a storage medium for realizing the method.

Inventors

Cai Youtian

Assignees

北京山山互联未来科技有限公司

Dates

Publication Date: 20260512
Application Date: 20260201

Claims (10)

1. The method for generating the complex test questions of the associated knowledge point skill ability is characterized by comprising the following steps of: determining the initial grasping degree weight of each knowledge point according to the basic assessment score of each knowledge point of the corresponding service class of the resident person; Determining corresponding weak knowledge points according to each initial grasping degree weight and a preset weight threshold; When the core knowledge points of the acquired orders of the resident personnel are the weak knowledge points or the technical standard information of the weak knowledge points is updated, determining a preset number of knowledge points from a preset full-quantity knowledge point association strength matrix as association knowledge points; determining the difficulty value of the complex test question according to the initial grasping degree weights of the weak knowledge points and the initial grasping degree weights of the preset number of associated knowledge points; generating a complex test question through a large language model according to the content of a preset question library, the weak knowledge points, the associated knowledge points and test question attributes corresponding to the difficulty values of the complex test question; Determining the review adaptation degree according to the number result of adding the preset number to 1 and the number of knowledge points in each knowledge review message; the knowledge review information and the complex test questions corresponding to the review adaptability larger than the adaptability threshold are sent to a terminal of a resident person; And obtaining retest examination result information of the retest questions, and determining corresponding update weights according to the retest examination result information, the initial grasping degree weights of the weak knowledge points and the initial grasping degree weights of the associated knowledge points.
2. The method of claim 1, wherein the initial grasping degree weight is calculated by the formula: Wherein, the Representing knowledge points Is used to determine the initial grasping degree weight of the model, Representing knowledge points Is used for the basic assessment score of the model (a), Representing knowledge points Is a full score of the basic examination of (a), The attenuation factor is indicated as such, , Indicating the number of months from the time when the resident does not make the basic check to the current time.
3. The method of claim 1, wherein determining a preset number of knowledge points from a preset full-scale knowledge point correlation intensity matrix as the correlation knowledge points comprises: screening a preset number of knowledge points, of which the association strength with the weak knowledge points is greater than or equal to a preset association strength threshold value, from a preset full-quantity knowledge point association strength matrix to serve as association knowledge points.
4. The method of claim 1, wherein determining the difficulty value of the complex test question based on the initial mastery weights of the weak knowledge points and the initial mastery weights of the preset number of associated knowledge points comprises: And determining the difficulty value of the complex test question according to the difficulty coefficient, the initial grasping degree weight of the weak knowledge points and the average value of the initial grasping degree weights of the preset number of the related knowledge points, wherein the difficulty coefficient is determined according to the initial grasping degree weight of the weak knowledge points.
5. The method of claim 4, wherein the complex test question difficulty value is calculated by the formula: Wherein, the Represents the difficulty value of the complex test question, The coefficient of difficulty is represented by a coefficient of difficulty, An initial grasping weight representing the weak knowledge point, The number of the preset number is indicated, Represent the first Initial grasping degree weights of the associated knowledge points.
6. The method of claim 1, wherein the generating the complex test question by the large language model according to the content of the preset question bank, the weak knowledge points, the associated knowledge points, and the test question attribute corresponding to the difficulty value of the complex test question comprises: Generating core test question contents through a large language model according to the contents of a preset question library and the weak knowledge points; Generating associated embedded test question contents by taking the associated knowledge points as constraint conditions and extension conditions through a large language model; And generating a complex test question through a large language model according to the core test question content, the associated embedded test question content and the test question attribute corresponding to the difficulty value of the complex test question.
7. The method of claim 1, wherein the determining the corresponding update weight based on the retest assessment result information, the initial mastery weight of the weak knowledge point, and the initial mastery weight of the associated knowledge point comprises: Calculating the difference value of the initial grasping degree weight between 1 and the weak knowledge point and the difference value of the initial grasping degree weight between 1 and the associated knowledge point; Calculating the ratio of the retest examination result information to the retest examination full score; Calculating the product of the difference value, the ratio and the smoothing coefficient to obtain a corresponding weight increment; Calculating the sum value of the initial grasping degree weight of the weak knowledge point and the corresponding weight increment and the sum value of the initial grasping degree weight of the associated knowledge point and the corresponding weight increment; And taking the smallest value of the sum value and 1 as the corresponding updating weight.
8. A system for generating a complex test of skills associated with knowledge points, comprising: The first determining module is used for determining the initial grasping degree weight of each knowledge point according to the basic assessment score of each knowledge point of the corresponding service class of the resident person; the second determining module is used for determining a corresponding weak knowledge point according to each initial grasping degree weight and a preset weight threshold value; the third determining module is used for determining a preset number of knowledge points from a preset full-quantity knowledge point association strength matrix to serve as association knowledge points when the core knowledge points of the resident, which are subjected to order taking, are the weak knowledge points or the technical standard information of the weak knowledge points is updated; A fourth determining module, configured to determine a difficulty value of the complex test question according to the initial grasping degree weight of the weak knowledge points and the initial grasping degree weight of the associated knowledge points of the preset number; The generation module is used for generating a complex test question through a large language model according to the content of a preset question library, the weak knowledge points, the associated knowledge points and test question attributes corresponding to the difficulty values of the complex test question; a fifth determining module, configured to determine a review adaptation degree according to the number result obtained by adding the preset number to 1 and the number of knowledge points in each knowledge review message; The pushing module is used for sending knowledge review information corresponding to review adaptability larger than the adaptability threshold and the complex test questions to a terminal of a resident person; And a sixth determining module, configured to obtain retest examination result information of the retest examination question, and determine a corresponding update weight according to the retest examination result information, the initial grasping degree weight of the weak knowledge point, and the initial grasping degree weight of the associated knowledge point.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the associated knowledge point skill ability test question generation method of any one of claims 1 to 7 when the program is executed.
10. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the associated knowledge point skill ability compound test question generation method of any of claims 1 to 7.

Description

Method, system, electronic equipment and storage medium for generating associated knowledge point skill capability complex test questions Technical Field The invention relates to the technical field of computer data processing, in particular to a method, a system, electronic equipment and a storage medium for generating a compound test question of related knowledge point skill ability. Background Along with the deep integration of the mobile Internet and local life service, various life skill service platforms are developed, and an efficient and convenient docking channel is provided for the demand parties such as home maintenance, installation cleaning, home service and the like and the master with corresponding skills. In order to ensure the service quality and improve the user experience, the prior platform generally establishes a knowledge and skill assessment system for the resident master. The system generally performs standardized knowledge testing in a specific field on a master, performs overall capability assessment and classification on the master according to assessment scores or grades, and takes the master as an important basis for dispatch, pricing or display. However, current assessment systems focus mainly on the overall score of the master or whether it passes the assessment, the outcome of which is more a static, generalized response to the master's level of comprehensive competence. The platform screens and matches the master based on only one total score or rank, but fails to deeply analyze and utilize detailed data in the assessment process. Specifically, the system ignores the identification and recording of weak knowledge points of the specific knowledge structure for each resident master. The examination results only indicate whether the master is "qualified" or "approximately at what level", but cannot accurately reveal specific deficiencies in specific knowledge points, operating specifications, or safety issues. Therefore, when distributing orders, if a service order involving weak knowledge points of a master is distributed to the master, service efficiency, solution effect and professionality of the service order will be greatly reduced, user satisfaction is directly reduced, even service disputes or security risks may be caused, fine management and continuous optimality of the overall service quality of the platform are affected, and the master lacks targeted weak point feedback, so that the master is difficult to effectively self-promote and learn directionally. Disclosure of Invention In order to solve the problems in the prior art, the invention provides a method, a system, electronic equipment and a storage medium for generating a complex test question of the skill ability of a related knowledge point. The technical problems to be solved by the invention are realized by the following technical scheme: The first aspect of the embodiment of the invention provides a method for generating a complex test question of the skill ability of a related knowledge point, which comprises the following steps: determining the initial grasping degree weight of each knowledge point according to the basic assessment score of each knowledge point of the corresponding service class of the resident person; Determining corresponding weak knowledge points according to each initial grasping degree weight and a preset weight threshold; When the core knowledge points of the acquired orders of the resident personnel are the weak knowledge points or the technical standard information of the weak knowledge points is updated, determining a preset number of knowledge points from a preset full-quantity knowledge point association strength matrix as association knowledge points; determining the difficulty value of the complex test question according to the initial grasping degree weights of the weak knowledge points and the initial grasping degree weights of the preset number of associated knowledge points; generating a complex test question through a large language model according to the content of a preset question library, the weak knowledge points, the associated knowledge points and test question attributes corresponding to the difficulty values of the complex test question; Determining the review adaptation degree according to the number result of adding the preset number to 1 and the number of knowledge points in each knowledge review message; the knowledge review information and the complex test questions corresponding to the review adaptability larger than the adaptability threshold are sent to a terminal of a resident person; And obtaining retest examination result information of the retest questions, and determining corresponding update weights according to the retest examination result information, the initial grasping degree weights of the weak knowledge points and the initial grasping degree weights of the associated knowledge points. In one embodiment of the present invention, the calculatio