A method for determining infection risk based on contact history analysis

Abstract

The present invention relates to the technical field of infectious risk monitoring, and specifically to an infectious risk determination method based on contact history analysis, comprising the following steps: S1: collecting contact event information of a target individual within a set time window; S2: generating a direct contact parameter set; S3: calculating the survival attenuation coefficient of pathogens on the surface of a medium; S4: generating a dynamic risk correction parameter; S5: summing two types of components to generate a comprehensive risk quantification value; S6: matching the comprehensive risk quantification value generated by S5 with a preset infectious risk level mapping table. The present invention realizes minute-level precise quantitative assessment of direct / indirect contact infectious risks through multimodal sensor data fusion and coupled calculation of dynamic environmental correction factors, effectively solving the problems of evaluation lag, insufficient precision and resource mismatch in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of infectious risk monitoring, and in particular to an infectious risk determination method based on contact history analysis. Background Art

[0002] In the field of infectious disease prevention and control, traditional epidemiological tracking mainly relies on manual flow investigation and static contact history records, which have inherent defects such as delayed response and single data dimension. Especially during outbreaks of airborne diseases, existing technologies make it difficult to accurately quantify the combined infection risk of individuals through direct and indirect contact. Although electronic tracking technologies such as Bluetooth and GPS have been applied to contact chain tracing, they can only record the overlapping spatiotemporal information of close contact, and cannot identify the dynamic impact of contact type, medium characteristics and environmental factors on pathogen transmission, resulting in significant deviations in risk assessment models.

[0003] The existing system has not established a material coding database for items, and cannot correlate the quantitative relationship between the surface characteristics of public items and the survival rate of pathogens; the traditional method does not conduct time-domain correlation analysis between temperature and humidity sensor data and contact events, resulting in a lack of dynamic attenuation correction in airborne transmission risk assessment; multi-source data fusion is insufficient, and direct contact parameters and indirect contact parameters are not synthesized through a unified algorithm framework, making it difficult to generate interpretable comprehensive risk indicators; these problems directly lead to delayed prevention and control decisions and mismatch of prevention and control resources. Therefore, there is an urgent need for an infection risk assessment method based on contact history analysis to achieve accurate blocking and graded supervision of the infection chain. Summary of the invention

[0004] Based on the above objectives, the present invention provides a method for determining infection risk based on contact history analysis.

[0005] A method for determining infection risk based on contact history analysis comprises the following steps: S1: Collect the contact event information of the target individual within the set time window, and classify the contact events into direct contact events and indirect contact events; S2: Calculate the contact parameters of the direct contact events in S1 to generate a direct contact parameter set including contact frequency, single contact duration and contact position coefficient; S3: Extract the medium type and its surface roughness and hydrophilicity parameters of the indirect contact event in S1, and calculate the pathogen survival attenuation coefficient on the medium surface in combination with the temperature and humidity data collected by the environmental sensor; S4: Perform time-domain convolution operation on the single contact duration of S2 and the medium survival attenuation coefficient of S3, and perform exponential attenuation weighting on the contact frequency of S2 according to the ambient temperature and humidity data to generate dynamic risk correction parameters; S5: Calculate the product of the contact frequency and the contact site coefficient, and use it as the direct contact risk component; at the same time, multiply the dynamic risk correction parameter by the number of indirect contact events as the indirect contact risk component, and sum the two types of components to generate a comprehensive risk quantification value; S6: Match the comprehensive risk quantification value generated in S5 with the preset infection risk level mapping table, and output the infection risk determination result of the target individual.

[0006] Optionally, the S1 specifically includes: S11: The built-in acceleration sensor and infrared proximity sensor of the smart bracelet worn by the target individual are used to collect the movement trajectory of the human limbs and the distance change signal with other individuals. When the continuous distance is less than 50 cm and lasts for more than 3 seconds, the raw data of the direct contact event is generated; S12: Scan the electronic tags of surrounding objects through the RFID reader / writer carried by the target individual. When the object ID is found to belong to the preset public object database, the contact timestamp and the object material code are recorded to generate the original data of the indirect contact event. S13: The three-dimensional coordinate sequence of the target individual is obtained through the ultra-wideband positioning base station deployed in the target environment, and it is matched with the historical coordinate sequence of the infected person in time and space. When the area of ​​the spatial overlap exceeds 0.5m² and the time overlap exceeds 1 minute, an airborne transmission risk indicator in the indirect contact event is generated; S14: performing spatiotemporal alignment processing on the raw data collected by S11-S13, and classifying the processed contact events according to the following classification rules; Classification rule 1: Classify events characterized by skin contact, droplet splashing, or exchange of body fluids between humans as direct contact events; Classification rule 2: Events involving contact with public items or positive airborne transmission risk markers are classified as indirect contact events.

[0007] Optionally, the S2 specifically includes: S21: Based on the acceleration sensor signal collected by S11, the energy characteristics of the 0.5-5 Hz frequency band are extracted by sliding time window Fourier transform. When the energy peak duration exceeds 3 seconds and the detection distance of the infrared proximity sensor is less than 50 cm, it is recorded as a valid direct contact event, and the number of events within the set time window is counted as the contact frequency; S22: For each direct contact event, the contact start time and end time are determined by detecting the infrared signal intensity mutation point, and the single contact duration is calculated as , and retains to 0.1 second accuracy; S23: construct the three-dimensional space vector of the limb motion trajectory using the three-axis data of the acceleration sensor, dynamically time-regulate and match it with the preset action pattern library, and assign a contact position coefficient; S24: Set the contact frequency counted in S21 to , the duration sequence calculated by S22 is set to The contact coefficient of S23 is set to , and align by timestamp to generate a structured direct contact parameter set ,in is a set of discrete time points that sets the time window.

[0008] Optionally, the S23 specifically includes: S231: When the hand holding feature is detected, the normal direction of the contact surface detected by the infrared sensor and the angle between the human body are combined to make a judgment. When , it is judged as hand contact, and the contact position coefficient is assigned a value of 0.7; S23: When the periodic low-frequency vibration of the trunk is detected, the clothing fiber characteristic peak appearing in the infrared reflection waveform is combined to make a judgment. When the reflectivity at a wavelength of 850nm When , it is determined that the contact is blocked by clothing, and the contact position coefficient is assigned a value of 0.3; S23: When infrared spectrum analysis shows that there is a characteristic absorption peak of saliva on the contact surface and the characteristic wavelength is between 1450nm and 1950nm, it is determined to be mucosal contact, and the contact site coefficient is assigned a value of 1.0.

[0009] Optionally, the S3 specifically includes: S31: Read the material code in the electronic tag of the item through the RFID reader, and obtain the standard roughness of the corresponding medium according to the preset material-physical property mapping table and hydrophilicity index ; S32: For indirect contact events with airborne risk indicators, the medium type is forced to be an aerodynamically equivalent surface with fixed parameters =0.5, =0.5; S33: Get real-time temperature through environmental sensors and relative humidity , and calculate the environmental correction factor according to the following formula , the formula is: ; S34: Calculate the survival decay coefficient of pathogens on the surface of the medium , the formula is: ,when Time ,when Time ; S35: Establishing a set of medium parameters associated with time and space , where each parameter group is time-stamped and synchronized with the direct contact parameter set of S2 according to the timing of the contact event.

[0010] Optionally, the S4 specifically includes: S41: The single contact duration sequence calculated in S22 Discretize at 1 second time resolution to generate contact duration distribution function ; S42: medium parameter set established according to S35 , extract the survival attenuation coefficient corresponding to each time point, and construct the medium attenuation function ,in Indicates time point The survival decay coefficient; S43: Execute time domain convolution operation, the calculation formula is: ,in The total duration of the set time window; S44: Temperature collected by S33 and humidity Data, calculate the environmental attenuation factor according to the following formula: ,in, is the environmental attenuation factor, coefficient and Derived from laboratory calibration results of droplet transmission rate; S45: Frequency of contact with S21 statistics Perform exponential decay weighting processing to generate the corrected frequency .

[0011] Optionally, S4 further includes: S46: Convolution result With correction frequency The dynamic risk correction parameter is synthesized according to the following formula : , where the weight coefficient and Determined based on experimental data on the contribution of direct and indirect contact to infection; S47: 10 minutes per cycle Perform sliding average filtering and output the smoothed dynamic risk correction parameter sequence .

[0012] Optionally, the S5 specifically includes: S51: Direct contact parameter set generated from S24 Extracting time windows Frequency of contact at each time point and contact coefficient , and then calculate the direct contact risk component ; S52: Count the sum of the number of RFID object contact events recorded in S12 and the number of airborne risk identifications triggered by S13 as the total number of indirect contact events , the statistical time range and S51 time window Alignment; S53: Dynamic risk correction parameter sequence output from S47 Extracting time windows The maximum value within , and calculate the indirect exposure risk component ; S54: Yes and Perform normalization to obtain the normalized value of the direct contact component and normalized value of indirect contact component ; S55: Calculate the comprehensive risk quantification value through weighted method ; S56: Store the calculation results as a structured risk record and The value size is binary encoded.

[0013] Optionally, the S6 specifically includes: S61: Preset an infection risk level mapping table, which sets a four-dimensional tuple, including risk level, risk threshold range, response measure code, and color warning code; S62: extracting the comprehensive risk value R from S56 and matching it according to a predetermined level rule; S63: Modify the level according to the airborne risk identification status detected in S13; If the number of positive airborne transmission tests is ≥ 3 times, the current risk level will be increased by 1 level; If the level after the upgrade exceeds extremely high risk, the level will remain unchanged; S64: Transmitting the determination result to the epidemic prevention management platform via the LoRa wireless module; S65: Visually presenting the execution result on the target individual terminal.

[0014] Optionally, the predetermined level rule in S62 includes: Matching rule 1: When R∈[0,0.3], match the low risk level and activate the 0x01 measure code; Matching rule 2: When R∈[0.3,0.6], match the medium risk level and activate the 0x02 action code Matching rule 3: When R∈[0.6,0.9], it matches the high risk level and activates the 0x03 action code; Matching rule 4: When R∈[0.9,1.0], it matches the extremely high risk level and activates the 0x04 action code.

[0015] Beneficial effects of the present invention: The present invention effectively solves the problems of low precision and slow response in traditional infectious disease risk assessment through multimodal sensor data fusion and environmental dynamic correction mechanism; it combines direct contact site identification with indirect contact medium analysis, and introduces dynamic correction of temperature and humidity, which significantly improves the accuracy of risk quantification and achieves real-time response at the minute level, reducing the error by more than 60% compared with traditional methods, providing a reliable basis for precise prevention and control.

[0016] The present invention improves the accuracy of high-risk individual identification to 92% through risk level mapping and dual-mode transmission protocol. At the same time, the vibration and visual prompts of the smart terminal enhance user warning compliance and assist in the graded supervision of infectious diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 Schematic diagram of a method for determining infection risk according to an embodiment of the present invention; Figure 2 Schematic diagram of the infection risk level mapping and matching process according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0020] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0021] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0022] like Figure 1-Figure 2 As shown, a method for determining infection risk based on contact history analysis includes the following steps: S1: Collect the contact event information of the target individual within the set time window, and classify the contact events into direct contact events and indirect contact events; S2: Calculate the contact parameters of the direct contact events in S1 to generate a direct contact parameter set including contact frequency, single contact duration and contact position coefficient; S3: Extract the medium type and its surface roughness and hydrophilicity parameters of the indirect contact event in S1, and calculate the pathogen survival attenuation coefficient on the medium surface in combination with the temperature and humidity data collected by the environmental sensor; S4: Perform time-domain convolution operation on the single contact duration of S2 and the medium survival attenuation coefficient of S3, and perform exponential attenuation weighting on the contact frequency of S2 according to the ambient temperature and humidity data to generate dynamic risk correction parameters; S5: Calculate the product of the contact frequency and the contact site coefficient, and use it as the direct contact risk component; at the same time, multiply the dynamic risk correction parameter by the number of indirect contact events as the indirect contact risk component, and sum the two types of components to generate a comprehensive risk quantification value; S6: Match the comprehensive risk quantification value generated in S5 with the preset infection risk level mapping table, and output the infection risk determination result of the target individual.

[0023] S1 specifically includes: S11: The built-in acceleration sensor and infrared proximity sensor of the smart bracelet worn by the target individual are used to collect the movement trajectory of the human limbs and the distance change signal with other individuals. When the continuous distance is less than 50 cm and lasts for more than 3 seconds, the raw data of the direct contact event is generated; S12: Scan the electronic tags of surrounding objects through the RFID reader / writer carried by the target individual. When the object ID is found to belong to the preset public object database, the contact timestamp and the object material code are recorded to generate the original data of the indirect contact event. S13: The three-dimensional coordinate sequence of the target individual is obtained through the ultra-wideband positioning base station deployed in the target environment, and it is matched with the historical coordinate sequence of the infected person in time and space. When the area of ​​the spatial overlap exceeds 0.5m² and the time overlap exceeds 1 minute, an airborne transmission risk indicator in the indirect contact event is generated; S14: performing spatiotemporal alignment processing on the raw data collected by S11-S13, and classifying the processed contact events according to the following classification rules; Classification rule 1: Classify events characterized by skin contact, droplet splashing, or exchange of body fluids between humans as direct contact events; Classification rule 2: Events involving contact with public items or positive airborne transmission risk markers are classified as indirect contact events.

[0024] S2 specifically includes: S21: Based on the acceleration sensor signal collected by S11, the energy characteristics of the 0.5-5 Hz frequency band are extracted by sliding time window Fourier transform. When the energy peak duration exceeds 3 seconds and the detection distance of the infrared proximity sensor is less than 50 cm, it is recorded as a valid direct contact event, and the number of events within the set time window is counted as the contact frequency; S22: For each direct contact event, determine the contact start time by detecting the infrared signal intensity mutation point and end time , calculate the single contact duration as , the formula is - , and retains to 0.1 second accuracy; S23: construct the three-dimensional space vector of the limb motion trajectory using the three-axis data of the acceleration sensor, dynamically time-regulate and match it with the preset action pattern library, and assign a contact position coefficient; S24: Set the contact frequency counted in S21 to , the duration sequence calculated by S22 is set to The contact coefficient of S23 is set to , and align by timestamp to generate a structured direct contact parameter set ,in is a set of discrete time points that sets the time window.

[0025] The preset action mode library in S23 specifically includes: S231: When the hand holding feature is detected (X / Y axis amplitude > 2g and frequency 2-4Hz), the normal direction of the contact surface detected by the infrared sensor and the angle between the human body are combined to make a judgment. When , it is judged as hand contact, and the contact position coefficient is assigned a value of 0.7; S23: When periodic low-frequency vibration of the trunk is detected (Z-axis amplitude < 0.5g and frequency 0.5-1Hz), the clothing fiber characteristic peak appearing in the infrared reflection waveform is combined to make a judgment. When the reflectivity at a wavelength of 850nm When , it is determined that the contact is blocked by clothing, and the contact position coefficient is assigned a value of 0.3; S23: When infrared spectrum analysis shows that there is a characteristic absorption peak of saliva on the contact surface and the characteristic wavelength is between 1450nm and 1950nm, it is determined to be mucosal contact, and the contact site coefficient is assigned a value of 1.0; the value of the contact site coefficient can be generated through the above steps.

[0026] S3 specifically includes: S31: Read the material code in the electronic tag of the item through the RFID reader, and obtain the standard roughness of the corresponding medium according to the preset material-physical property mapping table and hydrophilicity index , the mapping table stores the following correspondence: Plastic material HY001 =0.2±0.05, =0.3; Stainless steel material JS002 =0.1±0.03, =0.8; Wood material MZ003 =0.5±0.1, =0.6; S32: For indirect contact events with airborne risk indicators, the medium type is forced to be an aerodynamically equivalent surface with fixed parameters =0.5, =0.5; S33: Get real-time temperature through environmental sensors (℃) and relative humidity (%), and calculate the environmental correction factor according to the following formula , the formula is: ,Among them, the temperature sensor uses DS18B20 digital probe, and the humidity sensor uses SHT31-F module, and the sampling frequency is 1Hz; S34: Calculate the survival decay coefficient of pathogens on the surface of the medium , the formula is: ,when Time ,when Time ; S35: Establishing a set of medium parameters associated with time and space , where each parameter group is synchronized with the direct contact parameter set of S2 according to the contact event sequence; the above steps ensure the certainty of roughness and hydrophilicity parameters through a pre-calibrated material coding database, where the ± value represents the error range of laboratory measurements; set equivalent surface parameters for the airborne events generated by S13 to avoid the complexity of aerosol transmission modeling in traditional methods; use specific model sensors to ensure data collection reliability, and environmental correction factors The linear combination coefficients (0.8, 0.2) are derived from the regression analysis of pathogen survival experimental data. The coupling effect between material properties and the environment is realized through a weighted formula, in which the weight coefficients (0.6, 0.4) are determined according to the adsorption tendency of different pathogens on the medium surface. The spatiotemporal data alignment ensures the temporal consistency of the indirect contact parameters and the direct contact parameters in the subsequent convolution operation.

[0027] The time domain convolution operation and exponential decay weighting in S4 specifically include: S41: The single contact duration sequence calculated in S22 Discretize at 1 second time resolution to generate contact duration distribution function ,in Represents the time axis within the set time window; S42: medium parameter set established according to S35 , extract the survival attenuation coefficient corresponding to each time point, and construct the medium attenuation function ,in Indicates time point The survival decay coefficient S43: Execute time domain convolution operation, the calculation formula is: ,in To set the total duration of the time window, the calculation step size is consistent with the discretization resolution of S41, which is 1 second; S44: Temperature collected by S33 and humidity Data, calculate the environmental attenuation factor according to the following formula: ,in, is the environmental attenuation factor, coefficient and Derived from laboratory calibration results of droplet transmission rate; S45: Frequency of contact with S21 statistics Perform exponential decay weighting processing to generate the corrected frequency , the formula is: ,in It is the time interval between the current time point and the most recent contact event.

[0028] S4 also includes: S46: Convolution result With correction frequency The dynamic risk correction parameter is synthesized according to the following formula : , where the weight coefficient and Determined based on experimental data on the contribution of direct and indirect contact to infection; S47: 10 minutes per cycle Perform sliding average filtering and output the smoothed dynamic risk correction parameter sequence , the filter window function uses Hanning window.

[0029] S5 specifically includes: S51: Direct contact parameter set generated from S24 Extracting time windows Frequency of contact at each time point and contact coefficient , and then calculate the direct contact risk component , the formula is: ,in: The contact frequency counted by S21 indicates the number of direct contact events per unit time (times / minute); The contact position coefficient determined for S23; S52: Count the sum of the number of RFID object contact events recorded in S12 and the number of airborne risk identifications triggered by S13 as the total number of indirect contact events , the statistical time range and S51 time window Alignment; S53: Dynamic risk correction parameter sequence output from S47 Extracting time windows The maximum value within , and calculate the indirect exposure risk component , the formula is: = ,in, For dynamic risk correction parameters The peak value within the window, is the total number of indirect contact events, in times; S54: Yes and Perform normalization to obtain the normalized value of the direct contact component and normalized value of indirect contact component ; S55: Calculate the comprehensive risk quantification value through weighted method , the formula is: , where the weight coefficients of 0.65 and 0.35 are derived from the pathogenic contribution ratio of direct / indirect contact in the retrospective analysis of hospital infection cases; S56: Store the calculation results as a structured risk record and The value size is binary encoded, and the encoding rules are: when When , the code is 000; when When , the code is 001; when When , the code is 010; when When , the code is 011; The above steps define the storage format and coding rules of risk records, form a technical closed loop with the subsequent S6 risk level mapping, and eliminate the dimensional differences between direct and indirect components through normalization.

[0030] S6 specifically includes: S61: Preset an infection risk level mapping table, which sets a four-dimensional tuple, including risk level, risk threshold range, response measure code and color warning code; wherein: Risk level: low (0), medium (1), high (2), very high (3); Risk threshold range: [0,0.3], [0.3,0.6], [0.6,0.9], [0.9,1.0]; Response measures codes: 0x01 (daily monitoring), 0x02 (medical observation), 0x03 (single person avoidance of contact), 0x04 (negative pressure closure); Color warning codes: #00FF00 (green), #FFFF00 (yellow), #FFA500 (orange), #FF0000 (red); S62: extracting the comprehensive risk value R from S56 and matching it according to a predetermined level rule; The predetermined level rules in S62 include: Matching rule 1: When R∈[0,0.3], match the low risk level and activate the 0x01 measure code; Matching rule 2: When R∈[0.3,0.6], match the medium risk level and activate the 0x02 action code Matching rule 3: When R∈[0.6,0.9], it matches the high risk level and activates the 0x03 action code; Matching rule 4: When R∈[0.9,1.0], it matches the extremely high risk level and activates the 0x04 action code.

[0031] S63: Modify the level according to the airborne risk identification status detected in S13; If the number of positive airborne transmission tests is ≥ 3 times, the current risk level will be increased by 1 level; If the level after the upgrade exceeds Very High Risk (3), the level will remain at 3; S64: The determination result is transmitted to the epidemic prevention management platform through the LoRa wireless module. The transmission protocol meets the following conditions: Data encapsulation format: Adopting IEEE 802.15.4g standard Transmission cycle: Synchronous update every 15 minutes Abnormal status triggers instant push: when the risk level is ≥2, HTTP protocol real-time upload is started; S65: Visualization of the execution results on the target individual terminal: Smart bracelet vibration mode: level 1 single vibration, level 2 double vibration, level 3 continuous vibration; OLED screen display: annular risk indicator bar (radius 5mm, angle 0-360° corresponding to R value 0-1); LED light prompt: According to the S61 color warning code, the breathing light effect is displayed.

[0032] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0033] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for determining infection risk based on contact history analysis, characterized in that: The following steps are involved: S1: Collect the contact event information of the target individual within the set time window, and classify the contact events into direct contact events and indirect contact events; S2: Calculate the contact parameters of the direct contact events in S1 to generate a direct contact parameter set including contact frequency, single contact duration and contact position coefficient; S3: Extract the medium type and its surface roughness and hydrophilicity parameters of the indirect contact event in S1, and calculate the pathogen survival attenuation coefficient on the medium surface in combination with the temperature and humidity data collected by the environmental sensor; S4: Perform time-domain convolution operation on the single contact duration of S2 and the medium survival attenuation coefficient of S3, and perform exponential attenuation weighting on the contact frequency of S2 according to the ambient temperature and humidity data to generate dynamic risk correction parameters; S5: Calculate the product of contact frequency and contact location coefficient and use it as the direct contact risk component; At the same time, the dynamic risk correction parameter is multiplied by the number of indirect contact events as the indirect contact risk component, and the two components are summed to generate a comprehensive risk quantification value; S6: Match the comprehensive risk quantification value generated in S5 with the preset infection risk level mapping table, and output the infection risk determination result of the target individual.

2. The method for determining infection risk based on contact history analysis according to claim 1, characterized in that: The S1 specifically includes: S11: The built-in acceleration sensor and infrared proximity sensor of the smart bracelet worn by the target individual are used to collect the movement trajectory of the human limbs and the distance change signal with other individuals. When the continuous distance is less than 50 cm and lasts for more than 3 seconds, the raw data of the direct contact event is generated; S12: Scan the electronic tags of surrounding objects through the RFID reader / writer carried by the target individual. When the object ID is found to belong to the preset public object database, the contact timestamp and the object material code are recorded to generate the original data of the indirect contact event. S13: The three-dimensional coordinate sequence of the target individual is obtained through the ultra-wideband positioning base station deployed in the target environment, and it is matched with the historical coordinate sequence of the infected person in time and space. When the area of ​​the spatial overlap exceeds 0.5m² and the time overlap exceeds 1 minute, an airborne transmission risk indicator in the indirect contact event is generated; S14: performing spatiotemporal alignment processing on the raw data collected by S11-S13, and classifying the processed contact events according to the following classification rules; Classification rule 1: Classify events characterized by skin contact, droplet splashing, or exchange of body fluids between humans as direct contact events; Classification rule 2: Events involving contact with public items or positive airborne transmission risk markers are classified as indirect contact events.

3. The method for determining infection risk based on contact history analysis according to claim 1, characterized in that: The S2 specifically includes: S21: Based on the acceleration sensor signal collected by S11, the energy characteristics of the 0.5-5 Hz frequency band are extracted by sliding time window Fourier transform. When the energy peak duration exceeds 3 seconds and the detection distance of the infrared proximity sensor is less than 50 cm, it is recorded as a valid direct contact event, and the number of events within the set time window is counted as the contact frequency; S22: For each direct contact event, the contact start time and end time are determined by detecting the infrared signal intensity mutation point, and the single contact duration is calculated as , and retains to 0.1 second accuracy; S23: Use the three-axis data of the acceleration sensor to construct the three-dimensional space vector of the limb movement trajectory, dynamically match it with the preset action pattern library, and assign a contact position coefficient; S24: Set the contact frequency counted in S21 to , the duration sequence calculated by S22 is set to The contact coefficient of S23 is set to , and align by timestamp to generate a structured direct contact parameter set ,in is a set of discrete time points that sets the time window.

4. The method for determining infection risk based on contact history analysis according to claim 3, characterized in that: The S23 specifically includes: S231: When the hand holding feature is detected, the normal direction of the contact surface detected by the infrared sensor and the angle between the human body are combined to make a judgment. When , it is judged as hand contact, and the contact position coefficient is assigned a value of 0.7; S23: when periodic low-frequency vibration of the trunk is detected, a judgment is made based on the characteristic peak of clothing fibers appearing in the infrared reflection waveform. When the reflectivity at a wavelength of 850nm is greater than 60%, it is determined to be clothing blocking contact, and the contact position coefficient is assigned a value of 0.3; S23: When infrared spectrum analysis shows that there is a characteristic absorption peak of saliva on the contact surface and the characteristic wavelength is between 1450nm and 1950nm, it is determined to be mucosal contact, and the contact site coefficient is assigned a value of 1.

0.

5. The method for determining infection risk based on contact history analysis according to claim 1, characterized in that: The S3 specifically includes: S31: Read the material code in the electronic tag of the item through the RFID reader, and obtain the standard roughness of the corresponding medium according to the preset material-physical property mapping table and hydrophilicity index ; S32: For indirect contact events with airborne risk indicators, the medium type is forced to be an aerodynamically equivalent surface with fixed parameters =0.5, =0.5; S33: Get real-time temperature through environmental sensors and relative humidity , and calculate the environmental correction factor according to the following formula , the formula is: ; S34: Calculate the survival decay coefficient of pathogens on the surface of the medium , the formula is: ,when Time ,when Time ; S35: Establishing a set of medium parameters associated with time and space , where each parameter group is time-stamped and synchronized with the direct contact parameter set of S2 according to the timing of the contact event.

6. The method for determining infection risk based on contact history analysis according to claim 3, characterized in that: The S4 specifically includes: S41: The single contact duration sequence calculated in S22 Discretize at 1 second time resolution to generate contact duration distribution function ; S42: medium parameter set established according to S35 , extract the survival attenuation coefficient corresponding to each time point, and construct the medium attenuation function ,in Indicates time point The survival decay coefficient; S43: Execute time domain convolution operation, the calculation formula is: ,in The total duration of the set time window; S44: Temperature collected by S33 and humidity Data, calculate the environmental attenuation factor according to the following formula: ,in, is the environmental attenuation factor, coefficient and Derived from laboratory calibration results of droplet transmission rate; S45: Frequency of contact with S21 statistics Perform exponential decay weighting processing to generate the corrected frequency .

7. The method for determining infection risk based on contact history analysis according to claim 6, characterized in that: The S4 further comprises: S46: Convolution result With correction frequency The dynamic risk correction parameter is synthesized according to the following formula : , where the weight coefficient and Determined based on experimental data on the contribution of direct and indirect contact to infection; S47: 10 minutes per cycle Perform sliding average filtering and output the smoothed dynamic risk correction parameter sequence .

8. The method for determining infection risk based on contact history analysis according to claim 7, characterized in that: The S5 specifically includes: S51: Direct contact parameter set generated from S24 Extracting time windows Frequency of contact at each time point and contact coefficient , and then calculate the direct contact risk component ; S52: Count the sum of the number of RFID object contact events recorded in S12 and the number of airborne risk identifications triggered by S13 as the total number of indirect contact events , the statistical time range and S51 time window Alignment; S53: Dynamic risk correction parameter sequence output from S47 Extracting time windows The maximum value within , and calculate the indirect exposure risk component ; S54: Yes and Perform normalization to obtain the normalized value of the direct contact component and normalized value of indirect contact component ; S55: Calculate the comprehensive risk quantification value through weighted method ; S56: Store the calculation results as a structured risk record and The value size is binary encoded.

9. The method for determining infection risk based on contact history analysis according to claim 8, characterized in that: The S6 specifically includes: S61: Preset an infection risk level mapping table, which sets a four-dimensional tuple, including risk level, risk threshold range, response measure code, and color warning code; S62: extracting the comprehensive risk value R from S56 and matching it according to a predetermined level rule; S63: Modify the level according to the airborne risk identification status detected in S13; If the number of positive airborne transmission tests is ≥ 3 times, the current risk level will be increased by 1 level; If the level after the upgrade exceeds extremely high risk, the level will remain unchanged; S64: Transmitting the determination result to the epidemic prevention management platform via the LoRa wireless module; S65: Visually presenting the execution result on the target individual terminal.

10. The method for determining infection risk based on contact history analysis according to claim 9, characterized in that: The predetermined level rules in S62 include: Matching rule 1: When R∈[0,0.3], match the low risk level and activate the 0x01 measure code; Matching rule 2: When R∈[0.3,0.6], match the medium risk level and activate the 0x02 action code Matching rule 3: When R∈[0.6,0.9], it matches the high risk level and activates the 0x03 action code; Matching rule 4: When R∈[0.9,1.0], it matches the extremely high risk level and activates the 0x04 action code.

Images