CN110688550A - Cognitive load evaluation method, device and system and storage medium - Google Patents
Cognitive load evaluation method, device and system and storage medium Download PDFInfo
- Publication number
- CN110688550A CN110688550A CN201910842346.9A CN201910842346A CN110688550A CN 110688550 A CN110688550 A CN 110688550A CN 201910842346 A CN201910842346 A CN 201910842346A CN 110688550 A CN110688550 A CN 110688550A
- Authority
- CN
- China
- Prior art keywords
- cognitive
- data set
- driver
- environment
- attribute value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a cognitive load evaluation method, a device, a system and a storage medium, wherein the cognitive load evaluation method comprises the following steps: acquiring a cognitive data set, and determining a cognitive environment where the cognitive data set is located; respectively calculating Euclidean distances between the cognitive data set and each clustering center in the cognitive environment of a preset clustering center database; and selecting the minimum Euclidean distance, and taking the cognitive load grade to which the cluster center corresponding to the minimum Euclidean distance belongs as the cognitive load grade of the cognitive data set. According to the scheme, the Euclidean distance between the cognitive data set and each clustering center in the cognitive environment of the preset clustering center database is calculated, so that the cognitive load grade of the cognitive data set can be determined, the cognitive load change caused by the change of the automobile driving function to an intelligent internet automobile driver can be ranked before the design and the design of the intelligent internet automobile are finalized, and the reasonability and the suitability of the design of the human-computer interface of the intelligent internet automobile are determined.
Description
Technical Field
The invention relates to the technical field of intelligent driving, in particular to a cognitive load evaluation method, a cognitive load evaluation device, a cognitive load evaluation system and a storage medium.
Background
In the intelligent networked automobile cabin, along with the continuous upgrading of information technology and the integration of new technology, the information cognition amount of a driver is increased, and the cognition load of the driver is correspondingly increased. The cognitive load of the driver is too large, so that the driver acts slowly, acts discontinuously, operates slowly, has weak attention and visual acuity, the performance of the intelligent networked automobile cannot be fully exerted, and the response speed and the ability of the driver to deal with emergency are reduced.
Therefore, the cognitive load of the driver needs to be evaluated before the design and the design of the automobile are finalized, so that whether the basic safe driving operation is influenced by the fact that the excessive cognitive load is caused to the driver or not is determined to be distributed to the new man-machine function, the adaptability of the operation process is finally ensured, the operation convenience and the efficiency of the driver are improved, and the excellent performance of the intelligent networked automobile is fully exerted.
The cognitive load of a driver of a conventional automobile is mainly evaluated for a single index, for example, a person uses changes of indexes such as the number of blinks, the number of gazing times or the pupil area to evaluate the intensity of the driving workload, and it is considered that in the case of an increase in the line-of-sight pressure, the driver tries to acquire more visual information by reducing the number of blinks and increasing the duration of gazing. However, the evaluation method adopts a single index, and the cognitive load of the driver cannot be truly and comprehensively reflected.
Disclosure of Invention
In view of this, embodiments of the present invention provide a cognitive load evaluation method, apparatus, system and storage medium to truly and comprehensively reflect a driver's cognitive load.
According to a first aspect, an embodiment of the present invention provides a cognitive load evaluation method, including the following steps:
acquiring a cognitive data set, and determining a cognitive environment in which the cognitive data set is positioned;
respectively calculating Euclidean distances between the cognitive data set and each clustering center in the cognitive environment of a preset clustering center database;
and selecting the minimum Euclidean distance, and taking the cognitive load grade to which the clustering center corresponding to the minimum Euclidean distance belongs as the cognitive load grade of the cognitive data set.
According to the cognitive load evaluation method provided by the embodiment of the invention, the cognitive data set is obtained, the Euclidean distance between the cognitive data set and each cluster center in the cognitive environment of the preset cluster center database is calculated, the cognitive load grade of the cluster center corresponding to the minimum Euclidean distance is taken as the cognitive load grade of the cognitive data set, the cognitive load of the cognitive data set can be reasonably reflected, and meanwhile, the cognitive load of a driver can be comprehensively reflected because the cognitive data set is acquired instead of a single index. By using the technical scheme of the invention, the cognitive load change caused by the change of the automobile driving function to the intelligent networked automobile driver can be graded before the design and the design of the intelligent networked automobile are finalized, so that the reasonability and the suitability of the design of the human-computer interface of the intelligent networked automobile are determined.
With reference to the first aspect, in a first implementation manner of the first aspect, the calculating a euclidean distance between the cognitive data set and each cluster center in the cognitive environment of a preset cluster center database includes:
calculating the Euclidean distance between the cognitive data set and any clustering center in the cognitive environment of the clustering center database by using a preset first formula;
traversing each clustering center in the cognitive environment to obtain Euclidean distances between the cognitive data set and each clustering center in the cognitive environment of the clustering center database;
wherein the first formula is
In the first formula, AnRepresenting the cognitive dataset, CknDenotes any cluster center, a11 st attribute value, a, representing the cognitive data set2 A 2 nd attribute value, a, representing the cognitive data setnN-th attribute value, C, representing the cognitive data setkl1 st attribute value, C, representing the center of the cluster k22 nd attribute value, C, representing the center of the clusterknAn nth attribute value representing the cluster center.
With reference to the first aspect, in a second embodiment of the first aspect, the cognitive load assessment method further includes: and constructing the clustering center database according to the sample cognitive data set.
With reference to the second implementation manner of the first aspect, in a third implementation manner of the first aspect, the building a cluster center database according to the sample cognitive data sets includes:
acquiring a plurality of sample cognitive data sets of the same cognitive environment;
correcting each sample cognitive data set by using preset reference data to obtain a corrected sample cognitive data set;
clustering the plurality of corrected sample cognitive data sets according to the number of cognitive load grades to obtain a clustering center of each grade of the cognitive load;
and traversing each cognitive environment to obtain a clustering center database.
With reference to the third implementation manner of the first aspect, in the fourth implementation manner of the first aspect, the modifying each sample cognitive data set by using preset reference data to obtain a modified sample cognitive data set includes:
subtracting the reference data corresponding to the attribute value from any attribute value in the sample cognitive data set to obtain a modified attribute value;
and traversing each attribute value in the sample cognitive data set to obtain a modified sample cognitive data set.
With reference to the first embodiment of the first aspect and the fourth embodiment of the first aspect, in a fifth embodiment of the first aspect, the attribute values of the cognitive dataset/sample cognitive dataset include one or more of the following: the method comprises the following steps of responding time of the operation of a driver, responding time of a peripheral visual detection scene of the driver, and a correct rate and a heart rate variation rate of the driver of the peripheral visual detection scene of the driver.
According to a second aspect, an embodiment of the present invention provides a cognitive load evaluation device, including:
the acquisition module is used for acquiring a cognitive data set;
the processing module is used for determining the cognitive environment where the cognitive data set is located;
the calculation module is used for calculating Euclidean distances between the cognitive data set and each clustering center in the cognitive environment of a preset clustering center database respectively;
and the cognitive load determining module is used for selecting the minimum Euclidean distance and taking the cognitive load grade to which the cluster center corresponding to the minimum Euclidean distance belongs as the cognitive load grade of the cognitive data set.
According to a third aspect, an embodiment of the present invention provides a cognitive load evaluation system, including:
the cognitive load evaluation method comprises a cognitive data acquisition subsystem, a memory and a processor, wherein the cognitive data acquisition subsystem, the memory and the processor are in communication connection with each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the cognitive load evaluation method according to the first aspect or any embodiment of the first aspect.
With reference to the third aspect, in a first implementation manner of the third aspect, the cognitive data acquisition subsystem is further disposed in the human-machine interface semi-physical simulation subsystem.
According to a fourth aspect, the present invention further provides a computer-readable storage medium, where computer instructions are stored, and the computer instructions are configured to cause the computer to execute the cognitive load evaluation method according to the first aspect or any of the embodiments of the first aspect.
Drawings
The features and advantages of the present invention will be more clearly understood by reference to the accompanying drawings, which are illustrative and not to be construed as limiting the invention in any way, and in which:
FIG. 1 is a schematic flow chart of a cognitive load assessment method in example 1 of the present invention;
fig. 2 is a schematic flow chart of constructing a cluster center database in embodiment 2 of the present invention;
FIG. 3 is a schematic structural diagram of a cognitive load evaluation device in embodiment 3 of the present invention;
fig. 4 is a schematic structural diagram of a cognitive load evaluation system in embodiment 4 of the present invention;
FIG. 5 is a schematic structural diagram of a hardware subsystem of an intelligent networked automobile human-computer interface in embodiment 4 of the present invention;
FIG. 6 is a schematic view of a workflow of an intelligent networked automobile driver cognitive data acquisition subsystem in embodiment 4 of the present invention;
fig. 7 is a schematic view of a workflow of a multi-source cognitive data processing subsystem of an intelligent networked automobile driver in embodiment 4 of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
The embodiment 1 of the present invention provides a cognitive load evaluation method, and fig. 1 is a schematic flow chart of the cognitive load evaluation method in the embodiment 1 of the present invention, and as shown in fig. 1, the cognitive load evaluation method in the embodiment 1 of the present invention includes the following steps:
s101: acquiring a cognitive data set, and determining the cognitive environment where the cognitive data set is located.
In example 1 of the present invention, cognitive data set AnIncludes a plurality of attribute values { a }1,a2,…,ai,…,an}. Exemplary cognitive data set AnIncluding driver operation reaction time a1Reaction time a of peripheral visual detection scene of driver2And the accuracy a of the peripheral vision detection scene of the driver3And the heart rate variability a of the driver4。
The cognitive environment in the embodiment of the invention refers to a driving scene where a driver is located when the cognitive data set is acquired and an operation stage where the driver is located in the driving scene. Specifically, the driving scene refers to a scene in which the automobile is driven, such as following, lane changing, overtaking, autonomous parking, and the like; the operation phase refers to what phase of driving the vehicle is, such as a start phase, an observation phase, a braking phase, a turning phase, an acceleration phase, a flameout phase, a getting-off phase, etc.
S102: and respectively calculating Euclidean distances between the cognitive data set and each clustering center in the cognitive environment of a preset clustering center database.
As a specific implementation manner, the calculating the euclidean distance between the cognitive data set and each cluster center in the cognitive environment of the preset cluster center database includes:
calculating the Euclidean distance between the cognitive data set and any clustering center in the cognitive environment of the clustering center database by using a preset first formula;
traversing each clustering center in the cognitive environment to obtain Euclidean distances between the cognitive data set and each clustering center in the cognitive environment of the clustering center database;
wherein the first formula is
In the first formula, AnRepresenting the cognitive dataset, CknDenotes any cluster center, a11 st attribute value, a, representing the cognitive data set2 A 2 nd attribute value, a, representing the cognitive data setnN-th attribute value, C, representing the cognitive data setkl1 st attribute value, C, representing the center of the cluster k22 nd attribute value, C, representing the center of the clusterknAn nth attribute value representing the cluster center.
S103: and selecting the minimum Euclidean distance, and taking the cognitive load grade to which the cluster center corresponding to the minimum Euclidean distance belongs as the cognitive load grade of the cognitive data.
The cognitive load evaluation method provided by embodiment 1 of the present invention obtains a cognitive data set, calculates the euclidean distance between the cognitive data set and each cluster center in the cognitive environment of a preset cluster center database, and uses the cognitive load grade to which the cluster center corresponding to the minimum euclidean distance belongs as the cognitive load grade of the cognitive data set, so as to reasonably reflect the cognitive load of the cognitive data set. By using the technical scheme of the invention, the cognitive load change caused by the change of the automobile driving function to the intelligent networked automobile driver can be graded before the design and the design of the intelligent networked automobile are finalized, so that the reasonability and the suitability of the design of the human-computer interface of the intelligent networked automobile are determined.
Example 2
The embodiment 2 of the invention provides a cognitive load evaluation method, and the cognitive load evaluation method of the embodiment 2 of the invention comprises the following steps:
s201: and constructing the clustering center database according to the sample cognitive data.
As a specific implementation manner, embodiment 2 of the present invention provides a method for constructing a clustering center database. Fig. 2 is a schematic flow chart of constructing a cluster center database in embodiment 2 of the present invention, and as shown in fig. 2, the method includes the following steps:
step 1: multiple sample cognitive datasets of the same cognitive environment are acquired.
Step 2: and correcting each sample cognitive data set by using preset reference data to obtain a corrected sample cognitive data set.
As a specific implementation manner, modifying each sample cognitive data set by using preset reference data, and obtaining a modified sample cognitive data set includes: subtracting the reference data corresponding to the attribute value from any attribute value in the sample cognitive data set to obtain a modified attribute value; and traversing each attribute value in the sample cognitive data set to obtain a modified sample cognitive data set.
For example, when the attribute value is a driver operation response time, the driver operation response time is directly used as the corrected attribute value. That is, the preset reference data corresponding to the driver's operation reaction time is set to zero.
And when the attribute value is the reaction time of the driver peripheral vision detection scene, subtracting the static peripheral vision detection scene reference reaction time from the reaction time of the driver peripheral vision detection scene to obtain a corrected attribute value. That is, the preset reference data corresponding to the reaction time of the driver peripheral vision detection scene is the static peripheral vision detection scene reference reaction time.
And when the attribute value is the accuracy of the peripheral vision detection scene of the driver, subtracting the accuracy of the static peripheral vision detection scene from the accuracy of the peripheral vision detection scene of the driver to obtain a corrected attribute value. That is, the preset reference data corresponding to the accuracy of the driver peripheral vision inspection scene is the static peripheral vision inspection scene accuracy.
And when the attribute value is the heart rate variation rate of the driver, subtracting the static reference heart rate variation rate from the heart rate variation rate of the driver to obtain a corrected attribute value. That is, the preset reference data corresponding to the heart rate variability of the driver is the static reference heart rate variability.
And step 3: and clustering the plurality of corrected sample cognitive data sets according to the number of cognitive load grades to obtain the clustering center of each grade of the cognitive load.
The cognitive load level of the driver may be divided into K levels (for example, in embodiment 2 of the present invention, K is 1,2,.., K is 3) and the cognitive data set a is divided into three levels, i.e., high, medium, and low levels), and the cognitive load level is divided into K levelsnMay include a plurality of attribute values a1,a2,…,ai,…,an} (e.g. including driver operation reaction time a1Average reaction time of driver peripheral vision detection scene a2Average accuracy a of driver peripheral vision inspection scene3Average heart rate variability of driver a4Four attribute values, n is 4). By testing a large number of experimental samples (>60) attribute values of the cognitive data sets are subjected to mean value clustering to obtain clustering centers C with different gradeskn，Ckn＝{ck1,ck2,…,ckj,…,ckn}。
And 4, step 4: and traversing each cognitive environment to obtain a clustering center database.
In embodiment 2 of the present invention, the cluster center database includes cluster centers of various cognitive environments, where the number of cluster centers of each cognitive environment is at least two.
The clustering center database constructed by the method can cover various typical and special scenes in the driving process, and classifies the clustering centers according to different stages of each scene, meanwhile, the correlation between each attribute value of the clustering centers and the cognitive load is obvious, and the set grade can reflect the change of the cognitive load more truly.
S202: acquiring a cognitive data set, and determining the cognitive environment where the cognitive data set is located.
S203: and respectively calculating Euclidean distances between the cognitive data set and each clustering center in the cognitive environment of a preset clustering center database.
S204: and selecting the minimum Euclidean distance, and taking the cognitive load grade to which the clustering center corresponding to the minimum Euclidean distance belongs as the cognitive load grade of the cognitive data set.
Example 3
Specifically, the obtaining module 30 is configured to obtain the cognitive data set.
And the processing module 32 is configured to determine a cognitive environment in which the cognitive data set is located.
And the calculating module 34 is configured to calculate euclidean distances between the cognitive data set and each cluster center in the cognitive environment of a preset cluster center database, respectively.
And the cognitive load determining module 36 is configured to select a minimum euclidean distance, and use a cognitive load level to which a cluster center corresponding to the minimum euclidean distance belongs as the cognitive load level of the cognitive data set.
As a specific implementation, the calculation module 34 is specifically configured to:
calculating the Euclidean distance between the cognitive data set and any clustering center in the cognitive environment of the clustering center database by using a preset first formula;
traversing each clustering center in the cognitive environment to obtain Euclidean distances between the cognitive data set and each clustering center in the cognitive environment of the clustering center database;
wherein the first formula is
In the first formula, AnRepresenting the cognitive dataset, CknDenotes any cluster center, a11 st attribute value, a, representing the cognitive data set2A 2 nd attribute value, a, representing the cognitive data setnN-th attribute value, C, representing the cognitive data setkl1 st attribute value, C, representing the center of the cluster k22 nd attribute value, C, representing the center of the clusterknAn nth attribute value representing the cluster center.
Further, the cognitive load evaluation device according to embodiment 3 of the present invention further includes a clustering center database construction module, configured to construct the clustering center database according to the sample cognitive data.
As a specific implementation manner, the cluster center database construction module is specifically configured to:
acquiring a plurality of sample cognitive data sets of the same cognitive environment;
correcting each sample cognitive data set by using preset reference data to obtain a corrected sample cognitive data set;
clustering the plurality of corrected sample cognitive data sets according to the number of cognitive load grades to obtain a clustering center of each grade of the cognitive load;
and traversing each cognitive environment to obtain a clustering center database.
As a specific implementation manner, the cluster center database construction module is specifically configured to: subtracting the reference data corresponding to the attribute value from any attribute value in the sample cognitive data set to obtain a modified attribute value; and traversing each attribute value in the sample cognitive data set to obtain a modified sample cognitive data set.
In embodiment 3 of the present invention, the attribute values of the cognitive dataset/sample cognitive dataset include one or more of the following: the method comprises the following steps of responding time of the operation of a driver, responding time of a peripheral visual detection scene of the driver, and a correct rate and a heart rate variation rate of the driver of the peripheral visual detection scene of the driver.
Example 4
Embodiment 4 of the present invention provides a cognitive load evaluation system, fig. 4 is a schematic structural diagram of the cognitive load evaluation system in embodiment 4 of the present invention, and as shown in fig. 4, a cognitive load evaluation device in embodiment 4 of the present invention includes: the system comprises an intelligent networked automobile human-computer interface semi-physical simulation subsystem 1, an intelligent networked automobile human-computer interface hardware subsystem 2, an intelligent networked automobile driver cognitive data acquisition subsystem 3 and an intelligent networked automobile driver multi-source cognitive data processing subsystem 4; the intelligent networked automobile human-computer interface semi-physical simulation subsystem 1 is used for performing semi-physical simulation on the environment in the process of driving a vehicle by a driver; the intelligent internet automobile human-computer interface hardware subsystem 2 is used for simulating a cockpit display control interface (the interface is a human-computer interface interactive system) in the scene operation process of a driver; the intelligent networked automobile driver cognitive data acquisition subsystem 3 is arranged in the intelligent networked automobile human-computer interface hardware subsystem 2 and is used for acquiring and recording load rating related data (namely cognitive data) of a driver in a vehicle driving process, and the intelligent networked automobile driver multi-source cognitive data processing subsystem 4 is used for calculating the cognitive load level of the driver in the vehicle driving process.
Fig. 5 is a schematic structural diagram of a hardware subsystem of an intelligent internet automobile human-machine interface in embodiment 4 of the present invention. As shown in fig. 5, the intelligent networked automobile human-machine interface hardware subsystem in embodiment 4 of the present invention includes an intelligent networked automobile human-machine interface operation simulation module (201 and 203 and 205 and 212), and an intelligent networked automobile driver scene data acquisition system terminal 204 of the intelligent networked automobile driver cognitive data acquisition subsystem 3.
Specifically, the intelligent networking automobile human-computer interface operation simulation module comprises a simulation cabin shell bracket 201, automobile doors 202a, 202b, 202c and 202 d; the system comprises a rear passenger seat 203, a front passenger seat 205, a driver seat 206, a gear shifting and operating device 207, a steering wheel 208, a front passenger entertainment screen 209, a central control display screen 210, a driver instrument 211 and an annular visual display screen 212, human-computer interface information in the driving process of the vehicle can be truly simulated through an intelligent network-connected automobile human-computer interface operation simulation module, and simulation equipment can be flexibly arranged according to scene requirements.
The copilot entertainment screen 209, the central control display screen 210, the driver instrument 211 and the annular view display screen 212 can create a real virtual driving scene for a driver, and provide in-vehicle information display and out-vehicle environment simulation information required by the scene. The virtual reality technology based on real object virtualization, virtual object virtualization and computer processing technology is mainly used for establishing a virtual space with high reality sense, immersion sense and interaction, and creating a high-fidelity virtual scene operating environment for a driver.
Specifically, as shown in fig. 6, the intelligent internet automobile driver cognitive data acquisition subsystem 3 is specifically configured to implement the following work flow:
firstly, a main power switch of the automobile semi-physical simulation system is turned on, a cognitive data acquisition subsystem of an automobile driver is debugged, whether data recording is normal or not is judged, if so, the step 31 is carried out, and if not, debugging is continued.
Step 31: testing and recording the reference response time of the static peripheral vision detection scene of the driver and the accuracy of the static peripheral vision detection scene of the driver;
step 32: testing and recording the static reference heart rate variation rate of the driver;
step 33: deploying a driving scene environment through the intelligent networked automobile human-computer interface semi-physical simulation subsystem 1, setting an operation stage of a driver in the scene, and performing the next step 34 after the setting is completed;
step 34: starting to collect a cognitive data set;
step 35: recording attribute values of all cognitive data sets of a driver in real time in the acquisition process: the method comprises the steps of responding time of the operation of drivers at different stages in the scene operation process, responding time of peripheral visual detection scenes of the drivers at different stages in the scene operation process, the accuracy rate of the peripheral visual detection scenes of the drivers at different stages in the scene operation process, and the heart rate variability rate of the drivers at different stages in the scene operation process.
Specifically, the intelligent networked automobile driver multi-source cognitive data processing subsystem 4 comprises a processor and a memory, and is specifically used for realizing the following work flow as shown in fig. 7:
step 401: reading static reference data of a driver in each cognitive environment: the method comprises the steps of reference response time of a static peripheral vision detection scene of a driver, the accuracy rate of the static peripheral vision detection scene of the driver and the static reference heart rate variability rate of the driver. Averaging the reference response times of a plurality of static peripheral vision detection scenes of the driver in each cognitive environment to obtain the average reference response time of the static peripheral vision detection scenes of the driver; averaging the accuracy rates of a plurality of static peripheral vision detection scenes of the driver in each cognitive environment to obtain the average accuracy rate of the static peripheral vision detection scenes of the driver; and averaging the plurality of static reference heart rate variability rates of the drivers in each cognitive environment to obtain the static average reference heart rate variability rate of the drivers.
Reading in sample cognitive data sets, wherein each sample cognitive data set comprises four attribute values: the method comprises the following steps of responding time of the operation of a driver, responding time of a peripheral visual detection scene of the driver, and a correct rate and a heart rate variation rate of the driver of the peripheral visual detection scene of the driver.
And subtracting the reference data corresponding to the attribute value from any attribute value in the sample cognitive data set to obtain the corrected attribute value. When the attribute value is the operation reaction time of the driver, directly taking the operation reaction time of the driver as the corrected attribute value; when the attribute value is the reaction time of the driver peripheral visual detection scene, subtracting the average reference reaction time of the static driver peripheral visual detection scene from the reaction time of the driver peripheral visual detection scene to obtain a corrected attribute value; when the attribute value is the accuracy of the peripheral vision detection scene of the driver, subtracting the average accuracy of the static peripheral vision detection scene of the driver from the accuracy of the peripheral vision detection scene of the driver to obtain a corrected attribute value; and when the attribute value is the heart rate variation rate of the driver, subtracting the static average reference heart rate variation rate of the driver from the heart rate variation rate of the driver to obtain a corrected attribute value.
Step 402: setting the cognitive load level of a driver to be a high level, a middle level and a low level;
step 403: and (3) utilizing the corrected attribute values of all cognitive data sets in the same cognitive environment: the operation response time of the driver, the response time of the peripheral vision detection scene of the driver, the accuracy rate of the peripheral vision detection scene of the driver, and the driver's mindRate variation rate, calculating clustering centers of 3 grades of cognitive load, and performing mean clustering to obtain clustering centers C of different grades in the cognitive environmentkj；
Step 404: repeating the step 403, traversing each cognitive environment to obtain a clustering center of each load grade in different cognitive environments, and obtaining a clustering center database;
step 405: collecting a new cognitive data set of a driver in any cognitive environment;
step 406: reading a new cognitive data set of a driver in any cognitive environment;
step 407: respectively calculating Euclidean distances between a new cognitive data set of a driver and 3 hierarchical clustering centers in a corresponding cognitive environment of a clustering center database; the Euclidean distance from the cluster center is the minimum, and the load grade of the cluster center is the cognitive load grade of the corresponding cognitive data set;
step 408: and repeating the steps 405-407, traversing each cognitive environment, and obtaining the cognitive load of each cognitive environment.
In embodiment 4 of the present invention, the processor may be a Central Processing Unit (CPU). The Processor may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, or a combination thereof.
The memory, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules. The processor executes various functional applications and data processing of the processor by running non-transitory software programs, instructions and modules stored in the memory, that is, the cognitive load evaluation method in the above method embodiments is implemented.
The memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor, and the like. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory located remotely from the processor, and such remote memory may be coupled to the processor via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory and, when executed by the processor, perform the cognitive load assessment method of the embodiment shown in fig. 1-2.
The details of the cognitive load evaluation system may be understood by referring to the corresponding descriptions and effects in the embodiments shown in fig. 1 to fig. 3, and are not described herein again.
The intelligent networked automobile driver cognitive load rating system provided by the embodiment 4 of the invention has the following characteristics:
(1) the intelligent networked automobile human-computer interface semi-physical simulation subsystem can truly simulate the driving scene and environment of an intelligent networked automobile, simulate the operation process of the scene of the intelligent networked automobile, and collect and record various cognitive data sets in the operation process of the scene of the driver through the intelligent networked automobile driver cognitive data collection system.
(2) The cognitive load grade of the driver can be calculated after scene operation is finished by means of the intelligent networked automobile human-computer interface semi-physical simulation subsystem, so that the change condition of the cognitive load of the driver at each scene stage is obtained.
(3) Compared with the traditional intelligent networked automobile design process, the cognitive load caused by the introduction of a new technology to the intelligent networked automobile driver can be evaluated before the design and the sizing of the intelligent networked automobile, so that the reasonability and the adaptability of the man-machine function distribution of the intelligent networked automobile driver cabin are determined, instead of improving the whole automobile design, the introduction of the new technology can be evaluated and a reasonable man-machine function distribution scheme can be selected through the method, and the vehicle design and development cost is reduced.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD) or a Solid State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (10)
1. A cognitive load evaluation method is characterized by comprising:
acquiring a cognitive data set, and determining a cognitive environment in which the cognitive data set is positioned;
respectively calculating Euclidean distances between the cognitive data set and each clustering center in the cognitive environment of a preset clustering center database;
and selecting the minimum Euclidean distance, and taking the cognitive load grade to which the clustering center corresponding to the minimum Euclidean distance belongs as the cognitive load grade of the cognitive data set.
2. The cognitive load evaluation method according to claim 1, wherein the calculating Euclidean distances between the cognitive data set and each cluster center in the cognitive environment of a preset cluster center database comprises:
calculating the Euclidean distance between the cognitive data set and any clustering center in the cognitive environment of the clustering center database by using a preset first formula;
traversing each clustering center in the cognitive environment to obtain Euclidean distances between the cognitive data set and each clustering center in the cognitive environment of the clustering center database;
wherein the first formula is
In the first formula, AnRepresenting the cognitive dataset, CknDenotes any cluster center, a11 st attribute value, a, representing the cognitive data set2A 2 nd attribute value, a, representing the cognitive data setnN-th attribute value, C, representing the cognitive data setkl1 st attribute value, C, representing the center of the clusterk22 nd attribute value, C, representing the center of the clusterknAn nth attribute value representing the cluster center.
3. The cognitive load assessment method according to claim 1, further comprising: and constructing the clustering center database according to the sample cognitive data set.
4. The cognitive load assessment method of claim 3, wherein said constructing a cluster-centric database from the sample cognitive dataset comprises:
acquiring a plurality of sample cognitive data sets of the same cognitive environment;
correcting each sample cognitive data set by using preset reference data to obtain a corrected sample cognitive data set;
clustering the plurality of corrected sample cognitive data sets according to the number of cognitive load grades to obtain a clustering center of each grade of the cognitive load;
and traversing each cognitive environment to obtain a clustering center database.
5. The cognitive load evaluation method according to claim 4, wherein the modifying each sample cognitive dataset by using the preset reference data to obtain a modified sample cognitive dataset comprises:
subtracting the reference data corresponding to the attribute value from any attribute value in the sample cognitive data set to obtain a modified attribute value;
and traversing each attribute value in the sample cognitive data set to obtain a modified sample cognitive data set.
6. The cognitive load assessment method according to claim 2 or 5, wherein the attribute values of the cognitive dataset/sample cognitive dataset comprise one or more of: the method comprises the following steps of responding time of the operation of a driver, responding time of a peripheral visual detection scene of the driver, and a correct rate and a heart rate variation rate of the driver of the peripheral visual detection scene of the driver.
7. A cognitive load evaluation device is characterized by comprising:
the acquisition module is used for acquiring a cognitive data set;
the processing module is used for determining the cognitive environment where the cognitive data set is located;
the calculation module is used for calculating Euclidean distances between the cognitive data set and each clustering center in the cognitive environment of a preset clustering center database respectively;
and the cognitive load determining module is used for selecting the minimum Euclidean distance and taking the cognitive load grade to which the cluster center corresponding to the minimum Euclidean distance belongs as the cognitive load grade of the cognitive data set.
8. A cognitive load evaluation system, comprising:
a cognitive data acquisition subsystem, a memory and a processor, wherein the cognitive data acquisition subsystem, the memory and the processor are communicatively connected with each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the cognitive load evaluation method according to any one of claims 1 to 6.
9. The cognitive load assessment system of claim 8, further comprising a human-machine interface semi-physical simulation subsystem, wherein the cognitive data acquisition subsystem is disposed within the human-machine interface semi-physical simulation subsystem.
10. A computer-readable storage medium storing computer instructions for causing a computer to perform the cognitive load assessment method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910842346.9A CN110688550A (en) | 2019-09-06 | 2019-09-06 | Cognitive load evaluation method, device and system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910842346.9A CN110688550A (en) | 2019-09-06 | 2019-09-06 | Cognitive load evaluation method, device and system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110688550A true CN110688550A (en) | 2020-01-14 |
Family
ID=69107858
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910842346.9A Pending CN110688550A (en) | 2019-09-06 | 2019-09-06 | Cognitive load evaluation method, device and system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110688550A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101690666A (en) * | 2009-10-13 | 2010-04-07 | 北京工业大学 | Driving working load calculation method of automobile driver |
| US20120174111A1 (en) * | 2010-12-30 | 2012-07-05 | Denso International America, Inc. | Method to determine driver workload function and usage of driver workload function for human-machine interface performance assessment |
| KR20140070098A (en) * | 2012-11-30 | 2014-06-10 | 한국원자력연구원 | System and method to evaluate workload |
| CN105564436A (en) * | 2016-02-24 | 2016-05-11 | 深圳市中天安驰有限责任公司 | Advanced driver assistance system |
| CN106815312A (en) * | 2016-12-21 | 2017-06-09 | 东软集团股份有限公司 | A kind of driver's evaluation method and device |
| CN109117731A (en) * | 2018-07-13 | 2019-01-01 | 华中师范大学 | A kind of classroom instruction cognitive load measuring system |
-
2019
- 2019-09-06 CN CN201910842346.9A patent/CN110688550A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101690666A (en) * | 2009-10-13 | 2010-04-07 | 北京工业大学 | Driving working load calculation method of automobile driver |
| US20120174111A1 (en) * | 2010-12-30 | 2012-07-05 | Denso International America, Inc. | Method to determine driver workload function and usage of driver workload function for human-machine interface performance assessment |
| KR20140070098A (en) * | 2012-11-30 | 2014-06-10 | 한국원자력연구원 | System and method to evaluate workload |
| CN105564436A (en) * | 2016-02-24 | 2016-05-11 | 深圳市中天安驰有限责任公司 | Advanced driver assistance system |
| CN106815312A (en) * | 2016-12-21 | 2017-06-09 | 东软集团股份有限公司 | A kind of driver's evaluation method and device |
| CN109117731A (en) * | 2018-07-13 | 2019-01-01 | 华中师范大学 | A kind of classroom instruction cognitive load measuring system |
Non-Patent Citations (1)
| Title |
|---|
| 戢晓峰 等: "ATIS环境下驾驶员认知负荷研究进展", 《安全与环境学报》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11354899B2 (en) | Visual inspection support using extended reality | |
| CN109017797B (en) | Driver emotion recognition method and vehicle-mounted control unit implementing same | |
| JP2021109653A (en) | Test method of autonomous travelling system, device, electronic equipment, program, and computer-readable recording medium | |
| CN108508881B (en) | Automatic driving control strategy adjusting method, device, equipment and storage medium | |
| CN110378483A (en) | The system and method for training machine learning model being deployed on analog platform | |
| CN111856969B (en) | Automatic driving simulation test method and device | |
| CN112693469A (en) | Method and device for testing vehicle taking over by driver, electronic equipment and medium | |
| CN107450511A (en) | Assess method, apparatus, equipment and the computer-readable storage medium of wagon control model | |
| CN114021840A (en) | Channel switching strategy generation method and device, computer storage medium and electronic equipment | |
| US11132850B1 (en) | Augmented reality diagnostic interface | |
| CN115392015A (en) | Automatic driving deduction system and deduction method based on digital twins | |
| CN110688550A (en) | Cognitive load evaluation method, device and system and storage medium | |
| CN104615008B (en) | Test result analysis method and system of AEB (Automatic Emergency Braking) system | |
| CN114782926B (en) | Driving scene recognition method, device, equipment, storage medium and program product | |
| DE102022126287A1 (en) | STORAGE AND RETRIEVAL OF UNSTRUCTURED DATA IN CONVERSATIONAL ARTIFICIAL INTELLIGENCE APPLICATIONS | |
| Zhang et al. | Driving data generation using affinity propagation, data augmentation, and convolutional neural network in communication system | |
| CN115563734A (en) | Fault-tolerant time interval calculation method and device, electronic equipment and storage medium | |
| CN115239408A (en) | Vehicle simulator | |
| CN115688254A (en) | Automatic driving risk prediction method and device, storage medium and electronic equipment | |
| US20220351614A1 (en) | Accident risk diagnosis method, accident risk diagnosis apparatus, and accident risk diagnosis system | |
| CN110782114B (en) | Driving behavior mining method and device, electronic equipment and storage medium | |
| EP3557421B1 (en) | System and method for automatic generation of a diagnostic model | |
| CN111623995A (en) | Vehicle body feeling evaluation method and device, electronic equipment and storage medium | |
| US20240221438A1 (en) | Data processing apparatus and non-transitory recording medium | |
| CN117058661B (en) | Driving behavior prediction method based on multisource information fusion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200114 |