Method, device, electronic device and storage medium for determining object participation

Abstract

The present invention relates to a method, device, electronic device and storage medium for determining object engagement, including: obtaining eye behavior information and object distribution information of each of a plurality of target objects; determining object fatigue information of each of a plurality of target objects based on the eye behavior information; inputting the object fatigue information and object distribution information of each of the plurality of target objects into an engagement prediction model, performing engagement prediction processing, and obtaining engagement corresponding to each of a plurality of distribution areas. According to the technical solution of the present invention, the object fatigue information of each of a plurality of target objects is determined through the eye behavior information of each of the plurality of target objects, and the engagement corresponding to each of a plurality of distribution areas is obtained based on the object fatigue information and object distribution information of each of the plurality of target objects, so that the lecturer can quickly understand the learning status of all students in the classroom through the engagement of each of the plurality of distribution areas.

Description

Technical Field

[0001] The present invention relates to the field of fatigue detection technology, and in particular to a method, device, electronic device and storage medium for determining object engagement. Background Art

[0002] With the rapid development and widespread application of new-generation information technology, the school teaching environment and classroom teaching models are also constantly changing. Based on dynamic learning data analysis and the use of "cloud, network, and terminal", the smart classroom that realizes data-based teaching decision-making, instant evaluation feedback, three-dimensional communication and interaction, and intelligent resource push is undoubtedly a hot topic in the current school informatization.

[0003] However, the existing technology only detects the fatigue level of a single student. In a classroom with a large number of students, the teacher cannot observe and pay attention to the fatigue level of each student while teaching, which may affect the learning progress of some students due to factors such as fatigue. Summary of the invention

[0004] The purpose of the present invention is to provide a method, device, electronic device and storage medium for determining object engagement, which determines the object fatigue information of multiple target objects through the eye behavior information of multiple target objects, and obtains the engagement corresponding to multiple distribution areas based on the object fatigue information and object distribution information of the multiple target objects, so that the lecturer can quickly understand the learning status of all students in the class through the engagement of multiple distribution areas.

[0005] To achieve the above object, the present invention provides the following solutions:

[0006] A method for determining an object's participation degree, the method comprising:

[0007] Obtaining eye behavior information and object distribution information of each of a plurality of target objects;

[0008] determining object fatigue information of each of the plurality of target objects according to the eye behavior information;

[0009] The object fatigue information of each of the multiple target objects and the object distribution information are input into a participation prediction model, and participation prediction processing is performed to obtain the participation corresponding to each of the multiple distribution areas.

[0010] Optionally, the method further includes:

[0011] Obtaining sample object distribution information, sample eye behavior information of the sample objects, and engagement labels of multiple sample regions;

[0012] Inputting the sample object distribution information and the sample eye behavior information into a preset machine learning model, performing engagement preset processing, and obtaining a predicted engagement;

[0013] Obtaining engagement loss information according to the predicted engagement and the engagement label;

[0014] The preset machine learning model is trained based on the engagement loss information to obtain the engagement prediction model.

[0015] Optionally, the eye behavior information includes at least two of blink frequency, blink intensity information, and blink duration; and determining the object fatigue information of each of the multiple target objects according to the eye behavior information includes:

[0016] Get the eye fatigue model;

[0017] The eye behavior information is input into the eye fatigue model to obtain object fatigue information of each target object.

[0018] Optionally, the eye behavior information includes blink frequency, blink intensity information, and blink duration, and the step of obtaining the eye behavior information of each of the plurality of target objects includes:

[0019] Obtaining EEG information of multiple target objects;

[0020] Determine, based on the EEG information, the number of blinks in a preset time period before a current moment, the blink intensity corresponding to each blink in the preset time period, and the blink duration;

[0021] Based on the number of blinks, obtaining the blink frequency;

[0022] Based on the blink intensity corresponding to each blink within the preset time period, average processing is performed to obtain the blink intensity information.

[0023] Optionally, after inputting the object fatigue information and the object distribution information of each of the multiple target objects into a participation prediction model to perform participation prediction processing and obtain the participation corresponding to each of the multiple distribution areas, the method further includes:

[0024] Determine a target area according to the participation degrees corresponding to the multiple distribution areas and a preset participation degree threshold, wherein the participation degree of the target area is less than or equal to the preset participation degree threshold, and the target area is at least one of the multiple distribution areas;

[0025] Sending a vibration instruction to a head mounted device of a target object corresponding to the target area to make the head mounted device vibrate;

[0026] Send push information to the electronic device of the push object corresponding to the target area.

[0027] Optionally, after determining the target area according to the participation degrees corresponding to the multiple distribution areas and the preset participation degree threshold, the method further includes:

[0028] In a case where object fatigue information of a target object corresponding to a distribution area other than the target area in the multiple distribution areas is greater than preset threshold information, the target object whose object fatigue information is greater than the preset threshold information in the distribution area other than the target area in the multiple distribution areas is regarded as a fatigue object;

[0029] A vibration instruction is sent to the head mounted device of the fatigue subject to make the head mounted device vibrate.

[0030] Optionally, obtaining object distribution information includes:

[0031] Acquire the location information of each of the plurality of target objects and the location information of each of the plurality of distribution areas;

[0032] Based on the respective position information of the plurality of target objects and the respective position information of the plurality of distribution areas, determining the target object located in each distribution area;

[0033] A mapping relationship between each distribution area and a target object within each distribution area is constructed, and the mapping relationship is used as the object distribution information.

[0034] On the other hand, the present invention also provides a device for determining the degree of participation of an object, the device comprising:

[0035] An information acquisition module, used to acquire eye behavior information and object distribution information of each of a plurality of target objects;

[0036] an information determination module, configured to determine object fatigue information of each of the plurality of target objects according to the eye behavior information;

[0037] The participation acquisition module is used to input the object fatigue information of each of the multiple target objects and the object distribution information into the participation prediction model, perform participation prediction processing, and obtain the participation corresponding to each of the multiple distribution areas.

[0038] On the other hand, the present invention also provides an electronic device, comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to execute the above-mentioned object engagement determination method.

[0039] On the other hand, the present invention further provides a non-volatile computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions implement the above-mentioned object participation determination method when executed by a processor.

[0040] The present invention provides a method, device, electronic device and storage medium for determining object engagement, which determine object fatigue information of multiple target objects through their respective eye behavior information, and obtain the engagement corresponding to multiple distribution areas based on their respective object fatigue information and object distribution information, so that the lecturer can quickly understand the learning status of all students in the classroom through the engagement of multiple distribution areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments or prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention, and those skilled in the art can obtain other drawings based on these drawings without creative work.

[0042] Figure 1 A method flow chart of a method for determining object participation provided by an embodiment of the present invention;

[0043] Figure 2 A method flow chart of a method for training a participation prediction model provided by an embodiment of the present invention;

[0044] Figure 3 A flow chart of a method for determining object fatigue information of each of the plurality of target objects according to the eye behavior information provided by an embodiment of the present invention;

[0045] Figure 4 A flow chart of a method for obtaining eye behavior information of multiple target objects provided by an embodiment of the present invention;

[0046] Figure 5 A flow chart of a method provided in an embodiment of the present invention after inputting object fatigue information of each of the plurality of target objects and the object distribution information into a participation prediction model, performing participation prediction processing, and obtaining the participation corresponding to each of the plurality of distribution areas;

[0047] Figure 6 A flow chart of a method for determining a target area according to participation levels corresponding to each of the plurality of distribution areas and a preset participation level threshold provided in an embodiment of the present invention;

[0048] Figure 7 A flow chart of a method for obtaining object distribution information provided by an embodiment of the present invention;

[0049] Figure 8 A structural block diagram of a device for determining object participation provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0051] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0052] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0053] The following describes an embodiment of the object monitoring method of the present invention. Figure 1 It is a method flow chart of a method for determining object participation provided by an embodiment of the present invention. This specification provides method operation steps as described in the embodiment or flowchart, but may include more or fewer operation steps based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the steps among many orders, and does not represent the only order of execution. When the system product is executed in practice, it can be executed in the order of the method shown in the embodiment or the accompanying drawings or in parallel (for example, in a parallel processor or multi-threaded processing environment).

[0054] like Figure 1 As shown, this embodiment provides a method for determining object participation, the method comprising:

[0055] S101. Obtain eye behavior information and object distribution information of each of a plurality of target objects.

[0056] Among them, multiple target objects may refer to objects that need to be measured for participation; specifically, they may be people. For example, in a classroom scenario, the target object may be a student; in a lecture or meeting scenario, the target object may be a participant. Eye behavior information may characterize the blinking process of the target object, and eye behavior information may refer to the collected relevant information about the blinking process of the target object. Eye behavior information may characterize the degree of blinking of the target object. Eye behavior information may include at least two of blinking frequency, blinking intensity information, and blinking duration. Object distribution information may characterize the location distribution of multiple target objects. The object distribution information may be the distribution area where each target object is located.

[0057] In practical applications, the EEG signal of each object is collected separately by an EEG acquisition device. The EEG acquisition device can be a head-mounted acquisition device. Specifically, the EEG acquisition device can acquire the EEG signal of the target object through forehead EEG sensor acquisition. The eye behavior information of each target object can be obtained by analyzing and processing the EEG signal of the target object. A location acquisition request can be sent to the head-mounted device of each target object; after receiving the location acquisition request, the head-mounted device of each target object obtains the location information through the positioning module, and sends the location information carrying the head-mounted device identifier to the object participation determination device. After receiving the location information sent by the head-mounted device of each object, the object participation determination device can obtain the object distribution information according to the location information of multiple target objects.

[0058] S102. Determine object fatigue information of each of the multiple target objects based on the eye behavior information.

[0059] The object fatigue information may represent the fatigue degree of the target object. The object fatigue information may be in the form of a numerical value or a grade. For example, the object fatigue information may include mild fatigue, moderate fatigue, and severe fatigue.

[0060] In practical applications, different interval thresholds may be set for the eye behavior information corresponding to the object fatigue information (such as fatigue level); the object fatigue information is obtained according to the interval threshold corresponding to the eye behavior information of the target object.

[0061] S103. Inputting the object fatigue information and object distribution information of the multiple target objects into the participation prediction model, performing participation prediction processing, and obtaining the participation corresponding to each of the multiple distribution areas.

[0062] Among them, the participation prediction model can be used to predict the participation of each of the multiple distribution areas. The multiple distribution areas can be multiple areas divided based on the position or number of multiple target objects in the same spatial range; in addition, the entirety of the spatial range can be taken as one of the sub-areas. It can be understood that the corresponding participation obtained by taking all target objects as a sub-area is the participation of all target objects. The participation corresponding to each distribution area can characterize the participation of multiple target objects in the distribution area. Specifically, the participation corresponding to each distribution area can be the ratio of the number of target objects in a non-fatigue state among the multiple target objects in the distribution area to the number of target objects in the distribution area, or it can also be the statistical value of the object fatigue information of multiple target objects in the distribution area; wherein the statistical value can include the mean, variance and / or standard deviation, etc. It can be understood that the higher the participation, the higher the degree of participation of the target objects in the spatial range in the main activities of the space; conversely, the lower the participation, the lower the degree of participation of the target objects in the spatial range in the main activities of the space.

[0063] The object fatigue information of the multiple target objects is determined through the eye behavior information of the multiple target objects, and the corresponding participation degrees of the multiple distribution areas are obtained based on the object fatigue information and object distribution information of the multiple target objects. This makes it convenient for the teaching teacher to quickly understand the learning status of all students in the class through the participation degrees of the multiple distribution areas.

[0064] Figure 2 A method flow chart of a method for training a participation prediction model provided by an embodiment of the present invention. In a possible implementation, Figure 2 As shown, the above method may also include:

[0065] S201. Obtain sample object distribution information, sample eye behavior information of sample objects, and engagement labels of multiple sample regions.

[0066] In practical applications, sample object distribution information, sample object eye behavior information, and engagement labels of multiple sample regions can be obtained through multiple experiments on multiple sample objects. For example, the above data can be obtained based on multiple different classroom teaching processes.

[0067] S202. Input the sample object distribution information and the sample eye behavior information into a preset machine learning model, perform preset engagement processing, and obtain the predicted engagement.

[0068] Among them, the preset machine learning model may include but is not limited to one of a neural network model, a regression model, a least squares model, a support vector machine, a Markov algorithm, etc., wherein the neural network model includes one or more of a deep neural network, a recurrent neural network, a convolutional neural network, etc. Deep learning is an algorithm for characterizing and learning a large amount of data. Deep learning is the inherent laws and representation levels of learning sample data. The information obtained in these learning processes is of great help in the interpretation of data such as text, images, and sounds. Its ultimate goal is to enable machines to have analytical learning capabilities like humans, and to be able to recognize data such as text, images, and sounds. The feature extraction of deep learning does not rely on manual work, but is automatically extracted. It has very strong learning and adaptability, is data-driven, and has a high upper limit.

[0069] S203. Obtain engagement loss information based on the predicted engagement and the engagement label.

[0070] The specific loss calculation process of the participation loss information is not limited in this disclosure.

[0071] S204. Train a preset machine learning model based on the engagement loss information to obtain an engagement prediction model.

[0072] The participation prediction model is generated through deep learning methods, avoiding complex calibration calculations and solutions.

[0073] Figure 3 A flow chart of a method for determining object fatigue information of multiple target objects according to eye behavior information provided by an embodiment of the present invention. In one possible implementation, the eye behavior information includes at least two of blink frequency, blink intensity information, and blink duration, such as Figure 3 As shown, the above step S102 may include:

[0074] S301. Obtain an eye fatigue model.

[0075] Among them, the eye fatigue model can be used to determine the object fatigue information.

[0076] In practical applications, the eye fatigue model can be obtained through machine learning. Specifically, the sample eye behavior information of multiple sample objects and the object fatigue information label of each sample object can be collected multiple times. The above multiple sample eye behavior information is input into a preset machine learning model, and fatigue information prediction processing is performed to obtain predicted object fatigue information. According to the predicted object fatigue information and the object fatigue information label, the object fatigue loss information is obtained. According to the object fatigue loss information, the preset machine learning model is trained to obtain the eye fatigue model.

[0077] S302. Input the eye behavior information into the eye fatigue model to obtain object fatigue information of each target object.

[0078] In practical applications, the eye behavior information may include at least two of blink frequency, blink intensity information, and blink duration. By inputting data in the eye behavior information of each target object into the eye fatigue model, the object fatigue information of each target object can be obtained.

[0079] Figure 4 A flow chart of a method for obtaining eye behavior information of multiple target objects provided by an embodiment of the present invention. In one possible implementation, the eye behavior information includes blink frequency, blink intensity information, and blink duration, such as Figure 4 As shown, obtaining eye behavior information of multiple target objects may include:

[0080] S401. Obtain EEG information of each of the multiple target objects.

[0081] The EEG information may represent the overall reflection of the electrophysiological activity of the target object's brain nerve cells on the cerebral cortex or scalp surface. The EEG information may include EEG signals.

[0082] In practical applications, the EEG information of a single target object can be collected through a head-mounted EEG signal acquisition device. Specifically, the forehead EEG can be collected through a single-lead differential electrode, and the bias electrode is fixed to the earlobe of each target object through a clip, and the EEG sampling frequency is 1KHz.

[0083] S402. Determine the number of blinks in a preset time period before the current moment, the blink intensity corresponding to each blink in the preset time period, and the blink duration based on the EEG information.

[0084] The preset time period may be one minute or other period of time, which is not limited in the present disclosure; in the present embodiment, the preset time period is one minute. The blink intensity may represent the relative strength of the blink. The blink duration may refer to the duration of blinking at a higher frequency.

[0085] In actual applications, with a step size of 1 second, it is determined whether the current EEG signal exceeds the preset threshold. If it exceeds, it is determined that the current state is blinking. Among them, before use, voice adaptation guidance can be used, "Please close your eyes for 10 seconds" to obtain the standard deviation a1 of the EEG signal during the user's eye closing process; "Please blink for 10 seconds" to obtain the standard deviation a2 of the EEG signal during the user's blinking process, thereby automatically setting the preset threshold to (a1+a2) / 2. The number of blinks per minute can be obtained by adding. The standard deviation of the EEG signal corresponding to each blink can be used as the blink intensity; or it can be equally divided into 3 levels from (a1+a2) / 2 to a2, and each blink can correspond to low, medium and high intensity respectively. The duration of blinking can be obtained by continuous statistics exceeding the preset threshold.

[0086] S403. Obtain a blink frequency based on the number of blinks.

[0087] In practical applications, the blinking frequency of the target object can be obtained based on the number of blinks per minute.

[0088] S404. Perform average processing based on the blink intensity corresponding to each blink within the preset time period to obtain blink intensity information.

[0089] In practical applications, the standard deviation of the EEG signal corresponding to each blink is used as the blink intensity, and the blink intensities corresponding to all blinks in a preset time period can be averaged, and the obtained average information is used as the blink intensity information.

[0090] By determining the eye behavior information of each target object through EEG information, it is not necessary to collect the image information of the target object, thus ensuring the privacy and security of the image.

[0091] Figure 5 A flowchart of a method for inputting object fatigue information and object distribution information of multiple target objects into a participation prediction model, performing participation prediction processing, and obtaining participation corresponding to multiple distribution areas is provided in an embodiment of the present invention. In one possible implementation, Figure 5 As shown, after inputting the object fatigue information and object distribution information of the multiple target objects into the participation prediction model, performing participation prediction processing, and obtaining the participation corresponding to the multiple distribution areas, the following may also be included:

[0092] S501. Determine a target area according to the participation degrees corresponding to the multiple distribution areas and a preset participation threshold, wherein the participation degree of the target area is less than or equal to the preset participation threshold, and the target area is at least one of the multiple distribution areas.

[0093] The preset participation threshold can be used to determine the target area. The preset participation threshold can be determined through multiple experiments.

[0094] In actual applications, when the participation degree corresponding to the distribution area is less than or equal to the preset participation threshold, the distribution area is the target area; when the participation degree corresponding to the distribution area is greater than the preset participation threshold, the distribution area is the non-target area.

[0095] S502: Send a vibration instruction to the head mounted device of the target object corresponding to the target area to make the head mounted device vibrate.

[0096] In practical applications, the head-mounted device of the target object may have a vibration function. After the head-mounted device receives the vibration instruction, the target object may be given feedback reminders through vibration to improve participation.

[0097] S503: Send push information to the electronic devices of the push objects corresponding to the target area.

[0098] The push object may refer to an electronic device of an associated object corresponding to the target object in the target area. For example, the associated object may be a teacher or a parent of the target object.

[0099] In actual applications, for teaching scenarios, push information can be sent to the push objects corresponding to the target areas whose participation is less than the preset participation threshold to remind parents or teachers that they need to pay attention and make adaptive adjustments. In addition, the participation change trend of each distribution area within a preset time (for example, within 40 minutes of a single class) can be obtained through the above predicted participation, and the change trend can be sent to the teacher as a reference, which helps teachers optimize the teaching process.

[0100] Figure 6 A flowchart of a method for determining a target area according to participation levels and a preset participation level threshold corresponding to a plurality of distribution areas provided in an embodiment of the present invention. In a possible implementation, Figure 6 As shown, after determining the target area according to the participation degrees corresponding to the multiple distribution areas and the preset participation degree threshold, the following may also be included:

[0101] S601. When object fatigue information of a target object corresponding to a distribution area other than a target area among multiple distribution areas is greater than preset threshold information, the target object whose object fatigue information in the distribution area other than the target area among multiple distribution areas is greater than preset threshold information is regarded as a fatigue object.

[0102] The preset threshold information can be used to determine the fatigue object. When the target object is regarded as the fatigue object, it can be represented that the target object is in a fatigue state.

[0103] S602: Send a vibration instruction to the head mounted device of the fatigued subject to make the head mounted device vibrate.

[0104] It is understandable that, when the distribution area is the target area, the participation of the distribution area can be considered to be low; when the distribution area is not the target area, the participation of the distribution area can be considered to be high, but some target objects in these distribution areas may also be in a fatigue state. By providing vibration feedback to fatigue objects in the distribution area that is not the target area, the participation of the target area can be further improved.

[0105] Figure 7 A flow chart of a method for obtaining object distribution information provided by an embodiment of the present invention. In a possible implementation, Figure 7 As shown, obtaining object distribution information may include:

[0106] S701. Obtain location information of each of a plurality of target objects and location information of each of a plurality of distribution areas.

[0107] The location information of each target object may represent the relative position of the target object in the space where all target objects are located. The location information of the distribution area may represent the specific range of the distribution area in the space where all target objects are located. The location information of the distribution area may include the location of the center of the distribution area and the length and width of the distribution area, or may also be the location information of multiple discrete points constituting the boundary of the distribution area.

[0108] In practical applications, by acquiring location information from the head-mounted device of each target object, the location information of each of the multiple target objects can be obtained. The multiple target objects can be grouped according to their distribution, and the target objects in each group are regarded as a group. Specifically, they can be divided into M distribution areas by location or by number of people, and all the objects in each distribution area can be regarded as the target objects corresponding to a group.

[0109] S702. Based on the respective position information of the plurality of target objects and the respective position information of the plurality of distribution areas, determine the target object in each distribution area.

[0110] In practical applications, the target object whose location information is in each distribution area can be used as the target object in the distribution area, thereby obtaining the target object in each distribution area. Specifically, each distribution area may include multiple target objects.

[0111] S703: Construct a mapping relationship between each distribution area and the target object in each distribution area, and use the mapping relationship as object distribution information.

[0112] Specifically, according to the multiple target objects corresponding to each distribution area, a mapping relationship between each distribution area and its corresponding multiple target objects may be established.

[0113] In practical applications, the object fatigue information of the target object in each distribution area is x i , then the distribution word bag matrix of object fatigue information in a random distribution area (containing K objects) is [x1,x2,x3,……,x k ] If the number of objects in a single distribution area is less than K (i.e., there are gaps) when dividing by distribution area, the gaps can be filled by taking the average, maximum, or minimum value of the fatigue of the objects in the area to ensure that the number of target objects in each distribution area is the same, thereby improving the accuracy of participation prediction.

[0114] Figure 8 FIG. 1 is a structural block diagram of a device for determining the degree of participation of an object provided by an embodiment of the present invention. On the other hand, this embodiment also provides a device for determining the degree of participation of an object, such as Figure 8 As shown, the device comprises:

[0115] An information acquisition module 10 is used to acquire eye behavior information and object distribution information of each of a plurality of target objects;

[0116] An information determination module 20, configured to determine object fatigue information of each of the plurality of target objects according to the eye behavior information;

[0117] The participation acquisition module 30 is used to input the object fatigue information and object distribution information of each of the multiple target objects into the participation prediction model, perform participation prediction processing, and obtain the participation corresponding to each of the multiple distribution areas.

[0118] On the other hand, an embodiment of the present invention further provides an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the above-mentioned object engagement determination method.

[0119] On the other hand, an embodiment of the present invention further provides a non-volatile computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions implement the above-mentioned object participation determination method when executed by a processor.

[0120] It should be noted that, for the sake of simplicity of description, the aforementioned method embodiments are all expressed as two series of action combinations, but those skilled in the art should be aware that the present invention is not limited by the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously. Similarly, the modules of the above-mentioned object engagement determination device refer to computer programs or program segments for performing one or more specific functions. In addition, the distinction between the above-mentioned modules does not mean that the actual program code must also be separated. In addition, the above-mentioned embodiments can be arbitrarily combined to obtain other embodiments.

[0121] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in certain embodiments, please refer to the relevant description of other embodiments. Those skilled in the art may also understand that the various illustrative logical blocks, units, and steps listed in the embodiments of the present invention may be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly demonstrate the interchangeability of hardware and software, the various illustrative components, units, and steps mentioned above have generally described their functions. Whether such functions are implemented by hardware or software depends on the specific application and the design requirements of the entire system. Those skilled in the art may use various methods to implement the described functions for each specific application, but such implementation should not be understood as exceeding the scope of protection of the embodiments of the present invention.

[0122] The above description has fully disclosed the specific embodiments of the present invention. It should be pointed out that any changes made by those skilled in the art to the specific embodiments of the present invention do not deviate from the scope of the claims of the present invention. Accordingly, the scope of the claims of the present invention is not limited to the above specific embodiments.

Claims

1. A method for determining object participation, characterized in that: The method comprises: Obtaining eye behavior information and object distribution information of each of a plurality of target objects; the eye behavior information includes at least two of blink frequency, blink intensity information, and blink duration; obtaining the object distribution information, including: obtaining position information of each of the plurality of target objects and position information of each of a plurality of distribution areas; determining a target object in each distribution area based on the position information of each of the plurality of target objects and the position information of each of the plurality of distribution areas; constructing a mapping relationship between each distribution area and the target object in each distribution area, and using the mapping relationship as the object distribution information; Determining object fatigue information of each of the plurality of target objects according to the eye behavior information; Determining object fatigue information of each of the plurality of target objects according to the eye behavior information comprises: acquiring an eye fatigue model; inputting the eye behavior information into the eye fatigue model to obtain object fatigue information of each target object; Inputting the object fatigue information of each of the multiple target objects and the object distribution information into a participation prediction model, performing participation prediction processing, and obtaining participation corresponding to each of the multiple distribution areas; The method further comprises: Obtain sample object distribution information, sample eye behavior information of sample objects, and engagement labels of multiple sample areas; input the sample object distribution information and the sample eye behavior information into a preset machine learning model, perform preset engagement processing, and obtain predicted engagement; obtain engagement loss information based on the predicted engagement and the engagement label; train the preset machine learning model based on the engagement loss information to obtain the engagement prediction model.

2. The method according to claim 1, characterized in that: The eye behavior information includes blink frequency, blink intensity information and blink duration. Obtaining the eye behavior information of each of the multiple target objects includes: Obtaining EEG information of multiple target objects; Determine, based on the EEG information, the number of blinks in a preset time period before a current moment, the blink intensity corresponding to each blink in the preset time period, and the blink duration; Based on the number of blinks, obtaining the blink frequency; Based on the blink intensity corresponding to each blink within the preset time period, average processing is performed to obtain the blink intensity information.

3. The method according to claim 1, characterized in that After inputting the object fatigue information and the object distribution information of each of the plurality of target objects into a participation prediction model to perform participation prediction processing to obtain the participation corresponding to each of the plurality of distribution areas, the method further includes: Determine a target area according to the participation degrees corresponding to the multiple distribution areas and a preset participation degree threshold, the participation degree of the target area is less than or equal to the preset participation degree threshold, and the target area is at least one of the multiple distribution areas; Sending a vibration instruction to a head mounted device of a target object corresponding to the target area to make the head mounted device vibrate; Send push information to the electronic device of the push object corresponding to the target area.

4. The method according to claim 3, characterized in that: After determining the target area according to the participation degrees corresponding to the plurality of distribution areas and the preset participation degree threshold, the method further includes: In a case where object fatigue information of a target object corresponding to a distribution area other than the target area in the multiple distribution areas is greater than preset threshold information, the target object whose object fatigue information is greater than the preset threshold information in the distribution area other than the target area in the multiple distribution areas is regarded as a fatigue object; A vibration instruction is sent to the head mounted device of the fatigue subject to make the head mounted device vibrate.

5. A device for determining object participation, characterized in that: The device comprises: An information acquisition module, used to acquire eye behavior information and object distribution information of each of a plurality of target objects; the eye behavior information includes at least two of blink frequency, blink intensity information and blink duration; acquiring the object distribution information, including: acquiring position information of each of the plurality of target objects and position information of each of a plurality of distribution areas; determining a target object in each distribution area based on the position information of each of the plurality of target objects and the position information of each of the plurality of distribution areas; constructing a mapping relationship between each of the distribution areas and the target objects in each of the distribution areas, and using the mapping relationship as the object distribution information; An information determination module is used to determine the object fatigue information of each of the multiple target objects according to the eye behavior information; the determining the object fatigue information of each of the multiple target objects according to the eye behavior information includes: obtaining an eye fatigue model; inputting the eye behavior information into the eye fatigue model to obtain the object fatigue information of each target object; An engagement acquisition module is used to input the object fatigue information of each of the multiple target objects and the object distribution information into an engagement prediction model, perform engagement prediction processing, and obtain the engagement corresponding to each of the multiple distribution areas; the engagement prediction model is obtained by training a preset machine learning model based on engagement loss information, the engagement loss information is obtained based on the predicted engagement and engagement labels of multiple sample areas, and the predicted engagement is obtained by inputting sample object distribution information and sample eye behavior information of the sample object into the preset machine learning model for engagement preset processing.

6. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to execute the executable instructions to implement the object engagement determination method described in any one of claims 1 to 4.

7. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the object engagement determination method described in any one of claims 1 to 4 is implemented.

Images