WO2023029430A1

WO2023029430A1 - Cognitive ability testing method, device, electrinic apparatus and storage medium

Info

Publication number: WO2023029430A1
Application number: PCT/CN2022/080226
Authority: WO
Inventors: 薛贵
Original assignee: 北京无疆脑智科技有限公司
Priority date: 2021-09-06
Filing date: 2022-03-10
Publication date: 2023-03-09
Also published as: CN114098730A; CN113468077B; CN113468077A; CN114098730B

Abstract

Disclosed are a cognitive ability testing method, a device, an electronic apparatus and a storage medium, involving: within a knowledge map of cognitive ability to be tested, pre-establishing each cognitive sub-ability to be tested and also correlation coefficients between various cognitive sub-abilities to be tested; then, beginning testing from a cognitive sub-ability to be tested corresponding to a central node in the knowledge map of cognitive ability to be tested; in the testing process, using already-tested test values for cognitive sub-abilities to be tested and also the correlation coefficients between nodes in the knowledge map of cognitive ability to be tested for determining, in real time, test values for as-yet-untested cognitive sub-abilities to be tested. If prediction of an as-yet-untested cognitive sub-ability to be tested reaches a preset test operation end condition, no further testing needs to be conducted on the as-yet-untested cognitive sub-ability to be tested, and the test can be ended, thus reducing the number of testing tasks and the time to complete the testing tasks by a subject, making subject cooperation easier to obtain, and improving testing efficiency.

Description

Cognitive ability test method, device, electronic device and storage medium

technical field

The embodiments of the present disclosure relate to the technical field of cognitive ability testing, and specifically relate to a cognitive ability testing method, device, electronic equipment, and storage medium.

Background technique

Cognitive ability refers to the ability of an individual to receive, process and process information, including attention, memory, thinking, reaction, self-control, etc. Cognitive ability has great influence on people's life, study and work. In order to achieve talent selection, disease diagnosis and ability assessment, a comprehensive assessment of cognitive ability is of great value and significance. At the same time, on the basis of cognitive ability assessment, targeted intervention training can also be provided. Therefore, a comprehensive and accurate assessment of cognitive ability can improve the pertinence and effectiveness of training.

Contents of the invention

Embodiments of the present disclosure provide a cognitive ability testing method, device, electronic equipment, and storage medium.

In the first aspect, an embodiment of the present disclosure provides a method for testing cognitive ability, the method comprising: obtaining a knowledge map of cognitive ability to be tested, the knowledge map of cognitive ability to be tested includes N nodes and the N The correlation coefficient between any two nodes in the nodes, each of the nodes is in one-to-one correspondence with the cognitive ability sub-ability to be tested in the preset cognitive ability sub-ability set to be tested, and each node corresponds to a A set of test tasks for the sub-ability of the cognitive ability to be tested; the central node in the N nodes is used as the current node to perform the following test operations: determine the task to be tested in the test task set associated with the current node; provide the test task, and obtain the task completion parameter information of the subject to complete the task to be tested; according to the task completion parameter information, determine that the subject corresponds to the test of the cognitive ability sub-ability to be tested corresponding to the current node value; according to the test value of the subject’s cognitive ability sub-ability corresponding to each node that has performed the test operation and each correlation coefficient in the knowledge map of the cognitive ability sub-ability to be tested, estimate the The subject corresponds to the test value of the cognitive ability sub-ability to be tested corresponding to the node in the knowledge map of the cognitive ability sub-ability to be tested that does not perform the test operation; determine whether the preset test operation end condition is met; respond to the determination Yes, end the test operation. In some optional embodiments, the method further includes: according to the test value of the subject corresponding to each cognitive ability to be tested in the preset cognitive ability set to be tested, Determining a task to be trained corresponding to the subject from a preset training task set, wherein each preset training task corresponds to a cognitive ability to be tested in the preset cognitive ability set to be tested; providing the task to be trained, and obtain task completion parameter information for the subject to complete the task to be trained.

In some optional embodiments, the method further includes: according to the test value of the subject corresponding to each cognitive ability sub-ability in the preset cognitive ability sub-ability set to be tested, from the preset In the training task set, the task to be trained corresponding to the subject is determined, wherein each of the preset training tasks corresponds to the cognitive ability sub-ability to be tested in the preset cognitive ability sub-ability set to be tested; The task to be trained is provided, and task completion parameter information for the subject to complete the task to be trained is acquired.

In some optional implementation manners, after the task to be trained is provided, and the subject completes the task completion parameter information of the task to be trained, the method further includes: using the cognition to be tested The central node among the N nodes of the ability knowledge graph is the current node, and the test operation is performed again to obtain the cognitive ability to be tested corresponding to the preset cognitive ability sub-ability set to be tested after the subject completes the training task. The test value of the cognitive ability sub-ability; according to the difference between the test values of the cognitive ability sub-ability to be tested in the preset cognitive ability sub-ability set to be tested according to the subject before completing the training task and after completing the training task, Determining training effect information for the subject.

In some optional implementation manners, according to the test value of the subject corresponding to each cognitive ability sub-ability in the preset cognitive ability sub-ability set to be tested, from the preset training task set Determining the task to be trained corresponding to the subject includes: selecting the subject with the smallest test value of the cognitive ability sub-ability to be tested corresponding to the subject in the preset cognitive ability sub-ability set to be tested Determine the cognitive ability sub-ability to be trained as the cognitive ability sub-ability to be trained; determine the candidate training tasks corresponding to the cognitive ability sub-ability to be trained in the training task set; determine the selected training tasks in each determined candidate training task Describe the training task.

In some optional implementation manners, each training task in the training task set has a corresponding difficulty coefficient; and determining the task to be trained among the determined candidate training tasks includes: according to a preset test value The corresponding relationship between the range and the range of the difficulty coefficient of the training task is to determine the range of the difficulty coefficient of the training task corresponding to the test value of the cognitive ability sub-ability to be trained, wherein the test value of the cognitive ability sub-ability to be trained is corresponding to the subject The test value of the sub-ability of the cognitive ability to be trained; among the determined candidate training tasks, the candidate training tasks whose difficulty coefficient is within the determined difficulty coefficient range are determined as the task to be trained.

In some optional implementation manners, the method further includes: according to the task completion parameter information of the subject completing the task to be trained, determining the completion degree score of the subject to complete the task to be trained.

In some optional implementation manners, the method further includes: determining the range of difficulty coefficient of the next task to be trained according to the degree of completion of the task to be trained by the subject; The candidate training task whose difficulty coefficient in the task is within the determined difficulty coefficient range of the next task to be trained is determined as the next task to be trained; the next task to be trained is provided, and the subject completes the The task completion parameter information of the next task to be trained.

In some optional implementation manners, the test operation further includes: in response to determining that the preset end condition of the test operation is not met, according to the subject corresponding to the cognitive ability knowledge map to be tested, the test is not performed The correlation coefficient between the operated node and the current node is used to determine the next node to be tested; and the next node to be tested is used as the current node, and the test operation is continued.

In some optional implementation manners, the next test subject is determined according to the correlation coefficient between the subject and the current node in the cognitive ability knowledge map corresponding to the subject that has not performed the test operation. The node includes: determining the node with the smallest correlation coefficient with the current node among the nodes in the cognitive ability knowledge map corresponding to the subject to be tested that has not performed the test operation, as the next node to be tested measuring node.

In some optional implementation manners, before performing the following test operations with the central node among the N nodes as the current node, the method further includes: determining the N nodes based on the cognitive ability knowledge map to be tested The central node in the node.

In some optional implementation manners, the determining the central node among the N nodes based on the cognitive ability knowledge map to be tested includes: determining the sum of correlation coefficients of each node among the N nodes, wherein, The sum of the correlation coefficients of a node is the sum of the correlation coefficients of other nodes different from the node among the N nodes and the node; the node with the largest correlation coefficient sum among the N nodes is determined as the central node.

In some optional implementation manners, the knowledge map of the cognitive ability to be tested is pre-established through the following knowledge map building step: obtaining an initial knowledge map of the cognitive ability to be tested, the initial knowledge map of the cognitive ability to be tested includes N nodes, each node in the initial cognitive ability knowledge map to be tested is in one-to-one correspondence with the cognitive ability sub-ability to be tested in the preset cognitive ability sub-ability set to be tested, and correspondingly used for testing the node A set of test tasks corresponding to the sub-ability of the cognitive ability to be tested; obtaining a set of training samples, wherein the training samples include the test tasks in the test task set corresponding to the nodes in the initial cognitive ability knowledge graph to be tested by the sample subject Sample task performance parameter information and corresponding label test values corresponding to each cognitive ability sub-ability in the preset cognitive ability sub-ability set to be tested; using machine learning methods, based on the training sample set The correlation coefficient between any two nodes in the cognitive ability knowledge map to be tested is adjusted; the initial cognitive ability knowledge map to be tested is determined as the preset cognitive ability knowledge map to be tested.

In some optional implementation manners, the cognitive ability knowledge graph to be tested further includes a correlation coefficient between each test task in the test task set corresponding to each node and the node; and the association between the current node Determining the task to be tested from the set of test tasks associated with the current node includes: determining the task to be tested with the test task having the highest correlation coefficient with the current node in the set of test tasks associated with the current node.

In some optional embodiments, the method further includes: determining the node with the smallest test value of the sub-ability of the cognitive ability to be tested corresponding to the subject among the nodes in the knowledge map of the cognitive ability to be tested It is the weakest node; determine the test task whose correlation coefficient is not the highest with the weakest node in the test task set corresponding to the weakest node as the first task to be continued; provide the first task to be continued test task, and obtain the task completion parameter information of the subject completing the first task to be tested; according to the task completion parameter information of the subject completing the first task to be tested, determine the subject The subject corresponds to the test value of the cognitive ability sub-ability to be tested corresponding to the weakest ability node.

In some optional embodiments, the method further includes: making the test value of the sub-ability of the cognitive ability to be tested corresponding to the subject in the node in the knowledge map of the cognitive ability to be tested less than the preset test value The node with the value threshold is determined as the node to be tested; for each node to be tested, the following test operation is performed: the test task set corresponding to the node to be tested has a non-highest correlation coefficient with the node to be tested The test task is determined as the second task to be continued; provide the second task to be tested, and obtain the task completion parameter information for the subject to complete the second task to be tested; The task completion parameter information of the second to-be-tested task determines the test value of the subject's cognitive ability sub-ability corresponding to the to-be-tested node.

In some optional implementation manners, according to the test value of the sub-ability of the cognitive ability to be tested corresponding to each node that has performed the test operation and the knowledge map of the cognitive ability to be tested Each correlation coefficient is used to estimate the test value of the subject's cognitive ability sub-ability corresponding to the node in the knowledge map of the cognitive ability to be tested that does not perform the test operation, including: for the subject Corresponding to the nodes in the knowledge map of the cognitive ability to be tested that have not performed the test operation, for the test values of the sub-ability of the cognitive ability to be tested corresponding to the nodes that have performed the test operation, according to The correlation coefficients of the nodes that have performed the test operation and the nodes that have not performed the test operation are weighted and summed, and the result of the weighted sum is determined as the node to be tested corresponding to the node that has not performed the test operation Test values for the Cognitive Ability sub-ability.

In some optional implementation manners, the preset test operation end condition includes at least one of the following: the subject corresponds to each node in the cognitive ability knowledge map that has performed the test operation and has not performed the test operation. The prediction accuracy rate of the node in the test operation is greater than a preset prediction accuracy rate threshold, or the test operation has been executed for each node in the N nodes.

In some optional embodiments, the cognitive ability to be tested is memory, and the preset sub-ability set of cognitive ability to be tested includes at least one of the following: sensory memory ability, short-term memory ability, semantic memory ability , Episodic memory ability, skill memory ability.

In some optional embodiments, the subject is a child with memory development difficulties, a patient with memory impairment caused by brain injury, an elderly person with normal memory or an elderly person with abnormal memory decline.

In some optional embodiments, the test task set corresponding to sensory memory ability includes multi-picture part report test task, the test task set corresponding to short-term memory ability includes position memory span and verbal memory span test task, and the corresponding semantic memory ability The test task set includes the picture naming test task, the test task set corresponding to the episodic memory ability includes the human brain-picture association memory test task, and the test task set corresponding to the skill memory ability includes the probability learning test task.

In some optional embodiments, the cognitive ability to be tested is attention, and the preset cognitive ability sub-ability set to be tested includes at least one of the following: attention capacity ability, selective attention ability, continuous attention ability , self-control ability, response ability.

In some alternative embodiments, the subject is a patient with ADHD.

In a second aspect, an embodiment of the present disclosure provides a cognitive ability testing device, which includes: an acquisition unit configured to acquire a cognitive ability knowledge map to be tested, and the cognitive ability knowledge map to be tested includes N The correlation coefficient between the node and any two nodes in the N nodes, each of the nodes is in one-to-one correspondence with the cognitive ability sub-ability to be tested in the preset cognitive ability sub-ability set to be tested, and each node corresponds to a useful A set of test tasks for testing the cognitive ability sub-capability to be tested corresponding to the node; the test unit is configured to perform the following test operations with the central node in the N nodes as the current node: test associated with the current node Determine the task to be tested in the task set; provide the task to be tested, and obtain task completion parameter information for the subject to complete the task to be tested; determine that the subject corresponds to the current The test value of the cognitive ability sub-ability to be tested corresponding to the node; according to the test value of the cognitive ability sub-ability to be tested corresponding to each node that has performed the test operation and the cognitive ability to be tested For each correlation coefficient in the knowledge map, estimate the test value of the subject's cognitive ability sub-ability corresponding to the node in the knowledge map of the cognitive ability to be tested that has not performed the test operation; determine whether the preset is satisfied A test operation end condition; in response to a determination of Yes, end the test operation.

In some optional embodiments, the device further includes: a task determination unit to be trained, configured to correspond to each cognitive ability to be tested in the preset cognitive ability sub-ability set to be tested according to the subject The test value of the sub-ability is to determine the task to be trained corresponding to the subject from the preset training task set, wherein each of the preset training tasks corresponds to the preset cognitive ability sub-ability set to be tested The cognitive ability sub-ability to be tested; the training unit is configured to provide the task to be trained, and obtain task completion parameter information for the subject to complete the task to be trained.

In some optional implementation manners, the device further includes: a retesting unit configured to, after providing the task to be trained and acquiring task completion parameter information for the subject to complete the task to be trained, Taking the central node among the N nodes of the knowledge map of the cognitive ability to be tested as the current node, the test operation is performed again to obtain the preset cognitive ability to be tested after the subject completes the training task. The test value of the cognitive ability sub-ability to be tested in the sub-ability set; the training effect evaluation unit is configured to correspond to the preset cognitive ability set to be tested according to the subject before completing the training task and after completing the training task. The test value difference of the cognitive ability to be tested is used to determine the training effect information of the subject.

In some optional implementation manners, the task-to-be-trained determination unit is further configured to: use the cognitive ability sub-ability to be tested corresponding to the subject in the preset cognitive ability sub-ability set to be tested The test value of the minimum cognitive ability sub-ability to be tested is determined as the cognitive ability sub-ability to be trained; determine the candidate training tasks corresponding to the cognitive ability sub-ability to be trained in the training task set; The task to be trained is determined in the candidate training tasks.

In some optional implementation manners, the device further includes: a training task completion degree score determination unit configured to determine the subject's The degree of completion score for completing the task to be trained.

In some optional implementation manners, the device further includes: a difficulty coefficient determining unit configured to determine the difficulty coefficient range of the next task to be trained according to the completion degree score of the subject to complete the task to be trained The next task to be trained determining unit is configured to determine the candidate training task whose difficulty coefficient is within the range of the determined difficulty coefficient of the next task to be trained among the determined candidate training tasks as the next task to be trained; The retraining unit is configured to provide the next task to be trained, and obtain task completion parameter information for the subject to complete the next task to be trained.

In some optional implementation manners, the apparatus further includes: a central node determination unit configured to, based on the knowledge to be tested The capability knowledge graph determines the central node among the N nodes.

In some optional implementation manners, the central node determination unit is further configured to: determine the sum of correlation coefficients of each node in the N nodes, wherein the sum of correlation coefficients of nodes is different from the sum of correlation coefficients among the N nodes The sum of the correlation coefficients of other nodes of the node and the node; the node with the largest sum of correlation coefficients among the N nodes is determined as the central node.

In some optional implementation manners, the device further includes: a weakest ability node determination unit, configured to use the cognitive ability to be tested corresponding to the subject in the node in the cognitive ability knowledge map to be tested The node with the smallest test value of the capability sub-capability is determined as the node with the weakest capability; the first task determination unit to be tested is configured to correlate the test task set corresponding to the node with the weakest capability with the node with the weakest capability The test task with a non-highest coefficient is determined as the first task to be continued; the first continuous test unit is configured to provide the first task to be continued and acquire the subject from completing the first task to be continued The task completion parameter information; the weakest ability test value determining unit is configured to determine that the subject corresponds to the weakest ability according to the task completion parameter information of the subject completing the first task to be tested continuously The test value of the cognitive ability sub-ability corresponding to the node.

In some optional implementation manners, the device further includes: a continuous measurement node determination unit configured to use the cognitive ability to be tested corresponding to the subject in the nodes in the cognitive ability knowledge graph to be tested A node whose test value of the sub-capability is less than a preset test value threshold is determined as a node to be tested; the second test unit is configured to perform the following test operation for each node to be tested: the node to be tested In the corresponding test task set, the test task with a non-highest correlation coefficient with the node to be tested is determined as the second task to be tested; the second task to be tested is provided, and the subject completes the first test task. Two task completion parameter information of the task to be continued test; according to the task completion parameter information of the second task to be tested by the subject, determine the cognition to be tested corresponding to the node to be tested by the subject The test value for the ability sub-ability.

In some alternative embodiments, the subject is a patient with ADHD.

In a third aspect, an embodiment of the present disclosure provides an electronic device, including: one or more processors; a storage device, on which one or more programs are stored. When executed by one or more processors, the above one or more processors implement the method described in any implementation manner of the first aspect.

In a fourth aspect, embodiments of the present disclosure provide a computer-readable storage medium, on which a computer program is stored, wherein, when the computer program is executed by one or more processors, any implementation manner in the first aspect can be realized. described method.

Each cognitive ability is composed of a variety of corresponding sub-cognitive abilities. Most of the current tests for a specific cognitive ability only use a single test task to measure a certain sub-cognitive ability of the individual in the corresponding cognitive ability, thus failing to fully test the individual's cognitive ability. In order to conduct a comprehensive test for a specific cognitive ability, it is necessary to perform corresponding test tasks for each sub-cognitive ability dimension included in the specific cognitive ability, resulting in a large number of test tasks and a long time, making it difficult to obtain Subject's cooperation.

In order to comprehensively test the subject's cognitive ability to be tested, the cognitive ability testing method, device, electronic device, and storage medium provided by the embodiments of the present disclosure, through pre-establishing the cognitive ability to be tested in the knowledge map of the cognitive ability to be tested The correlation coefficient between the ability sub-ability and different cognitive ability sub-ability to be tested, and then start the test from the cognitive ability sub-ability to be tested corresponding to the central node in the cognitive ability knowledge graph to be tested, and during the test, According to the tested test value of the cognitive ability sub-ability to be tested and the correlation coefficient between the nodes in the cognitive ability knowledge map to be tested, the test value of the untested cognitive ability sub-ability to be tested is determined in real time. If it is judged that there is no need to further test the untested cognitive ability sub-abilities according to the preset test operation end conditions, the test can be ended, and then all the cognitive ability sub-abilities to be tested can be obtained without testing all the cognitive ability sub-abilities to be tested. The test results of a comprehensive test of the cognitive ability to be measured. Compared with the need to test all the sub-abilities of the cognitive ability to be tested to achieve a comprehensive test, it reduces the number and time for the subjects to complete the test tasks, and it is easier to obtain the cooperation of the subjects and improve the quality of the test subjects. Measure the accuracy and efficiency of cognitive ability tests.

Description of drawings

Other features, objects and advantages of the present disclosure will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for purposes of illustrating specific embodiments and are not to be considered as limitations of the present disclosure. In the attached picture:

FIG. 1 is an exemplary system architecture diagram to which an embodiment of the present disclosure can be applied;

Figure 2A is a flow chart of one embodiment of a cognitive ability testing method according to the present disclosure;

FIG. 2B is a schematic diagram of an embodiment of a knowledge map of cognitive abilities to be tested according to the present disclosure;

FIG. 2C is an exploded flowchart of one embodiment of step 202 according to the present disclosure;

FIG. 3 is a flow chart of an embodiment of the knowledge map building steps according to the present disclosure;

FIG. 4 is a flowchart of another embodiment of the cognitive ability testing method according to the present disclosure;

Fig. 5 is a structural schematic diagram of an embodiment of a cognitive ability testing device according to the present disclosure;

FIG. 6 is a structural schematic diagram of a computer system suitable for implementing an electronic device according to an embodiment of the present disclosure.

Detailed ways

The present disclosure will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain related inventions, rather than to limit the invention. It should also be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.

It should be noted that, in the case of no conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and embodiments.

FIG. 1 shows an exemplary system architecture 100 to which embodiments of the cognitive ability testing method, device, electronic device and storage medium of the present disclosure can be applied.

As shown in FIG. 1 , a system architecture 100 may include

terminal devices

101 , 102 , 103 , a network 104 and a server 105 . The network 104 is used as a medium for providing communication links between the

terminal devices

101 , 102 , 103 and the server 105 . Network 104 may include various connection types, such as wires, wireless communication links, or fiber optic cables, among others.

Users can use

terminal devices

101 , 102 , 103 to interact with server 105 via network 104 to receive or send messages and the like. Various communication client applications can be installed on the

terminal devices

101 , 102 , 103 , such as cognitive ability test applications, speech recognition applications, web browser applications, and the like.

The

terminal devices

101, 102, and 103 may be hardware or software. When the

terminal devices

101, 102, and 103 are hardware, they can be various electronic devices with display screens, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Compression Standard Audio Layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Compression Standard Audio Layer 4) players, laptops and desktop computers, etc. When the

terminal devices

101, 102, and 103 are software, they can be installed in the terminal devices listed above. It can be implemented as a plurality of software or software modules (for example, to provide cognitive ability testing services), and can also be implemented as a single software or software module. No specific limitation is made here.

In some cases, the cognitive ability testing method provided in the present disclosure can be executed by the

terminal devices

101 , 102 , 103 , and correspondingly, the cognitive ability testing apparatus can be set in the

terminal devices

101 , 102 , 103 . At this time, the system architecture 100 may not include the server 105 .

In some cases, the cognitive ability testing method provided in the present disclosure can be jointly executed by the

terminal devices

101, 102, 103 and the server 105, for example, the step of "obtaining the

knowledge

102 and 103 are performed, and steps such as “taking the central node among the N nodes as the current node to perform the following test operation” can be performed by the server 105 . The present disclosure does not limit this. Correspondingly, the apparatus for testing cognitive ability can also be set in the

terminal devices

101, 102, 103 and the server 105 respectively.

In some cases, the cognitive ability testing method provided by the present disclosure may be executed by the server 105, and correspondingly, the cognitive ability testing device may also be set in the server 105, and at this time, the system architecture 100 may not include the

terminal device

101 , 102, 103.

It should be noted that the server 105 may be hardware or software. When the server 105 is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or as a single server. When the server 105 is software, it can be implemented as multiple software or software modules (for example, for providing distributed services), or as a single software or software module. No specific limitation is made here.

It should be understood that the numbers of terminal devices, networks and servers in Fig. 1 are only illustrative. According to the implementation needs, there can be any number of terminal devices, networks and servers.

Continue to refer to FIG. 2A, which shows a process 200 according to an embodiment of the cognitive ability testing method of the present disclosure, the cognitive ability testing method includes the following steps:

Step 201, acquiring the knowledge map of the cognitive ability to be tested.

In this embodiment, the execution subject of the cognitive ability testing method (such as the

terminal equipment

101, 102, 103 shown in FIG. The shown server 105) acquires the knowledge map of the cognitive ability to be tested.

Here, the knowledge map of the cognitive ability to be tested may include N nodes and correlation coefficients between any two of the N nodes. Wherein, N is a positive integer. Each node is in one-to-one correspondence with the cognitive ability sub-ability to be tested in the preset cognitive ability sub-ability set to be tested. Moreover, each node may correspond to a set of test tasks for testing the sub-capability of the cognitive ability to be tested corresponding to the node.

For ease of understanding, please refer to FIG. 2B . FIG. 2B shows a schematic diagram of an embodiment of a knowledge map of cognitive ability to be tested according to the present disclosure. As shown in Figure 2B, the cognitive ability knowledge graph to be tested includes five nodes, corresponding to the cognitive ability sub-ability A1 to be tested, the cognitive ability sub-ability A2 to be tested, the cognitive ability sub-ability A3 to be tested, the cognitive ability sub-ability to be tested Cognitive ability sub-ability A4 and the cognitive ability sub-ability to be tested A5. Among them, the cognitive ability sub-ability to be tested corresponds to the test task T1 and the test task T2, the cognitive ability sub-ability to be tested corresponds to the test task T3, the test task T4, and the test task T5, and the cognitive ability sub-ability to be tested corresponds to the test task T3, the test task T4 and the test task T5. A3 corresponds to test task T6 and test task T7, the cognitive ability sub-ability to be tested corresponds to test task T8 and test task T9, and the cognitive ability sub-ability to be tested corresponds to test task T10, test task T11 and test task T12 . The values displayed on the connecting lines between different nodes in Figure 2B are used to represent the correlation coefficients between the corresponding cognitive ability sub-abilities to be tested at both ends of the connecting line. For example, in Figure 2B, between the cognitive ability sub-ability A1 to be tested and the cognitive ability sub-ability A2 to be tested, the cognitive ability sub-ability A3 to be tested, the cognitive ability sub-ability A4 to be tested, and the cognitive ability sub-ability A5 to be tested The correlation coefficients between them are 0.4, 0.2, 0.6 and 0.8 respectively, which indicates that the correlation between the tested cognitive ability sub-ability A1 and the tested cognitive ability sub-ability A5 is the highest, and that between the tested cognitive ability sub-ability A3 The correlation between them is the lowest.

Here, the set of cognitive ability sub-capacities to be tested may be pre-formulated by technicians (for example, psychologists or sociological experts) according to professional knowledge (for example, psychological or sociological knowledge) and stored in the above-mentioned execution subject. A collection of cognitive ability sub-abilities to be tested.

Here, each test task may correspond to a cognitive ability sub-ability to be tested, and each test task is used to test its corresponding cognitive ability sub-ability to be tested. The test task can be pre-formulated and stored in the above-mentioned execution subject by a technician (for example, a psychologist or sociology expert) based on professional knowledge (for example, psychology and/or sociology knowledge), and is used to interact with the subject In order to realize the sequence of program instructions for testing the corresponding sub-abilities of cognitive abilities of the subjects to be tested.

In some optional embodiments, the cognitive ability to be tested may be memory.

Based on the above optional implementation, the preset cognitive ability sub-ability set to be tested can be a preset memory ability set, and the preset memory ability set may include at least one of the following: sensory memory ability, short-term memory ability, semantic memory ability, episodic memory ability, skill memory ability.

Here, the sensory memory ability may refer to the subject's ability to simultaneously remember multiple target objects within a short period of time (eg, 1 second). The test task set corresponding to the sensory memory ability is used to test the sensory memory ability of the subjects. The test task set corresponding to the sensory memory ability may include, for example, a picture part report test task. The so-called part of the picture report test task refers to: multiple different target objects are presented on the display device and disappear quickly (for example, within 1 second), and the subjects are required to remember each target object, and in the follow-up test according to the task Request to report to a specific target audience. Wherein, the target object can be, for example, color blocks of different colors and/or shapes, arrows of different colors and/or orientations, common objects in daily life, human faces, different fruits, vegetables, animals or image objects of cartoon images, etc.

Here, the short-term memory ability may refer to the subject's ability to temporarily store a certain amount of material in the working memory of the mind. The test task set corresponding to the short-term memory ability is used to test the short-term memory ability of the subjects. The test task set corresponding to the short-term memory ability may include, for example, a multi-location memory span test task and a verbal memory span test task. The so-called position memory span test task refers to: multiple target objects are presented on the display device simultaneously or sequentially, and the subjects are required to remember each target object in turn, and report the target objects in the required order, reverse order or other specific order in the follow-up test. The target object that was presented. Wherein, the target object may be materials such as spatial position, sound, picture or color, orientation, etc. The so-called verbal memory span test task refers to: multiple text or digital objects are presented on the display device at the same time or sequentially, and the subjects are required to remember each target object in turn, and follow the required order, reverse order or other specific order in the follow-up test. Reports the target object that was presented.

Here, the semantic memory ability may be: the subject's ability to retain semantic knowledge for a long time (for example, within 1 minute). The test task set corresponding to the semantic memory ability is used to test the semantic memory ability of the subjects. The test task set corresponding to the semantic memory ability may include, for example, a picture naming task. The so-called picture naming test task refers to: a series of images are continuously presented on the display device, and the subjects are required to quickly say the name of the target object corresponding to the image. These objects can be, for example, specified objects, animals, plants, people, etc.

Here, episodic memory ability may be the subject's ability to remember specific events. The test task set corresponding to the episodic memory ability is used to test the episodic memory ability of the subjects. The test task set corresponding to the episodic memory ability may include, for example, a human brain-picture association memory test task. The so-called human brain-picture association memory test task can refer to, for example: presenting two different images in pairs or successively on a display device, requiring the subject to remember the connection between the two different images, and after a certain period of time, The cue text was presented so that the subject could recall the image that matched the cue, based on the cue text. These images may be images used to indicate different sensory channels such as different vision, hearing, touch, smell, etc. or different object types.

Here, skill memory ability can be: the subject's ability to quickly learn to make correct action responses to different stimuli according to the rules based on feedback. The test task set corresponding to the skill memory ability is used to test the subject's skill memory ability. The test task set corresponding to the skill memory ability may include, for example, a probability learning test task. The so-called probabilistic learning test task refers to presenting the target object on the display device, requiring the subject to make a certain action response to the target object, and adjusting and optimizing the behavior according to the right-wrong feedback, so as to gradually improve the accuracy of the action response.

In some optional embodiments, the cognitive ability to be tested may be attention.

Based on the above optional implementation, the preset cognitive ability sub-ability set to be tested can be a preset attention ability set, and the preset attention ability set can include at least one of the following: attention capacity ability, selective attention ability, continuous Attention, self-control, and responsiveness.

Here, the attention capacity ability may refer to the subject's ability to remember multiple objects at the same time. The test task set corresponding to the attention capacity ability is used to test the subject's attention capacity ability. The set of test tasks corresponding to the attention capacity capability may include, for example, attention capacity type test tasks. The so-called attention-capacity test task refers to: multiple different target objects are presented on the display device, and the subjects are required to remember the appearance and position of each target object, and accurately recall or select the corresponding target object in the follow-up test. . Wherein, the target object may be, for example, color blocks of different colors and/or shapes, arrows of different colors and/or orientations, common objects in daily life, human faces, and the like.

Selective attention ability may refer to the subject's ability to focus on a specific object among multiple objects. The test task set corresponding to the selective attention ability is used to test the subject's selective attention ability. The selection of the test task set corresponding to the attention ability may include, for example, a multi-object tracking test task. The so-called multi-target tracking test task refers to: multiple irregularly moving targets are presented on the display device, and the subjects are required to memorize specific targets among the above-mentioned multiple irregularly moving targets, and recognize them in subsequent tests. specific goals. Wherein, the target may be, for example, images of fireflies, bees, or butterflies.

Sustained attention ability can be: the subject's ability to keep the focus on the target. The set of test tasks corresponding to sustained attention ability is used to test the subject's sustained attention ability. The set of test tasks corresponding to the sustained attention ability may include, for example, continuous work tasks. The so-called continuous operation test task refers to: a series of targets are continuously presented on the display device, and the subjects are required to continuously respond to the targets within a period of time. These objects can be specified numbers, text, graphics and so on.

Here, self-control ability can be: the subject's ability to control impulsive behavior. The test task set corresponding to the self-control ability is used to test the self-control ability of the subjects. The test task set corresponding to the self-control ability may include, for example, an impulse control test task. The so-called impulse control test task can refer to, for example: presenting a scrolling image on a display device, the image includes different channel images and target objects, requiring the subject to control the target object to pass through the channel corresponding to the specified channel image according to the predetermined requirements, and Instead of going through the channel corresponding to the image of the same channel according to the inertial habit, the ability of the subject to get rid of the habit can be tested through this impulsive resistance test task.

Here, the responsiveness may be: the subject's ability to respond quickly to external stimuli. The test task set corresponding to the response ability is used to test the subject's response ability. The test task set corresponding to the reaction ability may include, for example, a reaction speed test task. The so-called reaction speed test task refers to: present the target object on the display device, ask the subject to make a specified action when the target object appears, and calculate the time interval between the target object appearing and the subject completing the specified action, through This interval can test the subject's responsiveness. It can be understood that the shorter the time interval, the stronger the subject's response ability; conversely, the longer the time interval, the weaker the subject's response ability.

In some optional implementation manners, the knowledge graph of the cognitive ability to be tested may also be pre-established through the knowledge graph building step 300 shown in FIG. 3 . The knowledge map building step 300 may include the following steps 301 to 304:

Step 301, acquiring an initial cognitive ability knowledge map to be tested.

Here, the initial cognitive ability knowledge graph to be tested includes N nodes, and each node in the initial cognitive ability knowledge graph to be tested is in one-to-one correspondence with the cognitive ability sub-ability to be tested in the preset cognitive ability sub-ability set to be tested . Each node in the initial cognitive ability knowledge graph to be tested corresponds to a test task set for testing the cognitive ability sub-ability to be tested corresponding to the node.

Step 302, acquiring a training sample set.

Here, the training samples may include the sample task performance parameter information of the sample subjects completing the test tasks in the test task set corresponding to the nodes in the initial cognitive ability knowledge graph to be tested and the corresponding preset cognitive ability sub-ability set to be tested. The marked test value corresponding to the cognitive ability sub-ability to be tested. That is, the training sample records the task performance parameter information of the sample subject to complete a test task and the corresponding task performance parameter information based on the test task for the sample subject in each of the different cognitive ability sub-assessments to be tested. Annotated test values for capabilities. Here, the corresponding labeled test values for different sub-abilities of the cognitive ability to be tested can be tested by professional technicians (for example, psychologists or sociologists) according to the task performance parameter information of the sample subjects. It is obtained by evaluating and marking different cognitive ability sub-abilities to be tested in the preset cognitive ability sub-ability set to be tested.

The training sample set can be regarded as recording the task performance parameter information of multiple sample subjects for completing the test tasks corresponding to different cognitive ability sub-abilities in the preset cognitive ability sub-ability set to be tested, and the corresponding information for each Annotated test values for different cognitive ability sub-abilities to be tested.

It should be noted that in practice, multiple sample subjects may be composed of representative populations. The so-called representative population means that a small number of sample subjects are used to simulate the composition of a large sample population, which has basically the same or similar composition as the large sample population. For example, when a large sample population includes 5% of Alzheimer's patients and 5% of children with memory development difficulties, multiple sample subjects can also include 5% of Alzheimer's patients and 5% of children with memory development difficulties. Children with memory development difficulties. For example, when a large sample population includes 10% ADHD patients, multiple sample subjects may also include 10% ADHD patients.

Step 303, using a machine learning method to adjust the correlation coefficient between any two nodes in the initial cognitive ability knowledge map to be tested based on the training sample set.

Here, the preset machine learning model can be obtained first, and the above machine learning model can include the correlation coefficient between each node in the initial cognitive ability knowledge graph to be tested, or optionally can also include the test task corresponding to each node The correlation coefficient between each test task in the set and this node. The above machine learning model is used to characterize the correspondence between the task performance parameter information of the test task and the test values of each cognitive ability sub-ability in the preset cognitive ability sub-ability set to be tested. Here, the machine learning model may include, for example, at least one of the following: a structural equation model, an artificial neural network model, and the like.

Then, perform the following parameter adjustment operations until the preset training end conditions are met:

The parameter adjustment operation may include: first, input the sample task performance parameter information (specifically, sample task identification and corresponding task performance parameter information) in the training sample set into the above-mentioned machine learning model, and obtain the actual output for each cognitive ability to be tested. The test value of the sub-ability; then, based on the difference between the actual output test value for each cognitive ability sub-ability to be tested and the marked test value of the corresponding cognitive ability sub-ability to be tested in the training sample, adjust the above-mentioned machine The model parameters of the learned model. Since the above machine learning model includes the correlation coefficient between each node in the initial cognitive ability knowledge map to be tested, or optionally also includes the correlation between each test task in the test task set corresponding to each node and the node coefficient. Furthermore, during the parameter adjustment operation, the correlation coefficient between each node in the initial cognitive ability knowledge graph to be tested can be adjusted, or optionally, the relationship between each test task in the test task set corresponding to each node and the node can be adjusted. The correlation coefficient between.

Here, the training end condition may include at least one of the following: the time to perform parameter adjustment operations reaches a preset duration, the number of times to perform parameter adjustment operations reaches a preset number of times, the actual output of the test value for each cognitive ability sub-ability to be tested and The difference between the marked test values of the corresponding cognitive ability sub-abilities to be tested in the training sample is smaller than the preset difference threshold.

Here, various implementation methods can be adopted to adjust the machine learning model based on the difference between the actual output test value for each cognitive ability sub-ability to be tested and the labeled test value of the corresponding cognitive ability sub-ability to be tested in the training sample model parameters. For example, stochastic gradient descent (SGD, Stochastic Gradient Descent), Newton's Method, Quasi-Newton Methods, Conjugate Gradient, heuristic optimization methods and other known Or various optimization algorithms developed in the future.

After step 303, the correlation coefficient between each node in the initial cognitive ability knowledge map to be tested can be adjusted, or optionally, the correlation coefficient between the test task and the node in the test task set corresponding to the node can also be adjusted.

Step 304, determining the initial cognitive ability knowledge map to be tested as the knowledge map of cognitive ability to be tested.

Using the knowledge map building step 300 shown in Figure 3 to pre-establish the knowledge map of the cognitive ability to be tested, because it is based on the task completion parameter information of multiple sample subjects actually completing the test task and the corresponding cognitive ability sub-ability to be tested The correlation coefficient between the nodes in the knowledge map of the cognitive ability to be tested is established by marking the test value, which reflects the degree of correlation between the corresponding sub-abilities of the cognitive ability to be tested, and then in the test operation in the subsequent step 202, for According to the sub-ability test value of the cognitive ability to be tested corresponding to the node that has completed the test operation, the sub-ability test value of the cognitive ability to be tested for the node that has not completed the test operation is speculated to provide a basis.

In step 202, a test operation is performed with the central node among the N nodes as the current node.

Here, first of all, various implementation methods may be used to determine the central node among the N nodes in the cognitive ability knowledge graph to be tested. For example, a preset node among the N nodes may be determined as the central node. For another example, a randomly selected node among the N nodes may also be determined as the central node.

In some optional implementation manners, the central node among the N nodes may be determined in the following manner:

In the first step, the sum of correlation coefficients of each node among the N nodes can be determined.

Here, the sum of the correlation coefficients of a node is the sum of the correlation coefficients of other nodes different from the node among the N nodes and the node.

In the second step, the node with the largest sum of correlation coefficients among the N nodes can be determined as the central node.

That is, the node with the highest degree of correlation and contact with other nodes among the N nodes is used as the central node to start the subsequent test operation.

Then, execute the test operation with the central node as the current node.

Here, the test operation may include steps 2021 to 2026 as shown in FIG. 2C:

Step 2021, determine the task to be tested in the test task set associated with the current node.

Here, various implementation manners may be used to determine the task to be tested in the test task set associated with the current node. For example, a preset test task in the test task set associated with the current node may be determined as the task to be tested. For another example, a randomly selected test task from the test task set associated with the current node may also be determined as the task to be tested.

Optionally, when the cognitive ability knowledge graph to be tested includes the correlation coefficient between the test task and the node, the test task with the largest correlation coefficient between the current node and the current node in the test task set associated with the current node can also be determined as The task to be tested. It can be understood that since the correlation coefficient between the test task and the node in the knowledge map of the cognitive ability to be tested represents the degree of correlation between the test task and the sub-ability of the cognitive ability to be tested corresponding to the node, according to this optional implementation mode The determined task to be tested is the most relevant to the cognitive ability sub-ability to be tested corresponding to the current node in the test task set associated with the current node. Starting from the task to be tested can quickly test the subject's ability to correspond to the current node. The sub-ability of the cognitive ability to be tested reduces the test time and improves the test efficiency.

For ease of understanding, please continue to refer to Figure 2B. Figure 2B shows the value displayed on the connection between the cognitive ability sub-ability node to be tested and the test task node in the knowledge map of the cognitive ability to be tested to represent the connection The correlation coefficient between the test task corresponding to one end and the cognitive ability sub-ability corresponding to the other end. For example, the correlation coefficient between the cognitive ability sub-ability A1 to be tested and the test task T1 in FIG. 2B is 0.41.

Step 2022, provide the task to be tested, and obtain task completion parameter information for the subject to complete the task to be tested.

For example, when the task to be tested is a sequence of program instructions, the sequence of program instructions corresponding to the task to be tested can be executed, and the task completion parameter information during the interaction process between the subject and the program instruction sequence, that is, the process of completing the task to be tested, can be obtained. Here, the task completion parameter information may be various related information in the process of the subject completing the task to be tested.

Step 2023, according to the task completion parameter information, determine the subject's test value corresponding to the sub-ability of the cognitive ability to be tested corresponding to the current node.

Here, according to the test value determination logic corresponding to the cognitive ability sub-ability to be tested corresponding to the current node, and according to the task completion parameter information of the subject's completion of the task to be tested, the subject's cognitive ability to be tested corresponding to the current node can be determined. The test value for the ability sub-ability. Here, the test value determination logic corresponding to the cognitive ability sub-ability to be tested corresponding to the current node may be the calculation of the task completion parameter information of the task to be tested to obtain the test value of the cognitive ability sub-ability to be tested corresponding to the current node The formula, or the test value determination logic corresponding to the cognitive ability sub-ability to be tested corresponding to the current node may be used to represent the task completion parameter information of the task to be tested and the test value corresponding to the cognitive ability sub-ability to be tested corresponding to the current node The correspondence table of the corresponding relationship between them. The above-mentioned calculation formula or corresponding relationship table may be completed by the technician based on a large number of sample subjects completing the task completion parameter information corresponding to the above-mentioned task to be tested and correspondingly corresponding to the sample subject's cognitive ability sub-ability to be tested at the current node The statistics of the marked test values are formulated in advance and stored in the calculation formula or corresponding relationship table of the above-mentioned execution subject.

It can be understood that the task to be tested is used to test the cognitive ability sub-ability to be tested corresponding to the current node, and in step 2023, the subject's The test value corresponding to the sub-ability of the cognitive ability to be tested corresponding to the current node can be used to represent the degree of the subject in the sub-ability of the cognitive ability to be tested corresponding to the current node.

Step 2024, according to the test value of the sub-ability of the cognitive ability to be tested corresponding to each node that has performed the test operation and the correlation coefficients in the knowledge map of the cognitive ability to be tested, estimate the cognitive ability of the subject to be tested The test value of the sub-ability of the cognitive ability to be tested corresponding to the node that has not performed the test operation in the knowledge graph.

Here, the correlation coefficient between two different nodes in the knowledge map of the cognitive ability to be tested is used to characterize the degree of correlation between the sub-ability of the cognitive ability to be tested corresponding to the two different nodes. That is, assuming that the correlation coefficient between two different nodes N1 and N2 in the knowledge map of the cognitive ability to be tested is high, it indicates that the two different nodes N1 and N2 correspond to the cognitive ability sub-ability A1 and A2 respectively. The degree of correlation is also relatively high. Correspondingly, it can be understood that if the test operation from step 2021 to step 2026 has been performed on the cognitive ability sub-ability A1 to be tested and the test value of the subject in the cognitive ability sub-ability A1 to be tested is obtained, Since the correlation between the cognitive ability sub-ability A2 and A1 is relatively high, the test value of the subject in the cognitive ability sub-ability A1 can be used to approximate the test value of the subject in the cognitive ability sub-ability A2. value, no need to test the sub-ability A2 of the cognitive ability to be tested.

Specifically, step 2024 may be performed as follows, for example:

For each node in the cognitive ability test knowledge graph that has not performed the test operation, perform the following first calculation step to determine the test value of the subject's cognitive ability sub-ability corresponding to the node that has not performed the test operation: First, among the nodes in the cognitive ability knowledge map to be tested, the nodes whose correlation coefficient with the node is greater than the preset correlation coefficient threshold are determined as the relevant nodes; The mean value of the test values of the cognitive ability corresponding to the relevant nodes is determined as the test value of the subject's cognitive ability corresponding to the node that has not performed the test operation.

In some optional implementation manners, step 2024 may also be performed as follows:

For the nodes in the knowledge map of the subject’s cognitive ability to be tested that have not performed the test operation, for the test value of the sub-ability of the subject’s cognitive ability to be tested corresponding to each node that has performed the test operation, according to the executed test A weighted summation is performed on the correlation coefficients of each node in operation and the node not performing the test operation, and the result of the weighted summation is determined as the test value of the cognitive ability sub-ability corresponding to the node not performing the test operation. According to this optional implementation, the test value of the sub-ability of the cognitive ability to be tested corresponding to the node in the cognitive ability knowledge graph of the subject that has not performed the test operation, which is calculated according to this optional embodiment, reflects that all subjects correspond to the The test value of the sub-ability of the cognitive ability to be tested corresponding to each node of the test operation is equivalent to more reference data, which can more accurately evaluate the subject's corresponding to the node in the cognitive ability knowledge graph of the test that has not performed the test operation. The test value of the cognitive ability sub-ability to be tested.

Step 2025, determine whether the preset test operation end condition is satisfied.

Here, the preset test operation end condition may be pre-formulated and stored in the above-mentioned execution subject by technical personnel (for example, psychological experts or sociological experts) based on professional knowledge (for example, psychological or sociological knowledge) and a summary of practical experience conditions of. If it is determined that the preset end condition of the test operation is satisfied, it is possible to determine to end the test operation, and then no longer test the subject's cognitive ability sub-ability corresponding to the node in the knowledge graph of the cognitive ability to be tested that has not performed the test operation .

In some optional implementation manners, the preset test operation end conditions may include at least one of the following:

First, the prediction accuracy of each node in the knowledge map of the subject's cognitive ability to be tested that has performed the test operation to the nodes that have not performed the test operation is greater than the preset accuracy threshold.

Second, a test operation has been performed on each of the N nodes in the knowledge graph of the cognitive ability to be tested.

That is, if at least one of the above two conditions is met, it may be determined to end the test operation.

Among them, regarding the first condition, the prediction accuracy rate of the subjects in the cognitive ability knowledge graph to be tested for nodes that have performed the test operation to the nodes that have not performed the test operation can be explained as follows: Knowledge graph of the cognitive ability to be tested Including N nodes, it is assumed that M nodes have performed the test operation, and the remaining (N-M) nodes have not performed the test operation, where M is a positive integer less than or equal to N. Here, for each of the (N-M) nodes Ni that have not performed the test operation, various methods can be used to calculate the prediction accuracy rate of the M nodes that have performed the test operation on the node Ni that has not performed the test operation. For example, the variation explanation rate can be adopted, that is, the variation explanation rate of the constructed regression equation between each node in the M nodes that have performed the test operation and the node Ni that has not performed the test operation is determined as the M nodes that have performed the test operation The prediction accuracy rate of the node Ni that has not performed the test operation. The first condition may be that the variation interpretation rate of each node that has performed the test operation to each node that has not performed the test operation in the subject's cognitive ability knowledge map corresponding to the test is greater than the preset prediction accuracy threshold.

If the first condition is met, it indicates that no test operation has been performed in the cognitive ability knowledge graph to be tested according to the test value of the cognitive ability sub-ability corresponding to each node in the knowledge graph of the cognitive ability to be tested that has performed the test operation It is reliable to estimate the test value of the cognitive ability sub-ability corresponding to the node to be tested, that is, it is not necessary to continue to test the cognitive ability sub-ability to be tested corresponding to the node that has not performed the test operation in the knowledge map of the cognitive ability to be tested. Keep testing.

If the second condition is met, that is, after all the sub-abilities of the cognitive ability to be tested corresponding to all the nodes in the knowledge map of the cognitive ability to be tested have completed the test operation, the subject corresponding to the knowledge map of the cognitive ability to be tested is obtained. The test value of the cognitive ability sub-ability corresponding to all nodes does not need to perform the test operation. In some optional implementation manners, the above execution subject may also proceed to the following step 2026 for execution if it is determined in step 2025 that the preset test operation end condition is not satisfied:

Step 2026: Determine the next node to be tested according to the correlation coefficient between the node that has not performed the test operation and the current node in the knowledge map of the subject's cognitive ability to be tested.

That is, if the above-mentioned execution subject determines not to end the test operation in step 2025, various implementation methods can be adopted, according to the correlation coefficient between the node that has not performed the test operation and the current node in the subject's cognitive ability knowledge graph corresponding to the test, The next node to be tested is determined among the nodes that have not performed the test operation in the subject's knowledge map corresponding to the cognitive ability to be tested. Because the correlation coefficient between two different nodes in the cognitive ability knowledge map to be tested is used to represent the degree of correlation between the sub-ability of the cognitive ability to be tested corresponding to the two different nodes. That is, assuming that the current node in the knowledge map of the cognitive ability to be tested is N3, and the subject corresponds to the node Ni in each node in the knowledge map of the cognitive ability to be tested that has not performed the test operation, if the correlation coefficient between Ni and N3 is relatively large, Then it can be considered that the cognitive ability sub-ability to be tested corresponding to node Ni is similar to the cognitive ability sub-ability to be tested corresponding to node N3, since the cognitive ability sub-ability to be tested corresponding to node N3 of the subject has been tested , it is no longer necessary to test the cognitive ability sub-ability corresponding to the node Ni. Conversely, if the correlation coefficient between Ni and N3 is relatively small, it can be considered that the cognitive ability sub-ability corresponding to node Ni is not similar to the cognitive ability sub-ability corresponding to node N3, although the subject’s node N3 The corresponding cognitive ability sub-ability to be tested has been tested, and the cognitive ability sub-ability to be tested corresponding to the node Ni needs to be tested again.

According to the above description, it can be seen that the executive body can select a node with a smaller correlation coefficient with the current node as the next node to be tested among the nodes in the knowledge map corresponding to the subject's cognitive ability to be tested that have not performed the test operation.

Optionally, step 2026 may be performed as follows: the node with the smallest correlation coefficient with the current node among the nodes in the knowledge map of the subject's cognitive ability corresponding to the test that has not performed the test operation is determined as the next node to be tested. That is, select the node least related to the current node as the next node to be tested.

Step 2027, continue to execute the test operation with the next node to be tested as the current node.

That is, take the next node to be tested determined in step 2026 as the current node, go to step 2021 and continue to execute, so as to test the subject's cognitive ability sub-ability to be tested corresponding to the current node after being updated with the next node to be tested Carry out the test and obtain the corresponding test values, and then estimate the test values of other nodes that have not performed the test operation based on the test values of the subjects corresponding to all the nodes that have performed the test operation, and determine again whether it is necessary to end the test operation, If it is determined to end the test operation in step 2025 again, the test operation will not be continued.

In some optional implementations, based on the optional implementation of determining the test task with the largest correlation coefficient with the current node in the test task set associated with the current node in step 2021 as the task to be tested, the above-mentioned executive body can also After performing step 202, perform the following steps 203' to 206':

Step 203', among the nodes in the knowledge map of the cognitive ability to be tested, the node with the smallest test value corresponding to the sub-ability of the cognitive ability to be tested is determined as the node with the weakest ability.

That is, after step 201 and step 202, the subject's cognitive ability to be tested corresponding to each node in the knowledge map of cognitive ability to be tested can be quickly measured, but further confirmation is needed as to whether the test is accurate. Specifically, if the subject has the lowest score in a certain sub-ability of cognitive ability to be tested, the test of the sub-ability of cognitive ability to be tested may be inaccurate, and continuous testing is required to improve the accuracy. That is, according to step 203', the subject's weakest cognitive ability sub-ability to be tested can be found first. Then go to step 204'.

Step 204', in the test task set corresponding to the node with the weakest capability, the test task with a non-highest correlation coefficient with the node with the weakest capability is determined as the first task to be tested continuously.

Since in step 2021, the subject has selected the test task with the largest correlation coefficient with the weakest node in the test task set corresponding to the weakest node determined in step 203', there is no need to use the above-mentioned The test task with the largest correlation coefficient with the weakest node is tested. Therefore, step 204' may be performed first to determine the first task to be tested, and then go to step 205'. For example, the first task to be continuously tested may be the test task with the second highest correlation coefficient with the node with the weakest capability in the test task set corresponding to the node with the weakest capability.

Step 205', providing the first task to be tested continuously, and obtaining the task completion parameter information of the subject completing the first task to be tested continuously.

That is, the subject's cognitive ability sub-ability to be tested corresponding to the weakest node is tested again with another test task, so as to improve the accuracy of the cognitive ability sub-ability to be tested corresponding to the weakest node.

Step 206', according to the task completion parameter information of the subject's completion of the first task to be tested, determine the test value of the sub-ability of the cognitive ability to be tested corresponding to the node with the weakest corresponding ability of the subject.

Here, the specific operations and technical effects of step 206' are basically the same as the operations and effects of

steps

201 and 2023 in the embodiment shown in FIG. 2A , and will not be repeated here.

According to the above optional implementation manner, it is possible to re-test the subject's cognitive ability sub-ability with the lowest score by replacing the test task, so as to improve the accuracy of the subject's test.

In some optional implementations, based on the optional implementation of determining the test task with the largest correlation coefficient with the current node in the test task set associated with the current node in step 2021 as the task to be tested, the above-mentioned executive body can also After performing step 202, perform the following steps 203" to 204":

Step 203", among the nodes in the knowledge map of the cognitive ability to be tested, the node whose test value corresponding to the sub-ability of the cognitive ability to be tested is less than the preset test value threshold is determined as the node to be continued.

That is, it can be considered that if the test subject’s score in a certain cognitive ability sub-ability to be tested is too low, the test may be inaccurate, and the test needs to be continued, and step 203” is performed to determine the cognitive ability to be tested corresponding to the node to be tested. Ability sub-ability needs to continue to be tested.

Step 204", performing a continuous testing operation for each node to be tested continuously.

That is, continue testing the cognitive ability sub-abilities to be tested corresponding to all nodes to be tested continuously to obtain the test values corresponding to these cognitive ability sub-ability to be tested. Among them, the continuous measurement operation may specifically include:

First, a test task that has a non-highest correlation coefficient with the node to be tested in the set of test tasks corresponding to the node to be tested continuously is determined as the second task to be tested continuously.

As can be seen from the description of the above optional implementation mode, similarly, here, for the cognitive ability sub-capability to be tested corresponding to the node to be tested, since it has already been included in the test set corresponding to the node to be tested in step 2021, the The test task with the largest correlation coefficient between the continued test nodes has been tested, so the test task needs to be replaced and re-tested to improve the accuracy of the test subject’s cognitive ability sub-ability corresponding to the test node to be tested .

Second, a second task to be tested is provided, and task completion parameter information for the subject to complete the second task to be tested is acquired.

Thirdly, according to the task completion parameter information of the second task to be tested by the subject, the test value of the subject's cognitive ability sub-ability corresponding to the node to be tested is determined.

According to the above optional implementation manner, it is possible to retest the sub-abilities of the cognitive abilities to be tested with low scores of the subjects by replacing the test tasks, so as to improve the accuracy of the tests on the subjects.

In the cognitive ability testing method provided by the above-mentioned embodiments of the present disclosure, by pre-establishing the correlation coefficient between each cognitive ability sub-ability to be tested and different cognitive ability sub-ability to be tested in the cognitive ability knowledge map to be tested, and then from The cognitive ability sub-ability to be tested corresponding to the central node in the knowledge map of the cognitive ability to be tested starts testing, and during the test, according to the test value of the cognitive ability sub-ability to be tested and the cognitive ability to be tested The correlation coefficient between nodes in the knowledge graph determines the test value of the untested cognitive ability sub-ability in real time. If it is determined that based on the test value of the untested cognitive ability sub-ability to be tested, there is no need to further test the untested cognitive ability sub-ability to be tested, the test can be ended, and then it is not necessary to test all the cognitive ability sub-ability to be tested. Performing the test results in a comprehensive test of the subject's cognitive ability to be tested. Compared with the need to test all the sub-abilities of the cognitive ability to be tested to achieve a comprehensive test, it reduces the number and time for the subjects to complete the test tasks, and it is easier to obtain the cooperation of the subjects and improve the efficiency of the test. In some embodiments, it is also possible to test the cognitive ability sub-ability with the lowest test value or the test value is too low by changing the test task, so as to further improve the test accuracy.

Continue to refer to FIG. 4 , which shows a flow 400 of another embodiment of the cognitive ability testing method according to the present disclosure. The cognitive ability testing method comprises the following steps:

Step 401, acquiring the knowledge map of the cognitive ability to be tested.

In step 402, a test operation is performed with the central node among the N nodes as the current node.

In this embodiment, the specific operations and technical effects of

steps

401 and 402 are basically the same as the operations and effects of

steps

201 and 202 in the embodiment shown in FIG. 2A , and will not be repeated here.

Step 403, according to the test values of the subject corresponding to each cognitive ability sub-ability in the preset cognitive ability sub-ability set to be tested, determine the task to be trained corresponding to the subject from the preset training task set.

Here, each training task in the preset training task set corresponds to the cognitive ability sub-ability to be tested in the cognitive ability sub-ability set to be tested in the preset cognitive ability sub-ability set. The sub-ability of the cognitive ability to be tested is trained.

Since the test values of the subject's corresponding cognitive ability sub-abilities to be tested in the preset cognitive ability sub-ability set to be tested have been obtained through step 401 and step 402, in order to test the subject's cognitive ability in certain cognitive abilities To improve the sub-abilities, various implementation methods can be adopted firstly, and according to the test values of the subjects corresponding to the sub-abilities of the cognitive abilities to be tested in the sub-abilities of the pre-set cognitive abilities to be tested, determine from the preset training task set and The task to be trained corresponding to the subject.

In some optional implementation manners, step 403 may be performed as follows:

First, among the preset cognitive ability sub-ability sets to be tested, the cognitive ability sub-ability to be tested that has the smallest test value of the cognitive ability sub-ability to be tested corresponding to the subject is determined as the cognitive ability sub-ability to be trained. That is, find out the subject's weakest cognitive ability as the cognitive ability sub-ability to be trained.

Then, a candidate training task corresponding to the cognitive ability sub-ability to be trained in the training task set is determined.

Here, the determined number of candidate training tasks may be one or more than one.

Finally, a task to be trained is determined among the determined candidate training tasks.

For example, a training task may be randomly selected from among the determined candidate training tasks and determined as the task to be trained.

For another example, when the candidate training tasks in the training task set are associated with a difficulty coefficient, the corresponding relationship between the preset test value range and the difficulty coefficient range of the candidate training task can be determined to determine the corresponding test value of the cognitive ability sub-ability to be trained. The range of the difficulty coefficient of the training task, wherein the test value of the sub-ability of the cognitive ability to be trained is the test value corresponding to the cognitive ability of the memory to be trained by the subject. Then, among the determined candidate training tasks, candidate training tasks whose difficulty coefficients are within the determined difficulty coefficient range are determined as tasks to be trained.

In some optional implementation manners, step 403 may also be performed as follows:

When the subject is associated with a corresponding cognitive ability to be improved (for example, for children with memory development difficulties, patients with memory impairment caused by brain injury, elderly people with normal memory or elderly people with abnormal memory decline, the corresponding cognitive ability to be improved Cognitive ability sub-abilities can include: sensory memory ability, short-term memory ability, semantic memory ability, episodic memory ability and skill memory ability), when the corresponding cognitive ability sub-ability to be tested can be selected from the preset training task set It is a candidate training task for the cognitive ability sub-ability to be improved. If one candidate training task is selected, the one candidate training task is used as the task to be trained corresponding to the subject. If more than one candidate training task is selected, the candidate training task may be randomly selected from each candidate training task as the task to be trained. Alternatively, when the training task in the training task set has a difficulty coefficient associated with it, it is possible to determine the cognitive ability to be tested corresponding to the subject to be improved according to the corresponding relationship between the range of the test value and the range of the difficulty coefficient of the training task. The test value of the ability corresponds to the range of the difficulty coefficient of the training task. Then, among the selected candidate training tasks, candidate training tasks whose difficulty coefficients are within the determined difficulty coefficient range are determined as tasks to be trained.

Step 404, provide the task to be trained, and obtain task completion parameter information for the subject to complete the task to be trained.

For example, when the task to be trained is a program instruction sequence, the program instruction sequence corresponding to the task to be trained can be executed, and the task completion parameter information during the interaction process between the subject and the program instruction sequence, that is, the completion of the task to be trained, can be obtained. Here, the task completion parameter information may be various related information of the subject in the process of completing the task to be trained.

After the above steps 401 to 404, on the basis of obtaining the test value of each cognitive ability sub-ability of the test subject corresponding to the cognitive ability sub-ability set to be tested, the training task can be determined according to the test results, and the training can be provided. After the task, the task completion parameter information of the subject completing the training task can be obtained, and then the corresponding training can be realized after a comprehensive test, that is, the training is more targeted.

In some optional implementation manners, the above process 400 may also include the following steps 405 and 406:

Step 405, take the central node among the N nodes of the cognitive ability knowledge map to be tested as the current node, and perform the test operation again to obtain the corresponding preset cognitive ability sub-ability set to be tested after the subject completes the training task. The test value of cognitive ability sub-ability.

That is, conduct a comprehensive assessment test on the subject's cognitive ability again, and obtain the test value of each cognitive ability sub-ability corresponding to the preset cognitive ability sub-ability set to be tested after the subject completes the training task .

Step 406: Determine the training effect information of the subject according to the test value difference of the corresponding cognitive ability sub-ability in the preset cognitive ability sub-ability set to be tested before and after the subject completes the training task.

Since in step 402 the test value difference of the cognitive ability sub-abilities to be tested corresponding to the preset cognitive ability sub-ability sets to be tested is obtained before the subject completes the training task, and after step 405 the subject completes the training After the task, the test value difference corresponding to the cognitive ability sub-ability to be tested in the cognitive ability sub-ability set to be tested is preset. In order to evaluate the training effect, various implementation methods can be used to determine the difference between the two. Information about the training effect of the test subjects.

For example, after the subject completes the training task, the test value of each cognitive ability sub-ability to be tested in the preset cognitive ability sub-ability set to be measured can be used to subtract the corresponding cognitive ability sub-ability to be tested before the subject completes the training task. ability test value, and then obtain the test value difference of each cognitive ability sub-ability to be tested, and use it as the training effect information of the subject, that is, the training effect information can include each of the preset cognitive ability sub-ability sets to be tested The test value difference corresponding to the sub-ability of the cognitive ability to be tested can then be used to evaluate the training effect of the subject on each sub-ability of the cognitive ability to be tested through the training effect information.

For another example, the cognitive ability sub-ability to be tested corresponding to the task to be trained determined in step 403 may be determined first. Then, subtract the test value of the corresponding cognitive ability sub-ability of the test subject before completing the training task from the test value of the cognitive ability sub-ability corresponding to the training task after the subject completes the training task, and then obtain the test value of the cognitive ability sub-ability to be tested. The test value difference of the cognitive ability sub-ability to be tested corresponding to the training task is used as the training effect information of the subject, that is, the training effect information only includes the test value difference corresponding to the cognitive ability sub-ability to be tested corresponding to the training task value, and then the training effect of the subject corresponding to the cognitive ability sub-ability to be tested corresponding to the task to be trained can be evaluated through the training effect information.

After step 405 and step 406, the training effect of the subject before and after training can be evaluated to clarify the effect of the training task.

In some optional implementation manners, the above process 400 may also include the following step 407:

Step 407, according to the task completion parameter information of the subject's completion of the task to be trained, determine the completion degree score of the subject's completion of the task to be trained.

For example, here, the technical personnel may preliminarily formulate a corresponding relationship table or calculation formula of the degree of completion score based on the statistical analysis of the task completion parameter information of different people in the sample population who also complete the task to be trained, wherein the corresponding relationship table of the degree of completion score is To characterize the correspondence between the task completion parameter information of the task to be trained and the completion score of the task to be trained, and the calculation formula of the completion score is used to calculate each data in the task completion parameter information of the task to be trained to obtain The completion score of the training task. In this way, here, based on the task completion parameter information of the subject's completion of the task to be trained, a corresponding search can be performed according to the above correspondence table or calculation can be performed according to the above calculation formula to obtain the completion degree score of the subject's completion of the task to be trained.

That is, after step 407, the task completion parameter information of the subject completing the task to be trained can be converted into a unified standard completion score.

Based on an optional implementation manner of the above step 407, optionally, the above process 400 may also include the following steps 408 to 410:

Step 408: Determine the difficulty coefficient range of the next task to be trained according to the degree of completion of the task to be trained by the subject.

It is understandable that the degree of completion of the subject’s completion of the task to be trained represents the degree of completion of the subject’s training task. If the degree of completion is higher, it indicates that the degree of completion of the subject is higher, which can improve the degree of completion of the next task to be trained. The difficulty coefficient of the task; on the contrary, if the degree of completion indicates that the degree of completion is low, the difficulty coefficient of the next task to be trained can be maintained or reduced. It should be noted that increasing, maintaining or reducing the difficulty coefficient of the next task to be trained here refers to the difficulty coefficient of the current task to be trained.

Specifically determining the range of the difficulty coefficient of the next task to be trained can be implemented in various manners. For example, a score-difficulty correspondence table or a difficulty coefficient calculation formula can be prepared in advance by professionals (for example, psychologists or sociologists) based on professional knowledge, wherein the score-difficulty correspondence table is used to represent the degree of completion The corresponding relationship with the task difficulty coefficient range, and the difficulty coefficient calculation formula is used to calculate the degree of completion score to obtain the difficulty coefficient range. In this way, here, based on the completion degree score of the subject to complete the task to be trained, the corresponding search can be performed according to the above-mentioned score and difficulty correspondence table or calculated according to the above-mentioned task difficulty coefficient calculation formula to obtain the difficulty coefficient range of the next task to be trained .

Step 409 , among the determined candidate training tasks, the candidate training tasks whose difficulty coefficients are within the range of the determined difficulty coefficient of the next task to be trained are determined as the next task to be trained.

Here, the determined candidate training tasks may be the training tasks determined in the two optional implementation manners of step 403 and corresponding to the subject's ability to be trained or ability to be improved.

According to step 409, the next task to be trained corresponds to the same cognitive ability sub-ability to be tested as the task to be trained that the subject has completed, but the next task to be trained is based on the degree of completion of the task to be trained by the subject The training task determined after adjusting the difficulty coefficient is suitable for the specific situation of the subject, and can gradually improve the subject's ability to be trained or to be improved.

Step 410, providing the next task to be trained, and acquiring task completion parameter information for the subject to complete the task to be trained.

After steps 408 to 410, after the subject completes the task to be trained, the task difficulty of the next task to be trained can be customized according to the subject's actual completion level, and then the subject's cognitive ability to be tested can be gradually improved.

It should be noted that in practice, step 407 to step 410 can be repeated multiple times to repeatedly train the subject on the cognitive ability to be trained or to be improved, and re-determine the difficulty coefficient of the training task after each training , so as to gradually improve the subject's cognitive ability to be trained or to be improved.

Of course, in practice, after repeating steps 407 to 410 multiple times, step 402 is executed again to test the subject's cognitive ability to be tested, and then steps 403 and 404 are executed to determine and provide a new The task to be trained, and then repeatedly execute step 407 to step 410, until step 403 is performed to test the subject again, according to the test results, it is no longer necessary to train, and the cognitive ability of the subject to be tested has been improved .

As can be seen from FIG. 4 , compared with the embodiment corresponding to FIG. 2A , the flow 400 of the cognitive ability test method in this embodiment is more than that after the test subject’s cognitive ability is tested, it is determined according to the test results. Steps of training tasks, providing training tasks, and obtaining training task completion parameter information, optionally including the step of evaluating the training effect, or optionally including adjusting the difficulty of the next training task according to the training task completion parameter information coefficients and repeat the training steps. Therefore, the solution described in this embodiment can provide training tasks according to the test results of the test subject's cognitive ability to be tested, and then realize the improvement of the test subject's cognitive ability to be tested.

Further referring to FIG. 5 , as an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a cognitive ability testing device, which corresponds to the method embodiment shown in FIG. 2A , the device Specifically, it can be applied to various electronic devices.

As shown in FIG. 5 , the cognitive ability testing device 500 of this embodiment includes: an acquisition unit 501 configured to acquire a knowledge map of the cognitive ability to be tested, the knowledge map of the cognitive ability to be tested includes N nodes and the The correlation coefficient between any two nodes in the N nodes, each of the nodes is in one-to-one correspondence with the cognitive ability sub-ability to be tested in the preset cognitive ability sub-ability set to be tested, and each node corresponds to a function for testing the node A set of test tasks corresponding to the cognitive ability sub-ability to be tested; the test unit 502 is configured to use the central node among the N nodes as the current node to perform the following test operations: in the test task set associated with the current node Determine the task to be tested; provide the task to be tested, and obtain task completion parameter information for the subject to complete the task to be tested; determine the subject corresponding to the current node according to the task completion parameter information The test value of the cognitive ability sub-ability to be tested; according to the test value of the cognitive ability sub-ability to be tested corresponding to each node that has performed the test operation and the knowledge map of the cognitive ability to be tested For each correlation coefficient, estimate the test value of the test subject corresponding to the sub-ability of the cognitive ability to be tested corresponding to the node in the knowledge map of the cognitive ability to be tested that has not performed the test operation; determine whether the preset test operation is satisfied Condition; in response to a determination of Yes, ending the test operation.

In this embodiment, the specific processing of the acquisition unit 501 and the test unit 502 of the cognitive ability test device 500 and the technical effects brought about by them can refer to the relevant descriptions of step 201 and step 202 in the embodiment corresponding to FIG. 2A respectively. This will not be repeated here.

In some optional implementation manners, the apparatus 500 may further include: a task-to-be-trained determination unit 503 configured to correspond to each test subject in the preset cognitive ability sub-ability set to be tested according to the subject. The test value of the cognitive ability sub-ability is to determine the task to be trained corresponding to the subject from the preset training task set, wherein each of the preset training tasks corresponds to the preset cognitive ability sub-ability to be tested The cognitive ability sub-ability to be tested in the ability set; the training unit 504 is configured to provide the task to be trained, and obtain task completion parameter information for the subject to complete the task to be trained.

In some optional implementation manners, the apparatus 500 may further include: a retesting unit 505, configured to provide the task to be trained, and obtain the task completion parameters for the subject to complete the task to be trained After information, the central node among the N nodes of the cognitive ability knowledge map to be tested is used as the current node, and the test operation is performed again to obtain the corresponding preset to be tested after the subject completes the training task. The test value of the cognitive ability sub-ability to be tested in the cognitive ability sub-ability set; the training effect evaluation unit 506 is configured to correspond to the preset cognitive ability to be tested according to the subject before completing the training task and after completing the training task. The test value difference of the cognitive ability to be tested in the cognitive ability set is used to determine the training effect information of the subject.

In some optional implementation manners, the task-to-be-trained determination unit 503 may be further configured to: use the cognitive ability to be tested corresponding to the subject in the preset cognitive ability sub-ability set to be tested The cognitive ability sub-ability to be tested with the smallest test value of the sub-ability is determined as the cognitive ability sub-ability to be trained; determine the candidate training task corresponding to the cognitive ability sub-ability to be trained in the training task set; The task to be trained is determined in each candidate training task.

In some optional implementation manners, each training task in the training task set has a corresponding difficulty coefficient; and determining the task to be trained among the determined candidate training tasks may include: according to a preset test The corresponding relationship between the value range and the range of the difficulty coefficient of the training task determines the range of the difficulty coefficient of the training task corresponding to the test value of the cognitive ability sub-ability to be trained, wherein the test value of the cognitive ability sub-ability to be trained is the subject Corresponding to the test value of the sub-ability of the cognitive ability to be trained; among the determined candidate training tasks, a candidate training task whose difficulty coefficient is within the determined difficulty coefficient range is determined as the task to be trained.

In some optional implementation manners, the apparatus 500 may further include: a training task completion degree score determination unit 507 configured to determine the The degree of completion score for the subject to complete the task to be trained.

In some optional implementation manners, the apparatus 500 may further include: a difficulty coefficient determining unit 508 configured to determine the next task to be trained according to the completion degree score of the task to be trained by the subject. Range of difficulty coefficient; the next task to be trained determining unit 509 is configured to determine the candidate training task whose difficulty coefficient is within the range of the determined difficulty coefficient of the next task to be trained among the determined candidate training tasks as the next The task to be trained; the retraining unit 510 is configured to provide the next task to be trained, and obtain task completion parameter information for the subject to complete the next task to be trained.

In some optional implementation manners, the test operation may further include: in response to determining that the preset end condition of the test operation is not satisfied, according to the test subject corresponding to the cognitive ability knowledge map to be tested, the The correlation coefficient between the node of the test operation and the current node is used to determine the next node to be tested; and the test operation is continued with the next node to be tested as the current node.

In some optional implementation manners, the next test subject is determined according to the correlation coefficient between the subject and the current node in the cognitive ability knowledge map corresponding to the subject that has not performed the test operation. The node may include: determining the node with the smallest correlation coefficient with the current node among the nodes in the cognitive ability knowledge map corresponding to the test subject that has not performed the test operation, as the next node Node to be tested.

In some optional implementation manners, the apparatus 500 may further include: a central node determination unit 511 configured to, before performing the following test operation with the central node among the N nodes as the current node, based on the Determine the central node among the N nodes by measuring the cognitive ability knowledge map.

In some optional implementation manners, the central node determination unit 511 may be further configured to: determine the sum of the correlation coefficients of each node in the N nodes, where the sum of the correlation coefficients of the nodes is The sum of the correlation coefficients of other nodes different from the node and the node; the node with the largest sum of correlation coefficients among the N nodes is determined as the central node.

In some optional implementation manners, the knowledge map of the cognitive ability to be tested may be pre-established through the following knowledge map building step: obtaining an initial knowledge map of the cognitive ability to be tested, the initial knowledge map of the cognitive ability to be tested Including N nodes, each node in the initial cognitive ability knowledge map to be tested is in one-to-one correspondence with the cognitive ability sub-ability to be tested in the preset cognitive ability sub-ability set to be tested, and is correspondingly useful for testing the cognitive ability sub-ability A set of test tasks corresponding to the sub-ability of the cognitive ability to be tested corresponding to the node; obtaining a set of training samples, wherein the training samples include sample subjects completing the test tasks in the set of test tasks corresponding to the nodes in the knowledge map of the initial cognitive ability to be tested The sample task performance parameter information and the corresponding marked test value corresponding to each cognitive ability sub-ability in the preset cognitive ability sub-ability set to be tested; using machine learning methods, based on the training sample set The correlation coefficient between any two nodes in the initial cognitive ability knowledge map to be tested is adjusted; the initial cognitive ability knowledge map to be tested is determined as the preset cognitive ability knowledge map to be tested.

In some optional implementation manners, the cognitive ability knowledge map to be tested may also include a correlation coefficient between each test task in the test task set corresponding to each node and the node; and the current node Determining the task to be tested in the associated test task set may include: determining the test task with the highest correlation coefficient between the current node and the current node in the test task set associated with the current node.

In some optional implementation manners, the apparatus 500 may further include: the weakest ability node determining unit 512, configured to use the node corresponding to the subject in the cognitive ability knowledge map to be tested The node with the smallest test value of the cognitive ability sub-ability is determined as the node with the weakest ability; the first task to be tested determination unit 513 is configured to set the test task set corresponding to the node with the weakest ability to the node with the weakest ability The test task whose correlation coefficient of the weak node is not the highest is determined as the first task to be continued; the first continuous test unit 514 is configured to provide the first task to be continued, and obtain the test subject's completion of the second task. The task completion parameter information of the task to be tested continuously; the weakest ability test value determining unit 515 is configured to determine the subject according to the task completion parameter information of the first task to be continuously tested by the subject Corresponding to the test value of the cognitive ability sub-ability to be tested corresponding to the weakest ability node.

In some optional implementation manners, the apparatus 500 may further include: a test continuation node determination unit 516 configured to use the test subject corresponding to the node in the test cognitive ability knowledge graph A node whose test value of the cognitive ability sub-ability is less than the preset test value threshold is determined as a node to be tested continuously; the second continuous test unit 517 is configured to perform the following continuous test operation for each node to be tested continuously: In the test task set corresponding to the node to be tested, the test task whose correlation coefficient is not the highest with the node to be tested is determined as the second task to be tested; the second task to be tested is provided, and the subject is obtained Complete the task completion parameter information of the second to-be-tested task; according to the task completion parameter information of the subject to complete the second to-be-tested task, determine that the subject corresponds to the to-be-tested node corresponding The test value of the cognitive ability sub-ability to be tested.

In some optional implementation manners, according to the test value of the sub-ability of the cognitive ability to be tested corresponding to each node that has performed the test operation and the knowledge map of the cognitive ability to be tested For each correlation coefficient, estimating the test value of the test subject corresponding to the sub-ability of the cognitive ability to be tested corresponding to the node in the knowledge map of the cognitive ability to be tested that does not perform the test operation may include: for the subject The one corresponds to the node in the knowledge map of the cognitive ability to be tested that has not performed the test operation, and the subject corresponds to the test value of the sub-ability of the cognitive ability to be tested corresponding to each node that has performed the test operation, Perform weighted summation according to the correlation coefficients between the nodes that have performed the test operation and the nodes that have not performed the test operation, and determine the result of the weighted summation as the pending node corresponding to the node that has not performed the test operation Measure the test value of cognitive ability sub-ability.

In some optional implementation manners, the preset end condition of the test operation may include at least one of the following: the subject corresponds to each node in the cognitive ability knowledge map that has performed the test operation and has not performed the test operation. The prediction accuracy rate of the node in the test operation is greater than a preset prediction accuracy rate threshold, or the test operation has been executed for each node in the N nodes.

In some optional implementation manners, the cognitive ability to be tested may be memory, and the preset cognitive ability sub-ability set to be tested may include at least one of the following: sensory memory ability, short-term memory ability, semantic Memory ability, episodic memory ability, skill memory ability.

In some optional embodiments, the subject may be a child with memory development difficulties, a patient with memory impairment caused by brain injury, an elderly person with normal memory or an elderly person with abnormal memory decline.

In some optional embodiments, the test task set corresponding to sensory memory ability may include multi-picture partial report test task, and the test task set corresponding to short-term memory ability may include position memory span and verbal memory span test task, semantic memory ability The corresponding test task set may include the picture naming test task, the test task set corresponding to the episodic memory ability may include the human brain-picture association memory test task, and the test task set corresponding to the skill memory ability may include the probability learning test task.

In some optional implementation manners, the cognitive ability to be tested may be attention, and the preset cognitive ability sub-ability set to be tested may include at least one of the following: attention capacity ability, selective attention ability, continuous Attention, self-control, and responsiveness.

In some alternative embodiments, the subject may be a patient with ADHD.

It should be noted that, for the implementation details and technical effects of each unit in the cognitive ability testing device provided by the embodiments of the present disclosure, reference may be made to the descriptions of other embodiments of the present disclosure, which will not be repeated here.

Referring now to FIG. 6 , it shows a schematic structural diagram of a computer system 600 suitable for implementing the electronic device of the present disclosure. The computer system 600 shown in FIG. 6 is only an example, and should not limit the functions and scope of use of the embodiments of the present disclosure.

As shown in FIG. 6, a computer system 600 may include a processing device (eg, a central processing unit, a graphics processing unit, etc.) 601 that may be accessed randomly according to a program stored in a read-only memory (ROM) 602 or loaded from a storage device 608. Various appropriate actions and processes are executed by programs in the memory (RAM) 603 . In the RAM 603, various programs and data necessary for the operation of the computer system 600 are also stored. The processing device 601, ROM 602, and RAM 603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to the bus 604 .

Generally, the following devices can be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, etc.; output devices 607, including, for example, a liquid crystal display (LCD), speaker, vibrator, etc. ; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609 . The communication means 609 may allow the computer system 600 to communicate with other devices wirelessly or by wire to exchange data. While FIG. 6 shows a computer system 600 of electronic devices having various means, it should be understood that implementing or possessing all of the illustrated means is not a requirement. More or fewer means may alternatively be implemented or provided.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, where the computer program includes program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via communication means 609, or from storage means 608, or from ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are executed.

It should be noted that the above-mentioned computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. A computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave carrying computer-readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can transmit, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device . Program code embodied on a computer readable medium may be transmitted by any appropriate medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

The above-mentioned computer-readable medium may be included in the above-mentioned electronic device, or may exist independently without being incorporated into the electronic device.

The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device realizes the authentication shown in the embodiment shown in FIG. 2A and its optional implementation manners. Cognitive ability testing method, and/or, the cognitive ability testing method shown in the embodiment shown in FIG. 4 and its optional implementation.

Computer program code for carrying out the operations of the present disclosure can be written in one or more programming languages, or combinations thereof, including object-oriented programming languages—such as Java, Smalltalk, C++, and conventional Procedural Programming Language - such as "C" or a similar programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as through an Internet service provider). Internet connection).

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or portion of code that contains one or more logical functions for implementing specified executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.

The units involved in the embodiments described in the present disclosure may be implemented by software or by hardware. Wherein, the name of the unit does not constitute a limitation of the unit itself under certain circumstances. For example, the acquisition unit can also be described as "a unit that acquires the knowledge map of the cognitive ability to be tested".

The above description is only a preferred embodiment of the present disclosure and an illustration of the applied technical principles. Those skilled in the art should understand that the disclosure scope involved in this disclosure is not limited to the technical solution formed by the specific combination of the above-mentioned technical features, but also covers the technical solutions formed by the above-mentioned technical features or Other technical solutions formed by any combination of equivalent features. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

Claims

A cognitive ability testing method comprising:

Obtain a knowledge map of the cognitive ability to be tested, the knowledge map of the cognitive ability to be tested includes N nodes and correlation coefficients between any two nodes in the N nodes, and each of the nodes is respectively related to the preset cognitive ability to be tested The cognitive ability sub-ability to be tested in the ability sub-ability set corresponds one by one, and each node corresponds to a test task set for testing the cognitive ability sub-ability to be tested corresponding to the node;

Taking the central node among the N nodes as the current node to perform the following test operations: determine the task to be tested in the test task set associated with the current node; provide the task to be tested, and obtain the subject to complete the test task The task completion parameter information of the test task; according to the task completion parameter information, determine the test value of the subject corresponding to the cognitive ability sub-ability to be tested corresponding to the current node; The test value of the cognitive ability sub-ability to be tested corresponding to each node of the test operation and each correlation coefficient in the knowledge graph of the cognitive ability sub-ability to be tested are estimated to be corresponding to the cognitive ability sub-ability of the subject. The test value of the cognitive ability sub-capability to be tested corresponding to the node in the capability knowledge graph that has not performed the test operation; determine whether the preset test operation end condition is satisfied; and end the test operation in response to the determination.
The method according to claim 1, wherein the method further comprises:

According to the test value of the test subject corresponding to each cognitive ability sub-ability to be tested in the preset cognitive ability sub-ability set to be tested, determine the training task corresponding to the subject from the preset training task set Tasks, wherein each of the preset training tasks corresponds to the cognitive ability sub-ability to be tested in the preset cognitive ability sub-ability set to be tested;

The task to be trained is provided, and task completion parameter information for the subject to complete the task to be trained is acquired.
The method according to claim 2, wherein, after providing the task to be trained and obtaining the task completion parameter information of the subject completing the task to be trained, the method further comprises:

Taking the central node among the N nodes of the knowledge map of the cognitive ability to be tested as the current node, the test operation is performed again to obtain the preset cognitive ability to be tested after the subject completes the training task. The test value of the cognitive ability sub-ability to be tested in the sub-ability set;

According to the test value difference corresponding to the sub-ability of the cognitive ability to be tested in the preset cognitive ability sub-ability set to be tested before and after the subject completes the training task, the training of the subject is determined. Effect information.
The method according to claim 2, wherein, according to the test value of the test subject corresponding to each cognitive ability sub-ability in the preset cognitive ability sub-ability set to be tested, from the preset training task The task to be trained corresponding to the subject is determined in the set, including:

Determining the cognitive ability sub-ability to be tested with the smallest test value of the cognitive ability sub-ability corresponding to the subject in the preset cognitive ability sub-ability set to be tested as the cognitive ability sub-ability to be trained ;

determining a candidate training task corresponding to the cognitive ability sub-ability to be trained in the training task set;

The task to be trained is determined among the determined candidate training tasks.
The method according to claim 4, wherein each training task in the training task set has a corresponding difficulty coefficient; and

The determining the task to be trained in each determined candidate training task includes:

According to the corresponding relationship between the preset test value range and the training task difficulty coefficient range, determine the training task difficulty coefficient range corresponding to the cognitive ability sub-ability test value to be trained, wherein the cognitive ability sub-ability test value to be trained is The test value of the subject corresponding to the cognitive ability sub-ability to be trained;

Among the determined candidate training tasks, a candidate training task whose difficulty coefficient is within the determined difficulty coefficient range is determined as the task to be trained.
The method according to claim 5, wherein the method further comprises:

According to the task completion parameter information of the subject completing the task to be trained, the completion degree score of the subject completing the task to be trained is determined.
The method according to claim 6, wherein the method further comprises:

Determine the difficulty coefficient range of the next task to be trained according to the degree of completion score of the task to be trained by the subject;

Determining a candidate training task whose difficulty coefficient is within the determined difficulty coefficient range of the next task to be trained among the determined candidate training tasks as the next task to be trained;

The next task to be trained is provided, and task completion parameter information for the subject to complete the next task to be trained is acquired.
The method according to claim 1, wherein said testing operation further comprises:

In response to determining that the preset test operation end condition is not satisfied, according to the correlation coefficient between the subject's node corresponding to the cognitive ability knowledge map to be tested and the node that has not performed the test operation and the current node, determine the next test operation measuring node;

Continue to execute the test operation with the next node to be tested as the current node.
The method according to claim 8, wherein, according to the correlation coefficient between the subject and the current node in the cognitive ability knowledge map corresponding to the subject that has not performed the test operation, determine the next Nodes to be tested, including:

Determining the node with the smallest correlation coefficient with the current node among the nodes in the knowledge map of the subject's cognitive ability to be tested that has not performed the test operation, as the next node to be tested.
The method according to claim 1, wherein, before performing the following test operations with the central node in the N nodes as the current node, the method further comprises:

A central node among the N nodes is determined based on the knowledge map of the cognitive ability to be tested.
The method according to claim 10, wherein said determining the central node among said N nodes based on said cognitive ability knowledge map to be tested comprises:

determining the sum of the correlation coefficients of each node in the N nodes, wherein the sum of the correlation coefficients of the nodes is the sum of the correlation coefficients of other nodes different from the node among the N nodes and the node;

The node with the largest correlation coefficient sum among the N nodes is determined as the central node.
The method according to claim 1, wherein the knowledge graph of the cognitive ability to be tested is pre-established through the following knowledge graph building steps:

Obtaining an initial cognitive ability knowledge map to be tested, the initial cognitive ability knowledge map to be tested includes N nodes, and each node in the initial cognitive ability knowledge map to be tested is respectively connected to the preset cognitive ability child to be tested In the capability set, the sub-capabilities of the cognitive abilities to be tested correspond one-to-one, and there is a set of test tasks for testing the sub-capacities of the cognitive abilities to be tested corresponding to the node;

Obtain a training sample set, wherein the training sample includes the sample task performance parameter information of the sample subject completing the test task set corresponding to the node in the initial cognitive ability knowledge graph to be tested and the corresponding preset test task The marked test value corresponding to each cognitive ability sub-ability to be tested in the cognitive ability sub-ability set;

Using a machine learning method to adjust the correlation coefficient between any two nodes in the initial cognitive ability knowledge graph to be tested based on the training sample set;

The initial knowledge map of the cognitive ability to be tested is determined as the preset knowledge map of the cognitive ability to be tested.
The method according to claim 12, wherein the cognitive ability knowledge map to be tested further includes a correlation coefficient between each test task and the node in the test task set corresponding to each node; and

The determining the task to be tested in the test task set associated with the current node includes:

The test task with the highest correlation coefficient with the current node in the set of test tasks associated with the current node determines the task to be tested.
The method according to claim 13, wherein the method further comprises:

Determining the node with the smallest test value of the sub-ability of the cognitive ability to be tested corresponding to the subject among the nodes in the knowledge map of the cognitive ability to be tested as the node with the weakest ability;

Determining a test task that has a non-highest correlation coefficient with the node with the weakest capability in the test task set corresponding to the node with the weakest capability as the first task to be continued;

providing the first task to be continued, and obtaining task completion parameter information for the subject to complete the first task to be continued;

According to the task completion parameter information of the subject completing the first task to be continuously tested, the test value of the subject's cognitive ability sub-ability to be tested corresponding to the weakest ability node is determined.
The method according to claim 13, wherein the method further comprises:

Among the nodes in the cognitive ability knowledge map to be tested, the nodes corresponding to the subject's cognitive ability sub-ability to be tested whose test value is less than the preset test value threshold are determined as nodes to be tested;

For each of the nodes to be tested, the following continuous test operation is performed: in the test task set corresponding to the node to be tested, the test task that has a non-highest correlation coefficient with the node to be tested is determined as the second task to be tested; Provide the second task to be tested continuously, and obtain the task completion parameter information of the subject completing the second task to be tested continuously; The parameter information is used to determine the test value of the subject corresponding to the sub-ability of the cognitive ability to be tested corresponding to the node to be tested.
The method according to claim 1, wherein, according to the test value of the sub-ability of the cognitive ability to be tested corresponding to each node that has performed the test operation and the knowledge of the cognitive ability to be tested Each correlation coefficient in the map estimates the test value of the subject's cognitive ability sub-ability corresponding to the node in the knowledge map of the cognitive ability to be tested that does not perform the test operation, including:

For the subject corresponding to the nodes in the knowledge graph of the cognitive ability to be tested that have not performed the test operation, for the subject corresponding to the nodes of the cognitive ability to be tested corresponding to the nodes that have performed the test operation The test value of the ability is weighted and summed according to the correlation coefficients between the nodes that have performed the test operation and the nodes that have not performed the test operation, and the result of the weighted sum is determined as the result of the test operation that has not been performed. The test value of the sub-ability of the cognitive ability to be tested corresponds to the node of .
The method according to claim 16, wherein the preset test operation end condition includes at least one of the following:

The prediction accuracy rate of the subject corresponding to each node that has performed the test operation in the cognitive ability knowledge map to the node that has not performed the test operation is greater than the preset prediction accuracy rate threshold, or for the N Each of the nodes has performed the test operation.
The method according to claim 1, wherein the cognitive ability to be tested is memory, and the set of sub-abilities of the preset cognitive ability to be tested includes at least one of the following: sensory memory ability, short-term memory ability, semantic Memory ability, episodic memory ability, skill memory ability.
The method according to claim 18, wherein the subject is a child with memory development difficulties, a patient with memory impairment caused by brain injury, an elderly person with normal memory or an elderly person with abnormal memory decline.
The method according to claim 19, wherein the test task set corresponding to the sensory memory ability includes a multi-picture partial report test task, the test task set corresponding to the short-term memory ability includes position memory span and verbal memory span test tasks, semantic memory ability The corresponding test task set includes the picture naming test task, the test task set corresponding to the episodic memory ability includes the human brain-picture association memory test task, and the test task set corresponding to the skill memory ability includes the probability learning test task.
The method according to claim 1, wherein the cognitive ability to be tested is attention, and the preset cognitive ability sub-ability set to be tested includes at least one of the following: attention capacity ability, selective attention ability, continuous Attention, self-control, and responsiveness.
The method of claim 21, wherein the subject is a person with ADHD.
A cognitive ability testing device, comprising:

The acquiring unit is configured to acquire a knowledge map of the cognitive ability to be tested, the knowledge map of the cognitive ability to be tested includes N nodes and correlation coefficients between any two nodes in the N nodes, and each of the nodes is respectively related to The cognitive ability sub-abilities to be tested in the preset cognitive ability sub-ability set to be tested correspond one-to-one, and each node corresponds to a test task set for testing the cognitive ability sub-ability to be tested corresponding to the node;

The test unit is configured to use the central node among the N nodes as the current node to perform the following test operations: determine the task to be tested in the test task set associated with the current node; provide the task to be tested, and obtain the tested task. The tester completes the task completion parameter information of the task to be tested; according to the task completion parameter information, determine the test value of the test subject corresponding to the cognitive ability sub-ability to be tested corresponding to the current node; according to the subject The tester corresponds to the test value of the cognitive ability sub-ability to be tested corresponding to each node that has performed the test operation and each correlation coefficient in the cognitive ability knowledge map to be tested, and estimates that the subject corresponds to the tested cognitive ability The test value of the cognitive ability sub-ability to be tested corresponding to the node in the cognitive ability knowledge graph that has not performed the test operation; determine whether the preset test operation end condition is satisfied; and end the test operation in response to the determination.
An electronic device comprising:

one or more processors;

a storage device on which one or more programs are stored,

When the one or more programs are executed by the one or more processors, the one or more processors are made to implement the method according to any one of claims 1-22.
A computer-readable storage medium on which a computer program is stored, wherein the computer program implements the method according to any one of claims 1-22 when executed by one or more processors.