Multi-sensing interactive medical hand-washing pool control method and integrated hand-washing pool

Abstract

The present invention discloses a multi-sensing interactive medical hand-brushing pool control method and an integrated hand-brushing pool, the method comprising: obtaining multiple infrared signal data by setting multiple infrared sensors in multiple areas of the hand-brushing pool; determining the use parameters of the current user based on the infrared signal data and the corresponding areas based on preset data matching rules; judging whether the hand-brushing behavior of the current user is standardized based on the process data rules corresponding to the use parameters and the infrared signal data; when it is judged that the hand-brushing behavior is not standardized, sending a warning message to the smart mirror of the hand-brushing pool for display. It can be seen that the present invention can effectively improve the standardization of the user's hand-brushing behavior, bring users a smarter and more convenient hand-brushing pool use experience, and reduce the occurrence of medical accidents.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a multi-sensing interactive medical hand-scrubbing pool control method and an integrated hand-scrubbing pool. Background Art

[0002] The standardized hand-washing process is a guarantee for the daily work safety of medical staff, and is also an important means of preventing the spread of contamination within the hospital. It can effectively prevent and control the spread of pathogens and prevent the occurrence of postoperative infection or transmission. However, the existing hand-washing pool equipment or control technology does not fully consider the use of infrared sensors and data processing to monitor user behavior and promptly warn of irregular hand-washing behavior. Therefore, it is impossible to achieve a more intelligent hand-washing pool service, and its safety protection function is also weak. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a multi-sensing interactive medical hand-brushing pool control method and an integrated hand-brushing pool, which can effectively improve the standardization of the user's hand-brushing behavior, bring the user a smarter and more convenient hand-brushing pool usage experience, and reduce the occurrence of medical accidents.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a multi-sensing interactive medical hand-scrubbing pool control method, the method comprising:

[0005] Acquire multiple infrared signal data by setting multiple infrared sensors in multiple areas of the hand washing pool;

[0006] Determine the usage parameters of the current user according to the infrared signal data and the corresponding area based on a preset data matching rule;

[0007] judging whether the hand-brushing behavior of the current user is standard according to the process data rules corresponding to the usage parameters and the infrared signal data;

[0008] When it is determined that the hand-brushing behavior is not standardized, a warning message is sent to the smart mirror of the hand-brushing pool for display.

[0009] As an optional embodiment, in the first aspect of the present invention, the area is a mirror area, a hand soap area, a faucet area, a disinfectant paper towel area, a hand brush area, a sink area, a disinfectant drain area or a medical waste bin area.

[0010] As an optional embodiment, in the first aspect of the present invention, the usage parameters include user type and usage scenario; the user type is the surgeon, outpatient doctor, nurse, caregiver, patient or patient's companion; the usage scenario is the pre-operative scene, post-operative scene, pre-nursing scene, post-nursing scene or daily process scene.

[0011] As an optional implementation, in the first aspect of the present invention, determining the usage parameters of the current user according to the infrared signal data and the corresponding area based on a preset data matching rule includes:

[0012] Filter out all infrared signal data corresponding to the area in the infrared signal data that belongs to the feature recognition area to obtain a feature recognition data set; the feature recognition area includes a mirror area, a sink area, a disinfection drain area, and a medical waste bin area;

[0013] Inputting the feature recognition data set into a trained personnel type classifier to obtain the user type corresponding to the current user; the personnel type classifier is trained by a training data set including a plurality of training feature recognition data sets and corresponding personnel type annotations;

[0014] The user type and the infrared signal data are input into a trained usage scenario prediction neural network to obtain a usage scenario corresponding to the current user.

[0015] As an optional implementation, in the first aspect of the present invention, the inputting of the user type and the infrared signal data into a trained usage scenario prediction neural network to obtain a usage scenario corresponding to the current user includes:

[0016] Arranging all the infrared signal data from early to late according to the signal acquisition time points to obtain a signal data sequence;

[0017] The signal data sequence and the user type are input into a trained RNN neural network to obtain an output usage scenario; the RNN neural network is trained by a training data set including multiple training infrared data series and corresponding user type annotations and usage scenario annotations.

[0018] As an optional implementation, in the first aspect of the present invention, judging whether the hand brushing behavior of the current user is standardized according to the process data rules corresponding to the usage parameters and the infrared signal data includes:

[0019] According to the usage parameters, a corresponding standard prediction neural network model and a preset data sequence rule are determined; the data sequence rule includes a plurality of area types arranged in order and corresponding time value reference values ​​and signal strength value reference values ​​of infrared signal data;

[0020] Calculating a first similarity parameter between the signal data sequence and the data sequence rule;

[0021] Inputting the signal data sequence into the canonical prediction neural network model to obtain canonical prediction value parameters;

[0022] Calculating a weighted average value of the first similarity parameter and the standard prediction value parameter to obtain a standard parameter;

[0023] When the standard parameter is less than a preset parameter threshold, it is determined that the hand brushing behavior of the current user is not standard.

[0024] As an optional embodiment, in the first aspect of the present invention, the canonical prediction neural network model is determined by the following steps:

[0025] For each historical infrared signal data sequence corresponding to a standard hand-brushing behavior in the historical database, determine a historical usage parameter corresponding to the historical infrared signal data sequence;

[0026] Calculating parameter similarity between the historical usage parameter and the usage parameter;

[0027] Determine the historical infrared signal data sequences whose parameter similarities are greater than a similarity threshold as positive sample data sets;

[0028] According to the positive sample data set, based on blank data filling and replacement operations, determining a corresponding negative sample data set;

[0029] The positive sample data set and the negative sample data set are input into the neural network model of the CNN network, and training is performed based on the L1 loss function, and the model parameters are optimized based on the gradient descent algorithm until convergence to obtain the standard prediction neural network model.

[0030] As an optional implementation, in the first aspect of the present invention, sending the warning information to the smart mirror of the hand-brushing pool for display includes:

[0031] For each of the regions, calculating the time difference between the acquisition time point of the infrared signal data corresponding to the region in the signal data series and the time value reference value of the corresponding region in the data sequence rule;

[0032] Calculate the intensity difference between the signal intensity value of the infrared signal data corresponding to the area in the signal data series and the signal intensity value reference value of the corresponding area in the data sequence rule;

[0033] Calculating a weighted average value of the time difference and the intensity difference to obtain a regional difference parameter corresponding to the region;

[0034] Determine the regions whose regional difference parameters are greater than a preset difference threshold as error regions; the difference threshold is proportional to the first similarity parameter;

[0035] A warning message including a warning for the error area is generated and sent to the smart mirror of the hand-brushing pool for display.

[0036] A second aspect of an embodiment of the present invention discloses a multi-sensing interactive medical hand-scrubbing pool control system, the system comprising:

[0037] An acquisition module, used for acquiring a plurality of infrared signal data through a plurality of infrared sensors arranged in a plurality of areas of the hand-washing pool;

[0038] A determination module, used to determine the usage parameters of the current user according to the infrared signal data and the corresponding area based on a preset data matching rule;

[0039] A judgment module, used to judge whether the hand brushing behavior of the current user is normal according to the process data rules corresponding to the usage parameters and the infrared signal data;

[0040] The display module is used to send a warning message to the smart mirror of the hand-brushing pool for display when it is determined that the hand-brushing behavior is not standardized.

[0041] As an optional embodiment, in the second aspect of the present invention, the area is a mirror area, a hand soap area, a faucet area, a disinfectant paper towel area, a hand brush area, a sink area, a disinfectant drain area or a medical waste bin area.

[0042] As an optional embodiment, in the second aspect of the present invention, the usage parameters include user type and usage scenario; the user type is the surgeon, outpatient doctor, nurse, caregiver, patient or patient's companion; the usage scenario is the pre-operative scene, post-operative scene, pre-nursing scene, post-nursing scene or daily process scene.

[0043] As an optional implementation, in the second aspect of the present invention, determining the usage parameters of the current user according to the infrared signal data and the corresponding area based on a preset data matching rule includes:

[0044] Filter out all infrared signal data corresponding to the area in the infrared signal data that belongs to the feature recognition area to obtain a feature recognition data set; the feature recognition area includes a mirror area, a sink area, a disinfection drain area, and a medical waste bin area;

[0045] Inputting the feature recognition data set into a trained personnel type classifier to obtain the user type corresponding to the current user; the personnel type classifier is trained by a training data set including a plurality of training feature recognition data sets and corresponding personnel type annotations;

[0046] The user type and the infrared signal data are input into a trained usage scenario prediction neural network to obtain a usage scenario corresponding to the current user.

[0047] As an optional implementation, in the second aspect of the present invention, the determination module inputs the user type and the infrared signal data into a trained usage scenario prediction neural network to obtain a specific usage scenario corresponding to the current user, including:

[0048] Arranging all the infrared signal data from early to late according to the signal acquisition time points to obtain a signal data sequence;

[0049] The signal data sequence and the user type are input into a trained RNN neural network to obtain an output usage scenario; the RNN neural network is trained by a training data set including multiple training infrared data series and corresponding user type annotations and usage scenario annotations.

[0050] As an optional implementation, in the second aspect of the present invention, the specific manner in which the judgment module judges whether the current user's hand brushing behavior is standardized according to the process data rules corresponding to the usage parameters and the infrared signal data includes:

[0051] According to the usage parameters, a corresponding standard prediction neural network model and a preset data sequence rule are determined; the data sequence rule includes a plurality of area types arranged in order and corresponding time value reference values ​​and signal strength value reference values ​​of infrared signal data;

[0052] Calculating a first similarity parameter between the signal data sequence and the data sequence rule;

[0053] Inputting the signal data sequence into the canonical prediction neural network model to obtain canonical prediction value parameters;

[0054] Calculating a weighted average value of the first similarity parameter and the standard prediction value parameter to obtain a standard parameter;

[0055] When the standard parameter is less than a preset parameter threshold, it is determined that the hand brushing behavior of the current user is not standard.

[0056] As an optional embodiment, in the second aspect of the present invention, the canonical prediction neural network model is determined by the following steps:

[0057] For each historical infrared signal data sequence corresponding to a standard hand-brushing behavior in the historical database, determine a historical usage parameter corresponding to the historical infrared signal data sequence;

[0058] Calculating parameter similarity between the historical usage parameter and the usage parameter;

[0059] Determine the historical infrared signal data sequences whose parameter similarities are greater than a similarity threshold as positive sample data sets;

[0060] According to the positive sample data set, based on blank data filling and replacement operations, determining a corresponding negative sample data set;

[0061] The positive sample data set and the negative sample data set are input into the neural network model of the CNN network, and training is performed based on the L1 loss function, and the model parameters are optimized based on the gradient descent algorithm until convergence to obtain the standard prediction neural network model.

[0062] As an optional implementation, in the second aspect of the present invention, the specific manner in which the display module sends the warning information to the smart mirror of the hand washing pool for display includes:

[0063] For each of the regions, calculating the time difference between the acquisition time point of the infrared signal data corresponding to the region in the signal data series and the time value reference value of the corresponding region in the data sequence rule;

[0064] Calculate the intensity difference between the signal intensity value of the infrared signal data corresponding to the area in the signal data series and the signal intensity value reference value of the corresponding area in the data sequence rule;

[0065] Calculating a weighted average value of the time difference and the intensity difference to obtain a regional difference parameter corresponding to the region;

[0066] Determine the regions whose regional difference parameters are greater than a preset difference threshold as error regions; the difference threshold is proportional to the first similarity parameter;

[0067] A warning message including a warning for the error area is generated and sent to the smart mirror of the hand-brushing pool for display.

[0068] The third aspect of the present invention discloses an integrated hand-washing pool, which includes a hand-washing pool body and a control device; infrared sensors are arranged at multiple positions of the hand-washing pool body, and the hand-washing pool body includes a mirror device, a smart mirror, a hand sanitizer device, a faucet device, a disinfecting paper towel device, a hand-washing brush device, a sink device, a disinfecting drain device and a medical waste bin device; the control device includes:

[0069] A memory storing executable program code;

[0070] a processor coupled to the memory, the processor being communicatively connected to the smart mirror and the infrared sensor;

[0071] The processor calls the executable program code stored in the memory to execute the multi-sensing interactive medical hand-brushing pool control method as described in any one of claims 1-8.

[0072] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the multi-sensing interactive medical hand-brushing pool control method disclosed in the first aspect of the present invention.

[0073] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0074] The present invention can fully acquire infrared data that can characterize user behavior through multiple infrared sensors set in multiple areas of the hand-brushing pool, and thereby determine the user's usage parameters and judge whether the behavior is standardized, and issue warnings in a timely manner, thereby effectively improving the standardization of the user's hand-brushing behavior, bringing the user a smarter and more convenient hand-brushing pool usage experience, and reducing the occurrence of medical accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0076] Figure 1 The present invention is a flowchart of a multi-sensing interactive medical hand-scrubbing pool control method disclosed in an embodiment of the present invention.

[0077] Figure 2 It is a structural schematic diagram of a multi-sensing interactive medical hand-scrubbing pool control system disclosed in an embodiment of the present invention.

[0078] Figure 3It is a structural schematic diagram of an integrated hand-brushing pool disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0079] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0080] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0081] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0082] The present invention discloses a multi-sensing interactive medical hand-brushing pool control method and an integrated hand-brushing pool, which can fully obtain infrared data that can characterize user behavior through multiple infrared sensors set in multiple areas of the hand-brushing pool, and thereby determine the user's usage parameters and judge whether the behavior is standardized, and issue warnings in a timely manner, thereby effectively improving the standardization of the user's hand-brushing behavior, providing users with a smarter and more convenient hand-brushing pool usage experience, and reducing the occurrence of medical accidents. The following is a detailed description.

[0083] Embodiment 1

[0084] See also Figure 1 , Figure 1 1 is a flow chart of a multi-sensing interactive medical hand-scrubbing pool control method disclosed in an embodiment of the present invention. Figure 1 The described multi-sensing interactive medical hand-washing pool control method can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the multi-sensing interactive medical hand-scrubbing pool control method may include the following operations:

[0085] 101. Acquire multiple infrared signal data by setting up multiple infrared sensors in multiple areas of the hand washing pool.

[0086] 102. Determine the usage parameters of the current user according to the infrared signal data and the corresponding area based on a preset data matching rule.

[0087] 103. Determine whether the current user's hand-swiping behavior is standard based on the process data rules corresponding to the usage parameters and the infrared signal data.

[0088] 104. When it is determined that the hand-brushing behavior is not standardized, a warning message is sent to the smart mirror of the hand-brushing pool for display.

[0089] It can be seen that the above-mentioned embodiments of the invention can fully obtain infrared data that can characterize user behavior through multiple infrared sensors set in multiple areas of the hand-brushing pool, and thereby determine the user's usage parameters and judge whether the behavior is standardized, and issue warnings in time, thereby effectively improving the standardization of the user's hand-brushing behavior, bringing users a smarter and more convenient hand-brushing pool usage experience, and reducing the occurrence of medical accidents.

[0090] As an optional embodiment, in the above steps, the area is a mirror area, a hand soap area, a faucet area, a disinfectant paper towel area, a hand brush area, a sink area, a disinfectant drain area or a medical waste bin area.

[0091] It can be seen that through the above-mentioned optional embodiments, the types of areas where infrared sensors are set are clarified, and the user's behavioral characteristics can be obtained more comprehensively, so as to facilitate the subsequent determination of the user's usage parameters and judge whether the behavior is standardized, and assist in improving the standardization of the user's hand-brushing behavior, bringing users a smarter and more convenient hand-brushing pool usage experience, and reducing the occurrence of medical accidents.

[0092] As an optional embodiment, in the above steps, the usage parameters include user type and usage scenario; the user type is the surgeon, outpatient doctor, nurse, caregiver, patient or patient's companion; the usage scenario is the pre-operative scenario, post-operative scenario, pre-nursing scenario, post-nursing scenario or daily process scenario.

[0093] It can be seen that through the above optional embodiments, the content and type of the usage parameters are clarified, which can more comprehensively characterize the user's usage characteristics, so as to facilitate the subsequent judgment of whether the behavior is standardized, and assist in improving the standardization of the user's hand-brushing behavior, bringing users a smarter and more convenient hand-brushing pool usage experience, and reducing the occurrence of medical accidents.

[0094] As an optional embodiment, in the above steps, determining the usage parameters of the current user according to the infrared signal data and the corresponding area based on a preset data matching rule includes:

[0095] Filter out all infrared signal data whose corresponding area in the infrared signal data belongs to the feature recognition area to obtain a feature recognition data set; optionally, the feature recognition area includes a mirror area, a sink area, a disinfection drain area, and a medical waste bin area;

[0096] Input the feature recognition data set into a trained personnel type classifier to obtain the user type corresponding to the current user; optionally, the personnel type classifier is trained by a training data set including multiple training feature recognition data sets and corresponding personnel type annotations;

[0097] The user type and infrared signal data are input into the trained usage scenario prediction neural network to obtain the usage scenario corresponding to the current user.

[0098] It can be seen that through the above-mentioned optional embodiments, the infrared signal data belonging to the area that can directly obtain the user's clothing, height or appearance characteristics can be screened out, so as to obtain the user type through algorithm identification, and then predict the usage scenario based on this, so as to more accurately determine the user's usage parameters, facilitate the subsequent judgment of whether the behavior is standardized, and assist in improving the standardization of the user's hand-brushing behavior, bringing users a smarter and more convenient hand-brushing pool usage experience, and reducing the occurrence of medical accidents.

[0099] As an optional embodiment, in the above steps, the user type and infrared signal data are input into a trained usage scenario prediction neural network to obtain the usage scenario corresponding to the current user, including:

[0100] Arrange all infrared signal data from early to late according to the signal acquisition time points to obtain a signal data sequence;

[0101] The signal data sequence and the user type are input into the trained RNN neural network to obtain the output usage scenario; the RNN neural network is trained by a training data set including multiple training infrared data series and corresponding user type annotations and usage scenario annotations.

[0102] It can be seen that through the above-mentioned optional embodiments, it is possible to accurately predict the usage scenarios of signal data sequences arranged in time points based on the trained RNN neural network, which is convenient for subsequent judgment of whether the behavior is standardized, and assists in improving the standardization of the user's hand-brushing behavior, bringing users a smarter and more convenient hand-brushing pool usage experience, and reducing the occurrence of medical accidents.

[0103] As an optional embodiment, in the above steps, judging whether the current user's hand brushing behavior is normal according to the process data rules corresponding to the usage parameters and the infrared signal data includes:

[0104] According to the usage parameters, a corresponding standard prediction neural network model and a preset data sequence rule are determined; optionally, the data sequence rule includes a plurality of area types arranged in order and corresponding time value reference values ​​and signal strength value reference values ​​of infrared signal data;

[0105] Calculating a first similarity parameter between the signal data sequence and the data sequence rule;

[0106] Inputting the signal data sequence into the canonical prediction neural network model to obtain canonical prediction value parameters;

[0107] Calculating a weighted average of the first similarity parameter and the canonical prediction value parameter to obtain a canonical parameter;

[0108] When the standard parameter is less than a preset parameter threshold, it is determined that the current user's hand-swiping behavior is not standard.

[0109] It can be seen that through the above-mentioned optional embodiments, the standardization degree of the signal data sequence can be measured based on the standard prediction neural network model and the data sequence rules respectively, so as to accurately judge whether the hand-brushing behavior is standardized, thereby improving the standardization degree of the user's hand-brushing behavior, bringing users a smarter and more convenient hand-brushing pool usage experience, and reducing the occurrence of medical accidents.

[0110] As an optional embodiment, in the above steps, the standard prediction neural network model is determined by the following steps:

[0111] For each historical infrared signal data sequence corresponding to a standard hand-brushing behavior in the historical database, determine a historical usage parameter corresponding to the historical infrared signal data sequence;

[0112] Calculate the parameter similarity between the historical usage parameters and the usage parameters;

[0113] The historical infrared signal data sequences whose parameter similarities are greater than a similarity threshold are determined as positive sample data sets;

[0114] According to the positive sample data set, the corresponding negative sample data set is determined based on blank data filling and replacement operations;

[0115] The positive sample data set and the negative sample data set are input into the neural network model of the CNN network, and trained based on the L1 loss function. The model parameters are optimized based on the gradient descent algorithm until convergence to obtain a standard prediction neural network model.

[0116] Specifically, the specific method for determining the negative sample data set is to perform random blank data filling and replacement operations on the corresponding historical infrared signal data sequence in the positive sample data set, and modify the corresponding data annotations to non-standard annotations, so as to obtain a negative sample data set corresponding to the random non-standard behavior.

[0117] It can be seen that through the above-mentioned optional embodiments, the training and determination details of the standard prediction neural network model are clarified, and a more accurate standard prediction neural network model is obtained by training historical data of standard hand-brushing behaviors with higher similarity, so as to accurately judge whether the hand-brushing behaviors are standard, thereby improving the standardization of the users' hand-brushing behaviors, bringing users a smarter and more convenient hand-brushing pool usage experience, and reducing the occurrence of medical accidents.

[0118] As an optional embodiment, in the above step, sending the warning information to the smart mirror of the hand washing pool for display includes:

[0119] For each region, the time difference between the acquisition time point of the infrared signal data corresponding to the region in the signal data series and the time value reference value of the corresponding region in the data sequence rule is calculated;

[0120] Calculate the intensity difference between the signal intensity value of the infrared signal data corresponding to the area in the signal data series and the reference value of the signal intensity value of the corresponding area in the data sequence rule;

[0121] Calculate the weighted average of the time difference and the intensity difference to obtain the regional difference parameter corresponding to the region;

[0122] Determine all regions whose regional difference parameters are greater than a preset difference threshold as error regions; optionally, the difference threshold is proportional to the first similarity parameter;

[0123] Generate warning information including warnings for error areas and send it to the smart mirror in the hand-washing pool for display.

[0124] It can be seen that through the above-mentioned optional embodiments, the areas where errors are most likely to occur in irregular hand-brushing behaviors can be determined by calculating the differences in specific areas between the signal data sequence and the preset data sequence rules, so as to provide more targeted warnings to users, thereby improving the standardization of users' hand-brushing behaviors, providing users with a smarter and more convenient hand-brushing pool experience, and reducing the occurrence of medical accidents.

[0125] Embodiment 2

[0126] See also Figure 2 , Figure 2 This is a schematic diagram of the structure of a multi-sensing interactive medical hand-washing pool control system disclosed in an embodiment of the present invention. Figure 2The described multi-sensing interactive medical hand-washing pool control system can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the multi-sensing interactive medical hand-scrubbing pool control system may include:

[0127] The acquisition module 201 is used to acquire multiple infrared signal data through multiple infrared sensors set in multiple areas of the hand washing pool.

[0128] The determination module 202 is used to determine the usage parameters of the current user according to the infrared signal data and the corresponding area based on a preset data matching rule.

[0129] The judgment module 203 is used to judge whether the current user's hand brushing behavior is normal according to the process data rules corresponding to the usage parameters and the infrared signal data.

[0130] The display module 204 is used to send a warning message to the smart mirror of the hand-brushing pool for display when it is determined that the hand-brushing behavior is not standardized.

[0131] It can be seen that the above-mentioned embodiments of the invention can fully obtain infrared data that can characterize user behavior through multiple infrared sensors set in multiple areas of the hand-brushing pool, and thereby determine the user's usage parameters and judge whether the behavior is standardized, and issue warnings in time, thereby effectively improving the standardization of the user's hand-brushing behavior, bringing users a smarter and more convenient hand-brushing pool usage experience, and reducing the occurrence of medical accidents.

[0132] As an optional embodiment, the area is a mirror area, a hand soap area, a faucet area, a disinfectant paper towel area, a hand brush area, a sink area, a disinfectant drain area or a medical waste bin area.

[0133] It can be seen that through the above-mentioned optional embodiments, the types of areas where infrared sensors are set are clarified, and the user's behavioral characteristics can be obtained more comprehensively, so as to facilitate the subsequent determination of the user's usage parameters and judge whether the behavior is standardized, and assist in improving the standardization of the user's hand-brushing behavior, bringing users a smarter and more convenient hand-brushing pool usage experience, and reducing the occurrence of medical accidents.

[0134] As an optional embodiment, the usage parameters include user type and usage scenario; the user type is the surgeon, outpatient doctor, nurse, caregiver, patient or patient's companion; the usage scenario is the pre-operative scenario, post-operative scenario, pre-nursing scenario, post-nursing scenario or daily process scenario.

[0135] It can be seen that through the above optional embodiments, the content and type of the usage parameters are clarified, which can more comprehensively characterize the user's usage characteristics, so as to facilitate the subsequent judgment of whether the behavior is standardized, and assist in improving the standardization of the user's hand-brushing behavior, bringing users a smarter and more convenient hand-brushing pool usage experience, and reducing the occurrence of medical accidents.

[0136] As an optional embodiment, according to the infrared signal data and the corresponding area, based on a preset data matching rule, the usage parameters of the current user are determined, including:

[0137] Filter out all infrared signal data whose corresponding area in the infrared signal data belongs to the feature recognition area to obtain a feature recognition data set; optionally, the feature recognition area includes a mirror area, a sink area, a disinfection drain area, and a medical waste bin area;

[0138] Input the feature recognition data set into a trained personnel type classifier to obtain the user type corresponding to the current user; optionally, the personnel type classifier is trained by a training data set including multiple training feature recognition data sets and corresponding personnel type annotations;

[0139] The user type and infrared signal data are input into the trained usage scenario prediction neural network to obtain the usage scenario corresponding to the current user.

[0140] It can be seen that through the above-mentioned optional embodiments, the infrared signal data belonging to the area that can directly obtain the user's clothing, height or appearance characteristics can be screened out, so as to obtain the user type through algorithm identification, and then predict the usage scenario based on this, so as to more accurately determine the user's usage parameters, facilitate the subsequent judgment of whether the behavior is standardized, and assist in improving the standardization of the user's hand-brushing behavior, bringing users a smarter and more convenient hand-brushing pool usage experience, and reducing the occurrence of medical accidents.

[0141] As an optional embodiment, the determination module inputs the user type and infrared signal data into the trained usage scenario prediction neural network to obtain the specific usage scenario corresponding to the current user, including:

[0142] Arrange all infrared signal data from early to late according to the signal acquisition time points to obtain a signal data sequence;

[0143] The signal data sequence and the user type are input into the trained RNN neural network to obtain the output usage scenario; the RNN neural network is trained by a training data set including multiple training infrared data series and corresponding user type annotations and usage scenario annotations.

[0144] It can be seen that through the above-mentioned optional embodiments, it is possible to accurately predict the usage scenarios of signal data sequences arranged in time points based on the trained RNN neural network, which is convenient for subsequent judgment of whether the behavior is standardized, and assists in improving the standardization of the user's hand-brushing behavior, bringing users a smarter and more convenient hand-brushing pool usage experience, and reducing the occurrence of medical accidents.

[0145] As an optional embodiment, the specific manner in which the judgment module judges whether the current user's hand brushing behavior is standardized according to the process data rules corresponding to the usage parameters and the infrared signal data includes:

[0146] According to the usage parameters, a corresponding standard prediction neural network model and a preset data sequence rule are determined; optionally, the data sequence rule includes a plurality of area types arranged in order and corresponding time value reference values ​​and signal strength value reference values ​​of infrared signal data;

[0147] Calculating a first similarity parameter between the signal data sequence and the data sequence rule;

[0148] Inputting the signal data sequence into the canonical prediction neural network model to obtain canonical prediction value parameters;

[0149] Calculating a weighted average of the first similarity parameter and the canonical prediction value parameter to obtain a canonical parameter;

[0150] When the standard parameter is less than a preset parameter threshold, it is determined that the current user's hand-swiping behavior is not standard.

[0151] It can be seen that through the above-mentioned optional embodiments, the standardization degree of the signal data sequence can be measured based on the standard prediction neural network model and the data sequence rules respectively, so as to accurately judge whether the hand-brushing behavior is standardized, thereby improving the standardization degree of the user's hand-brushing behavior, bringing users a smarter and more convenient hand-brushing pool usage experience, and reducing the occurrence of medical accidents.

[0152] As an optional embodiment, the canonical prediction neural network model is determined by the following steps:

[0153] For each historical infrared signal data sequence corresponding to a standard hand-brushing behavior in the historical database, determine a historical usage parameter corresponding to the historical infrared signal data sequence;

[0154] Calculate the parameter similarity between the historical usage parameters and the usage parameters;

[0155] The historical infrared signal data sequences whose parameter similarities are greater than a similarity threshold are determined as positive sample data sets;

[0156] According to the positive sample data set, the corresponding negative sample data set is determined based on blank data filling and replacement operations;

[0157] The positive sample data set and the negative sample data set are input into the neural network model of the CNN network, and trained based on the L1 loss function. The model parameters are optimized based on the gradient descent algorithm until convergence to obtain a standard prediction neural network model.

[0158] It can be seen that through the above-mentioned optional embodiments, the training and determination details of the standard prediction neural network model are clarified, and a more accurate standard prediction neural network model is obtained by training historical data of standard hand-brushing behaviors with higher similarity, so as to accurately judge whether the hand-brushing behaviors are standard, thereby improving the standardization of the users' hand-brushing behaviors, bringing users a smarter and more convenient hand-brushing pool usage experience, and reducing the occurrence of medical accidents.

[0159] As an optional embodiment, the specific manner in which the display module sends the warning information to the smart mirror of the hand washing pool for display includes:

[0160] For each region, the time difference between the acquisition time point of the infrared signal data corresponding to the region in the signal data series and the time value reference value of the corresponding region in the data sequence rule is calculated;

[0161] Calculate the intensity difference between the signal intensity value of the infrared signal data corresponding to the area in the signal data series and the reference value of the signal intensity value of the corresponding area in the data sequence rule;

[0162] Calculate the weighted average of the time difference and the intensity difference to obtain the regional difference parameter corresponding to the region;

[0163] Determine all regions whose regional difference parameters are greater than a preset difference threshold as error regions; optionally, the difference threshold is proportional to the first similarity parameter;

[0164] Generate warning information including warnings for error areas and send it to the smart mirror in the hand-washing pool for display.

[0165] It can be seen that through the above-mentioned optional embodiments, the areas where errors are most likely to occur in irregular hand-brushing behaviors can be determined by calculating the differences in specific areas between the signal data sequence and the preset data sequence rules, so as to provide more targeted warnings to users, thereby improving the standardization of users' hand-brushing behaviors, providing users with a smarter and more convenient hand-brushing pool experience, and reducing the occurrence of medical accidents.

[0166] Embodiment 3

[0167] See also Figure 3 , Figure 3 An integrated hand-washing pool disclosed in an embodiment of the present invention includes a hand-washing pool body and a control device (not shown in the figure). Specifically, Figure 3 The right side is a three-dimensional schematic diagram of the whole hand-washing pool. Figure 3 The structure of the hand-washing pool body is shown on the left. As shown in the figure, the hand-washing pool body includes a mirror device, a smart mirror, a hand sanitizer device, a faucet device, a disinfectant paper towel device, a hand-washing brush device, a sink device, a disinfectant drain device and a medical waste bin device. Specifically, the smart mirror has a display function.

[0168] More specifically, infrared sensors are provided at multiple areas of the hand brushing pool to obtain user motion information. For more specific technical details, please refer to the description in the above embodiments.

[0169] Specifically, the control device includes:

[0170] A memory storing executable program code;

[0171] a processor coupled to the memory, the processor being communicatively connected to the smart mirror and the infrared sensor;

[0172] The processor calls the executable program code stored in the memory to execute the steps of the multi-sensing interactive medical hand-brushing pool control method described in the first embodiment.

[0173] Embodiment 4

[0174] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the multi-sensing interactive medical hand-brushing pool control method described in the first embodiment.

[0175] Embodiment 5

[0176] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the multi-sensing interactive medical hand-brushing pool control method described in the first embodiment.

[0177] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0178] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0179] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0180] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0181] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0182] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0183] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0184] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0185] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0186] Computer readable media include permanent and non-permanent, removable and non-removable media that can be used to store information 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 technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include transitory media such as modulated data signals and carrier waves.

[0187] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0188] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0189] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0190] Finally, it should be noted that the multi-sensing interactive medical hand-brushing pool control method and integrated hand-brushing pool disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features therein may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A multi-sensing interactive medical hand-scrubbing pool control method, characterized in that: The method comprises: Acquire multiple infrared signal data by setting multiple infrared sensors in multiple areas of the hand washing pool; According to the infrared signal data and the corresponding area, based on the preset data matching rules, the usage parameters of the current user are determined; the usage parameters include the user type and the usage scenario; the user type is the surgeon, outpatient doctor, nurse, care worker, patient or patient companion; the usage scenario is the pre-operative scenario, the post-operative scenario, the pre-nursing scenario, the post-nursing scenario or the daily process scenario; according to the infrared signal data and the corresponding area, based on the preset data matching rules, the usage parameters of the current user are determined, including: Filter out all infrared signal data corresponding to the area in the infrared signal data that belongs to the feature recognition area to obtain a feature recognition data set; the feature recognition area includes a mirror area, a sink area, a disinfection drain area, and a medical waste bin area; Inputting the feature recognition data set into a trained personnel type classifier to obtain the user type corresponding to the current user; the personnel type classifier is trained by a training data set including a plurality of training feature recognition data sets and corresponding personnel type annotations; Arranging all the infrared signal data from early to late according to the signal acquisition time points to obtain a signal data sequence; The signal data sequence and the user type are input into a trained RNN neural network to obtain an output usage scenario; the RNN neural network is trained by a training data set including a plurality of training infrared data series and corresponding user type annotations and usage scenario annotations; Judging whether the hand brushing behavior of the current user is standard according to the process data rules corresponding to the usage parameters and the infrared signal data, includes: According to the usage parameters, a corresponding standard prediction neural network model and a preset data sequence rule are determined; the data sequence rule includes a plurality of area types arranged in order and corresponding time value reference values ​​and signal strength value reference values ​​of infrared signal data; Calculating a first similarity parameter between the signal data sequence and the data sequence rule; Inputting the signal data sequence into the canonical prediction neural network model to obtain canonical prediction value parameters; Calculating a weighted average value of the first similarity parameter and the standard prediction value parameter to obtain a standard parameter; When the standard parameter is less than a preset parameter threshold, determining that the current user's hand brushing behavior is not standard; When it is determined that the hand-brushing behavior is not standardized, a warning message is sent to the smart mirror of the hand-brushing pool for display.

2. The multi-sensing interactive medical hand-scrubbing pool control method according to claim 1, characterized in that: The area is a mirror area, a hand soap area, a faucet area, a disinfectant paper towel area, a hand brush area, a sink area, a disinfectant drain area or a medical waste bin area.

3. The multi-sensing interactive medical hand-scrubbing pool control method according to claim 1, characterized in that: The canonical prediction neural network model is determined by the following steps: For each historical infrared signal data sequence corresponding to a standard hand-brushing behavior in the historical database, determine a historical usage parameter corresponding to the historical infrared signal data sequence; Calculating parameter similarity between the historical usage parameter and the usage parameter; Determine the historical infrared signal data sequences whose parameter similarities are greater than a similarity threshold as positive sample data sets; According to the positive sample data set, based on blank data filling and replacement operations, determining a corresponding negative sample data set; The positive sample data set and the negative sample data set are input into the neural network model of the CNN network, and training is performed based on the L1 loss function, and the model parameters are optimized based on the gradient descent algorithm until convergence to obtain the standard prediction neural network model.

4. The multi-sensing interactive medical hand-scrubbing pool control method according to claim 1, characterized in that: The sending of the warning information to the smart mirror of the hand-washing pool for display includes: For each of the regions, calculating the time difference between the acquisition time point of the infrared signal data corresponding to the region in the signal data series and the time value reference value of the corresponding region in the data sequence rule; Calculate the intensity difference between the signal intensity value of the infrared signal data corresponding to the area in the signal data series and the signal intensity value reference value of the corresponding area in the data sequence rule; Calculating a weighted average value of the time difference and the intensity difference to obtain a regional difference parameter corresponding to the region; Determine the regions whose regional difference parameters are greater than a preset difference threshold as error regions; the difference threshold is proportional to the first similarity parameter; A warning message including a warning for the error area is generated and sent to the smart mirror of the hand-brushing pool for display.

5. A multi-sensing interactive medical hand-scrubbing pool control system, characterized in that: The system comprises: An acquisition module, used for acquiring a plurality of infrared signal data through a plurality of infrared sensors arranged in a plurality of areas of the hand-washing pool; The determination module is used to determine the usage parameters of the current user according to the infrared signal data and the corresponding area based on the preset data matching rules; the usage parameters include the user type and the usage scenario; the user type is the surgeon, outpatient doctor, nurse, care worker, patient or patient companion; the usage scenario is the pre-operative scenario, the post-operative scenario, the pre-nursing scenario, the post-nursing scenario or the daily process scenario; the specific manner in which the determination module determines the usage parameters of the current user according to the infrared signal data and the corresponding area based on the preset data matching rules includes: Filter out all infrared signal data corresponding to the area in the infrared signal data that belongs to the feature recognition area to obtain a feature recognition data set; the feature recognition area includes a mirror area, a sink area, a disinfection drain area, and a medical waste bin area; Inputting the feature recognition data set into a trained personnel type classifier to obtain the user type corresponding to the current user; the personnel type classifier is trained by a training data set including a plurality of training feature recognition data sets and corresponding personnel type annotations; Arranging all the infrared signal data from early to late according to the signal acquisition time points to obtain a signal data sequence; The signal data sequence and the user type are input into a trained RNN neural network to obtain an output usage scenario; the RNN neural network is trained by a training data set including a plurality of training infrared data series and corresponding user type annotations and usage scenario annotations; A judgment module, used to judge whether the current user's hand brushing behavior is normal according to the process data rules corresponding to the usage parameters and the infrared signal data, including: According to the usage parameters, a corresponding standard prediction neural network model and a preset data sequence rule are determined; the data sequence rule includes a plurality of area types arranged in order and corresponding time value reference values ​​and signal strength value reference values ​​of infrared signal data; Calculating a first similarity parameter between the signal data sequence and the data sequence rule; Inputting the signal data sequence into the canonical prediction neural network model to obtain canonical prediction value parameters; Calculating a weighted average value of the first similarity parameter and the standard prediction value parameter to obtain a standard parameter; When the standard parameter is less than a preset parameter threshold, determining that the current user's hand brushing behavior is not standard; The display module is used to send a warning message to the smart mirror of the hand-brushing pool for display when it is determined that the hand-brushing behavior is not standardized.

6. An integrated hand-washing pool, characterized in that: The integrated hand-washing pool includes a hand-washing pool body and a control device; infrared sensors are arranged at multiple positions of the hand-washing pool body, and the hand-washing pool body includes a mirror device, a smart mirror, a hand sanitizer device, a faucet device, a disinfecting paper towel device, a hand-washing brush device, a sink device, a disinfecting drain device and a medical waste bin device; the control device includes: A memory storing executable program code; a processor coupled to the memory, the processor being communicatively connected to the smart mirror and the infrared sensor; The processor calls the executable program code stored in the memory to execute the multi-sensing interactive medical hand-brushing pool control method as described in any one of claims 1-4.

Images