Man-machine interaction system and method for training developmental reading disorder phoneme distinguishing capability

Abstract

The invention discloses a man-machine interaction system and a man-machine interaction method for training the phoneme distinguishing capability of developmental reading disorder. The man-machine interaction system comprises an evaluation unit which is used for collecting personal information of a user and evaluation results of voice consciousness; the parameter configuration unit is connected with the evaluation unit, is provided with a preset element library and a preset rule library, and is used for configuring a practice interaction task and a formal interaction task with preset difficulty for the user based on the evaluation result; the exercise task unit and the formal task unit are both connected with the parameter configuration unit so as to perform man-machine interaction with a user according to the sequence of first exercise and then formal; the learning unit is connected with the formal task unit so as to perform learning reinforcement when the user answers an error and perform formal interaction again after learning is completed; and the feedback unit is connected with the formal task unit and is used for feeding back the interaction result to the user. According to the invention, learning and practice are combined, so that the knowledge boundary of children is expanded, and the confidence and learning ability of children are improved.

Description

Technical Field

[0001] The invention relates to a human-computer interaction system for training the phoneme discrimination ability of developmental dyslexia, and also relates to a corresponding human-computer interaction method, belonging to the technical field of human-computer interaction. Background Art

[0002] The level of cognitive development has a significant impact on children's reading development, especially for children with dyslexia, who generally have problems with cognitive retardation. Reading-related cognitive skills include phonological awareness, naming speed, and morpheme awareness. Phonological awareness is the ability of children to respond to and control speech fragments, which is particularly important for children with dyslexia. Phonological awareness involves the manipulation and discrimination of speech representations, which is improved through exercises such as phoneme deletion and phoneme substitution. In the reading process, phonological awareness helps convert the spelling of words into pronunciation, that is, phonetic encoding ability. Studies have shown that children with dyslexia have difficulties in finding words and naming speed, which is related to deficiencies in phonological awareness.

[0003] Empirical studies have further confirmed the importance of phonological awareness to children's Chinese reading. For example, an intervention teaching study on 62 children with dyslexia compared the effects of phonological awareness teaching, word formation awareness teaching, a combination of the two, and a control group, and found that the phonological awareness teaching group performed best in the phonological awareness test. Another study used methods such as phoneme deletion to improve children's fine processing ability of phonemes. The results showed that the children who underwent intervention had significantly improved their phonological awareness scores, reaching a level comparable to that of normal children. These studies emphasize the importance of phonological awareness intervention in improving the phonological awareness and literacy skills of children with dyslexia.

[0004] Chinese patent application CN115547151A discloses an audio-visual integrated reading training system and method, which aims to train users to listen to voice information synchronously while reading through the combination of an accompanying audio reading device and Chinese text reading materials, so as to achieve the matching of pronunciation and text, thereby improving the cross-channel integration ability of users with reading disabilities. The system simulates the natural reading learning process to improve the user's reading ability. However, although the system takes into account visual and auditory processing defects, its intervention materials still use traditional reading materials, mainly training at the behavioral level, without improving the user's underlying cognitive ability through interactive tasks. This means that although the system helps to simulate a real reading environment, it may have limitations in improving cognitive ability. Summary of the invention

[0005] The primary technical problem to be solved by the present invention is to provide a human-computer interaction system for training the phoneme discrimination ability of developmental dyslexia.

[0006] Another technical problem to be solved by the present invention is to provide a human-computer interaction method for training the phoneme discrimination ability of developmental dyslexia.

[0007] In order to achieve the above technical objectives, the present invention adopts the following technical solutions:

[0008] According to a first aspect of an embodiment of the present invention, there is provided a human-computer interaction system for training the phoneme discrimination ability of developmental dyslexia, comprising:

[0009] The evaluation unit includes an information input module and a cognitive evaluation module; wherein the information input module is used to collect the user's personal information, and the cognitive evaluation module is used to evaluate the user's speech awareness and obtain the evaluation results;

[0010] A parameter configuration unit, connected to the evaluation unit and having a preset element library and a preset rule library, to configure practice interaction tasks and formal interaction tasks of preset difficulty for the user based on the evaluation result; wherein the preset element library at least includes a shooting panel, a basketball, a pronunciation speaker, an activity button and a pause button; and the preset rule library at least includes: difficulty level, syllable combination, syllable pronunciation, syllable identification requirements, shooting requirements, basketball color and correctness feedback;

[0011] A practice task unit connected to the parameter configuration unit to perform human-computer interaction with the user based on the practice interaction task; wherein a task trial of the practice interaction task is configured to select a matching syllable from a pair of easily confused syllable combinations according to the pronunciation of a syllable, and matching prompt information is displayed for each task trial;

[0012] a formal task unit connected to the practice task unit and the parameter configuration unit to perform human-computer interaction with the user based on the formal interactive task; wherein a task trial of the formal interactive task is configured to select a matching syllable from a pair of easily confused syllable combinations according to the pronunciation of a syllable, and each task trial only displays matching prompt information when an answer is wrong;

[0013] A learning unit connected to the formal task unit, so that when the user gives an incorrect answer, the learning unit is entered, and after repeated practice n times based on the syllable combination to which the user gave an incorrect answer, the learning unit is returned to the formal task unit for the next task trial;

[0014] A feedback unit is connected to the formal task unit to obtain the human-computer interaction data of the user completing the formal interaction task and to feed back the interaction result to the user.

[0015] Preferably, a task trial of the practice interaction task is configured in the following manner:

[0016] Retrieving a shooting panel from the preset element library; wherein the shooting panel includes two baskets of different colors;

[0017] A pair of easily confused syllable combinations is randomly selected from the preset rule library and presented above two baskets of different colors;

[0018] Based on the syllable combination, the syllable pronunciation of one of the syllables is retrieved from the preset rule library and played and presented in the form of sound;

[0019] Retrieving a basketball from the preset element library, and retrieving syllable identification requirements, shooting requirements, basketball color, and correctness feedback from the preset rule library, so as to require the user to throw the basketball into the basket corresponding to the correct syllable;

[0020] The color of the basketball is the same as the color of the basket where the correct syllable is located.

[0021] Preferably, a task trial of the formal interactive task is configured in the following manner:

[0022] Retrieving a shooting panel from the preset element library; wherein the shooting panel includes two baskets of different colors;

[0023] A pair of easily confused syllable combinations is randomly selected from the preset rule library and presented above two baskets of different colors;

[0024] Based on the syllable combination, the syllable pronunciation of one of the syllables is retrieved from the preset rule library and played and presented in the form of sound;

[0025] Retrieving a basketball from the preset element library, and retrieving syllable identification requirements, shooting requirements, basketball color, and correctness feedback from the preset rule library, so as to require the user to throw the basketball into the basket corresponding to the correct syllable;

[0026] The initial color of the basketball is different from the colors of the two baskets, and when the user gives an incorrect answer, it changes to the color of the basket where the correct syllable is located, and each time the syllable combination is switched, the basketball returns to its initial color.

[0027] Preferably, the formal task unit further includes a difficulty adjustment module for obtaining behavioral response data of the user performing human-computer interaction and dynamically adjusting the task difficulty based on the behavioral response data;

[0028] Among them, when the cumulative number of times N that the user shoots with the basketball of the initial color is not less than a, and the accuracy rate is not less than b, the task difficulty increases by one level, and the cumulative number N is reset to zero; otherwise, the current task difficulty remains unchanged.

[0029] Preferably, the human-computer interaction system further comprises:

[0030] An updating unit connected to the formal task unit and the parameter configuration unit to update the parameter configuration unit based on the human-computer interaction data of the user completing the formal interaction task;

[0031] The data update at least includes: reducing the extraction weight of the syllable combination with the correct answer, adding new syllable combinations or replacing some syllable combinations.

[0032] Among them, the initial extraction weights of all syllable combinations are the same.

[0033] Preferably, the human-computer interaction system further comprises:

[0034] The wrong question bank is connected to the formal task unit to obtain the human-computer interaction data of the user completing the formal interactive task and store the syllable combinations that the user answered incorrectly.

[0035] Preferably, in the learning unit, the color of the basketball is the same as the color of the basket where the correct syllable is located.

[0036] According to a second aspect of an embodiment of the present invention, there is provided a human-computer interaction method using the above human-computer interaction system, comprising the following steps:

[0037] Obtain the user's personal information and speech awareness assessment results;

[0038] Based on the evaluation result of the user, configuring the practice interaction task and the formal interaction task of preset difficulty for the user based on the parameter configuration unit;

[0039] Performing human-computer interaction with the user based on the practice interaction task through a practice task unit until the user completes the practice interaction task;

[0040] Performing human-computer interaction with the user based on the formal interactive task through the formal task unit until the current human-computer interaction ends; wherein, during the human-computer interaction, after repeatedly practicing n times based on the syllable combination answered incorrectly by the user through the learning unit, returning to the formal task unit to perform the next task trial;

[0041] The interaction result of this human-computer interaction is fed back to the user through the feedback unit and stored in the user database; wherein the interaction result at least includes: the final score, the final difficulty, the interaction time and the syllable combination of the wrong answer.

[0042] Preferably, during the process of the user completing the formal interactive task, the user's behavioral response data of human-computer interaction is obtained through the difficulty adjustment module, and the task difficulty is dynamically adjusted based on the behavioral response data;

[0043] Among them, when the cumulative number of times N that the user shoots with the basketball of the initial color is not less than a, and the accuracy rate is not less than b, the task difficulty increases by one level, and the cumulative number N is reset to zero; otherwise, the current task difficulty remains unchanged.

[0044] Preferably, when the user starts the current human-computer interaction, the final difficulty of the previous human-computer interaction is retrieved from the user database as the initial difficulty of the current human-computer interaction.

[0045] Compared with the prior art, the present invention has the following technical effects:

[0046] (1) Start with intervention on the linguistic level deficits in developmental dyslexia, focus on intervention on children's phonemic awareness, and ensure that the designed training system is effective and scientific.

[0047] (2) Combining learning and practice, using clever methods to allow users to seamlessly connect practice and learning, which not only expands children's knowledge boundaries and avoids the inability to practice due to their knowledge reserves, but also improves children's self-confidence and learning ability.

[0048] (3) The interactive tasks are highly targeted, the interactive methods are lively and interesting, and the operations are simple and easy to understand. Compared with the reading method using text materials, it is more conducive to the understanding and operation of children with developmental dyslexia and helps to improve their acceptance of interactive tasks.

[0049] (4) The interactive tasks are generated using computer software, which can directly change the difficulty of the items according to parameters such as the user's accuracy rate. It can be widely used in dyslexia training for students with different reading levels and has strong practicality.

[0050] (5) It can be used on common electronic devices on the market, making the interactive process visual, facilitating remote real-time monitoring by parents and doctors, and enabling remote practice and practice at any time, thus breaking the limitations of time and space, improving practice efficiency, and making clinical intervention for dyslexia more convenient. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A schematic diagram of the structure of a human-computer interaction system for training the phoneme discrimination ability of developmental dyslexia provided by the first embodiment of the present invention;

[0052] Figure 2 An overall flow chart of a human-computer interaction method for training the phoneme discrimination ability of developmental dyslexia provided by the second embodiment of the present invention;

[0053] Figure 3 This is a detailed flow chart of a human-computer interaction method for training the phoneme discrimination ability of developmental dyslexia provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0054] The technical content of the present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0055] The technical concept of the embodiment of the present invention is to design an audio-visual phoneme discrimination interactive system that allows users to "learn by practicing". Specifically, practice and learning are integrated so that users do not feel separated. When they encounter a phoneme combination that they do not know, they can immediately learn it and then continue with the subsequent interaction. This audio-visual interaction that combines learning and practice can not only expand the phonetic knowledge of children with dyslexia, but also increase their phoneme recognition skills, better understand and process voice information, enhance voice awareness, and improve reading accuracy.

[0056] On this basis, the embodiment of the present invention is based on cognitive defects at the linguistic level and is designed in accordance with the psychological paradigm of audio-visual phoneme discrimination tasks. By training children with reading disabilities to process pinyin phoneme information, the children's ability to analyze and process speech is enhanced, thereby improving reading accuracy. In addition, the embodiment of the present invention uses electronic equipment and computer software to design interactive tasks, supporting users to interact anytime and anywhere, simplifying the interactive process. The interactive project can adjust the difficulty adaptively by adjusting parameters according to the different abilities of the users, greatly improving the practicality of the interaction and making it widely applicable to children with different reading levels.

[0057] First embodiment

[0058] like Figure 1 As shown, a human-computer interaction system for training the phoneme discrimination ability of developmental dyslexia provided by the first embodiment of the present invention includes an evaluation unit 1, a parameter configuration unit 2, a practice task unit 3, a formal task unit 4, a learning unit 5 and a feedback unit 6. Among them, the evaluation unit 1 is used to collect the user's personal information and the evaluation results of speech awareness. The parameter configuration unit 2 is connected to the evaluation unit 1 and has a preset element library and a preset rule library to configure the practice interaction tasks and formal interaction tasks of preset difficulty for the user based on the evaluation results. The practice task unit 3 and the formal task unit 4 are both connected to the parameter configuration unit 2 to perform human-computer interaction with the user based on the practice interaction tasks and the formal interaction tasks in the order of practice first and then formal. The learning unit 5 is connected to the formal task unit 4 to reinforce learning when the user answers incorrectly, and to perform formal interaction again after learning is completed. The feedback unit 6 is connected to the formal task unit 4 to obtain the human-computer interaction data of the user completing the formal interaction task, and to feedback the interaction results to the user.

[0059] Below, each functional unit of the human-computer interaction system is described in detail:

[0060] 1. Evaluation Unit

[0061] In this embodiment, the evaluation unit 1 includes an information entry module 11 and a cognitive evaluation module 12. Specifically, the information entry module 11 is used to collect the user's personal information, such as age, gender, education level, etc., and store it in a user database. The cognitive evaluation module 12 is used to evaluate the user's speech awareness (for example, through a built-in scale or a built-in evaluation task) and obtain the evaluation results.

[0062] 2. Parameter Configuration Unit

[0063] In this embodiment, the parameter configuration unit 2 has a preset element library 21 and a preset rule library 22. The preset element library at least includes a shooting panel, a basketball, a pronunciation speaker, an activity button, and a pause button; the preset rule library at least includes: difficulty level, syllable combination, syllable pronunciation, syllable identification requirements, shooting requirements, basketball color, and correct or incorrect feedback.

[0064] The following describes in detail the configuration process of the practice interaction task and the formal interaction task:

[0065] (1) Practice interactive task configuration

[0066] ① Call up the shooting panel from the preset element library, where the shooting panel includes two baskets of different colors.

[0067] ② Randomly select a pair of easily confused syllable combinations (for example, pa and ba) from the preset rule library and present them above two baskets of different colors.

[0068] ③ Based on the syllable combination, the syllable pronunciation of one of the syllables is retrieved from the preset rule library and presented in the form of sound.

[0069] ④ A basketball is retrieved from the preset element library, and syllable identification requirements, shooting requirements, basketball color, and correctness feedback are retrieved from the preset rule library to require the user to throw the basketball into the basket corresponding to the correct syllable. The color of the basketball is the same as the color of the basket at the location of the correct syllable.

[0070] In this embodiment, a practice interaction task includes multiple task trials (3 in this embodiment, and can also be set to 4, 5 or more), and each task trial is configured through the above steps ① to ④ to be configured into the final practice interaction task.

[0071] It is understandable that the purpose of this practice interaction task is to help users understand the rules. Therefore, matching prompt information is set in each task trial (i.e., the color of the basketball is the same as the color of the basket where the correct syllable is located), thus forming a directed interactive task so that users can understand the task requirements more quickly.

[0072] (2) Configuration of formal interaction tasks

[0073] ① Retrieve the shooting panel from the preset element library, where the shooting panel includes two baskets of different colors (for example: blue and pink).

[0074] ② Randomly select a pair of easily confused syllable combinations (for example, pa and ba) from the preset rule library and present them above two baskets of different colors.

[0075] ③ Based on the syllable combination, the syllable pronunciation of one of the syllables is retrieved from the preset rule library and presented in the form of sound.

[0076] ④ Retrieve the basketball from the preset element library, and retrieve the syllable identification requirements, shooting requirements, basketball color, and correctness feedback from the preset rule library to require the user to throw the basketball into the basket corresponding to the correct syllable. The initial color of the basketball (e.g., brown) is different from the colors of the two baskets, and changes to the color of the basket where the correct syllable is located when the user answers incorrectly, and the basketball returns to its initial color each time the syllable combination is switched.

[0077] In this embodiment, a formal interaction task includes multiple task trials and a preset interaction duration. Within the preset interaction duration, the user can continuously complete different task trials (the specific number varies according to the user's ability). Each task trial is configured through the above steps ① to ④ to form the final formal interaction task.

[0078] It is understandable that the purpose of this formal interactive task is to improve the user's speech awareness ability. Therefore, in each task trial, matching prompt information (the color of the basketball changes) only appears when the answer is wrong, and when the answer is correct, the basketball maintains its initial color. This forms an interactive task combined with teaching with progressive difficulty.

[0079] 3. Practice Task Unit

[0080] The practice task unit 3 is connected to the parameter configuration unit 2. When the parameter configuration unit 2 completes the configuration of the practice interaction task and the formal interaction task, the user first enters the practice task unit 3 to perform human-computer interaction based on the practice interaction task. Among them, a task trial of the practice interaction task is configured to select a matching syllable from a pair of easily confused syllable combinations according to the pronunciation of a syllable, and each task trial displays matching prompt information.

[0081] In the rule description stage, text and pictures are included to explain the interaction process and rules in detail, making it easier for users to remember the rules. Finally, a start interaction button appears just below the rule description box in the middle of the screen, which users need to click to confirm and start the interaction.

[0082] The following are the specific steps for practicing interactive tasks:

[0083] In the first step, the user clicks OK to start practice training.

[0084] Select a background image from the background gallery.

[0085] Retrieve from the preset rule library: (1) Difficulty level (2) Syllable combination (3) Syllable pronunciation (4) Syllable identification requirements (5) Basketball shooting requirements (6) Basketball color rules (7) True or false feedback.

[0086] Select from the preset element library: (1) Shooting panel (2) Basketball (3) Voice speaker (4) Activity button (5) Pause button.

[0087] The syllable combinations that need to be identified are presented according to the difficulty level 1. In addition, some interactive design buttons are presented in a long-term continuous mode, including: (1) Activity button, presented at the top of the screen, the button is a specific activity icon extracted from the element library, including: difficulty, remaining time, score (2) Pause button, presented at the upper left corner of the screen, with help written on the button.

[0088] For example: the user clicks OK to start training. After the training task starts, a voice prompt is played first: throw the ball into the basket that is the same as the one pronounced by the speaker. The training difficulty is 1. According to the difficulty, the syllable combination "pa and ba" is called, where pa is presented to the user through the speaker, and the color of the basketball is the same as the basket at the position of the syllable "pa". The rules require that the ball be thrown into the basket that is the same as the one pronounced by the speaker, that is, the user needs to throw the basketball into the basket corresponding to pa. The user can also react directly based on the color of the basketball and the basket.

[0089] In the second step, the user performs the shooting task and clicks on the basket to complete the shooting. After the user makes a choice, the following feedback is given based on whether the user's choice is correct or not:

[0090] If the user does not make a selection within the time limit, the screen will prompt that the time has expired and the user will proceed to the next question. If the user makes a correct selection and shoots the ball, the screen will prompt that the answer is correct and the user will proceed to the next question. If the user makes an incorrect selection and shoots the ball, the screen will prompt that the answer is incorrect and the user will proceed to the next question.

[0091] Step 3: Practice 3 questions in total (not limited to this number). After completing them, the practice phase ends.

[0092] In this embodiment, after the user completes the practice interaction task, he / she enters the formal task unit for interaction.

[0093] 4. Formal Task Unit

[0094] In this embodiment, the formal task unit 4 is connected with the practice task unit 3 and the parameter configuration unit 2 to perform human-computer interaction with the user based on the formal interaction task after the user completes the practice interaction task. Among them, a task trial of the formal interaction task is configured to select a matching syllable from a pair of easily confused syllable combinations according to the pronunciation of a syllable, and each task trial only displays matching prompt information when the answer is wrong.

[0095] In the rule description stage, text and pictures are included to explain the interaction process and rules in detail, making it easier for users to remember the rules. Finally, a start interaction button appears just below the rule description box in the middle of the screen, which users need to click to confirm and start the interaction.

[0096] The following are the specific steps of the formal interaction task:

[0097] In the first step, the user clicks OK to start the formal interactive task.

[0098] Select a background image from the background gallery.

[0099] Retrieve from the preset rule library: (1) Difficulty level (2) Syllable combination (3) Syllable pronunciation (4) Syllable identification requirements (5) Basketball shooting requirements (6) Basketball color rules.

[0100] Select from the preset element library: (1) Shooting panel (2) Basketball (3) Voice speaker (4) Activity button (5) Pause button.

[0101] The syllable library presents the syllable combinations that need to be identified according to the difficulty level. In addition, some interactive design buttons are presented in a long-term continuous presentation mode, including: (1) Activity button, presented at the top of the screen, the button is a specific activity icon extracted from the element library, including: difficulty, remaining time, score (2) Pause button, presented at the upper left of the screen, with help written on the button.

[0102] For example: the user clicks OK to start the interaction. After the interactive task starts, a voice prompt is played first: throw the ball into the basket that is the same as the speaker's pronunciation. The difficulty of the first round of training is 1. According to the difficulty, the syllable combination "pa and ba" is selected, where pa is presented to the user through the speaker. At the beginning, the color of the basketball is brown. The rules require that the ball be thrown into the basket that is the same as the speaker's pronunciation, that is, the user needs to throw the basketball into the basket corresponding to pa.

[0103] In the second step, the user performs a basketball shooting task by clicking on the basket. If the answer is correct, the user proceeds to the next syllable identification trial; if the answer is incorrect, the user enters the learning stage (described in detail below).

[0104] The third step is to record the correctness of the user's choices in the user database, and randomly present the questions that the user answered incorrectly in the following step. The wrong questions are recorded and presented in the feedback stage.

[0105] Step 4: When the preset interaction time is reached, this round ends.

[0106] In addition, in this embodiment, preferably, the formal task unit 4 also includes a difficulty adjustment module 41, which is used to obtain the behavioral response data of the user's human-computer interaction and dynamically adjust the task difficulty based on the behavioral response data. Specifically, if the cumulative number of times N that the user shoots with the basketball of the initial color is not less than a, and the accuracy rate is not less than b, the task difficulty is increased by one level, and the cumulative number N is reset; otherwise, the current task difficulty remains unchanged.

[0107] 5. Learning Unit

[0108] The learning unit 5 is connected to the formal task unit 4, so that when the user makes an incorrect answer, the user enters the learning unit 5, and after repeating the practice n times based on the syllable combination that the user answered incorrectly, the user returns to the formal task unit for the next task trial. In the learning unit, the color of the basketball is the same as the color of the basket where the correct syllable is located.

[0109] Specifically, when the user makes an incorrect shot in a task trial, the color of the basketball changes from brown to the color of the basket corresponding to the correct syllable (blue or pink). At this time, the syllable combination is repeated n times, the position of the syllable combination changes randomly, and the color of the basketball is the same as the color of the basket corresponding to the correct syllable, thus helping the user to make judgments.

[0110] It is understandable that during the formal interaction, each time the user gives an incorrect answer, he / she will enter the learning unit 5 for corresponding learning until the formal interaction ends.

[0111] 6. Feedback Unit

[0112] The feedback unit 6 is connected to the formal task unit 4 to obtain the human-computer interaction data of the user completing the formal interaction task and to feed back the interaction result to the user.

[0113] Specifically, in this embodiment, the feedback unit 6 obtains the human-computer interaction result of this time according to the human-computer interaction data of the user, and stores it in the user database. The human-computer interaction result at least includes: the final score, the final difficulty, the interaction time, and the wrong syllable combination. In this way, not only can the user be presented with the interaction situation of this time, but also data support can be provided for the next human-computer interaction based on the human-computer interaction data of this time.

[0114] In the above embodiment, preferably, the human-computer interaction system also includes an updating unit 7. The updating unit 7 is connected to the formal task unit 4 and the parameter configuration unit 2 to update the parameter configuration unit based on the human-computer interaction data of the user completing the formal interaction task. Specifically, when the user completes the formal interaction task, it is possible to obtain which syllable combinations are answered correctly and which are answered incorrectly in this interaction based on the human-computer interaction data. Thus, the parameter configuration unit can be updated by reducing the extraction weight of the syllable combination that is answered correctly, supplementing new syllable combinations, or replacing some syllable combinations. Among them, the initial extraction weights of all syllable combinations are the same. After the formal interaction is over, the extraction weights of the questions answered correctly are reduced to w. 1 , the weight of the wrongly answered questions remains the initial weight w 0 .

[0115] In the above embodiment, preferably, the human-computer interaction system further includes a wrong question bank 8. The wrong question bank 8 is connected to the formal task unit 4 to obtain the human-computer interaction data of the user completing the formal interaction task, and store the syllable combination that the user answered incorrectly. It can be understood that the wrong question bank 8 can be connected to the parameter configuration unit 2, so that the corresponding syllable combination in the parameter configuration unit 2 (i.e., the syllable combination that the user answered incorrectly) is transferred to the wrong question bank 8, so as to facilitate the user to review and concentrate on practicing.

[0116] Second embodiment

[0117] like Figure 2 and Figure 3 As shown, based on the above first embodiment, the second embodiment of the present invention provides a human-computer interaction method for training the phoneme discrimination ability of developmental dyslexia, which specifically includes steps S1 to S5:

[0118] S1: Obtain the user's personal information and speech awareness assessment results.

[0119] Specifically, when a user logs into the human-computer interaction system, he or she needs to first enter personal information and then conduct a speech awareness assessment to form a user profile for the user.

[0120] S2: Based on the evaluation result of the user, the parameter configuration unit 2 configures the practice interaction task and the formal interaction task of preset difficulty for the user.

[0121] Specifically, in this step, the parameter configuration unit 2 will retrieve the data in the user database, and then according to the data in the user database, the system will perform algorithm calculation and deployment and generate an audiovisual phoneme discrimination task suitable for the user level. The specific task configuration process refers to the description of the parameter configuration unit 2 in the first embodiment, which will not be repeated here.

[0122] Among them, when the algorithm is calculated, the system will determine whether the user is an initial user. If it is an initial user, the user's age, education level, current speech awareness assessment score and audio-visual ability task-based assessment score are retrieved to calculate the audio-visual phoneme discrimination ability, and then the initial task level is determined based on the user's audio-visual phoneme discrimination ability. If it is a historical user, the above steps are omitted, and the task difficulty level and interaction duration corresponding to the user's audio-visual phoneme discrimination level obtained at the end of the last interaction are inherited as the task difficulty level and interaction duration of this user's interaction.

[0123] S3: Performing human-computer interaction with the user based on the practice interaction task through the practice task unit until the user completes the practice interaction task.

[0124] After completing the configuration of the practice interaction task and the formal interaction task based on step S2, the user will enter the practice task unit 3 to perform human-computer interaction based on the practice interaction task. The specific human-computer interaction steps refer to the description of the practice task unit 3 in the first embodiment above, which will not be repeated here.

[0125] S4: Conduct human-computer interaction with the user through formal task units based on formal interaction tasks until the human-computer interaction ends.

[0126] In this embodiment, after the user completes step S3, the user will enter the formal task unit 4 to perform human-computer interaction based on the formal interaction task until the preset interaction time is reached. The specific human-computer interaction steps refer to the description of the formal task unit 4 in the first embodiment above, which will not be repeated here.

[0127] It should be noted that during the human-computer interaction process, the difficulty adjustment module 41 will dynamically adjust the task difficulty based on preset rules. In addition, when the user answers incorrectly, he / she will enter the learning unit 5 for learning. The specific learning process refers to the description of the learning unit 5 in the first embodiment above, which will not be repeated here.

[0128] S5: Feedback the interaction result of this human-computer interaction to the user through the feedback unit and store it in the user database.

[0129] Specifically, when the user completes the formal interactive task in the formal task unit 4, the feedback unit 6 will feedback the interaction result of this human-computer interaction to the user, and the interaction result at least includes: the final score, the final difficulty, the interaction time and the syllable combination of the incorrect answer.

[0130] In addition, the interaction result will be stored in the user database for subsequent data retrieval. When the user starts the next human-computer interaction, the final difficulty of the previous human-computer interaction can be directly retrieved from the user database as the initial difficulty of the next human-computer interaction.

[0131] In summary, the human-computer interaction system and method for training the phoneme discrimination ability of developmental dyslexia provided by the embodiments of the present invention have the following beneficial effects:

[0132] (1) Start with intervention on the linguistic level deficits in developmental dyslexia, focus on intervention on children's phonemic awareness, and ensure that the designed training system is effective and scientific.

[0133] (2) Combining learning and practice, using clever methods to allow users to seamlessly connect practice and learning, which not only expands children's knowledge boundaries and avoids the inability to practice due to their knowledge reserves, but also improves children's self-confidence and learning ability.

[0134] (3) The interactive tasks are highly targeted, the interactive methods are lively and interesting, and the operations are simple and easy to understand. Compared with the reading method using text materials, it is more conducive to the understanding and operation of children with developmental dyslexia and helps to improve their acceptance of interactive tasks.

[0135] (4) The interactive tasks are generated using computer software, which can directly change the difficulty of the items according to parameters such as the user's accuracy rate. It can be widely used in dyslexia training for students with different reading levels and has strong practicality.

[0136] (5) It can be used on common electronic devices on the market, making the interactive process visual, facilitating remote real-time monitoring by parents and doctors, and enabling remote practice and practice at any time, thus breaking the limitations of time and space, improving practice efficiency, and making clinical intervention for dyslexia more convenient.

[0137] It should be noted that the above embodiments are only examples, and the technical solutions of the various embodiments can be combined, all within the protection scope of the present invention.

[0138] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0139] The above is a detailed description of the human-computer interaction system and method for training the phoneme discrimination ability of developmental dyslexia provided by the present invention. For those skilled in the art, any obvious changes made to it without departing from the essence of the present invention will constitute an infringement of the patent right of the present invention and will bear the corresponding legal liability.

Claims

1. A human-computer interaction system for training the phoneme discrimination ability of developmental dyslexia, characterized in that include: The evaluation unit includes an information input module and a cognitive evaluation module; wherein the information input module is used to collect the user's personal information, and the cognitive evaluation module is used to evaluate the user's speech awareness and obtain the evaluation results; A parameter configuration unit, connected to the evaluation unit and having a preset element library and a preset rule library, to configure practice interaction tasks and formal interaction tasks of preset difficulty for the user based on the evaluation result; wherein the preset element library at least includes a shooting panel, a basketball, a pronunciation speaker, an activity button and a pause button; and the preset rule library at least includes: difficulty level, syllable combination, syllable pronunciation, syllable identification requirements, shooting requirements, basketball color and correctness feedback; A practice task unit connected to the parameter configuration unit to perform human-computer interaction with the user based on the practice interaction task; wherein a task trial of the practice interaction task is configured to select a matching syllable from a pair of easily confused syllable combinations according to the pronunciation of a syllable, and matching prompt information is displayed for each task trial; a formal task unit connected to the practice task unit and the parameter configuration unit to perform human-computer interaction with the user based on the formal interactive task; wherein a task trial of the formal interactive task is configured to select a matching syllable from a pair of easily confused syllable combinations according to the pronunciation of a syllable, and each task trial only displays matching prompt information when an answer is wrong; A learning unit connected to the formal task unit, so that when the user gives an incorrect answer, the learning unit is entered, and after repeated practice n times based on the syllable combination to which the user gave an incorrect answer, the learning unit is returned to the formal task unit for the next task trial; A feedback unit is connected to the formal task unit to obtain the human-computer interaction data of the user completing the formal interaction task and to feed back the interaction result to the user.

2. The human-computer interaction system according to claim 1, characterized in that A task trial of the practice interaction task is configured in the following way: Retrieving a shooting panel from the preset element library; wherein the shooting panel includes two baskets of different colors; A pair of easily confused syllable combinations is randomly selected from the preset rule library and presented above two baskets of different colors; Based on the syllable combination, the syllable pronunciation of one of the syllables is retrieved from the preset rule library and played and presented in the form of sound; Retrieving a basketball from the preset element library, and retrieving syllable identification requirements, shooting requirements, basketball color, and correctness feedback from the preset rule library, so as to require the user to throw the basketball into the basket corresponding to the correct syllable; The color of the basketball is the same as the color of the basket where the correct syllable is located.

3. The human-computer interaction system according to claim 1, characterized in that A task trial of the formal interaction task is configured in the following way: Retrieving a shooting panel from the preset element library; wherein the shooting panel includes two baskets of different colors; A pair of easily confused syllable combinations is randomly selected from the preset rule library and presented above two baskets of different colors; Based on the syllable combination, the syllable pronunciation of one of the syllables is retrieved from the preset rule library and played and presented in the form of sound; Retrieving a basketball from the preset element library, and retrieving syllable identification requirements, shooting requirements, basketball color, and correctness feedback from the preset rule library, so as to require the user to throw the basketball into the basket corresponding to the correct syllable; The initial color of the basketball is different from the colors of the two baskets, and when the user gives an incorrect answer, it changes to the color of the basket where the correct syllable is located, and each time the syllable combination is switched, the basketball returns to its initial color.

4. The human-computer interaction system according to claim 1, wherein: The formal task unit also includes a difficulty adjustment module for obtaining behavioral response data of a user performing human-computer interaction and dynamically adjusting the task difficulty based on the behavioral response data; Among them, when the cumulative number of times N that the user shoots with the basketball of the initial color is not less than a, and the accuracy rate is not less than b, the task difficulty increases by one level, and the cumulative number N is reset to zero; otherwise, the current task difficulty remains unchanged.

5. The human-computer interaction system according to claim 1, characterized in that Also includes: An updating unit connected to the formal task unit and the parameter configuration unit to update the parameter configuration unit based on the human-computer interaction data of the user completing the formal interaction task; The data update at least includes: reducing the extraction weight of the syllable combination with the correct answer, adding a new syllable combination or replacing part of the syllable combination; Among them, the initial extraction weights of all syllable combinations are the same.

6. The human-computer interaction system according to claim 1, characterized in that Also includes: The wrong question bank is connected to the formal task unit to obtain the human-computer interaction data of the user completing the formal interactive task and store the syllable combinations that the user answered incorrectly.

7. The human-computer interaction system according to claim 1, characterized in that: In the learning unit, the color of the basketball is the same as the color of the basket where the correct syllable is located.

8. A human-computer interaction method for training the phoneme discrimination ability of developmental dyslexia, based on the human-computer interaction system according to any one of claims 1 to 7, characterized in that The steps include: Obtain the user's personal information and speech awareness assessment results; Based on the evaluation result of the user, configuring the practice interaction task and the formal interaction task of preset difficulty for the user based on the parameter configuration unit; Performing human-computer interaction with the user based on the practice interaction task through a practice task unit until the user completes the practice interaction task; Performing human-computer interaction with the user based on the formal interactive task through the formal task unit until the current human-computer interaction ends; wherein, during the human-computer interaction, after repeatedly practicing n times based on the syllable combination answered incorrectly by the user through the learning unit, returning to the formal task unit to perform the next task trial; The interaction result of this human-computer interaction is fed back to the user through the feedback unit and stored in the user database; wherein the interaction result at least includes: the final score, the final difficulty, the interaction time and the syllable combination of the wrong answer.

9. The human-computer interaction method according to claim 8, characterized in that: In the process of the user completing the formal interactive task, the user's behavioral response data of human-computer interaction is obtained through the difficulty adjustment module, and the task difficulty is dynamically adjusted based on the behavioral response data; Among them, when the cumulative number of times N that the user shoots with the basketball of the initial color is not less than a, and the accuracy rate is not less than b, the task difficulty increases by one level, and the cumulative number N is reset to zero; otherwise, the current task difficulty remains unchanged.

10. The human-computer interaction method according to claim 8, characterized in that: When the user starts this human-computer interaction, the final difficulty of the previous human-computer interaction is retrieved from the user database as the initial difficulty of this human-computer interaction.

Images