CN117330850B

CN117330850B - Radiation detection method, system, equipment and medium for intelligent mobile terminal

Info

Publication number: CN117330850B
Application number: CN202311632844.3A
Authority: CN
Inventors: 王蓉
Original assignee: Unilab Shanghai Co ltd
Current assignee: Unilab Shanghai Co ltd
Priority date: 2023-12-01
Filing date: 2023-12-01
Publication date: 2024-03-15
Anticipated expiration: 2043-12-01
Also published as: CN117330850A

Abstract

The invention relates to the technical field of electromagnetic radiation detection, and discloses a radiation detection method, a radiation detection system, radiation detection equipment and radiation detection media for an intelligent mobile terminal, wherein the radiation detection method, the radiation detection system, the radiation detection equipment and the radiation detection media comprise the following steps of: measuring an electromagnetic radiation initial value and acquiring shielding coefficient characteristic data; step 2: determining a radiation shielding factor based on the shielding factor characteristic data and the second machine learning model; step 3: acquiring radiation correction characteristic data, and correcting an electromagnetic radiation initial value based on the radiation correction characteristic data, a radiation shielding coefficient and a first machine learning model to obtain an electromagnetic radiation correction value; step 4: screening a target correction value, and comparing and analyzing the target correction value to obtain a comparison and analysis result; step 5: repeating the steps to obtain comparison and analysis results of all the sampling inspection terminals; step 6: the quality alarm grade under the lottery batch is determined according to the comparison and analysis results of all the lottery terminals, and the invention is beneficial to avoiding large-scale reworking of the intelligent mobile terminal.

Description

Radiation detection method, system, equipment and medium for intelligent mobile terminal

Technical Field

The present invention relates to the field of electromagnetic radiation detection technology, and more particularly, to a radiation detection method, system, device, and medium for an intelligent mobile terminal.

Background

Currently, an intelligent mobile terminal performs electromagnetic compatibility (EMC) detection and electromagnetic radiation (EMR) detection before production and delivery; electromagnetic radiation refers to the propagation of electromagnetic waves, including radiation generated by wireless communication devices, electronic devices, and power systems, such as radio waves, microwaves, radio frequency radiation, and the like; these electromagnetic emissions may in some cases have an adverse effect on human health and may also interfere with the proper functioning of other electronic devices or with the stability of the communication system; the intelligent mobile terminal is beneficial to finding out the intelligent mobile terminal with exceeding radiation by detecting the electromagnetic radiation, and can be subjected to targeted electromagnetic radiation inhibition (a technology or method for reducing or limiting the electromagnetic radiation intensity of the mobile terminal equipment, which aims at reducing the generation or propagation of the electromagnetic radiation so as to reduce the potential harm and interference to human bodies, electronic equipment or communication systems), thereby ensuring that the intelligent mobile terminal meets the electromagnetic radiation regulation standards of different countries and regions and ensuring the use safety of users.

At present, the existing radiation detection method for the intelligent mobile terminal is mostly realized by manually utilizing an electromagnetic radiation monitor; although some other related technologies exist, for example, chinese patent with the publication number CN107449973B discloses a method, apparatus and terminal for detecting electromagnetic radiation of a terminal, and further, for example, chinese patent with the publication number CN111060752a discloses a method, a control terminal, a device and a readable storage medium for detecting electromagnetic radiation of a terminal, the method can be applied to electromagnetic radiation detection of a part of terminals, but research and practical application of the method and the related technologies find that the method and the related technologies have at least the following part of defects:

(1) The detection period is longer, the electromagnetic radiation detection efficiency is lower, the degree of automation is low, and the method is not suitable for the production scene of large-scale intelligent mobile terminals;

(2) The detection environment is relatively stable, the consideration of interference to external factors is lacking, the radiation measurement result of the intelligent mobile terminal cannot be corrected, and the condition that the radiation exceeds standard is easily generated after the intelligent mobile terminal leaves the factory is easily caused;

(3) The intelligent mobile terminal can not be timely produced and warned based on the electromagnetic radiation correction result, and large-scale reworking of the intelligent mobile terminal is easy to occur.

Disclosure of Invention

In order to overcome the above-mentioned drawbacks of the prior art, embodiments of the present invention provide a radiation detection method, system, device and medium for an intelligent mobile terminal.

In order to achieve the above purpose, the present invention provides the following technical solutions:

a radiation detection method for an intelligent mobile terminal, the method comprising:

step 1: under the lot of the lottery, electromagnetic radiation of the radio frequency module in the ith lottery terminal at different temperatures is measured to obtain M electromagnetic radiation initial values, shielding coefficient characteristic data of the ith lottery terminal are obtained, and i and M are positive integers larger than zero; the shielding coefficient characteristic data comprise a terminal model, a terminal shell material, a terminal shell thickness, a terminal shell conductivity and a terminal shell dielectric constant;

Step 2: determining a radiation shielding coefficient of an ith spot check terminal based on shielding coefficient characteristic data and a pre-constructed second machine learning model;

the generation logic of the radiation shielding coefficient is as follows:

acquiring electromagnetic radiation output power of a radio frequency module, electromagnetic radiation receiving power under the condition of no shell and electromagnetic radiation receiving power under the condition of the shell;

based on the electromagnetic radiation output power of the radio frequency module, the electromagnetic radiation receiving power under the condition of no shell and the electromagnetic radiation receiving power under the condition of the shell, carrying out formulated calculation to obtain a radiation shielding coefficient; the calculation formula is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein: />Represents the radiation shielding coefficient in decibels +.>Representing the electromagnetic radiation output power of the radio frequency module in watts +.>Representing the electromagnetic radiation receiving power in watts,/without a housing>Representing the electromagnetic radiation receiving power in watts with the housing;

step 3: acquiring radiation correction characteristic data, correcting each electromagnetic radiation initial value of the radio frequency module based on the radiation correction characteristic data, the radiation shielding coefficient of the ith sampling inspection terminal and a pre-constructed first machine learning model to obtain N electromagnetic radiation correction values, wherein N is a positive integer greater than zero; the radiation correction characteristic data comprise a terminal model, transmitting power, transmitting frequency, gain of a transmitting antenna and a transmitting frequency band; the pre-constructed first machine learning model is generated based on pre-acquired electromagnetic radiation test data in a training mode;

Step 4: screening target correction values in the N electromagnetic radiation correction values, and comparing and analyzing the target correction values to obtain comparison and analysis results of the ith sampling inspection terminal; the comparison and analysis result comprises that the electromagnetic radiation meets the standard and the electromagnetic radiation does not meet the standard;

step 5: repeating the steps 1 to 4 until i=Q, ending the cycle to obtain comparison analysis results of all the sampling terminals, wherein Q is a positive integer greater than zero;

step 6: and determining the quality alarm grade under the lottery batch according to the comparison and analysis results of all the lottery terminals, and carrying out production alarm according to the quality alarm grade.

Further, the generation logic of the pre-constructed second machine learning model is as follows: acquiring historical shielding coefficient sample data, wherein the historical shielding coefficient sample data comprises shielding coefficient characteristic data and corresponding radiation shielding coefficients thereof; dividing historical shielding coefficient sample data into a shielding coefficient training set and a shielding coefficient testing set; constructing a regression network model, taking shielding coefficient characteristic data in a shielding coefficient training set as input of the regression network model, taking a radiation shielding coefficient in the shielding coefficient training set as output of the regression network model, training the regression network model to obtain a second initial regression network model, taking the sum of minimized second prediction accuracy as a training target, carrying out model evaluation on the second initial regression network model by using a shielding coefficient test set, and taking the second initial regression network model when the sum of the second prediction accuracy reaches convergence as a pre-constructed second machine learning model; the calculation formula of the second prediction accuracy is as follows; Wherein->For each group of numbers of masking coefficient feature data, +.>For the second prediction accuracy, +.>Is->Predictive value of radiation shielding coefficient corresponding to group shielding coefficient characteristic data, < >>Is->Actual values of the radiation shielding coefficients corresponding to the group shielding coefficient characteristic data, wherein +.>、/>And->In decibels.

Further, pre-acquiring electromagnetic radiation test data includes:

step a1: placing R standard test terminals in a test batch under a set standard constant temperature test environment, and placing the standard test terminals under a temperature change test environment, wherein R is a positive integer greater than zero;

step a2: measuring a first electromagnetic radiation test value of an r-th standard test terminal under a set standard constant temperature test environment;

step a3: measuring a second electromagnetic radiation test value of the r standard test terminal at the j-th degree under a temperature change test environment, wherein r and j are positive integers larger than zero;

step a4: taking the difference value of the first electromagnetic radiation test value and the second electromagnetic radiation test value as an electromagnetic radiation deviation value, judging whether the electromagnetic radiation deviation value is in a preset electromagnetic radiation deviation value interval, if not, enabling j=j+c, and jumping back to the step a3, and if so, correlating the electromagnetic radiation deviation value with the j-th temperature to obtain a group of relations between the electromagnetic radiation deviation value of the r-th standard test terminal and the j-th temperature, wherein c is a positive integer larger than zero;

Step a5: repeating the steps a1 to a4 until j=T, ending the cycle to obtain the S group relation between the electromagnetic radiation deviation value of the r standard test terminal and the j-th temperature, enabling r=r+1, and jumping back to the steps a2 and T, S to be a positive integer larger than zero;

step a6: repeating the step a5 until r=R, ending the cycle, obtaining the S group relation between the electromagnetic radiation deviation values of the R standard test terminals and the jth temperature, and taking the S group relation between the electromagnetic radiation deviation values of the R standard test terminals and the jth temperature as electromagnetic radiation test data.

Further, acquiring electromagnetic radiation test data in advance, further includes:

step b1: placing R standard test terminals in a test batch under a set standard constant electromagnetic noise test environment, and placing the standard test terminals under an electromagnetic noise change test environment;

step b2: measuring a third electromagnetic radiation test value of the r standard test terminal under a set standard constant electromagnetic noise test environment;

step b3: under an electromagnetic noise change test environment, measuring a fourth electromagnetic radiation test value of the r standard test terminal under the v dB;

step b4: taking the difference value of the third electromagnetic radiation test value and the fourth electromagnetic radiation test value as an electromagnetic radiation deviation value, judging whether the electromagnetic radiation deviation value is in a preset electromagnetic radiation deviation value interval, if not, enabling v=v+d, and jumping back to the step b3, and if so, correlating the electromagnetic radiation deviation value with a v decibel to obtain a group of relations between the electromagnetic radiation deviation value of the r standard test terminal and the v decibel, wherein v and d are positive integers larger than zero;

Step b5: repeating the steps b1 to b4 until v=y, ending the cycle to obtain the relation between the electromagnetic radiation deviation value of the r standard test terminal and the S group of the v db, and jumping back to the step b2, wherein Y is a positive integer greater than zero;

step b6: repeating the step b5 until r=r, ending the cycle, obtaining the S group relation between the electromagnetic radiation deviation values of the R standard test terminals and the v db, and taking the S group relation between the electromagnetic radiation deviation values of the R standard test terminals and the v db as electromagnetic radiation test data.

Further, the generation logic of the pre-built first machine learning model is as follows:

acquiring a terminal model, transmitting power, transmitting frequency, gain of a transmitting antenna, transmitting frequency band and radiation shielding coefficient of a test terminal, extracting a relation between an electromagnetic radiation deviation value in electromagnetic radiation test data and each degree centigrade, and extracting a relation between the electromagnetic radiation deviation value in the electromagnetic radiation test data and each decibel;

taking the relation between the terminal model, the transmitting power, the transmitting frequency, the gain of a transmitting antenna, the transmitting frequency band, the radiation shielding coefficient, the electromagnetic radiation deviation value and each degree celsius and the relation between the electromagnetic radiation deviation value and each decibel as a radiation correction sample set, and dividing the radiation correction sample set into a radiation correction training set and a radiation correction test set;

Constructing a neural network model, taking the radiation correction training set as input data of the neural network model, and training the neural network model to obtain an initial neural network model;

and testing the initial neural network model by using the radiation correction test set, and outputting the initial neural network model with the accuracy greater than or equal to the preset test accuracy as a pre-constructed first machine learning model.

Further, correcting each electromagnetic radiation initial value of the radio frequency module includes:

step c1: acquiring electromagnetic radiation initial values of radio frequency modules in the ith sampling inspection terminal at the jth degree centigrade and the v db; the radiation correction characteristic data of the ith sampling inspection terminal and the radiation shielding coefficient of the ith sampling inspection terminal are obtained;

step c2: inputting the temperature j, the electromagnetic noise v, the radiation correction characteristic data and the radiation shielding coefficient of the ith spot check terminal to a pre-constructed first machine learning model to obtain an electromagnetic radiation deviation value;

step c3: performing accumulation operation on the electromagnetic radiation initial value and the electromagnetic radiation deviation value to obtain an electromagnetic radiation correction value at the j-th degree celsius and the v-th decibel; let j=j+c, v=v+d, and jump back to step c1;

step c4: repeating the steps c1 to c3 until j=t and v=y, and ending the cycle to obtain N electromagnetic radiation correction values.

Further, the comparison and analysis of the target correction value includes:

setting a target correction standard interval, and comparing the target correction value with the target correction standard interval;

if the target correction value is in the target correction standard interval, determining that the electromagnetic radiation of the corresponding spot check terminal meets the standard, and jumping the step 1 to i=i+1;

if the target correction value is not in the target correction standard interval, judging that the electromagnetic radiation of the corresponding spot check terminal does not accord with the standard, taking the corresponding spot check terminal as an illegal terminal, and jumping to the step 1 by i=i+1.

A radiation detection system for an intelligent mobile terminal, comprising:

the data acquisition module is used for measuring electromagnetic radiation of the radio frequency module in the ith sampling inspection terminal at different temperatures under the sampling batch to obtain M electromagnetic radiation initial values, and acquiring shielding coefficient characteristic data of the ith sampling inspection terminal, wherein i and M are positive integers larger than zero;

the shielding coefficient determining module is used for determining the radiation shielding coefficient of the ith sampling inspection terminal based on the shielding coefficient characteristic data and a pre-constructed second machine learning model;

the numerical correction module is used for acquiring radiation correction characteristic data, correcting each electromagnetic radiation initial value of the radio frequency module based on the radiation correction characteristic data, the radiation shielding coefficient of the ith sampling inspection terminal and a pre-constructed first machine learning model to obtain N electromagnetic radiation correction values, wherein N is a positive integer greater than zero;

The data comparison module is used for screening target correction values in the N electromagnetic radiation correction values, and comparing and analyzing the target correction values to obtain comparison and analysis results of the ith sampling inspection terminal; the comparison and analysis result comprises that the electromagnetic radiation meets the standard and the electromagnetic radiation does not meet the standard;

the cycle processing module is configured to repeat the data acquisition module 210 to the data comparison module 240 until the cycle is ended when i=q, and obtain comparison analysis results of all the sampling inspection terminals, where Q is a positive integer greater than zero;

and the production alarm module is used for determining the quality alarm grade under the lottery batch according to the comparison and analysis results of all the lottery terminals and carrying out production alarm according to the quality alarm grade.

An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the radiation detection method for an intelligent mobile terminal of any of the preceding claims when the computer program is executed.

A computer readable storage medium having stored thereon a computer program which when executed by a processor implements the radiation detection method for a smart mobile terminal of any of the above.

Compared with the prior art, the invention has the beneficial effects that:

1. the application discloses a radiation detection method, a radiation detection system, radiation detection equipment and radiation detection media for an intelligent mobile terminal, which comprise the steps of firstly measuring an electromagnetic radiation initial value and acquiring shielding coefficient characteristic data; then determining a radiation shielding coefficient based on the shielding coefficient characteristic data and a pre-constructed second machine learning model; then acquiring radiation correction characteristic data, and correcting an electromagnetic radiation initial value based on the radiation correction characteristic data, a radiation shielding coefficient and a pre-constructed first machine learning model to obtain an electromagnetic radiation correction value; then screening a target correction value, and comparing and analyzing the target correction value to obtain a comparison and analysis result; then repeating the steps to obtain comparison and analysis results of all the sampling inspection terminals; finally, determining the quality alarm grade under the lottery batch according to the comparison and analysis results of all the lottery terminals; based on the steps, the method and the device can correct the radiation measurement result of the intelligent mobile terminal, thereby being beneficial to eliminating electromagnetic radiation measurement deviation caused by external factors.

2. The invention has short detection period and high degree of automation, and is suitable for the production scene of large-scale intelligent mobile terminals; in addition, the intelligent mobile terminal is timely produced and warned based on the electromagnetic radiation correction result, so that the intelligent mobile terminal is prevented from being reworked in a large scale.

Drawings

FIG. 1 is a flow chart of a radiation detection method for an intelligent mobile terminal provided by the invention;

FIG. 2 is a schematic diagram of a radiation detection system for an intelligent mobile terminal provided by the present invention;

fig. 3 is a schematic structural diagram of an electronic device according to the present invention;

fig. 4 is a schematic structural diagram of a computer readable storage medium according to the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

Example 1

Referring to fig. 2, the disclosure of the present embodiment provides a radiation detection system for an intelligent mobile terminal, including:

the data acquisition module 210 is configured to measure electromagnetic radiation of the radio frequency module in the ith sampling terminal at different temperatures in a sampling batch, obtain M electromagnetic radiation initial values, and acquire shielding coefficient characteristic data of the ith sampling terminal, where i and M are positive integers greater than zero;

It should be appreciated that: the sampling inspection terminal is specifically an intelligent mobile terminal, and the intelligent mobile terminal needs to perform radiation level quality inspection before delivery so as to judge whether the sampling inspection terminal meets delivery or use standards; randomly extracting a plurality of intelligent mobile terminals when the radiation level quality inspection is carried out, and taking the plurality of intelligent mobile terminals as a sampling inspection batch;

it should be noted that: the radio frequency module comprises a radio frequency transceiver, a radio frequency amplifier, a filter, an antenna connector, an antenna, a radio frequency switch, a control circuit and the like;

also to be described is: electromagnetic radiation of the radio frequency module at different temperatures is measured based on electromagnetic radiation measuring instruments including, but not limited to, electromagnetic field intensity instruments, spectrum analyzers, magnetic field intensity instruments, and the like;

specifically, the shielding coefficient characteristic data comprise a terminal model, a terminal shell material, a terminal shell thickness, a terminal shell conductivity and a terminal shell dielectric constant;

a shielding coefficient determining module 220, configured to determine a radiation shielding coefficient of the i-th sampling inspection terminal based on the shielding coefficient feature data and a pre-constructed second machine learning model;

in implementation, the generation logic of the pre-built second machine learning model is as follows: acquiring historical shielding coefficient sample data, wherein the historical shielding coefficient sample data comprises shielding coefficient characteristic data and corresponding radiation shielding coefficients thereof; dividing historical shielding coefficient sample data into a shielding coefficient training set and a shielding coefficient testing set; constructing a regression network model, taking the shielding coefficient characteristic data in the shielding coefficient training set as the input of the regression network model, taking the radiation shielding coefficient in the shielding coefficient training set as the output of the regression network model, training the regression network model to obtain a second initial regression network model, and taking the minimum radiation shielding coefficient in the shielding coefficient training set as the output of the regression network model Modeling and evaluating a second initial regression network model by using a masking coefficient test set by taking the sum of the second prediction accuracy as a training target, and taking the second initial regression network model when the sum of the second prediction accuracy reaches convergence as a pre-constructed second machine learning model; the calculation formula of the second prediction accuracy is as follows;wherein->For each group of numbers of masking coefficient feature data, +.>For the second prediction accuracy, +.>Is->Predictive value of radiation shielding coefficient corresponding to group shielding coefficient characteristic data, < >>Is->Actual values of the radiation shielding coefficients corresponding to the group shielding coefficient characteristic data, wherein +.>、/>And->In decibels.

It should be noted that: the regression network model is specifically one of a decision tree regression network model, a support vector machine regression network model, a linear regression network model, a random forest regression model and the like;

wherein the generation logic of the radiation shielding coefficient is as follows:

it should be appreciated that: the electromagnetic radiation receiving power under the condition of no shell and the electromagnetic radiation receiving power under the condition of the shell refer to electromagnetic radiation output by the intelligent mobile terminal under the condition of the shell or not;

it should be appreciated that: decibels are a unit of comparison that has no direct physical meaning, but rather is used to represent the logarithm of the ratio of two powers, in the formula we convert the power ratio into units of decibels by taking the logarithm and multiplying by 10 so that the radiation shielding factor can be more easily compared to different scenarios and standards;

it should be noted that: the data are pre-stored in a system database or acquired by an electromagnetic radiation measuring instrument;

the numerical correction module 230 is configured to obtain radiation correction feature data, correct each electromagnetic radiation initial value of the radio frequency module based on the radiation correction feature data, the radiation shielding coefficient of the ith sampling inspection terminal, and a pre-constructed first machine learning model, and obtain N electromagnetic radiation correction values, where N is a positive integer greater than zero;

Specifically, the radiation correction characteristic data comprises a terminal model, a transmitting power, a transmitting frequency, a gain of a transmitting antenna and a transmitting frequency band;

specifically, the pre-constructed first machine learning model is generated based on pre-acquired electromagnetic radiation test data in a training manner;

in a specific embodiment, pre-acquiring electromagnetic radiation test data includes:

it should be noted that: the temperature control device is used for setting the temperature in the set standard constant temperature test environment in a constant temperature state and adjusting the temperature change in the temperature change test environment, and the temperature sensor is used for feeding back the temperature values in the set standard constant temperature test environment and the temperature change test environment in real time;

an exemplary illustration is: if the preset electromagnetic radiation deviation value interval is [500,1000], if the electromagnetic radiation deviation value is 1100, judging that the electromagnetic radiation deviation value is not in the preset electromagnetic radiation deviation value interval, and if the electromagnetic radiation deviation value is 550, judging that the electromagnetic radiation deviation value is in the preset electromagnetic radiation deviation value interval;

step a6: repeating the step a5 until r=R, ending the cycle, obtaining the S group relation between the electromagnetic radiation deviation values of the R standard test terminals and the jth temperature, and taking the S group relation between the electromagnetic radiation deviation values of the R standard test terminals and the jth temperature as electromagnetic radiation test data;

In another specific embodiment, the pre-acquiring electromagnetic radiation test data further comprises:

it should be noted that: an electromagnetic noise generator and an electromagnetic noise detection device are arranged in the set standard constant electromagnetic noise test environment and the electromagnetic noise change test environment, the electromagnetic noise generator is used for setting electromagnetic noise in the set standard constant electromagnetic noise test environment in a constant state and adjusting electromagnetic noise change in the electromagnetic noise change test environment, and the electromagnetic noise detection device is used for feeding back electromagnetic noise values in the set standard constant electromagnetic noise test environment and the electromagnetic noise change test environment in real time;

It should be appreciated that: electromagnetic noise can have an effect on electromagnetic radiation intensity, where decibels are used to represent the intensity or power ratio of electromagnetic noise;

step b6: repeating the step b5 until the cycle is ended when r=R, obtaining the S group relation between the electromagnetic radiation deviation values of the R standard test terminals and the v dB, and taking the S group relation between the electromagnetic radiation deviation values of the R standard test terminals and the v dB as electromagnetic radiation test data;

In implementation, the generation logic of the pre-built first machine learning model is as follows:

it should be appreciated that: in a model training stage, the input of the neural network model is temperature, electromagnetic noise, radiation correction characteristic data and radiation shielding coefficient, and the output of the neural network model is an electromagnetic radiation deviation value;

Testing the initial neural network model by using a radiation correction test set, and outputting the initial neural network model with the accuracy greater than or equal to a preset test accuracy as a pre-constructed first machine learning model;

it should be noted that: the neural network model is specifically one of an RNN neural network model, a long-short-time memory network model or a convolution neural network model and the like;

in an implementation, correcting each electromagnetic radiation initial value of the radio frequency module includes:

step c4: repeating the steps c1 to c3 until j=T and v=Y, and ending the cycle to obtain N electromagnetic radiation correction values;

The data comparison module 240 is configured to screen a target correction value of the N electromagnetic radiation correction values, and perform comparison analysis on the target correction value to obtain a comparison analysis result of the ith sampling inspection terminal; the comparison and analysis result comprises that the electromagnetic radiation meets the standard and the electromagnetic radiation does not meet the standard;

in an implementation, screening the target correction value of the N electromagnetic radiation correction values includes:

sequencing N electromagnetic radiation correction values according to the value from large to small;

taking electromagnetic radiation correction values at the first sorting position and the last sorting position as target correction values;

in an implementation, the comparing the target correction value to the analysis includes:

if the target correction value is in the target correction standard interval, determining that the electromagnetic radiation of the corresponding spot check terminal meets the standard, and jumping back to the data acquisition module 210 by making i=i+1;

if the target correction value is not in the target correction standard interval, determining that the electromagnetic radiation of the corresponding spot check terminal does not accord with the standard, taking the corresponding spot check terminal as an illegal terminal, and jumping i=i+1 back to the data acquisition module 210;

it should be noted that: if the electromagnetic radiation correction value of the first sequencing position in the target correction value is larger than the maximum value in the target correction standard interval, indicating that the electromagnetic radiation exceeding condition exists in the corresponding spot check terminal; conversely, if the electromagnetic radiation correction value of the tail sequencing position in the target correction value is smaller than the minimum value in the target correction standard interval, the condition that the electromagnetic radiation does not reach the standard exists in the corresponding spot check terminal is indicated; it should be appreciated that: whether the electromagnetic radiation exceeds the standard or the electromagnetic radiation does not reach the standard, the corresponding sampling inspection terminal is not in accordance with the factory standard;

The circulation processing module 250 is configured to repeat the data acquisition module 210 to the data comparison module 240 until the circulation is ended when i=q, and obtain comparison analysis results of all the sampling inspection terminals, where Q is a positive integer greater than zero;

it should be understood that: the comparison and analysis results of all the sampling inspection terminals introduce the condition that the electromagnetic radiation of each corresponding sampling inspection terminal meets the standard or the electromagnetic radiation does not meet the standard, and simultaneously record and mark the corresponding terminal belonging to the illegal terminal;

the production alarm module 260 is configured to determine a quality alarm level under the lot of the lottery according to the comparison and analysis results of all the sampling terminals, and perform production alarm according to the quality alarm level;

in an implementation, determining a quality alert level for a lot of lots, including;

counting the total number of offending terminals；

Setting a gradient thresholdAnd->Wherein->The total number of offending terminalsComparing with a gradient threshold value;

if it isGenerating a first-level quality alarm grade;

if it isGenerating a secondary quality alarm grade;

if it isGenerating three-level quality alarm grades;

it should be noted that: the first-level quality alarm level indicates that more illegal terminals exist in the current lot of the lottery, and the side surfaces reflect serious problems and larger omission in the production process of the current intelligent mobile terminal, and the production and maintenance should be stopped immediately to find the problem; the secondary quality alarm level reflects the moderate problem existing in the production process of the current intelligent mobile terminal on the side surface, and the secondary quality alarm level is maintained in time; and the three-level quality alarm level indicates that fewer illegal terminals in the current lottery batch are in line with the production yield standard.

Example 2

Referring to fig. 1, the disclosure of the present embodiment provides a radiation detection method for an intelligent mobile terminal, where the method includes:

step 1: under the lot of the lottery, electromagnetic radiation of the radio frequency module in the ith lottery terminal at different temperatures is measured to obtain M electromagnetic radiation initial values, shielding coefficient characteristic data of the ith lottery terminal are obtained, and i and M are positive integers larger than zero;

in implementation, the generation logic of the pre-built second machine learning model is as follows:acquiring historical shielding coefficient sample data, wherein the historical shielding coefficient sample data comprises shielding coefficient characteristic data and corresponding radiation shielding coefficients thereof; dividing historical shielding coefficient sample data into a shielding coefficient training set and a shielding coefficient testing set; constructing a regression network model, taking shielding coefficient characteristic data in a shielding coefficient training set as input of the regression network model, taking a radiation shielding coefficient in the shielding coefficient training set as output of the regression network model, training the regression network model to obtain a second initial regression network model, taking the sum of minimized second prediction accuracy as a training target, carrying out model evaluation on the second initial regression network model by using a shielding coefficient test set, and taking the second initial regression network model when the sum of the second prediction accuracy reaches convergence as a pre-constructed second machine learning model; the calculation formula of the second prediction accuracy is as follows; Wherein->For each group of numbers of masking coefficient feature data, +.>For the second prediction accuracy, +.>Is->Predictive value of radiation shielding coefficient corresponding to group shielding coefficient characteristic data, < >>Is->Actual values of the radiation shielding coefficients corresponding to the group shielding coefficient characteristic data, wherein +.>、/>And->In decibels.

based on the electromagnetic radiation output power of the radio frequency module, the electromagnetic radiation receiving power under the condition of no shell and the electromagnetic radiation receiving power under the condition of the shell, carrying out formulated calculation to obtain a radiation shielding coefficient; the calculation formula is as follows: The method comprises the steps of carrying out a first treatment on the surface of the Wherein: />Represents the radiation shielding coefficient in decibels +.>Representing the electromagnetic radiation output power of the radio frequency module in watts +.>Representing the electromagnetic radiation receiving power in watts,/without a housing>Representing electromagnetic radiation receiving power in the presence of a housingThe units are watts;

step 3: acquiring radiation correction characteristic data, correcting each electromagnetic radiation initial value of the radio frequency module based on the radiation correction characteristic data, the radiation shielding coefficient of the ith sampling inspection terminal and a pre-constructed first machine learning model to obtain N electromagnetic radiation correction values, wherein N is a positive integer greater than zero;

if the target correction value is not in the target correction standard interval, judging that the electromagnetic radiation of the corresponding selective detection terminal does not accord with the standard, taking the corresponding selective detection terminal as a violation terminal, and jumping back to the step 1, wherein i=i+1;

step 6: determining quality alarm levels under the lots according to comparison and analysis results of all the sampling inspection terminals, and carrying out production alarm according to the quality alarm levels;

counting the total number of offending terminals；

if it isGenerating a first-level quality alarm grade;

if it isGenerating a secondary quality alarm grade;

if it isGenerating three-level quality alarm grades;

Example 3

Referring to fig. 3, the disclosure provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements any one of the radiation detection methods for an intelligent mobile terminal provided by the above methods when executing the computer program.

Since the electronic device described in this embodiment is an electronic device used to implement the radiation detection method for an intelligent mobile terminal in this embodiment, based on the radiation detection method for an intelligent mobile terminal described in this embodiment, those skilled in the art can understand the specific implementation of the electronic device and various modifications thereof, so how to implement the method in this embodiment will not be described in detail herein. Electronic devices used by those skilled in the art to implement the radiation detection method for an intelligent mobile terminal in the embodiments of the present application are all within the scope of protection intended by the present application.

Example 4

Referring to fig. 4, the disclosure of the present embodiment provides a computer readable storage medium, where a computer program is stored, where the computer program is executed by a processor to implement the radiation detection method for an intelligent mobile terminal according to any one of the above.

The above formulas are all formulas with dimensionality removed and numerical value calculated, the formulas are formulas with the latest real situation obtained by software simulation by collecting a large amount of data, and preset parameters, weights and threshold selection in the formulas are set by those skilled in the art according to the actual situation.

The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with embodiments of the present invention are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center over a wired network or a wireless network. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.

In the several embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely one, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other forms.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.

Claims

1. A radiation detection method for an intelligent mobile terminal, the method comprising:

the generation logic of the pre-built second machine learning model is as follows: acquiring historical shielding coefficient sample data, wherein the historical shielding coefficient sample data comprises shielding coefficient characteristic data and corresponding radiation shielding coefficients thereof; dividing historical shielding coefficient sample data into a shielding coefficient training set and a shielding coefficient testing set; constructing a regression network model, taking shielding coefficient characteristic data in a shielding coefficient training set as input of the regression network model, taking a radiation shielding coefficient in the shielding coefficient training set as output of the regression network model, training the regression network model to obtain a second initial regression network model, taking the sum of minimized second prediction accuracy as a training target, carrying out model evaluation on the second initial regression network model by using a shielding coefficient test set, and taking the second initial regression network model when the sum of the second prediction accuracy reaches convergence as a pre-constructed second machine learning model; the calculation formula of the second prediction accuracy is as follows: Wherein->For each group of numbers of masking coefficient feature data, +.>For the second prediction accuracy, +.>Is->Predictive value of radiation shielding coefficient corresponding to group shielding coefficient characteristic data, < >>Is->Actual values of the radiation shielding coefficients corresponding to the group shielding coefficient characteristic data, wherein +.>、/>And->Is in decibels;

the generation logic of the radiation shielding coefficient is as follows:

2. The radiation detection method for an intelligent mobile terminal according to claim 1, wherein acquiring electromagnetic radiation test data in advance comprises:

3. The radiation detection method for an intelligent mobile terminal according to claim 2, wherein the electromagnetic radiation test data is acquired in advance, further comprising:

4. A radiation detection method for an intelligent mobile terminal according to claim 3, wherein the generation logic of the pre-constructed first machine learning model is as follows:

5. The radiation detection method for an intelligent mobile terminal according to claim 4, wherein correcting each electromagnetic radiation initial value of the radio frequency module comprises:

6. The radiation detection method for an intelligent mobile terminal according to claim 5, wherein comparing and analyzing the target correction value comprises:

7. A radiation detection system for an intelligent mobile terminal, comprising:

the data acquisition module is used for measuring electromagnetic radiation of the radio frequency module in the ith sampling inspection terminal at different temperatures under the sampling batch to obtain M electromagnetic radiation initial values, and acquiring shielding coefficient characteristic data of the ith sampling inspection terminal, wherein i and M are positive integers larger than zero; the shielding coefficient characteristic data comprise a terminal model, a terminal shell material, a terminal shell thickness, a terminal shell conductivity and a terminal shell dielectric constant;

the generation logic of the pre-built second machine learning model is as follows: acquiring historical shielding coefficient sample data, wherein the historical shielding coefficient sample data comprises shielding coefficient characteristic data and corresponding radiation shielding coefficients thereof; dividing historical shielding coefficient sample data into a shielding coefficient training set and a shielding coefficient testing set; constructing a regression network model, taking the mask coefficient characteristic data in the mask coefficient training set as the input of the regression network model, taking the radiation mask coefficient in the mask coefficient training set as the output of the regression network model, training the regression network model to obtain a second initial regression network model, taking the sum of the minimum second prediction accuracy as a training target, and utilizingThe masking coefficient test set carries out model evaluation on the second initial regression network model, and the second initial regression network model when the sum of the second prediction accuracy reaches convergence is used as a pre-constructed second machine learning model; the calculation formula of the second prediction accuracy is as follows: Wherein->For each group of numbers of masking coefficient feature data, +.>For the second prediction accuracy, +.>Is->Predictive value of radiation shielding coefficient corresponding to group shielding coefficient characteristic data, < >>Is->Actual values of the radiation shielding coefficients corresponding to the group shielding coefficient characteristic data, wherein +.>、And->Is in decibels;

the generation logic of the radiation shielding coefficient is as follows:

the numerical correction module is used for acquiring radiation correction characteristic data, correcting each electromagnetic radiation initial value of the radio frequency module based on the radiation correction characteristic data, the radiation shielding coefficient of the ith sampling inspection terminal and a pre-constructed first machine learning model to obtain N electromagnetic radiation correction values, wherein N is a positive integer greater than zero; the radiation correction characteristic data comprise a terminal model, transmitting power, transmitting frequency, gain of a transmitting antenna and a transmitting frequency band; the pre-constructed first machine learning model is generated based on pre-acquired electromagnetic radiation test data in a training mode;

the circulation processing module is used for repeating the data acquisition module to the data comparison module until the circulation is ended when i=Q, so as to obtain comparison analysis results of all the sampling inspection terminals, wherein Q is a positive integer greater than zero;

8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the radiation detection method for an intelligent mobile terminal according to any of claims 1 to 6 when the computer program is executed by the processor.

9. A computer readable storage medium, characterized in that it has stored thereon a computer program which, when executed by a processor, implements the radiation detection method for an intelligent mobile terminal according to any of claims 1 to 6.