CN117257304A - Cognitive ability evaluation method and device, electronic equipment and storage medium - Google Patents

Cognitive ability evaluation method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN117257304A
CN117257304A CN202311559696.7A CN202311559696A CN117257304A CN 117257304 A CN117257304 A CN 117257304A CN 202311559696 A CN202311559696 A CN 202311559696A CN 117257304 A CN117257304 A CN 117257304A
Authority
CN
China
Prior art keywords
panel
attribute
answer
cognitive ability
question
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202311559696.7A
Other languages
Chinese (zh)
Other versions
CN117257304B (en
Inventor
陈崇雨
曾翔钰
董乐
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
DMAI Guangzhou Co Ltd
Original Assignee
DMAI Guangzhou Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by DMAI Guangzhou Co Ltd filed Critical DMAI Guangzhou Co Ltd
Priority to CN202311559696.7A priority Critical patent/CN117257304B/en
Publication of CN117257304A publication Critical patent/CN117257304A/en
Application granted granted Critical
Publication of CN117257304B publication Critical patent/CN117257304B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
    • A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

The application provides a cognitive ability evaluation method, a device, electronic equipment and a storage medium, wherein the method comprises the following steps: analyzing the topic generation parameters to determine the attribute values and rule information of the determined panels; the question generation parameters comprise a question panel, a plurality of attribute rule pairs corresponding to the questions and the number of answer panels; based on the determined attribute values of the panels and the rule information, determining the attribute values of the panels to be determined of the questions, rendering the attribute values of the panels to be determined, and generating a question panel and an answer option panel of the questions corresponding to the question generation parameters; and the control tester responds to the questions based on the question panel and the answer option panel, determines a target answer of the tester, and determines target cognitive ability evaluation data of the tester based on the target answer, the cognitive ability dimension vector and a plurality of attribute rule pairs. The multi-dimensional evaluation of the cognitive ability of the user is realized, and the cognitive ability of the tester is evaluated more accurately.

Description

Cognitive ability evaluation method and device, electronic equipment and storage medium
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a cognitive ability evaluation method, a device, an electronic apparatus, and a storage medium.
Background
Cognitive ability refers to the ability of an individual to process information during perception, memory, thinking, judgment, problem solving, etc., and relates to the entire process from sensory input to the output of information. Psychologists and educational students have developed a number of methods to evaluate these abilities for talent screening and gradually evolved into tools for various purposes, including academic evaluation, professional screening, and mental health evaluation.
The research shows that the current intelligence quotient testing system has limitations, and mainly shows the following aspects: (1) The question banks of many systems are relatively fixed, meaning that once a user is familiar with a question, the accuracy of the test is compromised. However, updating or replacing the title can result in significant time and economic costs. (2) Most systems employ standardized methods, and few systems are capable of providing customized tests for individuals. (3) The interpretation and labeling of many exams relies on expert judgment or manually engaged interpretation labels, which not only increases cost, but can also lead to a degree of subjectivity. Therefore, how to quickly and accurately evaluate the cognitive ability of a tester becomes a non-trivial technical problem.
Disclosure of Invention
In view of the foregoing, an object of the present application is to provide a cognitive ability evaluation method, apparatus, electronic device, and storage medium, which efficiently generate questions by using a question panel, a plurality of attribute rule pairs corresponding to the questions, and the number of answer panels, and further, realize multidimensional evaluation of cognitive ability of a user by using a relation between a question generation parameter and a cognitive ability dimension, thereby more accurately evaluating cognitive ability of a tester.
The embodiment of the application provides a cognitive ability evaluation method, which comprises the following steps:
analyzing the topic generation parameters to determine the attribute value and rule information of the determined panel for the topic; the title generation parameters comprise a panel of a title, a plurality of attribute rule pairs corresponding to the title and the number of answer panels;
based on the determined attribute values of the panels and the rule information, determining the attribute values of the panels to be determined of the questions, rendering the attribute values of the panels to be determined, and generating a question panel and an answer option panel of the questions corresponding to the question generation parameters;
and controlling a tester to answer the questions based on the question panel and the answer option panel, determining target answers of the tester, and determining target cognitive ability evaluation data of the tester based on the target answers, the cognitive ability dimension vector and a plurality of attribute rule pairs.
In one possible implementation manner, the determining the attribute value of the panel to be determined of the title based on the determined attribute value of the panel and the rule information includes:
if the rule information of the attribute rule pair is the sum or subtraction rule information, determining the attribute value of the panel to be determined based on the attribute value of the first column panel and the attribute value of the second column panel in the determined panels;
if the rule information of the attribute rule pair is monotonically increasing or decreasing information, determining an attribute value of a panel to be determined based on the attribute value of a first column of panels in the determined panels;
if the rule information of the attribute rule pair is constant information, determining the attribute value of the first column of panels in the determined panels as the attribute value of the panel to be determined;
and if the rule information of the attribute rule pair is three-distribution information, determining attribute values of three panels in the first row of the determined panels, and determining the attribute values of the panels to be determined.
In one possible implementation manner, the rendering the attribute value of the panel to be determined, generating a question panel and an answer option panel of the question corresponding to the question generation parameter, includes:
Rendering the attribute value of each panel to be determined to generate a question panel of the question;
predicting a question answer attribute value based on the attribute value of the determined panel and the corresponding rule information, and adjusting at least one attribute value in the question answer attribute values to determine a plurality of wrong answers;
and generating an answer option panel of the question based on the plurality of wrong answers, the correct answers corresponding to the question answer attribute values and the number of answer panels.
In one possible implementation manner, the determining the target cognitive ability evaluation data of the tester based on the target answer, the cognitive ability dimension vector and the attribute rule pairs includes:
mapping each attribute rule pair with the cognitive ability dimension vector to determine a first weight vector, and mapping the topic panel with the cognitive ability dimension vector to determine a second weight vector;
determining first cognitive ability evaluation data inspected by the title based on the weight of the panel, the first weight vector, the weight of the attribute rule pairs, the number of the attribute rule pairs and the second weight vector;
Determining second cognitive ability evaluation data of the tester reflected by the target answer based on the corresponding first weight vector of the attribute rule pair corresponding to the target answer, the corresponding reward and punishment factor of the panel, the second weight vector and the number of the attribute rule pair;
and controlling the tester to answer the next question to determine a second target answer, and performing iterative evaluation on the cognitive ability of the tester based on the first cognitive ability evaluation data inspected by the next question and the second cognitive ability evaluation data reflected by the second target answer until a plurality of questions are completed, so as to determine target cognitive ability evaluation data of the tester.
In one possible implementation manner, the determining the second cognitive ability evaluation data of the tester reflected by the target answer based on the first weight vector corresponding to the attribute rule pair corresponding to the target answer, the punishment factor corresponding to the panel, the second weight vector and the number of attribute rule pairs includes:
If the target answer is a wrong answer, determining a corresponding first weight vector of an attribute rule pair violated by the wrong answer and an attribute rule pair violated by the wrong answer;
and determining second cognitive ability evaluation data of the tester reflected by the target answer based on the corresponding first weight vector of the attribute rule pair against which the wrong answer is violated, the reward and punishment factor of the wrong answer, the reward and punishment factor corresponding to the panel, the second weight vector and the number of the attribute rule pair.
In one possible implementation manner, after the control tester answers the questions based on the question panel and the answer option panel, determining a target answer of the tester, and determining the cognitive ability of the tester based on the target answer, the cognitive ability dimension vector and a plurality of attribute rule pairs, the cognitive ability evaluation method further includes:
determining a target topic generation parameter matched with the cognitive ability of the tester based on a cosine similarity calculation formula;
and generating the target topics in a self-adaptive mode based on the target topic generation parameters.
In one possible implementation manner, after the control tester answers the questions based on the question panel and the answer option panel, determining a target answer of the tester, and determining the cognitive ability of the tester based on the target answer, the cognitive ability dimension vector and a plurality of attribute rule pairs, the cognitive ability evaluation method further includes:
and respectively analyzing attribute information of each panel in the question panels of the questions, rule information in the question panels of the questions and answers of the questions based on an analysis preset template.
In one possible implementation manner, after the control tester answers the questions based on the question panel and the answer option panel, determining a target answer of the tester, and determining the cognitive ability of the tester based on the target answer, the cognitive ability dimension vector and a plurality of attribute rule pairs, the cognitive ability evaluation method further includes:
comparing the attribute values of the wrong answer option panels and the attribute values of the correct answer option panels in the answer option panels, and determining the attribute value difference between the wrong answer option panels and the correct answer option panels;
And carrying out wrong answer analysis on the attribute value difference between the wrong answer option panel and the correct answer option panel based on a wrong answer analysis preset library.
In one possible implementation, the topic generation parameter is determined by:
determining attribute information of a question selected by a user in a question generation parameter definition interface, a panel of the question, rule information of the question and the number of answer panels;
processing the attribute information and the rule information based on a preset feasibility rule to generate a plurality of attribute rule pairs corresponding to the topics;
determining the title generation parameters based on the panel of the title, the attribute rule pair corresponding to the title and the number of answer panels;
the attribute information comprises the number of graphics in the panel of the question, the slot index value of the graphics in the panel of the question, the shape of the graphics in the panel of the question, the size of the graphics in the panel of the question and the color of the graphics in the panel of the question.
The embodiment of the application also provides a cognitive ability evaluation device, which comprises:
the processing module is used for analyzing the topic generation parameters and determining the attribute value and rule information of the determined panel of the topic; the title generation parameters comprise a panel of a title, a plurality of attribute rule pairs corresponding to the title and the number of answer panels;
The title generation module is used for determining the attribute value of the panel to be determined of the title based on the determined attribute value of the panel and the rule information, rendering the attribute value of the panel to be determined, and generating a question panel and an answer option panel of the title corresponding to the title generation parameter;
and the cognitive ability evaluation module is used for controlling a tester to answer the questions based on the question panel and the answer option panel, determining a target answer of the tester, and determining target cognitive ability evaluation data of the tester based on the target answer, the cognitive ability dimension vector and a plurality of attribute rule pairs.
The embodiment of the application also provides electronic equipment, which comprises: the system comprises a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, when the electronic device is running, the processor and the memory are communicated through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the cognitive ability assessment method.
The embodiments of the present application also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the cognitive ability assessment method as described above.
The embodiment of the application provides a cognitive ability evaluation method, a device, electronic equipment and a storage medium, wherein the cognitive ability evaluation method comprises the following steps: analyzing the topic generation parameters to determine the attribute values and rule information of the determined panels; the title generation parameters comprise a panel of a title, a plurality of attribute rule pairs corresponding to the title and the number of answer panels; based on the determined attribute values of the panels and the rule information, determining the attribute values of the panels to be determined of the questions, rendering the attribute values of the panels to be determined, and generating a question panel and an answer option panel of the questions corresponding to the question generation parameters; and controlling a tester to answer the questions based on the question panel and the answer option panel, determining target answers of the tester, and determining target cognitive ability evaluation data of the tester based on the target answers, the cognitive ability dimension vector and a plurality of attribute rule pairs. The questions are efficiently generated by using the question panels, the plurality of attribute rule pairs corresponding to the questions and the number of answer panels, and the multidimensional assessment of the cognitive ability of the user is realized by using the relation between the question generation parameters and the cognitive ability dimension, so that the cognitive ability of the tester is more accurately assessed.
In order to make the above objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered limiting the scope, and that other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a cognitive ability assessment method provided in an embodiment of the present application;
FIG. 2 is a schematic diagram of a problem panel according to an embodiment of the present disclosure;
FIG. 3 is a diagram of an answer panel according to an embodiment of the disclosure;
fig. 4 is a schematic diagram of a cognitive ability assessment method according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a cognitive ability evaluation device according to an embodiment of the present disclosure;
FIG. 6 is a second schematic structural diagram of a cognitive ability evaluation device according to an embodiment of the present disclosure;
Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it should be understood that the accompanying drawings in the present application are only for the purpose of illustration and description, and are not intended to limit the protection scope of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. A flowchart, as used in this application, illustrates operations implemented according to some embodiments of the present application. It should be appreciated that the operations of the flow diagrams may be implemented out of order and that steps without logical context may be performed in reverse order or concurrently. Moreover, one or more other operations may be added to the flow diagrams and one or more operations may be removed from the flow diagrams as directed by those skilled in the art.
In addition, the described embodiments are only some, but not all, of the embodiments of the present application. The components of the embodiments of the present application, which are generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, as provided in the accompanying drawings, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, are intended to be within the scope of the present application.
To enable one skilled in the art to utilize the present disclosure, the following embodiments are provided in connection with a particular application scenario for which the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the disclosure.
First, application scenarios applicable to the present application will be described. The method and the device can be applied to the technical field of computers.
The research shows that the current intelligence quotient testing system has limitations, and mainly shows the following aspects: (1) The question banks of many systems are relatively fixed, meaning that once a user is familiar with a question, the accuracy of the test is compromised. However, updating or replacing the title can result in significant time and economic costs. (2) Most systems employ standardized methods, and few systems are capable of providing customized tests for individuals. (3) The interpretation and labeling of many exams relies on expert judgment or manually engaged interpretation labels, which not only increases cost, but can also lead to a degree of subjectivity. Therefore, how to quickly and accurately evaluate the cognitive ability of a tester becomes a non-trivial technical problem.
Based on the above, the embodiment of the application provides a cognitive ability evaluation method, which is used for efficiently generating the questions by using the question panels, the plurality of attribute rule pairs corresponding to the questions and the number of answer panels, and realizing multidimensional evaluation of the cognitive ability of the user by using the relation between the question generation parameters and the cognitive ability dimension, so as to evaluate the cognitive ability of the tester more accurately.
Referring to fig. 1, fig. 1 is a flowchart of a cognitive ability evaluation method according to an embodiment of the present application. As shown in fig. 1, a cognitive ability assessment method provided in an embodiment of the present application includes:
s101: analyzing the topic generation parameters to determine the attribute value and rule information of the determined panel for the topic; the question generation parameters comprise a question panel, a plurality of attribute rule pairs corresponding to the questions and the number of answer panels.
In the step, the title generation parameters are analyzed and processed to determine the attribute values and rule information of the determined panel.
The question generation parameters comprise a question panel, a plurality of attribute rule pairs corresponding to the questions and the number of answer panels, and the question generation parameters can be generated for user configuration.
Here, parameters are generated for the titleUnpacking it into<The panel of the title is provided with a display,<attribute 1, rule 1>,<Attribute 2, rule 2>,<Attribute 3, rule 3>,<Attribute 4, rule 4>Number of answer panels>And determining the attribute value of the determined panel and the rule information.
Here, the determined panel is a panel generated according to the topic generation parameters, and the determined panel has content information of the topic, so that the panel to be determined is determined according to the attribute value and rule information of the determined panel, thereby improving the efficiency and accuracy of the topic.
In one possible implementation, the topic generation parameter is determined by:
a: and determining attribute information of the topics selected by the user in the topic generation parameter definition interface, the panels of the topics, rule information of the topics and the number of answer panels.
Here, the attribute information of the title, the panel of the title, the rule information of the title, and the number of answer panels selected by the user at the title generation parameter definition interface are determined.
Wherein, a question is generally composed of a question panel and an answer panel. The problem panel is a matrix containing graphics or images, 3x3 in size, with a blank panel that needs to be filled. The answer panel is a list containing several graphics or images for the participants to choose from. In this scheme, the question generation parameters include a panel of questions, T attribute-rule pairs, and the number N of answer panels, collectively referred to as "question generation parameters". The topic generation parameters control the complexity of the topic and examine the tester's cognitive ability in multiple dimensions. The title generation parameter is a tuple Wherein->Representing the structure of the title, < >>Is a set of T attribute-rule pairs, e.gWherein->Representing attribute informationValue in a predefined set of attributes +.>，/>Representing rule information, dependent on a predefined rule set +.>，/>Is the number of answer panels. Attribute-rule pairs represent the application of specified attributes to specified rules.
The question panel is a panel corresponding to a question element in the question panel, for example, the question element may be graphic information. If the question panel is 3x3, the number of question panels is 8, and the last panel in the question panel is usually a blank panel. The panel structure names of the titles are Center, 2x2 Grid, 3x3 Grid, left-Right, up-Down, out-In Center, respectively. The Center corresponds to 1 panel 1 graph, the position is centered, the 2x2 Grid corresponds to 1 panel 4 graphs, the 2x2 distribution is realized, the 3x3 Grid corresponds to 1 panel 9 graphs, the 3x3 distribution is realized, the Left-Right corresponds to 1 panel 2 sub-panels, the Left-Right structure is realized, the Up-Down corresponds to 1 panel 2 sub-panels, the Up-In Center corresponds to 1 panel 2 sub-panels, the inside and outside structure is realized, the inside sub-panels only have one graph, the position is In the sub-panels, the Out-In Center corresponds to 1 panel 2 sub-panels, the inside and outside structure is realized, and the inside sub-panels are In the 2x2 Grid or 3x3 Grid.
The attribute information of the title includes the Number of graphics in the panel of the title (Number), the Position index value of the graphics in the panel of the title (Position), the shape of the graphics in the panel of the title (Type), the Size of the graphics in the panel of the title (Size), and the Color of the graphics in the panel of the title (Color).
The rule information comprises Constant rules, and the values of attribute information under rule management in the same row are not changed; the progress rule is monotonically increasing (decreasing), and in the same row, the attribute value is monotonically increasing (decreasing), and the increment (decrease) is 1 or 2; arithmic rules sum or subtract, same line class, attribute value of first panel plus attribute value of second panel equals attribute value of third panel. For the Position attribute, the implementation is set addition and subtraction. The rule is not applicable to the Type attribute; distribution Three rule, three distribution rules, three values are selected under the attribute under the rule management, and the Three values are distributed in different rows. If the first action [1, 2, 3], the second action [2, 3, 1], then the third action [3, 1, 2].
B: and processing the attribute information and the rule information based on a preset feasibility rule to generate a plurality of attribute rule pairs corresponding to the topics.
Here, the attribute information and the rule information are processed according to a preset feasibility rule, and a plurality of attribute rule pairs corresponding to the topics are generated.
Here, the topic generation parameters need to follow the feasibility rules. For example, for a panel structure of Center, the progress rule cannot be applied to the attributes Position and Number, because the structure Center has one and only one graphic, and cannot be incremented in the Number of graphics. The structural panel, attributes, rule feasibility tables are given below.
The feasibility rule is related to the panel structure, rule information and attribute information, and is set according to practical application, for example, for a panel Center, the progress rule cannot be applied to the attributes Position and Number, because the panel Center has one and only one graph, and cannot be increased in the Number of graphs.
C: and determining the title generation parameters based on the panels of the title, the attribute rule pairs corresponding to the title and the number of answer panels.
Here, the topic generation parameters are determined based on the topic panel, the topic-corresponding attribute rule pair, and the number of answer panels.
Here, the topic generation process is controlled by the topic generation parameters, and the setting has a direct influence on the difficulty level, complexity and cognitive ability field of investigation of the topic. These parameters may be specified directly by the user or may be dynamically adjusted based on the user's cognitive abilities. The user can set the question generation parameters according to the own requirements, including the panels of the questions, attribute-rule pairs, the number of answer panels, and the like. Through manually setting parameters, a user can more accurately control the generation process of the questions, so that the requirements of the user are better met. This approach is very flexible and can cope with a variety of different needs and scenarios. The system may infer the cognitive abilities of the user based on the user's performance in previous topics or other evaluation data and dynamically adjust the topic generation parameters accordingly. In this way, the system can automatically generate questions with moderate difficulty for the user, thereby better meeting the demands of the user. The method can effectively improve the learning effect and experience of the user, and is particularly suitable for personalized learning and education scenes.
S102: and based on the determined attribute values of the panels and the rule information, determining the attribute values of the panels to be determined of the questions, rendering the attribute values of the panels to be determined, and generating a question panel and an answer option panel of the questions corresponding to the question generation parameters.
In the step, according to the determined attribute values of the panels and the rule information, the attribute values of the panels to be determined of the questions are determined, the attribute values of the panels to be determined are rendered, and the question panels and the answer option panels of the questions corresponding to the question generation parameters are generated.
Here, the attribute values of the determined panels are sampled, and the sampled attribute values are applied to specific rules according to the selected rule information, so that the attribute values of other panels to be determined are calculated. This process continues until all panel attribute values are determined. By the method, the attribute value determining module can ensure that the generated problem panel accords with preset rules and conditions, and the efficiency of generating the questions can be improved.
In one possible implementation manner, the determining the attribute value of the panel to be determined of the title based on the determined attribute value of the panel and the rule information includes:
(1): and if the rule information of the attribute rule pair is the sum or subtraction rule information, determining the attribute value of the panel to be determined based on the attribute value of the first column of panels and the attribute value of the second column of panels in the determined panels.
Here, if the rule information of the attribute rule pair is sum or subtraction rule information, determining the attribute value of the panel to be determined according to the attribute value of the first column panel and the attribute value of the second column panel in the determined panels.
(2): and if the rule information of the attribute rule pair is monotonically increasing or decreasing information, determining the attribute value of the panel to be determined based on the attribute value of the first column of panels in the determined panel.
Here, if the rule information of the attribute rule pair is monotonically increasing or decreasing information, the attribute value of the panel to be determined is determined according to the attribute value of the first column of panels in the determined panel.
(3): and if the rule information of the attribute rule pair is constant information, determining the attribute value of the first column of panels in the determined panels as the attribute value of the panel to be determined.
Here, if the rule information of the attribute rule pair is constant information, the attribute value of the first column of panels among the determined panels is determined as the attribute value of the panel to be determined.
(4): and if the rule information of the attribute rule pair is three-distribution information, determining attribute values of three panels in the first row of the determined panels, and determining the attribute values of the panels to be determined.
Here, if the rule information of the attribute rule pair is three-distribution information, the attribute values of three panels in the first row of the determined panels determine the attribute values of the panels to be determined.
The three distribution information is to sample the attribute values of three panels in the first row at the same time, the attribute values of three panels in the second row are one arrangement of the three panels in the first row, and the third row is another arrangement.
In one possible implementation manner, the rendering the attribute value of the panel to be determined, generating a question panel and an answer option panel of the question corresponding to the question generation parameter, includes:
a: and rendering the attribute value of each panel to be determined to generate a question panel of the question.
Here, the attribute value of each panel to be determined is rendered, a question panel of the question is generated, and the panel at any position is removed in the rendering process.
b: and predicting a question answer attribute value based on the attribute value of the determined panel and the corresponding rule information, and adjusting at least one attribute value in the question answer attribute values to determine a plurality of wrong answers.
Here, according to the determined attribute values of the panel and the corresponding rule information, the attribute values of the answers to the questions are predicted, and at least one attribute value among the attribute values of the answers to the questions is adjusted to determine a plurality of wrong answers.
c: and generating an answer option panel of the question based on the plurality of wrong answers, the correct answers corresponding to the question answer attribute values and the number of answer panels.
Here, the answer option panel of the question is generated according to the plurality of wrong answers, the correct answers corresponding to the question answer attribute values, and the number of answer panels.
In a specific embodiment, for Number and Position attributes, there is only one graph under the Constant rule; for the Type attribute, sampling the Type attribute values of three panels of the first row, wherein the second row and the third row are respectively arranged in two types; and the rule facing the Color attribute in a mode of increasing 1 is adopted for the rule of the Size attribute, the Size attribute and the Color attribute are reduced by 1, under the progress rule, each row samples the attribute value of the first panel, the attribute values of the second column and the third column are calculated by the progress rule, and the attribute value of the final title generation panel is calculated as shown in the following table:
The attribute value of this table is rendered, and the panel at the last position is removed, so that the question panel of the title rendered by the table is shown in fig. 2. The answer attribute is set, and by adjusting one or more attribute values of the determined answer, the matching relationship between the attribute and the corresponding rule is destroyed, so that other alternative answers are generated, and an answer option panel for generating the questions is shown in fig. 3, wherein the panel 8 in fig. 3 is the correct answer in the embodiment.
S103: and controlling a tester to answer the questions based on the question panel and the answer option panel, determining target answers of the tester, and determining target cognitive ability evaluation data of the tester based on the target answers, the cognitive ability dimension vector and a plurality of attribute rule pairs.
In the step, a control tester responds to the questions according to the question panel and the answer option panel, determines a target answer of the tester, and determines target cognitive ability evaluation data of the tester according to the target answer, the cognitive ability dimension vector and a plurality of attribute rule pairs.
The target cognitive ability evaluation data is data for representing cognitive ability of the tester, and can be scores.
Wherein a series of cognitive ability dimensions, such as mathematical ability, shape awareness, logical reasoning, etc., are used with vectorsRepresenting the resulting cognitive ability dimension vector.
In one possible implementation manner, the determining the target cognitive ability evaluation data of the tester based on the target answer, the cognitive ability dimension vector and the attribute rule pairs includes:
i: and mapping each attribute rule pair with the cognitive ability dimension vector to determine a first weight vector, and mapping the title panel with the cognitive ability dimension vector to determine a second weight vector.
Here, each attribute rule pair is mapped with a cognitive ability dimension vector to determine a first weight vector, and a question panel is mapped with the cognitive ability dimension vector to determine a second weight vector.
Wherein for the structure and attribute-rule pairs in the topic generation parameters, each attribute-rule pair is determinedEach element affects the investigation of cognitive ability, so question panel +.>The cognitive ability profile examined can also be expressed as +.>. Each attribute-rule pair +.>Mapping to a vector yields a first weight +. >Each of which is->Representation->For->Individual cognitive competence dimension->Is a function of (a) and (b). For the topic structure->Mapping it to a cognitive ability vector to obtain a second weight vector. For example, for a certain attribute-rule pair +.>The cognitive vector examined is +.>Representing its 70% examining mathematical ability, 30% examining shape awareness.
II: and determining first cognitive ability evaluation data inspected by the title based on the weight of the panel, the first weight vector, the weight of the attribute rule pair, the number of the attribute rule pair and the second weight vector.
Here, the first cognitive ability evaluation data examined by the title is determined by the following formula:
wherein,is the weight of the panel, +.>Is->Weights of individual attribute-rule pairs. Weight here->And->Needs to be set up +.>For first cognitive ability assessment data, < +.>For the first weight vector, +.>As a second weight vector of the set of weights,Kis the number of attribute rule pairs.
III: and determining second cognitive ability evaluation data of the tester reflected by the target answer based on the corresponding first weight vector of the attribute rule pair corresponding to the target answer, the corresponding reward and punishment factor of the panel, the second weight vector and the number of the attribute rule pair.
Here, the second cognitive ability evaluation data of the tester reflected by the target answer is determined by the following formula:
wherein,is the weight of the panel, +.>Is a punishment factor corresponding to the panel, +.>For second cognitive ability assessment data, < >>For the first weight vector, +.>As a second weight vector of the set of weights,Kfor the number of attribute rule pairs +.>And the reward and punishment factor corresponding to the target answer is 0.
In one possible implementation manner, the determining the second cognitive ability evaluation data of the tester reflected by the target answer based on the first weight vector corresponding to the attribute rule pair corresponding to the target answer, the punishment factor corresponding to the panel, the second weight vector and the number of attribute rule pairs includes:
i: and if the target answer is a wrong answer, determining a corresponding first weight vector of the attribute rule pair violated by the wrong answer and the attribute rule pair violated by the wrong answer.
If the target answer is a wrong answer, determining a corresponding first weight vector of the attribute rule pair violated by the wrong answer and the attribute rule pair violated by the wrong answer.
ii: and determining second cognitive ability evaluation data of the tester reflected by the target answer based on the corresponding first weight vector of the attribute rule pair against which the wrong answer is violated, the reward and punishment factor of the wrong answer, the reward and punishment factor corresponding to the panel, the second weight vector and the number of the attribute rule pair.
And determining second cognitive ability evaluation data of the tester reflected by the target answer according to the corresponding first weight vector of the attribute rule pair against which the wrong answer is violated, the reward and punishment factor of the wrong answer, the reward and punishment factor corresponding to the panel, the second weight vector and the number of the attribute rule pair.
Wherein the testers choose wrong answers to reflect their weaknesses in cognitive ability. The wrong answer is violation of structural attribute rules and the like, and is setViolation->Attribute rule pair, then for its corresponding cognitive ability +.>Giving a penalty factor->Cognitive ability examined on a panel structure +.>Giving a penalty factor->。
In the scheme, the relation between the question generation parameters and the cognitive ability dimension is utilized, so that the multidimensional evaluation of the cognitive ability of the user is realized. There is a many-to-many mapping relationship between the topic generation parameters and the cognitive ability dimensions, which can be examined for multiple cognitive ability dimensions. When the user selects the wrong answer, it can be inferred, according to the attribute values of the wrong answer and the violation of the corresponding rules, which cognitive ability dimensions the user is deficient in.
IV: and controlling the tester to answer the next question to determine a second target answer, and performing iterative evaluation on the cognitive ability of the tester based on the first cognitive ability evaluation data inspected by the next question and the second cognitive ability evaluation data reflected by the second target answer until a plurality of questions are completed, so as to determine target cognitive ability evaluation data of the tester.
Here, the tester is controlled to answer the next question to determine a second target answer, and the cognitive ability of the tester is subjected to iterative evaluation according to the first cognitive ability evaluation data inspected by the next question and the second cognitive ability evaluation data reflected by the second target answer until the answer of a plurality of questions is completed, so that the target cognitive ability evaluation data of the tester is determined.
Here, the target cognitive ability evaluation data of the tester is determined by the following formula:
wherein,for first cognitive ability assessment data, < +.>For second cognitive ability assessment data, < >>For target cognitive ability assessment data, +.>Target cognitive ability evaluation data for the last question,/for the subject>Is a parameter.
In one possible implementation manner, after the control tester answers the questions based on the question panel and the answer option panel, determining a target answer of the tester, and determining the cognitive ability of the tester based on the target answer, the cognitive ability dimension vector and a plurality of attribute rule pairs, the cognitive ability evaluation method further includes:
Determining a target topic generation parameter matched with the cognitive ability of the tester based on a cosine similarity calculation formula; and generating the target topics in a self-adaptive mode based on the target topic generation parameters.
Here, the target topic generation parameter matched with the cognitive ability of the tester can be determined according to the cosine similarity calculation formula, and then the target topic can be generated in a self-adaptive manner according to the topic generation parameter.
In the scheme, a parameterization question setting method is adopted to normalize and structure a question generation process, and attribute rule pairs, a question structure and the like are adopted as question generation parameters. In this way, we can efficiently generate topics and form a huge topic library. Different attribute rule pairs correspond to different question generation modes, so that questions with different styles and difficulties are generated. By setting different attribute rule pairs, the attribute and rule of the questions can be accurately controlled, so that the user requirements are effectively met, and the diversification of the question bank is realized.
In one possible implementation manner, after the control tester answers the questions based on the question panel and the answer option panel, determining a target answer of the tester, and determining the cognitive ability of the tester based on the target answer, the cognitive ability dimension vector and a plurality of attribute rule pairs, the cognitive ability evaluation method further includes:
And respectively analyzing attribute information of each panel in the question panels of the questions, rule information in the question panels of the questions and answers of the questions based on an analysis preset template.
Here, the attribute information of each panel among the question panels of the questions, the rule information among the question panels of the questions, and the answers to the questions are analyzed according to the analysis preset templates, respectively.
The method is characterized in that the generated topic analysis adopts a mode of combining panel characteristics and a preset template library to realize spoken language interpretation, and is generally divided into three parts: panel attribute interpretation, rule interpretation, and answer interpretation. Panel attribute interpretation: this section explains the properties of each panel in detail. It generally includes descriptions of various features (e.g., shape, size, color, and number, etc.) in a graphic or image. By interpreting the attributes of each panel, the comprehender can be helped to more clearly understand the underlying information of the title. This section explains in detail how the properties of the missing panel are deduced from the existing panel according to the given rules. It generally relates to the elucidation of mathematical, logical, pattern matching, etc. operations in the application of rules. By interpreting the process of applying rules, an understanding of logical relationships in topics can be aided more deeply by an understanding. Answer interpretation: this section explains how to select the correct answer based on panel properties and rules. It typically includes an interpretation of answer choices and wrong answer choices. By interpreting the selection process of the answer, the comprehender can be helped to understand and solve the problem more accurately.
Here, for example, explanation is made for a type rule: panel attribute interpretation the shapes in the first row of three panels are: round, quadrilateral, hexagonal; panel attribute interpretation the shapes in the second row of three panels are: quadrilateral, hexagonal, circular; panel attribute interpretation the shapes in the first two panels of the third row are: hexagonal and circular; the first two rows are each an arrangement of [ circular, quadrilateral, hexagonal ]; the final panel is quadrilateral in shape, constituting a third arrangement [ hexagonal, circular, quadrilateral ].
In one possible implementation manner, after the control tester answers the questions based on the question panel and the answer option panel, determining a target answer of the tester, and determining the cognitive ability of the tester based on the target answer, the cognitive ability dimension vector and a plurality of attribute rule pairs, the cognitive ability evaluation method further includes:
comparing the attribute values of the wrong answer option panels and the attribute values of the correct answer option panels in the answer option panels, and determining the attribute value difference between the wrong answer option panels and the correct answer option panels; and carrying out wrong answer analysis on the attribute value difference between the wrong answer option panel and the correct answer option panel based on a wrong answer analysis preset library.
And comparing the attribute values of the wrong answer option panels and the attribute values of the correct answer option panels in the answer option panels, determining the attribute value difference between the wrong answer option panels and the correct answer option panels, and analyzing the wrong answer according to the attribute value difference between the wrong answer option panels and the correct answer option panels by a wrong answer analysis preset library.
Here, the wrong answer parsing may be as follows:
according to the method and the device, the analysis is automatically generated without the intervention of an expert, and the interpretation can be automatically generated for the title by utilizing the interpretation generation module. Such interpretation not only allows the user to more easily understand questions and answers, but also helps the user identify their own points of cognitive weakness. The patent adopts a mode of presetting a template library to generate spoken language interpretation. The templates are composed of natural language in the corpus, so that the generation of interpretation is avoided to a certain extent, and the interpretation is more in line with the expression habit and the sense of language of people.
Further, referring to fig. 4, fig. 4 is a schematic diagram of a cognitive ability evaluation method according to an embodiment of the present application. As shown in fig. 4, a question generation module of the cognitive ability evaluation device acquires a question generation parameter, determines an attribute value and rule information of a panel, renders the attribute value of the panel to be determined according to the attribute value of the panel to be determined, generates a question panel and an answer option panel of a question corresponding to the question generation parameter, and the cognitive ability evaluation module controls a tester to answer the question and determines target cognitive ability evaluation data of the tester according to the answer of the tester and the question. The analysis generating module analyzes the attribute information of each panel in the question panels of the questions, the rule information in the question panels of the questions, the answers of the questions and the wrong answers according to the analysis preset template.
The cognitive ability evaluation method provided by the embodiment of the application comprises the following steps: analyzing the topic generation parameters to determine the attribute values and rule information of the determined panels; the title generation parameters comprise a panel of a title, a plurality of attribute rule pairs corresponding to the title and the number of answer panels; based on the determined attribute values of the panels and the rule information, determining the attribute values of the panels to be determined of the questions, rendering the attribute values of the panels to be determined, and generating a question panel and an answer option panel of the questions corresponding to the question generation parameters; and controlling a tester to answer the questions based on the question panel and the answer option panel, determining target answers of the tester, and determining target cognitive ability evaluation data of the tester based on the target answers, the cognitive ability dimension vector and a plurality of attribute rule pairs. The questions are efficiently generated by using the question panels, the plurality of attribute rule pairs corresponding to the questions and the number of answer panels, and the multidimensional assessment of the cognitive ability of the user is realized by using the relation between the question generation parameters and the cognitive ability dimension, so that the cognitive ability of the tester is more accurately assessed.
Referring to fig. 5 and 6, fig. 5 is a schematic structural diagram of a cognitive ability evaluation device according to an embodiment of the present disclosure; fig. 6 is a second schematic structural diagram of a cognitive ability evaluation device according to an embodiment of the present disclosure. As shown in fig. 5, the cognitive ability evaluation device 500 includes:
the processing module 510 is configured to analyze the topic generation parameter, and determine an attribute value and rule information of a determined panel for the topic; the title generation parameters comprise a panel of a title, a plurality of attribute rule pairs corresponding to the title and the number of answer panels;
the question generation module 520 is configured to determine an attribute value of a panel to be determined of the question based on the determined attribute value of the panel and rule information, render the attribute value of the panel to be determined, and generate a question panel and an answer option panel of the question corresponding to the question generation parameter;
the cognitive ability evaluation module 530 is configured to control a tester to answer the question based on the question panel and the answer option panel, determine a target answer of the tester, and determine target cognitive ability evaluation data of the tester based on the target answer, the cognitive ability dimension vector, and a plurality of attribute rule pairs.
Further, when the topic generation module 520 is configured to determine the attribute value of the panel to be determined of the topic based on the determined attribute value of the panel and the rule information, the topic generation module 520 is specifically configured to:
if the rule information of the attribute rule pair is the sum or subtraction rule information, determining the attribute value of the panel to be determined based on the attribute value of the first column panel and the attribute value of the second column panel in the determined panels;
if the rule information of the attribute rule pair is monotonically increasing or decreasing information, determining an attribute value of a panel to be determined based on the attribute value of a first column of panels in the determined panels;
if the rule information of the attribute rule pair is constant information, determining the attribute value of the first column of panels in the determined panels as the attribute value of the panel to be determined;
and if the rule information of the attribute rule pair is three-distribution information, determining attribute values of three panels in the first row of the determined panels, and determining the attribute values of the panels to be determined.
Further, when the question generation module 520 is configured to render the attribute value of the panel to be determined, and generate a question panel and an answer option panel of the question corresponding to the question generation parameter, the question generation module 520 is specifically configured to:
Rendering the attribute value of each panel to be determined to generate a question panel of the question;
predicting a question answer attribute value based on the attribute value of the determined panel and the corresponding rule information, and adjusting at least one attribute value in the question answer attribute values to determine a plurality of wrong answers;
and generating an answer option panel of the question based on the plurality of wrong answers, the correct answers corresponding to the question answer attribute values and the number of answer panels.
Further, when the cognitive ability evaluation module 530 is configured to determine the target cognitive ability evaluation data of the tester based on the target answer, the cognitive ability dimension vector and the plurality of attribute rule pairs, the cognitive ability evaluation module 530 is specifically configured to:
mapping each attribute rule pair with the cognitive ability dimension vector to determine a first weight vector, and mapping the topic panel with the cognitive ability dimension vector to determine a second weight vector;
determining first cognitive ability evaluation data inspected by the title based on the weight of the panel, the first weight vector, the weight of the attribute rule pairs, the number of the attribute rule pairs and the second weight vector;
Determining second cognitive ability evaluation data of the tester reflected by the target answer based on the corresponding first weight vector of the attribute rule pair corresponding to the target answer, the corresponding reward and punishment factor of the panel, the second weight vector and the number of the attribute rule pair;
and controlling the tester to answer the next question to determine a second target answer, and performing iterative evaluation on the cognitive ability of the tester based on the first cognitive ability evaluation data inspected by the next question and the second cognitive ability evaluation data reflected by the second target answer until a plurality of questions are completed, so as to determine target cognitive ability evaluation data of the tester.
Further, when the cognitive ability evaluation module 530 is configured to determine the second cognitive ability evaluation data of the tester reflected by the target answer based on the first weight vector corresponding to the attribute rule pair corresponding to the target answer, the punishment factor corresponding to the panel, the second weight vector, and the number of attribute rule pairs, the cognitive ability evaluation module 530 is specifically configured to:
If the target answer is a wrong answer, determining a corresponding first weight vector of an attribute rule pair violated by the wrong answer and an attribute rule pair violated by the wrong answer;
and determining second cognitive ability evaluation data of the tester reflected by the target answer based on the corresponding first weight vector of the attribute rule pair against which the wrong answer is violated, the reward and punishment factor of the wrong answer, the reward and punishment factor corresponding to the panel, the second weight vector and the number of the attribute rule pair.
Further, as shown in fig. 6, the cognitive ability evaluation device 500 further includes an adaptive topic generation module 540, where the adaptive topic generation module 540 is configured to:
determining a target topic generation parameter matched with the cognitive ability of the tester based on a cosine similarity calculation formula;
and generating the target topics in a self-adaptive mode based on the target topic generation parameters.
Further, as shown in fig. 6, the cognitive ability evaluation device 500 further includes a resolution generation module 550, where the resolution generation module 550 is configured to:
and respectively analyzing attribute information of each panel in the question panels of the questions, rule information in the question panels of the questions and answers of the questions based on an analysis preset template.
Further, the parsing generation module 550 is further configured to:
comparing the attribute values of the wrong answer option panels and the attribute values of the correct answer option panels in the answer option panels, and determining the attribute value difference between the wrong answer option panels and the correct answer option panels;
and carrying out wrong answer analysis on the attribute value difference between the wrong answer option panel and the correct answer option panel based on a wrong answer analysis preset library.
Further, as shown in fig. 6, the cognitive ability evaluation device 500 further includes a topic parameter generation module 560, where the topic parameter generation module 560 is configured to:
determining attribute information of a question selected by a user in a question generation parameter definition interface, a panel of the question, rule information of the question and the number of answer panels;
processing the attribute information and the rule information based on a preset feasibility rule to generate a plurality of attribute rule pairs corresponding to the topics;
determining the title generation parameters based on the panel of the title, the attribute rule pair corresponding to the title and the number of answer panels;
the attribute information comprises the number of graphics in the panel of the question, the slot index value of the graphics in the panel of the question, the shape of the graphics in the panel of the question, the size of the graphics in the panel of the question and the color of the graphics in the panel of the question.
The embodiment of the application provides a cognitive ability evaluation device, cognitive ability evaluation device includes: the processing module is used for analyzing the topic generation parameters and determining the attribute value and rule information of the determined panel; the title generation parameters comprise a panel of a title, a plurality of attribute rule pairs corresponding to the title and the number of answer panels; the title generation module is used for determining the attribute value of the panel to be determined of the title based on the determined attribute value of the panel and the rule information, rendering the attribute value of the panel to be determined, and generating a question panel and an answer option panel of the title corresponding to the title generation parameter; and the cognitive ability evaluation module is used for controlling a tester to answer the questions based on the question panel and the answer option panel, determining a target answer of the tester, and determining target cognitive ability evaluation data of the tester based on the target answer, the cognitive ability dimension vector and a plurality of attribute rule pairs. The questions are efficiently generated by using the question panels, the plurality of attribute rule pairs corresponding to the questions and the number of answer panels, and the multidimensional assessment of the cognitive ability of the user is realized by using the relation between the question generation parameters and the cognitive ability dimension, so that the cognitive ability of the tester is more accurately assessed.
Referring to fig. 7, fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 7, the electronic device 700 includes a processor 710, a memory 720, and a bus 730.
The memory 720 stores machine-readable instructions executable by the processor 710, when the electronic device 700 is running, the processor 710 communicates with the memory 720 through the bus 730, and when the machine-readable instructions are executed by the processor 710, a step of a cognitive ability assessment method in the method embodiment shown in fig. 1 may be executed, and a specific implementation may refer to the method embodiment and will not be described herein.
The embodiment of the present application further provides a computer readable storage medium, where a computer program is stored on the computer readable storage medium, and when the computer program is executed by a processor, the steps of a cognitive ability assessment method in the method embodiment shown in fig. 1 may be executed, and a specific implementation manner may refer to the method embodiment and will not be described herein.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Finally, it should be noted that: the foregoing examples are merely specific embodiments of the present application, and are not intended to limit the scope of the present application, but the present application is not limited thereto, and those skilled in the art will appreciate that while the foregoing examples are described in detail, the present application is not limited thereto. Any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or make equivalent substitutions for some of the technical features within the technical scope of the disclosure of the present application; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (12)

1. A cognitive ability assessment method, characterized in that the cognitive ability assessment method comprises:
analyzing the topic generation parameters to determine the attribute value and rule information of the determined panel for the topic; the title generation parameters comprise a panel of a title, a plurality of attribute rule pairs corresponding to the title and the number of answer panels;
based on the determined attribute values of the panels and the rule information, determining the attribute values of the panels to be determined of the questions, rendering the attribute values of the panels to be determined, and generating a question panel and an answer option panel of the questions corresponding to the question generation parameters;
and controlling a tester to answer the questions based on the question panel and the answer option panel, determining target answers of the tester, and determining target cognitive ability evaluation data of the tester based on the target answers, the cognitive ability dimension vector and a plurality of attribute rule pairs.
2. The cognitive ability assessment method according to claim 1, wherein the determining the attribute value of the panel to be determined for the topic based on the determined attribute value of the panel and rule information comprises:
If the rule information of the attribute rule pair is the sum or subtraction rule information, determining the attribute value of the panel to be determined based on the attribute value of the first column panel and the attribute value of the second column panel in the determined panels;
if the rule information of the attribute rule pair is monotonically increasing or decreasing information, determining an attribute value of a panel to be determined based on the attribute value of a first column of panels in the determined panels;
if the rule information of the attribute rule pair is constant information, determining the attribute value of the first column of panels in the determined panels as the attribute value of the panel to be determined;
and if the rule information of the attribute rule pair is three-distribution information, determining attribute values of three panels in the first row of the determined panels, and determining the attribute values of the panels to be determined.
3. The cognitive ability assessment method according to claim 1, wherein the rendering the attribute values of the panel to be determined, generating a question panel and an answer option panel of a question corresponding to the question generation parameter, includes:
rendering the attribute value of each panel to be determined to generate a question panel of the question;
Predicting a question answer attribute value based on the attribute value of the determined panel and the corresponding rule information, and adjusting at least one attribute value in the question answer attribute values to determine a plurality of wrong answers;
and generating an answer option panel of the question based on the plurality of wrong answers, the correct answers corresponding to the question answer attribute values and the number of answer panels.
4. The cognitive ability assessment method according to claim 1, wherein the determining the target cognitive ability assessment data of the tester based on the target answer, a cognitive ability dimension vector, and a plurality of attribute rule pairs comprises:
mapping each attribute rule pair with the cognitive ability dimension vector to determine a first weight vector, and mapping the topic panel with the cognitive ability dimension vector to determine a second weight vector;
determining first cognitive ability evaluation data inspected by the title based on the weight of the panel, the first weight vector, the weight of the attribute rule pairs, the number of the attribute rule pairs and the second weight vector;
determining second cognitive ability evaluation data of the tester reflected by the target answer based on the corresponding first weight vector of the attribute rule pair corresponding to the target answer, the corresponding reward and punishment factor of the panel, the second weight vector and the number of the attribute rule pair;
And controlling the tester to answer the next question to determine a second target answer, and performing iterative evaluation on the cognitive ability of the tester based on the first cognitive ability evaluation data inspected by the next question and the second cognitive ability evaluation data reflected by the second target answer until a plurality of questions are completed, so as to determine target cognitive ability evaluation data of the tester.
5. The cognitive ability assessment method according to claim 4, wherein the determining the second cognitive ability assessment data of the tester reflected by the target answer based on the number of the attribute rule pairs corresponding to the target answer, the first weight vector corresponding to the attribute rule pairs corresponding to the target answer, the punishment factors corresponding to the panel, the second weight vector, and the attribute rule pairs includes:
if the target answer is a wrong answer, determining a corresponding first weight vector of an attribute rule pair violated by the wrong answer and an attribute rule pair violated by the wrong answer;
and determining second cognitive ability evaluation data of the tester reflected by the target answer based on the corresponding first weight vector of the attribute rule pair against which the wrong answer is violated, the reward and punishment factor of the wrong answer, the reward and punishment factor corresponding to the panel, the second weight vector and the number of the attribute rule pair.
6. The cognitive ability assessment method according to claim 1, wherein after the control tester answers the questions based on the question panel and the answer option panel, determining a target answer of the tester, and determining the cognitive ability of the tester based on the target answer, a cognitive ability dimension vector, and a plurality of attribute rule pairs, the cognitive ability assessment method further comprises:
determining a target topic generation parameter matched with the cognitive ability of the tester based on a cosine similarity calculation formula;
and generating the target topics in a self-adaptive mode based on the target topic generation parameters.
7. The cognitive ability assessment method according to claim 1, wherein after the control tester answers the questions based on the question panel and the answer option panel, determining a target answer of the tester, and determining the cognitive ability of the tester based on the target answer, a cognitive ability dimension vector, and a plurality of attribute rule pairs, the cognitive ability assessment method further comprises:
and respectively analyzing attribute information of each panel in the question panels of the questions, rule information in the question panels of the questions and answers of the questions based on an analysis preset template.
8. The cognitive ability assessment method according to claim 1, wherein after the control tester answers the questions based on the question panel and the answer option panel, determining a target answer of the tester, and determining the cognitive ability of the tester based on the target answer, a cognitive ability dimension vector, and a plurality of attribute rule pairs, the cognitive ability assessment method further comprises:
comparing the attribute values of the wrong answer option panels and the attribute values of the correct answer option panels in the answer option panels, and determining the attribute value difference between the wrong answer option panels and the correct answer option panels;
and carrying out wrong answer analysis on the attribute value difference between the wrong answer option panel and the correct answer option panel based on a wrong answer analysis preset library.
9. The cognitive ability assessment method according to claim 1, wherein the topic generation parameters are determined by:
determining attribute information of a question selected by a user in a question generation parameter definition interface, a panel of the question, rule information of the question and the number of answer panels;
Processing the attribute information and the rule information based on a preset feasibility rule to generate a plurality of attribute rule pairs corresponding to the topics;
determining the title generation parameters based on the panel of the title, the attribute rule pair corresponding to the title and the number of answer panels;
the attribute information comprises the number of graphics in the panel of the question, the slot index value of the graphics in the panel of the question, the shape of the graphics in the panel of the question, the size of the graphics in the panel of the question and the color of the graphics in the panel of the question.
10. A cognitive ability assessment apparatus, characterized in that the cognitive ability assessment apparatus comprises:
the processing module is used for analyzing the topic generation parameters and determining the attribute value and rule information of the determined panel of the topic; the title generation parameters comprise a panel of a title, a plurality of attribute rule pairs corresponding to the title and the number of answer panels;
the title generation module is used for determining the attribute value of the panel to be determined of the title based on the determined attribute value of the panel and the rule information, rendering the attribute value of the panel to be determined, and generating a question panel and an answer option panel of the title corresponding to the title generation parameter;
And the cognitive ability evaluation module is used for controlling a tester to answer the questions based on the question panel and the answer option panel, determining a target answer of the tester, and determining target cognitive ability evaluation data of the tester based on the target answer, the cognitive ability dimension vector and a plurality of attribute rule pairs.
11. An electronic device, comprising: a processor, a memory and a bus, said memory storing machine readable instructions executable by said processor, said processor and said memory communicating via said bus when the electronic device is running, said machine readable instructions when executed by said processor performing the steps of the cognitive ability assessment method according to any one of claims 1 to 9.
12. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, performs the steps of the cognitive ability assessment method according to any one of claims 1 to 9.
CN202311559696.7A 2023-11-22 2023-11-22 Cognitive ability evaluation method and device, electronic equipment and storage medium Active CN117257304B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311559696.7A CN117257304B (en) 2023-11-22 2023-11-22 Cognitive ability evaluation method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311559696.7A CN117257304B (en) 2023-11-22 2023-11-22 Cognitive ability evaluation method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN117257304A true CN117257304A (en) 2023-12-22
CN117257304B CN117257304B (en) 2024-03-01

Family

ID=89216451

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311559696.7A Active CN117257304B (en) 2023-11-22 2023-11-22 Cognitive ability evaluation method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117257304B (en)

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006079113A (en) * 2005-10-03 2006-03-23 Nec Corp Test problem setting system, test problem setting method and program therefor
CN102012959A (en) * 2009-09-08 2011-04-13 刘金硕 Mathematical modeling method for automatically constructing graph intelligence topic generation cognitive system
CN106409041A (en) * 2016-11-22 2017-02-15 深圳市鹰硕技术有限公司 Generation method and system for gap filling test question and grading method and system for gap filling test paper
US20170105666A1 (en) * 2014-07-08 2017-04-20 Samsung Electronics Co., Ltd. Cognitive function test device and method
US20180060279A1 (en) * 2016-08-28 2018-03-01 Leaderamp, Inc. System and method for creating a metrological/psychometric instrument
CN108133736A (en) * 2017-12-22 2018-06-08 谢海群 A kind of adaptivity cognitive function appraisal procedure and system
CN110400636A (en) * 2019-06-21 2019-11-01 首都医科大学附属北京天坛医院 Recognize appraisal procedure, device, computer equipment and storage medium
CN110752033A (en) * 2019-08-30 2020-02-04 康美健康云服务有限公司 Informationization method and system for cognitive assessment and readable storage medium
CN112786202A (en) * 2021-01-27 2021-05-11 安徽华米健康科技有限公司 Health awareness parameter detection method and device, electronic equipment and storage medium
CN113796834A (en) * 2021-09-18 2021-12-17 北京世纪好未来教育科技有限公司 Cognitive ability assessment method, device, equipment and storage medium
CN114547122A (en) * 2022-02-22 2022-05-27 平安科技（深圳）有限公司 Test question generation method and device, electronic equipment and storage medium
CN115471903A (en) * 2021-06-11 2022-12-13 见臻科技股份有限公司 Cognitive assessment system
CN115910325A (en) * 2022-11-25 2023-04-04 首都医科大学宣武医院 Modeling method for cognitive task evaluation, cognitive task evaluation method and system
CN115966274A (en) * 2022-12-20 2023-04-14 平安臻颐年(上海)企业管理有限公司 Method and device for screening questionnaire questions, electronic equipment and storage medium

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006079113A (en) * 2005-10-03 2006-03-23 Nec Corp Test problem setting system, test problem setting method and program therefor
CN102012959A (en) * 2009-09-08 2011-04-13 刘金硕 Mathematical modeling method for automatically constructing graph intelligence topic generation cognitive system
US20170105666A1 (en) * 2014-07-08 2017-04-20 Samsung Electronics Co., Ltd. Cognitive function test device and method
US20180060279A1 (en) * 2016-08-28 2018-03-01 Leaderamp, Inc. System and method for creating a metrological/psychometric instrument
CN106409041A (en) * 2016-11-22 2017-02-15 深圳市鹰硕技术有限公司 Generation method and system for gap filling test question and grading method and system for gap filling test paper
CN108133736A (en) * 2017-12-22 2018-06-08 谢海群 A kind of adaptivity cognitive function appraisal procedure and system
CN110400636A (en) * 2019-06-21 2019-11-01 首都医科大学附属北京天坛医院 Recognize appraisal procedure, device, computer equipment and storage medium
CN110752033A (en) * 2019-08-30 2020-02-04 康美健康云服务有限公司 Informationization method and system for cognitive assessment and readable storage medium
CN112786202A (en) * 2021-01-27 2021-05-11 安徽华米健康科技有限公司 Health awareness parameter detection method and device, electronic equipment and storage medium
CN115471903A (en) * 2021-06-11 2022-12-13 见臻科技股份有限公司 Cognitive assessment system
CN113796834A (en) * 2021-09-18 2021-12-17 北京世纪好未来教育科技有限公司 Cognitive ability assessment method, device, equipment and storage medium
CN114547122A (en) * 2022-02-22 2022-05-27 平安科技（深圳）有限公司 Test question generation method and device, electronic equipment and storage medium
CN115910325A (en) * 2022-11-25 2023-04-04 首都医科大学宣武医院 Modeling method for cognitive task evaluation, cognitive task evaluation method and system
CN115966274A (en) * 2022-12-20 2023-04-14 平安臻颐年(上海)企业管理有限公司 Method and device for screening questionnaire questions, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN117257304B (en) 2024-03-01

Similar Documents

Publication Publication Date Title
Ravand et al. Partial least squares structural equation modeling with R
Purwanto Education research quantitative analysis for little respondents: comparing of Lisrel, Tetrad, GSCA, Amos, SmartPLS, WarpPLS, and SPSS
Depaoli et al. The importance of prior sensitivity analysis in Bayesian statistics: demonstrations using an interactive Shiny App
JP7474517B2 (en) Machine learning method, device and computer program for providing personalized educational content based on learning efficiency
Joo et al. Integrating user interface and personal innovativeness into the TAM for mobile learning in Cyber University
US11417232B2 (en) Method, apparatus, and computer program for operating machine-learning framework
Derya GURER et al. Factors affecting students' attitudes toward computer programming
US20120231439A1 (en) Method of Model Scaling for an Automated Essay Scoring System
CN111159419B (en) Knowledge tracking data processing method, system and storage medium based on graph convolution
Ni et al. Deepqr: Neural-based quality ratings for learnersourced multiple-choice questions
KR102075936B1 (en) Method, apparatus and computer program for operating a machine learning for providing personalized educational contents based on learning efficiency
Cook Measurement of cognitive load during multimedia learning activities
US20130004931A1 (en) Computer-Implemented Systems and Methods for Determining Content Analysis Metrics for Constructed Responses
Stütz et al. Characteristics of learning tasks in accounting textbooks: an AI assisted analysis
Costa et al. Automatic classification of computational thinking skills in elementary school math questions
KR101836206B1 (en) Method, apparatus and computer program for providing personalized educational contents
Ozbey et al. The determination and analysis of factors affecting to student learning by artificial intelligence in higher education
CN117257304B (en) Cognitive ability evaluation method and device, electronic equipment and storage medium
Patil et al. Visualization of statistically significant correlation coefficients from a correlation matrix: a call for a change in practice
US20220300836A1 (en) Machine Learning Techniques for Generating Visualization Recommendations
Baran et al. PRACTICAL TRAINING OF STUDENTS THROUGH THE IMPLEMENTATION OF PROJECTS IN THE FIELD OF INTERFACE DESIGN AND SYSTEMS ERGONOMICS
Gordon et al. Visualizing and Understanding Hypothesis Testing Using Dynamic Software
Uglev et al. Synthesizing Didactic Explanatory Texts in Intelligent Tutoring Systems Based on the Information in Cognitive Maps
Bayés et al. A study on statistical technological and pedagogical content knowledge on an innovative course on quantitative research methods
KR20180127188A (en) Method, apparatus and computer program for operating a machine learning framework for providing personalized educational contents

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant