Information processing system

Abstract

The application provides an information processing system for a smart terminal. The method of the information processing system in the application comprises the following steps: obtaining to-be-processed interaction information and physical data information; performing feature extraction on the to-be-processed interaction information and the physical data information to obtain interaction feature information and physical feature information; and processing the interaction feature information and the physical feature information by using a target model to obtain a target processing result.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to an information processing system. Background Technology

[0002] Currently, with the rapid development of the internet and smart devices, the per capita ownership of smart devices such as mobile phones, tablets, smart TVs, and smart computers is increasing, and users are becoming increasingly reliant on using smart devices for work and entertainment. However, overuse of smart devices may lead to problems such as decreased vision, sleep disorders, and anxiety. Summary of the Invention

[0003] This application provides an information processing system.

[0004] On the one hand, the information processing system provided in this application embodiment also includes an information processing method, which includes the following steps:

[0005] Acquire the interaction information and vital sign data to be processed;

[0006] Feature extraction is performed on the interaction information to be processed and the vital sign data information to obtain interaction feature information and vital sign feature information;

[0007] The interaction feature information and the vital sign feature information are processed using the target model to obtain the target processing result.

[0008] On the other hand, this application provides a system comprising:

[0009] The information acquisition module is configured to acquire interactive information and vital sign data to be processed.

[0010] The feature extraction module is configured to extract features from the interaction information to be processed and the vital sign data information to obtain interaction feature information and vital sign feature information.

[0011] The information processing module is configured to process the interaction feature information and the vital sign feature information using the target model to obtain the target processing result.

[0012] On the other hand, this application also provides an information processing device, the information processing device comprising:

[0013] One or more processors;

[0014] Memory; and

[0015] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the steps of the information processing method.

[0016] On the other hand, this application also provides a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to perform the steps in the information processing method described above. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram illustrating a scenario of the information processing method in an embodiment of this application.

[0019] Figure 2 This is a flowchart illustrating one embodiment of the information processing method in this application.

[0020] Figure 3 A schematic diagram of the structure of an embodiment of the information processing system provided in this application;

[0021] Figure 4 This is a schematic diagram of the structure of one embodiment of the information processing device provided in this application. Detailed Implementation

[0022] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0024] In this application, the term "exemplary" is used to mean "serving as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0025] To facilitate understanding of the information processing method provided in the embodiments of this application, the application scenarios of the information processing method provided in the embodiments of this application will be described first. Specifically, the information processing method provided in the embodiments of this application is mainly applied to various smart devices. By analyzing the user's interaction information, physiological information, and daily routine information when using smart devices, it assesses whether the user is overusing smart devices, and thus reminds and intervenes the user when the user's overuse of smart devices affects the user's normal daily routine.

[0026] With the rapid development of the internet and smart devices, the per capita ownership of smart devices such as mobile phones, tablets, smart TVs, and smart computers is increasing, and users are becoming increasingly reliant on them for work and entertainment. However, excessive use of smart devices can lead to health problems such as vision problems, sleep disorders, and anxiety. Current methods for preventing user addiction to electronic devices involve setting fixed usage time limits, which lack consideration for individual physiological differences and actual usage patterns, resulting in poor intervention and reminder effectiveness in preventing excessive use of electronic products.

[0027] Based on this, this application proposes an information processing system to solve the technical problem that the intervention effect of relying solely on usage time limits to assess and intervene in users' excessive use of electronic products is poor.

[0028] The information processing method in this embodiment of the invention is applied to an information processing system, which is set in an information processing device. The information processing device is provided with one or more processors, a memory, and one or more application programs. The one or more application programs are stored in the memory and configured to be executed by the processor to implement the information processing method. The information processing device can be a smart terminal, such as a mobile phone, tablet computer, network device, and smart computer. Optionally, the information processing device can also be a server or a service cluster composed of multiple servers.

[0029] like Figure 1 As shown, Figure 1 This is a schematic diagram of an information processing method according to an embodiment of the present application. The information processing scenario in this embodiment includes an information processing device 100 (the information processing device 100 integrates an information processing apparatus), and the information processing device 100 is equipped with a computer-readable storage medium corresponding to the information processing method to execute the steps of the information processing method.

[0030] Understandable, Figure 1 The information processing device in the information processing method scenario shown, or the device included in the information processing device, does not constitute a limitation on the embodiments of the present invention. That is, the number or type of the information processing device in the information processing method scenario, or the number or type of the device included in each device, does not affect the overall implementation of the technical solution in the embodiments of the present invention, and can all be considered as equivalent substitutions or derivatives of the technical solutions claimed in the embodiments of the present invention.

[0031] In this embodiment of the invention, the information processing device 100 is mainly used to: acquire interactive information to be processed, and vital sign data information corresponding to the interactive information to be processed;

[0032] The target model is used to process the interaction information to be processed and the vital sign data information to obtain the target processing result.

[0033] The information processing device 100 in this embodiment of the invention can be an independent information processing device, such as a mobile phone, tablet computer, network device, server and smart computer, or an information processing network or information processing cluster composed of multiple information processing devices.

[0034] This application provides an information processing system, which will be described in detail below.

[0035] It will be understood by those skilled in the art that Figure 1 The application environment shown is only one application scenario related to the solution of this application and does not constitute a limitation on the application scenario of this application. Other application environments may include more than one application scenario. Figure 1 The number of more or fewer information processing devices, or information processing network connections shown, for example Figure 1 Only one information processing device is shown in the figure. It is understood that the scenario of this information processing method may also include one or more information processing devices, which are not specifically limited here. The information processing device 100 may also include a memory for storing the target processing results and other data.

[0036] It should be noted that, Figure 1 The schematic diagram of the information processing method shown is merely an example. The scenarios of the information processing method described in the embodiments of the present invention are intended to more clearly illustrate the technical solutions of the embodiments of the present invention and do not constitute a limitation on the technical solutions provided in the embodiments of the present invention.

[0037] Based on the scenarios described above, various embodiments of the information processing method disclosed in this invention are proposed.

[0038] like Figure 2 As shown, Figure 2 This is a flowchart illustrating one embodiment of the information processing method in this application. The information processing method includes the following steps 201 to 202:

[0039] 201. Obtain the interaction information and vital sign data to be processed;

[0040] The information processing method in this embodiment is applied to an information processing device in an information processing system. The type and number of information processing devices are not specifically limited; that is, the information processing device can be one or more intelligent terminals or servers equipped with a target processing model capable of information processing. In one specific embodiment, the information processing device is an intelligent device that intervenes in the use of a specified target interactive terminal by a user to prevent excessive use that could affect the user's physical and mental health. The information processing device can be the target interactive terminal itself or an intelligent device communicatively connected to the target interactive terminal. For example, in one specific embodiment, the information processing device can be an intelligent terminal such as a mobile phone, tablet computer, smart TV, or smart computer to be interactively intervened. Furthermore, the information processing device can also be a mobile terminal or intelligent gateway device communicatively connected to the intelligent terminal to be interactively intervened.

[0041] Specifically, during operation, the information processing device responds to information processing requests. These requests are designed to drive the device to intervene in user interaction with the target interactive terminal, preventing excessive use of the terminal. The triggering method for these requests is not specifically limited; they can be initiated by the user, for example, by clicking an anti-addiction button on the device (either a physical button or a virtual button control on a designated monitoring settings page). Alternatively, the requests can be automatically triggered by the device, for instance, by an interactive monitoring process that automatically triggers the request when the user uses the target interactive terminal.

[0042] Specifically, after receiving an information processing request, the information processing device acquires the interaction information to be processed, as well as the vital sign data information corresponding to the interaction information to be processed.

[0043] The interaction information to be processed is time-series data representing user terminal usage behavior on various target interactive terminals. In one specific embodiment, the interaction information to be processed includes first interaction processing information representing the usage duration of a specified device, and second interaction processing information representing the usage duration of a specified application. The specified device includes smart device types such as mobile phones, tablets, smart TVs and smart computers, projection devices, virtual devices (e.g., VR / AR / XR virtual terminals), and smart wearable devices (e.g., smart glasses). The specified application can include video applications (e.g., iQiyi, Tencent Video, Youku Video, Bilibili, Douyin, and Kuaishou), live streaming applications (e.g., Huya Live, Douyu Live, Douyin Live, and e-commerce live streaming), game applications and social applications (Xiaohongshu, Weibo, and Baidu Tieba), educational applications, and browser applications.

[0044] For example, in one specific embodiment, the first processing information includes any one or more of the following: mobile phone usage time, and / or tablet usage time, and / or television usage time, and / or computer usage time, and / or projector usage time, and / or virtual device usage time, and / or smart wearable device (e.g., smart glasses) usage time.

[0045] For example, in another specific embodiment, the usage time of the game application, and / or the usage time of the video application, and / or the usage time of the live streaming application, and / or the usage time of the social application, and / or the usage time of the educational application, and / or the usage time of the browser application, etc., is any one or more of these application usage times.

[0046] For example, in one specific embodiment, the information processing device collects the target user's pending interaction information, including first interaction information regarding mobile phone use, which states that the mobile phone was used for 2.5 hours between 9:00 PM and 11:30 PM. Second interaction information states that during this time period, the target user's interaction time with the target short video application was 1.5 hours, and the interaction time with the target game application was 1 hour.

[0047] For example, in another specific embodiment, the information processing device collects pending interaction information from another target user, including first interaction information about using a tablet computer: the tablet was used for 1 hour between 12:00 PM and 1:00 PM, and for 4 hours between 7:00 PM and 11:00 PM. Second interaction processing information indicates that the target user's interaction time with the target video application during the aforementioned time periods was 5 hours.

[0048] The interactive data to be processed can be time-series data containing timestamp information obtained by the information interaction device by reading the terminal usage information of each target interactive terminal and the application usage information of each application in each target interactive terminal.

[0049] The vital signs data information refers to the physiological data and daily routine data of the user when using various target interactive terminals. In one specific embodiment, the vital signs data information includes first vital signs data information corresponding to various physiological indicators of the user when using various target interactive terminals. In addition, the vital signs data information also includes second vital signs data information representing the user's daily routine habits.

[0050] Optionally, in one specific embodiment, the first vital sign data information may be the user's heart rate physiological index and sleep duration index. Furthermore, in other embodiments, the first vital sign data information may also be other physiological indicators. For example, the first vital sign data includes any one or more of the following: heart rate physiological index, and / or sleep duration index, and / or body temperature vital sign data, and / or heart rate variability data, and / or stress vital sign data, and / or respiratory vital sign data.

[0051] Optionally, in one specific embodiment, the second vital sign data information may be data such as the user's daily routine (i.e., wake-up time and bedtime, etc.) and the user's work time information. For example, the second vital sign data information includes any one or more of the following: wake-up habit data, and / or bedtime habit data, and / or nap habit data, and / or work habit data, and / or meal habit data.

[0052] Among them, wake-up habit data represents the wake-up time information corresponding to the user's daily habit of waking up. Bedtime habit data represents the bedtime information corresponding to the user's daily habit of going to bed. Naptime habit data represents the time information of the user's daily short rest. Work habit data represents the time information of the user's daily work. Meal habit data represents the user's fixed mealtimes.

[0053] Optionally, in one embodiment, the information processing device can read the target user's vital sign data through a communication-connected smart wearable device or other smart device. For example, in one specific embodiment, the information processing device can communicate and interact with a smart wearable device (such as a smartwatch, smart bracelet, and heart rate monitor) worn by the target user, and drive the smart wearable device to collect the user's physiological indicators (such as heart rate indicators) when using the target interactive terminal or other physiological indicators under specified user behavior (such as sleep duration indicators obtained by sleep detection of the target user) to obtain vital sign data.

[0054] Optionally, after acquiring vital sign data and interaction information to be processed, the information processing device also preprocesses the vital sign data and interaction information to be processed. That is, it performs data cleaning on the vital sign data and interaction information to be processed, removes missing and outlier values, and aligns the vital sign data and interaction information from different sources in time to form a unified time series data, thus obtaining preprocessed vital sign data and interaction information to be processed. Based on the preprocessed vital sign data and interaction information to be processed, it assesses whether there is a risk of the user overusing the target interactive terminal, thereby determining whether corresponding interactive intervention operations need to be output.

[0055] 202. Perform feature extraction on the interaction information to be processed and the vital sign data information to obtain interaction feature information and vital sign feature information;

[0056] Specifically, after acquiring the interactive information to be processed and the vital sign data, the information processing device also performs feature extraction on the interactive information to be processed and the vital sign data respectively, thereby obtaining the interactive feature information corresponding to the interactive information to be processed and the vital sign feature information corresponding to the vital sign data.

[0057] In this embodiment of the application, before the information processing device acquires the interaction information to be processed and uses the target model to evaluate the usage status of the interaction information to be processed and the vital sign data information, it also performs a first feature extraction on the interaction information to be processed to obtain interaction feature information.

[0058] Optionally, in one embodiment, the interaction information to be processed includes first interaction processing information representing the usage time of a specified device, and second interaction processing information representing the usage time of a specified application. After obtaining the first interaction processing information and the second interaction processing information, the information processing device extracts corresponding usage behavior features from the first interaction processing information and the second interaction processing information, respectively, to obtain the first interaction information feature corresponding to the first interaction processing information and the second interaction information feature corresponding to the second interaction processing information.

[0059] Optionally, the information processing device determines the first interaction information feature based on the first interaction processing information and the first feature extraction parameters. The first feature extraction parameters are indicator functions representing the usage time of each target interaction terminal. The information processing device pre-sets corresponding first feature extraction parameters for each target interaction terminal, and extracts features from the first interaction processing information using these parameters to obtain the first interaction information feature representing the usage time of each target interaction terminal. That is, the information processing device obtains the first interaction information feature by calculating the sum of the products of each first interaction processing information and the first feature extraction parameters. Optionally, in a specific embodiment, the method for obtaining the first interaction information feature includes:

[0060] U d =∑ i Δt i *δ(d i =d)

[0061] Among them, U d For the first interactive information feature, Δt i For the first interactive processing information, δ(d) i =d) is the first feature extraction parameter. Where, when d... i When d = , the first feature extraction parameter is set to 1; otherwise, the first feature extraction parameter is set to 0.

[0062] Optionally, the information processing device further determines the second interaction information feature based on the second interaction processing information and the second feature extraction parameters. The second feature extraction parameters are indicator function values ​​representing each application. The information processing device pre-sets corresponding second feature extraction parameters for various target applications used by the user, and extracts features from the second interaction processing information using these parameters to obtain the second interaction information feature representing the usage duration of each target application. That is, the information processing device obtains the second interaction information feature by calculating the sum of the products of each second interaction processing information and the second feature extraction parameters. Optionally, in a specific embodiment, the method for obtaining the second interaction information feature includes:

[0063] U a =∑ i Δt i *δ(a i =a)

[0064] Among them, U d For the second interactive information feature, Δt i For the second interactive processing information, δ(a) i =a) is the first feature extraction parameter. Where, when a i When = a, the first feature extraction parameter is set to 1; otherwise, the first feature extraction parameter is set to 0.

[0065] Optionally, after determining the first interactive information feature corresponding to the usage time of each target interactive terminal and the second interactive information feature corresponding to the usage time of each target application, the information processing device further determines interactive feature information based on the first interactive information feature and the second interactive information feature. That is, the information processing device determines the first interactive information feature and the second interactive information feature as interactive feature information.

[0066] Optionally, before acquiring vital sign data and using the target model to evaluate the usage status of the interactive information to be processed and vital sign data, the information processing device may also extract vital sign features from the vital sign data to obtain vital sign feature information that characterizes the user's physiological state.

[0067] Optionally, in one embodiment, after acquiring the vital sign data, the information processing device acquires the first vital sign data and the second vital sign data from the data to be processed, and determines the first vital sign feature information of the vital sign data based on the first and second vital sign data. The first vital sign feature information is physiological characteristic information characterizing the association between the target object and the target interactive terminal.

[0068] Optionally, the information processing device determines the first statistical data information corresponding to the first vital sign data information based on the first vital sign data information. That is, after the information processing device collects the first vital sign data information representing the target user's heart rate index, it calculates the average value of the first vital sign data information to obtain the first statistical data information representing the average heart rate of the target object when using the target interactive terminal.

[0069] Optionally, the information processing device further performs calculations based on the first vital sign data and the first statistical data to determine the heart rate vital sign characteristics of the first vital sign data. In one specific embodiment, the heart rate vital sign characteristics are the heart rate variability (HRV) parameter of the target object when using the target interactive terminal.

[0070] Optionally, this heart rate characteristic is obtained by calculating and processing the first vital sign data and the first statistical data through the feature calculation model in the target model, wherein the feature calculation model is as follows:

[0071]

[0072] HRV refers to heart rate characteristics, HR j For primary vital sign data, HR avg This is the primary statistical data.

[0073] Optionally, the information processing device further acquires second vital sign data from the vital sign data, and determines the target state feature based on the second vital sign data and the first data indication parameter. The second vital sign data is time-series data representing the duration of the user's sleep state. The target state feature represents the cumulative sleep duration of the target user within a specific time period. In one specific embodiment, this specific time period is the past 24 hours. The target state extraction parameter is an indication function value representing the corresponding duration of the target user's sleep state. The calculation method for the target state feature is as follows:

[0074] s total =∑ j Δt j *δ(s j =Sleep)

[0075] Among them, the S total For the target state characteristics, Δt j For the second vital sign data, δ(s) j =Sleep) is the target state for parameter extraction.

[0076] Optionally, after acquiring the heart rate and target state characteristics, the information processing device determines the first vital sign information based on these characteristics. That is, the information processing device determines the heart rate and target state characteristics as the first vital sign information.

[0077] Optionally, in another embodiment, the vital sign data information further includes third vital sign data information representing the user's habitual bedtime data and fourth vital sign data information representing the user's habitual wake-up time data. The second vital sign feature information corresponding to the vital sign feature information is then determined based on the third and fourth vital sign data information.

[0078] Optionally, the information processing device stores first target data information representing the target user's ideal bedtime and second target data information representing the target user's ideal wake-up time. The information processing device calculates the bedtime deviation value between the target user's actual bedtime and ideal bedtime based on the third data information and the first target data information, and determines this bedtime deviation value as the first sleep-wake characteristic. That is, the information processing device calculates the absolute value of the difference between the third data information and the first target data information to obtain the first sleep-wake characteristic. Optionally, the calculation method of the first sleep-wake characteristic is as follows:

[0079]

[0080] Where, ΔT sleep The primary characteristic of daily routine, For third vital sign data information, t sleep This is the primary target data information.

[0081] Optionally, the information processing device further calculates the bedtime deviation value between the target user's actual wake-up time and ideal wake-up time based on the fourth data information and the second target data information, and determines the wake-up deviation value as the second sleep-wake characteristic. That is, the information processing device calculates the absolute value of the difference between the fourth data information and the second target data information to obtain the second sleep-wake characteristic. Optionally, the calculation method of the second sleep-wake characteristic is as follows:

[0082] ΔT wake =|T wake_actual -T wake |

[0083] Where, ΔT wake As the second sleep pattern, T wake_actual For the fourth vital sign data, T wake This is the second target data information.

[0084] Optionally, after acquiring the first and second sleep characteristics, the information processing device generates second vital sign information based on the first and second sleep characteristics, that is, the information processing device determines the first and second sleep characteristics as the second vital sign information.

[0085] 203. The target model is used to process the interaction feature information and the vital sign feature information to obtain the target processing result.

[0086] Optionally, after acquiring the interaction feature information and vital sign feature information, the information processing device uses the target model to evaluate and process the interaction feature information and vital sign feature information to obtain the target processing result.

[0087] Optionally, in one specific embodiment, the information processing device generates multimodal input information based on the interaction feature information and the vital sign feature information. That is, the information processing device fuses the acquired interaction feature information and vital sign feature information to obtain fused feature information, and uses the fused feature information and the input template information of the target model to generate multimodal input information that can be recognized and processed by the target model. The multimodal input information is a multimodal feature vector containing interaction feature information and vital sign feature information. The input template information is a vector template information indicating the vector arrangement of each modal feature information in the fused feature information (e.g., the position or sequence number of each modal feature information) to meet the information processing requirements of the target model.

[0088] Multimodal input information comprises data including at least two unimodal information sources. Furthermore, multimodal information is suitable for complex tasks requiring the integration of multiple information sources, such as sentiment analysis, robot interaction, and autonomous driving. By integrating information from multiple modalities, higher performance and accuracy can typically be achieved in these tasks.

[0089] Optionally, in one specific embodiment, the expression for the multimodal input information or input template information is as follows:

[0090] X = [U total U d U a HRV, HR avg S total ΔT sleep ΔT wake ]

[0091] Where X represents multimodal input information.

[0092] Optionally, after acquiring multimodal input information, the information processing device inputs the multimodal input information into the target model, uses the first data calculation model in the target model to evaluate the multimodal input information, obtains target evaluation data, and determines target processing information based on the target evaluation data and the target evaluation threshold used to characterize whether there is a risk of excessive use of smart devices by the user.

[0093] Optionally, the information processing device acquires the first model parameters and the first bias parameters of the target model, wherein the first model parameters are the model parameter vector obtained by training the target model.

[0094] The information processing device uses a first data calculation model in the target model to calculate and process the first model parameters, the first bias parameter, and the multimodal input information to obtain the initial evaluation parameters. It then uses the first data processing model to determine the target evaluation data based on the target activation data and the initial evaluation parameters. Specifically, the information processing device uses the first data calculation model in the target model to calculate the dot product of the first model parameters and the multimodal input information. It then determines the initial evaluation parameters based on the dot product of the first model parameters and the multimodal input information and the first bias parameter. Finally, it uses the first data processing model to normalize the initial evaluation parameters using the target activation data, mapping the initial evaluation parameters to the target value range to obtain the target evaluation data. Optionally, in a specific embodiment, the expression of the first data processing model is as follows:

[0095] R=σ(θ T X+b)

[0096] Where R represents the target evaluation data, θ represents the first model parameter, b represents the first bias parameter, X represents the multimodal input information, and σ represents the target activation data. In a specific embodiment, this...

[0097] Optionally, after the information processing device inputs the multimodal input information into the target model, it uses the target model to evaluate the usage status of the target object using the target interactive terminal based on the multimodal input information, thereby obtaining target evaluation data. This target evaluation data serves as an evaluation parameter characterizing the risk of overuse of the target terminal by the target object. The target value range for this target evaluation data is [0,1], where a higher value indicates a higher risk of overuse.

[0098] Optionally, the information processing device also pre-sets a usage risk rating to characterize whether there is a risk of overuse of the target interactive terminal by the target user. Each usage risk rating corresponds to a different target assessment threshold. After obtaining the target assessment data, the information processing device determines the target risk rating corresponding to the target assessment data by comparing the target assessment data with the target assessment threshold, and obtains the terminal intervention interaction information corresponding to the target risk rating, and determines the terminal intervention interaction information as the target processing result.

[0099] Optionally, in one specific embodiment, the risk rating includes using a low-risk rating, using a medium-risk rating, and using a high-risk rating.

[0100] Optionally, in one specific embodiment, the information processing device determines the target assessment threshold corresponding to the low-risk rating as the first assessment threshold. When the target assessment data is lower than the first assessment threshold, the information processing device determines that the target risk rating corresponding to the target assessment data is to use the low-risk rating, and determines that the target processing result is a result that does not require intervention.

[0101] Optionally, in one specific embodiment, the information processing device determines the target assessment threshold corresponding to the in-use risk rating as a first assessment threshold and a second assessment threshold. That is, when the target assessment data is greater than or equal to the first assessment threshold and less than the second assessment threshold, the information processing device determines the target risk rating corresponding to the target assessment data as an in-use risk rating, and determines the target processing result as the terminal intervention interaction information corresponding to the in-use risk rating: reminding the target user to take a proper rest and suspend the use of the target interactive terminal or other smart terminal in the form of pop-ups, notifications, etc.

[0102] Optionally, in another specific embodiment, the information processing device determines the target assessment threshold corresponding to the risk rating in use as the second assessment threshold. That is, when the target assessment data is greater than or equal to the second assessment threshold, the information processing device determines the target risk rating corresponding to the target assessment data as a high-risk rating for use, and determines the target processing result as the terminal intervention interaction information corresponding to the high-risk rating for use: that is, providing suggestions to assist the user in recovery or rest and temporarily restricting the user's access to certain applications.

[0103] Optionally, in other embodiments, the information processing device may also set other usage risk ratings and intervention interaction information corresponding to the usage risk ratings.

[0104] Optionally, in other embodiments, before processing the interaction information and the vital sign data using the target model to obtain the target processing result, the information processing device also acquires an initial model and multimodal training data for training the initial model. The multimodal training data includes interaction feature information samples carrying first training label data and multimodal feature vector samples carrying second training label data and vital sign feature information.

[0105] Optionally, after acquiring the initial model and multimodal training data, the information processing device uses the multimodal training data and the corresponding training label data to train the initial model to obtain the target model.

[0106] Optionally, the information processing device uses the target model to evaluate and train the multimodal training data to obtain training evaluation data, and determines the initial model parameters of the initial model based on the training evaluation data, training label data, and a preset target loss function, wherein the expression of the target loss function is as follows:

[0107]

[0108] Where L(θ, b) is the target loss function, y k For training labeled data (whether it is overused, 1 indicates overuse, 0 indicates normal), R k The data is for training and evaluation, where m is the total number of samples.

[0109] Optionally, after determining the initial model parameters, the information processing device further adjusts the initial model parameters using the target optimization unit and the initial model parameters. Specifically, the information processing device updates the initial model parameters using the target optimization unit and the learning rate parameter of the initial model to obtain the target model parameters, and then adjusts the initial model using these target model parameters to obtain the trained target model. The target optimization unit can be a gradient descent unit or a variant module of the Adam optimizer, etc. The update method for the target model parameters is as follows:

[0110]

[0111] Where α is the learning rate parameter of the initial model.

[0112] Optionally, the information processing device also periodically updates the multimodal training data and updates the model parameters of the target model based on the updated multimodal training data, so that the target model can better adapt to changes in user habits. Furthermore, it adjusts the target evaluation threshold and the corresponding usage risk rating based on user feedback and model implementation effects to improve the model recognition accuracy.

[0113] In this embodiment, the information processing device acquires interactive information to be processed and corresponding vital sign data. It then processes the interactive information and vital sign data using a target model to obtain a target processing result. This is achieved by collecting the user's interactive information to be processed and vital sign data representing the user's physiological and sleep-wake cycles when the user uses the target terminal. The device extracts the interactive feature information of the interactive information to be processed and the corresponding vital sign feature information, respectively. The target model then uses these interactive feature information and vital sign feature information to evaluate the user's interaction process from multiple dimensions, determining whether the user is overusing the target terminal. Based on the evaluation results, a target processing result is generated, and intervention or reminders are given to the user regarding their use of the target terminal. This reduces the negative impact of excessive use of electronic products on user health and improves the effectiveness of interactive intervention.

[0114] To better implement the information processing method in the embodiments of this application, an information processing system is also provided in the embodiments of this application, such as... Figure 3 As shown, Figure 3 This is a schematic diagram of the structure of the information processing system provided in the embodiments of this application. Specifically, the information processing system 300 includes:

[0115] The information acquisition module 301 is configured to acquire interactive information to be processed and vital sign data information;

[0116] The feature extraction module 302 is configured to extract features from the interaction information to be processed and the vital sign data information to obtain interaction feature information and vital sign feature information.

[0117] The information processing module 303 is configured to process the interaction feature information and the vital sign feature information using the target model to obtain the target processing result.

[0118] In one possible implementation of this embodiment, the information processing system performs feature extraction on the interaction information to be processed and the vital sign data information to obtain interaction feature information and vital sign feature information, including:

[0119] The first interaction information feature is determined based on the first interaction processing information and the first feature extraction parameters;

[0120] The second interaction information feature is determined based on the second interaction processing information and the second feature extraction parameters;

[0121] Interaction feature information is determined based on the first interaction information feature and the second interaction information feature.

[0122] In one possible implementation of this embodiment, the heart rate vital sign features in the information processing system are obtained by calculating and processing the first vital sign data information and the first statistical data information using a feature calculation model;

[0123] The feature calculation model is as follows:

[0124]

[0125] HRV refers to heart rate characteristics, HR j For primary vital sign data, HR avg This is the primary statistical data.

[0126] In one possible implementation of this embodiment, the vital sign data information in the information processing system further includes third vital sign data information and fourth vital sign data information, and the vital sign feature information includes second vital sign feature information;

[0127] The step of extracting features from the interaction information to be processed and the vital sign data to obtain interaction feature information and vital sign feature information includes:

[0128] Calculate the absolute value of the difference between the third vital sign data and the first target data to obtain the first commutation characteristic;

[0129] The absolute value of the difference between the fourth vital sign data and the second target data is calculated to obtain the second commutation and respiration characteristics;

[0130] The second vital sign information is generated based on the first and second sleep patterns.

[0131] In one possible implementation of this embodiment, the information processing system uses the target model to process the interaction feature information and the vital sign feature information to obtain the target processing result, including:

[0132] Multimodal input information is generated based on the interaction feature information and the vital sign feature information;

[0133] The multimodal input information is processed using the target model to obtain target processing information.

[0134] In one possible implementation of this embodiment, the information processing system generates multimodal input information based on the interaction feature information and the vital sign feature information, including:

[0135] The interaction feature information and the vital sign feature information are fused to obtain fused feature information;

[0136] The multimodal input information of the target model is generated using the fused feature information and the input template information of the target model.

[0137] In one possible implementation of this embodiment, the information processing system uses the target model to process the multimodal input information to obtain target processing information, including:

[0138] The multimodal input information is evaluated using the first data calculation model in the target model to obtain target evaluation data;

[0139] Based on the target evaluation data and target evaluation threshold, target processing information is obtained.

[0140] In one possible implementation of this embodiment, the information processing system uses a first data calculation model in the target model to evaluate the multimodal input information to obtain target evaluation data, including:

[0141] The first data calculation model is used to calculate and process the multimodal input information, the first model parameters, and the first bias parameters to obtain the initial evaluation parameters;

[0142] The target evaluation data is determined using the first data calculation model based on the target activation data and the initial evaluation parameters.

[0143] In one possible implementation of this embodiment, the target evaluation data in the information processing system is calculated by the first data calculation model according to the target activation function and the initial evaluation parameters;

[0144] The first data calculation model is as follows:

[0145] R=σ(θ T X+b)

[0146] Where R represents the target evaluation data, θ represents the first model parameters, b represents the first bias parameter, X represents the multimodal input information, σ represents the target activation data, and θ T X+b is the initial evaluation parameter corresponding to the multimodal input information.

[0147] In one possible implementation of this embodiment, the target processing result in the information processing system is the terminal intervention interaction information corresponding to the target evaluation threshold;

[0148] After processing the interaction information to be processed and the vital sign data information using the target model to obtain the target processing result, the method further includes:

[0149] The terminal intervention interaction information is output to the target interactive terminal to obtain the terminal intervention result.

[0150] In this embodiment, the information processing system acquires interactive information to be processed and corresponding vital sign data. It then processes this interactive information and the corresponding vital sign data using a target model to obtain a target processing result. This is achieved by collecting the user's interactive information to be processed and vital sign data representing the user's physiological and sleep-wake cycles when the user uses the target terminal. The system extracts the interactive feature information from the interactive information to be processed and the corresponding vital sign feature information from the vital sign data. The target model then uses these interactive feature information and vital sign feature information to evaluate the user's interaction process from multiple dimensions, determining whether the user is overusing the target terminal. Based on the evaluation results, a target processing result is generated, and intervention or reminders are given to the user regarding their use of the target terminal. This reduces the negative impact of excessive electronic product use on user health and improves the effectiveness of interactive intervention.

[0151] This invention also provides an information processing device, such as... Figure 4 As shown, Figure 4 This is a schematic diagram of an embodiment of the information processing device provided in this application.

[0152] The information processing device integrates any of the information processing systems provided in the embodiments of the present invention, and the information processing device includes:

[0153] One or more processors;

[0154] Memory; and

[0155] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor of the steps in the information processing method described in any of the embodiments of the above information processing method.

[0156] Specifically, an information processing device may include components such as a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will understand that... Figure 4 The information processing device structure shown does not constitute a limitation on the information processing device. It may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0157] The processor 401 is the control center of the information processing device. It connects various parts of the device via various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in the memory 402, and by calling data stored in the memory 402, thereby providing overall monitoring of the information processing device. Optionally, the processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 401.

[0158] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, video playback function, etc.), etc.; the data storage area may store data created according to the use of the information processing device, etc. In addition, the memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0159] The information processing device also includes a power supply 403 that supplies power to the various components. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 403 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0160] The information processing device may also include an input unit 404, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0161] Although not shown, the information processing device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 401 in the information processing device loads the executable files corresponding to the processes of one or more application programs into the memory 402 according to the following instructions, and the processor 401 runs the application programs stored in the memory 402 to realize various functions, as follows:

[0162] Acquire the interaction information to be processed, and the corresponding vital sign data information;

[0163] The target model is used to process the interaction information to be processed and the vital sign data information to obtain the target processing result.

[0164] Therefore, embodiments of the present invention provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, etc. A computer program is stored thereon, which is loaded by a processor to execute the steps of any of the information processing methods provided in the embodiments of the present invention. For example, the computer program loaded by the processor can execute the following steps:

[0165] Acquire the interaction information to be processed, and the corresponding vital sign data information;

[0166] The target model is used to process the interaction information to be processed and the vital sign data information to obtain the target processing result.

[0167] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the detailed descriptions of other embodiments above, which will not be repeated here.

[0168] In practice, each of the above units or structures can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units or structures, please refer to the previous method embodiments, which will not be repeated here.

[0169] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0170] The above provides a detailed description of an information processing method provided by the embodiments of this application. Specific embodiments have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method, characterized in that, The method includes: Acquire the interaction information and vital sign data to be processed; Feature extraction is performed on the interaction information to be processed and the vital sign data information to obtain interaction feature information and vital sign feature information; The interaction feature information and the vital sign feature information are processed using the target model to obtain the target processing result.

2. The method according to claim 1, characterized in that, The interaction information to be processed includes first interaction processing information and second interaction processing information; The step of extracting features from the interaction information to be processed and the vital sign data to obtain interaction feature information and vital sign feature information includes: The first interaction information feature is determined based on the first interaction processing information and the first feature extraction parameters; The second interaction information feature is determined based on the second interaction processing information and the second feature extraction parameters; Interaction feature information is determined based on the first interaction information feature and the second interaction information feature.

3. The method according to claim 1, characterized in that, The vital signs data information includes first vital signs data information and second vital signs data information, and the vital signs feature information includes first vital signs feature information; The step of extracting features from the interaction information to be processed and the vital sign data to obtain interaction feature information and vital sign feature information includes: Calculate the average value corresponding to the first vital sign data to obtain the first statistical data information; Based on the first vital sign data and the first statistical data, calculations are performed to obtain heart rate vital sign characteristics; The target state extraction parameters and the second vital sign data information are calculated and processed to obtain the target state features; The first vital sign information is determined based on the heart rate characteristics and the target state characteristics.

4. The method according to claim 3, characterized in that, The heart rate vital signs characteristics are obtained by calculating and processing the first vital sign data information and the first statistical data information through a feature calculation model; The feature calculation model is as follows: HRV refers to heart rate characteristics, HR j For primary vital sign data, HR avg This is the primary statistical data.

5. The method according to claim 1, characterized in that, The vital signs data information also includes third vital signs data information and fourth vital signs data information, and the vital signs feature information includes second vital signs feature information; The step of extracting features from the interaction information to be processed and the vital sign data to obtain interaction feature information and vital sign feature information includes: Calculate the absolute value of the difference between the third vital sign data and the first target data to obtain the first commutation characteristic; The absolute value of the difference between the fourth vital sign data and the second target data is calculated to obtain the second commutation and respiration characteristics; The second vital sign information is generated based on the first and second sleep patterns.

6. The method according to claim 1, characterized in that, The process of using the target model to process the interaction feature information and the vital sign feature information to obtain the target processing result includes: Multimodal input information is generated based on the interaction feature information and the vital sign feature information; The multimodal input information is processed using the target model to obtain target processing information.

7. The method according to claim 6, characterized in that, The step of generating multimodal input information based on the interaction feature information and the vital sign feature information includes: The interaction feature information and the vital sign feature information are fused to obtain fused feature information; The multimodal input information of the target model is generated using the fused feature information and the input template information of the target model.

8. The method according to claim 6, characterized in that, The process of using the target model to process the multimodal input information to obtain target processing information includes: The multimodal input information is evaluated using the first data calculation model in the target model to obtain target evaluation data; Based on the target evaluation data and target evaluation threshold, target processing information is obtained.

9. The method according to claim 8, characterized in that, The step of evaluating the multimodal input information using the first data calculation model in the target model to obtain target evaluation data includes: The first data calculation model is used to calculate and process the multimodal input information, the first model parameters, and the first bias parameters to obtain the initial evaluation parameters; The target evaluation data is determined using the first data calculation model based on the target activation data and the initial evaluation parameters.

10. The method according to claim 9, characterized in that, The target evaluation data is calculated by the first data calculation model according to the target activation function and the initial evaluation parameters; The first data calculation model is as follows: R=σ(θ T X+b) Where R represents the target evaluation data, θ represents the first model parameters, b represents the first bias parameter, X represents the multimodal input information, σ represents the target activation data, and θ T X+b is the initial evaluation parameter corresponding to the multimodal input information.

11. The method according to any one of claims 1-10, characterized in that, The interaction information to be processed includes first interaction processing information representing the usage time of a specified device, and / or second interaction processing information representing the usage time of a specified application; the first interaction processing information includes mobile phone usage time, and / or, tablet usage time, and / or, TV usage time, and / or, computer usage time, and / or, projector usage time, and / or, virtual device usage time, and / or, smart wearable device usage time; the second interaction processing information includes game application usage time, and / or, video application usage time, and / or, live streaming application usage time, and / or, social application usage time, and / or, educational application usage time, and / or, browser application usage time; The vital signs data information includes first vital signs data information representing various physiological indicators of the user when using each target interactive terminal, and / or second vital signs data information representing the user's daily routines; the first vital signs data information includes heart rate physiological indicators, and / or sleep duration indicators, and / or body temperature vital signs data, and / or heart rate variability data, and / or stress vital signs data, and / or respiratory vital signs data; the second vital signs data information includes wake-up habit data, and / or bedtime habit data, and / or nap habit data, and / or work habit data, and / or meal habit data; The target processing result is the terminal intervention interaction information corresponding to the target evaluation threshold; After processing the interaction information to be processed and the vital sign data information using the target model to obtain the target processing result, the method further includes: The terminal intervention interaction information is output to the target interactive terminal to obtain the terminal intervention result.

12. A system, characterized in that, The system includes: The information acquisition module is configured to acquire interactive information and vital sign data to be processed. The feature extraction module is configured to extract features from the interaction information to be processed and the vital sign data information to obtain interaction feature information and vital sign feature information. The information processing module is configured to process the interaction feature information and the vital sign feature information using the target model to obtain the target processing result; Optionally, the interaction information to be processed includes first interaction processing information and second interaction processing information; the feature extraction module performs feature extraction on the interaction information to be processed and the vital sign data information to obtain interaction feature information and vital sign feature information, including: The first interaction information feature is determined based on the first interaction processing information and the first feature extraction parameters; The second interaction information feature is determined based on the second interaction processing information and the second feature extraction parameters; Interaction feature information is determined based on the first interaction information feature and the second interaction information feature; Optionally, the vital sign data information includes first vital sign data information and second vital sign data information, and the vital sign feature information includes first vital sign feature information; The feature extraction module extracts features from the interaction information to be processed and the vital sign data to obtain interaction feature information and vital sign feature information, including: Calculate the average value corresponding to the first vital sign data to obtain the first statistical data information; Based on the first vital sign data and the first statistical data, calculations are performed to obtain heart rate vital sign characteristics; The target state extraction parameters and the second vital sign data information are calculated and processed to obtain the target state features; The first vital sign information is determined based on the heart rate characteristics and the target state characteristics; Optionally, the heart rate vital sign features in the feature extraction module are obtained by calculating and processing the first vital sign data information and the first statistical data information through a feature calculation model; The feature calculation model is as follows: HRV refers to heart rate characteristics, HR j For primary vital sign data, HR avg This is the primary statistical data information; Optionally, the vital sign data information further includes third vital sign data information and fourth vital sign data information, and the vital sign feature information includes second vital sign feature information; The feature extraction module extracts features from the interaction information to be processed and the vital sign data information to obtain interaction feature information and vital sign feature information, including: Calculate the absolute value of the difference between the third vital sign data and the first target data to obtain the first commutation characteristic; The absolute value of the difference between the fourth vital sign data and the second target data is calculated to obtain the second commutation and respiration characteristics; The second vital sign information is generated based on the first and second sleep patterns; Optionally, the information processing module uses the target model to process the interaction feature information and the vital sign feature information to obtain the target processing result, including: Multimodal input information is generated based on the interaction feature information and the vital sign feature information; The multimodal input information is processed using the target model to obtain target processing information; Optionally, the information processing module generates multimodal input information based on the interaction feature information and the vital sign feature information, including: The interaction feature information and the vital sign feature information are fused to obtain fused feature information; The multimodal input information of the target model is generated using the fused feature information and the input template information of the target model; Optionally, the information processing module uses the target model to process the multimodal input information to obtain target processing information, including: The multimodal input information is evaluated using the first data calculation model in the target model to obtain target evaluation data; Based on the target evaluation data and target evaluation threshold, target processing information is obtained; Optionally, the information processing module uses the first data calculation model in the target model to evaluate the multimodal input information to obtain target evaluation data, including: The first data calculation model is used to calculate and process the multimodal input information, the first model parameters, and the first bias parameters to obtain the initial evaluation parameters; The target evaluation data is determined using the first data calculation model based on the target activation data and the initial evaluation parameters; Optionally, the target evaluation data is calculated by the information processing module using the first data calculation model according to the target activation function and the initial evaluation parameters; The first data calculation model is as follows: R=σ(θ T X+b) Where R represents the target evaluation data, θ represents the first model parameters, b represents the first bias parameter, X represents the multimodal input information, σ represents the target activation data, and θ T X+b is the initial evaluation parameter corresponding to the multimodal input information; Optionally, the interaction information to be processed includes first interaction processing information representing the usage time of a specified device, and / or second interaction processing information representing the usage time of a specified application; the first interaction processing information includes mobile phone usage time, and / or tablet usage time, and / or television usage time, and / or computer usage time, and / or projector usage time, and / or virtual device usage time, and / or smart wearable device usage time; the second interaction processing information includes game application usage time, and / or video application usage time, and / or live streaming application usage time, and / or social application usage time, and / or educational application usage time, and / or browser application usage time; The vital signs data information includes first vital signs data information representing various physiological indicators of the user when using each target interactive terminal, and / or second vital signs data information representing the user's daily routines; the first vital signs data information includes heart rate physiological indicators, and / or sleep duration indicators, and / or body temperature vital signs data, and / or heart rate variability data, and / or stress vital signs data, and / or respiratory vital signs data; the second vital signs data information includes wake-up habit data, and / or bedtime habit data, and / or nap habit data, and / or work habit data, and / or meal habit data; The target processing result is the terminal intervention interaction information corresponding to the target evaluation threshold; After processing the interaction information to be processed and the vital sign data information using the target model to obtain the target processing result, the method further includes: The terminal intervention interaction information is output to the target interactive terminal to obtain the terminal intervention result.

13. A device, characterized in that, The term includes: One or more processors; Memory; as well as One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the steps of the method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, It stores a computer program, which is loaded by a processor to perform the steps of the method according to any one of claims 1 to 11.

Images