CN-121971091-A - Multi-equipment concurrency emotion screening intelligent chip and terminal

CN121971091ACN 121971091 ACN121971091 ACN 121971091ACN-121971091-A

Abstract

The invention discloses an intelligent chip and a terminal for multi-equipment concurrent emotion screening, which relate to the technical field of emotion screening and comprise a sign parameter acquisition module, a data validity analysis module, a validity threshold acquisition module, an acquisition frequency correction module and an acquisition frequency optimization module, wherein the sign parameter acquisition module is used for acquiring multi-source sign parameters, the data validity analysis module is used for carrying out consistency analysis on the multi-source sign parameters to acquire data validity parameters, the validity threshold acquisition module is used for acquiring a validity threshold, the acquisition frequency correction module is used for acquiring correction acquisition frequency to acquire updated sign parameters when the data validity parameters are smaller than the validity threshold, emotion recognition is carried out, and the acquisition frequency optimization module is used for carrying out emotion recognition on the multi-source sign parameters and optimizing the acquisition frequency to acquire efficiency acquisition frequency and carry out multi-source sign parameter acquisition. The method solves the technical problem that the emotion screening data acquisition strategy in the prior art cannot be adapted to the actual scene.

Inventors

YAN ZHENGHANG
ZHANG WEN
ZHAO JIAN

Assignees

北京讯众通信技术股份有限公司

Dates

Publication Date: 20260505
Application Date: 20260324

Claims (10)

1. A multi-device concurrent emotion screening smart chip, comprising: the sign parameter acquisition module is used for acquiring multi-source sign parameters based on the multi-source emotion perception equipment; The data validity analysis module is used for carrying out consistency analysis on the multi-source sign parameters to obtain data validity parameters; the effectiveness threshold acquisition module is used for acquiring the effectiveness threshold based on the multi-source sign parameters of the users in the same scene in the current scene; the acquisition frequency correction module is used for correcting the acquisition frequency based on the data validity parameter when the data validity parameter is smaller than the validity threshold value, acquiring corrected acquisition frequency for data acquisition, acquiring updated sign parameter and carrying out emotion recognition; And the acquisition frequency optimization module is used for carrying out emotion recognition on the multi-source sign parameters when the data validity parameters are larger than or equal to the validity threshold value, optimizing the acquisition frequency based on the emotion recognition results of the current user and the emotion recognition result sets of a plurality of users in the current scene, acquiring the efficiency acquisition frequency and acquiring the multi-source sign parameters.
2. The multi-device concurrent emotion screening smart chip of claim 1, wherein obtaining multi-source sign parameters based on multi-source emotion sensing devices comprises: Respectively acquiring heart rate parameters and RRI parameters through multisource emotion sensing equipment, wherein the heart rate parameters are heart beating times in unit time, and the RRI parameters are time interval sequences of two continuous heartbeats; Collecting activity parameters by a motion sensor of the multi-source emotion sensing equipment, wherein the activity parameters are acceleration average values of human body limb motions in unit time; And performing time stamp synchronous binding on the collected heart rate parameter, the RRI parameter and the activity parameter, and integrating to form the multi-source sign parameter.
3. The multi-device concurrency emotion screening smart chip of claim 1, wherein performing a consistency analysis on the multi-source sign parameters to obtain data validity parameters comprises: Carrying out relevance calculation on heart rate parameters and RRI parameters in the multisource sign parameters to obtain sign relevance; Analyzing and calculating based on the heart rate parameters to obtain heart rate stability coefficients; Calculating the deviation degree of the heart rate stability coefficient and the activity parameter, and obtaining a behavior consistency parameter; subtracting the behavior consistency parameter from the calculation 1 to obtain a behavior validity parameter; And carrying out weighted calculation on the sign association degree and the behavior validity parameter to obtain a data validity parameter.
4. The multi-device concurrency emotion screening smart chip of claim 1, wherein obtaining the validity threshold based on multi-source sign parameters of a user of the same scene as the current scene comprises: acquiring multi-source sign parameters of all users in the same scene in the current scene to form a scene data validity parameter set; Calculating an arithmetic average value of the scene data validity parameter set to obtain a scene validity average value; Calculating the variation coefficient of the scene data validity parameter set to obtain scene validity dispersion; and carrying out weighted operation based on the scene effectiveness mean value and the scene effectiveness dispersion to obtain an effectiveness threshold.
5. The multi-device concurrency emotion screening smart chip of claim 1, wherein when the data validity parameter is less than a validity threshold, performing acquisition frequency correction based on the data validity parameter, acquiring corrected acquisition frequency for data acquisition, acquiring updated sign parameters, performing emotion recognition, comprising: when the data validity parameter is smaller than a validity threshold, judging an invalid reason, and acquiring the invalid reason; Acquiring a frequency correction coefficient based on the invalid reason; multiplying the current acquisition frequency by 1 plus a frequency correction coefficient to obtain a corrected acquisition frequency; Acquiring data by adopting the corrected acquisition frequency, acquiring updated sign parameters, and continuing consistency analysis and iterative updating until the data validity parameters are greater than or equal to the validity threshold; inputting the updated sign parameters into an emotion recognition analyzer to obtain emotion recognition results.
6. The multi-device concurrency emotion screening smart chip of claim 5, wherein when the data validity parameter is less than a validity threshold, making an invalidation reason decision to obtain an invalidation reason comprises: when the data validity parameter is smaller than a validity threshold value, judging an invalid reason; if the sign association degree is lower than the sign association threshold and the behavior validity parameter is lower than the behavior validity threshold, judging that the invalid cause is abnormal in association with the collection of the heart rate and the RRI parameter, and weighting and calculating the waveform peak deviation rate and the RRI peak deletion rate of the heart rate parameter to obtain a waveform abnormality correction coefficient; If the behavior validity parameter is greater than or equal to a behavior validity threshold and the sign association degree is greater than or equal to a sign association threshold, judging that the invalid cause is abnormal matching of the behavior and the heart rate characteristics, calculating the ratio of the signal fluctuation coefficient of the heart rate parameter to the activity signal fluctuation coefficient, and obtaining a matching abnormality correction coefficient; If the sign association degree is lower than a sign association threshold and the behavior validity parameter is greater than or equal to a behavior validity threshold, judging that the invalid cause is associated matching double abnormality, and weighting and calculating the waveform abnormality correction coefficient and the matching abnormality correction coefficient to obtain a double abnormality correction coefficient; and taking the abnormal correction coefficient corresponding to the invalid reason as a frequency correction coefficient.
7. The multi-device concurrency emotion screening smart chip of claim 6, wherein the construction of the emotion recognition analyzer comprises: acquiring sample multisource sign parameters and corresponding emotion labels as a sample training set; Constructing an emotion recognition analyzer based on the neural network; And training the emotion recognition analyzer by adopting the sample training set until convergence, and obtaining the trained emotion recognition analyzer.
8. The multi-device concurrency emotion screening intelligent chip of claim 1, wherein when the data validity parameter is greater than or equal to a validity threshold, performing emotion recognition on the multi-source sign parameter, and optimizing the collection frequency based on the emotion recognition result of the current user and the emotion recognition result set of a plurality of users in the current scene, obtaining an efficient collection frequency, and performing multi-source sign parameter acquisition, including: inputting the multi-source sign parameters into an emotion recognition analyzer when the data validity parameters are larger than or equal to a validity threshold value, and obtaining emotion recognition results; Acquiring efficiency optimization parameters based on the emotion recognition result; and multiplying the efficiency optimization coefficient by the acquisition frequency to acquire the efficiency acquisition frequency, and acquiring the multisource sign parameters.
9. The multi-device concurrency emotion screening smart chip of claim 8, wherein obtaining efficiency optimization parameters based on the emotion recognition results comprises: Acquiring emotion classification corresponding to emotion recognition results of the current user; carrying out emotion recognition on a plurality of users in the same scene, obtaining an emotion recognition result set, and carrying out emotion classification to obtain group emotion portraits; Acquiring a group efficiency optimization coefficient based on the group emotion portraits; Acquiring a user efficiency optimization coefficient based on the emotion classification of the current user; And carrying out weighted calculation on the group efficiency optimization coefficient and the user efficiency optimization coefficient to obtain an efficiency optimization coefficient.
10. A multi-device concurrent emotion screening terminal, comprising: a multi-device concurrency emotion screening smart chip as claimed in any one of claims 1 to 9.

Description

Multi-equipment concurrency emotion screening intelligent chip and terminal Technical Field The invention relates to the technical field of emotion screening, in particular to a multi-equipment concurrent emotion screening intelligent chip and a terminal. Background In existing emotion screening techniques, user sign data is typically acquired by means of a single type of physiological sensor or a fixed acquisition frequency device. The method often adopts a static acquisition strategy, namely, all users sample data according to preset uniform frequency, so that dynamic changes of the quality of the sign signals of different users and different scenes are ignored, and self-adaptive balance is difficult to realize between data validity and acquisition efficiency improvement. Disclosure of Invention The application provides a multi-equipment concurrent emotion screening intelligent chip and a terminal, which are used for solving the technical problem that in the prior art, data quality and collection efficiency cannot be dynamically adapted due to fixed emotion screening data collection strategies. In view of the above, the application provides a multi-device concurrent emotion screening intelligent chip and a terminal. In a first aspect, the present application provides a multi-device concurrency emotion screening smart chip, the smart chip comprising: the sign parameter acquisition module is used for acquiring multi-source sign parameters based on the multi-source emotion perception equipment; The data validity analysis module is used for carrying out consistency analysis on the multi-source sign parameters to obtain data validity parameters; the effectiveness threshold acquisition module is used for acquiring the effectiveness threshold based on the multi-source sign parameters of the users in the same scene in the current scene; the acquisition frequency correction module is used for correcting the acquisition frequency based on the data validity parameter when the data validity parameter is smaller than the validity threshold value, acquiring corrected acquisition frequency for data acquisition, acquiring updated sign parameter and carrying out emotion recognition; And the acquisition frequency optimization module is used for carrying out emotion recognition on the multi-source sign parameters when the data validity parameters are larger than or equal to the validity threshold value, optimizing the acquisition frequency based on the emotion recognition results of the current user and the emotion recognition result sets of a plurality of users in the current scene, acquiring the efficiency acquisition frequency and acquiring the multi-source sign parameters. In a second aspect, the present application provides a multi-device concurrent emotion screening terminal, including: a multi-device concurrency emotion screening smart chip as in the first aspect. One or more technical schemes provided by the application have at least the following technical effects or advantages: The application provides a multi-equipment concurrent emotion screening intelligent chip and a terminal, which are used for acquiring data validity parameters by carrying out consistency analysis on multi-source sign parameters in real time, dynamically setting validity thresholds by combining the sign data of a plurality of users in a current scene, and then adaptively adjusting acquisition frequencies according to comparison results of the data validity parameters and the thresholds, wherein frequency correction is carried out to improve acquisition quality when the data validity is insufficient, and frequency optimization is carried out by combining emotion recognition results of individuals and groups to reduce acquisition expenditure when the data validity reaches the standard, so that dynamic balance of data quality guarantee and acquisition efficiency is realized. Compared with the traditional method, the technical scheme provided by the application remarkably improves the self-adaptive capacity of the acquisition of the physical sign data under the concurrent scene of multiple devices, can flexibly switch the correction mode and the optimization mode according to the signal quality fluctuation of different users and the distribution characteristics of group data in the scene, and effectively avoids the fluctuation of the data effectiveness and the resource waste caused by a fixed acquisition strategy. The application achieves the technical effects of taking the reliability of data acquisition, the accuracy of emotion recognition and the energy efficiency of operation into consideration in the multi-source emotion perception process. Drawings In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of th