Method and device for generating behavior training schedule and computer equipment

Abstract

The application relates to a behavior training course table generation method and device and computer equipment. The method comprises the following steps: obtaining an evaluation scale, a behavior training course database and an abnormal answering result of a user for the evaluation scale, wherein the training course database comprises a course number; determining a mapping relationship between the evaluation scale and the behavior training course database according to the course number, obtaining an initial behavior training course from the behavior training course database according to the abnormal answering result and the mapping relationship; generating an initial behavior training course table according to the initial behavior training course, and sending the initial behavior training course table to a display terminal for display. The method can flexibly generate a customized behavior training course table.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence, and in particular to a method, apparatus and computer device for generating behavior training schedules. Background Technology

[0002] Traditional behavioral training methods are often unattractive to children, especially young children, who generally have poor concentration and compliance, leading to unsatisfactory training results.

[0003] With the advancement of the internet and the development of technology, children's behavioral training has begun to incorporate tablets, video games, and other methods to promote interaction between children and screen content and stimulate children's initiative. However, current training systems using these traditional methods only cover the training aspect, and the generated questions are relatively rigid, unable to address the issue of children memorizing questions in groups, lacking digital statistics, and customized, phased curriculum arrangements.

[0004] Currently, no effective solution has been proposed to address the lack of customized, phased, and flexible course arrangements in related technologies. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, and computer equipment for generating behavioral training schedules to address the aforementioned technical problems.

[0006] Firstly, this application provides a method for generating a behavioral training schedule. The method includes:

[0007] Obtain rating scales, a database of behavioral training courses, and abnormal responses from users to the rating scales. The training course database includes course numbers.

[0008] The mapping relationship between the rating scale and the behavior training course database is determined based on the course number. The initial behavior training course is obtained from the behavior training course database based on the abnormal answer results and the mapping relationship.

[0009] Generate an initial behavior training schedule based on the initial behavior training course, and send the initial behavior training schedule to the display terminal for display.

[0010] In one embodiment, the method for generating the behavior training schedule further includes:

[0011] Obtain the preset basic classification criteria, classify the behavior training course database according to the basic classification criteria, and obtain the basic classification results, which include at least one basic course category.

[0012] Obtain a preset extended classification standard, classify the basic course categories according to the extended classification standard, and obtain extended classification results, which include at least one extended course category;

[0013] The basic course categories are coded to obtain the basic coding results. The basic coding results are then segmented according to the extended course categories to obtain the extended coding results.

[0014] Obtain the preset genetic probability, and generate the next stage of behavioral training schedule based on the genetic probability, extended coding results, and initial behavioral training course.

[0015] In one embodiment, obtaining the next stage behavior training schedule based on the extended encoding result of the genetic probability and the initial behavior training course includes:

[0016] Obtain the fitness function, calculate the fitness value of the initial behavior training courses based on the fitness function, sort the initial behavior training courses according to the fitness value, and obtain the initial behavior training course sequence.

[0017] Based on the extended coding results, the current parent course sequence is obtained from the initial behavior training course sequence according to the preset selection probability, and the current child course sequence is obtained from the current parent course sequence according to the genetic probability. The current parent course sequence includes at least one current parent course, and the current child course sequence includes at least one current child course.

[0018] The fitness values ​​of the current parent course and the current child course are calculated based on the fitness function. The fitness values ​​of the current parent course and the current child course are compared pairwise, and the courses with higher fitness values ​​are retained to generate the next generation of parent courses. The above steps are repeated until the number of iterations reaches the preset maximum number of generations, at which point the iteration ends and the next stage of behavior training course schedule is obtained.

[0019] In one embodiment, the function for obtaining the fitness value includes:

[0020] The system obtains test item attribute indicators, weight values ​​of test item attribute indicators, and user requirements. The behavior training course includes at least one test item attribute indicator, wherein the user requirements include the user's target test item attribute indicators, and the behavior training course database includes at least one of the aforementioned behavior training courses.

[0021] Identify the correlation between the test item attribute indicators and the target test item attribute indicators, and generate an adaptive value function based on the correlation and the weight values ​​of the test item attribute indicators.

[0022] In one embodiment, after comparing the fitness values ​​of the current parent course with those of the current child course pairwise and retaining the courses with higher fitness values ​​to generate the next generation of parent courses, the method for generating the behavior training schedule further includes:

[0023] Obtain the preset fitness threshold;

[0024] The fitness value of the next generation behavior training course is obtained by the fitness value function. The fitness values ​​of the next generation behavior training courses are compared pairwise. If the difference between the fitness values ​​of two next generation behavior training courses is less than the fitness value threshold, the next generation course with the higher fitness value is retained to obtain the weight reduction behavior training course table. The next generation course table includes at least one next generation parent course.

[0025] In one embodiment, the weight loss behavior training schedule includes at least one weight loss behavior training course. After obtaining the weight loss rehabilitation schedule, the method for generating the behavior training schedule further includes:

[0026] Get the preset target number of questions;

[0027] The number of weight reduction behavior training courses is detected, and the number of weight reduction behavior training courses is compared with the target value of the number of questions to obtain the difference result. If the number of weight reduction behavior training courses is less than the target value of the number of questions, the current parent courses are sorted according to the fitness value to obtain the sorting result.

[0028] Based on the sorting results and the difference results, the current parent class courses are added to the weight reduction behavior training course table in descending order to obtain the next stage behavior training course table.

[0029] In one embodiment, obtaining the current child class course sequence from the current parent class course sequence based on genetic probability includes:

[0030] Obtain the preset crossover probability, and based on the extended encoding result, obtain the current child course sequence from the current parent course sequence according to the crossover probability;

[0031] And / or,

[0032] Obtain the preset mutation probability, and based on the extended encoding result, obtain the current child course sequence from the current parent course sequence according to the mutation probability.

[0033] In one embodiment, generating an initial behavior training schedule based on the initial behavior training course and sending the initial behavior training schedule to a display terminal for display includes:

[0034] Obtain the target type threshold and user requirements, which also include the target training course type;

[0035] Select target behavior training courses based on the initial behavior training courses and target training course types. The target behavior training courses include at least one target course type. Detect the number of courses in the target course type, where the number of courses in the target course type is less than the target type threshold.

[0036] Generate an initial behavior training schedule based on the target behavior training course.

[0037] Secondly, this application also provides a behavioral training schedule generation device. The device includes:

[0038] The acquisition module is used to acquire rating scales, a behavioral training course database, and abnormal answers from users to the rating scales. The training course database includes course numbers and at least one type of behavioral training course.

[0039] The calculation module is used to determine the mapping relationship between the rating scale and the behavior training course database based on the course number, and to obtain the initial behavior training course from the behavior training course database based on abnormal answer results and the mapping relationship.

[0040] The generation module is used to send the initial behavior training course to the user's terminal and generate the initial behavior training course schedule.

[0041] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0042] Obtain rating scales, a database of behavioral training courses, and abnormal responses from users to the rating scales. The training course database includes course numbers.

[0043] The mapping relationship between the rating scale and the behavior training course database is determined based on the course number. The initial behavior training course is obtained from the behavior training course database based on the abnormal answer results and the mapping relationship.

[0044] Generate an initial behavior training schedule based on the initial behavior training course, and send the initial behavior training schedule to the display terminal for display.

[0045] The aforementioned method, apparatus, and computer equipment for generating behavior training schedules first obtain the user's answer results based on an assessment scale; second, based on a preset mapping relationship, generate a corresponding initial behavior training course according to the answer results; finally, generate an initial behavior training schedule based on the initial behavior training course and send the initial behavior training schedule to a display terminal for display. This behavior training schedule generation method solves the problem of not being able to generate customized, phased behavior training schedules, and can flexibly generate different types of questions, thus better achieving the training effect for children. Furthermore, combining the training course with electronic products can better motivate children, making the training course more attractive to them and achieving better training results. Attached Figure Description

[0046] Figure 1 This is a flowchart illustrating a method for generating a behavior training schedule in one embodiment;

[0047] Figure 2 This is a flowchart illustrating the behavior training schedule generation method in another embodiment;

[0048] Figure 3 This is a flowchart illustrating a preferred embodiment of a behavior training schedule generation method.

[0049] Figure 4 This is a schematic diagram of a behavior training schedule generation device in one embodiment;

[0050] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0052] In one embodiment, such as Figure 1 As shown, a method for generating a behavior training schedule is provided. Figure 1 This application presents a flowchart of a method for generating a performance-based behavioral training course, which includes the following steps:

[0053] Step S110: Obtain the rating scale, the behavior training course database, and the user's abnormal answers to the rating scale, wherein the training course database includes course numbers.

[0054] The behavior training course database contains a large number of behavior training courses. Each course has content and outcome attributes. The outcome attributes include training completion status and effects, which do not participate in the generation of behavior training courses. The content attributes mainly include age division, course type, course name, course options, course answers, level information, difficulty level, etc. Each course must have the relevant constraints imposed by these attributes.

[0055] Step S120: Determine the mapping relationship between the rating scale and the behavior training course database based on the course number, and obtain the initial behavior training course from the behavior training course database based on the abnormal answer results and the mapping relationship.

[0056] The rating scales and behavior training courses have a pre-defined mapping relationship, which can be determined based on the course number. Upon receiving abnormal responses, the initial behavior training course can be retrieved from the behavior training course database based on this mapping relationship. Furthermore, the behavior training courses are mainly divided into three categories: listening, language, and cognition. There is a pre-defined category ratio between the rating scales and the behavior training courses. The corresponding behavior training courses are extracted according to different categories and abnormal responses within each category to obtain the initial behavior training courses.

[0057] Step S130: Generate an initial behavior training schedule based on the initial behavior training course, and send the initial behavior training schedule to the display terminal for display.

[0058] After generating the initial behavior training course, an initial behavior training schedule can be generated based on this course. The generation of the initial behavior training schedule supports modular component drag-and-drop functionality. Users can also select from these selections to obtain a target behavior training course, from which an initial behavior training schedule can be generated. Furthermore, the display terminal includes, but is not limited to, mobile devices, institutional devices, computers, and platform devices.

[0059] Through steps S110 to S130, firstly, an assessment scale, a preset behavioral training course database, and the user's answers to the assessment scale are obtained. These answers include abnormal responses. The preset behavioral training course database includes at least one behavioral training course. Further, the behavioral training courses are divided into three categories, with a fixed number of courses in each category. There is a preset mapping relationship between the questions in the assessment scale and the courses in the behavioral training course database, and a preset category ratio relationship exists between the assessment scale and the behavioral training courses. Based on this category ratio relationship and the preset mapping relationship, corresponding behavioral training courses are obtained by category. The three categories of behavioral training courses are then combined to obtain the initial behavioral training course. This demonstrates that, unlike traditional behavioral training methods, which are often rigid and fail to stimulate children's interest or prevent them from rote memorization, the behavioral training schedule generation method in this application can generate questions flexibly and specifically, largely avoiding rote memorization. Furthermore, the behavioral training schedule generation method in this application can achieve phased and customized course arrangements, enabling children to receive more comprehensive training results.

[0060] In one embodiment, Figure 2 This is a flowchart illustrating a behavior training schedule generation method in another embodiment. The behavior training schedule generation method further includes:

[0061] Step S240: Obtain a preset basic classification standard, classify the behavior training course database according to the basic classification standard to obtain a basic classification result, which includes at least one basic course category; obtain a preset extended classification standard, classify the basic course categories according to the extended classification standard to obtain an extended classification result, which includes at least one extended course category; encode the basic course categories to obtain basic coding results, segment the basic coding results according to the extended course categories to obtain extended coding results; obtain a preset genetic probability, and generate the next stage behavior training course schedule based on the genetic probability, the extended coding results, and the initial behavior training course.

[0062] Specifically, the behavioral training course database can be divided into three main categories according to basic classification criteria: hearing, language, and cognition. These three categories are further subdivided according to extended classification criteria. For example, the hearing category can be divided into hearing abnormalities, hearing impairments, etc., resulting in extended classification results. After classification, the basic course categories are encoded to obtain basic coding results. These basic coding results are then segmented according to the extended course categories to obtain extended coding results. Specifically, this encoding can be binary encoding. Each basic classification result is binary encoded, and the code is divided into several sub-segments according to the extended classification criteria, with each sub-segment having an independent code. After obtaining the extended coding results, a preset genetic probability is obtained. Based on the genetic probability, the extended coding results, and the initial behavioral training course, the next stage of behavioral training course schedule is generated. Specifically, the genetic probability includes a preset crossover probability, a preset mutation probability, and a preset fitness function. This demonstrates that a detailed classification of the behavior training course database allows for comprehensive training of children in all aspects. Furthermore, encoding the classification results facilitates subsequent steps such as course selection and iterative generation of offspring courses. Representing the courses using binary encoding allows for the application of genetic algorithms to efficiently generate the next stage of the behavior training course schedule.

[0063] In one embodiment, obtaining the next stage of behavioral training schedule based on genetic probability, extended coding results, and the initial behavioral training course includes:

[0064] Obtain the fitness function, calculate the fitness value of the initial behavior training courses based on the fitness function, and sort the initial behavior training courses according to the fitness values ​​to obtain the initial behavior training course sequence. Based on the extended encoding results, obtain the current parent course sequence from the initial behavior training course sequence according to the preset selection probability, and obtain the current child course sequence from the current parent course sequence according to the inheritance probability. The current parent course sequence includes at least one current parent course, and the current child course sequence includes at least one current child course. Calculate the fitness value of the current parent course and the current child course according to the fitness function, compare the current parent course fitness value and the current child course fitness value pairwise, retain the course with the higher fitness value, and generate the next generation parent course sequence. Repeat the above steps until the number of iterations reaches the preset maximum number of generations, at which point the iteration ends, and the behavior training course table for the next stage is obtained.

[0065] Specifically, the fitness function calculates the fitness value of each course based on its content attributes. After calculating the fitness value of the initial behavioral training courses according to the preset fitness function, the initial behavioral training courses are sorted from largest to smallest based on their fitness values, generating an individual queue, i.e., the initial behavioral training course sequence. The current parent course sequence is then obtained from the initial behavioral training course sequence based on a preset selection probability. This selection operation determines the individuals for recombination and crossover. The current parent course sequence includes at least one current parent course. After obtaining the current parent course sequence, the current child course sequence is obtained from the current parent course sequence according to a preset inheritance probability, which includes crossover probability and mutation probability. The current parent course sequence and the current child course sequence are calculated according to the fitness function. After the fitness values ​​are calculated, the individual with the highest fitness value in the child course sequence is compared with the individual with the highest fitness value in the parent course sequence. If the fitness value of the parent individual is higher than that of the child individual, then the parent individual replaces the course with the lowest fitness value in the child course sequence to generate the next generation of parent course sequences. This process is repeated until the preset maximum number of generations is reached. Furthermore, since the number of courses varies across different basic classification results, the preset maximum generation also differs; the larger the number of behavioral training courses, the larger the maximum generation. This demonstrates that, based on selection strategies and genetic probabilities, an iterative approach is proposed to transform a large number of courses into codes. Efficient iteration of the codes, utilizing crossover and mutation calculations, is achieved, providing targeted, customized courses for different users. Moreover, since this iteration is related to the number of courses, the larger the number of courses, the larger the required maximum generation. The maximum generation can be adjusted based on different actual situations to obtain an accurate number of courses, precisely generating the corresponding next-stage behavioral training course schedule for different users.

[0066] In one embodiment, the function for obtaining the fitness value includes:

[0067] Obtain test item attribute indicators, weight values ​​of test item attribute indicators, and user requirements. The behavior training course includes at least one test item attribute indicator, whereby the user requirements include the user's target test item attribute indicator. The behavior training course database includes at least one behavior training course. Confirm the correlation between the test item attribute indicators and the target test item attribute indicators, and generate an adaptive value function based on the correlation and the weight values ​​of the test item attribute indicators.

[0068] Specifically, the fitness function in this application is constructed as follows:

[0069]

[0070] Among them, f iω represents the absolute value of the error between the i-th attribute indicator and the user's requirement. i Let $j$ represent the weight of the i-th attribute indicator in relation to the course, $j$ be the number of attribute indicators involved in the evaluation, and $f$ be the sum of the absolute values ​​of the errors between all indicators and the user's requirements. Each course in the behavior training course database needs to calculate its fitness value based on the fitness value function. The smaller the fitness value, the more well the course suits the user's needs. It can be seen that the fitness value function focuses on calculating whether the behavior training course closely matches the user's needs. Specifying multiple attribute indicators for each behavior training course facilitates comprehensive calculation of each course, yielding the most suitable result. This also lays the foundation for iterating the behavior training course schedule based on the course's fitness value in subsequent steps.

[0071] In one embodiment, the method further includes:

[0072] Obtain the preset fitness threshold;

[0073] The fitness value of the next generation behavior training course is obtained by the fitness value function. The fitness values ​​of the next generation behavior training courses are compared pairwise. If the difference between the fitness values ​​of two next generation behavior training courses is less than the fitness value threshold, the next generation course with the higher fitness value is retained to obtain the weight reduction behavior training course table. The next generation course table includes at least one next generation parent course.

[0074] Specifically, in the new generation of individuals formed by the algorithm of this application through selection, crossover, and mutation, the presence of similar individuals can easily lead to premature convergence. Therefore, it is necessary to de-duplicate the behavioral training courses. This involves calculating behavioral training courses whose fitness differences are less than a preset fitness threshold, retaining those with higher fitness values, and deleting those with lower fitness values, resulting in a de-duplicated behavioral training course list. This de-duplication step is also based on encoding and fitness values. It can be seen that the de-duplication step enables the algorithm of this application to complete iterations more effectively and converge quickly. Furthermore, timely deletion of unnecessary courses reduces unnecessary computational burden and significantly improves computational efficiency.

[0075] In one embodiment, the method further includes:

[0076] Get the preset target number of questions;

[0077] The number of weight reduction behavior training courses is detected, and the number of weight reduction behavior training courses is compared with the target number of questions to obtain the difference result. If the number of weight reduction behavior training courses is less than the target number of questions, the current parent courses are sorted according to the fitness value to obtain the sorting result. Based on the sorting result and the difference result, the current parent courses are added to the weight reduction behavior training course table in descending order to obtain the next stage behavior training course table.

[0078] Specifically, since the number of behavioral training courses is fixed, the weight reduction behavioral training course schedule needs to be supplemented after weight reduction is completed. The supplementary course individuals can be obtained by selecting high-quality individuals from the parent courses. The current parent courses are sorted according to their fitness values. After sorting, based on the sorting results and the difference results, the current parent courses are added to the weight reduction behavioral training course schedule in ascending order to obtain the behavioral training course schedule for the next stage.

[0079] In one embodiment, the method further includes:

[0080] Obtain the preset crossover probability, and based on the extended encoding result, obtain the current child course sequence from the current parent course sequence according to the crossover probability;

[0081] And / or,

[0082] Obtain the preset mutation probability, and based on the extended encoding result, obtain the current child course sequence from the current parent course sequence according to the mutation probability.

[0083] Specifically, the crossover operation includes the crossover probability mentioned above. The crossover operation directly swaps the two encoded behavior training courses bit by bit according to a certain crossover probability. Considering convergence speed, global search, and incorporating small-scale competition and selection operations, each current parent course retains only one individual for generation, ensuring the offspring population size remains unchanged. The selected current parent courses are randomly assigned, and the same number of current subclass courses are generated through crossover, resulting in a current subclass course sequence. And / or, the mutation operation includes the mutation probability mentioned above. The mutation operation mutates the behavior training course encoding according to a certain mutation probability. This mutation process includes, but is not limited to, operations such as inversion, two-point swapping, adjacent swapping, interval reversal, and single-point movement. The expanded encoding result represents a certain number of expanded classification results. Mutation cannot change the size of each expanded encoding result. Furthermore, the mutation operation can only be performed on a per-expanded encoding result basis, selecting the behavior training course to be replaced from the same type of course according to a certain mutation probability. This demonstrates that after generating the initial behavioral training curriculum, it is transformed according to preset classification criteria and genetic probabilities to obtain the next-stage behavioral training curriculum. Furthermore, the genetic probabilities include crossover and mutation probabilities. After multiple iterations, the resulting next-stage behavioral training curriculum possesses digitized statistics and a customized, phased curriculum arrangement, forming a closed loop of "assessment-reporting-training-reassessment-retraining." Compared to traditional behavioral training curriculum generation, the customized behavioral training curriculum generated in this application achieves better training results.

[0084] In one embodiment, the method further includes:

[0085] Obtain the target type threshold and user requirements, which also include the target training course type;

[0086] Select target behavior training courses based on the initial behavior training courses and target training course types. The target behavior training courses include at least one target course type. Detect the number of courses in the target course type, where the number of courses in the target course type is less than the target type threshold.

[0087] Generate an initial behavior training schedule based on the target behavior training course.

[0088] Specifically, the platform's behavior training curriculum system also supports online customized courses and modular drag-and-drop functionality. Users can select relevant courses from the generated curriculum and train directly, freely combining training content to achieve a personalized recommendation and customized curriculum system. It's important to note that there is a limit to the number of courses a user can select in this application. Therefore, this application allows for more life-oriented and customized behavior training course generation. Users can choose target behavior training courses based on their individual circumstances, making training more efficient and convenient, and more attractive to children.

[0089] This embodiment also provides a specific embodiment of a method for generating behavioral training schedules, such as... Figure 3 As shown, Figure 3 This is a schematic diagram of the process for generating a behavior training schedule in a preferred embodiment.

[0090] Step S310: Generate an initial behavior training course based on the rating scale and the user's answers. The questions in the rating scale have a pre-defined mapping relationship with the courses in the behavior training course database. Based on any abnormal results in the answers, corresponding behavior training courses are selected from the behavior training course database to obtain the initial behavior training course table.

[0091] Step S320: Obtain a preset basic classification standard. Classify the behavior training course database according to the basic classification standard. In this application, the behavior training course database is divided into three basic categories: hearing, language, and cognition. Based on a preset extended classification standard, classify the basic classification results to obtain extended classification results. For example, the basic classification result of hearing can be further subdivided into two extended classification results: hearing abnormality and hearing impairment. Encode the behavior training course database according to the extended classification results, including but not limited to binary encoding.

[0092] Step S330: Generate the next-stage behavior training schedule based on the preset genetic probabilities and extended coding results. First, the generation of the next-stage behavior training schedule is based on the fitness function. Each behavior training course in the behavior training course database includes at least one question attribute indicator, such as course type, course options, difficulty level, and level information. Based on the preset fitness function, the fitness level of each behavior training course for the user is calculated based on the question attribute indicators; the lower the fitness value, the stronger the fitness of the course. Second, behavior training courses are selected from the initial behavior training schedule based on the preset fitness value and selection strategy to generate the current parent course sequence. Specifically, the selection strategy involves sorting all questions in the question bank according to their fitness, generating an individual sequence, and determining the individuals to be copied in the individual sequence based on a certain selection probability to generate the current parent course sequence. Then, based on the preset genetic probabilities, the current child course sequence is generated from the current parent course sequence. Specifically, the genetic probabilities include crossover probability and mutation probability. Finally, the fitness values ​​of the current parent course and the current child course are calculated based on the fitness function, and then compared pairwise. Courses with higher fitness values ​​are retained to generate the next generation of parent courses. The next generation of parent courses is then de-duplicated and supplemented. The above steps are repeated until the number of iterations reaches the preset maximum number of generations, at which point the iteration ends, and the next stage of behavior training curriculum is obtained.

[0093] The behavioral training curriculum is dynamically generated, and customized courses are also available. Users can conduct behavioral training at home or choose remote guidance from professionals. It offers customized courses and periodic training programs, with behavioral training reports generated online, truly providing comprehensive services to users.

[0094] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0095] Based on the same inventive concept, this application also provides an apparatus for implementing the above-mentioned generation of behavior training schedules. The solution provided by this apparatus is similar to the solution described in the above method. Therefore, the specific limitations of one or more behavior training schedule generation apparatus embodiments provided below can be found in the limitations of the behavior training schedule generation method above, and will not be repeated here.

[0096] In one embodiment, such as Figure 4 As shown, a behavior training course generation device is provided, including: an acquisition module 41, a calculation module 42, and a generation module 43, wherein:

[0097] The acquisition module 41 is used to acquire rating scales, a behavior training course database, and abnormal answer results of users on the rating scales, wherein the training course database includes course numbers and at least one behavior training course.

[0098] The calculation module 42 is used to determine the mapping relationship between the rating scale and the behavior training course database according to the course number, and to obtain the initial behavior training course from the behavior training course database according to the abnormal answer results and the mapping relationship.

[0099] The generation module 43 is used to send the initial behavior training course to the user terminal and generate the initial behavior training course schedule.

[0100] Specifically, the acquisition module 41 is connected to the calculation module 42. The acquisition module 41 acquires an assessment scale, a preset behavior training course database, and the user's answers to the assessment scale, including abnormal answers. Furthermore, a preset mapping relationship exists between the assessment scale and the behavior training course database. The acquisition module 41 sends the assessment scale, the behavior training course database, and the abnormal answers to the calculation module 42. Based on the preset mapping relationship and the abnormal answers, the calculation module 42 extracts the corresponding behavior training courses from the behavior training course database. This initial behavior training course is then sent to the generation module 43, which generates an initial behavior training course schedule based on the user's input requirements.

[0101] The aforementioned behavior training schedule generation device not only breaks away from traditional behavior training methods, but furthermore, the behavior training schedule generation device in this application solves the problem of children memorizing questions, and generates different behavior training courses in a customized and phased manner according to different users, thus achieving better training results.

[0102] Each module in the aforementioned behavioral training schedule generation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0103] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for generating a behavior training schedule. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0104] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the behavior training schedule generation device to which the present application is applied. The specific behavior training schedule generation device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0105] Those skilled in the art should understand that the technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments have been described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0106] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for generating a behavioral training schedule, characterized in that, The method includes: Obtain rating scales, a behavioral training course database, and abnormal answers from users to the rating scales, wherein the training course database includes course numbers; The mapping relationship between the rating scale and the behavior training course database is determined based on the course number, and the initial behavior training course is obtained from the behavior training course database based on the abnormal answer results and the mapping relationship. Obtain a preset basic classification standard, classify the behavior training course database according to the basic classification standard, and obtain a basic classification result, wherein the basic classification result includes at least one basic course category; Obtain a preset extended classification standard, classify the basic course categories according to the extended classification standard, and obtain an extended classification result, wherein the extended classification result includes at least one extended course category; The basic course categories are encoded to obtain basic encoding results. The basic encoding results are then segmented according to the extended course categories to obtain extended encoding results. Obtain a preset genetic probability, and generate a behavior training course schedule for the next stage based on the genetic probability, the extended encoding result, and the initial behavior training course, including: obtaining a fitness function, calculating the fitness value of the initial behavior training course based on the fitness function, and sorting the initial behavior training course according to the fitness value to obtain an initial behavior training course sequence. Based on the extended encoding result, the current parent course sequence is obtained from the initial behavior training course sequence according to the preset selection probability, and the current child course sequence is obtained from the current parent course sequence according to the genetic probability, wherein the current parent course sequence includes at least one current parent course, and the current child course sequence includes at least one current child course. The fitness value of the current parent course and the fitness value of the current child course are calculated according to the fitness value function. The fitness values ​​of the current parent course and the current child course are compared pairwise, and the courses with higher fitness values ​​are retained to generate the next generation of parent courses. The above steps are repeated until the number of iterations reaches the preset maximum number of generations, at which point the iteration ends and the next stage of behavior training course schedule is obtained. The next stage of behavioral training schedule will be sent to the display terminal for display.

2. The method according to claim 1, characterized in that, The function for obtaining the fitness value includes: The system acquires test item attribute indicators, the weight values ​​of the test item attribute indicators, and user requirements. The behavior training course includes at least one of the test item attribute indicators, wherein the user requirements include the user's target test item attribute indicators, and the behavior training course database includes at least one of the behavior training courses. Confirm the correlation between the test item attribute indicators and the target test item attribute indicators, and generate the fitness function based on the correlation and the weight values ​​of the test item attribute indicators.

3. The method according to claim 1, characterized in that, After comparing the fitness values ​​of the current parent class courses with the fitness values ​​of the current child class courses pairwise, retaining the courses with higher fitness values, and generating the next generation of parent class course sequences, the method further includes: Obtain the preset fitness threshold; The fitness value of the next generation behavior training course is obtained according to the fitness value function. The fitness values ​​of the next generation behavior training courses are compared pairwise. If there are two next generation behavior training courses whose fitness values ​​differ from each other by less than the fitness value threshold, the next generation course with the higher fitness value is retained to obtain the weight reduction behavior training course table. The next generation course includes at least one next generation parent course.

4. The method according to claim 3, characterized in that, The weight loss behavior training schedule includes at least one weight loss behavior training course. After obtaining the weight loss rehabilitation schedule, the method further includes: Get the preset target number of questions; The number of weight reduction behavior training courses is detected, and the number of weight reduction behavior training courses is compared with the target value of the number of questions to obtain the difference result. If the number of weight reduction behavior training courses is less than the target value of the number of questions, the current parent courses are sorted according to the fitness value to obtain the sorting result. Based on the sorting results and the difference results, the current parent class courses are added to the weight reduction behavior training course table in descending order to obtain the next stage behavior training course table.

5. The method according to claim 1, characterized in that, The step of obtaining the current child class course sequence from the current parent class course sequence based on the genetic probability includes: Obtain the preset crossover probability, and based on the extended encoding result, obtain the current subclass course sequence from the current parent class course sequence according to the crossover probability; And / or, Obtain the preset mutation probability, and based on the extended encoding result, obtain the current subclass course sequence from the current parent class course sequence according to the mutation probability.

6. The method according to claim 1, characterized in that, The step of generating an initial behavior training schedule based on the initial behavior training course and sending the initial behavior training schedule to a display terminal for display includes: Obtain the target type threshold and user requirements, wherein the user requirements also include the target training course type; Select a target behavior training course based on the initial behavior training course and the target training course type. The target behavior training course includes at least one target course type. Detect the number of courses in the target course type, wherein the number of courses in the target course type is less than the target type threshold. The initial behavior training schedule is generated based on the target behavior training course.

7. A device for generating a behavior training schedule, characterized in that, The device includes: The acquisition module is used to acquire rating scales, a behavior training course database, and abnormal answers from users to the rating scales. The training course database includes course numbers and at least one behavior training course. The calculation module is used to determine the mapping relationship between the rating scale and the behavior training course database according to the course number, obtain the initial behavior training course from the behavior training course database according to the abnormal answer results and the mapping relationship; obtain the preset basic classification standard, classify the behavior training course database according to the basic classification standard, and obtain the basic classification result, wherein the basic classification result includes at least one basic course category. Obtain a preset extended classification standard, classify the basic course categories according to the extended classification standard, and obtain an extended classification result, wherein the extended classification result includes at least one extended course category; The basic course categories are encoded to obtain basic encoding results. The basic encoding results are then segmented according to the extended course categories to obtain extended encoding results. Obtain a preset genetic probability, and generate a behavior training course schedule for the next stage based on the genetic probability, the extended encoding result, and the initial behavior training course, including: obtaining a fitness function, calculating the fitness value of the initial behavior training course based on the fitness function, and sorting the initial behavior training course according to the fitness value to obtain an initial behavior training course sequence. Based on the extended encoding result, the current parent course sequence is obtained from the initial behavior training course sequence according to the preset selection probability, and the current child course sequence is obtained from the current parent course sequence according to the genetic probability, wherein the current parent course sequence includes at least one current parent course, and the current child course sequence includes at least one current child course. The fitness value of the current parent course and the fitness value of the current child course are calculated according to the fitness value function. The fitness values ​​of the current parent course and the current child course are compared pairwise, and the courses with higher fitness values ​​are retained to generate the next generation of parent courses. The above steps are repeated until the number of iterations reaches the preset maximum number of generations, at which point the iteration ends and the next stage of behavior training course schedule is obtained. The generation module is used to send the next stage of behavioral training schedule to the display terminal for display.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

Images