Method for intelligent monitoring and early warning of accommodation site cleaning and disinfection

Abstract

This application relates to the field of monitoring technology and discloses an intelligent monitoring and early warning method for cleaning and disinfection in accommodation facilities. This method can monitor and record the disinfection process in real time, ensuring that hotel supplies are properly disinfected according to prescribed hygiene standards. Any non-compliant procedures can be reported. The method includes: acquiring a first video stream from a first camera; determining, through image recognition, whether cleaning personnel have entered the disinfection room within a preset time; if not, issuing a first alarm. Based on the first video stream, determining whether the attire of the cleaning personnel entering the disinfection room meets preset standards; if not, issuing a second alarm. Acquiring a second video stream from a second camera, the second video stream including areas of a first, second, and third water tank; determining whether there are any objects other than cups in the first water tank; if so, issuing a third alarm. Based on a first electrical signal emitted by a first sensor in the second water tank, determining whether the liquid in the second water tank is disinfectant; if not, issuing a fourth alarm; and determining whether the soaking time of the cups in the second water tank meets a first threshold; if not, issuing a fifth alarm. Comparing the distance between the cups and towels in the third water tank; if the distance is lower than a second threshold, issuing a sixth alarm.

Description

Technical Field

[0001] This application relates to the field of monitoring technology, and in particular to a method for monitoring the disinfection process in a disinfection room. Background Technology

[0002] This section is intended to provide background or context for the embodiments of this application as set forth in the claims. The content in this section is for reference only and does not constitute an admission or confirmation that it is prior art that has been disclosed.

[0003] In the modern hotel industry, ensuring the health and safety of customers is paramount. Proper cleaning and disinfection of hotel supplies is a fundamental requirement. However, observations and market research reveal significant irregularities in the disinfection processes of many hotels, which not only affect the effectiveness of disinfection but may also pose a threat to customer health and safety.

[0004] First, existing disinfection room procedures often lack standardization and systematicity. Observations have revealed that some hotel disinfection staff rarely or for extended periods enter the disinfection room during routine operations, indicating that corresponding hotel equipment is not being disinfected daily as required. According to industry standards, hotel equipment should be disinfected daily to ensure hygiene and safety, but this requirement is often overlooked in practice.

[0005] Secondly, some staff members wipe cups and other tableware with towels. While this removes surface stains, it fails to effectively kill potential bacteria and viruses. The correct disinfection method involves using specialized equipment, such as a disinfection pool or cabinet. In a disinfection pool, utensils should be immersed in disinfectant for a certain period before drying; while physical disinfection cabinets use ultraviolet light or high temperatures to achieve disinfection.

[0006] Due to the inadequacy of existing procedures, the disinfection effect of hotel supplies cannot be fully guaranteed, which may result in residual bacteria and viruses on hotel supplies, increasing the risk of infection for customers. Summary of the Invention

[0007] The purpose of this application is to provide an intelligent monitoring and early warning method for cleaning and disinfection of accommodation facilities, which can monitor and record the disinfection process in real time, ensure that hotel supplies are properly disinfected in accordance with the prescribed hygiene standards, and report relevant information if there are any irregularities in the process.

[0008] This application discloses an intelligent monitoring and early warning method for cleaning and disinfection of accommodation facilities, including:

[0009] The system acquires the first video stream captured by the first camera, and uses image recognition to determine whether cleaning personnel have entered the disinfection room within a preset time. If not, it issues the first alarm.

[0010] Based on the first video stream, determine whether the clothing of the cleaning personnel entering the disinfection room meets the preset standard; if not, issue a second alarm.

[0011] Acquire a second video stream captured by a second camera, the second video stream including the areas of the first pool, the second pool, and the third pool;

[0012] Based on the second video stream, perform the following operations:

[0013] Determine if there are any objects other than cups in the first pool; if so, issue a third alarm.

[0014] Based on the first electrical signal emitted by the first sensor in the second water tank, it is determined whether the liquid in the second water tank is disinfectant. If not, a fourth alarm is issued. Furthermore, it is determined whether the soaking time of the cup in the second water tank meets a first threshold. If not, a third alarm is issued.

[0015] Five alerts;

[0016] If the distance between the cup and the towel in the third pool is lower than the second threshold, a sixth alarm is issued.

[0017] In a preferred embodiment, the step of determining whether cleaning personnel have entered the disinfection room within a preset time period through image recognition further includes:

[0018] The first video stream acquired is preprocessed;

[0019] An algorithm is used to determine whether objects in the first video stream contain human bodies;

[0020] If the object in the first video stream contains a human body, record the timestamp when the human body appears in the first video stream.

[0021] Calculate the difference between the current timestamp and the timestamp of the last record. If the difference is greater than the preset time, issue the first alarm.

[0022] In a preferred embodiment, the step of determining whether cleaning personnel have entered the disinfection room within a preset time period through image recognition further includes:

[0023] The first video stream acquired is preprocessed;

[0024] An algorithm is used to determine whether objects in the first video stream contain human bodies;

[0025] Whenever a human body is detected, the existing timer is reset and a new timer is started;

[0026] If the new timer is not reset within the preset time, the first alarm will be issued.

[0027] In a preferred embodiment, determining whether the attire of the cleaning personnel entering the disinfection room meets the preset standards further includes:

[0028] A convolutional neural network is trained using image samples that meet the preset criteria to obtain a clothing judgment model;

[0029] A predefined workwear feature library is established, which includes workwear feature vectors. The workwear feature vectors are obtained by extracting features from the image samples labeled as workwear during the training phase of the clothing judgment model.

[0030] Load the clothing judgment model and input the preprocessed first video stream into the clothing judgment model;

[0031] The clothing judgment model extracts a first video stream feature vector for each captured first video stream, and the first video stream feature vector includes visual information in the first video stream;

[0032] The similarity between the workwear feature vector and the first video stream feature vector is compared. If the similarity is lower than the similarity threshold, the second alarm is issued.

[0033] In a preferred embodiment, determining whether there are any foreign objects other than cups in the first pool further includes:

[0034] The second video stream is preprocessed, and the interior of the first pool is set as the first region of interest in the second video stream;

[0035] A deep learning model is used to detect all objects in the second video stream. The deep learning model provides bounding boxes for the objects. It is determined whether the bounding boxes are located within the first region of interest. The detected objects are classified as cup items and non-cup items.

[0036] If the bounding box within the first region of interest is a bounding box for a non-cup item, then the third alarm is issued.

[0037] In a preferred embodiment, determining whether the liquid in the second water tank is a disinfectant further includes:

[0038] The second video stream is preprocessed, and the interior of the second water pool is set as the second region of interest in the second video stream;

[0039] The first deep learning model is used to analyze the preprocessed second video stream to determine whether there are bubbles in the second region of interest. If there are no bubbles in the second region of interest, the fourth alarm is issued.

[0040] In a preferred embodiment, determining whether the liquid in the second water tank is a disinfectant further includes:

[0041] The conductivity of the second water tank is obtained by a conductivity meter, and the first electrical signal including the conductivity is sent to the data processing unit.

[0042] The data processing unit determines whether the conductivity is lower than the conductivity threshold of the disinfectant. If so, it issues the fourth alarm.

[0043] In a preferred embodiment, determining whether the liquid in the second water tank is a disinfectant further includes:

[0044] The infrared spectrum of the second water tank is obtained by an infrared detector, and it is determined whether the infrared spectrum matches the infrared spectrum of the disinfectant. If it does not match, the fourth alarm is issued.

[0045] In a preferred embodiment, comparing the distance between the cup and the towel in the third pool further includes:

[0046] The second video stream acquired is preprocessed;

[0047] A second deep learning model is used to detect objects in the second video stream, the deep learning model being used to identify towels and cups and to provide towel bounding boxes and cup bounding boxes;

[0048] The system analyzes whether the bounding boxes of the towel and the cup provided by the deep learning model have overlapping areas. If there are overlapping areas, the system calculates the intersection area of ​​the bounding boxes of the towel and the cup. If the intersection area exceeds a preset threshold, the sixth alarm is issued.

[0049] This application also discloses an intelligent monitoring and early warning method for cleaning and disinfection of accommodation facilities, including:

[0050] The system acquires the first video stream captured by the first camera, and uses image recognition to determine whether cleaning personnel have entered the disinfection room within a preset time. If not, it issues the first alarm.

[0051] Based on the first video stream, the first feature in the first video stream is compared with the first feature vector pre-stored in the database to determine whether the clothing of the cleaning personnel entering the disinfection room meets the preset standard. If not, a second alarm is issued.

[0052] The system acquires a second video stream captured by a second camera, which includes the areas of the first and second pools. It then determines whether there are any objects other than cups in the first and second pools. If so, it issues a third alarm.

[0053] The operating power of the disinfection cabinet is obtained from the smart socket connected to the disinfection cabinet. The operating power is compared with a third threshold. If the operating power is lower than the third threshold, a seventh alarm is issued. Furthermore, it is determined whether the duration of the operating power greater than the third threshold meets a fourth threshold. If not, an eighth alarm is issued.

[0054] In this embodiment, multiple high-precision cameras and sensors are integrated to collect and analyze data in real time at each stage of the disinfection room operation. First, using images acquired by the first camera, the system uses image recognition technology to determine whether cleaning personnel have entered the disinfection room on time. If no personnel are detected, the system will automatically issue a first alarm to prompt management personnel to intervene. In addition, the system can also determine whether the cleaning personnel's attire meets preset safety standards based on images acquired by the cameras. If there is a violation, a second alarm is triggered. While the first camera monitors the entire disinfection room, the invention uses a second camera to monitor the first, second, and third water tank areas for the use of the disinfection pools. To ensure the disinfection process is standardized and free of contaminants, the system monitors the second pool using a first sensor to verify that the liquid is the prescribed disinfectant. If the liquid does not meet the standards, a fourth alarm is triggered. Simultaneously, the system calculates the soaking time of cups and utensils in the disinfectant solution. If the soaking time does not reach the first threshold, a fifth alarm is triggered to ensure that each utensil is thoroughly disinfected. By comparing the distance between cups and towels in the third pool, a sixth alarm is triggered if the distance is below the set second threshold to prevent cross-contamination. This comprehensive monitoring method not only improves the operational quality and effectiveness of disinfection but also significantly reduces the risk of human negligence through a systematic feedback and alarm mechanism, thereby enhancing the overall hygiene and safety standards of the hotel service.

[0055] Furthermore, through image processing and human body recognition technology, the entry and exit of cleaning personnel can be monitored in real time, and the standardized use of the disinfection room can be ensured by checking whether the timer has been reset. This real-time data recording and analysis not only improves the accuracy of monitoring, but also significantly enhances the automation level of disinfection room management. In addition, the clothing judgment model trained by convolutional neural networks significantly improves the accuracy of monitoring the compliance of cleaning personnel's clothing, and enhances the safety and hygiene standards of the working environment.

[0056] Furthermore, by using deep learning models to accurately identify and classify objects in the disinfection room, as well as conductivity and infrared spectroscopy analysis techniques, the chemical composition and activity state of the disinfectant can be effectively monitored, ensuring that the second pool uses disinfectant and that it remains effective at all times. In addition, by analyzing the spatial relationship between towels and cups, potential cross-contamination between towels and cups can be effectively prevented, thereby significantly improving the scientific nature and safety of the entire disinfection process.

[0057] Furthermore, by monitoring the operating power of the disinfection cabinet, the system can not only determine whether the disinfection cabinet is in normal working condition, but also ensure the continuous operating efficiency of the disinfection cabinet by monitoring the power maintenance time. If the power is lower than or the maintenance time is insufficient to achieve the predetermined disinfection effect, the system will issue a corresponding alarm, thereby ensuring the effectiveness and reliability of the disinfection equipment.

[0058] The various technical features disclosed in the above-described invention, the various technical features disclosed in the following embodiments and examples, and the various technical features disclosed in the accompanying drawings can be freely combined to form various new technical solutions (all of which should be considered as having been recorded in this specification), unless such a combination of technical features is technically infeasible. For example, in one example, feature A+B+C is disclosed, and in another example, feature A+B+D+E is disclosed. Features C and D are equivalent technical means that serve the same function, and technically only one needs to be used; it is impossible to use both simultaneously. Feature E can be technically combined with feature C. Therefore, the solution A+B+C+D should not be considered as having been recorded because it is technically infeasible, while the solution A+B+C+E should be considered as having been recorded. Attached Figure Description

[0059] Figure 1 This is a schematic diagram of the intelligent monitoring and early warning model according to the first embodiment of this application;

[0060] Figure 2 This is a schematic diagram of the intelligent monitoring and early warning model according to the first embodiment of this application;

[0061] Figure 3 This is a schematic diagram of the intelligent monitoring and early warning model according to the first embodiment of this application;

[0062] Figure 4 This is a schematic diagram of the intelligent monitoring and early warning model according to the first embodiment of this application;

[0063] Figure 5 This is a schematic diagram of the intelligent monitoring and early warning model according to the first embodiment of this application;

[0064] Figure 6This is a schematic diagram of the intelligent monitoring and early warning model according to the first embodiment of this application;

[0065] Figure 7 This is a schematic diagram of the intelligent monitoring and early warning model according to the second embodiment of this application. Detailed Implementation

[0066] In the following description, many technical details are presented to help the reader better understand this application. However, those skilled in the art will understand that the technical solutions claimed in this application can be implemented even without these technical details and various variations and modifications based on the following embodiments.

[0067] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0068] The first embodiment of this application relates to an intelligent monitoring and early warning method for cleaning and disinfection of accommodation facilities, the process of which is as follows: Figure 1 As shown, the method includes the following steps:

[0069] In step 101, the first video stream captured by the first camera is acquired, and image recognition is used to determine whether cleaning personnel have entered the disinfection room within a preset time. If not, the first alarm is issued.

[0070] In step 102, based on the first video stream, it is determined whether the attire of the cleaning personnel entering the disinfection room meets the preset standards. If not, a second alarm is issued.

[0071] In step 103, the second video stream captured by the second camera is obtained. The second video stream includes the areas of the first pool, the second pool and the third pool. It is determined whether there are any foreign objects outside the cup in the first pool. If so, a third alarm is issued.

[0072] In step 104, based on the first electrical signal emitted by the first sensor in the second pool, it is determined whether the liquid in the second pool is disinfectant. If not, a fourth alarm is issued. Furthermore, it is determined whether the soaking time of the cup in the second pool meets the first threshold. If not, a fifth alarm is issued.

[0073] In step 105, the distance between the cup and the towel in the third pool is compared. If the distance is lower than the second threshold, a sixth alarm is issued.

[0074] In an optional embodiment, such as Figure 2 As shown, step 101 may also include:

[0075] In step 201, the acquired first video stream is preprocessed. Optionally, the preprocessing steps may include, but are not limited to, resizing, cropping, noise reduction, and color normalization, to facilitate subsequent operations.

[0076] In step 202, it is confirmed whether the objects in the first video stream include human bodies.

[0077] In step 203, if the object in the first video stream contains a human body, the timestamp of when the human body appears in the first video stream is recorded.

[0078] In step 204, the difference between the current timestamp and the timestamp of the last record is calculated. If the difference is greater than a preset time, a first alarm is issued.

[0079] In an optional embodiment, the timestamp of each human body detected is stored in a database or system file.

[0080] In an optional embodiment, such as Figure 3 As shown, step 101 may also include:

[0081] In step 301, the first video stream acquired is preprocessed.

[0082] In step 302, an algorithm is used to determine whether the objects in the first video stream contain human bodies.

[0083] In step 303, whenever a human body is detected, the existing timer is reset and a new timer is started.

[0084] In step 304, if the new timer is not set within a preset time, a first alarm is issued.

[0085] In an optional embodiment, such as Figure 4 As shown, step 102 may also include:

[0086] In step 401, input image samples that meet preset standards to train a convolutional neural network to obtain a clothing judgment model.

[0087] In step 402, a predefined workwear feature library is established. The workwear feature library includes workwear feature vectors, which are obtained by extracting features from image samples labeled as workwear during the training phase of the clothing judgment model.

[0088] In step 403, the clothing judgment model is loaded by inputting the preprocessed first video stream into the clothing judgment model.

[0089] In step 404, a first video stream feature vector is extracted for each captured first video stream using a clothing judgment model. The first video stream feature vector includes visual information from the first video stream. Optionally, the visual information may include texture, color, and pattern, etc.

[0090] In step 405, the similarity between the work clothes feature vector and the first video stream feature vector is compared. If the similarity is lower than the similarity threshold, a second alarm is issued.

[0091] In an alternative embodiment, the feature vector of the first video stream extracted in real time can be compared with the feature vector of the work clothes by using a vector similarity metric such as cosine similarity or Euclidean distance.

[0092] In an optional embodiment, such as Figure 5 As shown, step 103 may also include:

[0093] In step 501, the acquired second video stream is preprocessed, and the interior of the first water tank is set as the first region of interest in the second video stream.

[0094] In step 502, a deep learning model is used to detect all objects in the second video stream. The deep learning model provides bounding boxes for the objects, determines whether the bounding boxes are located within the first region of interest, and classifies the detected objects into cup-shaped items and non-cup-shaped items.

[0095] In step 503, if the bounding box within the first region of interest is a bounding box for a non-cup item, a third alarm is issued.

[0096] In an optional embodiment, step 104 may further include:

[0097] The second video stream is preprocessed, and the interior of the second water pool is set as the second region of interest in the second video stream.

[0098] The first deep learning model is used to analyze the preprocessed second video stream to determine whether there are bubbles in the second region of interest. If there are no bubbles in the second region of interest, a fourth alarm is issued.

[0099] In an optional embodiment, the second video stream detects whether there is an action of pouring disinfectant and whether there is an action of taking out a cup. If so, the duration between the action of pouring disinfectant and the action of taking out the cup is calculated to determine whether the soaking time meets the first threshold.

[0100] In an optional embodiment, the action of pouring disinfectant is detected in the second video stream, and it is determined whether there are air bubbles in the second region of interest.

[0101] In an optional embodiment, step 104 may further include:

[0102] The conductivity of the second water tank is obtained by a conductivity meter, and a first electrical signal including the conductivity is sent to the data processing unit.

[0103] The data processing unit determines whether the conductivity is lower than the conductivity threshold of the disinfectant. If so, it issues the fourth alarm.

[0104] In an optional embodiment, step 104 may further include:

[0105] The infrared spectrum of the second water tank is obtained by an infrared detector to determine whether the infrared spectrum matches the infrared spectrum of the disinfectant. If it does not match, a fourth alarm is issued.

[0106] In an optional embodiment, such as Figure 6 As shown, step 105 may also include:

[0107] In step 601, the acquired second video stream is preprocessed.

[0108] In step 602, a second deep learning model is used to detect objects in the second video stream. The deep learning model is used to identify towels and cups and provides bounding boxes for towels and cups.

[0109] In step 603, it is analyzed whether there is an overlapping area between the towel bounding box and the cup bounding box provided by the deep learning model. If there is an overlapping area, the intersection area of ​​the towel bounding box and the cup bounding box is calculated. If the intersection area exceeds a preset threshold, a sixth alarm is issued.

[0110] In an optional embodiment, the result of issuing an alarm and the associated alarm reason can be stored in the system log. For example, the result of issuing a second alarm and the associated first video stream feature vector data can be stored in the system log.

[0111] To better understand the technical solution of this application, a specific example is provided below. The details listed in this example are mainly for ease of understanding and are not intended to limit the scope of protection of this application.

[0112] The system first uses a first camera to capture the initial video stream at the entrance of the disinfection room. Image preprocessing techniques, such as adjusting brightness and contrast and cropping, are used to optimize the image for subsequent processing. A trained convolutional neural network (CNN) model is used to detect the presence of human figures in the image. A timer monitors the time interval between people entering and exiting. If the timer is not reset within a preset time (i.e., no new person enters), the system automatically issues a first alarm. After disinfection personnel enter the disinfection room, the system continues to check whether their attire conforms to a preset work uniform standard. The system's built-in attire judgment model extracts feature vectors from the personnel images and compares them with a predefined work uniform feature library. If the similarity is lower than a preset threshold, the personnel's attire is deemed non-compliant, triggering a second alarm.

[0113] While the first camera captures the initial video stream at the entrance of the disinfection room, the second camera captures images of the three water tank areas. The system preprocesses the images from this second video stream and defines each water tank as a different region of interest. The system uses a deep learning model to detect objects within each region and identify whether they are cups or non-cup items. If a non-cup item is detected in the first water tank, the system will issue a third alarm. Furthermore, monitoring of the second water tank includes not only detection using a visual model but also determining whether the liquid in the tank is disinfectant using an installed conductivity sensor. If the conductivity indicates that the liquid is not disinfectant or the cup soaking time does not meet a preset threshold, the system will issue a fourth and fifth alarm, respectively. Monitoring of the third water tank focuses on detecting the distance between the cups and towels. When these two are too close, the system calculates the intersection area of ​​their bounding boxes and issues a sixth alarm if this area exceeds a predetermined threshold.

[0114] Through the highly integrated technical solution of this application, the monitoring system can not only provide real-time feedback on the current hygiene status, but also help optimize the disinfection and cleaning process through long-term data analysis, providing strong technical support for maintaining high standards of hygiene and safety.

[0115] The second embodiment of this application relates to an intelligent monitoring and early warning method for cleaning and disinfection of accommodation facilities, the process of which is as follows: Figure 7 As shown, the method includes the following steps:

[0116] In step 701, the first video stream captured by the first camera is acquired, and image recognition is used to determine whether cleaning personnel have entered the disinfection room within a preset time. If not, the first alarm is issued.

[0117] In step 702, based on the first video stream, the feature vector of the first video stream in the first video stream is compared with the work clothes feature vector stored in the database to determine whether the clothing of the cleaning personnel entering the disinfection room meets the preset standard. If not, a second alarm is issued.

[0118] In step 703, the second video stream captured by the second camera is acquired. The second video stream includes the areas of the first pool and the second pool. It is determined whether there are any foreign objects other than cups in the first pool and the second pool. If so, a third alarm is issued.

[0119] In step 704, the operating power of the disinfection cabinet is obtained from the smart socket connected to the disinfection cabinet. The operating power is compared with the third threshold. If the operating power is lower than the third threshold, a seventh alarm is issued. Furthermore, it is determined whether the operating power duration greater than the third threshold meets the fourth threshold. If not, an eighth alarm is issued.

[0120] In an optional embodiment, the second video stream includes a first water tank, a second water tank, and a disinfection cabinet area. The second video stream is preprocessed to determine whether the disinfection cabinet door is opened in the second video stream.

[0121] In one optional embodiment, the smart socket connects to a gateway via a wireless communication protocol. The gateway can be connected to a network switch via wired or wireless connection. The network switch is connected to an edge server via a network cable. The smart socket sends a first electrical signal when the operating power of the physical sterilizer falls below a third threshold. The third threshold, defined as the minimum power required for the physical sterilizer to sterilize cups inside during normal operation, is set via the management terminal's interface. The gateway, acting as the core node for data aggregation and transmission, receives power data from the smart socket and video streams from the camera. The network switch connects to the edge server via a high-speed Ethernet cable for storing and processing large amounts of data, including video analytics and power monitoring data. The edge server performs real-time data analysis, identifying any instances where the sterilizer's power falls below the threshold or any non-compliant scenes captured by the camera. When the smart socket detects that the sterilizer's power is below the third threshold, it automatically sends an alarm signal to the gateway. Similarly, the AI ​​camera automatically sends an alarm when it detects any abnormal activity. Upon receiving the alarm, the gateway immediately sends the alarm information to the management terminal via the network switch, allowing operators to respond quickly and take necessary maintenance or emergency measures.

[0122] The first embodiment is a method embodiment corresponding to this embodiment. The technical details in the first embodiment can be applied to this embodiment, and vice versa. The difference between this embodiment and the first embodiment is that the disinfection method used in this embodiment is a physical disinfection method using a disinfection cabinet.

[0123] Accordingly, embodiments of this application also provide a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the various method embodiments of this application. Computer-readable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device. As defined herein, computer-readable storage media does not include transient media, such as modulated data signals and carrier waves.

[0124] Furthermore, embodiments of this application also provide a computer program product, including computer-executable instructions that, when executed by a processor, implement the steps in the above-described method embodiments.

[0125] It should be noted that in this application, relational terms 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 thereof 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 a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. In this application, if it refers to performing an action according to an element, it means performing the action at least according to that element, including two cases: performing the action only according to that element, and performing the action according to that element and other elements. Expressions such as "multiple," "repeatedly," and "various" include two, two times, two kinds, and more than two, more than two times, and more than two kinds.

[0126] The numbering used in describing the steps of a method does not inherently limit the order of these steps. For example, a step with a higher number does not necessarily have to be executed after a step with a lower number; it can be executed first and then second, or even in parallel, as long as this execution order is reasonable to someone skilled in the art. Similarly, multiple steps with consecutively numbered sequences (e.g., step 101, step 102, step 103, etc.) do not restrict other steps from being executed between them; for example, there can be other steps between step 101 and step 102.

[0127] This specification includes combinations of various embodiments described herein. Individual references to embodiments are made (e.g., "one embodiment," "some embodiments," or "preferred embodiments"); however, these embodiments are not mutually exclusive unless indicated to be mutually exclusive or are readily apparent to those skilled in the art. It should be noted that the word "or" is used in a non-exclusive sense throughout this specification unless the context explicitly indicates or requires it.

[0128] All references to this specification are considered to be incorporated integrally into the disclosure of this application so that they can serve as the basis for modifications if necessary. Furthermore, it should be understood that the above descriptions are merely preferred embodiments of this specification and are not intended to limit the scope of protection of this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of one or more embodiments of this specification should be included within the scope of protection of one or more embodiments of this specification.

[0129] In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for intelligent monitoring and early warning of cleaning and disinfection in accommodation facilities, characterized in that, include: The system acquires the first video stream captured by the first camera, and uses image recognition to determine whether cleaning personnel have entered the disinfection room within a preset time. If not, it issues the first alarm. Based on the first video stream, determine whether the clothing of the cleaning personnel entering the disinfection room meets the preset standard; if not, issue a second alarm. Acquire a second video stream captured by a second camera, the second video stream including the areas of the first pool, the second pool, and the third pool; Based on the second video stream, perform the following operations: Determine if there are any objects other than cups in the first pool; if so, issue a third alarm. Based on the first electrical signal emitted by the first sensor in the second water tank, it is determined whether the liquid in the second water tank is disinfectant. If not, a fourth alarm is issued. Furthermore, it is determined whether the soaking time of the cup in the second water tank meets the first threshold. If not, a fifth alarm is issued. If the distance between the cup and the towel in the third pool is lower than the second threshold, a sixth alarm is issued.

2. The intelligent monitoring and early warning method for cleaning and disinfection of accommodation facilities as described in claim 1, characterized in that, The method of determining whether cleaning personnel have entered the disinfection room within a preset time using image recognition also includes: The first video stream acquired is preprocessed; An algorithm is used to determine whether objects in the first video stream contain human bodies; If the object in the first video stream contains a human body, record the timestamp when the human body appears in the first video stream. Calculate the difference between the current timestamp and the timestamp of the last record. If the difference is greater than the preset time, issue the first alarm.

3. The intelligent monitoring and early warning method for cleaning and disinfection of accommodation facilities as described in claim 1, characterized in that, The method of determining whether cleaning personnel have entered the disinfection room within a preset time using image recognition also includes: The first video stream acquired is preprocessed; An algorithm is used to determine whether objects in the first video stream contain human bodies; Whenever a human body is detected, the existing timer is reset and a new timer is started; If the new timer is not reset within the preset time, the first alarm will be issued.

4. The intelligent monitoring and early warning method for cleaning and disinfection of accommodation facilities as described in claim 1, characterized in that, The determination of whether the attire of the cleaning personnel entering the disinfection room meets the preset standards also includes: A convolutional neural network is trained using image samples that meet the preset criteria to obtain a clothing judgment model; A predefined workwear feature library is established, which includes workwear feature vectors. The workwear feature vectors are obtained by extracting features from the image samples labeled as workwear during the training phase of the clothing judgment model. Load the clothing judgment model and input the preprocessed first video stream into the clothing judgment model; The clothing judgment model extracts a first video stream feature vector for each captured first video stream, and the first video stream feature vector includes visual information in the first video stream; The similarity between the workwear feature vector and the first video stream feature vector is compared. If the similarity is lower than the similarity threshold, the second alarm is issued.

5. The intelligent monitoring and early warning method for cleaning and disinfection of accommodation facilities as described in claim 1, characterized in that, The determination of whether there are any foreign objects other than cups in the first pool also includes: The second video stream is preprocessed, and the interior of the first pool is set as the first region of interest in the second video stream; A deep learning model is used to detect all objects in the second video stream. The deep learning model provides bounding boxes for the objects. It is determined whether the bounding boxes are located within the first region of interest. The detected objects are classified as cup items and non-cup items. If the bounding box within the first region of interest is a bounding box for a non-cup item, then the third alarm is issued.

6. The intelligent monitoring and early warning method for cleaning and disinfection of accommodation facilities as described in claim 1, characterized in that, The step of determining whether the liquid in the second water tank is a disinfectant also includes: The second video stream is preprocessed, and the interior of the second water pool is set as the second region of interest in the second video stream; The first deep learning model is used to analyze the preprocessed second video stream to determine whether there are bubbles in the second region of interest. If there are no bubbles in the second region of interest, the fourth alarm is issued.

7. The intelligent monitoring and early warning method for cleaning and disinfection of accommodation facilities as described in claim 1, characterized in that, The step of determining whether the liquid in the second water tank is a disinfectant also includes: The conductivity of the second water tank is obtained by a conductivity meter, and the first electrical signal including the conductivity is sent to the data processing unit. The data processing unit determines whether the conductivity is lower than the conductivity threshold of the disinfectant. If so, it issues the fourth alarm.

8. The intelligent monitoring and early warning method for cleaning and disinfection of accommodation facilities as described in claim 1, characterized in that, The step of determining whether the liquid in the second water tank is a disinfectant also includes: The infrared spectrum of the second water tank is obtained by an infrared detector, and it is determined whether the infrared spectrum matches the infrared spectrum of the disinfectant. If it does not match, the fourth alarm is issued.

9. The intelligent monitoring and early warning method for cleaning and disinfection of accommodation facilities as described in claim 1, characterized in that, The comparison of the distance between the cup and the towel in the third pool also includes: The second video stream acquired is preprocessed; A second deep learning model is used to detect objects in the second video stream, the deep learning model being used to identify towels and cups and to provide towel bounding boxes and cup bounding boxes; The system analyzes whether the bounding boxes of the towel and the cup provided by the deep learning model have overlapping areas. If there are overlapping areas, the system calculates the intersection area of ​​the bounding boxes of the towel and the cup. If the intersection area exceeds a preset threshold, the sixth alarm is issued.

10. A method for intelligent monitoring and early warning of cleaning and disinfection in accommodation facilities, characterized in that, include: The system acquires the first video stream captured by the first camera, and uses image recognition to determine whether cleaning personnel have entered the disinfection room within a preset time. If not, it issues the first alarm. Based on the first video stream, the first feature in the first video stream is compared with the first feature vector pre-stored in the database to determine whether the clothing of the cleaning personnel entering the disinfection room meets the preset standard. If not, a second alarm is issued. The system acquires a second video stream captured by a second camera, which includes the areas of the first and second pools. It then determines whether there are any objects other than cups in the first and second pools. If so, it issues a third alarm. The operating power of the disinfection cabinet is obtained from the smart socket connected to the disinfection cabinet. The operating power is compared with a third threshold. If the operating power is lower than the third threshold, a seventh alarm is issued. Furthermore, it is determined whether the duration of the operating power greater than the third threshold meets a fourth threshold. If not, an eighth alarm is issued.

Images