Reading and related cognitive ability defect recognition device and method

Abstract

The embodiment of the invention provides a reading and related cognitive ability defect recognition device and method. The device comprises a test content generation module which is used for generating test content for testing the reading capability of a user according to basic information of the user under the condition that the reading capability defect risk of the user is determined, and displaying the test content to the user through an operation interface; the cognitive defect identification module is used for acquiring a response result of the user for the test content, and identifying whether the user has reading and related cognitive ability defects based on the response result; and the defect factor matching module is used for matching the users according to different reading-related cognitive ability defect factors under the condition of determining that the users have reading and related cognitive ability defects, and determining the reading-related cognitive ability defect factors matched with the users. By adopting the mode, whether the user has the reading ability defect or not can be identified, and the essential factors which really cause the reading ability defect of the user can also be identified.

Description

Technical Field

[0001] This application relates to computer technology, and more specifically, to a device and method for identifying reading and related cognitive ability deficiencies. Background Technology

[0002] In existing technologies, reading ability tests typically employ simple tests to identify any deficiencies in reading skills. However, these tests often fail to pinpoint the underlying causes of these deficiencies, thus failing to address the root causes of the reading difficulties. Summary of the Invention

[0003] To address the aforementioned problems, the purpose of this invention is to provide a device and method for identifying reading and related cognitive ability deficiencies.

[0004] In a first aspect, embodiments of the present invention provide a reading and related cognitive ability deficit identification device, comprising:

[0005] The test content generation module is used to generate test content for testing the user's reading ability based on the user's basic information when it is determined that the user has a risk of reading ability deficiency, and to display the test content to the user through the operation interface.

[0006] The cognitive deficit identification module is used to obtain the user's response results to the test content, and to identify whether the user has reading and related cognitive ability deficits based on the response results;

[0007] The defect factor matching module is used to match the user with different reading-related cognitive ability defect factors when it is determined that the user has reading and related cognitive ability defects, and to determine at least one reading-related cognitive ability defect factor matched by the user.

[0008] Secondly, embodiments of the present invention also provide a method for identifying reading and related cognitive ability deficits, including:

[0009] If it is determined that a user has a risk of reading impairment, test content for testing the user's reading ability is generated based on the user's basic information, and the test content is displayed to the user.

[0010] Obtain the user's response to the test content, and identify whether the user has a reading ability deficiency based on the response results;

[0011] If it is determined that a user has a reading ability deficit, the user is matched with different reading-related cognitive ability deficit factors to determine at least one reading-related cognitive ability deficit factor matched with the user.

[0012] In the solution provided by the first aspect of the present invention, it is possible not only to identify whether a user has a reading ability deficiency, but also to identify the actual factors that cause the user to have a reading ability deficiency, namely, reading-related cognitive ability deficiency factors, which is conducive to improving the user's reading ability based on reading-related cognitive ability deficiency factors. Attached Figure Description

[0013] The accompanying drawings, which are provided to further illustrate this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application.

[0014] Figure 1 A flowchart of a reading and related cognitive ability deficit identification method provided by an embodiment of the present invention is shown;

[0015] Figure 2 A flowchart illustrating a test content generation method provided by an embodiment of the present invention is shown;

[0016] Figure 3 This paper illustrates a flowchart of the comparison of Chinese character recognition difficulty in the reading-related cognitive ability deficit factor identification method provided in an embodiment of the present invention;

[0017] Figure 4 A schematic diagram of a test content for testing a user's reading ability provided by an embodiment of the present invention is shown;

[0018] Figure 5 A schematic diagram of a matching object for speech cognitive deficits provided by an embodiment of the present invention is shown;

[0019] Figure 6 This diagram illustrates a matching object for a morpheme cognitive deficiency provided in an embodiment of the present invention.

[0020] Figure 7 This diagram illustrates a matching object for orthography cognitive deficiencies provided by an embodiment of the present invention.

[0021] Figure 8 This diagram illustrates the structure of a reading and related cognitive ability deficit identification device provided in an embodiment of the present invention.

[0022] Figure 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present invention is shown. Detailed Implementation

[0023] To make the technical solutions and advantages of the embodiments of this application clearer, the exemplary embodiments of this application will be described in further detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not an exhaustive list of all embodiments. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be combined with each other.

[0024] In the description of this invention, it should be understood that the terms "vertical," "horizontal," "inner," "outer," "upper," "lower," "front," "rear," "left," "right," "center," "longitudinal," "transverse," "length," "width," and "thickness," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0025] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0026] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0027] Current research on insufficient Chinese reading ability is limited. While some researchers have attempted to assess the reading level of test subjects using self-designed Chinese reading tests and have referenced international standards to determine whether test subjects have reading ability deficits, these studies still have some shortcomings. First, current testing methods are not comprehensive enough, often focusing solely on testing reading ability while neglecting cognitive skills closely related to reading development. In fact, lagging reading ability may stem from multiple factors, and it is necessary to identify the reading-related cognitive ability deficits of test subjects in order to provide targeted improvement for their reading ability. Furthermore, identifying users' reading-related cognitive ability deficits also helps in determining whether users have reading disorders. Unless otherwise specified, "users" in the following text refers to test subjects who have taken reading ability tests.

[0028] like Figure 1 As shown, in response to the aforementioned technical problems, this application provides a method for identifying reading and related cognitive ability deficits, including:

[0029] S101, if it is determined that a user has a risk of reading impairment, generate test content for testing the user's reading ability based on the user's basic information, and display the test content to the user;

[0030] S102, Obtain the user's response to the test content, and identify whether the user has reading and related cognitive ability deficits based on the response results;

[0031] S103, if it is determined that the user has a reading and related cognitive ability deficit, the user is matched for different reading-related cognitive ability deficit factors to determine at least one reading-related cognitive ability deficit factor matched for the user.

[0032] By using the above method to test users' reading ability, it is possible not only to identify whether users have reading ability deficiencies, but also to identify the real reasons that cause these deficiencies, namely, the factors that lead to reading-related cognitive ability deficiencies. This will help to address the problem of insufficient reading ability in the future by identifying these factors.

[0033] In S101 above, the following methods may be used to determine whether a user has a reading ability deficiency risk.

[0034] In one implementation, a semi-structured interview about the user's reading behavior can be conducted online or offline. Specific questions may include: What types of errors do you frequently make while reading? Do you often mispronounce words or confuse word forms while reading? How do you feel about your reading speed? How does it compare to your peers? Do you pause or repeat words in sentences? Are you able to extract key information and understand the main idea of ​​an article? Do you often need to review or ask others to explain what you've read? Have these problems existed since the beginning of your reading journey? How long have they lasted? Have you received any reading training? What is your family's language environment like? If the user's answers confirm that they indeed have most of the above problems, it can be determined that the user is at risk of reading impairment.

[0035] It is understandable that individuals with reading disabilities can be adults or minors. When the test subjects are minors, questionnaires can also be distributed to their parents, who can then describe the child's actual reading ability. In one specific approach, the questionnaire can be designed with 30 questions across eight areas: word recognition, Chinese character writing, composition, oral expression, verbal memory, motivation and attitude, focus, and mathematics. This questionnaire has been tested and found to have good reliability and validity. Each question contains five options, scored as follows: "Never = 1", "Rarely = 2", "Sometimes = 3", "Often = 4", and "Always = 5". A total average score of 2 is used to differentiate between individuals with and without reading disabilities. In other words, having parents complete the questionnaire provides information about the child's usual reading performance; if the parents' total average score is greater than or equal to 2, it indicates a risk of reading disability in the child.

[0036] By employing the above methods, the risk of reading impairment can be determined by combining the user's own interviews with information provided by the user's parents. When conducted offline, the interviews can be conducted face-to-face by relevant testers, who will then distribute paper questionnaires to the user's parents. The testers will manually determine if the user is at risk of reading impairment. When conducted online, the user or their parents can trigger the appropriate testing software. The software will display the interview content and questionnaire to the user or their parents through a user interface. The user or their parents can then complete the interview or questionnaire responses using text or voice input via the input components provided in the interface. The testing software will then determine if the user is at risk of reading impairment based on the interview content or questionnaire results.

[0037] If the above methods determine that the user does not have a reading disability risk, there is no need to execute the subsequent methods. Conversely, if the above methods determine that the user has a reading disability risk, then proceed with the subsequent methods.

[0038] In S101, when generating test content for testing the user's reading ability based on the user's basic information and displaying the test content to the user, specifically, it may involve obtaining a pre-built Chinese character database corresponding to the user's basic information; generating test content for testing the user's reading accuracy and fluency based on the Chinese characters in the obtained Chinese character database, where the basic information may include the user's education level, the user's age, the user's region, etc., and the education level may be the user's highest level of education. The following explanation will use the education level as an example of the basic information.

[0039] When testing users, because different users' reading abilities are related to their education level, users cannot read content composed of Chinese characters they have not learned. Therefore, it is necessary to generate test content based on the users' education level.

[0040] When generating test content based on users' education levels, different Chinese character databases can be pre-built for different educational levels. For example, for those with primary school education as their highest level, separate databases can be created for each grade level, or even for each semester. For instance, one database could be built for first-grade students in the fall semester, and another for first-grade students in the spring semester. Each database would contain characters from the corresponding textbooks for that semester and previous semesters.

[0041] Inaccurate and disjointed reading are the most obvious characteristics of users with reading impairments.

[0042] Therefore, when generating test content to test users' reading ability, the specific test content generated is to test users' reading accuracy and reading fluency.

[0043] When generating test content to test the accuracy of a user's reading, a portion of Chinese characters can be randomly selected from a pre-built Chinese character database corresponding to the user's education level, for example, 150 Chinese characters can be randomly selected and displayed to the user, who can then read each character individually.

[0044] When generating test content to assess a user's reading fluency, one could randomly select characters from a pre-built Chinese character database corresponding to the user's education level, assemble them into words, for example, randomly select 300 characters, form words, and display them to the user, who would then read each word aloud. This generates test content to assess the user's fluency in reading words.

[0045] In addition, when generating test content to test a user's reading fluency, a portion of Chinese characters can be randomly selected from a pre-built Chinese character database corresponding to the user's education level. For example, 300 Chinese characters can be randomly selected, and the user can read each Chinese character separately to generate test content to test the user's reading fluency.

[0046] Considering that if the Chinese characters in the test are randomly arranged, and if more difficult characters alternate with easier characters, both users with poor reading skills and those with strong reading skills may not be able to recognize them fluently within the time limit, then the test will not be able to effectively differentiate users' reading abilities. Therefore, to improve the test's discriminatory power, this implementation sorts the Chinese characters from easy to difficult, so as to ensure that test subjects encounter relatively simple characters first within the limited test time, and the difficulty of the characters gradually increases.

[0047] Specifically, in one implementation, all Chinese characters in the pre-built Chinese character database can be divided into at least two difficulty levels according to the recognition difficulty, and at least one Chinese character can be selected from each of the at least two different difficulty levels to form a Chinese character set; the total number of Chinese characters in the Chinese character set is within a preset range.

[0048] The above set of Chinese characters is sorted in order of increasing recognition difficulty.

[0049] When test content needs to be generated, the test content is generated based on the sorted set of Chinese characters mentioned above, in which the Chinese characters in the set are arranged in the order within the set.

[0050] For Chinese characters in a pre-built Chinese character database, they can be divided into at least two difficulty levels based on the difficulty of character recognition (hereinafter, the number of difficulty levels in the character database is denoted as Z, where Z is an integer greater than or equal to 2). Specifically, the characters can be classified according to their frequency in their source. The frequency of a character is closely related to the difficulty of its recognition; the higher the frequency of a character, the more frequently users encounter that character, and the lower the difficulty of recognizing it.

[0051] When classifying Chinese characters according to their frequency, in one example, the frequency of each character in the source text of the pre-built character set is first obtained. All characters are then sorted in ascending (or descending) order of frequency. The sorted characters are then divided into at least two frequency levels, i.e., difficulty levels, at equal intervals. The higher the frequency of the characters in each frequency level, the lower the recognition difficulty of that level. Since the number of characters in each frequency level is an integer, there may be cases where characters cannot be evenly distributed across levels. In such cases, the number of characters in one frequency level (e.g., the last frequency level) can be different from the other frequency levels, prioritizing ensuring that the number of characters in other frequency levels is the same. The number of characters in each frequency level and the total number of frequency levels can be set based on factors such as the total number of characters in the character set and the total number of characters to be selected.

[0052] Taking a character set containing 3682 Chinese characters as an example, assuming it needs to be divided into 20 frequency levels, after sorting the characters from highest to lowest frequency, we can calculate that each level contains an average of 184.1 characters based on 3682 / 20 = 184.1. Since the number of characters in each frequency level is an integer, rounding results in each level containing 184 characters. Therefore, dividing the characters in the character set into frequency levels, levels 1-19 each contain 184 characters, and level 20 contains 186 characters. The difficulty of character recognition increases progressively from frequency level 1 to 20.

[0053] After classifying the Chinese characters in the character set, in one embodiment, at least one character is selected from at least two different difficulty levels to form a character set. This ensures that the test content generated based on this character set includes characters at multiple difficulty levels, progressing from low to high. Furthermore, to ensure good testing results and avoid problems such as too few characters leading to insufficient assessment of user reading fluency, or too many characters resulting in low completion rates for most users within a limited time, the total number of characters in the character set in this embodiment should be within a preset range, such as 100-200 characters, 140-160 characters, or 100 characters. The numerical range can be selected based on past reading fluency tests to determine the range that yields the best testing results.

[0054] In one example, when selecting Chinese characters from various difficulty levels, at least one character can be selected from each difficulty level. Taking the division of Chinese characters in the character set into Z difficulty levels as an example, at least one character can be selected from each difficulty level. For example, the same number of characters (denoted as K, where K is an integer greater than 0) can be selected, resulting in a total of Z×K characters, and Z×K falls within a preset numerical range. In another example, the number of characters selected from each difficulty level can be different. For example, if the number of characters in each difficulty level is different, different numbers of characters can be selected from each difficulty level according to the ratio of the number of characters in each difficulty level.

[0055] Sorting Chinese characters is a crucial step in ensuring the effectiveness of the test. The selected set of characters can be sorted according to at least one sorting rule to arrange them in order of increasing recognition difficulty, allowing users to prioritize recognizing the easier characters in a shorter time. Examples of sorting rules are illustrated below:

[0056] In one embodiment, the sorting rule includes: sorting the Chinese character set in descending order of frequency. Specifically, the sorting can be based on the specific frequency of each Chinese character; or, characters with frequencies within the same numerical range can be considered the same frequency, and sorted according to the numerical interval to which the frequency belongs. For example, characters with frequencies between 500 and 1000 can be considered the same frequency, and characters with frequencies between 1001 and 1500 can be considered the same frequency. In the sorting process, characters with frequencies between 1001 and 1500 are considered higher than those between 500 and 1000. Alternatively, the character frequency levels of the character set can be used as described in the above embodiment, and characters with frequencies within the same frequency level can be considered the same frequency and sorted according to the frequency level.

[0057] In another embodiment, the sorting rule includes: sorting the Chinese character sets according to the age of learning the characters from youngest to oldest. In one example, since Chinese character teaching mainly relies on textbooks, the time when a character appears in the textbook reflects the age at which the character is learned, and related research shows that the younger the age at which characters are learned, the lower the difficulty of recognizing them. Therefore, the sets can be sorted according to the number of textbook volumes in which the character first appears. Here, the number of textbook volumes is negatively correlated with the order in which the textbooks are used and positively correlated with the age at which the character is learned. For example, in a set of 12 elementary school textbooks, the first semester of first grade is volume 1, the second semester of first grade is volume 2, the first semester of second grade is volume 3, and so on. When determining the first appearance number of a Chinese character in a textbook, in one example, for textbooks with a character list, the number of the textbook to which the character list belongs can be used as the first appearance number. For instance, if the same character appears in the character lists of both textbooks 3 and 4, since textbook 3 appears before textbook 4, textbook 3 is used as the first appearance number. Furthermore, for multiple characters recorded in the same character list, they can be sorted according to their order of appearance within the list.

[0058] In another embodiment, the sorting rules include: sorting the Chinese character set according to the difficulty of character recognition as determined by an authoritative institution, from low to high. In one example, the characters can be sorted according to the difficulty of character recognition as defined in the "Compulsory Education Chinese Language Curriculum Standards" issued by the Ministry of Education. The character list attached to the "Compulsory Education Chinese Language Curriculum Standards" includes three sub-lists: "Basic Character List for Character Recognition and Writing Instruction," "Commonly Used Character List for Compulsory Education Chinese Language Curriculum (I)," and "Commonly Used Character List for Compulsory Education Chinese Language Curriculum (II)." The characters in the "Basic Character List for Character Recognition and Writing Instruction" (300 characters in total) are recorded as Level 1 of the syllabus; the characters in the "Commonly Used Character List for Compulsory Education Chinese Language Curriculum (I)" that do not appear in the "Basic Character List for Character Recognition and Writing Instruction" (2200 characters in total) are recorded as Level 2 of the syllabus; and the characters in the "Commonly Used Character List for Compulsory Education Chinese Language Curriculum (II)" that do not appear in the other two sub-lists (1000 characters in total) are recorded as Level 3 of the syllabus. Thus, the difficulty of the characters increases progressively. Therefore, the set of Chinese characters can be sorted according to the difficulty of recognizing the corresponding Chinese characters in the character list, from low to high.

[0059] In another embodiment, the sorting rule includes: sorting the Chinese character set according to the actual recognition level of the characters by similar test subjects from high to low. In one example, the actual recognition level of the characters by similar test subjects is reflected in the actual recognition accuracy rate of the characters by similar test subjects; the higher the actual recognition accuracy rate, the higher the actual recognition level. Specifically, when obtaining the actual recognition accuracy rate of the characters by similar test subjects, the average recognition accuracy rate of a portion of similar test subjects can be collected in advance as the actual recognition accuracy rate through questionnaires, tests, or exercises; when the test subjects are students from multiple grades, a portion of students from each grade can be sampled to collect their recognition accuracy rate for any Chinese character, and then the average recognition accuracy rate of students from each grade can be calculated as the actual recognition accuracy rate. In another example, when the test subjects are students, the actual recognition level of the characters by similar test subjects is reflected in the grade at which similar test subjects first mastered the characters; the lower the grade, the higher the actual recognition level. For the same Chinese character, the students' true recognition accuracy rate may increase with the grade level. When the true recognition accuracy rate reaches a threshold, it can be regarded that the students in that grade have mastered the Chinese character. Therefore, the grade in which the true recognition accuracy rate first reaches the threshold can be regarded as the grade in which the students first mastered the Chinese character.

[0060] The sorting rules in the examples above can be used individually or in combination. In one example, the set of Chinese characters can be first sorted in descending order of frequency. For characters with the same frequency, they can be further sorted in ascending order of the number of textbooks in which they first appear. For characters with the same number of textbooks in which they first appear, they can be further sorted in ascending order of difficulty as defined in the "Compulsory Education Chinese Language Curriculum Standards." In addition to the sorting rules in the examples above, other existing rules (such as the structural complexity of Chinese characters) can also be used to sort the set of Chinese characters in ascending order of recognition difficulty.

[0061] In some embodiments, test content can be generated directly after the Chinese character set is sorted. In other embodiments, the sorted Chinese character set can be stored first, and the test content can be generated later when it is determined that it needs to be generated. For example, before the paper version of the test content needs to be printed, the generation of test content can be triggered based on the input of the staff; or before the electronic version of the test content needs to be tested, the generation of test content can be triggered based on the input of the user, and so on. The following is an example description of how test content is generated based on the sorted Chinese character set.

[0062] In one embodiment, when test content needs to be generated, the sorted Chinese characters can be directly arranged in a specific way and presented as test content for user reading. Preferably, the arrangement can be in matrix form, such as a 15×10 matrix or a 10×10 matrix, and arranged in a way that conforms to domestic reading habits (from left to right, from top to bottom), so that multiple Chinese characters can be read by the user in order of increasing difficulty. Furthermore, in order to reduce the interference between multiple visual targets, which may affect the user's visual judgment and thus their test scores, the Chinese characters can be displayed to the user in a visually sparse manner. When the reading fluency test is conducted on paper, the Chinese characters can be arranged in matrix form on the test paper. In cases where there are many Chinese characters and it is difficult to arrange them on the same page of test paper, the Chinese characters can be arranged into at least two matrices, and each matrix can be printed on a separate test paper. For example, if the set of Chinese characters contains 100 characters, they can be arranged in order into four 5×5 matrices and printed on four separate test papers. When reading fluency testing is conducted electronically, Chinese characters can be arranged in a matrix at designated positions on the electronic testing interface. Furthermore, when there are a large number of Chinese characters that are difficult to arrange on the same interface, the characters can be arranged into at least two matrices and displayed sequentially according to specific triggering conditions (such as manual triggering by the user).

[0063] In reading comprehension testing, it may be necessary to test the same user multiple times in certain situations. For example, when it's necessary to monitor a user's reading ability over time, or when a user's single test result may deviate significantly due to special reasons (such as nervousness), multiple tests can be conducted on the same user, and the results from these multiple tests can be combined to assess the user's reading ability. However, if the same test content or highly similar test content is used for multiple tests on the same user, the practice effect may lead to significant testing bias. Conversely, if the content of each test differs too much, it may also result in significant testing bias.

[0064] In response to the above situation, such as Figure 2 As shown in the embodiments of this application, a method for generating test content is also provided. This method includes at least the following steps:

[0065] Step 201: Select the same number of Chinese characters from the pre-built character set to form a first set of Chinese characters and a second set of Chinese characters. At least some of the Chinese characters in the first set of Chinese characters and the second set of Chinese characters are different.

[0066] In this step, the construction of the font library and the classification of difficulty levels can be referred to the above text.

[0067] When selecting Chinese characters, in one embodiment, characters can be selected sequentially from the character set to form a first set and a second set, for example, first selecting characters to form the first set and then selecting characters to form the second set. In another embodiment, twice the number of characters can be selected from the character set at once and then evenly distributed among the first and second sets, resulting in a first set and a second set with completely different elements. For specific character selection methods in the above embodiments, please refer to the embodiments described above.

[0068] Taking the example that each set of Chinese characters needs to select 100 Chinese characters from the character library, assuming that the character library is divided into 20 difficulty levels, we can first use a random sampling method to select 5 Chinese characters from each difficulty level to form a first set of 100 Chinese characters. Then, we can use the same random sampling method to select 5 Chinese characters from each difficulty level to form a second set of 100 Chinese characters.

[0069] In one embodiment, to ensure that at least some characters in the first and second character sets are different, the two character sets can be compared. If the characters in the two character sets are completely identical, characters can be reselected to recombine one or both character sets, and the comparison operation is returned based on the recombined character sets until at least some characters in the two character sets are different. When selecting characters to recombine character sets, all characters in the character sets can be reselected, or only some characters can be reselected, such as only the characters in the overlapping parts of the two character sets. In another embodiment, an upper limit can be set on the number of identical characters in the two character sets. If the number of identical characters in the two character sets exceeds this upper limit, characters can be reselected to recombine one or both character sets. In yet another embodiment, after selecting characters, the comparison of character sets can be temporarily suspended, and in step 203, it can be determined whether characters in the same position in the two sorted character sets are identical.

[0070] Step 202: Sort the first set of Chinese characters and the second set of Chinese characters in order of increasing recognition difficulty.

[0071] In this step, the specific sorting rules for each set of Chinese characters can be found above. To ensure that the difficulty of the test content generated based on the first and second sets of Chinese characters is as similar as possible, in one embodiment, the first and second sets of Chinese characters can be sorted according to the same sorting rules.

[0072] Step 203: For the sorted first and second sets of Chinese characters, if the difference in recognition difficulty of the Chinese characters in the same position is within a preset range, the first and second sets of Chinese characters are used to generate test content in the future.

[0073] In step 203, it is determined whether the difference in recognition difficulty between Chinese characters at the same position in the first and second Chinese character sets is within a preset range. There are multiple ways to achieve this, and examples are described below.

[0074] In one example, characters at the same position in the first and second character sets can be compared one by one to determine if the difference in recognition difficulty between each character in the first set and the character at the same position in the second set is within a preset range. In another example, the first and second character sets can be divided into multiple character groups at equal intervals, each containing the same number of consecutive characters. The difference in recognition difficulty between each character group in the first set and the character group at the same position in the second set can be determined to be within a preset range. When determining the difference in recognition difficulty, the sum or average recognition difficulty of each character group can be calculated. In yet another example, based on the sliding window concept, sliding windows of the same length can be set for the first and second character sets, and sliding them from the same starting point with the same length. The difference in recognition difficulty of the characters within the window after each sliding is compared to determine if it is within a preset range. Through these embodiments, the recognition difficulty of the two character sets can be compared based on different granularities to adapt to different testing needs.

[0075] When determining the specific difficulty of Chinese character recognition, you can refer to the above method of recognition based on the frequency of Chinese characters. The following example illustrates this by comparing each character in two sets of Chinese characters one by one:

[0076] In one example, the frequency of each character in the first character set and the characters at the same position in the second character set can be compared sequentially. If the difference in the frequency of two characters is within a first range, then the recognition difficulty difference between the two characters at that position is determined to be within a preset range. Alternatively, the frequency can be pre-divided into multiple frequency levels according to numerical values, or if the character library has already been divided into frequency levels, the frequency level can be directly used. If the difference in the frequency levels of two characters is within a second range, then the recognition difficulty difference between the two characters at that position is determined to be within a preset range.

[0077] If, after assessment, the difference in recognition difficulty between any position of a character in the first and second character sets is not within a preset range, then the character at that position in the first and / or second character sets can be adjusted to bring the adjusted recognition difficulty difference within the preset range or reduce the recognition difficulty difference. Alternatively, the process can return to step 201 to reorganize the first and / or second character sets. It should be noted that if a scheme is adopted to adjust the characters in both the first and second character sets at a certain position, the adjusted characters should still maintain the order of difficulty from easiest to hardest with their adjacent characters.

[0078] There are multiple ways to adjust Chinese characters. The following example illustrates how to adjust a single Chinese character at any position in two sets of characters:

[0079] In one example, if two Chinese characters at any position are judged to have a recognition difficulty difference outside the preset range because their frequency difference is outside the first range, then the Chinese character at that position in the first character set (hereinafter referred to as character Y1) can be used as a benchmark. A new Chinese character from the character set whose frequency difference with Y1 falls within the first range can be selected, and this new character replaces the original Chinese character at that position in the second character set. During the reselection, all Chinese characters whose frequency difference with Y1 falls within the first range can be selected first, and then one character can be randomly selected from them. During random selection, Y1 itself can be excluded from the selection range. Furthermore, if no Chinese character in the character set has a frequency difference within the first range with Y1, then the Chinese character with the closest frequency to Y1 is selected first. After the replacement is completed, the recognition difficulty difference between the two Chinese characters at that position is reassessed to be within the preset range.

[0080] In another example, if two Chinese characters at any position are judged to have a recognition difficulty difference outside the preset range because their frequency difference falls within the first range but their literacy level difference does not fall within the third range, then the Chinese character at that position in the first character set (hereinafter referred to as character Y2) can be used as a benchmark. A new Chinese character can be selected from the character set whose frequency difference with character Y2 falls within the first range and whose literacy level difference falls within the third range. This new character can then replace the original Chinese character at that position in the second character set. During the reselection, all Chinese characters whose frequency difference with character Y2 falls within the first range and whose literacy level difference falls within the third range can be selected first. Then, a character can be randomly selected from these characters. Furthermore, during the random selection, character Y2 itself can be removed from the selection range. Furthermore, if there are no Chinese characters in the character set whose difference in Y2 frequency falls within the first range and whose difference in literacy level falls within the third range, then characters that meet one of these criteria can be selected first. For example, all Chinese characters whose difference in Y2 literacy level falls within the third range can be selected first, and then the Chinese character whose Y2 frequency is closest to the Chinese character can be chosen from among them. After the replacement is completed, the difference in recognition difficulty between the two Chinese characters at that position is reassessed to ensure it is within the preset range.

[0081] It should be noted that the above adjustments are merely examples, and any improvements made by those skilled in the art to the above embodiments based on the ideas provided in this application should be considered within the scope of protection of this application.

[0082] In one example, while making the two sets of Chinese characters similar in difficulty, it is also necessary to introduce certain differences in their content to minimize testing bias caused by the practice effect. Specifically, this could be achieved by ensuring that every character in the same position in the first and second sets of Chinese characters after sorting is different. More specifically, if two characters in any position in the first and second sets of Chinese characters are the same, one of the characters can be reselected.

[0083] Step 204: When test content needs to be generated, first test content and second test content are generated based on the first set of Chinese characters and the second set of Chinese characters, respectively. In the first test content, the Chinese characters in the first set of Chinese characters are arranged in the order within the current set, and in the second test content, the Chinese characters in the second set of Chinese characters are arranged in the order within the current set.

[0084] In this step, the process of generating test content for each set of Chinese characters can be referred to above. To make the difficulty of the generated first and second test content as similar as possible, in one embodiment, the first and second test content can be generated using the same process, such as the same layout and the same test-related information.

[0085] It is understandable that when generating test content using the above method, the two test contents are of the same type. For example, both the first test content and the second test content are test content used to test the accuracy of user reading, or both are test content used to test the fluency of user reading.

[0086] To facilitate understanding of the above process, a specific example will be used below to illustrate the method for generating the test content.

[0087] Assuming the pre-built character set is divided into 20 frequency levels at equal intervals, we can first randomly select 5 Chinese characters from each frequency level to form a first set of 100 characters, and then randomly select 5 Chinese characters from each frequency level to form a second set of 100 characters.

[0088] When sorting the first and second sets of Chinese characters in order of increasing recognition difficulty, this example uses the same sorting method as described above for both sets: sorting by frequency from high to low; if there are characters with the same frequency, then the literacy level of these characters is further determined, and they are sorted by literacy level from low to high; if there are characters with the same literacy level, then the outline level of these characters is further determined, and they are sorted by outline level from low to high.

[0089] For ease of description, any Chinese character in the sorted first set of Chinese characters will be denoted as A below i , and any Chinese character in the second set of Chinese characters will be denoted as B i , where 1 ≤ i ≤ 100. Figure 3 The flowchart showing the comparison of Chinese character recognition difficulty provided by the embodiments of the present application is as follows Figure 3 As shown, in this example, the Chinese characters at the same positions in the first set of Chinese characters and the second set of Chinese characters are compared one by one, that is, comparing A1 with B1, A2 with B2, A3 with B3..., and determining whether their word frequency levels and literacy table levels are the same.

[0090] When i takes any value, if A i and B i have the same word frequency level and literacy table level, it is considered that the difference in the recognition difficulty of the two Chinese characters is within the preset range, and the existing B i remains unchanged; if any one of the word frequency level and literacy table level of A i and B i is different, it is considered that the difference in the recognition difficulty of the two Chinese characters is not within the preset range, and B i needs to be adjusted.

[0091] When adjusting B i , first screen in the font library whether there is a Chinese character with the same word frequency level and literacy table level as A i (excluding A i ). If multiple Chinese characters are screened out, one can be randomly selected from them as the new B i . If there is no Chinese character in the font library with the same word frequency level and literacy table level as A i , then first screen out the Chinese characters with the same literacy table level as A i [[ID=�8]] (excluding A i ), and then select the Chinese character with the word frequency level closest to A i from them as the new B i . The following is an example with specific Chinese characters: Assume that the 65th Chinese character in the first set of Chinese characters (i.e., A 65 ) is "裸", its word frequency is 6, and its literacy table level is 6, while the 65th Chinese character in the second set of Chinese characters (i.e., B 65 ) is "睦", its word frequency is 6, and its literacy table level is 7. Since the literacy table levels are different, B 65 needs to be reselected. When reselecting the character, first, according to A 65 , all Chinese characters with a word frequency of 6 and a literacy table level of 6 are selected from the font library, and then one character is randomly selected from them as the new B 65 to replace the original B 65If there is no Chinese character in the character set with a frequency of 6 and a literacy level of 6, then first filter out all Chinese characters with a literacy level of 6 from the character set, and then select the character whose frequency level is closest to 6 from these characters, for example, a Chinese character with a frequency level of 5 or 7 as the new B. 65 Replace the original B 65 Therefore, it is believed that A 65 and B after the replacement 65 The difference in recognition difficulty is within the preset range.

[0092] Finally, the sorted first set of Chinese characters and the adjusted (or unadjusted) second set of Chinese characters are arranged in a 10×10 matrix from left to right and from top to bottom, respectively, to serve as test content for reading accuracy or reading fluency.

[0093] In one implementation, to assess the degree of impairment in a user's reading ability, it is necessary to test the user's higher-level reading skills. Therefore, after generating test content based on Chinese characters from the acquired Chinese character database to test the user's reading accuracy and fluency, it is also necessary to generate test content based on Chinese characters from the acquired Chinese character database to test the user's reading comprehension and dictation abilities.

[0094] Specifically, when generating test content based on Chinese characters from an acquired Chinese character database to assess a user's reading comprehension ability, several sentences can be generated from the acquired characters. These sentences are then sorted by the number of characters in ascending order and presented to the user. To test the user's reading comprehension ability, some of these sentences conform to natural laws, while others do not, allowing the user to judge whether each sentence conforms to natural laws. For example, a sentence that does not conform to natural laws could be: "The sun rises from the east," while a sentence that conforms to natural laws could be: "Swallows can fly," etc.

[0095] like Figure 4 As shown, each sentence can be displayed on the user interface, which also includes components for determining whether a sentence conforms to natural laws, such as... Figure 4 The component includes checkmarks and crosses. Users can click on this component to judge whether each sentence conforms to natural laws.

[0096] When generating test content for testing the user's dictation ability based on the Chinese characters in the acquired Chinese character database, several Chinese characters can be randomly selected from the acquired Chinese character database as dictation objects, and the dictation objects can be played aloud so that the user can write down the dictation objects based on what they hear.

[0097] The test content generated using the above method to test users' reading comprehension and dictation abilities can be further determined based on the user's responses. For example, the worse the user's reading comprehension and dictation abilities are, the higher the degree of impairment in their reading ability.

[0098] In the above S102, when identifying whether a user has a reading ability deficit based on the response results, it can be determined that the user has a reading ability deficit if the user's reading accuracy score obtained from the response results is lower than the reading accuracy norm score of people with the same level of education as the user, and the difference reaches the first preset standard deviation.

[0099] Alternatively, if the user's reading accuracy score obtained from the response results is lower than the reading accuracy norm score of people with the same level of education as the user, and the difference reaches the second preset standard deviation but does not reach the first preset standard deviation, and the user's reading fluency score is lower than the reading fluency norm score of people with the same level of education as the user, and the difference reaches the first preset standard deviation, then it is determined that the user has a reading ability deficiency.

[0100] In this application, reading accuracy is the most basic test criterion. If a user's reading accuracy is significantly lower than the average reading accuracy level of a group with similar educational backgrounds, the user is directly deemed to have a reading ability deficiency. If a user's reading accuracy is slightly lower than the average reading accuracy level of a group with similar educational backgrounds, but their reading fluency is significantly lower than the average reading fluency level of a group with similar educational backgrounds, the user is also considered to have a reading ability deficiency. The first presupposed standard deviation in this application can be 1.5, and the second presupposed standard deviation can be 1.

[0101] When determining whether a user's score is lower than the norm score for reading accuracy among people with the same level of education and within a first preset standard deviation, the user's raw reading accuracy score can be converted into a standardized score using the formula: (Raw score - Normative mean) / Normative standard deviation. For example, Xiaoming participated in a reading test in the fall semester of third grade. His reading accuracy score was 36, and his reading fluency score was 69. Referring to the norm for the fall semester of third grade, his reading accuracy z-score was -3, and his reading fluency z-score was -0.36. Xiaoming's standardized reading accuracy score is 3 standard deviations lower than the average level of his grade and more than 1.5 standard deviations lower. Therefore, it can be determined that Xiaoming has a reading ability deficiency.

[0102] The user's reading accuracy score can be calculated for each word in the reading accuracy test content. One point is awarded for each correctly read word, and the accumulated score is the user's reading accuracy score. The normative mean and standard deviation can be obtained by statistically analyzing the scores of people with similar educational levels to the user.

[0103] The following methods can be used to calculate a user's reading fluency score.

[0104] Obtain the time it takes for a user to complete a reading fluency test and the number of Chinese characters correctly recognized.

[0105] The user's score is calculated based on the time taken and the number of Chinese characters used.

[0106] In one embodiment, a test duration (hereinafter referred to as the first duration) is set for the reading fluency test. The timer starts simultaneously with the user's start of the test. If the user fails to recognize all Chinese characters within the first duration, the test terminates when the first duration is reached, and this first duration is recorded as the user's test time for completing the reading fluency test. If the user completes the recognition of all Chinese characters within the first duration, the actual time taken is recorded as the test time when the user completes the recognition of all Chinese characters, i.e., when the user completes the reading fluency test, and the test terminates. Therefore, while ensuring the test duration remains within a reasonable range, it effectively distinguishes between users with slower and faster character recognition speeds.

[0107] In another embodiment, the reading fluency test can set a single-character test duration (hereinafter referred to as the second duration). If the user fails to recognize any Chinese character within the second duration, the user's recognition time for that character is recorded as the second duration, and the user continues to recognize the next Chinese character. If the user completes the recognition of any Chinese character within the second duration, the user's actual recognition time is recorded, and the user continues to recognize the next Chinese character. By summing the user's recognition time for each Chinese character, the user's test duration is obtained. In one example, if the user's recognition time for multiple consecutive Chinese characters exceeds the second duration, the test can be terminated directly, and the recognition time for each subsequent Chinese character is recorded as the second duration.

[0108] In one embodiment, for any given Chinese character, the user is required to pronounce the character, and the user's correct recognition of the character is determined based on whether the pronunciation is correct. Specifically, when pronouncing the character, if the character is a polyphonic character, the user can determine correct recognition by pronouncing any correct pronunciation. Furthermore, if the user cannot recognize the character, they can choose to skip it and continue to recognize the next character. In another embodiment, for any given Chinese character, the user is required to correctly write down the pronunciation of the character or correctly select the pronunciation of the character, and the user's correct recognition of the character is determined based on whether the pronunciation is correct.

[0109] The reading fluency test in this application embodiment can be an offline test. In one example, a paper-based test can be used, with a dedicated test instructor responsible for timing, obtaining the correctness of Chinese character recognition, and calculating the test score. The reading fluency test in this application embodiment can also be an online test. In one example, an electronic device providing online testing can be used, which will time the test and obtain the correctness of Chinese character recognition. Specifically, the electronic device can display the test content to the user through a display device, record the test duration through a timer, and obtain the user's recognition results of Chinese characters through input devices such as a sound acquisition device and a handwriting input tablet. The recognition results are then compared with the correct answers to determine and record the correctness of Chinese character recognition. Finally, the test score is calculated based on the test duration.

[0110] As one example, the test score can be calculated using the following formula: Test Score = Number of correctly recognized Chinese characters / Total time. This allows for a single test score to simultaneously assess both the user's vocabulary and reading speed. Alternatively, a separate score can be calculated for both vocabulary size and reading speed to evaluate the user's reading fluency from two dimensions.

[0111] After determining whether a user has a reading disability, it can be decided whether to proceed with further testing. If the user does not have a reading disability, no further testing is necessary. Conversely, if the user does have a reading disability, it is necessary to further identify the underlying causes of the disability.

[0112] Through actual research, the inventors discovered that the substantial reason for users' reading ability deficiencies is that users have deficiencies in reading-related cognitive abilities or other deficiencies. These deficiencies stem from at least one of the following factors: phonological cognitive deficiencies, morpheme cognitive deficiencies, orthographic cognitive deficiencies.

[0113] In S102 above, if a user has a reading ability deficit, it is also necessary to determine whether the user has other deficits. If they do not match, it is determined that the user has a reading-related cognitive ability deficit.

[0114] Other deficiencies could include physical or intellectual disabilities. For example, impaired vision or hearing could lead to reading difficulties, or a low intellectual level could result in reading impairment. It's possible to determine if a user's reading impairment is caused by other deficiencies by obtaining their physical and intellectual test results. If these results match other deficiencies—for example, if hearing tests show significant hearing loss or vision impairment—then the user is considered to have other deficiencies.

[0115] Furthermore, S103 may specifically determine that the user's reading ability deficiency is caused by the user's reading-related cognitive ability deficiency when the user does not match other deficiencies, and then obtain matching objects for the user's phonological cognitive deficiency, morpheme cognitive deficiency and orthography cognitive deficiency respectively when the user has reading-related cognitive ability deficiency.

[0116] The user is matched using the obtained matching objects. If the user matches any matching object, the reading-related cognitive ability deficit factors corresponding to the matching object are determined.

[0117] In this embodiment, when it is necessary to determine whether a user has phonological cognitive deficiencies, morpheme cognitive deficiencies, or orthographic cognitive deficiencies, it is also necessary to assess the user's education level. This involves obtaining a pre-constructed Chinese character database corresponding to the user's education level, generating matching objects based on the characters in this database, and further matching the user. It is understood that a user may simultaneously possess one or more cognitive deficiencies; that is, multiple reading-related cognitive ability deficiencies may simultaneously lead to both reading ability deficiencies and reading-related cognitive ability deficiencies. Therefore, it is necessary to match the user separately using matching objects for each type of reading-related cognitive ability deficiency factor to comprehensively detect the user's reading-related cognitive ability deficiencies.

[0118] Specifically, when obtaining matching objects for speech recognition deficiencies, morpheme recognition deficiencies, and orthographic recognition deficiencies, matching objects for speech recognition deficiencies, morpheme recognition deficiencies, and orthographic recognition deficiencies can be generated separately for each user in advance, and the matching objects can be obtained after determining that the user does not match other deficiencies. Alternatively, matching objects can be generated separately for speech recognition deficiencies, morpheme recognition deficiencies, and orthographic recognition deficiencies after determining that the user does not match other deficiencies. This disclosure does not limit the timing of generating matching objects.

[0119] Specifically, when generating matching objects for speech recognition deficiencies, one can obtain a portion of Chinese characters from a Chinese character database to form a speech recognition character set, and then generate the pinyin of all Chinese characters in that speech recognition character set.

[0120] For each Chinese character in the speech character set, some syllables are deleted from the pinyin of each pinyin, and the pinyin content after deleting some syllables is displayed to the user as a matching object for speech cognitive deficiency;

[0121] When matching users using the generated matching objects, specifically, it can be to obtain the user's reading results of the pinyin content after deleting each syllable, determine whether each reading result is accurate, and calculate the user's speech cognition ability score based on the accuracy of each reading result;

[0122] If the user's speech cognition score is lower than the speech cognition norm score of people with the same level of education, and the difference reaches the second preset standard deviation, then the user is identified as a match for speech cognition deficiency.

[0123] For example, such as Figure 5 As shown, the pinyin for the first Chinese character is "shu". The user is prompted not to pronounce the syllable "sh", but to pronounce it as "u", and the system judges whether the user's pronunciation is correct. When deleting syllables for each Chinese character, it can be done by deleting the initial sound, middle sound, and final sound. The set of Chinese characters in the speech character set can be a preset number, such as 20. If the user makes a certain number of consecutive mistakes, such as 5, the test stops. The number of correct mistakes is calculated, and the user's speech cognition ability score is calculated based on the number of correct mistakes. If the user's speech cognition ability score is lower than the speech cognition norm score of people with the same level of education by 1 standard deviation, the user is considered to have a speech cognition deficit.

[0124] In addition to using the methods mentioned above to determine whether a user has speech cognitive impairment, the following methods can also be used.

[0125] One approach is to generate matching objects for speech cognitive deficiencies by obtaining a first preset number of Arabic numerals to form a first set of numerals, and generating a numeral matrix based on the first set of numerals as matching objects for speech cognitive deficiencies and displaying it to the user; wherein the numeral matrix includes several rows, each row includes all the numerals in the set of numerals, and the order of the numerals in each row is different.

[0126] When matching users using the generated matching objects, the system can specifically obtain the user's reading results for each Arabic numeral in the digit matrix, determine the correctness of each reading result, and record the user's time. Based on the user's time and the number of correct readings, a score for the user's speech recognition ability is calculated. If the user's speech recognition ability score is lower than the speech recognition norm score of a group with the same level of education by one standard deviation, the user is considered to have a speech recognition deficit. This method can be used to test a user's ability to quickly access and generate speech from visual input, thus determining whether the user has a deficiency in rapid naming ability within speech recognition.

[0127] Another approach is to generate matching objects for speech cognitive deficiencies by obtaining a second preset number of Arabic numerals to form a second set of numbers, arranging the numbers in the second set of numbers in a preset order, and displaying the arrangement result to the user as a matching object for speech cognitive deficiencies.

[0128] When matching users using the generated matching objects, the arrangement result can be hidden first, prompting the user to recite the arrangement result forwards and backwards, and then the accuracy of the recitation can be determined. The user's phonological cognitive ability score is calculated based on the number of correctly recited Arabic numerals. If the user's phonological cognitive ability score is lower than the phonological cognitive norm score of a group with the same level of education by one standard deviation, the user is considered to have a phonological cognitive deficit. This method can be used to test the user's short-term phonological memory and retention ability, thus determining whether the user has a deficit in phonological memory within phonological cognitive ability.

[0129] Understandably, when determining whether a user has a speech cognitive deficit, the three methods mentioned above can be used to match the user. If a user's speech cognitive deficit score in any of these areas is lower than the speech cognitive norm score of a group with the same level of education by one standard deviation, then the user is considered to have a speech cognitive deficit. Alternatively, the first method can be used as the primary method; if the speech cognitive deficit score obtained using the first method is lower than the speech cognitive norm score of a group with the same level of education by one standard deviation, then the user is considered to have a speech cognitive deficit.

[0130] In one implementation, when generating matching objects for morpheme recognition deficiencies, it may be to obtain a set of morpheme recognition Chinese characters composed of some Chinese characters in the Chinese character database, in order to address morpheme recognition deficiencies.

[0131] For any target Chinese character in the morpheme-based Chinese character set, generate a target word that includes that target Chinese character, and display all target words corresponding to the morpheme-based Chinese character set as morpheme-based cognitive defect matching objects to the user;

[0132] When matching users using the generated matching objects, the specific steps may be to obtain the synonyms and dissimilar morphemes provided by the user for each target word, including the target Chinese character and the target word, determine whether the synonyms and dissimilar morphemes are correct, and calculate the user's morpheme cognition ability score based on the judgment result corresponding to each target word.

[0133] If a user's morpheme recognition score is lower than the morpheme recognition norm score of a group of people with the same level of education, and the difference reaches the second preset standard deviation, then the user is matched with a matching object for that morpheme recognition deficiency.

[0134] For example, such as Figure 6As shown, the target Chinese character is "包" (bag), and the target word is "书包" (schoolbag). Prompt the user to say synonymous morpheme words and non-synonymous morpheme words of "书包" that include the Chinese character "包". For example, a synonymous morpheme word can be "背包" (backpack), and a non-synonymous morpheme word can be "包装" (packaging). Judge whether the provided synonymous morpheme words and non-synonymous morpheme words by the user are correct, and calculate the score of the user's morpheme cognitive ability according to the judgment results corresponding to each target word. For example, for each target word, getting the synonymous morpheme word right scores 1 point, and getting the non-synonymous morpheme word right scores 1 point, that is, the full score for each target word is 2 points. If the score of the user's morpheme cognitive ability is less than the morpheme cognitive norm score of the population with the same educational level by 1 standard deviation, it is determined that the user has a morpheme cognitive defect.

[0135] In one implementation, when generating matching objects for orthographic cognitive defects, it can be to obtain some Chinese characters in the Chinese character database to form an orthographic cognitive Chinese character set, and divide the orthographic cognitive Chinese character set into a true character set and a non-character set;

[0136] Perform predefined non-character processing on each Chinese character in the non-character set; the predefined non-character processing includes mirroring the Chinese character, changing the positions of the components of the Chinese character, and replacing the components of the Chinese character with non-character components;

[0137] Show each character in the true character set and the non-character set after the predefined non-character processing to the user as an orthographic cognitive defect matching object.

[0138] When using the generated matching objects to match the user, specifically, it can be to obtain the results of the user's judgment on whether each character is a standard Chinese character, determine whether each judgment result is correct, and calculate the score of the user's orthographic cognitive ability according to the correctness of each judgment result;

[0139] If the score of the orthographic cognitive ability is lower than the orthographic cognitive norm score of the population with the same educational level as the user, and the difference reaches the second preset standard deviation, it is determined that the user matches the matching object of the orthographic cognitive defect.

[0140] As Figure 7 shown, this character is a non-character. Display this non-character on the interface and prompt the user to judge whether this character is a standard Chinese character, and obtain the user's judgment result.

[0141] After obtaining the user's judgment results for each character, calculate the score of the user's orthographic cognitive ability. If the score of the user's orthographic cognitive ability is lower than the orthographic cognitive norm score of the population with the same educational level as the user by 1 standard deviation, it is determined that the user has an orthographic cognitive defect.

[0142] It is understandable that when calculating the standard deviation for matching users with different reading-related cognitive deficit factors, the method used is the same as the method used to identify whether a user has a reading deficit based on their response results, and will not be repeated here. This method not only identifies whether a user has a reading deficit, but also identifies the substantive factors that truly cause it, thus facilitating subsequent improvement of the user's reading ability based on these substantive factors. Furthermore, many users with reading deficits are often identified as having dyslexia. However, if the user's reading deficit is due to other factors, such as physical or intellectual disabilities, they should not be identified as having dyslexia. Conversely, if a user has a reading deficit not caused by other factors, but by at least one of the following cognitive deficits: phonological cognition deficit, morpheme cognition deficit, orthographic cognition deficit, it indicates that the user does indeed have certain cognitive deficits in reading. If the user's reading deficit and cognitive deficit persist for a period of time, such as up to 6 months, then it can be determined that the user does indeed have a dyslexia. Therefore, the solution proposed in this application can also assist in determining whether a user has a dyslexia.

[0143] Based on the same inventive concept as the reading-related cognitive ability deficit identification method provided in this application, embodiments of this application also provide a reading and related cognitive ability deficit identification device, which can be installed in electronic devices such as mobile phones, tablets, and laptops. Figure 8 As shown, the device includes:

[0144] The test content generation module 810 is used to generate test content for testing the user's reading ability based on the user's basic information when it is determined that the user has a risk of reading ability deficiency, and to display the test content to the user through the operation interface.

[0145] The cognitive deficit identification module 820 is used to obtain the user's response results to the test content, and to identify whether the user has reading and related cognitive ability deficits based on the response results;

[0146] The defect factor matching module 830 is used to match the user with different reading-related cognitive ability defect factors when it is determined that the user has reading and related cognitive ability defects, and to determine at least one reading-related cognitive ability defect factor matched by the user.

[0147] In one implementation, the test content generation module 810 is specifically used to obtain a pre-built Chinese character database corresponding to the user's education level;

[0148] Test content was generated based on Chinese characters obtained from the Chinese character database to test the user's reading accuracy and fluency.

[0149] In one implementation, the test content generation module 810 is specifically used to select N Chinese characters from a pre-built Chinese character database as set elements to generate a Chinese character data set T1 = {t}. 11 , t 12 , ..., t 1N} and the Chinese character data set T2={t 21 , t 22 , ..., t 2N Each Chinese character data in the Chinese character database includes a Chinese character identifier, a recognition difficulty attribute, and a difficulty level attribute. The recognition difficulty attribute value indicates the level of recognition difficulty of the Chinese character corresponding to the Chinese character data, and the difficulty level attribute value is set based on the recognition difficulty attribute value. T1 and T2 both contain Chinese character data with different difficulty level attribute values, and the elements of their sets are at least partially different.

[0150] It should be noted that the Chinese character data set T1 = {t 11 , t 12 , ..., t 1N} and the Chinese character data set T2={t 21 , t 22 , ..., t 2N The labels of the elements in the set} indicate the position (or order) of the elements, not the elements themselves. For example, t 11 t represents the first element of set T1. 12 This represents the second set element in T1.

[0151] Sort the Chinese character data in T1 and T2 according to the recognition difficulty attribute value, so that the Chinese character data in T1 and T2 are arranged in order of recognition difficulty from low to high.

[0152] For sorted T1 and T2, if i takes any integer value between 1 and N, then t 1i and t 2i The differences in the recognition difficulty attributes are all within the preset range;

[0153] When test content needs to be generated, t in T1 will be... 11 to t 1N The corresponding Chinese characters are arranged in order to generate the first test content, and t in T2 is used. 21 to t 2NThe corresponding Chinese characters are arranged in sequence to generate the second test content; both the first test content and the second test content are test contents for testing the user's reading accuracy or both are test contents for testing the user's reading fluency.

[0154] In a specific example, it is assumed that the set generation module 501 selects N Chinese characters from the Chinese character database to form a Chinese character data set T1 = {t 11 , t 12 , t 13 , ……, t 1N}, where t 11 corresponds to the Chinese character "才", t 12 corresponds to the Chinese character "野", t 13 corresponds to the Chinese character "禾". Since the recognition difficulty of the Chinese character "野" is greater than that of the Chinese character "禾", after sorting, the Chinese character data corresponding to the Chinese character "野" will be arranged after the Chinese character "禾". For example, after sorting, t 11 corresponds to the Chinese character "才", t 12 corresponds to the Chinese character "禾", t 13 corresponds to the Chinese character "野", that is, t 11 fixedly represents the first set element in T1, t 12 fixedly represents the second set element in T1, and so on.

[0155] In one implementation, the test content generation module 810 is further configured to generate test content for testing the user's reading comprehension ability and dictation ability based on the Chinese characters in the obtained Chinese character database.

[0156] In one implementation, the cognitive defect recognition module 820 is specifically configured to determine that the user has a reading ability defect if the reading accuracy score of the user obtained from the response result is lower than the reading accuracy norm score of the user's peers with the same educational level and the difference reaches the first preset standard deviation;

[0157] Or, if the reading accuracy score of the user obtained from the response result is lower than the reading accuracy norm score of the user's peers with the same educational level, the difference reaches the second preset standard deviation and does not reach the first preset standard deviation, and the reading fluency score of the user is lower than the reading fluency norm score of the user's peers with the same educational level and the difference reaches the first preset standard deviation, then it is determined that the user has a reading ability defect.

[0158] In one implementation, the cognitive defect recognition module is specifically configured to determine whether the user matches other defects when the user has a reading ability defect. If not, it is determined that the user has a reading-related cognitive ability defect.

[0159] In one embodiment, the reading-related cognitive ability deficit factors include: phonological cognitive deficit, morpheme cognitive deficit, and orthography cognitive deficit;

[0160] The defect factor matching module 830 is specifically used to obtain matching objects for speech recognition defects, morpheme recognition defects and orthography recognition defects respectively.

[0161] The user is matched using the acquired matching objects. If the user matches any matching object, the reading-related cognitive ability deficit factors corresponding to the matching object are determined.

[0162] In one embodiment, the defect factor matching module 830 is specifically used to obtain a set of Chinese characters for speech recognition based on a portion of the Chinese characters in the Chinese character database, and generate the pinyin of all Chinese characters in the set of Chinese characters for speech recognition based on speech recognition defects.

[0163] For each Chinese character in the speech-character set, some syllables are deleted from the pinyin of that pinyin, and the pinyin content after deleting some syllables is displayed to the user as a matching object for speech cognitive deficiency.

[0164] In one embodiment, the defect factor matching module 830 is further configured to acquire a first preset number of Arabic numerals to form a first number set for speech recognition defects, and generate a number matrix based on the first number set as a matching object for speech recognition defects and display it to the user; wherein the number matrix includes several rows, each row includes all the numbers in the number set, and the order of the numbers in each row is different.

[0165] In one embodiment, the defect factor matching module 830 is further configured to, for speech recognition defects, obtain a second preset number of Arabic numerals to form a second number set, arrange the numbers in the second number set in a preset order, and display the arrangement result to the user as a matching object for speech recognition defects.

[0166] In one embodiment, the defect factor matching module 830 is further configured to obtain a set of Chinese characters that constitute morpheme cognition in the Chinese character database, targeting morpheme cognition defects.

[0167] For any target Chinese character in the morpheme-based Chinese character set, generate a target word that includes that target Chinese character, and display all target words corresponding to the morpheme-based Chinese character set as morpheme-based cognitive defect matching objects to the user.

[0168] In one embodiment, the defect factor matching module 830 is further configured to, in response to orthographic recognition defects, obtain a set of orthographic recognition characters composed of a portion of the Chinese characters in the Chinese character database, and divide the set of orthographic recognition characters into a set of true characters and a set of non-characters.

[0169] Each Chinese character in the non-character set undergoes predefined non-character processing; the predefined non-character processing includes mirroring the Chinese character, changing the position of the components of the Chinese character, and replacing the components of the Chinese character with non-character components;

[0170] Each character in the set of true characters and the set of non-character characters after predefined non-character processing is displayed to the user as a matching object for orthographic cognitive defects.

[0171] In one implementation, the defect factor matching module 830 is specifically used to obtain the user's reading results of the pinyin content after each deleted syllable, determine whether each reading result is accurate, and calculate the user's speech cognition ability score based on the accuracy of each reading result.

[0172] If the user's speech cognition score is lower than the speech cognition norm score of people with the same level of education, and the difference reaches the second preset standard deviation, then the user is determined to be matched with a target for the speech cognition deficiency.

[0173] In one implementation, the defect factor matching module 830 is specifically used to obtain the synonyms and dissimilar morphemes of the target Chinese character and the target word provided by the user for each target word, determine whether the synonyms and dissimilar morphemes are correct, and calculate the user's morpheme cognition ability score based on the judgment result corresponding to each target word.

[0174] If the score of the user's morpheme cognition ability is lower than the morpheme cognition norm score of people with the same level of education as the user, and the difference reaches the second preset standard deviation, then the user is determined to be matched with the matching object of the morpheme cognition deficiency.

[0175] In one implementation, the defect factor matching module 830 is specifically used to obtain the result of the user's judgment on whether each character is a standard Chinese character, determine whether each judgment result is correct, and calculate the user's orthography recognition ability score based on the correctness of each judgment result.

[0176] If the score of the orthography cognition ability is lower than the orthography cognition norm score of the user's equivalent education level, and the difference reaches the second preset standard deviation, then the user is determined to be a match for the orthography cognition deficiency.

[0177] The solutions in this application embodiment can be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0178] Furthermore, embodiments of the present invention also provide an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are connected via the bus. When the computer program is executed by the processor, it implements the various processes of the various embodiments of the above-described methods for identifying reading and related cognitive impairments, and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0179] For details, see Figure 9 As shown, the electronic device includes a bus 1110, a processor 1120, a transceiver 1130, a bus interface 1140, a memory 1150, and a user interface 1160.

[0180] In this embodiment of the invention, the electronic device further includes a computer program stored in a memory 1150 and executable on a processor 1120, wherein the computer program, when executed by the processor 1120, implements the above-described method for identifying reading and related cognitive impairments.

[0181] Transceiver 1130 is used to receive and send data under the control of processor 1120.

[0182] In this embodiment of the invention, a bus architecture (represented by bus 1110) is used. Bus 1110 may include any number of interconnected buses and bridges. Bus 1110 connects various circuits, including one or more processors represented by processor 1120 and memory represented by memory 1150.

[0183] Bus 1110 represents one or more of several types of bus architectures, including memory buses and memory controllers, peripheral buses, Accelerated Graphics Port (AGP), processors, or local buses using any bus architecture from various bus architectures. As an example and not a limitation, such architectures include: Industry Standard Architecture (ISA) buses, Micro Channel Architecture (MCA) buses, Enhanced ISA (EISA) buses, Video Electronics Standards Association (VESA) buses, and Peripheral Component Interconnect (PCI) buses.

[0184] The processor 1120 can be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method embodiments can be completed by integrated logic circuits in the processor hardware or by instructions in software form. The processors mentioned above include: general-purpose processors, central processing units (CPUs), network processors (NPs), digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), complex programmable logic devices (CPLDs), programmable logic arrays (PLAs), microcontroller units (MCUs) or other programmable logic devices, discrete gates, transistor logic devices, and discrete hardware components. They can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. For example, the processor can be a single-core processor or a multi-core processor, and the processor can be integrated on a single chip or located on multiple different chips.

[0185] Processor 1120 can be a microprocessor or any conventional processor. The method steps disclosed in the embodiments of the present invention can be directly executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in readable storage media known in the art, such as Random Access Memory (RAM), Flash Memory, Read-Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), registers, etc. The readable storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0186] Bus 1110 can also connect various other circuits, such as peripheral devices, voltage regulators, or power management circuits. Bus interface 1140 provides an interface between bus 1110 and transceiver 1130, all of which are well known in the art. Therefore, embodiments of the present invention will not be described further.

[0187] Transceiver 1130 can be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. For example, transceiver 1130 receives external data from other devices, and transceiver 1130 is used to send data processed by processor 1120 to other devices. Depending on the nature of the computer system, a user interface 1160 may also be provided, such as a touchscreen, physical keyboard, monitor, mouse, speaker, microphone, trackball, joystick, or stylus.

[0188] It should be understood that, in embodiments of the present invention, memory 1150 may further include memory remotely configured relative to processor 1120, and such remotely configured memory can be connected to a server via a network. One or more portions of the aforementioned network may be an ad hoc network, intranet, extranet, virtual private network (VPN), local area network (LAN), wireless local area network (WLAN), wide area network (WAN), wireless wide area network (WWAN), metropolitan area network (MAN), Internet, public switched telephone network (PSTN), ordinary old-style telephone service (POTS), cellular telephone network, wireless network, Wi-Fi network, and combinations of two or more of the aforementioned networks. For example, cellular telephone networks and wireless networks can be Global System for Mobile Communications (GSM), Code Division Multiple Access (CDMA), WiMAX, General Packet Radio Service (GPRS), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), LTE Frequency Division Duplex (FDD), LTE Time Division Duplex (TDD), Advanced Long Term Evolution (LTE-A), Universal Mobile Telecommunications System (UMTS), Enhanced Mobile Broadband (eMBB), Massive Machine Type Communication (mMTC), Ultra Reliable Low Latency Communications (uRLLC), etc.

[0189] It should be understood that the memory 1150 in the embodiments of the present invention may be volatile memory or non-volatile memory, or may include both volatile memory and non-volatile memory. Non-volatile memory includes: read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory.

[0190] Volatile memory includes random access memory (RAM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 1150 of the electronic device described in this embodiment includes, but is not limited to, the above-described and any other suitable types of memory.

[0191] In this embodiment of the invention, the memory 1150 stores the following elements of the operating system 1151 and the application 1152: executable modules, data structures, or subsets thereof, or extended sets thereof.

[0192] Specifically, the operating system 1151 includes various system programs, such as a framework layer, a core library layer, and a driver layer, used to implement various basic business functions and handle hardware-based tasks. The application program 1152 includes various applications, such as a media player and a browser, used to implement various application functions. Programs implementing the methods of this embodiment of the invention can be included in the application program 1152. The application program 1152 includes applets, objects, components, logic, data structures, and other computer system executable instructions that perform specific tasks or implement specific abstract data types.

[0193] Furthermore, embodiments of the present invention also provide a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements the various processes of the various embodiments of the above-described reading and related cognitive ability defect identification methods, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0194] Computer-readable storage media include: permanent and non-permanent, removable and non-removable media, which are tangible devices capable of retaining and storing instructions for use by an instruction execution device. Computer-readable storage media include: electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, and any suitable combination thereof. Computer-readable storage media include: phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, optical disc read-only memory (CD-ROM), digital versatile optical disc (DVD) or other optical storage, magnetic tape storage, magnetic disk storage or other magnetic storage devices, memory sticks, mechanical encoding devices (e.g., punched cards or raised structures in grooves on which instructions are recorded), or any other non-transfer medium that can be used to store information accessible by a computing device. As defined in the embodiments of the present invention, computer-readable storage media do not include temporary signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses passing through fiber optic cables), or electrical signals transmitted through wires.

[0195] The computer program code contained in the aforementioned computer-readable storage medium may be transmitted using any suitable medium, including wireless, wire, optical fiber, radio frequency (RF), or any suitable combination thereof.

[0196] Computer program code for performing the operations of the embodiments of the present invention can be written in assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, integrated circuit configuration data, or in one or more programming languages ​​or combinations thereof. The programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The computer program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer or an external computer via any type of network, including a local area network (LAN) or a wide area network (WAN).

[0197] This invention also provides a computer program comprising one or more computer instructions. When the computer instructions are loaded and executed on a processor, all or part of the processes or functions described in the embodiments of this application are generated.

[0198] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0199] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A device for identifying reading and related cognitive ability deficits, characterized in that, include: The test content generation module is used to generate test content for testing the user's reading ability based on the user's basic information when it is determined that the user has a risk of reading ability deficiency, and to display the test content to the user through the operation interface. The cognitive deficit identification module is used to obtain the user's response results to the test content, and to identify whether the user has reading and related cognitive ability deficits based on the response results; The defect factor matching module is used to match the user with different reading-related cognitive ability defect factors when it is determined that the user has reading and related cognitive ability defects, and to determine at least one reading-related cognitive ability defect factor matched by the user.

2. The apparatus according to claim 1, characterized in that, The test content generation module is specifically used to obtain a pre-built Chinese character database corresponding to the user's education level; Test content was generated based on Chinese characters obtained from the Chinese character database to test the user's reading accuracy and fluency.

3. The apparatus according to claim 2, characterized in that, The test content generation module is specifically used to select N Chinese characters from a pre-built Chinese character database as set elements to generate a Chinese character data set T1 = {t}. 11 , t 12 , ..., t 1N } and the Chinese character data set T2={t 21 , t 22 , ..., t 2N Each Chinese character data in the Chinese character database includes a Chinese character identifier, a recognition difficulty attribute, and a difficulty level attribute. The recognition difficulty attribute value indicates the level of recognition difficulty of the Chinese character corresponding to the Chinese character data, and the difficulty level attribute value is set based on the recognition difficulty attribute value. T1 and T2 both contain Chinese character data with different difficulty level attribute values, and the elements of their sets are at least partially different. Sort the Chinese character data in T1 and T2 according to the recognition difficulty attribute value, so that the Chinese character data in T1 and T2 are arranged in order of recognition difficulty from low to high. For sorted T1 and T2, if i takes any integer value between 1 and N, then t 1i and t 2i The differences in the recognition difficulty attributes are all within the preset range; When test content needs to be generated, t in T1 will be... 11 to t 1N The corresponding Chinese characters are arranged in order to generate the first test content, and t in T2 is used. 21 to t 2N The corresponding Chinese characters are arranged in sequence to generate the second test content; both the first test content and the second test content are test content used to test the user's reading accuracy, or both are test content used to test the user's reading fluency.

4. The apparatus according to claim 2, characterized in that, The test content generation module is also used to generate test content based on the Chinese characters in the acquired Chinese character database to test the user's reading comprehension and dictation abilities.

5. The apparatus according to claim 2, characterized in that, The cognitive deficit identification module is specifically used to determine that the user has a reading ability deficit if the reading accuracy score obtained from the response result is lower than the reading accuracy norm score of people with the same level of education as the user, and the difference reaches a first preset standard deviation. Alternatively, if the user's reading accuracy score, obtained from the response results, is lower than the reading accuracy norm score of a group of people with the same level of education, and the difference reaches the second preset standard deviation but not the first preset standard deviation, and the user's reading fluency score is lower than the reading fluency norm score of a group of people with the same level of education, and the difference reaches the first preset standard deviation, then it is determined that the user has a reading ability deficiency.

6. The apparatus according to claim 5, characterized in that, The cognitive deficit identification module is specifically used to determine whether the user has other deficits when the user has reading ability deficits. If no other deficits are found, the module determines that the user has reading-related cognitive ability deficits.

7. The apparatus according to claim 1, characterized in that, The reading-related cognitive ability deficit factors include: phonological cognitive deficits, morpheme cognitive deficits, and orthography cognitive deficits; The defect factor matching module is specifically used to obtain matching objects for speech cognition defects, morpheme cognition defects and orthography cognition defects respectively. The user is matched using the acquired matching objects. If the user matches any matching object, the reading-related cognitive ability deficit factors corresponding to the matching object are determined.

8. The apparatus according to claim 7, characterized in that, The defect factor matching module is specifically used to obtain a partial set of Chinese characters from the Chinese character database to form a set of Chinese characters for speech recognition, and to generate the pinyin of all Chinese characters in the set of Chinese characters for speech recognition in response to speech recognition defects. For each Chinese character in the speech-character set, some syllables are deleted from the pinyin of that pinyin, and the pinyin content after deleting some syllables is displayed to the user as a matching object for speech cognitive deficiency.

9. The apparatus according to claim 8, characterized in that, The defect factor matching module is specifically used to obtain the user's reading results of the pinyin content after each deleted syllable, determine whether each reading result is accurate, and calculate the user's speech cognition ability score based on the accuracy of each reading result; If the user's speech cognition score is lower than the speech cognition norm score of people with the same level of education, and the difference reaches the second preset standard deviation, then the user is determined to be matched with a target for the speech cognition deficiency.

10. The apparatus according to claim 7, characterized in that, The defect factor matching module is further configured to acquire a first preset number of Arabic numerals to form a first number set for speech recognition defects, and generate a number matrix based on the first number set as a matching object for speech recognition defects and display it to the user; wherein the number matrix includes several rows, each row includes all the numbers in the number set, and the order of the numbers in each row is different.

11. The apparatus according to claim 10, characterized in that, The defect factor matching module is further configured to acquire a second preset number of Arabic numerals to form a second number set for speech recognition defects, arrange the numbers in the second number set in a preset order, and display the arrangement result to the user as a matching object for speech recognition defects.

12. The apparatus according to claim 7, characterized in that, The defect factor matching module is also used to obtain a set of Chinese characters composed of partial Chinese characters from the Chinese character database for morpheme cognition defects. For any target Chinese character in the morpheme-based Chinese character set, generate a target word that includes that target Chinese character, and display all target words corresponding to the morpheme-based Chinese character set as morpheme-based cognitive defect matching objects to the user.

13. The apparatus according to claim 12, characterized in that, The defect factor matching module is specifically used to obtain the synonyms and dissimilar morphemes of the target Chinese character and the target word provided by the user for each target word, determine whether the synonyms and dissimilar morphemes are correct, and calculate the user's morpheme cognition ability score based on the judgment result corresponding to each target word. If the score of the user's morpheme cognition ability is lower than the morpheme cognition norm score of people with the same level of education as the user, and the difference reaches the second preset standard deviation, then the user is determined to be matched with the matching object of the morpheme cognition deficiency.

14. The apparatus according to claim 7, characterized in that, The defect factor matching module is also used to obtain a set of orthographically recognized Chinese characters from the Chinese character database to form a set of orthographically recognized Chinese characters in response to orthographically recognized defects, and to divide the set of orthographically recognized Chinese characters into a set of true characters and a set of non-characters. Each Chinese character in the non-character set undergoes predefined non-character processing; the predefined non-character processing includes mirroring the Chinese character, changing the position of the components of the Chinese character, and replacing the components of the Chinese character with non-character components; Each character in the set of true characters and the set of non-character characters after predefined non-character processing is displayed to the user as a matching object for orthographic cognitive defects.

15. The apparatus according to claim 14, characterized in that, The defect factor matching module is specifically used to obtain the results of the user's judgment on whether each character is a standard Chinese character, determine whether each judgment result is correct, and calculate the user's orthography cognition ability score based on the correctness of each judgment result. If the score of the orthography cognition ability is lower than the orthography cognition norm score of the user's equivalent education level, and the difference reaches the second preset standard deviation, then the user is determined to be a match for the orthography cognition deficiency.

16. A method for identifying reading and related cognitive ability deficits, characterized in that, The method includes: If it is determined that a user has a risk of reading impairment, test content for testing the user's reading ability is generated based on the user's basic information, and the test content is displayed to the user. Obtain the user's response to the test content, and identify whether the user has reading and related cognitive ability deficiencies based on the response results; If it is determined that a user has reading and related cognitive ability deficits, the user is matched with different reading-related cognitive ability deficit factors to determine at least one reading-related cognitive ability deficit factor matched by the user.

17. The method according to claim 16, characterized in that, The step of generating test content for testing the user's reading ability based on the user's basic information includes: Obtain a pre-built Chinese character database corresponding to the user's education level; Test content was generated based on Chinese characters obtained from the Chinese character database to test the user's reading accuracy and fluency.

18. The method according to claim 17, characterized in that, The test content for testing the user's reading accuracy and fluency, based on the Chinese character generation from the acquired Chinese character database, includes: The same number of Chinese characters are selected from the Chinese character database to form a first set of Chinese characters and a second set of Chinese characters; all Chinese characters in the Chinese character database are divided into at least two difficulty levels according to their recognition difficulty, and both the first set of Chinese characters and the second set of Chinese characters include Chinese characters of at least two difficulty levels, and at least some of the Chinese characters in the two sets are different; The first set of Chinese characters and the second set of Chinese characters are sorted in order of increasing recognition difficulty; For the sorted first set of Chinese characters and the second set of Chinese characters, if the difference in recognition difficulty of Chinese characters in the same position is within a preset range, the first set of Chinese characters and the second set of Chinese characters will be used to generate test content in the future. When test content needs to be generated, first test content and second test content are generated based on the first set of Chinese characters and the second set of Chinese characters, respectively. In the first test content, the Chinese characters in the first set of Chinese characters are arranged in the order within the set, and in the second test content, the Chinese characters in the second set of Chinese characters are arranged in the order within the set. Both the first test content and the second test content are test content used to test the user's reading accuracy, or both are test content used to test the user's reading fluency.

19. The method according to claim 17, characterized in that, Also includes: Test content is generated based on Chinese characters obtained from the Chinese character database to test the user's reading comprehension and dictation abilities.

20. The method according to claim 17, characterized in that, The step of identifying whether the user has reading and related cognitive ability deficits based on the response results includes: If the user's reading accuracy score obtained from the response results is lower than the reading accuracy norm score of people with the same level of education as the user, and the difference reaches the first preset standard deviation, then it is determined that the user has a reading ability deficiency. Alternatively, if the user's reading accuracy score, obtained from the response results, is lower than the reading accuracy norm score of a group of people with the same level of education, and the difference reaches the second preset standard deviation but not the first preset standard deviation, and the user's reading fluency score is lower than the reading fluency norm score of a group of people with the same level of education, and the difference reaches the first preset standard deviation, then it is determined that the user has a reading ability deficiency.

21. The method according to claim 20, characterized in that, Also includes: If the user has a reading ability deficit, determine whether the user matches other deficits. If not, determine that the user has a reading-related cognitive ability deficit.

22. The method according to claim 16, characterized in that, The reading-related cognitive ability deficit factors include: phonological cognitive deficits, morpheme cognitive deficits, and orthography cognitive deficits; The process of matching the user with different reading-related cognitive ability deficit factors to determine at least one reading-related cognitive ability deficit factor matched by the user includes: Matching objects were obtained for speech recognition deficits, morpheme recognition deficits, and orthography recognition deficits, respectively. The user is matched using the acquired matching objects. If the user matches any matching object, the reading-related cognitive ability deficit factors corresponding to the matching object are determined.

23. The method according to claim 22, characterized in that, The process of obtaining matching objects for speech recognition deficits, morpheme recognition deficits, and orthography recognition deficits includes: To address the deficiencies in speech recognition, a set of speech recognition characters is formed by acquiring a portion of Chinese characters from a Chinese character database, and the pinyin of all Chinese characters in the speech recognition character set is generated. For each Chinese character in the speech-character set, some syllables are deleted from the pinyin of that pinyin, and the pinyin content after deleting some syllables is displayed to the user as a matching object for speech cognitive deficiency.

24. The method according to claim 23, characterized in that, The step of matching the users using the generated matching objects includes: Obtain the user's reading results for the pinyin content after deleting each syllable, determine whether each reading result is accurate, and calculate the user's speech cognition ability score based on the accuracy of each reading result; If the user's speech cognition score is lower than the speech cognition norm score of people with the same level of education, and the difference reaches the second preset standard deviation, then the user is determined to be matched with a target for the speech cognition deficiency.

25. The method according to claim 22, characterized in that, Also includes: To address speech recognition deficiencies, a first set of numbers is formed by acquiring a first preset number of Arabic numerals. A number matrix is ​​generated based on the first set of numbers and displayed to the user as a matching object for speech recognition deficiencies. The number matrix includes several rows, each row including all the numbers in the number set, and the order of the numbers in each row is different.

26. The method according to claim 25, characterized in that, Also includes: To address speech recognition deficiencies, a second set of numbers is formed by acquiring a second preset number of Arabic numerals. The numbers in the second set of numbers are arranged in a preset order, and the arrangement result is displayed to the user as a matching object for speech recognition deficiencies.

27. The method according to claim 22, characterized in that, The method further includes: To address the deficiencies in morpheme recognition, a set of morpheme-based Chinese characters composed of some Chinese characters from a Chinese character database was obtained. For any target Chinese character in the morpheme-based Chinese character set, generate a target word that includes that target Chinese character, and display all target words corresponding to the morpheme-based Chinese character set as morpheme-based cognitive defect matching objects to the user.

28. The method according to claim 27, characterized in that, The step of matching the users using the generated matching objects includes: The system obtains synonyms and dissimilar morphemes provided by the user for each target word, including the target Chinese character and the target word. It then determines whether the synonyms and dissimilar morphemes are correct and calculates the user's morpheme recognition ability score based on the judgment result for each target word. If the score of the user's morpheme cognition ability is lower than the morpheme cognition norm score of people with the same level of education as the user, and the difference reaches the second preset standard deviation, then the user is determined to be matched with the matching object of the morpheme cognition deficiency.

29. The method according to claim 22, characterized in that, The method further includes: To address the shortcomings of orthographic recognition, a set of orthographically recognized Chinese characters is formed by obtaining a portion of Chinese characters from a Chinese character database, and this set is then divided into a set of true characters and a set of non-characters. Each Chinese character in the non-character set undergoes predefined non-character processing; the predefined non-character processing includes mirroring the Chinese character, changing the position of the components of the Chinese character, and replacing the components of the Chinese character with non-character components; Each character in the set of true characters and the set of non-character characters after predefined non-character processing is displayed to the user as a matching object for orthographic cognitive defects.

30. The method according to claim 29, characterized in that, The step of matching the users using the generated matching objects includes: Obtain the results of the user's judgment on whether each character is a standard Chinese character, determine whether each judgment result is correct, and calculate the user's orthography recognition ability score based on the correctness of each judgment result; If the score of the orthography cognition ability is lower than the orthography cognition norm score of the user's equivalent education level, and the difference reaches the second preset standard deviation, then the user is determined to be a match for the orthography cognition deficiency.

31. An electronic device comprising a processor and a memory, the memory storing a computer program, characterized in that, The processor executes the computer program stored in the memory to implement the steps in the reading and related cognitive impairment identification method as described in any one of claims 16 to 30.

32. A computer program comprising computer instructions, characterized in that, When computer instructions are executed by a processor, they implement the steps of the reading and related cognitive ability deficit identification method according to any one of claims 16 to 30.

33. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the reading and related cognitive impairment identification method as described in any one of claims 16 to 30.

Images