Generalized training content generation method and device for autism patient

Abstract

The invention relates to a generalization training content generation method and device for autism patients, computer equipment and a storage medium. The method comprises the following steps: acquiring personalized feature data of an autism patient, and acquiring training target data, generalization baseline data and a generalization stage of generalization training of the autism patient; generating initial generalization training content of the autism patient according to the training target data, the generalization baseline data, the generalization stage and a pre-trained large language model; and performing feature fusion on the training roles of the initial generalization training content according to the personalized feature data to obtain standard generalization training content of the autism patient. By adopting the method, the training content can be enriched and the individuation degree can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent medical treatment, in particular to a generalization training content generation method and device for autism patients, a computer device and a storage medium. BACKGROUND

[0002] Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder, and its core symptoms include difficulties in social interaction and communication, narrow interests, and repetitive stereotyped behaviors. In the field of autism intervention, generalization is recognized as the gold standard for testing intervention effectiveness. Generalization training enables autism patients to successfully transfer and appropriately apply skills learned in specific training situations to real and varied life situations.

[0003] However, the traditional generalization training content generation method for autism patients has the problems of single training content and low degree of individualization. SUMMARY

[0004] Therefore, it is necessary to provide a generalization training content generation method, device, computer device and storage medium for autism patients, which can enrich the training content and improve the degree of individualization.

[0005] In a first aspect, a generalization training content generation method for autism patients is provided, which is applied to a server; the method comprises: obtaining individualized feature data of an autism patient, and obtaining training target data, generalization baseline data and generalization stage of the generalization training of the autism patient; generating initial generalization training content for the autism patient according to the training target data, the generalization baseline data, the generalization stage and a pre-trained large language model; performing feature fusion on the training role of the initial generalization training content according to the individualized feature data to obtain standard generalization training content for the autism patient.

[0006] In one embodiment, obtaining the training target data, the generalization baseline data and the generalization stage of the generalization training of the autism patient comprises: obtaining a personal digital model of the autism patient; performing training target evaluation according to the personal digital model to obtain the training target data; performing generalization baseline evaluation according to the personal digital model to obtain the generalization baseline data and the generalization stage.

[0007] In one of the embodiments, the personal digital model of the autism patient is obtained, including: obtaining generalization baseline evaluation data, autism diagnosis data, and behavior characteristic data of the autism patient; performing data structural processing on the generalization baseline evaluation data, the autism diagnosis data, and the behavior characteristic data to obtain a structured database; generating the personal digital model according to the structured database; wherein the personal digital model is used to represent age characteristics, object difference characteristics, and social and cultural evaluation characteristics of the autism patient.

[0008] In one of the embodiments, the initial generalization training content of the autism patient is generated according to the training target data, the generalization baseline data, the generalization stage, and the pre-trained large language model, including: determining a scene variation type and a training complexity level of the generalization training according to the generalization stage; determining a training type of the generalization training according to the generalization baseline data, and obtaining a target prompt word after query processing in a prompt word database according to the training type; inputting the training target data, the scene variation type, the training complexity level, and the target prompt word into the large language model to obtain the initial generalization training content.

[0009] In one of the embodiments, the method further includes: generating an auxiliary prompt content of the generalization training according to a highest level of the auxiliary prompt level of the generalization training; and automatically displaying the standard generalization training content and the auxiliary prompt content to the user terminal of the autism patient.

[0010] In one of the embodiments, the method further includes: obtaining training behavior monitoring data of the generalization training sent by the user terminal; analyzing the training behavior monitoring data to obtain a training behavior analysis result of the generalization training; wherein the training behavior analysis result includes a training reaction time and a training accuracy rate of the generalization training; displaying training feedback content to the user terminal according to the training behavior analysis result, and adjusting the auxiliary prompt level according to the training behavior analysis result.

[0011] In one of the embodiments, the method further includes: counting all training behavior analysis results of the autism patient in a current training period; performing generalization index evaluation according to each training behavior analysis result to obtain a generalization index evaluation result; the generalization index evaluation includes stimulus generalization evaluation, reaction generalization evaluation, and maintenance generalization evaluation; the generalization index evaluation result includes a stimulus generalization evaluation result, a reaction generalization evaluation result, and a maintenance generalization evaluation result; calculating a comprehensive generalization index according to the stimulus generalization evaluation result, a weight of the stimulus generalization evaluation result, the reaction generalization evaluation result, a weight of the reaction generalization evaluation result, the maintenance generalization evaluation result, and a weight of the maintenance generalization evaluation result; and automatically adjusting a scene variation type and a training complexity level of a next training period according to the comprehensive generalization index.

[0012] In a second aspect, a device for generating generalization training content for an autism patient is provided, and the device is applied to a server. The device comprises a data acquisition module, a content generation module, and a feature fusion module.

[0013] The data acquisition module is configured to acquire personalized feature data of the autism patient, and acquire training target data, generalization baseline data, and a generalization stage of the generalization training of the autism patient. The content generation module is configured to generate initial generalization training content for the autism patient according to the training target data, the generalization baseline data, the generalization stage, and a pre-trained large language model. The feature fusion module is configured to perform feature fusion on a training role of the initial generalization training content according to the personalized feature data, to obtain standard generalization training content for the autism patient.

[0014] In a third aspect, a computer device is provided, which comprises a memory and a processor. The memory stores a computer program, and the processor implements the steps of any of the above method embodiments when executing the computer program.

[0015] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by a processor to implement the steps of any of the above method embodiments.

[0016] The above method, device, computer device, and storage medium for generating generalization training content for an autism patient acquire personalized feature data of the autism patient, and acquire training target data, generalization baseline data, and a generalization stage of the generalization training of the autism patient. Then, initial generalization training content for the autism patient is generated according to the training target data, the generalization baseline data, the generalization stage, and a pre-trained large language model. Next, feature fusion is performed on a training role of the initial generalization training content according to the personalized feature data, to obtain standard generalization training content for the autism patient. This enriches the scene complexity of the training content, improves the individualization and systematicness of the training content, facilitates the establishment of a deep emotional connection with the autism patient through the training content, and improves the efficiency and rehabilitation effect of the generalization training. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 An application environment diagram of the method for generating generalization training content for an autism patient in an embodiment; Figure 2 A first flowchart of the method for generating generalization training content for an autism patient in an embodiment; Figure 3 A flowchart of acquiring training target data, generalization baseline data, and a generalization stage of the generalization training of an autism patient in an embodiment; Figure 4A flowchart of a process of obtaining a personal digital model of an autism patient in an embodiment; Figure 5 A flowchart of a process of generating initial generalization training content of an autism patient according to training target data, generalization baseline data, a generalization stage, and a pre-trained large language model in an embodiment; Figure 6 A second flowchart of a method of generating generalization training content of an autism patient in an embodiment; Figure 7 A third flowchart of a method of generating generalization training content of an autism patient in an embodiment; Figure 8 A block diagram of a structure of a device for generating generalization training content of an autism patient in an embodiment; Figure 9 An internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0018] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not intended to limit the present application.

[0019] In order to facilitate the understanding of the present application, the present application will be described more fully below with reference to the related drawings. The embodiments of the present application are shown in the accompanying drawings. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used in the specification of the present application are only for the purpose of describing specific embodiments of the present application and are not intended to limit the present application.

[0021] It can be understood that the terms "first", "second", and the like used in the present application can be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from another element. For example, without departing from the scope of the present application, a first resistor can be referred to as a second resistor, and similarly, a second resistor can be referred to as a first resistor. The first resistor and the second resistor are both resistors, but they are not the same resistor.

[0022] It can be understood that "connection" in the following embodiments, if the circuits, modules, units, etc. connected to each other have the transmission of electrical signals or data, it should be understood as "electrically connected", "communicatively connected", etc.

[0023] As used herein, the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. It will be further understood that the terms "comprises," "comprising," "includes," "including," or "has," "having," or the like, when used in this specification, specify the presence of stated features, integers, steps, operations, elements, or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or groups thereof.

[0024] The autism patient generalization training content generation method provided by the present application can be applied to the application environment as shown in Figure 1 The user terminal 102 of the autism patient communicates with the server 104 through the network. The user terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0025] In one embodiment, as shown in Figure 2 A autism patient generalization training content generation method is provided, and the method is applied to the server 104 in Figure 1 for example, which includes the following steps 201 to 203.

[0026] Step 201, obtaining personalized feature data of the autism patient, and obtaining training target data, generalization baseline data, and generalization stage of the autism patient's generalization training.

[0027] The personalized feature data is data used to describe the personalized features of the autism patient. The training target data is data used to describe the training target of the autism patient's generalization training. The generalization baseline data is data used to describe the generalization baseline of the autism patient's generalization training. Specifically, the server 104 obtains the personalized feature data of the autism patient, and obtains the training target data, the generalization baseline data, and the generalization stage of the autism patient's generalization training.

[0028] In one specific example, the personalized feature data can include, but is not limited to, the autism patient's interest preference, attention characteristics, and communication method. The training target data includes record data indicating that the autism patient's language length training target is from single word to double word; the generalization baseline data includes record data indicating that the hearing sensitivity preference female voice generalization training is to the hearing insensitivity preference male voice. The above is only a specific example, and in actual application, it can be flexibly set according to user demand, which is not limited here.

[0029] In one embodiment, as shown in Figure 3As shown, the training target data, the generalization baseline data and the generalization stage of the generalization training of the autism patient are obtained, including steps 301 to 303.

[0030] Step 301, obtaining a personal digital model of the autism patient; Step 302, performing training target evaluation according to the personal digital model to obtain training target data; Step 303, performing generalization baseline evaluation according to the personal digital model to obtain generalization baseline data and generalization stage.

[0031] Specifically, the server 104 obtains a personal digital model of the autism patient; then, performs training target evaluation according to the personal digital model to obtain training target data; finally, performs generalization baseline evaluation according to the personal digital model to obtain generalization baseline data and generalization stage, thereby improving the efficiency, accuracy and convenience of obtaining the training target data, the generalization baseline data and the generalization stage of the generalization training of the autism patient.

[0032] In one of the embodiments, as shown, Figure 4 the personal digital model of the autism patient is obtained, including steps 401 to 403.

[0033] Step 401, obtaining generalization baseline evaluation data, autism diagnosis data and behavior characteristic data of the autism patient; Step 402, performing data structural processing on the generalization baseline evaluation data, the autism diagnosis data and the behavior characteristic data to obtain a structured database; Step 403, generating a personal digital model according to the structured database; The personal digital model is used to represent the age characteristics, object difference characteristics and social and cultural evaluation characteristics of the autism patient. Specifically, the generalization baseline evaluation data are data used for evaluating the generalization baseline. It can be understood that the generalization baseline evaluation data can be obtained by a standardized evaluation tool (CARS tool) but are not limited thereto. The server 104 obtains the generalization baseline evaluation data, the autism diagnosis data and the behavior characteristic data of the autism patient; then, performs data structural processing on the generalization baseline evaluation data, the autism diagnosis data and the behavior characteristic data to obtain a structured database; and then, generates a personal digital model according to the structured database, so that the personal digital model can accurately and comprehensively describe the autism patient.

[0034] In one specific example, the autism diagnosis data can include but are not limited to the age, gender, diagnosis information, diagnosis report and cognitive level evaluation table of the autism patient. The generalization baseline evaluation data can include but are not limited to language evaluation grades and obstacle evaluation grades. The above are only specific examples, and in actual application, they can be flexibly set according to user needs, which are not limited herein.

[0035] In one specific example, the personal digital model is used to represent the age characteristics, object difference characteristics and social and cultural assessment characteristics of the autistic patient; the age characteristics of the autistic patient are used to determine the typical characteristics and ability range of the autistic development stage; the object difference characteristics of the autistic patient are used to identify the advantage and challenge fields of the autistic patient; and the social and cultural assessment characteristics of the autistic patient are used to determine the cultural suitability of the training content. The above is only a specific example, and in actual application, it is flexible to set according to user needs, and is not limited herein.

[0036] In this embodiment, the generalization baseline evaluation data, autism diagnosis data and behavior characteristic data of the autistic patient are obtained; then, the generalization baseline evaluation data, autism diagnosis data and behavior characteristic data are subjected to data structural processing to obtain a structured database; then, the personal digital model is generated according to the structured database, so that the autistic patient can be accurately and comprehensively described through the personal digital model.

[0037] In this embodiment, the personal digital model of the autistic patient is obtained; then, the training target evaluation is performed according to the personal digital model to obtain training target data; finally, the generalization baseline evaluation is performed according to the personal digital model to obtain generalization baseline data and a generalization stage, which improves the efficiency, accuracy and convenience of obtaining the training target data, generalization baseline data and generalization stage of the autistic patient for generalization training.

[0038] Step 202, generating initial generalization training content of the autistic patient according to the training target data, generalization baseline data, generalization stage and pre-trained large language model.

[0039] Specifically, the server 104 generates the initial generalization training content of the autistic patient according to the training target data, generalization baseline data, generalization stage and pre-trained large language model, so as to realize the generalization situation expansion of the initial generalization training content and the intelligent, personalized and scaled generation of the initial generalization training content.

[0040] In one of the embodiments, as shown in Figure 5 the initial generalization training content of the autistic patient is generated according to the training target data, generalization baseline data, generalization stage and pre-trained large language model, including steps 501 to 503.

[0041] Step 501, determining the scene variation type and training complexity level of the generalization training according to the generalization stage; Step 502, determining the training type of the generalization training according to the generalization baseline data, and obtaining the target prompt word after query processing in the prompt word database according to the training type; Step 503, input the training target data, scene variation type, training complexity level and target prompt into the large language model to obtain the initial generalization training content.

[0042] Specifically, the server 104 determines the scene variation type and the training complexity level of the generalization training according to the generalization stage; then, determines the training type of the generalization training according to the generalization baseline data, and obtains the target prompt after query processing in the prompt database according to the training type; finally, inputs the training target data, scene variation type, training complexity level and target prompt into the large language model to obtain the initial generalization training content, so as to realize the generalization situation expansion of the initial generalization training content and the intelligent, personalized and scaled generation of the initial generalization training content.

[0043] In this embodiment, the scene variation type and the training complexity level of the generalization training are determined according to the generalization stage; then, the training type of the generalization training is determined according to the generalization baseline data, and the target prompt is obtained after query processing in the prompt database according to the training type; finally, the training target data, scene variation type, training complexity level and target prompt are input into the large language model to obtain the initial generalization training content, so as to realize the generalization situation expansion of the initial generalization training content and the intelligent, personalized and scaled generation of the initial generalization training content.

[0044] In one specific example, the large language model can include but is not limited to an LLM large language sub-model, a speech processing sub-model and a picture processing sub-model; the target prompt includes a first sub-target prompt, a second sub-target prompt and a third sub-target prompt.

[0045] The training target data, scene variation type, training complexity level and first sub-target prompt are input into the LLM large language sub-model to obtain a social story text; The training target data, scene variation type, training complexity level, social story text and second sub-target prompt are input into the speech processing sub-model to obtain a target audio of the social story text; The training target data, scene variation type, training complexity level, social story text and third sub-target prompt are input into the picture processing sub-model to obtain a target animation of the social story text; The social story text, target audio and target animation are feature fused to obtain the initial generalization training content. The above is only a specific example, and in actual application, it is flexibly set according to user demand, which is not limited here.

[0046] Step 203, according to the individualized feature data, the training role of the initial generalization training content is feature fused to obtain the standard generalization training content of the autistic patient.

[0047] Specifically, the server 104 fuses the features of the training roles of the initial generalized training content according to the personalized feature data to obtain the standard generalized training content of the autistic patient, enriches the scene complexity of the training content, improves the personalization degree and systematicness of the training content, facilitates the establishment of deep emotional connection with the autistic patient through the training content, and improves the efficiency and rehabilitation effect of the generalized training.

[0048] In one specific example, the interest preferences of the autistic patient include familiar role voice features and facial features; the features of the training roles of the initial generalized training content are fused according to the personalized feature data to obtain the standard generalized training content of the autistic patient, which includes: Based on face swap technology, the facial features of the familiar role are used to replace the facial features of the training role of the initial generalized training content to obtain the initial generalized training content of the autistic patient after the avatar replacement processing; Based on voice cloning technology, the voice features of the familiar role are used to simulate the voice of the training role of the initial generalized training content after the avatar replacement processing to obtain the standard generalized training content of the autistic patient.

[0049] It can be understood that face swap technology is an artificial intelligence technology that replaces the facial features of one person to another person's face through deep learning technology. Voice cloning technology refers to a technology that simulates and generates specific voice features through artificial intelligence technology. The above is only a specific example, and in actual application, it is flexibly set according to user needs, which is not limited here.

[0050] Based on this, the above-mentioned generalized training content generation method for autistic patients acquires personalized feature data of autistic patients and acquires training target data, generalized baseline data, and generalized stages of the generalized training of the autistic patients; then, the initial generalized training content of the autistic patient is generated according to the training target data, the generalized baseline data, the generalized stages, and the pre-trained large language model; next, the features of the training roles of the initial generalized training content are fused according to the personalized feature data to obtain the standard generalized training content of the autistic patient, which enriches the scene complexity of the training content, improves the personalization degree and systematicness of the training content, facilitates the establishment of deep emotional connection with the autistic patient through the training content, and improves the efficiency and rehabilitation effect of the generalized training.

[0051] In one embodiment, as shown in Figure 6 the method further includes steps 601 to 602.

[0052] Step 601: generating the auxiliary prompt content of the generalized training according to the highest level of the auxiliary prompt level of the generalized training; Step 602, automatically displaying standard generalization training content and auxiliary prompt content to the user terminal of the autistic patient.

[0053] Specifically, the server 104 generates auxiliary prompt content of the generalization training according to the highest level of the auxiliary prompt level of the generalization training; and then, automatically displays standard generalization training content and auxiliary prompt content to the user terminal of the autistic patient, ensuring the stable establishment of the generalization skills of the autistic patient and the continuous improvement of the generalization ability.

[0054] In one specific example, the auxiliary prompt content is scaffolding, which refers to the temporary support structure provided for the autistic patient in the learning process, which is gradually removed as the learner ability of the autistic patient improves. The above is only a specific example, which is flexibly set according to user needs in actual application, and is not limited herein.

[0055] In this embodiment, auxiliary prompt content of the generalization training is generated according to the highest level of the auxiliary prompt level of the generalization training; and then, standard generalization training content and auxiliary prompt content are automatically displayed to the user terminal of the autistic patient, ensuring the stable establishment of the generalization skills of the autistic patient and the continuous improvement of the generalization ability.

[0056] In one of the embodiments, as shown in Figure 6 The method further includes steps 603 to 605.

[0057] Step 603, obtaining training behavior monitoring data of the generalization training sent by the user terminal; Step 604, analyzing the training behavior monitoring data to obtain training behavior analysis results of the generalization training; Step 605, displaying training feedback content to the user terminal according to the training behavior analysis results, and adjusting the auxiliary prompt level according to the training behavior analysis results.

[0058] The training behavior analysis results include training reaction time and training accuracy of the generalization training. Specifically, the server 104 obtains training behavior monitoring data of the generalization training sent by the user terminal; then, analyzes the training behavior monitoring data to obtain training behavior analysis results of the generalization training; and then, displays training feedback content to the user terminal according to the training behavior analysis results, and adjusts the auxiliary prompt level according to the training behavior analysis results, so as to dynamically adjust the auxiliary prompt level of the auxiliary prompt content, and realize the smooth removal of the auxiliary prompt content from the maximum support to the independent completion.

[0059] In one specific example, the training feedback content includes training instant feedback and personalized encouragement, which are only specific examples, and are flexibly set according to user needs in actual application, and are not limited herein.

[0060] In the embodiment, the training behavior monitoring data of the generalization training sent by the user terminal is acquired; then, the training behavior monitoring data is analyzed to obtain the training behavior analysis result of the generalization training; then, the training feedback content is displayed to the user terminal according to the training behavior analysis result, and the auxiliary prompt level is adjusted according to the training behavior analysis result, so as to dynamically adjust the auxiliary prompt level of the auxiliary prompt content, and realize the smooth removal of the auxiliary prompt content from the maximum support to the independent completion.

[0061] In one of the embodiments, as shown in Figure 7 The method further includes steps 701 to 704.

[0062] Step 701, statistics of all training behavior analysis results of the autistic patient in the current training period; Step 702, generalization index evaluation according to each training behavior analysis result, to obtain the generalization index evaluation result; Step 703, calculation according to the stimulus generalization evaluation result, the weight of the stimulus generalization evaluation result, the reaction generalization evaluation result, the weight of the reaction generalization evaluation result, the maintenance generalization evaluation result and the weight of the maintenance generalization evaluation result, to obtain the comprehensive generalization index; Step 704, automatic adjustment of the scene variation type and the training complexity level of the next training period according to the comprehensive generalization index.

[0063] Among them, the generalization index evaluation includes stimulus generalization evaluation, reaction generalization evaluation and maintenance generalization evaluation; the generalization index evaluation result includes stimulus generalization evaluation result, reaction generalization evaluation result and maintenance generalization evaluation result.

[0064] Specifically, the server 104 statistics of all training behavior analysis results of the autistic patient in the current training period; then, the generalization index evaluation is carried out according to each training behavior analysis result, to obtain the generalization index evaluation result; then, the comprehensive generalization index is calculated according to the stimulus generalization evaluation result, the weight of the stimulus generalization evaluation result, the reaction generalization evaluation result, the weight of the reaction generalization evaluation result, the maintenance generalization evaluation result and the weight of the maintenance generalization evaluation result; then, the scene variation type and the training complexity level of the next training period are automatically adjusted according to the comprehensive generalization index, which avoids the subjective evaluation of the generalization training effect and facilitates the optimization of the standard generalization training content of the next training period.

[0065] In the embodiment, all training behavior analysis results of the autism patient in the current training period are counted; then, generalization index evaluation is performed according to each training behavior analysis result to obtain a generalization index evaluation result; then, the comprehensive generalization index is calculated according to the stimulus generalization evaluation result, the weight of the stimulus generalization evaluation result, the response generalization evaluation result, the weight of the response generalization evaluation result, the maintenance generalization evaluation result and the weight of the maintenance generalization evaluation result; then, the scene variation type and the training complexity level of the next training period are automatically adjusted according to the comprehensive generalization index, which avoids the subjectivity of the evaluation of the generalization training effect and facilitates the optimization of the standard generalization training content of the next training period.

[0066] It should be understood that, although Figures 2-7 The steps in the flowchart of the method are displayed in sequence according to the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, Figures 2-7 At least part of the steps in the method can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or sub-steps or stages of other steps.

[0067] In a second aspect, as shown in Figure 8 A generalization training content generation device for autism patients is provided, which is applied to a server; the device comprises a data acquisition module 810, a content generation module 820 and a feature fusion module 830.

[0068] The data acquisition module 810 is configured to acquire individualized feature data of the autism patient, and acquire training target data, generalization baseline data and a generalization stage of the generalization training of the autism patient; the content generation module 820 is configured to generate initial generalization training content of the autism patient according to the training target data, the generalization baseline data, the generalization stage and a pre-trained large language model; and the feature fusion module 830 is configured to perform feature fusion on a training role of the initial generalization training content according to the individualized feature data, to obtain standard generalization training content of the autism patient.

[0069] In one embodiment, the data acquisition module 810 comprises a first data acquisition unit.

[0070] The first digital acquisition unit is configured to acquire a personal digital model of the autistic patient; the first digital acquisition unit is configured to perform training target evaluation based on the personal digital model to obtain training target data; and the first digital acquisition unit is configured to perform generalization baseline evaluation based on the personal digital model to obtain generalization baseline data and a generalization stage.

[0071] In one of the embodiments, the first digital acquisition unit includes a personal digital model generator.

[0072] The personal digital model generator is configured to acquire generalization baseline evaluation data, autism diagnosis data, and behavior characteristic data of the autistic patient; the personal digital model generator is configured to perform data structuralization processing on the generalization baseline evaluation data, the autism diagnosis data, and the behavior characteristic data to obtain a structured database; the personal digital model generator is configured to generate a personal digital model based on the structured database; and the personal digital model is configured to represent age characteristics, object difference characteristics, and social and cultural evaluation characteristics of the autistic patient.

[0073] In one of the embodiments, the content generation module 820 includes a content generation unit.

[0074] The content generation unit is configured to determine a scene variation type and a training complexity level of the generalization training based on the generalization stage; the content generation unit is configured to determine a training type of the generalization training based on the generalization baseline data, and to obtain a target prompt word by performing query processing on the target prompt word in a prompt word database according to the training type; and the content generation unit is configured to input the training target data, the scene variation type, the training complexity level, and the target prompt word into a large language model to obtain initial generalization training content.

[0075] In one of the embodiments, the apparatus further includes a scaffolding module.

[0076] The scaffolding module is configured to generate auxiliary prompt content of the generalization training according to a highest level of an auxiliary prompt level of the generalization training; and the scaffolding module is configured to automatically display the standard generalization training content and the auxiliary prompt content to a user terminal of the autistic patient.

[0077] In one of the embodiments, the scaffolding module is further configured to acquire training behavior monitoring data of the generalization training sent by the user terminal; the scaffolding module is further configured to analyze the training behavior monitoring data to obtain training behavior analysis results of the generalization training; the training behavior analysis results include training reaction time and training accuracy of the generalization training; the scaffolding module is further configured to display training feedback content to the user terminal according to the training behavior analysis results, and to adjust the auxiliary prompt level according to the training behavior analysis results.

[0078] In one of the embodiments, the apparatus further includes a training evaluation module.

[0079] The training evaluation module is configured to count all training behavior analysis results of the autism patient in the current training period, and evaluate the generalization indicators according to the training behavior analysis results to obtain generalization indicator evaluation results. The generalization indicator evaluation includes stimulus generalization evaluation, response generalization evaluation, and maintenance generalization evaluation. The generalization indicator evaluation results include stimulus generalization evaluation results, response generalization evaluation results, and maintenance generalization evaluation results. The training evaluation module is configured to calculate a comprehensive generalization index according to the stimulus generalization evaluation results, the weight of the stimulus generalization evaluation results, the response generalization evaluation results, the weight of the response generalization evaluation results, the maintenance generalization evaluation results, and the weight of the maintenance generalization evaluation results. The training evaluation module is configured to automatically adjust the scene variation type and the training complexity level of the next training period according to the comprehensive generalization index.

[0080] The specific limitations of the autism patient generalization training content generation device can be referred to the limitations of the autism patient generalization training content generation method described above, which will not be repeated here. Each module in the autism patient generalization training content generation device described above can be realized by software, hardware, and combinations thereof, in whole or in part. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0081] In one embodiment, a computer device, which can be a server, is provided, and an internal structure diagram of the computer device can be as shown in Figure 9 The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is configured to store personalized feature data, training target data, generalization baseline data, and a generalization stage. The network interface of the computer device is configured to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement an autism patient generalization training content generation method.

[0082] Those skilled in the art can understand that Figure 9 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0083] In a third aspect, a computer device is provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of any of the above method embodiments when executing the computer program.

[0084] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program, when executed by a processor, implements the steps of any of the above method embodiments.

[0085] A person of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above method embodiments. Any reference to memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0086] Any combination of the above technical features of the above embodiments can be combined. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present disclosure.

[0087] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of the patent of the present application should be subject to the appended claims.​

Claims

1. A method for generating generalization training content for autistic patients, characterized in that, The method is applied to a server; the method comprises: Obtaining personalized feature data of an autistic patient, and obtaining training target data, generalization baseline data and generalization stage of the generalization training of the autistic patient; Generating initial generalization training content of the autistic patient according to the training target data, the generalization baseline data, the generalization stage and a pre-trained large language model; According to the personalized feature data, the training role of the initial generalization training content is fused to obtain the standard generalization training content of the autistic patient.

2. The method of claim 1, wherein, The method further comprises: Obtaining the training target data, the generalization baseline data and the generalization stage of the generalization training of the autistic patient comprises: Obtaining the personal digital model of the autistic patient; According to the personal digital model, the training target evaluation is carried out to obtain the training target data; 3. The method of claim 2, wherein, According to the personal digital model, the generalization baseline evaluation is carried out to obtain the generalization baseline data and the generalization stage. The method further comprises: Obtaining the personal digital model of the autistic patient comprises: Obtaining generalization baseline evaluation data, autism diagnosis data and behavior feature data of the autistic patient; 4. The method of claim 1, wherein, The generalization baseline evaluation data, the autism diagnosis data and the behavior feature data are subjected to data structural processing to obtain a structured database; According to the structured database, the personal digital model is generated; wherein the personal digital model is used to represent the age characteristics, object difference characteristics and social and cultural evaluation characteristics of the autistic patient. The method further comprises: According to the generalization stage, the scene variation type and the training complexity level of the generalization training are determined; 5. The method of claim 4, wherein, According to the generalization baseline data, the training type of the generalization training is determined, and after query processing in the prompt word database according to the training type, target prompt words are obtained; The training target data, the scene variation type, the training complexity level and the target prompt words are input into the large language model to obtain the initial generalization training content. The method further comprises:

6. The method of claim 5, wherein, According to the highest level of the auxiliary prompt level of the generalization training, the auxiliary prompt content of the generalization training is generated; The standard generalization training content and the auxiliary prompt content are automatically displayed to the user terminal of the autistic patient. The method further comprises: Obtaining the training behavior monitoring data of the generalization training sent by the user terminal; 7. The method of claim 6, wherein, Analyzing the training behavior monitoring data to obtain the training behavior analysis result of the generalization training; wherein the training behavior analysis result comprises the training reaction time and the training accuracy of the generalization training; According to the training behavior analysis result, training feedback content is displayed to the user terminal, and the auxiliary prompt level is adjusted according to the training behavior analysis result. The method further comprises: Statistically obtaining all the training behavior analysis results of the autistic patient in the current training period; According to the analysis results of each training behavior, a generalization index evaluation is performed to obtain a generalization index evaluation result; the generalization index evaluation includes stimulus generalization evaluation, response generalization evaluation, and maintenance generalization evaluation; and the generalization index evaluation result includes stimulus generalization evaluation result, response generalization evaluation result, and maintenance generalization evaluation result; According to the stimulus generalization evaluation result, the weight of the stimulus generalization evaluation result, the response generalization evaluation result, the weight of the response generalization evaluation result, the maintenance generalization evaluation result, and the weight of the maintenance generalization evaluation result, a comprehensive generalization index is calculated; According to the comprehensive generalization index, the scene variation type and the training complexity level of the next training cycle are automatically adjusted. 8.A device for generating a content for generalization training of an autism patient, characterized by The device is applied to a server; and the device comprises: A data acquisition module is configured to acquire personalized feature data of an autistic patient, and acquire training target data, generalization baseline data, and a generalization stage of the autistic patient; A content generation module is configured to generate initial generalization training content of the autistic patient according to the training target data, the generalization baseline data, the generalization stage, and a pre-trained large language model; A feature fusion module is configured to perform feature fusion on a training role of the initial generalization training content according to the personalized feature data, to obtain standard generalization training content of the autistic patient.

9. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the method of any one of claims 1 to 7.

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

Images