Multi-party real-time interactive reading system and multi-party real-time interactive reading control method

Abstract

The application is suitable for the field of electronic display technology, and provides a multi-party real-time interactive reading system and a multi-party real-time interactive reading control method. The multi-party real-time interactive reading system comprises a relaxation collection terminal, a teacher terminal interactive device, a parent terminal interactive device and a cloud relaxation coupling scheduling engine. The relaxation collection terminal collects the original physical parameters of electrophoretic particles of a water ink screen through a particle sensing collection hardware group. A local operation hardware group generates a standardized multi-dimensional relaxation vector and an intrinsic weight of a data packet according to the original physical parameters. A slicing modulation hardware transmits the data packet according to the weight. The cloud relaxation coupling scheduling engine receives the original relaxation data packet, identifies the user cognitive state according to the standardized multi-dimensional relaxation vector, completes the hierarchical storage of the time sequence relaxation data, generates hierarchical heuristic question data, learning situation visualization graph data and parent-child reading task data. The user reading behavior is converted into the quantitative representation of the micro-physical quantity of the electrophoretic particles, which provides a unified physical quantitative basis for the cognitive state judgment, learning situation analysis and multi-terminal data association, thereby improving the collaborative efficiency in the multi-party interactive reading scene.

Description

Technical Field

[0001] This application belongs to the field of electronic display technology, and in particular relates to a multi-party real-time interactive reading system and a multi-party real-time interactive reading control method. Background Technology

[0002] Currently, online multi-party interactive reading systems generally rely on software programs running on terminal devices and general artificial intelligence algorithms deployed in the cloud. These systems primarily collect data on users' macro-level behaviors at the software level, such as page-turning speed, reading time, comment content, and click behavior. Based on this macro-level data, the system drives interaction and assesses learning progress through algorithms. However, the aforementioned technical methods suffer from problems such as inaccurate assessment of user cognitive states, low interaction quality, poor AI guidance effects, and a limited range of dimensions for learning progress analysis. Furthermore, behavioral data from parents' and teachers' ends and reading data from students' ends belong to different data domains, making it difficult to establish a quantifiable correlation between the two domains. Summary of the Invention

[0003] This application provides a multi-party real-time interactive reading system and a multi-party real-time interactive reading control method, aiming to solve the technical problems in the prior art such as inaccurate judgment of user cognitive state, low interaction quality, poor AI guidance effect, and single dimension of learning analysis.

[0004] In a first aspect, embodiments of this application provide a multi-party real-time interactive reading system, comprising: a plurality of relaxation acquisition terminals, a teacher-side interactive device, a parent-side interactive device, and a cloud-based relaxation coupling scheduling engine; the cloud-based relaxation coupling scheduling engine establishes bidirectional hardware communication links with all the relaxation acquisition terminals, the teacher-side interactive devices, and the parent-side interactive devices via a communication bus; each relaxation acquisition terminal includes a particle sensing acquisition hardware group, a local computing hardware group, a slice modulation hardware, a local timing cache hardware, an e-ink screen display driver hardware, and a terminal power management hardware; the output of the particle sensing acquisition hardware group is connected to the input of the local computing hardware group, the output of the local computing hardware group is connected to the input of the slice modulation hardware, the output of the slice modulation hardware is connected to the input of the local timing cache hardware and the input of the cloud-based relaxation coupling scheduling engine; the input of the e-ink screen display driver hardware is connected to the output of the cloud-based relaxation coupling scheduling engine; the output of the terminal power management hardware is connected to the power input of all hardware modules within the relaxation acquisition terminal. The particle sensing and acquisition hardware group is used to collect the original physical parameters of electrophoretic particles in the pixel area of ​​the e-ink screen and the user's handwritten interaction data, and transmit them to the local computing hardware group. The local computing hardware group is used to generate a standardized multidimensional relaxation vector based on the original physical parameters, generate data packet intrinsic weights based on the standardized multidimensional relaxation vector, and output native relaxation data packets to the slice modulation hardware. The slice modulation hardware is used to allocate hardware transmission channels according to the intrinsic weight of the data packets and store low-weight data packets in the local timing buffer hardware. The cloud-based relaxation coupling scheduling engine is used to receive the native relaxation data packets, identify the user's cognitive state based on the standardized multidimensional relaxation vector, complete the hierarchical storage of time-series data, and generate hierarchical heuristic questioning data, learning progress visualization map data, and parent-child co-reading task data. The teacher-side interactive device is used to issue shared reading configuration commands, display a visual learning progress graph, and push teaching guidance data to the corresponding relaxation collection terminal based on the learning progress points. The parent-side interactive device is used to collect particle physics parameters corresponding to parent interaction behaviors, generate parent interaction relaxation vectors and upload them to the cloud relaxation coupling scheduling engine, and receive parent-child co-reading task data issued by the cloud relaxation coupling scheduling engine. The e-ink screen display driver hardware is used to receive data signals sent by the cloud-based relaxation coupling scheduling engine and drive the e-ink screen to complete multi-character screen rendering.

[0005] Secondly, embodiments of this application provide a multi-party real-time interactive reading control method, including the following steps: Step 1: The teacher-side interactive device sends out a shared reading configuration command, and the cloud-based relaxation coupling scheduling engine creates a shared reading space and completes the initialization of relaxation baseline parameters; Step 2: The particle sensing and acquisition hardware group collects the original physical parameters of the electrophoretic particles and the handwritten interactive data. The local computing hardware group generates standardized multidimensional relaxation vectors and data packet intrinsic weights based on the original physical parameters. Step 3: The slice modulation hardware allocates transmission channels according to the intrinsic weight of the data packets, transmits high-weight data packets and medium-weight data packets to the cloud relaxation coupling scheduling engine, and caches low-weight data packets in the local time-series cache hardware and uploads them in batches when the relaxation acquisition terminal enters a low-power state; the low-power state refers to the low-energy operation mode when the relaxation acquisition terminal is in an inactive interactive state. Step four: The cloud-based relaxation coupling scheduling engine receives the native relaxation data packet, identifies the user's cognitive state through the cognitive discrimination model, and writes the time-series relaxation data into the hierarchical time-series memory hardware storage area in layers. Step 5: The layered AI-guided hardware unit retrieves the time-series data stored in the three hardware partitions, generates three-level layered heuristic query data, and sends it to the e-ink screen display driver hardware to complete the screen rendering. Step 6: The parent-side interactive device uploads the parent interaction relaxation vector, and the home-school coupling calculation hardware unit generates the home-school relaxation coupling degree. When the home-school relaxation coupling degree is lower than the judgment benchmark, a parent-child co-reading task matching the physical location of cognitive impairment is generated and pushed to the parent-side interactive device. Step 7: The teacher's interactive device aggregates the relaxation vector data of the whole class to generate a heat map, and distributes teaching guidance data according to the relaxation physical location corresponding to the heat peak. Step 8: Repeat steps 2 to 7. After a single reading session is completed, the cloud-based relaxation coupling scheduling engine archives the chapter time-series data to the full-cycle relaxation-associated memory hardware partition.

[0006] In this embodiment, the particle sensing hardware group collects the original physical parameters of electrophoretic particles in the pixel area of ​​the e-ink screen, and the local computing hardware group generates standardized multidimensional relaxation vectors based on these original physical parameters. This transforms macroscopic behaviors such as page-turning time and dwell time during the user's reading process into quantitative representations of microscopic physical quantities such as electrophoretic particle flipping time, afterimage relaxation decay value, and cumulative number of pixel area disturbances, providing a physical dimension input with definite values ​​for the analysis of reading behavior. The cloud-based relaxation coupling scheduling engine identifies the user's cognitive state based on these standardized multidimensional relaxation vectors, transforming the determination of the user's cognitive state in the system from an estimate based on indirect behavioral data to a quantitative value based on measured physical parameters. By completing the hierarchical storage of temporal relaxation data, the relaxation vectors at each moment during the reading process maintain a sequential relationship in time, and the relaxation vectors at each pixel position maintain a coordinate correspondence in space, thus preserving the temporal path of cognitive state changes and text position information in the storage structure of the reading data. By generating hierarchical heuristic question data based on hierarchically stored temporal relaxation data, AI guidance is correlated with cognitive blocks encountered by users at specific text locations. Comparative reflection question data and cross-time period tracing question data are generated based on chapter temporal differences and cross-task historical cognitive records, enhancing the progressiveness and continuity of AI guidance. By generating parent-child co-reading task data and making targeted pushes based on the degree of relaxation coupling between home and school, parents' interactive behaviors and students' cognitive states are matched within the same quantitative space. By generating learning progress visualization map data, the data obtained by teachers and parents is correlated with the relaxation vectors generated by students at specific text locations within the same quantitative space. Attached Figure Description

[0007] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0008] Figure 1 This is a schematic diagram of the overall architecture of a multi-party real-time interactive reading system according to an embodiment of this application; Figure 2 This is a block diagram of the internal structure of the relaxation acquisition terminal according to an embodiment of this application; Figure 3 This is a block diagram of the internal structure of the cloud-based relaxation coupling scheduling engine according to an embodiment of this application. Detailed Implementation

[0009] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0010] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0011] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0012] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0013] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0014] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0015] Please see Figures 1 to 3 This application provides a multi-party real-time interactive reading system and its control method. The particle sensing hardware within the relaxation acquisition terminal collects the original physical parameters of electrophoretic particles generated in the pixel area of ​​the e-ink screen due to user interaction. The local computing hardware generates a standardized multi-dimensional relaxation vector based on these original physical parameters using a normalization formula. The slicing modulation hardware performs hierarchical transmission scheduling of data packets based on the intrinsic weight of the data packets calculated from this vector. The cloud-based relaxation coupling scheduling engine receives the original relaxed data packets, identifies the user's cognitive state based on the vector, and completes the hierarchical storage of time-series data and the generation of multi-party interactive data.

[0016] This application provides a multi-party real-time interactive reading system, comprising: several relaxation acquisition terminals, teacher-side interactive devices, parent-side interactive devices, and a cloud-based relaxation coupling scheduling engine; the cloud-based relaxation coupling scheduling engine establishes bidirectional hardware communication links with all the relaxation acquisition terminals, teacher-side interactive devices, and parent-side interactive devices via a communication bus; each relaxation acquisition terminal includes a particle sensing acquisition hardware group, a local computing hardware group, a slice modulation hardware, a local timing cache hardware, an e-ink screen display driver hardware, and a terminal power management hardware; the output of the particle sensing acquisition hardware group is connected to the input of the local computing hardware group, the output of the local computing hardware group is connected to the input of the slice modulation hardware, the output of the slice modulation hardware is connected to the input of the local timing cache hardware and the input of the cloud-based relaxation coupling scheduling engine; the input of the e-ink screen display driver hardware is connected to the output of the cloud-based relaxation coupling scheduling engine; the output of the terminal power management hardware is connected to the power input of all hardware modules within the relaxation acquisition terminal. The particle sensing and acquisition hardware group is used to collect the original physical parameters of electrophoretic particles in the pixel area of ​​the e-ink screen and the user's handwritten interaction data, and transmit them to the local computing hardware group. The local computing hardware group is used to generate a standardized multidimensional relaxation vector based on the original physical parameters, generate data packet intrinsic weights based on the standardized multidimensional relaxation vector, and output native relaxation data packets to the slice modulation hardware. The slice modulation hardware is used to allocate hardware transmission channels according to the intrinsic weight of the data packets and store low-weight data packets in the local timing buffer hardware. The cloud-based relaxation coupling scheduling engine is used to receive the native relaxation data packets, identify the user's cognitive state based on the standardized multidimensional relaxation vector, complete the hierarchical storage of time-series data, and generate hierarchical heuristic questioning data, learning progress visualization map data, and parent-child co-reading task data. The teacher-side interactive device is used to issue shared reading configuration instructions, display a learning progress visualization map, and push teaching guidance data to the corresponding relaxation acquisition terminal based on the learning progress points; that is, the teacher-side interactive device is used to issue shared reading configuration instructions, generate and display a learning progress visualization map based on the learning progress visualization map data, and push teaching guidance data to the corresponding relaxation acquisition terminal based on the learning progress points. The parent-side interactive device is used to collect particle physics parameters corresponding to parent interaction behaviors, generate parent interaction relaxation vectors and upload them to the cloud relaxation coupling scheduling engine, and receive parent-child co-reading task data issued by the cloud relaxation coupling scheduling engine. The e-ink screen display driver hardware is used to receive data signals sent by the cloud-based relaxation coupling scheduling engine and drive the e-ink screen to complete multi-character screen rendering.

[0017] Among them, the relaxation acquisition terminal refers to a dedicated hardware device that uses an e-ink screen as a carrier. Its function is to collect the physical relaxation characteristics of electrophoretic particles on the e-ink screen during user interaction and perform localized preliminary calculations and data processing.

[0018] Among them, the cloud-based relaxation coupling scheduling engine refers to the core computing and scheduling hub deployed on the cloud server. It consists of a series of functionally specific hardware units, which are responsible for receiving and processing data from various terminals, executing core logic such as cognitive state determination, time-series data storage, AI guidance generation, and home-school behavior coupling calculation, and issuing instructions and data to various interactive devices.

[0019] Among them, the standardized multidimensional relaxation vector (hereinafter referred to as vector) refers to the process of converting the original physical parameters of electrophoretic particles with multiple dimensions and different dimensions (hereinafter referred to as original physical parameters) into a standardized data representation with uniform dimensions and a numerical range in the [0,1] interval through a fixed normalization mathematical formula.

[0020] Among them, the intrinsic weight of the data packet (hereinafter referred to as weight) is a quantitative indicator that represents the cognitive value of the information contained in the data packet, calculated by a fixed weighted fusion formula based on the standardized multidimensional relaxation vector.

[0021] Among them, the learning situation visualization map refers to the set of visual data generated by the cloud relaxation coupling scheduling engine based on the hierarchically stored time-series relaxation data, which is used to characterize the distribution of cognitive status of students in a class or individual.

[0022] In this context, "learning situation points" refer to the physical locations in the learning situation visualization map that represent collective cognitive blockages, specifically the relaxation physical locations corresponding to thermal peak points. Relaxation physical locations refer to the pixel coordinates on the e-ink screen corresponding to the original physical parameters of electrophoretic particles or the standardized multidimensional relaxation vectors, used to spatially associate user interaction behavior with specific text content on the screen. Pixel locations and relaxation physical locations have the same meaning in this application and can be used interchangeably.

[0023] In this embodiment, the particle sensing hardware group inside the relaxation acquisition terminal measures the electrophoretic particle flipping time, afterimage relaxation decay sampling data, and the cumulative number of particle disturbances in the pixel area of ​​the e-ink screen, and outputs these raw physical parameters to the local computing hardware group. The local computing hardware group converts these raw physical parameters into a standardized multidimensional relaxation vector through a normalization operation circuit and a weight operation circuit, and calculates the intrinsic weight of the data packet. The native relaxation data packet containing the vector and weight is transmitted to the slice modulation hardware. According to the weight value, the slice modulation hardware uploads the data packet to the cloud relaxation coupling scheduling engine through the communication bus, or temporarily stores the low-weight data packet in the local timing cache hardware. That is, according to the weight value, the slice modulation hardware transmits high-weight and medium-weight data packets to the cloud relaxation coupling scheduling engine through the communication bus, and temporarily stores low-weight data packets in the local timing cache hardware. After receiving the data packet, the cloud relaxation coupling scheduling engine identifies the cognitive state based on the vector, and sends the processing result to the teacher's interactive device, the parent's interactive device, or renders it on the relaxation acquisition terminal through the e-ink screen display driver hardware. By transforming user reading behavior into a quantitative representation of the microscopic physical quantities of electrophoretic particles, a physical dimension input with definite values ​​is provided for the analysis of reading behavior, which helps to improve the objectivity of cognitive state determination.

[0024] In one optional embodiment, the cloud-based relaxation coupling scheduling engine includes a cognitive discrimination model, a hierarchical temporal memory hardware storage area, a home-school coupling computing hardware unit, and a hierarchical AI guidance hardware unit. The cognitive discriminant model is used to identify the user's cognitive state based on the standardized multidimensional relaxation vector; The hierarchical time-series memory hardware storage area is used to complete the hierarchical storage of time-series data; The home-school coupling computation hardware unit is used to generate the home-school relaxation coupling degree based on the parent interaction relaxation vector and the student's synchronous relaxation vector. The hierarchical AI guidance hardware unit is used to generate hierarchical heuristic question data based on hierarchical time-series data.

[0025] The cognitive discrimination model refers to a set of computation links and maximum value selection circuits contained within the cloud-based relaxation coupling scheduling engine, which are used to map the input standardized multidimensional relaxation vector into discrete cognitive state labels.

[0026] Among them, the hierarchical time-series memory hardware storage area refers to the storage hardware that is physically divided into multiple independent partitions inside the cloud relaxation coupling scheduling engine, which is used to classify and store time-series relaxation data according to different time scales.

[0027] Among them, the home-school coupling computing hardware unit refers to the distance calculation circuit and difference calculation circuit contained in the cloud-based relaxation coupling scheduling engine, which is used to calculate the degree of quantitative matching between parent interaction behavior and student's cognitive state at the same time.

[0028] Among them, the hierarchical AI guidance hardware unit refers to the hardware unit inside the cloud-based relaxation coupling scheduling engine that retrieves time-series data from different partitions of the hierarchical time-series memory hardware storage area and generates different levels of heuristic question data according to preset rules.

[0029] In this embodiment, the cognitive discriminant model receives standardized multidimensional relaxation vectors from the relaxation acquisition terminal and outputs one of three cognitive labels: deep thinking, cognitive blockage, or shallow browsing. Time-series data with these cognitive labels are written to different partitions of the hierarchical time-series memory hardware storage area. The home-school coupling computing hardware unit receives parent interaction relaxation vectors from the parent's interactive device and retrieves the corresponding student's concurrent relaxation vectors from the hierarchical time-series memory hardware storage area, calculating the coupling degree between the two. The hierarchical AI guidance hardware unit generates hierarchical heuristic question data based on the hierarchically stored time-series data. Through the hierarchical storage and hierarchical guidance mechanism of the time-series relaxation data, AI questions are associated with the user's historical cognitive records, which helps improve the continuity of AI guidance.

[0030] In one optional embodiment, the particle sensing and acquisition hardware group includes an electrophoretic particle relaxation photoelectric acquisition array and a pressure-sensitive and pixel relaxation bound sensing unit. The electrophoretic particle relaxation photoelectric acquisition array acquires three types of raw physical parameters according to a fixed acquisition period: electrophoretic particle flipping time, afterimage relaxation attenuation sampling data, and cumulative number of particle disturbances in the pixel area. The pressure-sensitive and pixel relaxation binding sensing unit collects handwriting pressure gradient, writing pause duration, and handwriting stroke pixel coordinate data, binds the handwriting data with the original physical parameters at the same pixel position, and transmits it to the local computing hardware group.

[0031] Among them, the electrophoretic particle relaxation photoelectric acquisition array refers to the array hardware consisting of multiple photoelectric sensing units covering the bottom of the e-ink screen, which is used to optically sample the state of electrophoretic particles in the pixel area according to a fixed time period.

[0032] Among them, the pressure-sensitive and pixel relaxation-bound sensing unit refers to the pressure sensing array covering the e-ink screen, which is used to collect pressure data and coordinate data generated by handwriting interaction, and associate and bind these data with the original physical parameters of electrophoretic particles at the same pixel position at the hardware level.

[0033] In this embodiment, the electrophoretic particle relaxation photoelectric acquisition array outputs three types of parameters at a fixed acquisition period: electrophoretic particle flipping time, afterimage relaxation attenuation sampling data, and cumulative number of particle perturbations in the pixel region. A pressure-sensitive and pixel relaxation-bound sensing unit synchronously acquires the pressure gradient, pause duration, and pen placement coordinates during user handwriting. This sensing unit binds the handwriting data with the photoelectric acquisition data at the same pixel location and transmits them uniformly to the local computing hardware group. By binding handwriting behavior data with particle physical parameters at the same pixel location, the dimensional integrity and correlation accuracy of user interaction data are improved.

[0034] In one optional embodiment, the local computing hardware group includes a normalization operation circuit and a weighting operation circuit; The output of the normalization operation circuit is connected to the input of the weight operation circuit, and the output of the weight operation circuit is connected to the input of the slice modulation hardware. The normalization operation circuit is used to perform normalization operations on the original physical parameters to generate the standardized multidimensional relaxation vector; The weighting circuit is used to perform weighted fusion on each component of the standardized multidimensional relaxation vector to generate the intrinsic weight of the data packet.

[0035] Among them, the normalization operation circuit refers to the dedicated circuit in the local computing hardware group used to perform dimensionless mathematical operations. Its input is multi-dimensional original physical parameters, and its output is a vector with unified dimensions and standardized numerical range.

[0036] The weighting operation circuit refers to a dedicated circuit within the local computing hardware group used to perform weighted summation operations. Its input is each component of the standardized multidimensional relaxation vector, and its output is the intrinsic weight value of the data packet.

[0037] In this embodiment, the normalization circuit receives the raw physical parameters transmitted by the particle sensing and acquisition hardware group and performs calculations according to the following formula:

[0038]

[0039]

[0040] in, This is the normalized particle flipping time component, with a range of [0, 1], dimensionless, and varying with... It increases with the increase of; The normalized afterimage relaxation decay component has a range of [0, 1], is dimensionless, and varies with... It increases with the increase of; This is the normalized cumulative number of particle perturbations component, with a range of [0, 1], dimensionless, and varying with... It increases as it increases. The time taken for a single particle flip, as collected by the particle sensing hardware group, is measured in nanoseconds. The image retention relaxation attenuation sampling data is the average value calculated after sampling the image intensity of the same pixel position multiple times within a preset time window. The unit is a dimensionless relative light intensity unit. This represents the cumulative number of particle disturbances in a pixel area collected by the particle sensing hardware group within a statistical period, expressed in times. This is the theoretical minimum particle flipping time calibrated at the time of equipment leaving the factory, in nanoseconds. This is the theoretical maximum particle flipping time calibrated at the time of equipment leaving the factory, in nanoseconds. This is the theoretical minimum value of the afterimage relaxation attenuation value calibrated at the factory, expressed in dimensionless units of relative light intensity. This is the theoretical maximum value of the afterimage relaxation attenuation value calibrated at the factory, expressed in dimensionless units of relative light intensity. This is the theoretical minimum number of cumulative particle disturbances calibrated at the time of equipment leaving the factory, expressed in times. The above six constants are the theoretical maximum number of cumulative particle disturbances calibrated at the time of device delivery, in units of times; all of them are preset values ​​fixed in the hardware.

[0041] The weighting circuit receives the vector and performs a weighted summation according to the following formula:

[0042] in, The calculated intrinsic weights of the data packets have a range of [0, 1], are dimensionless, and vary with... , , It increases as it increases. This is the weighting coefficient for the time consumed during the flipping process. Its value range is [0, 1], it is dimensionless, and it represents... The contribution ratio of a component to the calculation of the intrinsic weight of a data packet; The image retention attenuation weighting coefficient has a range of [0, 1], is dimensionless, and represents... The contribution ratio of a component to the calculation of the intrinsic weight of a data packet; The cumulative weighting coefficient for perturbation has a range of [0, 1], is dimensionless, and represents... The contribution ratio of a component to the calculation of the intrinsic weight of a data packet; , , All are preset values ​​fixed at the factory and meet the requirements. The weighting circuit outputs the native relaxed data packet containing the vector and weights to the slice modulation hardware. By performing the conversion from raw physical parameters to standardized vectors on the terminal side, the data preprocessing burden in the cloud is reduced, which helps to improve the overall computing efficiency of the system.

[0043] In one optional embodiment, the communication bus includes a cognitive data sub-bus, an asynchronous cache sub-bus, and a home-school interaction sub-bus; The slicing modulation hardware includes a comparison circuit, which divides the data packets into high-weight data packets, medium-weight data packets, and low-weight data packets according to their intrinsic weights. The high-weight and medium-weight data packets are allocated to the cognitive data sub-bus, and the low-weight data packets are stored in the local timing cache hardware. When the relaxation acquisition terminal enters a low-power state, the low-weight data packets stored in the local timing cache hardware are transmitted to the cloud relaxation coupling scheduling engine through the asynchronous cache sub-bus.

[0044] The cognitive data subbus refers to the high-speed transmission channel in the communication bus used to carry high-weight and medium-weight data packets.

[0045] Among them, the asynchronous buffer sub-bus refers to the low-speed transmission channel in the communication bus used for batch transmission of low-weight data packets when the terminal is inactive.

[0046] Among them, the home-school interaction sub-bus refers to the transmission channel in the communication bus that is dedicated to carrying data interaction between the parent's interactive device and the cloud-based relaxed coupling scheduling engine.

[0047] Among them, the comparison circuit refers to the hardware circuit inside the slice modulation hardware used to compare the intrinsic weight of the data packet with a preset threshold, and to classify and route the data packet according to the comparison result.

[0048] High-weight data packets refer to natively relaxed data packets with an intrinsic weight greater than or equal to 0.7, and their corresponding user interaction behaviors have high cognitive value. Medium-weight data packets refer to natively relaxed data packets with an intrinsic weight greater than or equal to 0.3 and less than 0.7, and their corresponding user interaction behaviors have moderate cognitive value. Low-weight data packets refer to natively relaxed data packets with an intrinsic weight less than 0.3, and their corresponding user interaction behaviors have low cognitive value.

[0049] In this embodiment of the application, the comparison circuit inside the slice modulation hardware assigns intrinsic weights to the data packets. Compare with a preset threshold. When When the value is ≥0.7, the data packet is classified as a high-weight data packet; when 0.3≤ When the weight is less than 0.7, it is classified as a medium-weighted data packet; when... When the weight is less than 0.3, the data is classified as a low-weight data packet. High-weight and medium-weight data packets are transmitted to the cloud relaxation coupling scheduling engine via the cognitive data subbus. Low-weight data packets are stored in local time-series buffer hardware and transmitted to the cloud via the asynchronous buffer subbus when the relaxation acquisition terminal enters a low-power state. By using hierarchical transmission scheduling based on the intrinsic weight of data packets, data with high cognitive value is given priority access to network resources, which helps reduce the transmission latency of core interactive data and improve the utilization efficiency of network bandwidth.

[0050] In one optional embodiment, the cloud-based relaxation coupling scheduling engine includes a cognitive discrimination model, which includes three sets of computation links and a maximum value selection circuit; The output terminals of the three sets of computation links are respectively connected to the three input terminals of the maximum value selection circuit; Each computational link outputs a judgment value based on the standardized multidimensional relaxation vector components and fixed constants; The three sets of computing links output judgment values ​​in parallel to the maximum value selection circuit. The maximum value selection circuit outputs the cognitive tag corresponding to the maximum judgment value. The cognitive tag is deep thinking, cognitive blockage, and shallow browsing.

[0051] Among them, the computation link refers to the hardware circuit inside the cognitive discriminant model used to execute a fixed linear discriminant function, and each link corresponds to a cognitive state.

[0052] Among them, the maximum value selection circuit refers to the hardware comparison circuit inside the cognitive discrimination model used to compare the magnitude of the judgment values ​​output by the three sets of operation links and output the cognitive label corresponding to the maximum value.

[0053] Among them, three sets of computing links receive the normalized multidimensional relaxation vector in parallel. The first set of computational links outputs the depth-of-thought judgment value based on the following formula:

[0054] in, The value used to determine deep thinking is a real number; the larger the value, the higher the probability that the input vector corresponds to a state of deep thinking. For deep thinking discriminant functions The weighting coefficients of the components are real numbers; For deep thinking discriminant functions The weighting coefficients of the components are real numbers; For deep thinking discriminant functions The weighting coefficients of the components are real numbers; The bias constant for the discrimination function is a real number.

[0055] The second set of computational links outputs the cognitive impairment assessment value based on the following formula:

[0056] in, The value for determining cognitive impairment is a real number. The larger the value, the higher the probability that the input vector corresponds to a state of cognitive impairment. In the cognitive impairment discriminant function The weighting coefficients of the components are real numbers; In the cognitive impairment discriminant function The weighting coefficients of the components are real numbers; In the cognitive impairment discriminant function The weighting coefficients of the components are real numbers; Let be the bias constant of the cognitive impairment discrimination function, and be a real number.

[0057] The third set of computation links outputs the shallow browsing determination value according to the following formula:

[0058] in, This is a value used to determine shallow browsing; it is a real number, and the larger the value, the higher the probability that the input vector corresponds to a shallow browsing state. In the shallow browsing discrimination function The weighting coefficients of the components are real numbers; In the shallow browsing discrimination function The weighting coefficients of the components are real numbers; In the shallow browsing discrimination function The weighting coefficients of the components are real numbers; is the bias constant of the shallow browsing discrimination function, and is a real number.

[0059] The above , , , , , , , , , , , These are all constants fixed at the time the model leaves the factory. The three judgment values ​​are output in parallel to the maximum value selection circuit, which outputs the cognitive label corresponding to the maximum value among the three values. By fixing the cognitive discrimination process into three sets of parallel operation links and the maximum value selection circuit, the process of determining the cognitive state is made open, transparent and reproducible, which helps to meet the traceability requirements of the core algorithm logic.

[0060] In one optional embodiment, the hierarchical temporal memory hardware storage area includes a single-page short-term relaxation memory hardware partition, a chapter-based continuous relaxation memory hardware partition, and a full-cycle relaxation-associated memory hardware partition. The single-page short-term relaxation memory hardware partition is used to store the short-term relaxation data of the current page, and the data is archived to the chapter continuous relaxation memory hardware partition after the e-ink screen performs a global refresh. The chapter-based continuous relaxation memory hardware partition is used to store the temporal relaxation data of each chapter within the same reading topic; The full-cycle relaxation-associated memory hardware partition is used to store correlated relaxation data across reading tasks; The hierarchical AI guidance hardware unit retrieves time-series data from the three hardware partitions to generate basic heuristic question data, comparative reflection question data, and cross-time period tracing question data.

[0061] Among them, the single-page short-time relaxation memory hardware partition (hereinafter referred to as single-page partition) refers to the storage area in the hierarchical time-series memory hardware storage area used to store the instantaneous relaxation data generated by the currently displayed page.

[0062] Among them, the chapter continuous relaxation memory hardware partition (hereinafter referred to as chapter partition) refers to the storage area in the hierarchical temporal memory hardware storage area used to store continuous temporal relaxation data across pages within the same reading topic.

[0063] Among them, the full-cycle relaxation-associated memory hardware partition (hereinafter referred to as full-cycle partition) refers to the storage area in the hierarchical time-series memory hardware storage area used to store relaxation data with long-term association characteristics that span different reading tasks.

[0064] In this embodiment, the relaxation data generated on the current page is first written to a single-page short-term relaxation memory hardware partition. When the e-ink screen performs a global refresh, the data in this partition is archived to a chapter-based continuous relaxation memory hardware partition. The temporal relaxation data of each chapter within the same reading topic is stored continuously in the chapter partition. After a single co-reading task ends, the data in the chapter partition is archived to a full-cycle relaxation-associated memory hardware partition. The hierarchical AI guidance hardware unit retrieves data from these three partitions respectively: data from the single-page partition to generate basic heuristic question data, data from the chapter partition to generate comparative reflection question data, and data from the full-cycle partition to generate cross-time period tracing question data. Through the design of the three-layer memory partitions, the AI ​​guidance generates questions of different depths at the single-page, chapter, and cross-task time scales, which helps to improve the progressiveness of the AI ​​guidance.

[0065] Optionally, the generation logic for basic heuristic question data is as follows: After the hierarchical AI-guided hardware unit retrieves the standardized multidimensional relaxation vector of a certain pixel position from the single-page short-term relaxation memory hardware partition, the hardware unit first extracts the cognitive label corresponding to the vector. If the cognitive label of the pixel position is cognitive blockage and the duration of the temporal relaxation data at that position in the single-page short-term relaxation memory hardware partition exceeds a preset dwell threshold, the basic heuristic question generation process is triggered. Specifically, the hardware unit matches the corresponding text content from the cloud relaxation coupling scheduling engine based on the coordinate information of the pixel position, extracts the keywords in the text content, and generates basic heuristic question data according to a preset question template. The question templates include: "Do you have any difficulties understanding the keywords?" and "Can you express your thoughts on the keywords?". The basic heuristic question data is used to guide users to reflect immediately on the specific knowledge points that cause cognitive blockage on the current page.

[0066] The logic for generating comparative reflection question data is as follows: After the hierarchical AI-guided hardware unit retrieves temporal relaxation data from multiple chapters within the same reading topic from the chapter-based continuous relaxation memory hardware partition, the hardware unit calculates the mean of each component of the standardized multidimensional relaxation vector corresponding to different text positions within the same chapter, obtaining a quantitative representation of the cognitive state at each text position within the chapter. The hardware unit compares the mean relaxation vectors of pixel regions corresponding to different knowledge points within the same chapter. If the Euclidean distance between the mean relaxation vectors of two knowledge points is greater than a preset difference threshold, it determines that there is a significant difference in the cognitive state of the two knowledge points, triggering the comparative reflection question generation process. Specifically, the hardware unit extracts text keywords corresponding to two knowledge points and generates comparative reflection question data according to a preset comparative question template. The question template includes: "You seem to think longer about knowledge point A. What are the connections and differences between it and knowledge point B?" and "How does your understanding of knowledge point A differ from that of knowledge point B?". The comparative reflection question data is used to guide users to make horizontal comparisons and connections between different knowledge points within the same reading topic.

[0067] The generation logic of cross-time periodic source tracing question data is as follows: After the hierarchical AI-guided hardware unit retrieves the temporal relaxation data across reading tasks from the full-cycle relaxation association memory hardware partition, the hardware unit performs pixel-by-pixel vector similarity calculation between the relaxation vector of each text position in the current reading task and the historical relaxation vector stored in the full-cycle partition. If the difference between the historical relaxation vector and the current relaxation vector at a certain text position in all three components is less than the preset source tracing threshold, then that position is marked as a cognitive source tracing trigger point, triggering the cross-time periodic source tracing question generation process. Specifically, the hardware unit extracts the keywords corresponding to the text position and retrieves the context information when the position first appeared in the historical reading task, generating cross-time periodic source tracing question data according to the preset source tracing question template. The question template includes: "You have also encountered keywords in the name of historical reading tasks before. Do you remember how you understood them at that time?" and "Regarding the question about keywords, how have your thoughts changed from before to now?". Cross-time periodic source tracing question data is used to guide users to make vertical connections between the cognitive obstacles encountered in the current reading and historical reading experiences, realizing cross-time periodic knowledge review and reflection.

[0068] The hierarchical AI-guided hardware unit retrieves temporal relaxation data from the corresponding partition of the hierarchical temporal memory hardware storage area and then performs the following operations in sequence: parses the standardized multidimensional relaxation vectors in the temporal relaxation data and extracts the cognitive state labels for each pixel position; selects the corresponding question type based on the current triggering conditions (single-page cognitive blockage timeout, significant differences in knowledge point vectors within a chapter, and cross-task vector similarity meeting the standard); retrieves a template from the corresponding question template library based on the selected question type; matches keywords in the text content based on pixel position or knowledge point name; and fills the keywords into the template to generate complete hierarchical heuristic question data.

[0069] In one optional embodiment, the home-school coupling computing hardware unit includes a distance calculation circuit and a difference calculation circuit; The output of the distance calculation circuit is connected to the input of the difference calculation circuit; The distance calculation circuit is used to calculate the physical distance between the parent's interactive relaxation vector and the student's synchronous relaxation vector; The difference calculation circuit is used to generate a home-school relaxation coupling degree based on the difference between the fixed reference value and the physical distance; When the home-school relaxation coupling degree is lower than the judgment benchmark, the cloud-based relaxation coupling scheduling engine retrieves the particle physical position corresponding to the cognitive blockage in the full-cycle relaxation-associated memory hardware partition, generates a parent-child co-reading task matching the particle physical position, and sends it to the parent's interactive device.

[0070] Among them, the distance calculation circuit refers to the hardware circuit inside the home-school coupling operation hardware unit used to calculate the Euclidean distance between two relaxation vectors in the quantization space.

[0071] Among them, the difference calculation circuit refers to the hardware circuit inside the home-school coupling calculation hardware unit used to calculate the difference between the fixed reference value and the above-mentioned physical distance, thereby obtaining the coupling degree value.

[0072] In this embodiment, the distance calculation circuit receives the parent interaction relaxation vector uploaded by the parent's terminal interaction device. And retrieve the relaxation vectors of students from the hierarchical sequential memory hardware storage area. The physical distance between the two can be calculated using the following formula. :

[0073] in, The Euclidean distance between the parent interaction relaxation vector and the student's concurrent relaxation vector is calculated as a dimensionless real number with a range of [0, 1]. ], which increases as the difference between the components of the two vectors increases. The flipping time component of the parent interaction relaxation vector has a range of [0, 1] and is dimensionless. Let be the afterimage attenuation component of the parent interaction relaxation vector, with a range of [0, 1] and dimensionless. Let be the cumulative perturbation component of the parent interaction relaxation vector, with a range of [0, 1] and dimensionless. The flipping time component of the student's synchronous relaxation vector has a range of [0, 1] and is dimensionless. Let be the afterimage attenuation component of the student's synchronous relaxation vector, with a range of [0, 1] and dimensionless. The cumulative perturbation component of the student's synchronous relaxation vector has a range of [0, 1] and is dimensionless.

[0074] The difference calculation circuit receives the distance. Calculate the home-school relaxation coupling degree according to the following formula. :

[0075] in, Let be the home-school relaxation coupling degree, be a dimensionless real number with a range of [0, 1], and be related to . It decreases as it increases. The maximum possible distance value is a preset value, a dimensionless real constant used for normalization, and its value is equal to... When the cloud-based relaxation coupling scheduling engine determines the degree of coupling... When the student's cognitive impairment falls below a preset threshold, the system retrieves the particle physics location corresponding to the student's historical cognitive impairment from the full-cycle relaxation-associated memory hardware partition. A parent-child reading task matching this location is then generated and sent to the parent's interactive device. By quantitatively calculating the home-school relaxation coupling degree, the system matches parental behavior with the student's cognitive state within the same quantitative space, helping to improve the accuracy of matching parent-child reading tasks with the student's learning needs.

[0076] In one optional embodiment, the cloud-based relaxation coupling scheduling engine includes a pre-interception circuit and a semantic verification circuit; The output of the pre-interception circuit is connected to the input of the semantic verification circuit, and the output of the semantic verification circuit is connected to all terminal hardware through the communication bus; the terminal hardware refers to the collective term for the relaxation acquisition terminal, the teacher's interactive device, and the parent's interactive device. The pre-interception circuit is used to compare the intrinsic weight of the data packet with the lower limit of the weight, and to intercept data packets that do not meet the weight conditions. The semantic verification circuit is used to match text content and filter interactive data based on pixel position relaxation measurement data.

[0077] Among them, the pre-interception circuit refers to the hardware comparison circuit in the cloud-based relaxation coupling scheduling engine used to pre-screen data packets based on their intrinsic weights before they enter the core analysis module.

[0078] The semantic verification circuit refers to the hardware processing circuit in the cloud-based relaxation coupling scheduling engine used to associate text content with pixel positions and perform secondary verification in combination with relaxation measurement data.

[0079] In this embodiment, after the native relaxed data packet enters the cloud-based relaxed coupling scheduling engine, it first passes through a pre-interception circuit. This circuit compares the intrinsic weight W of the data packet with a preset lower limit value, intercepting data packets with weights lower than the lower limit. Data packets that pass the pre-interception then enter the semantic verification circuit. This circuit matches the text corresponding to that position in the reading content based on the pixel coordinate information in the data packet, and makes a comprehensive judgment based on the relaxation measurement data of that pixel position. By performing weight pre-screening through the pre-interception circuit, the amount of data entering the semantic verification stage is reduced, which helps to improve cloud processing efficiency.

[0080] In one optional embodiment, the teacher-side interactive device includes a heatmap generation hardware unit; The heatmap generation hardware unit is used to aggregate the standardized multidimensional relaxation vectors of all students in the same chapter, and render the heatmap peak points according to the vector mean deviation of each pixel region. The heatmap peak points correspond to the physical locations of cognitive impairment in the class group. The teacher-side interactive device binds the teaching guidance data with the relaxation physical location corresponding to the thermal peak point and pushes it to the corresponding relaxation acquisition terminal.

[0081] The heatmap generation hardware unit refers to the hardware processing unit inside the teacher's interactive device that aggregates the relaxation vector data of all students in the class and generates a visual heatmap based on the vector statistical characteristics of each pixel region.

[0082] In this embodiment, the teacher-side interactive device obtains learning visualization map data from the cloud-based relaxation coupling scheduling engine via a communication bus. This data includes the aggregated statistical results of standardized multidimensional relaxation vectors generated by all students in the same reading chapter. The heatmap generation hardware unit renders and generates a heatmap based on this learning visualization map data. Specifically, it visualizes and maps the vector mean deviation values ​​of each pixel position in the learning visualization map data, and renders heatmap peak points based on the vector mean deviation values ​​of each pixel region. The heatmap is a specific visualization form of the learning visualization map on the teacher's end. Regions with mean deviations higher than the average level are marked as heatmap peak points. The teacher-side interactive device binds the teaching guidance data with the relaxation physical location corresponding to the heatmap peak point and pushes it to the corresponding relaxation acquisition terminal through the cloud-based relaxation coupling scheduling engine. By aggregating the relaxation vector data of all students in the class through the heatmap generation hardware unit, the physical location of group cognitive blockage is presented in a visual way, which helps teachers quickly locate common difficulties in the class and improve the pertinence of teaching guidance.

[0083] In one optional embodiment, the terminal power management hardware includes a phase detection circuit and a power supply regulation circuit; The output terminal of the phase detection circuit is connected to the input terminal of the power supply regulation circuit; The phase detection circuit is used to obtain the phase difference value of the multi-channel sensing phase signals output by the particle sensing acquisition hardware group; The power supply regulation circuit outputs a first power supply voltage when the phase difference is less than a fixed threshold, and outputs a second power supply voltage when the phase difference is greater than or equal to the fixed threshold, wherein the first power supply voltage is greater than the second power supply voltage.

[0084] Among them, the phase detection circuit refers to the hardware circuit inside the terminal power management hardware used to monitor the phase relationship between multiple sensing signals output by the particle sensing acquisition hardware group and calculate their phase difference.

[0085] Among them, the power supply regulation circuit refers to the hardware regulation circuit inside the terminal power management hardware used to switch the output power supply voltage level according to the magnitude of the phase difference.

[0086] The first supply voltage refers to the supply voltage output by the power supply regulation circuit when the phase difference is less than a fixed threshold, and the second supply voltage refers to the supply voltage output by the power supply regulation circuit when the phase difference is greater than or equal to the fixed threshold. The first supply voltage is greater than the second supply voltage.

[0087] In this embodiment, the phase detection circuit acquires the phase of multiple sensing signals output from the electrophoretic particle relaxation photoelectric acquisition array in the particle sensing acquisition hardware group, and calculates the phase difference between each signal. The power supply adjustment circuit receives the phase difference and compares it with a preset fixed threshold. When the phase difference is less than the fixed threshold, the power supply adjustment circuit outputs a first power supply voltage. When the phase difference is greater than or equal to the fixed threshold, the power supply adjustment circuit outputs a second power supply voltage, where the first power supply voltage is greater than the second power supply voltage. By dynamically adjusting the power supply voltage according to the phase difference of the sensing signals, the power supply voltage is reduced when the sensing activity is low, which helps to extend the battery life of the relaxation acquisition terminal.

[0088] This application also provides a multi-party real-time interactive reading control method, which runs on the aforementioned multi-party real-time interactive reading system.

[0089] Step 1: The teacher-side interactive device sends out a shared reading configuration command, and the cloud-based relaxation coupling scheduling engine creates a shared reading space and completes the initialization of relaxation baseline parameters.

[0090] In step one, the teacher issues a shared reading configuration command via the teacher-side interactive device, specifying the reading content and the list of participating students. Upon receiving this command, the cloud-based relaxation coupling scheduling engine creates a shared reading space and initializes global relaxation baseline parameters. These relaxation baseline parameters include... , , , , , The above parameters are fixed when the equipment leaves the factory.

[0091] Step 2: The particle sensing and acquisition hardware group collects the original physical parameters of the electrophoretic particles and the handwritten interactive data. The local computing hardware group generates standardized multidimensional relaxation vectors and data packet intrinsic weights based on the original physical parameters.

[0092] In step two, while students are reading on the relaxation acquisition terminal, the particle sensing acquisition hardware group acquires the raw physical parameters. , , The system processes handwritten data and sends it to the local computing hardware unit. The normalization circuitry of the local computing hardware unit then processes the data. , , Perform normalization operations to generate standardized multidimensional relaxation vectors. The weighting circuit performs a weighted summation of the three components of the vector to generate the intrinsic weights of the data packet. The local computing hardware group will vector Weight The bound handwritten data is encapsulated into a native relaxed data packet.

[0093] Step 3: The slice modulation hardware allocates transmission channels according to the intrinsic weight of the data packets, transmits high-weight data packets and medium-weight data packets to the cloud relaxation coupling scheduling engine, and caches low-weight data packets in the local time-series cache hardware and uploads them in batches when the relaxation acquisition terminal enters a low-power state.

[0094] In step three, the comparison circuit of the slice modulation hardware will weight... Compare with the curing threshold. If... If the value is ≥0.7, the data packet is classified as a high-weight data packet and transmitted in real time to the cloud-based relaxed coupling scheduling engine through the highest priority channel of the cognitive data subbus. If 0.3 ≤ If the weight is less than 0.7, the data packet is classified as a medium-weighted data packet and transmitted to the cloud-based relaxed coupling scheduling engine via the secondary priority channel of the cognitive data subbus. If the value is less than 0.3, the data packet is classified as a low-weight data packet and sent to the local timing buffer hardware. When the relaxation acquisition terminal enters a low-power state, it is uploaded to the cloud in batches through the asynchronous buffer sub-bus.

[0095] Step four: The cloud-based relaxation coupling scheduling engine receives the native relaxation data packet, identifies the user's cognitive state through the cognitive discrimination model, and writes the time-series relaxation data into the hierarchical time-series memory hardware storage area in layers.

[0096] In step four, the cloud-based relaxation coupling scheduling engine receives the native relaxation data packet, which contains the relaxation vector. The data is fed into the cognitive discrimination model. The three sets of computational links in the cognitive discrimination model compute the output values ​​of three discrimination functions: deep thinking, cognitive blockage, and shallow browsing in parallel. The maximum value selection circuit outputs the cognitive label corresponding to the maximum value among the three values; the cognitive label is either deep thinking, cognitive blockage, or shallow browsing. The labeled temporal relaxation data is written to the corresponding partition of the hierarchical temporal memory hardware storage area.

[0097] Step 5: The layered AI-guided hardware unit retrieves time-series relaxation data stored in three hardware partitions, generates third-order layered heuristic questioning data, and sends it to the e-ink screen display driver hardware to complete screen rendering. The third-order layered heuristic questioning data includes basic heuristic questioning data, comparative reflection questioning data, and cross-time period tracing questioning data.

[0098] In step five, the hierarchical AI-guided hardware unit retrieves current page data from the single-page short-term relaxation memory hardware partition of the hierarchical temporal memory hardware storage area to generate basic heuristic question data; it retrieves continuous temporal data within the same reading topic from the chapter-based continuous relaxation memory hardware partition to generate comparative reflection question data; and it retrieves historical data across reading tasks from the full-cycle relaxation-related memory hardware partition to generate cross-time period tracing question data. The above three-tiered hierarchical heuristic question data are then distributed to the e-ink display driver hardware via the cloud-based relaxation coupling scheduling engine, where the image is rendered on the e-ink screen of the relaxation acquisition terminal.

[0099] Step 6: The parent-side interactive device uploads the parent interaction relaxation vector, and the home-school coupling calculation hardware unit generates the home-school relaxation coupling degree. When the home-school relaxation coupling degree is lower than the judgment benchmark, a parent-child co-reading task matching the physical location of cognitive impairment is generated and pushed to the parent-side interactive device.

[0100] In step six, parents' interactive behaviors on the parent-side interactive device are quantified into parent interaction relaxation vectors and uploaded to the cloud-based relaxation coupling scheduling engine. The distance calculation circuit of the home-school coupling computation hardware unit retrieves the student's relaxation vectors from the hierarchical time-series memory hardware storage area and calculates the Euclidean distance between them. The difference calculation circuit receives this distance and calculates the home-school relaxation coupling degree based on the difference between the fixed reference value and this distance. When the cloud-based relaxation coupling scheduling engine determines the degree of coupling... When the score is below the preset threshold, the particle physics location corresponding to the student's historical cognitive impairment is retrieved from the full-cycle relaxation-associated memory hardware partition. A parent-child reading task matching the physical location is generated and sent to the parent's interactive device.

[0101] Step seven: The teacher-side interactive device aggregates the relaxation vector data of the entire class to generate a heat map, and distributes teaching guidance data according to the relaxation physical location corresponding to the heat map peak. The heat map is a specific visualization form of the learning visualization map. It is generated by the heat map generation hardware unit of the teacher-side interactive device based on the learning visualization map data, and displays the physical location distribution of group cognitive impairment through color gradation or peak points.

[0102] In step seven, the teacher-side interactive device acquires the learning situation visualization map data from the cloud-based relaxation coupling scheduling engine via the communication bus. The heatmap generation hardware unit renders and generates a heatmap based on this learning situation visualization map data, that is, it visualizes and maps the vector mean deviation value of each pixel position in the learning situation visualization map data, and renders the heatmap peak points based on the vector mean deviation value of each pixel region. Regions with mean deviations higher than the average level are marked as heatmap peak points, which correspond to the physical location of cognitive impairment in the class group. The teacher-side interactive device binds the teaching guidance data with the relaxation physical location corresponding to the heatmap peak point, and pushes it to the corresponding relaxation acquisition terminal through the cloud-based relaxation coupling scheduling engine.

[0103] Step 8: Repeat steps 2 to 7. After a single reading session is completed, the cloud-based relaxation coupling scheduling engine archives the chapter-based temporal relaxation data to the full-cycle relaxation-associated memory hardware partition.

[0104] In step eight, steps two through seven are repeated. After a single shared reading task concludes, the cloud-based relaxation coupling scheduling engine archives the chapter-based temporal relaxation data generated by this task from the chapter-based continuous relaxation memory hardware partition to the full-cycle relaxation-associated memory hardware partition. By archiving the chapter-based temporal relaxation data to the full-cycle relaxation-associated memory hardware partition, cognitive data across reading tasks can be accumulated and stored, helping to provide a data foundation for long-term learning analysis.

[0105] In another possible implementation, the particle sensing hardware assembly can employ a different sensing principle. Utilizing the physical principle that the movement of electrophoretic particles within a pixel unit causes a change in the unit's dielectric constant, leading to a change in its equivalent capacitance, the electrophoretic particle relaxation photoelectric acquisition array can be replaced with a pixel capacitance sensing array. This array continuously scans the capacitance value of each pixel unit, and the system extracts the equivalent capacitance by analyzing the characteristics of the capacitance value change curve. , , Parameters. Subsequent normalization, weight calculation, and other steps are the same as in the above embodiments. This scheme utilizes the change in dielectric constant caused by the displacement of electrophoretic particles for state monitoring, without relying on optical acquisition devices, which helps reduce the hardware cost of the relaxation acquisition terminal and improve the anti-interference capability of the sensing signal in strong light environments.

[0106] Furthermore, the functionality of the slice modulation hardware can also be implemented in other ways. The slice modulation hardware can be replaced with a network service quality marking module, which can be software or firmware integrated into the terminal's network protocol stack. The terminal calculates the intrinsic weight value of the data packet. Then, the QoS tagging module according to The value sets the corresponding Differential Service Code Point (DSC) value for this IP packet. High-weight packets are marked for expedited forwarding, while low-weight packets are marked for best-effort forwarding. Network devices that support QoS recognize these markings and prioritize their processing. When implementing tiered data transmission through QoS marking, the system does not need to establish separate physical transmission channels for high- and low-weight packets, which helps reduce the configuration complexity of the communication link between the terminal and the cloud and improves the flexibility of network resource allocation among different packet types.

[0107] In another implementation, the cognitive discriminant model in the cloud-based relaxation coupling scheduling engine can employ a decision tree model. The multivariate linear discriminant model is replaced with a fixed decision tree discriminant module. The structure of this decision tree and the judgment thresholds for all nodes are trained and fixed using standard sample data before the device leaves the factory. When the cloud engine receives the relaxation vector... Then, it is input into the fixed decision tree model. The model starts from the root node and, based on... A component value is compared with the threshold of a node, and the process is traversed layer by layer until a leaf node that uniquely corresponds to a certain cognitive state label is reached. The computational path of the decision tree model consists of explicit comparison rules, which helps to reduce the computational complexity of the cloud inference process, improve the interpretability of cognitive state discrimination, and enhance the stability of the model training results in hardware implementation.

[0108] This application also provides a computer device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the steps in the above method embodiments.

[0109] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0110] This application provides a computer program product that, when run on a computer device, enables the computer device to execute the steps described in the various method embodiments above.

[0111] The computer device provided in this application embodiment may include, but is not limited to, a processor and a memory. The processor may be a Central Processing Unit (CPU), but it can 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, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0112] In some embodiments, the memory may be an internal storage unit of the computer device, such as a hard drive or RAM. In other embodiments, the memory may be an external storage device of the computer device, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory may include both internal and external storage units of the computer device.

[0113] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a device / computer equipment, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0114] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0115] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0116] In the embodiments provided in this application, it should be understood that the disclosed apparatus / computer devices and methods can be implemented in other ways. For example, the apparatus / computer device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0117] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0118] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A multi-party real-time interactive reading system, characterized in that, include: Several relaxation acquisition terminals, teacher-side interactive devices, parent-side interactive devices, and a cloud-based relaxation coupling scheduling engine; The cloud-based relaxation coupling scheduling engine establishes bidirectional hardware communication links with all relaxation acquisition terminals, the teacher-side interactive devices, and the parent-side interactive devices via a communication bus. Each relaxation acquisition terminal includes a particle sensing acquisition hardware group, a local computing hardware group, a slice modulation hardware group, a local timing cache hardware group, an e-ink display driver hardware group, and a terminal power management hardware group. The output of the particle sensing acquisition hardware group is connected to the input of the local computing hardware group, and the output of the local computing hardware group is connected to the input of the slice modulation hardware group. The output of the slice modulation hardware group is connected to the input of the local timing cache hardware group and the input of the cloud-based relaxation coupling scheduling engine. The input of the e-ink display driver hardware group is connected to the output of the cloud-based relaxation coupling scheduling engine. The output of the terminal power management hardware group is connected to the power input of all hardware modules within the relaxation acquisition terminal. The particle sensing and acquisition hardware group is used to collect the original physical parameters of electrophoretic particles in the pixel area of ​​the e-ink screen and the user's handwritten interaction data, and transmit them to the local computing hardware group. The local computing hardware group is used to generate a standardized multidimensional relaxation vector based on the original physical parameters, generate data packet intrinsic weights based on the standardized multidimensional relaxation vector, and output native relaxation data packets to the slice modulation hardware. The slice modulation hardware is used to allocate hardware transmission channels according to the intrinsic weight of the data packets and store low-weight data packets in the local timing buffer hardware. The cloud-based relaxation coupling scheduling engine is used to receive the native relaxation data packets, identify the user's cognitive state based on the standardized multidimensional relaxation vector, complete the hierarchical storage of time-series data, and generate hierarchical heuristic questioning data, learning progress visualization map data, and parent-child co-reading task data. The teacher-side interactive device is used to issue shared reading configuration commands, display a visual learning progress graph, and push teaching guidance data to the corresponding relaxation collection terminal based on the learning progress points. The parent-side interactive device is used to collect particle physics parameters corresponding to parent interaction behaviors, generate parent interaction relaxation vectors and upload them to the cloud relaxation coupling scheduling engine, and receive parent-child co-reading task data issued by the cloud relaxation coupling scheduling engine. The e-ink screen display driver hardware is used to receive data signals sent by the cloud-based relaxation coupling scheduling engine and drive the e-ink screen to complete multi-character screen rendering.

2. The multi-party real-time interactive reading system according to claim 1, characterized in that, The cloud-based relaxation coupling scheduling engine includes a cognitive discrimination model, a hierarchical temporal memory hardware storage area, a home-school coupled computing hardware unit, and a hierarchical AI guidance hardware unit. The cognitive discriminant model is used to identify the user's cognitive state based on the standardized multidimensional relaxation vector; The hierarchical time-series memory hardware storage area is used to complete the hierarchical storage of time-series data; The home-school coupling computation hardware unit is used to generate the home-school relaxation coupling degree based on the parent interaction relaxation vector and the student's synchronous relaxation vector. The hierarchical AI guidance hardware unit is used to generate hierarchical heuristic question data based on hierarchical time-series data.

3. The multi-party real-time interactive reading system according to claim 1, characterized in that, The particle sensing and acquisition hardware group includes an electrophoretic particle relaxation photoelectric acquisition array and a pressure-sensitive and pixel relaxation bound sensing unit. The electrophoretic particle relaxation photoelectric acquisition array acquires three types of raw physical parameters according to a fixed acquisition period: electrophoretic particle flipping time, afterimage relaxation attenuation sampling data, and cumulative number of particle disturbances in the pixel area. The pressure-sensitive and pixel relaxation binding sensing unit collects handwriting pressure gradient, writing pause duration, and handwriting stroke pixel coordinate data, binds the handwriting data with the original physical parameters at the same pixel position, and transmits it to the local computing hardware group.

4. The multi-party real-time interactive reading system according to claim 1, characterized in that, The local computing hardware group includes a normalization operation circuit and a weight operation circuit; The output of the normalization operation circuit is connected to the input of the weight operation circuit, and the output of the weight operation circuit is connected to the input of the slice modulation hardware. The normalization operation circuit is used to perform normalization operations on the original physical parameters to generate the standardized multidimensional relaxation vector; The weighting circuit is used to perform weighted fusion on each component of the standardized multidimensional relaxation vector to generate the intrinsic weight of the data packet.

5. The multi-party real-time interactive reading system according to claim 1, characterized in that, The cloud-based relaxation coupling scheduling engine includes a cognitive discrimination model, which includes three sets of computation links and a maximum value selection circuit. The output terminals of the three sets of computation links are respectively connected to the three input terminals of the maximum value selection circuit; Each computational link outputs a judgment value based on the standardized multidimensional relaxation vector components and fixed constants; The three sets of computing links output judgment values ​​in parallel to the maximum value selection circuit. The maximum value selection circuit outputs the cognitive tag corresponding to the maximum judgment value. The cognitive tag is deep thinking, cognitive blockage, and shallow browsing.

6. The multi-party real-time interactive reading system according to claim 2, characterized in that, The hierarchical temporal memory hardware storage area includes a single-page short-time relaxation memory hardware partition, a chapter-based continuous relaxation memory hardware partition, and a full-cycle relaxation-associated memory hardware partition. The single-page short-term relaxation memory hardware partition is used to store the short-term relaxation data of the current page, and the data is archived to the chapter continuous relaxation memory hardware partition after the e-ink screen performs a global refresh. The chapter-based continuous relaxation memory hardware partition is used to store the temporal relaxation data of each chapter within the same reading topic; The full-cycle relaxation-associated memory hardware partition is used to store correlated relaxation data across reading tasks; The hierarchical AI guidance hardware unit retrieves time-series data from the three hardware partitions to generate basic heuristic question data, comparative reflection question data, and cross-time period tracing question data.

7. The multi-party real-time interactive reading system according to claim 6, characterized in that, The home-school coupling computing hardware unit includes a distance calculation circuit and a difference calculation circuit; The output of the distance calculation circuit is connected to the input of the difference calculation circuit; The distance calculation circuit is used to calculate the physical distance between the parent's interactive relaxation vector and the student's synchronous relaxation vector; The difference calculation circuit is used to generate a home-school relaxation coupling degree based on the difference between the fixed reference value and the physical distance; When the home-school relaxation coupling degree is lower than the judgment benchmark, the cloud-based relaxation coupling scheduling engine retrieves the particle physical position corresponding to the cognitive blockage in the full-cycle relaxation-associated memory hardware partition, generates a parent-child co-reading task matching the particle physical position, and sends it to the parent's interactive device.

8. The multi-party real-time interactive reading system according to claim 1, characterized in that, The cloud-based relaxation coupling scheduling engine includes a front-end interception circuit and a semantic verification circuit. The output of the pre-interception circuit is connected to the input of the semantic verification circuit, and the output of the semantic verification circuit is connected to all terminal hardware through the communication bus. The pre-interception circuit is used to compare the intrinsic weight of the data packet with the lower limit of the weight, and to intercept data packets that do not meet the weight conditions. The semantic verification circuit is used to match text content and filter interactive data based on pixel position relaxation measurement data.

9. The multi-party real-time interactive reading system according to claim 1, characterized in that, The teacher-side interactive device includes a heatmap generation hardware unit; The heatmap generation hardware unit is used to aggregate the standardized multidimensional relaxation vectors of all students in the same chapter, and render the heatmap peak points according to the vector mean deviation of each pixel region. The heatmap peak points correspond to the physical locations of cognitive impairment in the class group. The teacher-side interactive device binds the teaching guidance data with the relaxation physical location corresponding to the thermal peak point and pushes it to the corresponding relaxation acquisition terminal.

10. A multi-party real-time interactive reading control method, characterized in that, Includes the following steps: Step 1: The teacher-side interactive device sends out a shared reading configuration command, and the cloud-based relaxation coupling scheduling engine creates a shared reading space and completes the initialization of relaxation baseline parameters; Step 2: The particle sensing and acquisition hardware group collects the original physical parameters of the electrophoretic particles and the handwritten interactive data. The local computing hardware group generates standardized multidimensional relaxation vectors and data packet intrinsic weights based on the original physical parameters. Step 3: The slice modulation hardware allocates transmission channels according to the intrinsic weight of the data packets, transmits high-weight data packets and medium-weight data packets to the cloud relaxation coupling scheduling engine, and caches low-weight data packets in the local time-series cache hardware and uploads them in batches when the relaxation acquisition terminal enters a low-power state. Step four: The cloud-based relaxation coupling scheduling engine receives the native relaxation data packet, identifies the user's cognitive state through the cognitive discrimination model, and writes the time-series relaxation data into the hierarchical time-series memory hardware storage area in layers. Step 5: The layered AI-guided hardware unit retrieves the time-series data stored in the three hardware partitions, generates three-level layered heuristic query data, and sends it to the e-ink screen display driver hardware to complete the screen rendering. Step 6: The parent-side interactive device uploads the parent interaction relaxation vector, and the home-school coupling calculation hardware unit generates the home-school relaxation coupling degree. When the home-school relaxation coupling degree is lower than the judgment benchmark, a parent-child co-reading task matching the physical location of cognitive impairment is generated and pushed to the parent-side interactive device. Step 7: The teacher's interactive device aggregates the relaxation vector data of the whole class to generate a heat map, and distributes teaching guidance data according to the relaxation physical location corresponding to the heat peak. Step 8: Repeat steps 2 to 7. After a single reading session is completed, the cloud-based relaxation coupling scheduling engine archives the chapter time-series data to the full-cycle relaxation-associated memory hardware partition.

Images