A comprehensive evaluation system for old-age public service facilities

By using drones to acquire images of facilities and employing image recognition models to confirm their status, the problem of slow manual verification has been solved, enabling efficient assessment of public service facilities for the elderly.

CN115660495BActive Publication Date: 2026-05-01SOUTH CHINA UNIV OF TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SOUTH CHINA UNIV OF TECH
Filing Date
2022-11-03
Publication Date
2026-05-01

AI Technical Summary

Technical Problem

In existing technologies, the confirmation of whether public service facilities for the elderly are operating normally relies on manual methods, which results in slow confirmation speed and affects assessment efficiency.

Method used

The system uses drones to acquire images of facility status and image recognition models to confirm facility operational status. It then combines coverage and satisfaction data to calculate a comprehensive evaluation score, thus achieving automated evaluation.

Benefits of technology

It has improved the efficiency and accuracy of the assessment of public service facilities for the elderly, reduced the demand for human resources, and improved the speed and quality of the assessment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115660495B_ABST
    Figure CN115660495B_ABST
Patent Text Reader

Abstract

The application belongs to the field of evaluation, and discloses a comprehensive evaluation system for old-age public service facilities, which comprises an input module, a confirmation module and an evaluation module; the input module is used for inputting the category and evaluation range of the old-age public service facilities by the staff; the confirmation module comprises an acquisition unit and a confirmation unit; the acquisition unit is used for acquiring the address of the old-age public service facilities conforming to the category; the confirmation unit is used for acquiring the state image of the old-age public service facility corresponding to the address by a UAV, and confirming whether the old-age public service facility is normally operated based on the state image; the evaluation module is used for evaluating the rationality of the distribution of the old-age public service facilities according to the old-age public service facilities normally operated, and obtaining an evaluation result; the application is applicable to the process of evaluating the existing old-age public service facilities in urban planning; and the application effectively improves the confirmation efficiency, and further improves the efficiency of the comprehensive evaluation of the old-age public service facilities.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of assessment, and more particularly to a comprehensive assessment system for public service facilities for the elderly. Background Technology

[0002] Institutions, buildings, and venues that provide specialized or comprehensive services to the elderly, including residential services, daily care, medical care, cultural education, and recreational activities, are generally referred to as elderly care public service facilities. To assess the rationality of the distribution of elderly care public service facilities, it is generally necessary to first obtain their locations from a map, and then evaluate the rationality of the distribution based on information such as their location, coverage area, and whether they are operating normally.

[0003] Because map information may not be updated in a timely manner, some elderly care public service facilities may still appear on the map even if they are closed. Therefore, it is necessary to confirm whether these facilities are operating normally, excluding those that are closed. Current technology typically involves sending personnel to the locations of these facilities to verify their operation. However, this method requires a significant amount of manpower and is relatively slow, reducing the efficiency of assessing the rationality of the distribution of elderly care public service facilities. Summary of the Invention

[0004] The purpose of this invention is to disclose a comprehensive evaluation system for public service facilities for the elderly, which solves the problem in the prior art that the manual confirmation method is used to confirm whether public service facilities for the elderly are operating normally, resulting in slow confirmation speed and affecting the efficiency of evaluating the rationality of the distribution of public service facilities for the elderly.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A comprehensive evaluation system for public service facilities for the elderly includes an input module, a confirmation module, and an evaluation module;

[0007] The input module is used by staff to input the category and assessment scope of elderly care public service facilities;

[0008] The confirmation module includes an acquisition unit and a confirmation unit;

[0009] The acquisition unit is used to acquire the addresses of elderly care public service facilities that conform to the aforementioned category;

[0010] The confirmation unit is used to obtain the status image of the elderly care public service facility corresponding to the address through the drone, and confirm whether the elderly care public service facility is operating normally based on the status image;

[0011] The assessment module is used to evaluate the rationality of the distribution of elderly care public service facilities based on the normal operation of the facilities, and to obtain the assessment results.

[0012] Preferably, the categories of public service facilities for the elderly include day care centers, senior canteens, elderly care institutions, and integrated home-based elderly care service platforms.

[0013] Preferably, obtaining the address of the elderly care public service facility that conforms to the aforementioned category includes:

[0014] Enter the category as a keyword into a map website to obtain the addresses of elderly care public service facilities that match the category within the assessment scope.

[0015] Preferably, the confirmation unit includes a drone and a terminal device;

[0016] The drone is used to acquire status images of the elderly care public service facilities corresponding to the address and send the status images to the terminal device;

[0017] The terminal equipment is used to perform image recognition processing on status images to confirm whether the public service facilities for the elderly are operating normally.

[0018] Preferably, the step of performing image recognition processing on the status image to confirm whether the elderly care public service facility is operating normally includes:

[0019] The state image is preprocessed to obtain a preprocessed image;

[0020] The pre-processed image is input into the image recognition model for processing. The model determines whether there are objects of a preset type in the pre-processed image. If so, it indicates that the elderly care public service facility is operating normally; otherwise, it indicates that the elderly care public service facility is not operating normally.

[0021] Preferably, the preprocessing of the state image to obtain a preprocessed image includes:

[0022] The state image is subjected to illumination optimization processing to obtain an illumination-optimized image;

[0023] The image with optimized lighting is denoised to obtain a denoised image;

[0024] The denoised image is segmented to obtain a preprocessed image.

[0025] Preferably, the image recognition model includes a convolutional neural network.

[0026] Preferably, the evaluation module includes a computing unit, a storage unit, and an evaluation unit;

[0027] The calculation unit is used to calculate the area of ​​the assessment scope;

[0028] The storage unit is used to store the coverage radius, the area of ​​the assessment scope, the list of normally operating elderly care public service facilities, and the satisfaction level of each category of elderly care public service facilities;

[0029] The calculation unit is also used to calculate the coverage rate and comprehensive evaluation score for each type of elderly care public service facility;

[0030] The assessment unit is used to rank various types of elderly care public service facilities based on comprehensive assessment scores to obtain assessment results.

[0031] Preferably, the coverage rate of the elderly care public service facilities is calculated in the following way:

[0032] For the i-th category of elderly care public service facilities, the coverage rate is cvrg i The following formula is used for calculation:

[0033]

[0034] In the formula, num i Let R represent the number of normally operating elderly care public service facilities in the i-th category, i∈[1,N], where N represents the total number of elderly care public service facility categories, and R i The radius of the public service facility for the i-th category of elderly care is represented by tlarea, and the area of ​​the assessment scope is represented by dcarea. i This represents the area of ​​the i-th category of elderly care public service facilities that is counted repeatedly.

[0035] Preferably, the comprehensive evaluation score is calculated in the following manner:

[0036]

[0037] In the formula, comassscr i cvrg represents the comprehensive evaluation score of the i-th category of elderly care public service facilities. i cvrst represents the coverage rate of the i-th category of elderly care public service facilities, and stif represents the preset maximum coverage rate. i Let represent the satisfaction level of the public service facilities for the elderly in the i-th category, tifst represent the preset maximum satisfaction level, and δ represent the proportional parameter, δ∈(0,1).

[0038] In the process of comprehensively evaluating elderly care public service facilities, this invention utilizes drones to acquire status images to confirm whether the facilities are operating normally. This effectively improves the efficiency of the confirmation process and, consequently, the overall efficiency of the comprehensive evaluation of elderly care public service facilities. This invention is applicable to the evaluation of existing elderly care public service facilities in urban planning. Attached Figure Description

[0039] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0040] Figure 1 This is a diagram illustrating one embodiment of the comprehensive evaluation system for elderly care public service facilities according to the present invention.

[0041] Figure 2 This is an embodiment of the present invention for obtaining a preprocessed image. Detailed Implementation

[0042] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0043] like Figure 1 As shown in one embodiment, the present invention provides a comprehensive evaluation system for public service facilities for the elderly, including an input module, a confirmation module, and an evaluation module;

[0044] The input module is used by staff to input the category and assessment scope of elderly care public service facilities;

[0045] The confirmation module includes an acquisition unit and a confirmation unit;

[0046] The acquisition unit is used to acquire the addresses of elderly care public service facilities that conform to the aforementioned category;

[0047] The confirmation unit is used to obtain the status image of the elderly care public service facility corresponding to the address through the drone, and confirm whether the elderly care public service facility is operating normally based on the status image;

[0048] The assessment module is used to evaluate the rationality of the distribution of elderly care public service facilities based on the normal operation of the facilities, and to obtain the assessment results.

[0049] In the process of comprehensively evaluating elderly care public service facilities, this invention utilizes drones to acquire status images to confirm whether the facilities are operating normally. This effectively improves the efficiency of the confirmation process and, consequently, the overall efficiency of the comprehensive evaluation of elderly care public service facilities. This invention is applicable to the evaluation of existing elderly care public service facilities in urban planning.

[0050] Preferably, the scope of the assessment may include administrative regions such as districts, towns, and cities.

[0051] Preferably, the categories of public service facilities for the elderly include day care centers, senior canteens, elderly care institutions, and integrated home-based elderly care service platforms.

[0052] Preferably, obtaining the address of the elderly care public service facility that conforms to the aforementioned category includes:

[0053] Enter the category as a keyword into a map website to obtain the addresses of elderly care public service facilities that match the category within the assessment scope.

[0054] Preferably, the confirmation unit includes a drone and a terminal device;

[0055] The drone is used to acquire status images of the elderly care public service facilities corresponding to the address and send the status images to the terminal device;

[0056] The terminal equipment is used to perform image recognition processing on status images to confirm whether the public service facilities for the elderly are operating normally.

[0057] Specifically, the location for obtaining the status image can be the entrance or exit of the corresponding elderly care public service facility, and whether it is operating normally can be determined by whether people are entering or leaving; while for elderly care public service facilities located outdoors, such as the elderly fitness park in the category of cultural activity center, the location for obtaining the status image can be the fitness facility area in the park.

[0058] Preferably, the step of performing image recognition processing on the status image to confirm whether the elderly care public service facility is operating normally includes:

[0059] The state image is preprocessed to obtain a preprocessed image;

[0060] The pre-processed image is input into the image recognition model for processing. The model determines whether there are objects of a preset type in the pre-processed image. If so, it indicates that the elderly care public service facility is operating normally; otherwise, it indicates that the elderly care public service facility is not operating normally.

[0061] Specifically, taking a senior citizen fitness park as an example, when senior citizens are detected in the fitness area, it indicates that the senior citizen public service facility is operating normally.

[0062] As a preferred option, such as Figure 2 As shown, the preprocessing of the state image to obtain a preprocessed image includes:

[0063] The state image is subjected to illumination optimization processing to obtain an illumination-optimized image;

[0064] The image with optimized lighting is denoised to obtain a denoised image;

[0065] The denoised image is segmented to obtain a preprocessed image.

[0066] The distribution of light in an image has a significant impact on subsequent image recognition. For example, if a target is located at the intersection of light and dark, and the image area containing the target is not optimized for lighting to even out the pixel values ​​of the pixels in that area, the target may not be correctly identified, resulting in incorrect image recognition results.

[0067] Preferably, the step of performing illumination optimization processing on the state image to obtain an illumination-optimized image includes:

[0068] Obtain the mediator image corresponding to the state image;

[0069] Perform detail restoration on the intermediate image to obtain the restored image;

[0070] Obtain an optimized illumination image based on the repaired image.

[0071] This invention does not perform illumination optimization processing solely in the RGB color space. Instead, it first acquires an intermediate image in the Lab color space, then performs detail restoration on the intermediate image to obtain a restored image. Next, the restored image is converted back to the RGB color space, and finally, the final optimization process is performed in the RGB color space based on Retinex theory. Because the acquisition of the restored image is not performed in the RGB color space, this invention only needs to perform calculations on one color channel, thus effectively improving the efficiency of illumination optimization processing.

[0072] Preferably, the intermediate image corresponding to the state image is obtained, including:

[0073] Convert the status image to the Lab color space;

[0074] Obtain the image imgfcum of the luminance component corresponding to the state image in the Lab color space;

[0075] Use the following formula to obtain the mediator image:

[0076]

[0077] Where, itrimg represents the intermediate image, itrimg(x,y) represents the pixel value of the pixel with coordinates (x,y) in imgfcum in itrimg, and U(x,y) represents the set of judgment pixels in imgfcum with the pixel with coordinates (x,y) as the center and an adaptive radius of T(x,y); imgfcum d This represents the pixel value of pixel d in U(x,y), where mas represents the maximum value.

[0078] The adaptive radius is obtained as follows:

[0079] If the pixel at coordinates (x, y) is not an edge pixel, then T(x, y) = maR; if the pixel at coordinates (x, y) is an edge pixel, then... maR represents the maximum value of the preset adaptive radius, imgfcum(x,y) represents the pixel value of the pixel at coordinates (x,y), and mxval represents the maximum value of the pixel value in imgfcum.

[0080] The intermediate image is obtained by utilizing the feature of similar pixel values ​​among adjacent pixels, thus transforming the acquisition process from a conventional estimation process to a process of obtaining the maximum pixel value, effectively reducing the time required to acquire the intermediate image and improving the processing efficiency of this invention. In the process of obtaining the maximum value, this invention introduces the concept of an adaptive radius. For non-edge pixels, the corresponding adaptive radius is a fixed value, while for edge pixels, the adaptive radius increases with the increase of the pixel value, because the larger the pixel value, the greater its influence on surrounding pixels. The adaptive radius can improve the accuracy of the obtained intermediate image, ensuring that the pixels in the intermediate image accurately reflect the distribution of pixel values ​​in the state image.

[0081] Preferably, the detailed restoration processing of the intermediate image to obtain the restored image includes:

[0082] The following formula is used to perform the first detail restoration process on the mediator image:

[0083]

[0084] In the formula, optitrimg represents the image obtained by the first detail restoration process, optitrimg(h) represents the pixel value of pixel h in the intermediate image after the first detail restoration process, Φ represents the scaling parameter, dowflit(itrimg(h)) represents the pixel value of pixel h after the boundary enhancement process of pixel h in itrimg, imgfcum(h) represents the pixel value of the pixel h in itrimg corresponding to the pixel in imgfcum, imgfcum(std) represents the pixel value of the pixel std with the largest pixel value in imgfcum, and itrimg(std) represents the pixel value of the pixel std corresponding to the pixel in itrimg.

[0085] The adaptive inpainting algorithm is used to perform a second detail restoration process on optitrimg to obtain the restored image.

[0086] In the repair process, the present invention employs a two-stage repair method. The first repair process can improve the boundary detail information in the intermediate image. However, in the process of improving the boundary detail, false details may be generated in some areas. Therefore, the present invention removes these false details through a second detail repair process, thereby obtaining an accurate repaired image.

[0087] Specifically, in the first repair process, in addition to considering boundary protrusion processing, the present invention also considers the detailed features in the luminance component image. Through the right side of the formula, the detailed features in the luminance component image are projected onto the intermediate image, thereby comprehensively improving the content of detailed information in the repaired image, which is beneficial to improving the content of detailed information in the illumination-optimized image.

[0088] Preferably, the boundary highlighting processing of pixel h in itrimg includes:

[0089] Use the following formula to highlight the boundary of pixel h:

[0090]

[0091] Where U(h) represents the set of pixels within a window of size (2D+1)×(2D+1) centered at pixel h, D represents the window size control parameter, itrimg(h) and itrimg(j) represent the gradient magnitudes of pixels h and j, respectively, dislmg(h,j) represents the distance between pixels h and j, and η val This represents the standard deviation of the difference between the gradient magnitudes of pixels in U(h) and pixels h. It represents the standard deviation of the distance between pixels in U(h) and pixel h.

[0092] During the boundary enhancement process, interference information generated during the acquisition of the state image was removed. Pixel processing considered both gradient magnitude and distance, ensuring that interference information was removed while avoiding the loss of detailed information.

[0093] Preferably, an adaptive inpainting algorithm is used to perform a second detail restoration process on optitrimg to obtain a restored image, including:

[0094] Establish a repair model:

[0095]

[0096] Where Q(twitrimg(h)) represents the restoration model, λ and μ represent weight coefficients, twitrimg(h) represents the pixel value of pixel h in the restored image twitrimg, and Θ represents the radial basis function. Ψ represents the control parameter;

[0097] Solve the restoration model to obtain the value of twitrimg(h) that minimizes Q(twitrimg(h)), thereby obtaining the restored image twitrimg.

[0098] In the second detail restoration process, this invention establishes a restoration model. The left part of the model is used to preserve detail information, while the right part is used to remove false details. This allows the restored image to accurately represent the illumination distribution in the state image, which is beneficial for improving the accuracy of subsequent illumination optimization processing based on Retinex theory.

[0099] Preferably, the step of obtaining an illumination-optimized image based on the repaired image includes:

[0100] Convert the repaired image to the RGB color space to obtain the image δ;

[0101] The illumination-optimized image optl is obtained using the following formula:

[0102] Log(optl)=Log(itimg)-Log(δ)

[0103] Here, itimg represents the state image.

[0104] Preferably, the step of performing noise reduction processing on the illumination-optimized image to obtain a noise-reduced image includes:

[0105] The wavelet denoising algorithm is used to denoise the illumination-optimized image to obtain a denoised image.

[0106] Specifically, noise reduction processing can effectively reduce the impact of noisy pixels on the accuracy of image recognition, because noisy pixels affect the image features obtained during the image recognition process.

[0107] Preferably, the step of performing image segmentation processing on the denoised image to obtain a preprocessed image includes:

[0108] Image segmentation algorithms are used to obtain the foreground region in the denoised image, and the foreground region is used as the preprocessed image.

[0109] Specifically, after image segmentation, the background part that is not related to the detection target is removed, leaving only the foreground part, which greatly reduces the number of pixels entering the image recognition stage and can improve the speed of image recognition.

[0110] Preferably, the image recognition model includes a convolutional neural network.

[0111] Preferably, the evaluation module includes a computing unit, a storage unit, and an evaluation unit;

[0112] The calculation unit is used to calculate the area of ​​the assessment scope;

[0113] The storage unit is used to store the coverage radius, the area of ​​the assessment scope, the list of normally operating elderly care public service facilities, and the satisfaction level of each category of elderly care public service facilities;

[0114] The calculation unit is also used to calculate the coverage rate and comprehensive evaluation score for each type of elderly care public service facility;

[0115] The assessment unit is used to rank various types of elderly care public service facilities based on comprehensive assessment scores to obtain assessment results.

[0116] Preferably, the coverage rate of the elderly care public service facilities is calculated in the following way:

[0117] For the i-th category of elderly care public service facilities, the coverage rate is cvrg i The following formula is used for calculation:

[0118]

[0119] In the formula, num i Let R represent the number of normally operating elderly care public service facilities in the i-th category, i∈[1,N], where N represents the total number of elderly care public service facility categories, and R i The radius of the public service facility for the i-th category of elderly care is represented by tlarea, and the area of ​​the assessment scope is represented by dcarea. iThis represents the area of ​​the i-th category of elderly care public service facilities that is counted repeatedly.

[0120] This invention focuses on the community living circle of the elderly. The elderly walk at a speed of approximately 40-50 m / min (walking speed approximately 0.8 m / s), and their activity fatigue limit is about 15 minutes. The upper limit of the facility coverage radius is set at an area that the elderly can reach within 15 minutes' walk, i.e., within 800 meters. This invention supplements existing regulations related to community living circles. The coverage radius and setting requirements for various types of elderly care public service facilities are shown in Table 1 below.

[0121] Table 1. Coverage radius and setup requirements for various types of elderly care public service facilities

[0122] Facility Name Setup Requirements Coverage radius Day care center 5 minutes walk 300m Elderly canteen 5 minutes walk 300m elderly care institutions 15-minute walk 800m Home-based elderly care integrated service platform 15-minute walk 800m

[0123] The area to be assessed can be measured using ArcGIS's area measurement tool.

[0124] Preferably, the comprehensive evaluation score is calculated in the following manner:

[0125]

[0126] In the formula, comassscr i cvrg represents the comprehensive evaluation score of the i-th category of elderly care public service facilities. i cvrst represents the coverage rate of the i-th category of elderly care public service facilities, and stif represents the preset maximum coverage rate. i Let represent the satisfaction level of the public service facilities for the elderly in the i-th category, tifst represent the preset maximum satisfaction level, and δ represent the proportional parameter, δ∈(0,1).

[0127] Satisfaction levels can be obtained through questionnaires.

[0128] As a preferred approach, after calculating the comprehensive evaluation score for each category of elderly care public service facilities, the evaluation results are obtained based on the scores. The category of elderly care public service facilities with the highest comprehensive evaluation scores are those that are already relatively complete, while the category of elderly care public service facilities with the lowest scores are those that still need further strengthening of construction efforts.

[0129] In particular, according to embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), it performs the functions defined in the methods of this application. It should be noted that the computer-readable medium described above in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wire segments, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless segments, wire segments, optical fibers, RF, etc., or any suitable combination thereof.

[0130] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are merely examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functions and structural principles of the present invention have been shown and explained in the embodiments. Without departing from the stated principles, the implementation of the present invention may have any variations or modifications.

Claims

1. A comprehensive evaluation system for public service facilities for the elderly, characterized in that, It includes an input module, a confirmation module, and an evaluation module; The input module is used by staff to input the category and assessment scope of elderly care public service facilities; The confirmation module includes an acquisition unit and a confirmation unit; The acquisition unit is used to acquire the addresses of elderly care public service facilities that conform to the aforementioned category; The confirmation unit is used to obtain the status image of the elderly care public service facility corresponding to the address through the drone, and confirm whether the elderly care public service facility is operating normally based on the status image; The assessment module is used to evaluate the rationality of the distribution of elderly care public service facilities based on the normal operation of the facilities, and to obtain the assessment results. The confirmation unit includes a drone and a terminal device; The drone is used to acquire status images of the elderly care public service facilities corresponding to the address and send the status images to the terminal device; The terminal equipment is used to perform image recognition processing on the status images to confirm whether the public service facilities for the elderly are operating normally. The process of performing image recognition processing on the status image to confirm whether the elderly care public service facilities are operating normally includes: The state image is preprocessed to obtain a preprocessed image; The preprocessed image is input into an image recognition model for processing. The model determines whether the preprocessed image contains objects of a preset type. If so, it indicates that the elderly care public service facility is operating normally; otherwise, it indicates that the facility is not operating normally. The preprocessing of the status image to obtain the preprocessed image includes: The state image is subjected to illumination optimization processing to obtain an illumination-optimized image; The image with optimized lighting is denoised to obtain a denoised image; The denoised image is segmented to obtain a preprocessed image; The step of performing illumination optimization processing on the state image to obtain an illumination-optimized image includes: Obtain the mediator image corresponding to the state image; Perform detail restoration on the intermediate image to obtain the restored image; Obtain an optimized illumination image based on the restored image; The intermediate image corresponding to the obtained state image includes: Convert the status image to the Lab color space; Obtain the image imgfcum of the luminance component corresponding to the state image in the Lab color space; Use the following formula to obtain the mediator image: Where, itrimg represents the intermediate image, itrimg(x,y) represents the pixel value of the pixel with coordinates (x,y) in imgfcum in itrimg, and U(x,y) represents the set of judgment pixels in imgfcum with the pixel with coordinates (x,y) as the center and an adaptive radius of T(x,y); imgfcum d This represents the pixel value of pixel d in U(x,y), where mas represents the maximum value. The adaptive radius is obtained as follows: If the pixel at coordinates (x, y) is not an edge pixel, then T(x, y) = maR; if the pixel at coordinates (x, y) is an edge pixel, then... maR represents the maximum value of the preset adaptive radius, imgfcum(x,y) represents the pixel value of the pixel at coordinates (x,y), and mxval represents the maximum value of the pixel value in imgfcum.

2. The comprehensive evaluation system for elderly care public service facilities according to claim 1, characterized in that, The categories of public service facilities for the elderly include day care centers, senior canteens, elderly care institutions, and integrated home-based elderly care service platforms.

3. The comprehensive evaluation system for elderly care public service facilities according to claim 1, characterized in that, Obtaining the address of elderly care public service facilities that conform to the aforementioned category includes: Enter the category as a keyword into a map website to obtain the addresses of elderly care public service facilities that match the category within the assessment scope.

4. The comprehensive evaluation system for elderly care public service facilities according to claim 1, characterized in that, The image recognition model includes a convolutional neural network.

5. The comprehensive evaluation system for elderly care public service facilities according to claim 1, characterized in that, The evaluation module includes a computing unit, a storage unit, and an evaluation unit; The calculation unit is used to calculate the area of ​​the assessment scope; The storage unit is used to store the coverage radius, the area of ​​the assessment scope, the list of normally operating elderly care public service facilities, and the satisfaction level of each category of elderly care public service facilities; The calculation unit is also used to calculate the coverage rate and comprehensive evaluation score for each type of elderly care public service facility; The assessment unit is used to rank various types of elderly care public service facilities based on comprehensive assessment scores to obtain assessment results.

6. The comprehensive evaluation system for elderly care public service facilities according to claim 5, characterized in that, The coverage rate of the aforementioned public service facilities for the elderly is calculated as follows: For the i-th category of elderly care public service facilities, the coverage rate is cvrg i The following formula is used for calculation: In the formula, num i Let R represent the number of normally operating elderly care public service facilities in the i-th category, i∈[1,N], where N represents the total number of elderly care public service facility categories, and R i The radius of the public service facility for the i-th category of elderly care is represented by tlarea, and the area of ​​the assessment scope is represented by dcarea. i This represents the area of ​​the i-th category of elderly care public service facilities that is counted repeatedly.

7. The comprehensive evaluation system for elderly care public service facilities according to claim 6, characterized in that, The overall evaluation score is calculated in the following manner: In the formula, comassscr i cvrg represents the comprehensive evaluation score of the i-th category of elderly care public service facilities. i cvrst represents the coverage rate of the i-th category of elderly care public service facilities, and stif represents the preset maximum coverage rate. i Let represent the satisfaction level of the public service facilities for the elderly in the i-th category, tifst represent the preset maximum satisfaction level, and δ represent the proportional parameter, δ∈(0,1).

Citation Information

Patent Citations

  • Method and device for screening cell suitable for old people, electronic equipment and computer readable medium

    CN114817427A

  • Road network monitoring method, device and equipment based on AI and readable storage medium

    CN115131744A