A method, apparatus, device, and storage medium for identifying personnel changes.

Abstract

This application discloses a method, apparatus, device, and storage medium for identifying population changes, applied in the field of population census. The method includes: acquiring initial height data of rented rooms collected by an ultrasonic device in the current period; performing density distribution analysis on the initial height data using a kernel density estimation algorithm to obtain a height distribution probability formula; fitting the height distribution probability formula into a height curve using a grid data cross-validation method; performing peak analysis on the height curve to determine the number and height of people in the rented room; and determining whether population change has occurred based on the number and height. This application utilizes density distribution analysis and grid data cross-validation to overcome the inaccuracies in detecting multiple people in existing technologies. Specifically, when multiple people are present in a rented room, this method can accurately detect the number and height of people in the room, and determine whether there has been a change in the number of people or population movement based on their height and number of people in the room.

Description

Technical Field

[0001] This application relates to the field of population census, and in particular to a method, apparatus, equipment and storage medium for identifying population changes. Background Technology

[0002] Rental housing, especially shared housing, is a major gathering place for the floating population. Its population structure is complex, the population mobility is high, and the occupants change rapidly, making it difficult for management departments to effectively grasp the actual living situation of the floating population in rental housing.

[0003] Existing technologies allow for door-to-door registration and screening by relevant personnel from management departments. However, this method is labor-intensive and inefficient, as the identities of those identified often change shortly after the screening is completed. Traditional methods also include using ultrasound and pyroelectric methods to detect height. From a probabilistic perspective, the height data of an individual person generally follows a normal distribution, which can be used to calculate suspected heights. However, when there are multiple occupants in a room, their height data overlaps, making it impossible to analyze the height distribution of people in the room using traditional statistical methods, thus making it impossible to determine the number of people and their individual heights. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a method, apparatus, device and storage medium for identifying personnel changes, which solves the problem of inaccurate personnel detection in the prior art.

[0005] To address the aforementioned technical problems, this application provides a method for identifying personnel changes, comprising:

[0006] Obtain the initial height data of the rented room collected by the ultrasonic device in the current cycle;

[0007] The initial height data were analyzed for density distribution using a kernel density estimation algorithm to obtain the height distribution probability formula.

[0008] The height distribution probability formula is fitted into a height curve using grid data cross-validation; the horizontal axis of the height curve represents the height value, and the vertical axis represents the probability value.

[0009] Peak analysis was performed on the height curve to determine the number of people and their heights in the rental house;

[0010] When the number of people is inconsistent with the number of people in the historical period or / and the difference between the height of the people and the height of people in the historical period is greater than a preset difference, the number of people in the rental house changes.

[0011] Optionally, obtaining the initial height data of the rented room collected by the ultrasound device in the current cycle includes:

[0012] Acquire the height data of people in the rental house collected by the ultrasonic device in the current cycle, as well as the sound intensity parameters corresponding to the height data of each person;

[0013] The initial height data is obtained by deleting the height data of the person whose sound intensity parameter is greater than the preset sound intensity threshold.

[0014] Optionally, the step of performing peak analysis on the height curve to determine the number of people and their heights in the rental room includes:

[0015] The peaks other than the highest peak in the height curve are taken as the set of peaks to be tested.

[0016] The peak threshold is set based on the probability value corresponding to the highest peak value;

[0017] Peaks that meet preset conditions are considered valid peaks; the preset conditions include peaks in the set of peaks to be tested that are greater than the peak threshold.

[0018] The number of effective peaks is calculated and used as the first quantity;

[0019] Add 1 to the first number to get the number of people in the rental house;

[0020] The height values ​​corresponding to the effective peak and the highest peak are taken as the height of the people in the rental house.

[0021] Optionally, the preset conditions may also include:

[0022] The peak position of the height curve is differentiable.

[0023] Optionally, the step of using the height values ​​corresponding to the effective peak and the highest peak as the height of the people in the rental room includes:

[0024] A preset height range is set based on the height values ​​corresponding to the effective peaks and the highest peaks.

[0025] The K-means algorithm is used to analyze the height data within the preset height range to obtain the effective peak and the height cluster point of the highest peak.

[0026] The height value corresponding to the height aggregation point is taken as the height of the people in the rental house.

[0027] Optional, also includes:

[0028] The DBSCAN algorithm is used to calculate height data whose density reaches a preset density threshold in the time dimension.

[0029] The height data of each cluster is further divided into multiple clusters based on the time dimension to obtain the clusters of the concentrated time periods of activity of people of each height.

[0030] The K-means algorithm is used to determine the center point of each of the multiple clusters in order to obtain the concentrated time period of activity for people of different heights;

[0031] The determination of whether the people in the rental house are permanent residents is based on the concentrated time period of the activities.

[0032] Optional, also includes:

[0033] Acquire illumination data collected by the light sensor;

[0034] Analyze the temporal distribution of illumination changes in the illumination data;

[0035] The time distribution is used as a daily routine pattern in the activity patterns of people in the rental property;

[0036] Based on the stated work and rest patterns, personnel tags were determined for the people living in the rental property.

[0037] This application also provides a personnel change identification device, including:

[0038] The acquisition module is used to acquire the initial height data of the rented room collected by the ultrasonic device in the current period;

[0039] The analysis module is used to perform density distribution analysis on the initial height data using a kernel density estimation algorithm to obtain the height distribution probability formula;

[0040] The fitting module is used to fit the height distribution probability formula into a height curve using grid data cross-validation; the horizontal axis of the height curve is the height value, and the vertical axis is the probability value.

[0041] The determination module is used to perform peak analysis on the height curve to determine the number of people and their heights in the rental house.

[0042] The judgment module is used to determine if the number of people in the rental house changes when the number of people is inconsistent with the number of people in the historical period or / and the difference between the height of the people and the height of people in the historical period is greater than a preset difference.

[0043] This application also provides a personnel change recognition device, including:

[0044] Memory, used to store computer programs;

[0045] A processor is used to execute the computer program to implement the steps of the personnel change identification method described above.

[0046] This application also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the personnel change identification method described above.

[0047] As can be seen, this application uses density distribution analysis and grid data cross-validation to fit the data, obtaining a fitted curve, and then determines the number and height of suspected individuals based on the fitted curve. Furthermore, when multiple people are present in a rental property, the application can accurately detect the number and height of people in the property, and determine whether there has been a change in the number of people or a movement of people by observing whether the number and height of people have changed.

[0048] In addition, this application also provides a personnel change identification device, equipment and storage medium, which also have the above-mentioned beneficial effects. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0050] Figure 1 A flowchart illustrating a personnel change identification method provided in this application embodiment;

[0051] Figure 2 This is a schematic diagram of the structure of a personnel change recognition device provided in an embodiment of this application;

[0052] Figure 3 This is a schematic diagram of the structure of a personnel change recognition device provided in an embodiment of this application. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0054] Rental housing, especially shared housing, is a major gathering place for the floating population. Its population structure is complex, with high mobility and rapid changes in residents, making it difficult for management departments to effectively grasp the actual living situation of the floating population within rental properties. Relying on management personnel to conduct door-to-door registration and screening is labor-intensive and inefficient; often, the occupants change shortly after a screening is completed. Using the personnel identification method provided in this application, which collects resident profiles, daily routines, and changes in those routines without physical contact, management departments can grasp core information such as whether a rental property is occupied, the number of residents, and whether there have been changes in occupancy. This allows management departments to target and manage changes in occupancy in key rooms. Please refer to the following for details. Figure 1 , Figure 1 A flowchart illustrating a personnel change identification method provided in this application embodiment. The method may include:

[0055] S101: Obtain the initial height data of the rented room collected by the ultrasonic device in the current cycle.

[0056] The execution subject in this embodiment is a terminal. This embodiment does not limit the type of terminal, as long as it can perform the operation of personnel change identification. For example, it can be a dedicated terminal; or it can be a general-purpose terminal.

[0057] Furthermore, to ensure the validity of the collected height data, the above-mentioned acquisition of the initial height data of the rental room collected by the ultrasound device in the current period may include the following steps, specifically including:

[0058] Step 21: Obtain the height data of the people in the rental house collected by the ultrasonic device in the current cycle, as well as the sound intensity parameters corresponding to the height data of each person;

[0059] Step 22: Delete the height data of people whose sound intensity parameters are greater than the preset sound intensity threshold to obtain the initial height data.

[0060] This embodiment does not limit the equipment used to collect height data. For example, an ultrasonic device can be used; or a combination of an ultrasonic device and a pyroelectric device can be used. To reduce power consumption, this embodiment can use a pyroelectric sensor to detect the presence of people in the vicinity, and then use an ultrasonic device to collect height data when people are present. In this embodiment, the pyroelectric sensor and the ultrasonic device can be placed at a suitable height in an open area within a rental property. The current period in this embodiment can be data collected within one week; or it can be data collected within half a month. This embodiment uses the height data collected by the ultrasonic device and the corresponding sound intensity parameter to filter the ultrasonically collected data, deleting height data with sound intensity parameters greater than a preset sound intensity threshold, ensuring the reliability of the collected height data. The preset sound intensity threshold in this embodiment is set empirically and can be 100; or it can be 90.

[0061] S102: The initial height data is analyzed for density distribution using the kernel density estimation algorithm to obtain the height distribution probability formula.

[0062] This embodiment uses a kernel density estimation algorithm to analyze the data and obtain the height distribution probability formula. The kernel function in this embodiment can be a Gaussian kernel function.

[0063] S103: Using grid data cross-validation, the height distribution probability formula is fitted into a height curve; the horizontal axis of the height curve represents the height value, and the vertical axis represents the probability value.

[0064] In this embodiment, the kernel density estimation algorithm and grid data cross-validation method are used to fit the collected initial height data to obtain the fitted curve, i.e., the height curve.

[0065] S104: Perform peak analysis on the height curve to determine the number of people and their heights in the rental property.

[0066] This embodiment determines the number of people and their heights in the rental house by analyzing the peaks in the height curve.

[0067] Furthermore, to avoid the influence of a small amount of noisy data and ensure the accuracy of personnel identification, the above-mentioned peak analysis of the height curve to determine the number of people and their heights in the rental house may include the following steps, specifically:

[0068] Step 31: Select all peaks except the highest peak in the height curve as the set of peaks to be tested.

[0069] Step 32: Set the peak threshold based on the probability value corresponding to the highest peak value;

[0070] Step 33: Select peaks that meet the preset conditions as valid peaks; the preset conditions include peaks in the set of peaks to be tested that are greater than the peak threshold.

[0071] Step 34: Calculate the number of valid peaks, which will be used as the first count;

[0072] Step 35: Add 1 to the first quantity to get the number of people in the rental house;

[0073] Step 36: Use the height values ​​corresponding to the effective peak and the highest peak as the height of the people in the rental house.

[0074] This embodiment filters the peaks in the height curve except for the highest peak, and sets an appropriate preset peak threshold based on the highest peak. For example, 1 / 5 of the highest peak can be set as the preset peak threshold, meaning that all peaks except the highest peak must reach more than 1 / 5 of the highest peak to be considered valid peaks. The height values ​​corresponding to all peaks obtained in this way can be used as the height values ​​of the people in the rental room; the number of peaks can be used as the number of people in the rental room.

[0075] Furthermore, to more effectively filter valid data, the preset conditions can also include:

[0076] The peak position of the height curve is differentiable.

[0077] Based on the previous step, we then determine whether the peak position is differentiable and delete the non-differentiable peaks.

[0078] Furthermore, to make the height values ​​more accurate, the aforementioned peak analysis of the height curve to determine the height of people in the rental property may include the following steps, specifically:

[0079] Step 51: Set the preset height range based on the height values ​​corresponding to the effective peaks and the highest peak;

[0080] Step 52: Use the K-means algorithm to analyze the height data within the preset height range to obtain the effective peaks and the height cluster points of the highest peaks;

[0081] Step 53: Use the height values ​​corresponding to the height aggregation points as the heights of the people in the rental house.

[0082] This embodiment considers that the peak height only represents the height with the highest probability of occurrence, therefore, it is necessary to effectively analyze the density of the nearby height distribution. This embodiment uses the K-means algorithm (K-means is an unsupervised learning clustering algorithm that groups similar objects into a cluster, and the cluster center is calculated by the mean of all points in the cluster) to analyze the data within ±3 cm of the peak height and calculate the height cluster point near the peak as the height of the people in the rental house.

[0083] Furthermore, in order to conduct further analysis of the people living in the rental property and to understand their daily routines, it may also include:

[0084] Step 61: Use the DBSCAN algorithm to calculate the height data where the density reaches the preset density threshold in the time dimension;

[0085] Step 62: Further divide the height data of each cluster into multiple clusters according to the time dimension to obtain the clusters of the concentrated time periods of activity of people of each height;

[0086] Step 63: Use the K-means algorithm to determine the center point of each cluster in multiple clusters to obtain the concentrated time period of activity for people of different heights;

[0087] Step 64: Determine whether the people in the rental house are permanent residents based on the concentrated time period of their activities.

[0088] This embodiment uses the height data of people in the current period to determine the concentrated time period of activity of each person in the rental house using the DBSCAN algorithm (Density-Based Spatial Clustering of Applications with Noise) and the Kmeans algorithm, and can determine whether the person is a permanent resident.

[0089] Furthermore, in order to analyze people's daily routines, it may also include:

[0090] Step 71: Acquire illumination data collected by the light sensor;

[0091] Step 72: Analyze the temporal distribution of illumination changes in the illumination data;

[0092] Step 73: Use time distribution as a basis for understanding the daily routine patterns within the activity patterns of people in the rental property;

[0093] Step 74: Determine the personnel tags of the people in the rental house based on their daily routines.

[0094] This embodiment also incorporates illumination data collected by a light sensor. Specifically, when the light sensor detects a significant change in illumination, it collects the illumination levels before and after the change. Since natural light in the same environment typically doesn't change drastically instantaneously, a change in illumination exceeding a threshold is considered to be caused by human activity. Because ultrasonic data collection has a limited range, illumination data can be used to further assess the credibility of whether someone is in the room. Furthermore, illumination data can be used to detect daily routines, determining sleep patterns to derive individual tags, including different types such as office workers, nocturnal individuals, and homebodies.

[0095] S105: When the number of people is inconsistent with the number of people in the historical period or / and the difference between the height of the people and the height of the people in the historical period is greater than a preset difference, the number of people in the rental house changes.

[0096] This embodiment can determine that there is a change in the number of people in the rental property by detecting a change in the number of people in the current period compared with the number of people in the historical period; or it can also determine that there is a change in the number of people in the rental property if the number of people in the current period does not change compared with the number of people in the historical period, but the height has changed.

[0097] The personnel flow identification method provided in this application involves acquiring initial height data of the rental property collected by an ultrasonic device in the current period; performing density distribution analysis on the initial height data using a kernel density estimation algorithm to obtain a height distribution probability formula; and fitting the height distribution probability formula into a height curve using a grid data cross-validation method. The horizontal axis of the height curve represents the height value, and the vertical axis represents the probability value. Peak analysis is performed on the height curve to determine the number of people and their heights in the rental property. If the number of people is inconsistent with the number of people in the historical period or / and the difference between the height of the people and the height of people in the historical period is greater than a preset difference, then the personnel in the rental property have changed. This method obtains a fitted curve by performing density distribution analysis on the data and using a grid data cross-validation method to fit the data. Based on the fitted curve, the number of suspected personnel and their heights are determined. Furthermore, even when there are multiple people in the rental property, the method can accurately detect the number and height of the people in the rental property, and determine whether there has been a change in the personnel in the rental property or whether there has been personnel flow by whether the number and height of the people have changed. Furthermore, the peaks are filtered to avoid the influence of a small amount of noise data, ensuring the accuracy of personnel identification; the data collected by the acquisition equipment is also filtered to ensure the validity of the collected height data; in order to make the height values ​​more accurate, the density of the height distribution near the peaks is effectively analyzed; and the collected data is analyzed from different angles to obtain the living patterns of the personnel.

[0098] To make this application easier to understand, the following details are provided:

[0099] The pyroelectric sensor uploads data on whether human activity was detected within half an hour, and the duration of such activity. Pyroelectric detection has a larger range than ultrasound. Therefore, after detecting a person entering the height acquisition range using pyroelectric sensors, ultrasound is activated to collect height data. The resulting raw height data includes the acquisition time, height, and ultrasonic intensity (used for height data reliability). Data with low reliability is removed from the raw height data using ultrasonic intensity to obtain initial height data. A kernel density estimation algorithm and grid cross-validation are used to fit the initial height data, resulting in a height curve. The peak points of the height curve are used to determine the peak values. Peak points are then filtered according to preset conditions to remove invalid data with low reliability, resulting in analyzed height data. The DBSCAN and K-means algorithms are used to divide the height data into several clusters, and the height and time period represented by each cluster are determined. A light sensor detects a significant change in illumination intensity, collecting data on the illumination intensity before and after the change. Since natural light in the same environment typically does not change drastically instantaneously, changes in illumination intensity exceeding a threshold are considered to be caused by human activity. Because ultrasonic data collection has a limited range, light data can be used to further assess the credibility of whether someone is inside the room.

[0100] Activity pattern dimension:

[0101] Activity pattern data can be analyzed using a 14-day cycle:

[0102] Step 1: Divide all data (including height analysis data, light data, and pyroelectric data) into 48 time periods based on the collection time, starting from 0:00, with each time period being half an hour.

[0103] Step 2: Based on the analyzed height data, height clusters within the period can be obtained. After removing clusters with data distribution <= 4 days, the remaining number of clusters is taken as the number of people in the rental house. This is the first dimension of activity pattern.

[0104] Step 3: Combining the height clusters and their corresponding clusters from the analyzed height data, the DBSCAN algorithm is used to calculate the density-reachable height data over time. Based on the time dimension, each cluster is further divided into multiple clusters, thus obtaining clusters of concentrated indoor activity time periods for individuals of different heights. The DBSCAN algorithm divides the height data into several different clusters, but it does not identify the cluster centers.

[0105] Step 4: Use the KMeans algorithm to calculate each cluster from Step 3 sequentially, determine the center point (time) of each cluster, and thus determine the main time periods for different heights. This is the second dimension of activity patterns.

[0106] Step 5: Based on the lighting data, it can be determined whether there are people active in the room during the 48 time periods of the activity, which serves as the third dimension of activity pattern.

[0107] Step 6: Based on the pyroelectric data, it can be determined whether there are people active in the room during 48 time periods, which serves as the fourth dimension of activity patterns.

[0108] Population assessment:

[0109] 1. Are there any permanent residents in the rented property?

[0110] Collect the combined data from dimensions 2, 3, and 4 of the daily activity patterns to distinguish whether there is any human activity in each time period.

[0111] If human activity is detected in more than 4 out of 48 time periods, then that day is considered a valid activity day.

[0112] If the percentage of valid activity days is greater than 60% within the judgment period, the rental property is considered to have permanent residents; otherwise, there are no permanent residents.

[0113] 2. The number of permanent residents in the rental property appears to have changed.

[0114] Assuming there are permanent residents in the rental property during the assessment period, the number of permanent residents in this period is determined based on activity pattern dimension 1. If there is a change compared to the previous period, the number of permanent residents is considered to have changed.

[0115] 3. Changes in the permanent residents of the rented property

[0116] Based on activity pattern dimension 1, the height of permanent residents can be determined. If the height of a resident in a given period differs from that in the previous period by more than a threshold, it is determined that the resident population has changed.

[0117] Based on activity patterns dimensions 2, 3, and 4, the peak activity periods of permanent residents can be determined. If the change in peak activity periods within a period exceeds a threshold, it is determined that there has been a change in permanent residents.

[0118] The personnel change identification device provided in the embodiments of this application is described below. The personnel change identification device described below and the personnel change identification method described above can be referred to each other.

[0119] Please refer to the details. Figure 2 , Figure 2 A schematic diagram of a personnel change recognition device provided in this application embodiment may include:

[0120] The acquisition module 100 is used to acquire the initial height data of the rented room collected by the ultrasonic device in the current cycle.

[0121] Analysis module 200 is used to perform density distribution analysis on the initial height data using a kernel density estimation algorithm to obtain a height distribution probability formula;

[0122] The fitting module 300 is used to fit the height distribution probability formula into a height curve using grid data cross-validation; the horizontal axis of the height curve is the height value, and the vertical axis is the probability value.

[0123] The determination module 400 is used to perform peak analysis on the height curve to determine the number of people and their heights in the rental house.

[0124] The judgment module 500 is used to determine if the number of people in the rental house changes when the number of people is inconsistent with the number of people in the historical period or / and the difference between the height of the people and the height of people in the historical period is greater than a preset difference.

[0125] Based on the above embodiments, the acquisition module 100 may include:

[0126] The acquisition unit is used to acquire the height data of people in the rental house collected by the ultrasonic device in the current cycle, as well as the sound intensity parameters corresponding to the height data of each person.

[0127] The deletion unit is used to delete the height data of the person whose sound intensity parameter is greater than the preset sound intensity threshold, so as to obtain the initial height data.

[0128] Based on the above embodiments, the determining module 400 may include:

[0129] The peak set determination unit is used to determine the peaks other than the highest peak in the height curve as the peak set to be tested.

[0130] A peak threshold setting unit is used to set a peak threshold based on the probability value corresponding to the highest peak value;

[0131] The judgment unit is used to identify peaks that meet preset conditions as valid peaks; the preset conditions include peaks in the set of peaks to be measured that are greater than the peak threshold.

[0132] A calculation unit is used to calculate the number of effective peaks, which is taken as a first quantity;

[0133] A personnel number determination unit is used to add 1 to the first quantity to obtain the number of personnel in the rental house;

[0134] The personnel height determination unit is used to determine the height value corresponding to the effective peak and the highest peak as the height of the personnel in the rental room.

[0135] Based on the above embodiments, the preset unit in the judgment unit may further include: the peak position of the height curve is differentiable.

[0136] Based on the above embodiments, the personnel height determination unit may include:

[0137] The preset height range setting subunit is used to set a preset height range based on the height values ​​corresponding to the effective peak and the highest peak.

[0138] The analysis subunit is used to analyze the height data within the preset height range using the K-means algorithm to obtain the effective peak and the height aggregation point of the highest peak.

[0139] The personnel height determination subunit is used to determine the height value corresponding to the height aggregation point as the height of the personnel in the rental house.

[0140] Based on the above embodiments, the personnel change recognition device may further include:

[0141] The height data determination module is used to calculate height data whose density reaches a preset density threshold in the time dimension using the DBSCAN algorithm.

[0142] The activity concentration time period clustering determination module is used to further divide the height data of each cluster into multiple clusters according to the time dimension, so as to obtain the activity concentration time period clusters of people of each height.

[0143] The activity concentration time period determination module is used to determine the center point of each cluster in the multiple clusters using the Kmeans algorithm, so as to obtain the activity concentration time period of people of different heights;

[0144] The permanent resident determination module is used to determine whether the people in the rental house are permanent residents based on the concentrated period of activity.

[0145] Based on the above embodiments, the personnel change recognition device may further include:

[0146] The illumination data acquisition module is used to acquire illumination data collected by the light sensor;

[0147] The time distribution analysis module is used to analyze the time distribution corresponding to changes in illumination in the illumination data;

[0148] The work-rest pattern determination module is used to use the time distribution as the work-rest pattern in the activity patterns of people in the rental house;

[0149] The personnel tag determination module is used to determine the personnel tags of the people in the rental house based on the work and rest patterns.

[0150] It should be noted that the order of the modules and units in the aforementioned personnel change recognition device can be changed without affecting the logic.

[0151] The personnel change identification device provided in this application includes: an acquisition module 100 for acquiring initial height data of the rental property collected by an ultrasonic device in the current period; an analysis module 200 for performing density distribution analysis on the initial height data using a kernel density estimation algorithm to obtain a height distribution probability formula; a fitting module 300 for fitting the height distribution probability formula into a height curve using a grid data cross-validation method; the horizontal axis of the height curve represents the height value, and the vertical axis represents the probability value; a determination module 400 for performing peak analysis on the height curve to determine the number of people and their heights in the rental property; and a judgment module 500 for determining that if the number of people is inconsistent with the number of people in the historical period or / and the difference between the height of the people and the height of the people in the historical period is greater than a preset difference, then the personnel in the rental property have changed. This device uses density distribution analysis and grid data cross-validation to fit the data, obtaining a fitted curve, and then determines the number of suspected personnel and their heights based on the fitted curve. Furthermore, even when multiple people are present in a rental property, the system can accurately detect the number and height of individuals. Changes in the number and height of occupants indicate changes in the property's occupants and potential movement of people. The system also filters data from peaks to avoid the influence of minor noise data, ensuring accurate identification. Furthermore, the system filters the data collected by the acquisition device to ensure the validity of the height data. To further improve the accuracy of height values, the density of height distribution near peaks is effectively analyzed. Finally, the system analyzes the collected data from different angles to reveal the daily routines of the individuals.

[0152] The personnel change identification device provided in the embodiments of this application is described below. The personnel change identification device described below and the personnel change identification method described above can be referred to each other.

[0153] Please refer to Figure 3 , Figure 3 The structural diagram of the personnel change recognition device provided in the embodiments of this application may include:

[0154] Memory 10 is used to store computer programs;

[0155] Processor 20 is used to execute computer programs to implement the aforementioned personnel change identification method.

[0156] The memory 10, processor 20, and communication interface 31 all communicate with each other through the communication bus 32.

[0157] In this embodiment, the memory 10 is used to store one or more programs. The programs may include program code, which includes computer operation instructions. In this embodiment, the memory 10 may store programs for implementing the following functions:

[0158] Obtain the initial height data of the rented room collected by the ultrasonic device in the current cycle;

[0159] The density distribution analysis of the initial height data was performed using the kernel density estimation algorithm to obtain the height distribution probability formula.

[0160] Using grid data cross-validation, the height distribution probability formula is fitted into a height curve; the horizontal axis of the height curve represents the height value, and the vertical axis represents the probability value.

[0161] Peak analysis of height curves can be performed to determine the number of people and their heights in the rental property.

[0162] When the number of people is inconsistent with the number of people in the historical period or / and the difference between the height of people and the height of people in the historical period is greater than the preset difference, the number of people in the rental house changes.

[0163] In one possible implementation, the memory 10 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and applications required for at least one function; and the data storage area may store data created during use.

[0164] Furthermore, memory 10 may include read-only memory and random access memory, providing instructions and data to the processor. A portion of the memory may also include NVRAM. The memory stores operating systems and operating instructions, executable modules, or data structures, or subsets thereof, or extended sets thereof, wherein the operating instructions may include various operating instructions for implementing various operations. The operating system may include various system programs for implementing various basic tasks and handling hardware-based tasks.

[0165] Processor 20 can be a central processing unit (CPU), an application-specific integrated circuit, a digital signal processor, a field-programmable gate array, or other programmable logic device. Processor 20 can be a microprocessor or any conventional processor. Processor 20 can call programs stored in memory 10.

[0166] Communication interface 31 can be an interface for the communication module, used to connect with other devices or systems.

[0167] Of course, it should be noted that, Figure 3 The structure shown does not constitute a limitation on the personnel change identification device in the embodiments of this application. In practical applications, the personnel change identification device may include more than Figure 3 More or fewer components as shown, or combinations of certain components.

[0168] The following describes the readable storage medium provided in the embodiments of this application. The storage medium described below can be referred to in correspondence with the personnel change identification method described above.

[0169] This application also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the personnel change identification method described above.

[0170] The storage medium can include various media that can store program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0171] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0172] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0173] Finally, it should be noted that in this document, relationships such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0174] The above provides a detailed description of a personnel change identification method, apparatus, device, and storage medium provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for identifying personnel changes, characterized in that, include: Obtain the initial height data of the rented room collected by the ultrasonic device in the current cycle; The initial height data were analyzed for density distribution using a kernel density estimation algorithm to obtain the height distribution probability formula. The height distribution probability formula is fitted into a height curve using grid data cross-validation; the horizontal axis of the height curve represents the height value, and the vertical axis represents the probability value. Peak analysis was performed on the height curve to determine the number of people and their heights in the rental house; When the number of people is inconsistent with the number of people in the historical period or / and the difference between the height of the people and the height of people in the historical period is greater than a preset difference, the number of people in the rental house changes.

2. The personnel change identification method according to claim 1, characterized in that, The acquisition of initial height data within the rental room collected by the ultrasound device in the current cycle includes: Acquire the height data of people in the rental house collected by the ultrasonic device in the current cycle, as well as the sound intensity parameters corresponding to the height data of each person; The initial height data is obtained by deleting the height data of the person whose sound intensity parameter is greater than the preset sound intensity threshold.

3. The personnel change identification method according to claim 1, characterized in that, The step of performing peak analysis on the height curve to determine the number of people and their heights in the rental property includes: The peaks other than the highest peak in the height curve are taken as the set of peaks to be tested. The peak threshold is set based on the probability value corresponding to the highest peak value; Peaks that meet preset conditions are considered valid peaks; the preset conditions include peaks in the set of peaks to be tested that are greater than the peak threshold. The number of effective peaks is calculated and used as the first quantity; Add 1 to the first number to get the number of people in the rental house; The height values ​​corresponding to the effective peak and the highest peak are taken as the height of the people in the rental house.

4. The personnel change identification method according to claim 3, characterized in that, The preset conditions also include: The peak position of the height curve is differentiable.

5. The personnel change identification method according to claim 3, characterized in that, The step of using the height values ​​corresponding to the effective peak and the highest peak as the height of the people in the rental room includes: A preset height range is set based on the height values ​​corresponding to the effective peaks and the highest peaks. The K-means algorithm is used to analyze the height data within the preset height range to obtain the effective peak and the height cluster point of the highest peak. The height value corresponding to the height aggregation point is taken as the height of the people in the rental house.

6. The personnel change identification method according to claim 1, characterized in that, Also includes: The DBSCAN algorithm is used to calculate height data whose density reaches a preset density threshold in the time dimension. The height data of each cluster is further divided into multiple clusters based on the time dimension to obtain the clusters of the concentrated time periods of activity of people of each height. The K-means algorithm is used to determine the center point of each of the multiple clusters in order to obtain the concentrated time period of activity for people of different heights; The determination of whether the people in the rental house are permanent residents is based on the concentrated time period of the activities.

7. The personnel change identification method according to claim 1, characterized in that, Also includes: Acquire illumination data collected by the light sensor; Analyze the temporal distribution of illumination changes in the illumination data; The time distribution is used as a daily routine pattern in the activity patterns of people in the rental property; Based on the stated work and rest patterns, personnel tags were determined for the people living in the rental property.

8. A personnel change identification device, characterized in that, include: The acquisition module is used to acquire the initial height data of the rented room collected by the ultrasonic device in the current period; The analysis module is used to perform density distribution analysis on the initial height data using a kernel density estimation algorithm to obtain the height distribution probability formula; The fitting module is used to fit the height distribution probability formula into a height curve using grid data cross-validation; the horizontal axis of the height curve is the height value, and the vertical axis is the probability value. The determination module is used to perform peak analysis on the height curve to determine the number of people and their heights in the rental house. The judgment module is used to determine if the number of people in the rental house changes when the number of people is inconsistent with the number of people in the historical period or / and the difference between the height of the people and the height of people in the historical period is greater than a preset difference.

9. A personnel change recognition device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the personnel change identification method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the steps of the personnel change identification method as described in any one of claims 1 to 7.

Images