A smart interaction system for home care of disabled old people

Abstract

The application provides a kind of disabled old people home care wisdom interaction system, comprising: behavior monitoring module, for monitoring the behavior of caregiver and disabled old people;Trigger module, for when the behavior of caregiver is associated with the behavior of the disabled old people and meets the associated behavior in the pre-configured associated trigger library, enter the auxiliary mode;Interaction module, for in auxiliary mode according to the interactive information of caregiver and / or disabled old people, output corresponding prompt information.The disabled old people home care wisdom interaction system of the application realizes the output of prompt information in the form of auxiliary interaction when the event outside the ability range of caregiver occurs, so as to realize effective event processing.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of behavior monitoring assistance, in particular to a home care intelligent interaction system for disabled old people. BACKGROUND

[0002] An old person who loses the ability to take care of himself is called a "disabled old person". According to the international standard analysis, if one or two of the six indicators of eating, dressing, getting in and out of bed, going to the toilet, walking indoors, and bathing cannot be done, it is defined as "mild disability", three to four cannot be done, it is defined as "moderate disability", and five to six cannot be done, it is defined as "severe disability".

[0003] The care of disabled old people has always been a concern of society. Generally, the carer carries out care, and the skills and event handling capabilities of the carer are different. When an event beyond the carer's cognitive processing range is encountered, effective event processing cannot be achieved. SUMMARY

[0004] One of the purposes of the present application is to provide a home care intelligent interaction system for disabled old people, which realizes the output of reminder information in an assisted interaction manner when an event outside the ability range of the carer occurs, thereby realizing effective event processing.

[0005] The home care intelligent interaction system for disabled old people provided by the embodiment of the present application comprises:

[0006] A behavior monitoring module for monitoring the behaviors of the carer and the disabled old person;

[0007] A triggering module for entering an assistance mode when the behavior of the carer is associated with the behavior of the disabled old person and meets the associated behavior in a pre-configured associated triggering library;

[0008] An interaction module for outputting corresponding prompt information according to the interaction information of the carer and / or the disabled old person in the assistance mode.

[0009] Preferably, the behavior monitoring module comprises:

[0010] An audio acquisition unit for acquiring audio data in the room;

[0011] An audio analysis unit for analyzing the audio data according to a keyword library to obtain a first analysis result.

[0012] Preferably, the behavior monitoring module further comprises:

[0013] An image acquisition unit for acquiring image data in the room;

[0014] An image analysis unit is configured to analyze the image data according to the behavior analysis model trained in advance to obtain a second analysis result.

[0015] Preferably, the behavior monitoring module further comprises:

[0016] A comprehensive analysis unit is configured to comprehensively analyze the first analysis result and the second analysis result to determine a final behavior analysis result.

[0017] Preferably, the triggering module comprises:

[0018] A correlation analysis unit is configured to perform correlation analysis on the behavior of the caregiver and the behavior of the disabled elderly to determine whether the behaviors of the caregiver and the disabled elderly are correlated;

[0019] A triggering analysis unit is configured to determine whether the correlated behaviors are correlated behaviors in the correlation triggering library when the behaviors of the caregiver and the disabled elderly are correlated.

[0020] A mode starting module is configured to enter an auxiliary mode when the correlated behaviors are the correlated behaviors in the correlation triggering library.

[0021] Preferably, the correlation analysis unit performs the following operations:

[0022] According to the pre-configured behavior code library, the behavior of the caregiver corresponds to a first code, and the behavior of the disabled elderly corresponds to a second code.

[0023] All third codes associated with the first code are extracted from the pre-configured correlation library, and the third codes are compared with the second code one by one; and / or, all third codes associated with the second code are extracted from the pre-configured correlation library, and the third codes are compared with the first code one by one.

[0024] When there is a same item for comparison, it is determined that the behaviors of the caregiver and the disabled elderly are correlated.

[0025] Preferably, the triggering analysis unit performs the following operations:

[0026] Another behavior code in the correlated behaviors related to the first code is extracted from the correlation triggering library as a fourth code, and the fourth code is compared with the second code one by one; and / or, another behavior code in the correlated behaviors related to the second code is extracted from the correlation triggering library as a fourth code, and the fourth code is compared with the first code one by one.

[0027] When there is a same item for comparison, it is determined that the behaviors of the caregiver and the disabled elderly are the correlated behaviors in the correlation triggering library.

[0028] Preferably, the interaction information received by the interaction module includes an interaction gesture and / or an interaction voice; and the prompt information is pre-stored information associated with the behavior of the corresponding disabled elderly.

[0029] Preferably, the intelligent interaction system for home care of the disabled old people further comprises:

[0030] a dangerous behavior early warning module, configured to make a dangerous judgment on the behavior of the disabled old people based on a first dangerous behavior library configured in advance according to the specific condition of the disabled old people, and to give a voice prompt to the caregiver and / or a pre-configured warning contact person when a dangerous behavior occurs.

[0031] Preferably, the intelligent interaction system for home care of the disabled old people further comprises:

[0032] an event reminding module, configured to give an event reminder based on a pre-configured event reminding item.

[0033] Other features and advantages of the present application will be further described in the following description, and will become apparent from the description, or be learned through practice of the present application. The objects and other advantages of the present application will be realized and achieved by the structure particularly pointed out in the written description and the appended drawings.

[0034] The technical solutions of the present application will be further described in detail below with the help of the accompanying drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0035] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, illustrate the present application, and explain the present application together with the embodiments of the present application, but do not limit the present application. In the drawings:

[0036] Figure 1 FIG. 1 is a schematic diagram of an intelligent interaction system for home care of the disabled old people in an embodiment of the present application;

[0037] Figure 2 FIG. 2 is a schematic diagram of abnormal event monitoring in an embodiment of the present application. DETAILED DESCRIPTION

[0038] The preferred embodiments of the present application will be described below in conjunction with the accompanying drawings, and it should be understood that the preferred embodiments described herein are only used to explain and illustrate the present application, and do not limit the present application.

[0039] The present application provides an intelligent interaction system for home care of the disabled old people, as shown in FIG. 1, comprising: Figure 1 a behavior monitoring module 1, configured to monitor the behavior of the caregiver and the disabled old people;

[0040] a triggering module 2, configured to enter an auxiliary mode when the behavior of the caregiver is associated with the behavior of the disabled old people and meets the associated behavior in a pre-configured associated triggering library;

[0041]

[0042] ​An interaction module 3 is configured to output corresponding prompt information according to interaction information of the caregiver and / or the disabled elderly in the assistance mode.

[0043] The embodiment adaptively enters the assistance mode by monitoring and analyzing behaviors of the caregiver and the disabled elderly, interacts with the caregiver and / or the disabled elderly in the assistance mode, and provides corresponding prompt information; when an event beyond the ability range of the caregiver occurs, the embodiment outputs reminder information in an assisted interaction manner, thereby effectively processing the event. The interaction information received by the interaction module 3 includes interaction gestures and / or interaction voice; the prompt information is pre-stored information associated with behaviors of the corresponding disabled elderly. For example, when the behavior of the disabled elderly includes any one of falling, fainting, and swallowing difficulty, and the behavior of the caregiver is any one of standing still and anxiously pacing, the system enters the assistance mode after being determined by the associated trigger library, and provides precise care support to the caregiver according to the needs of the caregiver; the interaction information of the caregiver includes voice information; the system outputs prompt information corresponding to the behavior of the elderly, specifically, the prompt information corresponding to falling is “confirm the falling impact position”; when the caregiver confirms that the feedback is “leg”, the system continues to output the prompt information “is there swelling, is there pain when pressing” to gradually guide the caregiver to process. In addition, the caregiver can make a gesture to trigger the system to enter the assistance mode, and the gesture includes any one of “stretching the hand towards the camera and bending the palm multiple times” and “stretching the hand upwards”.

[0044] The implementation of the assistance reminder function of the system is based on the monitoring and judgment of behaviors of the caregiver and the disabled elderly. In order to realize behavior monitoring, the embodiment provides three behavior analysis modes, which are as follows.

[0045] I. Audio analysis mode, the audio data in the room is collected by the audio collection unit of the behavior monitoring module 1; the collected audio data is analyzed by the audio analysis unit according to the keyword library to obtain a first analysis result. The audio data can be collected by a sound collector arranged in the room; the keyword library is constructed in advance, and a plurality of keywords in the keyword library correspond to a first analysis result, for example, “eat” and “medicine” correspond to the behavior of feeding medicine by the caregiver; the behavior of the disabled elderly reminds the caregiver, etc.

[0046] II. Image analysis mode, the image data in the room is collected by the image collection unit of the behavior monitoring module 1; the collected image data is input into the behavior analysis model trained and converged in advance by the image analysis unit for analysis to obtain a second analysis result. The image data can be collected by a camera arranged in the room; the behavior analysis model is a neural network model; and the behavior analysis by the neural network model is a mature technology, which will not be described here.

[0047] III. The comprehensive analysis is performed by the comprehensive analysis unit of the behavior monitoring module 1 on the basis of the audio analysis and the image analysis, and the first analysis result and the second analysis result are comprehensively analyzed to determine the final behavior analysis result. That is, there is only one first analysis result and one second analysis result at the same time, and the behavior of the existing behavior analysis result is the final behavior analysis result; when the same behavior exists at the same time, any analysis result is the final behavior analysis result; when the behaviors are different, the image analysis is temporarily used as the final behavior analysis result, and then the result is recorded and confirmed by the user again, and the result determined by the user again is used as the final result.

[0048] In order to realize the behavior correlation analysis, in one embodiment, the trigger module 2 comprises:

[0049] The correlation analysis unit is configured to perform correlation analysis on the behaviors of the caregiver and the disabled elderly person, and determine whether the behaviors of the caregiver and the disabled elderly person are correlated.

[0050] The trigger analysis unit is configured to determine whether the correlated behaviors are the correlated behaviors in the correlation trigger library when the behaviors of the caregiver and the disabled elderly person are correlated.

[0051] The mode starting module is configured to enter the auxiliary mode when the correlated behaviors are the correlated behaviors in the correlation trigger library.

[0052] The correlation analysis unit performs the following operations:

[0053] According to the pre-configured behavior coding library, the first code corresponding to the behavior of the caregiver and the second code corresponding to the behavior of the disabled elderly person are determined.

[0054] All third codes associated with the first code are extracted from the pre-configured correlation library, and the third codes are compared with the second code one by one; and / or all third codes associated with the second code are extracted from the pre-configured correlation library, and the third codes are compared with the first code one by one.

[0055] When there is a same item for comparison, it is determined that the behaviors of the caregiver and the disabled elderly person are correlated.

[0056] The trigger analysis unit performs the following operations:

[0057] Another behavior code in the correlated behaviors related to the first code is extracted from the correlation trigger library as a fourth code, and the fourth code is compared with the second code one by one; and / or another behavior code in the correlated behaviors related to the second code is extracted from the correlation trigger library as a fourth code, and the fourth code is compared with the first code one by one.

[0058] When there is a same item for comparison, it is determined that the behaviors of the caregiver and the disabled elderly person are the correlated behaviors in the correlation trigger library.

[0059] In an embodiment, the intelligent interaction system for home care of the disabled elderly further comprises:

[0060] a dangerous behavior warning module configured to determine the dangerous behavior of the disabled elderly based on a first dangerous behavior library configured in advance according to the specific condition of the disabled elderly, and to warn the caregiver and / or the pre-configured warning contact person through voice prompt when the dangerous behavior occurs.

[0061] The first dangerous behavior library is configured in advance by storing the corresponding behavior codes in the behavior code library into the first dangerous behavior library after analyzing the specific condition of the disabled elderly by a professional. In this way, the dangerous behavior of the disabled elderly can be warned during daily operation. In addition, a corresponding second dangerous behavior library can be configured for the caregiver to warn the dangerous behavior of the caregiver. The behavior codes corresponding to the behaviors of beating and abusing the elderly can be added to the second dangerous behavior library for synchronous monitoring.

[0062] In an embodiment, the intelligent interaction system for home care of the disabled elderly further comprises:

[0063] an event reminder module configured to perform event reminders based on pre-configured event reminder items. The time reminder items can be configured by the user in advance, such as daily medication reminders, meal reminders, etc.

[0064] In an embodiment, the intelligent interaction system for home care of the disabled elderly further comprises:

[0065] a recommendation module configured to receive a recommendation request of a user and output a recommendation list of caregivers according to the recommendation request;

[0066] The recommendation request is generated by the user operating the mobile terminal, and the data is filled in the data acquisition interface corresponding to the recommendation request. The filled-in data includes the age of the disabled elderly, the gender of the disabled elderly, the care address, and the feedback data of the ability questionnaire items of the disabled elderly. The recommendation request includes a request instruction and the data filled in by the user in the data acquisition interface.

[0067] The recommendation module performs the following operations:

[0068] According to the feedback data of the ability questionnaire items of the disabled elderly in the recommendation request and the corresponding quantitative scoring standard, the ability evaluation values of each item are determined, and the ability data set of the disabled elderly is constructed based on the ability evaluation values. The ability data set is arranged in a predetermined order and position.

[0069] The capability dataset is matched with each standard capability dataset in the corresponding association table of each caregiver stored in the system, when there is a standard capability dataset matching the capability dataset, the corresponding caregiver is taken as a recommended selection, and the standard capability dataset matching the capability dataset is taken as a positioning dataset;

[0070] The recommended selections are sorted according to the situation of the positioning dataset in the association table, the required salary range, and the expected remuneration range input by the user, and the evaluation of the historical principal;

[0071] The sorted recommended selections are outputted, and personal characteristics are marked. The personal characteristics include: evaluation sentences of the manager, self-evaluation sentences of the individual, and evaluation sentences of the historical principal.

[0072] The specific sorting steps between the recommended selections are as follows:

[0073] According to the values corresponding to each data in the standard capability dataset and the pre-configured weights, the total score corresponding to each standard capability dataset in the association table is calculated;

[0074] The standard capability datasets in the association table are sorted according to the total score from low to high, and the ability adaptation degree is determined according to the ratio of the sorting position number of the positioning dataset to the total number of the standard capability datasets;

[0075] The salary expectation adaptation degree is determined according to the degree of coincidence between the required salary range and the expected remuneration range input by the user;

[0076] The evaluation of the historical principal is quantified and then the sum value is taken as the evaluation value. The evaluation value is set by a maximum threshold, and when the evaluation value calculated by quantification is greater than the maximum threshold, the maximum threshold is taken as the final evaluation value;

[0077] According to the ability adaptation degree, the salary expectation adaptation degree, and the evaluation value, the corresponding pre-configured weighting coefficients are multiplied respectively, and then the sum value is calculated to obtain a priority recommendation value;

[0078] The priority recommendation values are sorted in descending order, and the ability adaptation degree, the salary expectation adaptation degree, and the evaluation value are marked in the recommendation interface and outputted synchronously.

[0079] The standard capability datasets in the corresponding association table of each caregiver are analyzed and constructed from the capability datasets of each patient that the caregiver can care for.

[0080] In one embodiment, the intelligent interactive system for home care of the disabled elderly people further comprises an abnormal event monitoring module;

[0081] As shown in Figure 2 The abnormal event monitoring module performs the following operations:

[0082] Step S1: constructing an abnormal event monitoring space model according to the internal space division of the house;

[0083] The model can be directly constructed by using the structural diagram of the house;

[0084] Step S2: taking the area not monitored by the camera as a hidden area and issuing a configuration inquiry;

[0085] Since the camera is generally set in the public area such as the living room and the dining room, the area not in the camera shooting range is not monitored, so the system needs the user input, and therefore issues a configuration inquiry;

[0086] Step S3: receiving the user's function configuration of each area and the stay time threshold configuration;

[0087] The function configuration includes: the old man's rest room, the bathroom, the master's room, the guest room, the warehouse, etc. In addition, when the user does not configure the stay time threshold or selects the default, the initial time threshold stored in the system is configured. The initial time threshold stored in the system includes: the old man's rest room from 12 noon to 2 pm; the threshold time of the bathroom is 30 minutes; the threshold of the master's room, the guest room and the warehouse for the disabled old people is 5 minutes; the master's room and the guest room are prohibited areas for caregivers, and the threshold time of the warehouse is 30 minutes;

[0088] Step S4: monitoring the trajectory of the disabled old people; when the time of entering each hidden area during the daytime care period is illegal, it is recorded as an abnormal event and sent to the user;

[0089] The trajectory monitoring is based on the analysis of the images shot by the camera, and the disabled old people can also wear positioning bracelets. The illegal judgment is the case of entering the specified time or exceeding the time threshold that can be entered. Similarly, the trajectory of the caregivers can also be monitored.

[0090] The abnormal event monitoring module performs the following operations:

[0091] When the caregiver and the disabled old people enter the hidden area at the same time and the time exceeds the corresponding set threshold, it is recorded as an abnormal event and the images from half an hour before entering to half an hour after leaving are retrieved as evidence associated with the abnormal event and stored;

[0092] When the caregiver and the disabled old people have behaviors such as cursing and beating each other, it is also recorded as an abnormal event;

[0093] When the caregiver intentionally moves behind the disabled elderly to form a situation of intentionally blocking the camera, it is also recorded as an abnormal event; Specifically: the line of sight direction of the caregiver is tracked, when the line of sight direction falls on the camera, a countdown (the initial value can be configured) is performed, before the countdown ends, the caregiver moves to the back of the disabled elderly (the outline of the elderly blocks 30% to 100% of the outline of the caregiver), it is judged that the caregiver exists in the situation of intentionally moving behind the disabled elderly to form a situation of intentionally blocking the camera;

[0094] The line of sight of the caregiver is monitored, and when the number of times the line of sight falls on the camera in a day is greater than a preset number threshold, it is recorded as an abnormal event; and the images within 5 minutes before and after each event point are associated and stored with the abnormal event.

[0095] In addition, the system can also analyze the care history of the caregiver, determine the key attention object and report to the manager; That is, when the caregiver changes the employer for many times in a short period of time (for example: changing the employer once a month), it can be regarded as a key attention object.

[0096] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these modifications and variations.

Claims

1. A home care intelligent interaction system for disabled old people, characterized in that, Comprise: Behavior monitoring module, trigger module, interactive module; wherein the behavior monitoring module monitors the behavior of caregivers and the cared-for; when the behavior of the caregiver is associated with the behavior of the cared-for and meets the associated behavior in the pre-configured associated trigger library, the trigger module triggers the entry into the auxiliary mode; after entering the auxiliary mode, the interactive module outputs corresponding prompt information according to the interaction information of the caregiver and / or the cared-for; Further comprising: an abnormal event monitoring module; Wherein, the abnormal event monitoring module performs the following operations: According to the internal space division of the house, an abnormal event monitoring space model is constructed; The area not monitored by the camera is regarded as a hidden area and a configuration inquiry is issued; Receive user's function configuration and stay time threshold configuration for each area; Monitor the trajectory of the disabled old people; when the time of entering each hidden area during the daytime care is illegal, it is recorded as an abnormal event and sent to the user; Monitor the caregiver's line of sight, and when the number of times the line of sight falls within the camera in a day is greater than the preset number of times threshold, it is recorded as an abnormal event.

2. The intelligent interactive system for home care of the disabled and elderly person according to claim 1, wherein, The behavior monitoring module comprises: an audio acquisition unit and an audio analysis unit, wherein the audio acquisition unit acquires indoor audio data; the acquired audio data is analyzed by the audio analysis unit according to the keyword library to obtain a first analysis result. 3.The intelligent interactive system for home care of the disabled and elderly person of claim 1, wherein, The behavior monitoring module further comprises: an image acquisition unit and an image analysis unit; wherein the image acquisition unit acquires indoor image data; the acquired image data is analyzed by the image analysis unit according to the pre-trained and converged behavior analysis model to obtain a second analysis result. 4.The intelligent interactive system for home care of the disabled and elderly people of claim 2 or 3, characterized in that, The behavior monitoring module further comprises: a comprehensive analysis unit, which comprehensively analyzes the first analysis result and the second analysis result to determine the final behavior analysis result.

5. The intelligent interactive system for home care of the disabled and elderly people according to claim 1, wherein, The trigger module comprises: an association analysis unit, a trigger analysis unit and a mode starting module; wherein the association analysis unit analyzes the behavior of the caregiver and the behavior of the cared-for to determine whether the behavior of the caregiver and the cared-for is associated; when the behavior of the caregiver and the cared-for is associated, the trigger analysis unit determines whether the associated behavior is the associated behavior in the associated trigger library; when it is the associated behavior in the associated trigger library, the mode starting module starts the auxiliary mode.

6. The intelligent interactive system for home care of the disabled and elderly person of claim 1, wherein, The interactive information received by the interactive module includes: interactive gestures and / or interactive speech; the prompt information is pre-stored information associated with the behavior of the corresponding cared-for.

7. The intelligent interactive system for home care of the disabled and elderly people according to claim 1, wherein, Further comprising: Dangerous behavior warning module, for dangerous judgment of the behavior of the cared-for based on the first dangerous behavior library configured in advance according to the specific circumstances of the cared-for, and when it occurs, the caregiver and / or the pre-configured warning contact person are prompted by voice. 8.The intelligent interactive system for home care of the disabled and elderly person of claim 1, wherein, Further comprising: Event reminder module, for event reminder based on pre-configured event reminder items. Further comprising: Event reminder module, for event reminder based on pre-configured event reminder items.

Images