Intelligent companion device control method, device, and medium

Abstract

The application provides a kind of intelligent companion equipment control method, equipment and medium, response user's interface operation instruction is traversed to determine dynamic prompt set to database;Based on interactive stagnation character, the prompt starting character of prompt sentence is determined, and the prompt evaluation data is obtained according to the memory proficiency of interactive sentence and prompt starting character;According to the number of prompt characters in prompt evaluation data and the element modal of prompt element, the element modal customization processing is carried out on the dynamic frame of dynamic prompt set, and the display data is obtained, which can dynamically customize the prompt data according to the interactive performance of the user, enhance the understanding of the user to interactive content, and improve the interactive experience.

Description

Technical Field

[0001] This invention relates to data processing technology, and more particularly to a control method, device, and medium for an intelligent companion device. Background Technology

[0002] With the deep integration of artificial intelligence and multimedia technology, smart companion devices have gradually become an important carrier for family education, especially for children's poetry enlightenment and traditional culture learning.

[0003] Currently, existing smart companion devices only output content and cannot dynamically customize interactive content according to the actual interaction of different users. In the process of interacting with users, the interaction logic is still in a rudimentary stage, mostly relying on simple trigger-based feedback. They cannot customize content according to the user's real-time interaction status, which affects the user's interactive experience, makes the interaction process less enjoyable, and makes it difficult to maintain the user's long-term learning interest.

[0004] Therefore, how to dynamically customize prompt data based on user interaction performance, enhance user understanding of interactive content, and improve the interactive experience has become an urgent problem to be solved. Summary of the Invention

[0005] This invention provides a method, device, and medium for controlling an intelligent companion device, which can dynamically customize prompt data based on the user's interactive performance, enhance the user's understanding of the interactive content, and improve the interactive experience.

[0006] A first aspect of the present invention provides a method for controlling an intelligent companion device, comprising: The database is traversed in response to user interface operation commands to determine the dynamic prompt set; The starting character of the prompt statement is determined based on the interactive pause character, and prompt evaluation data is obtained based on the memory proficiency of the interactive statement and the starting character of the prompt. Based on the number of prompt characters and the modality of prompt elements in the prompt evaluation data, the dynamic frames of the dynamic prompt set are processed to customize the element modality, resulting in display data.

[0007] Optionally, in one possible implementation of the first aspect, determining the prompt start character of the prompt statement based on the interactive pause character includes: Record the recording time of each interactive character in the interactive statement, and obtain the interruption duration based on the current time and the recording time; When the duration of the interruption is determined to be greater than the duration of the prompt interval, the interactive statement is compared with the standard text to obtain the text to be interacted with, and the first character of the text to be interacted with is taken as the interactive pause character; The statement in the standard text corresponding to the interactive pause character is used as a prompt statement. When the number of historical prompts for the interactive pause character is less than the preset number of forgotten characters, the interactive pause character is used as the prompt start character. When it is determined that the number of historical prompts is greater than or equal to the preset number of forgettings, the forgetting difference is obtained based on the difference between the number of historical prompts and the preset number of forgettings, and the forgetting coefficient is calculated by comparing the forgetting difference with the preset number of forgettings. The number of interval characters is obtained by multiplying the forgetting coefficient and the number of forgotten characters, and the starting character of the prompt statement is determined based on the number of interval characters and the interactive pause character.

[0008] Optionally, in one possible implementation of the first aspect, determining the prompt start character of the prompt statement based on the interval character count and the interactive pause character includes: The number of uninteractive characters in the prompt statement is counted to obtain the remaining number. When the number of characters in the interval is greater than or equal to the remaining number, the forgetting coefficient is multiplied by the prompt interval duration to obtain the extended interval duration, and the extended interval duration is added to the prompt interval duration to obtain the first interval duration. When the duration of the interruption is determined to be greater than the duration of the first interval, the character indicating a pause in the interaction is used as the starting character for the prompt. When the number of characters in the interval is determined to be less than the remaining number, the number of characters in the interval is moved sequentially from the starting character of the interactive pause character to the corresponding character as the prompt starting character.

[0009] Optionally, in one possible implementation of the first aspect, obtaining the prompt evaluation data based on the memorization proficiency of the interactive statement and the prompt's initial character includes: The audio of the interactive statement is compared with the standard audio to obtain the clarity coefficient; The audio of the statement is compared with the character order of the standard audio to obtain the number of correctly memorized characters. The accuracy coefficient is obtained based on the ratio of the number of correctly memorized characters to the number of standard characters in the standard audio. The memorization proficiency of the interactive statements is obtained based on the clarity coefficient and the accuracy coefficient. The prompt evaluation data is obtained based on the memory proficiency and the remaining number of characters corresponding to the starting character of the prompt.

[0010] Optionally, in one possible implementation of the first aspect, obtaining the prompt evaluation data based on the memory proficiency and the remaining number corresponding to the prompt starting character includes: Based on the memory proficiency, the preset prompt table is traversed and compared to obtain the initial number of prompts and the prompt element modality, the prompt element modality including the screen modality and the fusion modality; The initial number of prompts is compared with the remaining number, and the smaller value is selected as the number of prompt characters. The prompt evaluation data includes the number of prompt characters and the prompt element modality.

[0011] Optionally, in one possible implementation of the first aspect, the step of performing element modality customization processing on the dynamic frames of the dynamic prompt set based on the number of prompt characters and the prompt element modality in the prompt evaluation data to obtain display data includes: Based on the prompt start character and the number of prompt characters, the prompt characters are obtained, and the prompt characters that are the same as the characters in the preset combination character set corresponding to the prompt statement are used as the combination label characters; Delete the characters in the prompt characters that are the same as those in the prompt character group corresponding to the combined label characters, and treat the remaining prompt characters as a single prompt element; The group of prompt characters corresponding to the combined label characters is used as a combined prompt element, and a prompt element is obtained based on the single prompt element and the combined prompt element; Based on the prompt element and the prompt element modality, the dynamic frame is processed to customize the element modality, and the display data is obtained.

[0012] Optionally, in one possible implementation of the first aspect, the step of performing element modality customization processing on the dynamic frame based on the prompt element and the prompt element modality to obtain display data includes: The element type of the prompt element is obtained based on its attributes, and the prompt data of each prompt element is obtained based on the element type. The corresponding prompt data is sequentially concatenated according to the text order of each prompt character in the prompt statement to obtain the screen display data; When the modality of the prompt element is determined to be a screen modality, the screen display data is used as the display data for the screen modality; When the modality of the prompt element is determined to be a fusion modality, the standard audio of the prompt character is associated with the corresponding prompt data to obtain fusion display data; The corresponding merged display data is sequentially concatenated according to the text order of each prompt character in the prompt statement to obtain the merged modality display data.

[0013] Optionally, in one possible implementation of the first aspect, obtaining the element type of the prompt element based on its attributes, and obtaining the prompt data for each prompt element according to the element type, includes: When the element type is determined to be a static element, a dynamic frame containing the static element is selected from the dynamic prompt set to obtain the frame to be displayed; The image elements corresponding to the static elements in the frame to be displayed are retained as elements, and the remaining image elements are deleted to obtain the static display frame. Based on the duration of a single element prompt, the retained elements are displayed alternately in bright and dark to obtain static prompt data; When the element type is determined to be a dynamic element, the dynamic prompt set is segmented into video segments according to the dynamic element and the duration of the single element prompt to obtain the video segment to be displayed. Based on the character semantics of the dynamic elements, the image elements related to the dynamic elements are retained as elements; Dynamic prompt data is generated based on the video segment to be displayed and the reserved elements. The prompt data includes static prompt data and dynamic prompt data.

[0014] Optionally, in one possible implementation of the first aspect, generating dynamic prompt data based on the video segment to be displayed and the reserved elements includes: When the number of elements to be retained is determined to be 1, the first dynamic frame in the video segment to be displayed is taken as the first dynamic frame, and the last dynamic frame is taken as the second dynamic frame. Identify the center coordinates of the first element in the first dynamic frame and the center coordinates of the second element in the second dynamic frame, and obtain the guiding direction based on the center coordinates of the first element and the center coordinates of the second element; Based on the guiding direction and the center point of the element in each dynamic frame, a guiding line is generated to obtain dynamic prompt screen data; When the number of elements to be retained is greater than 1, guide lines are generated by connecting the center points of the elements to be retained in sequence according to the text order of the elements, thus obtaining dynamic prompt data.

[0015] A second aspect of the present invention provides a smart companion device control device, comprising: The response module is used to traverse the database to determine the dynamic prompt set in response to the user's interface operation commands; The determination module is used to determine the prompt start character of the prompt statement based on the interactive pause character, and to obtain prompt evaluation data based on the memorization proficiency of the interactive statement and the prompt start character; The customization module is used to perform element modality customization processing on the dynamic frames of the dynamic prompt set based on the number of prompt characters and the prompt element modality in the prompt evaluation data, so as to obtain display data.

[0016] A third aspect of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program, wherein the computer program is stored in the memory, and the processor executes the computer program to perform the methods described in the first aspect of the present invention and various possible methods related to the first aspect.

[0017] A fourth aspect of the present invention provides a storage medium storing a computer program, which, when executed by a processor, is used to implement the first aspect of the present invention and various methods possibly involved in the first aspect.

[0018] The beneficial effects of this invention are as follows: 1. This invention can dynamically customize prompt data based on user interaction, improving the accuracy of prompts, enhancing user understanding of interactive content, and improving the interactive experience. This invention can accurately identify paused characters and determine the starting character for prompts that matches the user's experience. Specifically, by recording the recording time of each interactive character and calculating the interval duration, this invention determines whether the user is experiencing a memorization pause. It compares the already interacted sentences with the standard text to accurately locate the first character of the text to be interacted with as the paused character, avoiding subjective misjudgment. For temporary and persistent forgetting points, this invention can dynamically adjust the starting character for prompts based on the historical number of prompts for the paused character. When the historical number of prompts is low, the paused character is used directly as the starting point for accurate prompting. When the historical number of prompts exceeds the preset number of forgettings, the number of characters between the pauses is calculated using a forgetting coefficient, and the starting point for prompts is moved back, forcing the user to complete the intermediate content independently, cutting off prompt dependence, and strengthening reverse reasoning memory. Simultaneously, when the number of characters between the pauses approaches the sentence boundary, the pause waiting time is automatically extended, giving the user more space to recall, ensuring a smooth memorization process and significantly improving long-term memory.

[0019] 2. This invention compares the user's memorized audio with the standard audio word by word, comprehensively calculating the user's memorization proficiency from two dimensions: pronunciation clarity and content accuracy. This achieves an objective assessment of the user's learning level. Based on the memorization proficiency, the invention automatically matches the number of prompt characters and the prompt modality. Users with good memory receive a small number of visual prompts without additional audio, while users with weak memory receive a combined visual and audio modality to enhance the prompt intensity. At the same time, this invention compares the number of prompts with the number of remaining characters in the sentence, taking the smaller value as the final number of prompts to avoid prompts exceeding limits or information redundancy. Through differentiated and adaptive prompting methods, this invention can provide precise assistance to users of different levels while adhering to the principle of minimal intervention, maximizing the stimulation of autonomous recall ability and improving learning efficiency.

[0020] 3. This invention can classify prompt characters into single elements and combined elements based on a dynamic set of poetry prompts, accurately extract corresponding image elements from dynamic videos, remove irrelevant backgrounds, and reduce visual interference. For static elements, single-frame highlighting and alternating light and dark prompts are used; for action elements, corresponding video clips are extracted, and guiding lines are generated by recognizing the center coordinates of elements in the first and last frames to clarify the character order and movement direction, preventing users from confusing the recitation order due to changes in the screen. Finally, the prompt fragments are spliced ​​together according to the order of the poem text to form a visual modal or fused modal display data, making the prompt content highly consistent with the semantics of the poem, intuitive, orderly, and understandable, thereby enhancing the fun and learning effect of reciting ancient poems. Attached Figure Description

[0021] Figure 1 A flowchart of a smart companion device control method provided by the present invention; Figure 2 A schematic diagram of a static display frame provided by the present invention; Figure 3 A schematic diagram of a guide line provided by the present invention; Figure 4 This is a schematic diagram of the structure of a smart companion device control device provided by the present invention; Figure 5 This is a schematic diagram of the hardware structure of an electronic device provided by the present invention. Detailed Implementation

[0022] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0023] like Figure 1 As shown, the present invention provides a control method for an intelligent companion device, comprising: S1, responds to the user's interface operation commands by traversing the database to determine the dynamic prompt set.

[0024] It should be noted that as an interactive learning tool for home and educational scenarios, intelligent companion devices usually perform functions such as poetry reading aloud, following reading, and recitation prompts. For example, during the process of independent poetry recitation by users, situations such as temporary forgetting, long-term pauses, and weak memory often occur. The device needs to give appropriate prompts according to the real-time recitation status, which should not only help users complete the recitation smoothly but also avoid over-prompts leading to memory dependence, so as to achieve true intelligent companionship and efficient learning. Since there are a large number of ancient poems, and the starting words in the first sentences of different ancient poems may be the same, in order to prevent the phenomenon that the ancient poem determined by the device according to the characters recited by the user first is inconsistent with the actual ancient poem that the user needs to recite. For example, when the ancient poem that the user actually wants to recite is "Autumn Wind Ode", but when reciting the two characters "autumn wind", it is easy to have multiple or mis-identify the recited poem as "Autumn Equinox Ode". Therefore, it is possible to preferentially receive the interface operation instruction for the user to select a poem, and then determine the poem display video corresponding to the corresponding poem in the database through the user's selection operation of the recited poem, so as to customize and generate the display of the prompt data according to the user's recitation situation later.

[0025] It can be understood that the interface operation instruction is the operation instruction information for poem selection on the device interface, the database is a database containing a large amount of information, such as a database containing poems and related video information, and the dynamic prompt set is the video data corresponding to the interactive content. For example, it can be a dynamic display video related to the whole poem, and it can be pre-set.

[0026] S2, determine the starting character of the prompt statement based on the interactive stagnant character, and obtain the prompt evaluation data according to the memory proficiency of the interactive statement and the starting character of the prompt.

[0027] It should be noted that since the position of the pause and forgetting during the user's poetry recitation cannot be accurately predicted in advance, it is necessary to determine the user's pause position in real time according to the user's recitation situation. Moreover, since the recitation situations of each user are different, the number of characters and the starting characters that need to be prompted with information are also inconsistent. Therefore, the characters that need to be prompted for the user can be determined according to the text characters where the user actually pauses, and the display data can be generated according to the prompt characters, so as to accurately prompt the user to continue reciting while strengthening the user's memory of the recited content.

[0028] Understandably, when a user remains stuck in the same position for an extended period, their memory and cognitive focus shrink to a very small area. To reduce user dependency, the starting character for subsequent prompts can be determined based on the historical number of prompts corresponding to the paused character. This enhances user memory and comprehension while providing information. Furthermore, since different users have varying levels of proficiency in reciting poetry—for example, some users have strong memories while others have weaker grasp of classical poems—this invention can also determine different data display methods based on different levels of memory proficiency. These methods could include visual displays or a combination of visual and audio prompts to provide recitation guidance to users.

[0029] Among them, the interactive pause character is the character at the position of forgetting pause when the user interacts with the device by voice; the prompt start character is the character at the starting position of the information prompt to the user; the interactive sentence is the content of the sentence spoken by the user; the memory proficiency is the degree of proficiency in voice interaction, such as the degree of proficiency in memorizing poems; and the prompt evaluation data is the data after evaluating the information prompt to the user, including the number of prompt characters and the modality of prompt elements.

[0030] In some embodiments, a specific implementation of step S2 (determining the prompt start character of the prompt statement based on the interactive pause character) includes: S21, record the recording time of each interactive character in the interactive statement, and obtain the interruption duration based on the current time and the recording time.

[0031] It is understandable that the pauses when users recite poems are essentially interruptions in character output. The core criterion for determining these interruptions is the time interval. Only by accurately recording the recording time of each interactive character can the duration of the pause between characters be calculated by comparing it with the current time. This allows us to determine whether the user is pausing during recitation based on the duration of the pause. If the recording time is not recorded, it is impossible to quantify whether the user's pause is normal, such as thinking about a sentence or forgetting something, which can easily lead to misjudgments. That is, normal pauses may be mistaken for pause prompts, or real pauses may be missed. By collecting time-dimensional data, the subjectively perceived pauses can be transformed into objectively quantified duration data, which facilitates the accurate identification of paused interactive characters in the future.

[0032] Among them, the interactive character is the text character corresponding to the interactive sentence, the recording time is the time when the device collects the voice signal corresponding to each interactive character. For example, when reciting the sentence "The Yellow River flows into the sea", the voice recording time of the corresponding interactive character "yellow" is 10:00:01, the recording time of "river" is 10:00:02, the current time is the current time that changes in real time, and the interruption duration is the time difference between the current time and the recording time of the last interactive character in the interactive sentence.

[0033] Through the above embodiments, the present invention can obtain the interruption duration of the interactive statement, avoid the error of manual supervisor judgment, and improve the accuracy of stuttering recognition.

[0034] S22. When it is determined that the interruption duration is greater than the prompt interval duration, compare the interactive statement with the standard text to obtain the pending interactive text, and use the first character of the pending interactive text as the interactive stuttering character.

[0035] It can be understood that the prompt interval duration is preset according to the normal punctuation interval of ordinary users reciting poems, such as 2 seconds. Exceeding this prompt interval duration indicates that the user is not making normal punctuation but experiencing forgetting stuttering. At this time, it is necessary to compare the recited statements of the user with the standard text of the poem, lock the unrecited part, and use the first character of the pending interactive text as the interactive stuttering character to accurately locate the starting position of the user's forgetting.

[0036] Among them, the prompt interval duration is the reference duration for determining whether there is stuttering in recitation, which is preset according to the normal recitation speed of users reciting poems. The standard text is the text corresponding to the interactive content. For example, it can be the complete and correct text of the corresponding poem stored in the database. The pending interactive text is the remaining text content that has not been recited after comparing the interactive statements of the user with the standard text. The interactive stuttering character is the character at the position of the forgetting pause when the user recites, that is, the first character of the pending interactive text.

[0037] S23. Use the statement in the standard text corresponding to the interactive stuttering character as the prompt statement. When it is determined that the historical prompt times of the interactive stuttering character are less than the preset forgetting times, use the interactive stuttering character as the prompt starting character.

[0038] It can be understood that when the historical prompt times of the interactive stuttering character are few, it means that the user has only temporarily forgotten. At this time, directly using the interactive stuttering character as the prompt starting character can accurately prompt the current forgetting point. At the same time, using the complete statement corresponding to the interactive stuttering character as the prompt statement limits the prompt range, that is, only for the forgotten statement segment, avoiding the prompt range being too large, such as the entire poem, resulting in redundant final prompt information and affecting the user's memory of the poem.

[0039] Among them, the prompt statement is the complete statement in the standard text that contains the interactive stuttering character. For example, when the interactive stuttering character is "Ru", the corresponding prompt statement is "The Yellow River flows into the sea". The historical prompt times are the number of times the same interactive stuttering character in the recited poem has been prompted in the historical recitation process. The preset forgetting times are the reference values preset to determine the degree of forgetting.

[0040] Through the above implementation methods, the present invention can use the statement corresponding to the interactive pause character as a prompt statement, prompting only the forgotten statement without interfering with the content already mastered by the user. In cases where the number of historical prompts is low, the interactive pause character can be used as the prompt starting character, enabling the user to accurately determine the prompt character when temporarily forgetting, so that the user can quickly and fluently memorize the remaining content.

[0041] S24, when it is determined that the number of historical prompts is greater than or equal to the preset number of forgettings, the forgetting difference is obtained based on the difference between the number of historical prompts and the preset number of forgettings, and the forgetting coefficient is calculated by comparing the forgetting difference with the preset number of forgettings.

[0042] Understandably, when the number of historical prompts is greater than or equal to the preset number of forgettings, it indicates that the user has a weak long-term memory of the interactive pause character or relies on the prompt. If the interactive pause character is still used as the starting character for the prompt, the brain will develop a waiting-to-be-awakened inertia, and the user will continue to repeatedly pause and rely on the prompt. Therefore, this invention can calculate the user's forgetting coefficient and determine the number of interval characters so as to skip the current interactive pause character for information prompts and move the prompt point to the back. In effect, it cuts off the direct clues that the user originally relied on. The more effort it takes to recall something, the deeper the memory. By increasing the number of intervals, the user's brain is forced to try to fill in the missing characters in the middle after seeing the prompt characters. This helps the user build associative memory instead of memorizing the order of individual text characters. This allows the user to deduce the previous text from the subsequent text even if they cannot remember a word in the middle, thus improving the robustness of memory.

[0043] Among them, the forgetting difference is the numerical difference between the number of historical prompts and the preset number of forgettings, and the forgetting coefficient is a numerical value representing the degree of forgetting, that is, the ratio of the forgetting difference to the preset number of forgettings.

[0044] S25, based on the product of the forgetting coefficient and the number of forgotten characters, the number of interval characters is obtained, and the prompting start character of the prompt statement is determined based on the number of interval characters and the interactive pause character.

[0045] Understandably, the number of forgotten characters is the baseline interval character count, which can be preset, such as 1. The interval character count is the difference in the number of characters between the prompt start character and the interactive pause character, that is, the product of the forgetting coefficient and the number of forgotten characters. When the product of the forgetting coefficient and the number of forgotten characters is not an integer, the calculated value is rounded up to obtain the interval character count.

[0046] Through the above implementation methods, the present invention can dynamically determine the starting character of the prompt based on the historical number of times the interactive pause character has been prompted, that is, adjust the starting point of the prompt according to the user's weak memory, thereby enhancing the effectiveness of the prompt while strengthening the user's memory.

[0047] In some embodiments, a specific implementation of step S25 (determining the prompt start character of the prompt statement based on the number of interval characters and the interactive pause character) includes: S251, count the number of uninteractive characters in the prompt statement to obtain the remaining number, and when it is determined that the number of interval characters is greater than or equal to the remaining number, multiply the forgetting coefficient by the prompt interval duration to obtain the extended interval duration, and add the extended interval duration to the prompt interval duration to obtain the first interval duration.

[0048] Understandably, when the number of characters in the interval is greater than or equal to the total number of characters that have not yet been memorized in the prompt statement, it means that if the prompt starting character is moved forward according to the original rules, it will directly exceed the range of the current prompt statement. In order to avoid abnormal situations such as having no characters to prompt or not being able to memorize the next uninterrupted statement, thus losing the meaning of the prompt, and in order not to undermine the design purpose of forced recall and reducing dependence, this step does not forcibly move the prompt starting point, but instead extends the pause judgment time, giving users more time to recall on their own. In the case of no characters to skip, extending the waiting time stimulates the user's memory potential, maintains the training intensity, and strengthens memory ability.

[0049] The remaining quantity is the total number of characters that the user has not yet memorized in the prompt statement; the extended interval duration is the additional waiting time added on top of the original prompt interval duration; and the first interval duration is the final extended total duration for determining lag.

[0050] Through the above implementation methods, the present invention can avoid the prompt points from exceeding the scope of the prompt statement due to excessively large intervals of characters, ensure that the prompt logic is always effective, and extend the duration is positively correlated with the forgetting coefficient. The weaker the memory, the longer the recall time is set for the user. Instead of directly downgrading the prompt, the waiting time is extended to force the user to recall on their own and strengthen the memory effect.

[0051] S252, when it is determined that the duration of the interruption is greater than the duration of the first interval, the interactive pause character is used as the prompt start character.

[0052] Understandably, if a user still experiences lag or is unable to recall information within the extended waiting time, it indicates that the user is genuinely unable to complete the memorization independently. Forcing the movement of the prompt point is then pointless. In this case, reverting to using the interactive pause character as the starting prompt character ensures that the user can continue the memorization process while minimizing reliance on prompts due to the extended waiting time, thus balancing fluency and memorization effectiveness.

[0053] It's easy to understand that when the interval duration is less than or equal to the first interval duration, it means that the user has already memorized the poem within the extended time period. Therefore, there is no need to determine the prompt position to provide content prompts; it is sufficient to continue monitoring the forgetting of the next character.

[0054] S253, when it is determined that the number of interval characters is less than the remaining number, the number of interval characters is moved sequentially from the starting character of the interactive pause character to the corresponding character as the prompt starting character.

[0055] Understandably, when the number of characters between the intervals is less than the remaining number, it means there are still enough uninterrupted characters in the prompt to safely move the starting character of the prompt forward without going out of bounds. Starting from the character where interaction stalls, the prompt moves sequentially to the position corresponding to the number of characters between the intervals, and uses the character at that position as the new starting character of the prompt. This breaks the user's reliance on the prompt at the original stuttering point, forcing the user to reverse the deduction and fill in the missing content in the middle, thereby establishing a more solid semantic memory link, rather than mechanical rote memorization. By increasing the number of characters between the intervals, the difficulty of memory retrieval is increased, allowing users to learn to make logical deductions when information is incomplete, so as to enhance the long-term mastery of the stubborn forgotten points of ancient poems.

[0056] Sequential movement refers to skipping a specified number of characters backward in the standard text sequence of the prompt statement, starting from the position of the interactive pause character and following the text arrangement direction.

[0057] In some embodiments, a specific implementation of step S2 (obtaining prompt evaluation data based on the memorization proficiency of the interactive statement and the prompt starting character) includes: S26, compare the audio of the interactive statement with the standard audio to obtain the clarity coefficient.

[0058] Understandably, when users have a vague memory of poems, their pronunciation is often accompanied by slurred and unclear pronunciation. In order to objectively evaluate users' recitation performance, it is necessary to first quantify the voice quality by comparing the audio of the sentences actually recited by the user with the standard audio in the database and calculating the clarity coefficient from dimensions such as pronunciation accuracy, volume, and continuity. This is used to make a comprehensive judgment on the proficiency of the memory in the future, and avoid misjudgment of proficiency due to voice quality issues.

[0059] Among them, the speech audio is the voice data of real-time interaction of users collected by the device, such as the voice data of reciting poems. The standard audio is the audio with clear and standard pronunciation that is pre-stored in the database, such as the audio of the demonstration reading of poems in the database. The clarity coefficient is a value used to quantify the clarity and standard of the user's recitation. The higher the coefficient, the clearer and more standard the pronunciation.

[0060] S27, compare the audio of the statement with the character order of the standard audio to obtain the number of correctly memorized characters, and obtain the accuracy coefficient based on the ratio of the number of correctly memorized characters to the number of standard characters in the standard audio.

[0061] Understandably, the core of memory proficiency is whether the user accurately remembers the content and order of the poem, rather than simply whether they pronounce it. Since the spoken characters match the sentences when the user recites the poem, but the order of the recited characters is disordered, it can also reflect that the user's memory proficiency is not high. By comparing the user's audio of the sentence word by word and in order with the standard audio word by word, counting the number of correctly recited characters, and then calculating the ratio with the total number of standard characters in the poem, the accuracy coefficient is obtained. The accuracy coefficient directly reflects the accuracy of the user's memory of the poem content.

[0062] Among them, the number of correctly memorized characters is the total number of characters whose order and wording are correct after comparing the content memorized by the user with the standard text word by word; the number of standard characters is the total number of characters contained in the current standard audio or standard text of the poem; and the accuracy coefficient is the ratio of the number of correctly memorized characters to the number of standard characters. The higher the coefficient, the more accurate the memorization.

[0063] S28. Based on the clarity coefficient and the accuracy coefficient, the memorization proficiency of the interactive statement is obtained.

[0064] Understandably, a single dimension cannot fully reflect a user's true memory level. For example, clear pronunciation but incorrect content, or correct content but unclear pronunciation, cannot be judged as proficient. Combining speech quality with content accuracy and comprehensively calculating memory proficiency can more comprehensively and realistically reflect the user's mastery of the current poem, so that accurate intelligent prompts can be provided later.

[0065] Among them, the memory proficiency is a total score obtained by combining pronunciation clarity and content accuracy, which is the sum of the clarity coefficient and the accuracy coefficient.

[0066] Through the above implementation methods, the present invention can obtain the user's memory proficiency, so as to determine the prompting method that is suitable for the user.

[0067] S29, obtain the prompt evaluation data based on the memory proficiency and the remaining quantity corresponding to the prompt starting character.

[0068] It is understandable that users with different levels of proficiency require different numbers of prompts and different prompting methods. Proficient users only need a few prompts, while less proficient users need more prompts. At the same time, the number of prompts cannot exceed the number of remaining unmemorized characters in the current sentence, otherwise an out-of-bounds prompt will occur. Therefore, based on the user's proficiency and the remaining number of characters, prompt evaluation data containing the number of prompt characters and the modality of prompt elements is generated to achieve adaptive control of prompt intensity and method.

[0069] In some embodiments, a specific implementation of step S29 (obtaining the prompt evaluation data based on the memory proficiency and the remaining quantity corresponding to the prompt starting character) includes: S291, based on the memory proficiency, the preset prompt table is traversed and compared to obtain the initial number of prompts and the prompt element modality, the prompt element modality including the screen modality and the fusion modality.

[0070] It is understandable that the number of prompt characters and the amount of prompt information correspond to different levels of memory proficiency. For example, users with high memory proficiency require fewer prompt characters and only visual prompts, while users with low memory proficiency require more prompt characters and may need to provide text prompts in addition to displaying visual content, possibly using a combination of visual and audio prompts. This allows for automatic adjustment of the prompting method based on different users' memory levels, achieving customized information prompts, improving prompting effectiveness, and increasing user memorability.

[0071] The preset prompt table is a pre-set reference table with memory proficiency and corresponding prompt evaluation data. For example, it can include the initial number of prompts and prompt element modality corresponding to the memory proficiency range. The initial number of prompts is the number of characters suggested for prompting based on the proficiency level. The prompt element modality is the display format of the prompt data, including the visual modality and the fusion modality. The visual modality is the form of visual prompts that are only provided through the mechanical visual function of the screen, and the fusion modality is the data form of simultaneous visual and voice prompts.

[0072] S292, the initial number of prompts is compared with the remaining number, and the smaller value is selected as the number of prompt characters. The prompt evaluation data includes the number of prompt characters and the prompt element modality.

[0073] Understandably, the initial number of prompts is a suggested value based on proficiency, but it may exceed the number of characters remaining in the current sentence that have not been memorized, causing the prompts to go out of bounds. Therefore, the smaller value between the initial number of prompts and the remaining number is taken as the final number of prompt characters. This ensures that the prompt information does not extend to the next sentence, ensuring the accuracy of the prompts. In other words, it prevents the prompt characters from covering up too much content that the user may memorize on their own later, achieving the principle of minimal intervention and ensuring the conciseness of the prompt data and the legality and validity of the prompt range.

[0074] The number of prompt characters refers to the final, actual number of characters displayed to the user.

[0075] S3, based on the number of prompt characters and the prompt element modality in the prompt evaluation data, perform element modality customization processing on the dynamic frames of the dynamic prompt set to obtain display data.

[0076] Understandably, after determining the starting character, number of prompt characters, and modality of prompt elements, it is necessary to generate intuitively perceptible visual or audio-visual content based on the dynamic prompt set. Since the dynamic prompt set contains complete dynamic video frames corresponding to the poems, direct playback would result in information redundancy, affecting the user's ability to quickly connect and memorize pauses. Therefore, it is necessary to filter, retain, delete, and combine elements in the dynamic frames based on the prompt evaluation data, so as to only prompt the content of the prompt and only display the elements that should be displayed, thus assisting memorization without interfering with the user's memory and achieving the goal of accurate prompting.

[0077] Among them, dynamic frames are each image frame in the dynamic video, and display data is the data that is finally output to the user for display prompts, such as video footage or a video that combines video and audio playing simultaneously.

[0078] Through the above implementation methods, the present invention can generate corresponding prompt display data in a targeted manner according to the user's actual memorization situation, improve the accuracy of the prompt content, and provide differentiated display formats for users with different memory levels, so as to enhance the user's memory.

[0079] In some embodiments, a specific implementation of step S3 (customizing the element modality of the dynamic frame of the dynamic prompt set according to the number of prompt characters and the prompt element modality in the prompt evaluation data to obtain display data) includes: S31, based on the prompt start character and the number of prompt characters, the prompt character is obtained, and the prompt character that is the same as the character in the preset combination character set corresponding to the prompt statement is used as the combination label character.

[0080] It can be understood that the prompt characters are the core content to be presented to the user. However, some characters in the poem are suitable for individual prompting, while some characters such as words and fixed imagery are suitable for group prompting. To distinguish these two situations, first determine the characters for this prompt based on the prompt start character and the number of prompt characters, then match them with the preset combined character set, and mark the characters belonging to phrases and fixed collocations as combined label characters, which is convenient for subsequent grouping to generate prompt elements.

[0081] Among them, the prompt characters are the corresponding text characters for which information needs to be prompted, that is, starting from the prompt start character, several consecutive characters to be prompted. The preset combined character set is a set of characters that cannot directly extract the corresponding elements from the dynamic frame, and can be a pre-set character set suitable for group prompting, such as "into" and "flow" in "The Yellow River flows into the sea". The combined label characters are the characters that need to be displayed as elements through combination, that is, the characters in the prompt characters that are the same as the preset combined character set. For example, when the preset combined character set contains "yellow", "into", and "flow", and the prompt character is "flows into the sea", the corresponding combined label characters are "into" and "flow". Since "into" and "flow" cannot directly extract the corresponding entity elements for display, the meaning corresponding to the prompt character needs to be displayed by means of semantics in the corresponding statement with the help of other elements.

[0082] It is worth mentioning that the characters in the preset combined character set are determined by the词性 of the characters, that is, prepositions, conjunctions, special nouns (i.e., spatial orientation words), verbs, etc. in ancient Chinese poems, which are element characters that cannot directly perform image element extraction on video frames. It is necessary to first merge and divide the characters in the statement, so that the corresponding characters can be added with combined labels, so that when comparing the prompt characters, it can be recognized whether the prompt character needs to be visualized with the help of other image elements.

[0083] S32. Delete the characters in the prompt characters that are the same as those in the prompt character group corresponding to the combined label characters, and use the remaining prompt characters as single prompt elements. <000,0228> It should be noted that the term "词性" in the original text is not accurately translated as there is no exact equivalent in English. It is more accurately described as "word class" or "syntactic category", but for the purpose of following the rules, the original term is retained. Also, the tag <000,0228> in the original seems to have a comma which might be an error, and it is translated as

[0084] as per the rule to preserve the 7 - digit tag exactly as - is.It can be understood that the combined label characters have been incorporated into the combined prompts. To avoid duplicate prompts and information confusion, the characters that have been incorporated into the combination need to be removed from the total prompt characters. The remaining characters that cannot be grouped are displayed separately as single prompt elements, ensuring that each character is prompted only once in one form. For example, when the prompt character is "flow into the sea", since "into" and "flow" are combined label characters and the corresponding prompt character group is "the Yellow River flows into the sea", the "flow into the sea" in the prompt characters needs to be deleted to avoid multiple displays of the "sea" element. After de-duplicating the characters, if there are still prompt characters in the prompt characters, it means that the character can be used to extract the image element from the dynamic frame for display separately. Therefore, the remaining prompt characters can be used as single prompt elements. If there are no remaining prompt characters, it means that the number of single prompt elements is 0.

[0085] Among them, the prompt character group is determined in advance according to the characters in the preset combined character set, that is, the character group obtained by dividing and combining the characters in the statement with the corresponding characters. For example, "into" and "flow" cannot be directly used for element display, so the set prompt character group can be "the Yellow River flows into the sea". "Before", "bright", and "light" in "Before my bed a pool of light" may not be directly used for element prompts in a single video frame in the dynamic prompt set. Therefore, the entity elements in the corresponding statement such as "bed" and "moon" can be used for meaning display prompts, and the obtained prompt character groups are "before the bed", "bright moon", and "moonlight", and the single prompt element is the character that can be used for separate element prompts, such as "bed".

[0086] S33. Use the combined label characters corresponding to the prompt character group as combined prompt elements, and obtain prompt elements according to the single prompt elements and the combined prompt elements.

[0087] It can be understood that the combined prompt element is the combined character element corresponding to the prompt character group, and the prompt element is the display element corresponding to the character for information prompt, including single prompt elements and combined prompt elements.

[0088] S34. Perform element modality customization processing on the dynamic frame based on the prompt element and the prompt element modality to obtain display data.

[0089] It can be understood that different prompt elements are suitable for different display forms, and different prompt modalities correspond to different user proficiencies. Therefore, the original dynamic frames in the dynamic prompt set can be processed according to the prompt element content and the prompt modality, screening, retaining, and highlighting the images related to the prompt characters, deleting irrelevant content, and finally generating display data that can be directly played.

[0090] Through the above implementation manners, the present invention can obtain display data, making the display content highly conform to the prompt requirements, only displaying useful information, and supporting multi-modal customization, adapting to different learning habits, and improving the accuracy of the displayed information.

[0091] In some embodiments, a specific implementation of step S34 (the element modality customization processing of the dynamic frame based on the prompt element and the prompt element modality to obtain display data) includes: S341, obtain the element type of the prompt element based on the attributes of the prompt element, and obtain the prompt data of each prompt element according to the element type.

[0092] Understandably, since different prompt elements correspond to different image features in the dynamic prompt set—for example, some correspond to static images like the sun and moon, while others correspond to dynamic actions like flowing or falling—the element type of a prompt element can be determined based on its corresponding attributes. These attributes can be based on the part-of-speech tag of the characters in the prompt element or on the characteristics of the image displayed in the dynamic prompt set. This allows for the generation of corresponding prompt data based on the element type, providing users with clearer and more intuitive information prompts and improving their speed of character recall.

[0093] Among them, the element type refers to the display type of the prompt element, including static type and dynamic type, and the prompt data refers to the visual prompt content generated according to the element type, including static prompt data and dynamic prompt data.

[0094] In some embodiments, a specific implementation of step S341 (obtaining the element type of the prompt element based on its attributes, and obtaining the prompt data of each prompt element according to the element type) includes: S3411, when the element type is determined to be a static element, a dynamic frame containing the static element is selected from the dynamic prompt set to obtain the frame to be displayed.

[0095] Understandably, static elements correspond to fixed and unchanging images. There is no need to play the entire video; it is sufficient to find a single frame containing the static image within the dynamic prompt set. This reduces resource consumption and makes the prompt information clearer and more intuitive.

[0096] Among them, static elements are prompt elements corresponding to fixed scenery and objects, and the frames to be displayed are single frames selected from the dynamic prompt set that contain static elements.

[0097] S3412, the image elements corresponding to the static elements in the frame to be displayed are retained as elements, and the remaining image elements are deleted to obtain a static display frame.

[0098] Understandably, the complex background of the original dynamic frame can distract the user. By retaining only the elements related to the prompt characters and removing irrelevant backgrounds and people, the focus of the prompt can be greatly highlighted, visual interference can be reduced, and the prompt content can be understood by the user at a glance, making the prompt content more intuitive and clear.

[0099] Among them, the reserved elements are the image regions in the frame to be displayed that correspond to the semantics of the static elements, such as... Figure 2 As shown, when a dynamic frame contains multiple image elements such as a bed, a house, a person, and a bright moon, and the element to be retained is the moon, the remaining image elements are deleted to obtain a static display frame. The static display frame is a single frame that has been processed to retain the core prompt image.

[0100] S3413, Based on the single-element prompt duration, the reserved elements are displayed alternately in bright and dark to obtain static prompt data.

[0101] Understandably, in order to draw users' attention to static prompts, the retained elements are displayed using alternating light and dark methods to enhance the sense of prompting, and the prompts are made to loop within the set single-element prompt duration to enhance the prompting effect.

[0102] Among them, the single-element prompt duration is the pre-set display time for each element, the alternating light and dark display is to retain the periodic changes in element brightness to highlight the prompt, and the static prompt data is the prompt data corresponding to static elements.

[0103] S3414, when the element type is determined to be a dynamic element, the dynamic prompt set is segmented into video segments according to the dynamic element and the single element prompt duration to obtain the video segment to be displayed.

[0104] Understandably, dynamic elements correspond to semantics of action, change, and process, such as "flow," "go," and "fall." A single static image cannot express these meanings. Therefore, a short animation is extracted based on the semantics and display duration to make the prompts more intuitive.

[0105] It's easy to understand that when the element type is dynamic, it may correspond to combined prompt elements, resulting in a larger number of characters. Therefore, the duration of the video segment can be calculated by multiplying the number of combined prompt elements by the number of single-element prompts to obtain the total clipping duration. The dynamic prompt set is then clipped so that the data displayed later is not compressed due to the presence of many elements, thus affecting the user's viewing experience.

[0106] Among them, dynamic elements are prompt elements that represent actions, changes, and trends, and the video segments to be displayed are short animation clips extracted from the dynamic prompt set.

[0107] S3415, based on the character semantics of the dynamic element, the image elements related to the dynamic element are retained as elements.

[0108] It is understandable that there may still be irrelevant content in dynamic videos. It is necessary to lock the core action images based on the semantics of the characters and only keep the parts related to the prompts to ensure that the image elements in the dynamic prompt data are not cluttered. For example, when the dynamic element is ocean current, the image areas corresponding to the ocean element in each video frame of the captured video segment can be kept, and the rest of irrelevant elements such as the Yellow River, sky, and trees can be deleted to avoid too many elements affecting the user's attention.

[0109] S3416, Generate dynamic prompt data based on the video segment to be displayed and the reserved elements, wherein the prompt data includes static prompt data and dynamic prompt data.

[0110] Understandably, image elements in each video frame of the video segment to be displayed are deleted based on the retained elements. When there are many characters and a large number of elements are displayed, in order to prevent users from getting the order of the characters they are memorizing wrong while watching the video data with prompts, for example, the dynamic prompt data is a video of the Yellow River flowing into the sea, but users may think that the sea is before the Yellow River, which will interfere with the user's memorization order. Therefore, in order to provide users with accurate character information prompts, the order of elements in the video segment to be displayed can be guided.

[0111] Among them, dynamic prompt data refers to prompt data corresponding to dynamic element types, which can be videos with guide icons.

[0112] In some embodiments, a specific implementation of step S3416 (generating dynamic prompt data based on the video segment to be displayed and the reserved element) includes: S34161, when the number of elements to be retained is determined to be 1, the first dynamic frame in the video segment to be displayed is taken as the first dynamic frame, and the last dynamic frame is taken as the second dynamic frame.

[0113] Understandably, when there is only one element to be retained, in order to make it clear to users the movement trend and change process of the element in the video, and to avoid users being unable to grasp the direction of the prompt due to changes in the dynamic screen, it is necessary to use the first frame and the last frame of the video segment to be displayed as the first dynamic frame and the second dynamic frame, respectively. By comparing the positional changes of the retained element in the first and last frames, the direction of the prompt can be determined, ensuring that users can accurately understand the semantic order of the characters based on the changes in the screen, and not confuse the order of memorization.

[0114] Among them, the reserved quantity is the quantity corresponding to the reserved element. For example, when the character corresponding to the dynamic element is "君不见", the corresponding reserved element is the person in the video frame, and the reserved element is 1. When the character corresponding to the dynamic element is "黄河入海流", the reserved element can be the one containing the Yellow River and the sea, and the corresponding reserved element is 2. The first dynamic frame is the first frame of the video segment to be displayed, and the second dynamic frame is the last frame of the video segment to be displayed.

[0115] S34162, identify the first element center coordinates of the reserved element in the first dynamic frame and the second element center coordinates in the second dynamic frame, and obtain the guiding indication direction according to the first element center coordinates and the second element center coordinates.

[0116] It can be understood that in order to prevent users from confusing the character recitation order when watching the dynamic prompt screen, it is necessary to guide the users through the visual direction. By identifying the center coordinates of the reserved element in the first and last dynamic frames, the moving path and pointing direction of the element in the video can be accurately determined, and this direction is used as the guiding indication direction, enabling the users to clearly understand the recitation order and the character change logic according to the screen indication, and preventing the order from being disordered.

[0117] Among them, the first element center coordinates are the center position coordinates of the reserved element in the first dynamic frame, the second element center coordinates are the center position coordinates of the reserved element in the second dynamic frame, and the guiding indication direction is the pointing direction for prompting the order, which can be obtained by comparing the first and last coordinates.

[0118] S34163, generate a guiding indication line according to the guiding indication direction and the element center points of the reserved element in each dynamic frame, and obtain the dynamic prompt screen data.

[0119] It can be understood that by superimposing the guiding indication line on the video screen, running through all dynamic frames along the movement path of the reserved element, users can clearly understand the change process and recitation order corresponding to the characters along the indication line when watching the prompt screen, which not only prompts the semantics but also standardizes the order, avoiding interference caused by the prompt screen.

[0120] Among them, the element center point is the center position point of the reserved element in each dynamic frame, the guiding indication line is a visual indication line generated according to the center of the reserved element and the guiding direction, and the dynamic prompt screen data is the prompt video data corresponding to the dynamic element.

[0121] S34164, when it is determined that the reserved quantity of the reserved element is greater than 1, connect the element center points of the reserved element in sequence according to the text order of the reserved element to generate a guiding indication line, and obtain the dynamic prompt data.

[0122] It can be understood that when the prompt content contains multiple reserved elements such as multi-character prompts, users are prone to confusing the order of multiple elements. Therefore, according to the recitation order of the poem text, the center points of each reserved element are sequentially connected to form a guiding indication line, enabling users to clarify the sequential relationship of characters along the direction of the indication line, achieving sequential prompts under multiple elements and multi-characters, and ensuring that the recitation logic is consistent with the visual prompt. For example, as Figure 3 shown, when the corresponding prompt character is "enter" in "The Yellow River flows into the sea", the relevant Yellow River and sea in the sentence can be used as reserved elements, and the center points of the elements corresponding to the Yellow River and the center points of the elements corresponding to the sea are sequentially connected according to the text order to obtain the guiding indication line.

[0123] Among them, the text order is the normal recitation order of the prompt character in the poem sentence.

[0124] S342, Sequentially splice the corresponding prompt data according to the text order of each prompt character in the prompt statement to obtain the visual display data.

[0125] It can be understood that different prompt characters correspond to different prompt data. In order to make the overall display画面与诗词原文顺序一致,需要按照提示语句中的文本顺序将各提示数据依次拼接,形成连贯、有序、符合背诵逻辑的完整画面展示数据,避免画面顺序与文本顺序不一致。

[0126] Among them, the visual display data is the complete visual prompt画面视频 after sequential splicing.

[0127] S343, When it is determined that the prompt element modality is the visual modality, use the visual display data as the display data of the visual modality.

[0128] It can be understood that for users with a relatively high memory proficiency and no need for strong prompts, the prompt can be completed by only showing the画面. To avoid over-reliance on the voice, therefore, when the prompt element modality is the visual modality, directly use the spliced visual display data as the final display data to achieve visual prompts without voice prompts, facilitating users' independent recall, reducing prompt dependence, and enhancing the memory effect.

[0129] S344, When it is determined that the prompt element modality is the fusion modality, associate the standard audio of the prompt character with the corresponding prompt data to obtain the fusion display data.

[0130] It can be understood that for users with a relatively low memory proficiency and serious forgetting, relying solely on visual prompts is insufficient, and synchronous visual and voice prompts are required. Therefore, the standard audio corresponding to the prompt character is associated and combined with the visual prompt data to form the fusion display data with synchronous audio and video, enhancing the prompt intensity and helping users quickly recall the content of the poem. It should be noted that there seems to be some inaccuracies or unclear expressions in the original Chinese text, such as "画面与诗词原文顺序一致" which is not very clear in its description. The above translation tries to make sense based on the overall context.

[0131] Among them, the integrated display data is the prompt data resulting from the combination of visual prompts and voice prompts.

[0132] By implementing the above methods, providing prompts to users with low proficiency through integrated data display can improve the success rate of prompts.

[0133] S345, according to the text order of each prompt character in the prompt statement, the corresponding fusion display data is sequentially concatenated to obtain the fusion modality display data.

[0134] Understandably, to ensure that the prompt order in the fusion mode is consistent with the original text of the poem, the fusion display data corresponding to each character needs to be spliced ​​together in the order of the text to form a complete display data that is integrated with the audiovisual, in the correct order, and with a coherent process, so that the changes in the screen and the standard voice are synchronized, and the most efficient intelligent prompts are achieved.

[0135] See Figure 4 This is a schematic diagram of the structure of a smart companion device control device provided in an embodiment of the present invention. The smart companion device control device includes: The response module is used to traverse the database and determine the dynamic prompt set in response to user interface operation commands.

[0136] The determination module is used to determine the starting character of the prompt statement based on the interactive pause character, and to obtain prompt evaluation data based on the memorization proficiency of the interactive statement and the starting character of the prompt.

[0137] The customization module is used to perform element modality customization processing on the dynamic frames of the dynamic prompt set based on the number of prompt characters and the prompt element modality in the prompt evaluation data, so as to obtain display data.

[0138] See Figure 5 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. The electronic device 50 includes: a processor 51, a memory 52, and a computer program; wherein... The memory 52 is used to store the computer program, and the memory may also be flash memory. The computer program is, for example, an application program or functional module that implements the above method.

[0139] The processor 51 is configured to execute the computer program stored in the memory to implement the various steps performed by the device in the above method. For details, please refer to the relevant descriptions in the preceding method embodiments.

[0140] Alternatively, the memory 52 can be either standalone or integrated with the processor 51.

[0141] When the memory 52 is a device independent of the processor 51, the device may further include: Bus 53 is used to connect the memory 52 and the processor 51.

[0142] The present invention also provides a readable storage medium storing a computer program, which, when executed by a processor, is used to implement the methods provided in the various embodiments described above.

[0143] The readable storage medium can be a computer storage medium or a communication medium. A communication medium includes any medium that facilitates the transfer of computer programs from one location to another. A computer storage medium can be any available medium accessible to a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application-Specific Integrated Circuit (ASIC). Alternatively, the ASIC can be located in a user equipment. Of course, the processor and the readable storage medium can also exist as discrete components in a communication device. The readable storage medium can be a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0144] The present invention also provides a program product including executable instructions stored in a readable storage medium. At least one processor of the device can read the executable instructions from the readable storage medium, and the at least one processor executes the executable instructions to cause the device to implement the methods provided in the various embodiments described above.

[0145] In the embodiments of the above-described device, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0146] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A control method for an intelligent companion device, characterized in that, include: The database is traversed in response to user interface operation commands to determine the dynamic prompt set; The starting character of the prompt statement is determined based on the interactive pause character, and prompt evaluation data is obtained based on the memory proficiency of the interactive statement and the starting character of the prompt. Based on the number of prompt characters and the modality of prompt elements in the prompt evaluation data, the dynamic frames of the dynamic prompt set are processed to customize the element modality, resulting in display data.

2. The method according to claim 1, characterized in that, The method for determining the starting character of a prompt statement based on interactive pause characters includes: Record the recording time of each interactive character in the interactive statement, and obtain the interruption duration based on the current time and the recording time; When the duration of the interruption is determined to be greater than the duration of the prompt interval, the interactive statement is compared with the standard text to obtain the text to be interacted with, and the first character of the text to be interacted with is taken as the interactive pause character; The statement in the standard text corresponding to the interactive pause character is used as a prompt statement. When the number of historical prompts for the interactive pause character is less than the preset number of forgotten characters, the interactive pause character is used as the prompt start character. When it is determined that the number of historical prompts is greater than or equal to the preset number of forgettings, the forgetting difference is obtained based on the difference between the number of historical prompts and the preset number of forgettings, and the forgetting coefficient is calculated by comparing the forgetting difference with the preset number of forgettings. The number of interval characters is obtained by multiplying the forgetting coefficient and the number of forgotten characters, and the starting character of the prompt statement is determined based on the number of interval characters and the interactive pause character.

3. The method according to claim 2, characterized in that, The step of determining the starting character of the prompt statement based on the interval character count and the interactive pause character includes: The number of uninteractive characters in the prompt statement is counted to obtain the remaining number. When the number of characters in the interval is greater than or equal to the remaining number, the forgetting coefficient is multiplied by the prompt interval duration to obtain the extended interval duration, and the extended interval duration is added to the prompt interval duration to obtain the first interval duration. When the duration of the interruption is determined to be greater than the duration of the first interval, the character indicating a pause in the interaction is used as the starting character for the prompt. When the number of characters in the interval is determined to be less than the remaining number, the number of characters in the interval is moved sequentially from the starting character of the interactive pause character to the corresponding character as the prompt starting character.

4. The method according to claim 3, characterized in that, The process of obtaining prompt evaluation data based on the user's familiarity with the interactive statements and the initial character of the prompt includes: The audio of the interactive statement is compared with the standard audio to obtain the clarity coefficient; The audio of the statement is compared with the character order of the standard audio to obtain the number of correctly memorized characters. The accuracy coefficient is obtained based on the ratio of the number of correctly memorized characters to the number of standard characters in the standard audio. The memorization proficiency of the interactive statements is obtained based on the clarity coefficient and the accuracy coefficient. The prompt evaluation data is obtained based on the memory proficiency and the remaining quantity corresponding to the prompt's starting character; The step of obtaining the prompt evaluation data based on the memory proficiency and the remaining quantity corresponding to the prompt's starting character includes: Based on the memory proficiency, the preset prompt table is traversed and compared to obtain the initial number of prompts and the prompt element modality, the prompt element modality including the screen modality and the fusion modality; The initial number of prompts is compared with the remaining number, and the smaller value is selected as the number of prompt characters. The prompt evaluation data includes the number of prompt characters and the prompt element modality.

5. The method according to claim 4, characterized in that, The step involves customizing the element modality of the dynamic frames of the dynamic prompt set based on the number of prompt characters and the prompt element modality in the prompt evaluation data to obtain display data, including: Based on the prompt start character and the number of prompt characters, the prompt characters are obtained, and the prompt characters that are the same as the characters in the preset combination character set corresponding to the prompt statement are used as the combination label characters; Delete the characters in the prompt characters that are the same as those in the prompt character group corresponding to the combined label characters, and treat the remaining prompt characters as a single prompt element; The group of prompt characters corresponding to the combined label characters is used as a combined prompt element, and a prompt element is obtained based on the single prompt element and the combined prompt element; Based on the prompt element and the prompt element modality, the dynamic frame is processed to customize the element modality, and the display data is obtained.

6. The method according to claim 5, characterized in that, The step of customizing the element modality of the dynamic frame based on the prompt element and the prompt element modality to obtain display data includes: The element type of the prompt element is obtained based on its attributes, and the prompt data of each prompt element is obtained based on the element type. The corresponding prompt data is sequentially concatenated according to the text order of each prompt character in the prompt statement to obtain the screen display data; When the modality of the prompt element is determined to be a screen modality, the screen display data is used as the display data for the screen modality; When the modality of the prompt element is determined to be a fusion modality, the standard audio of the prompt character is associated with the corresponding prompt data to obtain fusion display data; The corresponding merged display data is sequentially concatenated according to the text order of each prompt character in the prompt statement to obtain the merged modality display data.

7. The method according to claim 6, characterized in that, The process of determining the element type of a prompt element based on its attributes, and then obtaining prompt data for each prompt element according to the element type, includes: When the element type is determined to be a static element, a dynamic frame containing the static element is selected from the dynamic prompt set to obtain the frame to be displayed; The image elements corresponding to the static elements in the frame to be displayed are retained as elements, and the remaining image elements are deleted to obtain the static display frame. Based on the duration of a single element prompt, the retained elements are displayed alternately in bright and dark to obtain static prompt data; When the element type is determined to be a dynamic element, the dynamic prompt set is segmented into video segments according to the dynamic element and the duration of the single element prompt to obtain the video segment to be displayed. Based on the character semantics of the dynamic elements, the image elements related to the dynamic elements are retained as elements; Dynamic prompt data is generated based on the video segment to be displayed and the reserved elements. The prompt data includes static prompt data and dynamic prompt data.

8. The method according to claim 7, characterized in that, The step of generating dynamic prompt data based on the video segment to be displayed and the reserved elements includes: When the number of elements to be retained is determined to be 1, the first dynamic frame in the video segment to be displayed is taken as the first dynamic frame, and the last dynamic frame is taken as the second dynamic frame. Identify the center coordinates of the first element in the first dynamic frame and the center coordinates of the second element in the second dynamic frame, and obtain the guiding direction based on the center coordinates of the first element and the center coordinates of the second element; Based on the guiding direction and the center point of the element in each dynamic frame, a guiding line is generated to obtain dynamic prompt screen data; When the number of elements to be retained is greater than 1, guide lines are generated by connecting the center points of the elements to be retained in sequence according to the text order of the elements, thus obtaining dynamic prompt data.

9. A control device for an intelligent companion device, characterized in that, include: The response module is used to traverse the database to determine the dynamic prompt set in response to the user's interface operation commands; The determination module is used to determine the prompt start character of the prompt statement based on the interactive pause character, and to obtain prompt evaluation data based on the memorization proficiency of the interactive statement and the prompt start character; The customization module is used to perform element modality customization processing on the dynamic frames of the dynamic prompt set based on the number of prompt characters and the prompt element modality in the prompt evaluation data, so as to obtain display data.

10. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, is used to implement the method described in any one of claims 1 to 8.

Images