Multifunctional assistance systems, especially for people living alone

Abstract

1. A multifunctional assistance system, particularly for a person living alone, comprising: a plurality of sensors distributed in a living area of ​​the person using the assistance system for monitoring predefined activities and predefined parameters; a control and communication unit provided in the living area for communicating with the sensors and the person; a database in which non-sensor-based information about the person and at least two different alert sequences are stored; and an evaluation unit for evaluating sensor data transmitted via the control and communication unit, the evaluation unit having access to the database and configured to detect from the sensor data potential abnormalities in the behavior and / or condition of the person, categorize the abnormalities into at least two categories, and trigger an alert based on the categorization in accordance with at least one of the at least two alert sequences.

Description

[Technical Field]

[0001] The present invention relates to a multifunctional assistance system, in particular for people living alone, and to a control and communication unit designed for this purpose. [Background technology]

[0002] Due to changing lifestyles and increasing age, the topic of self-determined living in old age has become increasingly relevant in recent years, both from a technological and macroeconomic point of view. Many people, even if they are mentally healthy, experience at least some degree of physical impairment as they age. However, many people prefer to live in their own apartment or house as much as possible, especially since there is a shortage of both nursing staff and care facilities, and it is no longer common in many societies for three or even four families to live under one roof.

[0003] A wide range of technological products, usually under the heading of Ambient Assisted Living (AAL), sometimes also called Active & Assisted Living, are already available to facilitate living in familiar environments, especially for people with certain physical limitations. Cogvis Software & Consulting GmbH (www.cogvis.ai), 1040 Vienna, offers, for example, a contactless fall sensor that can detect a person's movement within an apartment room using infrared measurements. Based on this, services and systems from this manufacturer offer automatic functions for fall detection and for generating alerts if a fall is detected. Similar functionality is offered by a contactless fall sensor from the Israeli company Vayyar (www.vayyar.com).

[0004] US2021 / 0074138A1, the disclosure of which is referenced in particular for technical implementations of automated fall detection that may also be used in the invention described herein, discloses a room monitoring system that uses infrared and other sensors such as LIDAR sensors to detect movements and evaluate them with the help of AI.

[0005] EP 1 566 782 A1 describes a fall detection system in which a domestic robot navigates to a person who has fallen and communicates with that person, triggering, for example, one or more requests for help. European Standard DIN EN 50134-2 (VDE 0830-4-2) specifies requirements for trigger devices for similar help-calling systems.

[0006] The concept of personalizing a fall detection algorithm for a particular person is known from EP 3 828 854 A1, where sensor data along with feedback information is transmitted to an external device which generates update information for the fall detection algorithm, which is then used by the fall detector to update and thereby personalize the fall detection algorithm.

[0007] Furthermore, numerous "smart home products" for the "intelligent" home are known, which are typically operated wirelessly via the Internet and / or WLAN and may exchange information with other devices including, for example, light switches, heating controllers, sensors that monitor when power consumers are switched on, and adapter plugs for switching on power consumers. For voice control of such products, so-called smart speakers are known that use AI support to evaluate voice commands and convert them into corresponding control commands for the product.

[0008] To support the provision of services, functions or applications via the Internet using portals and / or voice call functions are known, in particular the following technical aids:

[0009] Keycloak is an open source software product published at www.keycloak.org that enables identity-based single sign-on and access management for applications and services.

[0010] Apache Kafka is an open source software product published at kafka.apache.org that processes data streams and provides interfaces for loading and exporting data streams to third-party systems.

[0011] Microsoft® Azure is a cloud computing platform from Microsoft, available via http: / / azure.microsoft.com, that can be used to provide applications and services.

[0012] At www.twilio.com, a cloud communications platform is provided that has a programming interface specifically for making and receiving voice calls.

[0013] At www.traefik.io / traefik / , software and platform solutions are offered that make services and applications available, among other things, through the portal. Summary of the Invention

[0014] Although known products certainly fulfil their respective objectives, there has been a lack of an integrated solution up until now that allows detecting not only falls but also other abnormalities in a person's daily life, and that also allows bundling various functions of assisted living in such a way that they can be used easily and safely even by non-technical people. Based on this basis, the present invention is based on the technical task of providing a similar assistance system, and a control and communication unit designed for such a system, that can not only bundle various functions but also allow them to interact synergistically.

[0015] The problem is solved by a multifunctional assistance system having the features of claim 1 and a control and communication unit having the features of claim 24. Advantageous embodiments and further developments are the subject of the dependent claims.

[0016] The assistance system according to the invention comprises a plurality of sensors distributed in the living area of ​​the person using said assistance system for monitoring predefined activities and predefined parameters. It is suitable for use in the person's own home, as well as in nursing homes, hospitals and assisted living facilities. Depending on the individual setup of the system, it can also advantageously be used in hotels, for example. The term "living area" should therefore be interpreted broadly.

[0017] The system further comprises a control and communication unit provided in the living area for communicating with the sensors and the person; a database in which non-sensor-based information about the person and at least two different alert sequences are stored; and an evaluation unit for evaluating sensor data transmitted via the control and communication unit, the evaluation unit having access to the database and configured to detect potential abnormalities in the person's behavior and / or condition from the sensor data, categorize the abnormalities into at least two categories, and trigger an alert based on the categorization according to at least one of the at least two alert sequences. An "alert sequence" is understood to be a computer-readable list of addresses and / or instructions stored in the database that can be used by the evaluation unit to trigger an alert so that specific people and / or facilities are notified in a predetermined sequence. The term "alert" is understood to mean any form of contact made to convey information that an abnormality has occurred. Thus, an alert can be, for example, an automated call to a specific person and / or the sending of a text message to the same person. If the person does not respond immediately, or within some time interval depending on the detected anomaly, an alert is triggered to the next person or facility in the alert sequence.

[0018] In the event of a specific behavioral and / or condition anomaly, various persons and / or facilities can be notified simultaneously and / or independently of whether previous "links" in the alert sequence have responded in each case. For example, if the assistance system detects a potentially life-threatening situation, automated messages can be sent simultaneously and independently to emergency physicians, cleaning staff, and relatives of the affected person. At least one of the alert sequences can be a dynamically updated alert sequence, i.e., the persons and / or facilities listed in the update sequence can store and change information about their availability, for example, according to predefinable criteria, and / or provide for identifying the location of at least certain persons provided in the alert sequence and updating the sequence so that persons closest to the living area monitored by the assistance system are notified first.

[0019] The term "database" may be understood to mean any type of memory that is accessible to the evaluation unit and that may be physically distributed across different units.

[0020] The term "non-sensor-based information" refers to all types of data relevant to the respective use case that cannot be obtained from sensors located in the living area, such as the name and age of the person using the assistance system, their medical history, certain current medications, information about their hobbies, and life history, if applicable.

[0021] The term "abnormalities in the behavior and / or condition of a person" refers to all types of deviations from the "normal" behavior or condition of that person. An abnormality in this sense can be, for example, a fall, but also abnormal high blood pressure, a change in toileting behavior, sudden nocturnal activity, etc. However, an abnormality in this sense can also be a request for help from the person, which activates the assistance system via voice control and triggers an alert.

[0022] The term "classifying into at least two categories" is understood here to mean that the detected abnormalities are categorized according to predefined criteria, for example, according to whether the respective abnormality indicates a potentially life-threatening condition of the person using the assistance system, so that immediate measures, such as alerting an emergency physician, must be initiated, or according to whether the abnormality indicates a more gradual decline in the person's health status, such as the onset of dementia. In the case of abnormalities that are not immediately life-threatening, a "silent alert" is triggered according to default settings, for example, to inform a doctor or nursing staff caring for the person using the assistance system that a change in the person's behavior indicates a decline in the person's health status, so that appropriate measures can be taken, if necessary. In this sense, the assistance system can advantageously be understood as a diagnostic tool that enables relevant professionals to make a diagnosis.

[0023] The term "evaluation unit" is not to be understood as a fixed physical unit, for example in the form of a dedicated computer, although it can also be realized in this way. Typically, the "evaluation unit" is a dynamically changing, self-learning artificial intelligence that uses software components, preferably specific hardware, to execute the steps provided in the desired evaluation and alert sequence. In this sense, it can be a cloud-based Internet platform that is set up as an evaluation unit in accordance with the present invention by appropriately configuring it. The hardware can be a cluster or network of hardware units capable of performing specific tasks such as speech recognition or speech generation, or similar existing services and modules through which existing services and modules are accessed. The control and communication unit can be coupled to the evaluation unit so that the evaluation unit can further check the status of the control and communication unit, for example, whether the software installed therein is up to date, and initiate an automatic update if necessary. However, the control and communication unit may also be capable of performing such checks itself. The present invention advantageously provides a great degree of flexibility, so that the assistance system can be easily and cost-effectively adapted to the respective application. For example, if a person moves into a home that already has an assistance system installed and was previously occupied by someone who speaks a different language than the person moving in, the assistance system can simply access a different language module. For example, if a new sensor is installed in a monitored living area, the control and communication unit can automatically retrieve the software interface / communication protocol needed to communicate with that sensor. The evaluation unit collects and stores the data sent to it via the control and communication unit, preferably in a protected area, preferably cloud-based, and never on-site in the monitored living area, so that a high level of data security can be easily guaranteed even if the control and communication unit fails.Communication between the evaluation unit and the control and communication unit is preferably carried out wirelessly via at least one telecommunication network, which can advantageously provide that the control and communication unit is equipped with its own communication device, e.g. an LTE device, and no router or local network is required.

[0024] The multifunctional assistance system is designed especially for people living alone, but can also be used without any restrictions, for example, by couples. It is characterized by its excellent retrofitting ability and generally does not require costly conversion or installation measures. It can use standard sensors that communicate with the control and communication unit via standardized communication protocols.

[0025] The multifunctional assistance system according to the present invention allows us to "break up" previous "data silos" (of individual sensors used, such as fall sensors, and individual devices used, such as smart speakers) and view data cumulatively so that new insights can be gained. For example, the assistance system according to the present invention can be configured to detect that a person using the system is no longer eating regularly and / or sleeping for very long periods of time after a change in medication. For example, refrigerator sensors, drawer sensors, and bed-monitoring motion sensors can be evaluated together with medication schedules stored in a database. The assistance system allows us to check so-called "ADLs" (Activities of Daily Living, a standard and measurement system used by health services to check a person's condition and the level of care they receive).

[0026] Further details and advantages of the invention will become apparent from the following purely exemplary and non-limiting description of one embodiment in conjunction with the drawing comprising three figures. [Brief explanation of the drawings]

[0027] [Figure 1] 1 is a schematic diagram of an apartment equipped with an assistance system according to the invention;

[0028] [Figure 2] 1 is a schematic diagram of a combined evaluation unit and control and communication unit;

[0029] [Figure 3] 1 is a schematic diagram of a method according to the present invention; DETAILED DESCRIPTION OF THE INVENTION

[0030] 1 shows an apartment in which a number of sensors are distributed for monitoring predefined activities and predefined parameters, and a control and communication unit 10 is provided for communication with the sensors and the persons. The databases belonging to the assistance systems and the evaluation unit are not shown.

[0031] The apartment shown has a hallway 12, a kitchen 14, a living room 16, a bedroom 18, and a bathroom 20. The apartment door 22 has a contact sensor 24. Corresponding contact sensors are also provided on certain cupboards and refrigerators in the kitchen 14 and on cupboards in the bedroom 18. These sensors 24 can be used to monitor the opening and closing of the apartment and cupboard doors. A blood pressure monitor 26 is located in the kitchen 14. The blood pressure monitor 26 can be a mobile device that can be located in any room.

[0032] Motion detectors 28 are provided in all rooms. Fall sensors 30 are provided in at least one room, in this case the living room 16.

[0033] Two current sensors 32 are provided in the kitchen 14 which monitor the switching on of certain appliances, such as the stove and oven, or certain other kitchen appliances.

[0034] A night light 34 is provided in the bedroom 18.

[0035] The weighing scale 36 is provided in the washroom 20. In this embodiment, the devices and sensors 22-36 may be wirelessly coupled to the control and communication unit 10 so that information recorded by them can be read out or, in the case of the night light 34, so that it can be activated by the control and communication unit 10.

[0036] The sensors shown, their location and their distribution in the individual rooms are purely exemplary to facilitate understanding of the invention. Further and / or other sensors may be provided, which may be distributed differently in the rooms. Using similar sensors, an assistance system may be realized which is configured according to claim 1 and which may also optionally have the following features:

[0037] The control and communication unit 10 can be configured to set up a local wireless communication network through which it can communicate with at least some of the sensors. This has the advantage that the sensors can be easily distributed in the living area to be monitored and positioned so that they optimally perform their respective tasks. Furthermore, faulty sensors can be easily replaced and new sensors can be easily integrated into the system without the need for cabling.

[0038] Preferably, the evaluation unit is configured as a non-local computing unit with which the control and communication unit 10 communicates wirelessly or, in particular, via a wired connection. This has various advantages. For example, the hardware effort in the monitored living area can be minimized, maintenance and updates of the evaluation unit can be simplified (the unit is usually formed by components located in a data center), and data transmitted to the evaluation unit via the control and communication unit can be particularly protected, especially in so-called "Internet of Things" (IoT) systems. The algorithms used by the evaluation unit are usually processed in the cloud. Even if the control and communication unit in the monitored living area malfunctions or is accidentally disconnected from the power source, data may not be lost. Furthermore, the control and communication unit is preferably configured so that it starts automatically when connected to a power source, eliminating the need for time-consuming startup procedures. In particular, elderly people who are not tech-savvy may disconnect the control and communication unit to connect different electrical appliances, such as vacuum cleaners, to the corresponding sockets and may find the special startup procedures confusing.

[0039] In a preferred embodiment, the control and communication unit is configured to check whether it is connected to the local power supply network and, if not, trigger an alert according to a predetermined alert sequence. Since the control and communication unit, as a central element of the local system, should always be online, this configuration ensures that interruptions in the activity of the control and communication unit are detected. For this purpose, the control and communication unit may have its own communication module and energy storage unit in order to be able to communicate with the evaluation unit in the event of a disconnection from the local electrical network or a failure of the electrical network.

[0040] Alternatively or additionally, it may be provided that the evaluation unit is configured to constantly or intermittently check the functionality of the control and communication unit and to trigger an alert according to a predetermined alert sequence if a malfunction is detected. Preferably, the control and communication unit is configured to constantly or intermittently check the functionality of the sensors and to trigger an alert according to a predetermined alert sequence if a malfunction is detected. Tests of the sensors may be triggered by the evaluation unit as part of remote maintenance.

[0041] Preferably, the control and communication unit is configured to communicate with the sensors by means of various communication protocols, in particular by means of at least some of the following protocols: Wi-Fi®, Bluetooth®, Zigbee®, Z-Wave®, 6LoWPAN, RFID, cellular IoT protocols, NB-IOT, 5G, NFC, LoRaWAN, LTE, protocols from the Infrared Data Association (IrDA), and IR remote control protocols from consumer electronic products. These protocols may be stored in the control and communication unit or may be available for retrieval in the evaluation unit. Ultimately, the only important thing is that commercially available sensors can be connected to the control and communication unit so that the data they record can be transferred to the evaluation unit without any major installation effort.

[0042] The control and communication unit typically comprises a microphone, a loudspeaker and a display, preferably a touch display, thus making it possible to communicate audibly and visually with the person using the assistance system.

[0043] The sensors used preferably comprise sensors from at least two of the following types of sensors: motion sensors, presence sensors, fall sensors, temperature sensors, door open sensors, window open sensors, current sensors for specific electrical devices, weight sensors, blood pressure sensors, infrared sensors, ultrasonic sensors, LIDAR sensors, blood glucose sensors, medicine cabinet sensors, refrigerator sensors, toothbrush sensors, smoke detectors, CO2 sensors. It should be noted that in the assistance system according to the invention, sensors that are actually "dumb" become "smart" because they suddenly have logic. For example, an electricity meter for a television may indicate that a person using the system is no longer keeping to his or her usual rhythm (e.g., watching the news at 8 p.m.). The electricity meter is therefore indirectly endowed with logic, i.e., via the evaluation unit, and in this sense becomes smart.

[0044] Preferably, the evaluation unit includes non-sensor-based data from the database when an abnormality is determined, and is configured to output any change in the non-sensor-based data as an abnormality condition when an abnormality is detected. For example, information about current medication may be stored in the database as non-sensor-based data. If an abnormality such as a change in sleep behavior is detected, the system may notify the person or unit to be alerted according to the respective alert sequence that an abnormality has occurred, either simultaneously with or shortly after the change in medication.

[0045] Preferably, the evaluation unit is configured to use a self-learning algorithm for the evaluation, so that the system automatically further develops itself and adapts to new life circumstances of the person using the system.

[0046] In another preferred embodiment, the control and communication unit is configured to interface with a smart home control unit, which advantageously allows the system to undertake activities far beyond fault determination and does not require the person using the system to become familiar with the various control units.

[0047] In a further preferred embodiment, the control and communication unit includes an evaluation unit and / or at least one mobile communication device that may be connected to the control and communication unit and through which information about the person and / or living area being released can be displayed to the user of the mobile communication device. The mobile communication device may be part of at least one of the at least two alert sequences. The communication device may be a standard smartphone, and the user may be, for example, a close relative of the person using the system. Thus, for example, an adult child can check at any time whether their mother, who requires care, is doing well. Advantageously, the mobile communication device may also be configured to control smart home control devices after appropriate authorization by the person using the assistance system. For example, a son can control the heating in a living area when he brings his mother home from a visit so that the living area is at a desired temperature upon arrival.

[0048] Preferably, the control and communication unit is configured to communicate with the person according to predefined or variable criteria. The variable criteria may be criteria learned from the person's previous behavior and / or condition. Thus, communication can be established with the person as needed and enabled without the person having to actively request it. For example, certain emotional disorders can be prevented or treated. For example, if it is determined that a person using the system feels lonely, an AI-assisted conversation can be automatically initiated, gratitude journaling (verbally and possibly automatically converted to writing) can be encouraged, and the person can be motivated to remember the good things in life. Filtering in the form of so-called sentiment analysis ensures that only positive thoughts are recorded. Triggering morning and evening conversations can be AI-assisted, and mornings and evenings can be more positive with pleasant sayings. It is also possible for the person to be encouraged to play brain-training memory-enhancing games.

[0049] Preferably, the control and communication unit is also configured to be used as a telephone and / or video telephone.

[0050] Advantageously, the assistance system is configured to allow the person to communicate with the system in natural language, which may be done using an AI-supported chatbot, where advantageously the assistance system allows the chatbot to be used without requiring special reprogramming.

[0051] If the assistance system communicates automatically with the person, the communication may concern, in particular, one topic from the following list of topics: queries about detected abnormalities, reminders for specific appointments and actions, rehabilitation measures, preventive measures, positive psychology interventions, errand requests. However, this list of topics is by no means exhaustive. For example, religious or nutritional topics can be discussed with AI support. Reminders for appointments or actions, such as eating, drinking water, or taking medicine, can also be spoken and simultaneously appear on the screen of the control and communication unit. A reminder can be marked as completed by confirming it.

[0052] Preferably, the evaluation unit is configured to use the current and historical sensor data to draw conclusions about at least some of the following conditions and capabilities of the person using the assistance system: health state, emotional state, cognitive ability, ability to live independently.

[0053] The assistance system according to the invention makes it possible to evaluate information about the condition and behavior of the person using the system to form a complete picture, which can be shared with other interested parties such as relatives, doctors or care services.

[0054] Since carrying on a conversation is often difficult for people who can no longer hear well, the control and communication unit can be equipped with a more powerful speaker and display all dialogue on a screen in clear, easy-to-read text.

[0055] Thanks to voice assistants and internet connectivity, residents can easily regain access to so-called "digital participation" even when they are not (or no longer) capable of handling IT. Generative AI allows the control and communication unit to conduct natural language dialogues and provide information or other advice on topics such as nutrition. A biographical study based on medical history forms is also possible. Here, the system gives advice on how a person can behave. Memories can also be processed. There are multiple modes by which a person can communicate with the control and communication unit. Thus, the system not only allows for quick contact with relatives, caregivers, etc. in emergencies, but also significantly contributes to managing daily life in an independent and safe manner despite certain health limitations. In doing so, enjoyment and interaction do not have to be neglected. Long-term monitoring of the behavior of a person using the system can be used to identify cognitive impairments. If a person wakes up more frequently at night and walks around the house, they probably have difficulty structuring their day, which could indicate the possibility of dementia or Parkinson's disease. The integrative approach is a special feature of the system. It is a holistic solution that combines information about activity and behavioral profiles to sound an alert or indicate that immediate support is needed. For example, there are also prompts or commands to take medicine at the right time, turn off the stove, or drink a drink. The focus here is on the concept of prevention. It is clear that the system not only allows for the prevention of sudden dangers, but also the observation of the progress of a person's behavior and / or condition. Changes in behavior are recorded during long-term observation to keep a record of the person's status. With consent, recorded dialogues can be used in long-term observation to understand how speech changes. Based on the status analysis, an expert can then assess whether there are any changes that need to be checked by a specialist.The system takes a holistic approach and provides support to address everyday life.

[0056] Health status information can be displayed as a dashboard and / or as a traffic light system. The person using the system can decide what data to see and who sees it. For example, many people do not want their children to see what they are doing in detail (e.g., how many times they visit the toilet).

[0057] The assistance system may support both prevention and rehabilitation, for example after a stroke, by launching games and speech exercises, for example.

[0058] Figure 2 shows a system according to the present invention with one of several possible configurations. The evaluation unit 10 is connected via a telecommunications network 20 or WAN (Wide Area Network) to a smartphone as an alert receiving device 30, a body-contactless fall sensor 40, and a control and communication unit 50. For simplicity of illustration, only one of the alert receiving devices and one of the fall sensors is shown in Figure 2. It should be understood that the evaluation unit 10 is configured to interact with multiple control and communication units in various living areas.

[0059] The control and communication unit 50 comprises an audio input and audio output device 52 with a loudspeaker and microphone, a processor 51 connected to a known memory unit 56 for loading and retrieving data and instructions, and a touch screen 54 for further input and / or output via a display.

[0060] The evaluation unit 10 comprises: a database 60 in which residential addresses are associated with at least one of the control and communication unit 50 and the fall sensor 40 to link each of the fall sensor output and the audio output and the control and communication unit input to one of the residential addresses; an IoT Hub 7 with multiple APIs 70 for fall sensor outputs, only one of which is shown in FIG. 2; a speech processing unit 80 for converting stored text sequences into audio output and audio input into other stored text sequences for voice control; An alert unit 82 that utilizes API 70 for fall sensor output and implements the following functions: - receiving the sensor output using API 70 for the tip output; - triggering an audio dialogue on the control and communication unit 50 according to the alert sequence and, if necessary, sending a request for assistance according to the link with an indication of the residential address if at least one condition is met, including the condition that the received one of the fall sensor outputs signals an alert, in particular a fall alert; - cancelling the alert if a denial of assistance is detected; - Sending a request for help to the alert receiving device 30 according to a schedule.

[0061] In the embodiment shown, the fall sensor 40 is part of a fall detection system set up using the network 20, and the fall sensor output is, for example, an evaluation of an infrared image from a sensor in the house. The API 70 is then configured as a gateway for receiving the evaluation by the evaluation unit.

[0062] The evaluation unit 10 also includes a helper database 62 in which each residential address is associated with a list of helper contacts with ranking order and helper availability times. The evaluation unit 10 is configured with a helper database module 94 to enable authorized, form-based remote access to the helper database 62, and thus serves as a portal for authorization-dependent access to the helper database 62 for deletion, modification, reading, and / or addition. This also allows helper availability times to be managed, and in particular entered.

[0063] The Send a Request for Help feature is set up to do the following: Create a selection of helper contacts in a list, including their assigned helper availability times, Send a request for assistance to one of 30 alert receiving devices according to the highest ranked helper contact in the selection and request confirmation; Check the number of contacts of helpers in the selection and receive confirmation; If the number is greater than 1 and there have been no confirmations for a predetermined period of time, updating the selection by removing the entry corresponding to the highest ranked helper contact; Repeatedly sending requests for assistance and requesting confirmation.

[0064] Further sensors 42, 44 for transmitting further sensor outputs are linked to the processor of the control and communication unit 50 by means of a wireless connection to the control and communication unit, as are the audio input and audio output devices 52. In the database, a link is further provided of the further sensor outputs to one of the residential addresses. The evaluation unit 10 also comprises APIs 72 for the further sensor outputs, only one of which is shown in FIG. 2.

[0065] The evaluation unit 10 also comprises an analysis unit 84 which implements the following functions: Creating an address-specific profile among residential addresses based on the link and using other sensor outputs and fall sensor outputs, if applicable; and · Record and categorize changes in profiles over time.

[0066] Other sensors 42, 44 are sensors for monitoring when a door is closed and / or when an electrical consumer such as a stove is switched on.

[0067] The evaluation unit 10 also includes a classification reconciliation module 96 that serves as a portal for authorization-dependent access to classifications for retrieval and / or factors of classifications for retrieval, modification, deletion, or supplementation via authorized, form-based remote access.

[0068] Advantageously, the ability to trigger a voice dialogue and provide a request for help is a function that requires the existence of a condition whose classification signals danger.

[0069] The evaluation unit 10 comprises a machine learning unit 86 that implements the following functions: Capturing feedback information by capturing the deletion or addition of classification factors for a set of addresses among residential addresses; Updating classification factors for a set of addresses; · Iteratively collecting feedback information and updating the classification factors using iterations of the classification factors to minimize the degree of detected cancellation of alerts and / or removal or addition of classification factors.

[0070] The evaluation unit 10 also comprises an appointment reminder unit 88 for reminding appointments by means of an audio output. The server unit 1 also comprises a voice input unit 90 with the capability to supplement the profile, for example, by voice input. The evaluation unit 10 is also set up as a portal for form-based remote setting of queries on voice input, in order to supplement the profile or to allow adjusting the classification, in particular the associated factors or weightings, via a classification module 96 using the portal in a form-based and permission-dependent manner. The evaluation unit 10 is also set up as a portal for setting appointment reminders in a permission-dependent manner, with the appointment reminder unit 88. For example, voice prompts for blood pressure readings or reminders for food and / or liquid intake can be set up.

[0071] In the control and communication unit 50, a processor 51 is connected to a memory such as a flash memory 56 that contains the necessary operating system, drivers and applications.

[0072] In this example embodiment, the evaluation unit 10 comprises a chatbot 92 for interacting with the audio output and input unit 52, in particular for voice games.

[0073] Here, the control and communication unit 50 also comprises a touch screen 54 as a display (not shown).

[0074] Figure 3 is a process diagram consistent with the process according to the invention. The process diagram is divided by vertical lines into: · The process in the apartment, shown on the left, The process of interaction with the Assistant outside the home, shown in the center, and The process in the evaluation unit 10 shown in FIG. 1; this is shown on the right.

[0075] The method illustrated in Figure 3 is a method for operating the network of hardware units schematized in Figure 2, in which data connections are provided from the fall sensor 40 to the evaluation unit 10, between the control and communication unit 50 and the evaluation unit 10, and from the latter to the alert receiving device 30. The following steps are carried out using the alert unit 82: (S1) receiving a tipping sensor output using API 70 for tipping output; (S2) triggering an audio dialogue on the control and communication unit 50 according to the link under at least one condition including a condition that a received one of the fall sensor outputs indicates a fall, and scheduling the transmission of a request for assistance indicating one of the residential addresses according to the link; (S3) executing a voice dialogue on the control and communication unit 50 when accessing the speech processing device 80; (S13) canceling the schedule by voice control when the next text sequence is recognized as a help refusal; (S6) Sending a request for assistance to the alert receiving device 30 according to a schedule.

[0076] The fall sensor 40 provides a fall sensor output in step S1 that indicates a fall event. A system in which sensor units in the home are connected to a cloud-based fall sensor platform that ultimately provides the fall sensor output in step S1 can also be used for the fall sensor output.

[0077] To receive the fall sensor output, an API 70 is provided in the evaluation unit, which allows the evaluation unit to proceed to step S2, where, based on the fall sensor output, the evaluation unit triggers an audio dialogue on the fall sensor 40 or on the control and communication unit 50 located in the same apartment as the sensor unit. The database 60 uses a link to ensure that the audio dialogue is correctly triggered on the control and communication unit 50 located in the apartment. This is done on the condition that one of the received fall sensor outputs indicates a fall. The audio dialogue is then executed on the control and communication unit 50 in step S3. For this purpose, audio streaming is set up between the control and communication unit 50 and the evaluation unit 10. Thus, the audio dialogue is executed in step S3 by the control and communication unit 50 accessing the speech processing unit 80, which may also interact with a cloud-based speech recognition service. The audio dialogue is executed on the control and communication unit 50 in step S3 to allow feedback from people in the house to the evaluation unit 10. An alert confirmation is received by the evaluation unit 10 in step S4 both when assistance is requested as feedback and when a predetermined period of time has elapsed after step S3 was triggered. As described above, the evaluation unit 10 is configured with a helper database 62 in which each residential address is assigned a list of helper contacts with rank order and helper availability times. If an alert confirmation is received, a selection of currently available helper contacts from the list is made in step S4.

[0078] In step S6, a request for assistance is then sent and confirmation is requested from one of the alert receiving devices corresponding to the highest ranked helper contact in the selection according to rank, for which purpose an email and an SMS are sent to and received by the assistant's smartphone in step S7.

[0079] According to the sequence described above, if at least one condition exists, including the condition that one of the received fall sensor outputs indicates a fall, scheduling of sending a request for assistance along the link with an indication of one of the residential addresses is then performed. Advantageously, scheduling can also be advanced when a stored text sequence is recognized as an assistance request.

[0080] Using a browser-based application on the Assistant's smartphone, the Assistant transmits the following in step S8: a check that triggers step S10 in the evaluation unit 10, or A rejection which triggers a step S9 in the evaluation unit 10.

[0081] Alternatively, the rejection that triggers step S9 in the evaluation unit 10 is carried out automatically via a process flow of step S7 that bypasses step S8, i.e. after a predetermined period has elapsed after step S6, during which step S10 was not triggered.

[0082] Alternatively, step S3 of performing a voice dialogue using voice control allows the voice control to cancel scheduling when a refusal of help is detected. Thus, voice control in step S13 cancels the scheduling of the help request even after it has been sent. A triggered alert can be marked as a false alert or non-critical. Furthermore, it is provided that the scheduling of sending the help request can be canceled in step S13, or on the smartphone in step S12, even after it has been sent. Scheduling means specifying the time and date from which the alert message should be sent according to step S6.

[0083] Furthermore, it is provided that the scheduling of sending a request for assistance can be cancelled if necessary even after it has been sent, by inputting on the touch screen 54 provided on the control and communication unit 50, or alternatively by means of buttons provided on the control and communication unit, step S14, or by voice control in step S15.

[0084] In step S5 it is checked whether the scheduling has been cancelled. If the schedule has not been cancelled, step S5 checks whether the number of helper contacts in the selection is greater than one. In step S5, if the number is greater than one, and if there has been no confirmation for a predetermined period of time as signalled by step S9, the selection is updated. The update is done by removing the entry corresponding to the highest ranked helper contact, followed by step S6 to alert the next helper, whereas otherwise if the number is one, step S6 is bypassed and the already alerted helpers are alerted again.

[0085] Thus, the following functions or steps are implemented in the evaluation unit: Check the number of contacts of helpers in the selection and receive confirmation; If the number is greater than 1 and there have been no confirmations for a predetermined period of time, updating the selection by removing the entry corresponding to the highest ranked helper contact; Repeatedly sending requests for assistance and requesting confirmation.

[0086] The confirmation in step S8 also triggers step S11, which displays a message on the touchscreen 54 of the control and communication unit 50 regarding the assistant's confirmation. In step S10, the scheduling of sending the help request is canceled, and the assistant is further prompted to consult by a message on the smartphone. Canceling the scheduling of the help request ensures that no further alerts may be sent in step S6 after step S5. A function or method part may also be provided to ensure that, after canceling the scheduling of the help request dispatch, no further alert dispatches may be made in step S6 after step S5, and that a message is sent to all assistants for which step S6 has been performed and for which confirmation has not been received via step S10. These assistants may therefore be notified that the alert has been resolved.

[0087] The consultation is performed via a voice call between the smartphone and the control and communication unit 50, which also has voice call and telephone functions set up for this purpose. The assistant then decides to either trigger step S13 on the smartphone or to go to the apartment. After the assistance has been provided, an input S14 is then made on the touchscreen 54 provided on the control and communication unit, or alternatively on a button provided on the terminal device or by voice control, which input cancels the scheduling of sending the assistance request in step S15 (possibly even after the assistance request has been sent).

[0088] The server device, in particular the portal and / or respective form-based input via units or modules 88, 94, may be configured for one or more of the following features or functions: Edit your user profile, including two-factor authentication; Set appointments with language reminders, - Set medications, including voice reminders; View medication regimens, Set drinking water reminders, including voice reminders or drinking sounds; Data acquisition and evaluation, especially of sensor outputs, Managing sensor technology, particularly via a classification adjustment module 96; · Monitor vitality values ​​using sensor output; · Administering licensing for kinship and care services; Event analysis based on sensor output, Alert handling, User Administration, Alert sequence management, Device management, Remote access to the control and communication units, in particular via teleport, Remote software updates on control and communication units Data migration.

[0089] Furthermore, the number of times each readable sensor output, in particular the fall sensor output, may also be captured by the evaluation unit 10, stored and made available within the portal.

[0090] Within the evaluation unit 10, an API can be provided for the voice interface, in particular for voice control, such as: API Twilio SMS, WhatsApp and phone calls, API Vayyar fall sensor, API Withings or Nokia.

[0091] The following techniques, features and products may be used to implement the evaluation unit 10: Domain-Driven Design Distributed streaming solutions using Kafka, including data replication, data aggregation, partitioning, load balancing and fail-safety; Identity management with Keycloak, including 2FA, OpenID Connect, OAuth2, authentication and authorization Microservice architecture using Kubernetes and Docker Secure connection between end devices and the cloud via Azure IoT Hub; Automatic data synchronization between the portal and end devices; Device simulators, ·Data analysis / AEDL, Quartz system scheduler.

[0092] Via step S11 described above, it is preferably displayed in a transparent manner how the alert sequence will be processed and who will be handling the case.

[0093] For sensor output, interfaces via Bluetooth to weight scales, blood pressure monitors, and blood glucose meters can be implemented as examples. Vitality data can be transmitted completely independently of the device via audio input and audio output devices with the help of a speech processing unit 80. This promotes participation, personal responsibility, and offers the possibility to continue using familiar devices.

[0094] Following step S6 described above, an exemplary text for the alert is: Fall: "Fall alert at the home of Maria Mustermann, Beispielweg 14, 12345 Irgendwo, time: 19:20 12.08.2020, phone number +49 1234 567891011 or +49 9876 543210. Could you please take care of this? 1=Yes, 9=No" Crisis situation: "Severely long period of inactivity at the home of Maria Mustermann at Beispielweg 14, 12345 Irgendwo, time: 19:20 12.08.2020, phone number +49 1234 567891011 or +49 9876 543210. Can you help with this? 1=Yes, 9=No" Vitality value: "Abnormal hypertension 167 / 102 at the home of Maria Mustermann, Beispielweg 14, 12345 Irgendwo, time: 19:20 12.08.2020, phone number +49 1234 567891011 or +49 9876 543210. Would you like to address this? 1 = yes, 9 = no." Advantageously, in step S6 the alert can optionally be sent via an API to another application. The German emergency service Malteser uses its own system to manage incoming emergency calls. This can then be addressed via a configurable API, and an API for reporting the alert back can also be provided.

[0095] In addition to the touchscreen 54, the evaluation unit 10 may also advantageously control outputs to smart home devices, such as lighting devices, via the control and communication unit 50 and in response to some of the sensor outputs and / or voice input to the audio input and output unit 52, and also according to settings provided to the evaluation unit 10 via the portal, possibly in a form-based and permission-dependent manner. (Other possible items) (Item 1) A multifunctional assistance system, especially for people living alone, comprising: a plurality of sensors distributed in a living area of ​​a person using the multifunctional assistance system for monitoring predefined activities and predefined parameters; a control and communication unit provided in said living area for communicating with said sensors and said person; a database having non-sensor-based information about the person and at least two different alert sequences; and an evaluation unit for evaluating the sensor data transmitted via said control and communication unit; wherein the evaluation unit is capable of accessing the database; Detecting potential anomalies in the person's behavior and / or condition from the sensor data; categorizing said anomalies into at least two categories; triggering an alert based on said categorization according to at least one of said at least two alert sequences. A multi-function assistance system configured as follows. (Item 2) Item 2. The multifunctional assistance system according to item 1, wherein the control and communication unit is configured to set up a local wireless communication network through which it can communicate with at least some of the sensors. (Item 3) 3. The multifunctional assistance system according to item 1 or 2, wherein the evaluation unit is configured as a non-local computing unit with which the control and communication unit communicates wirelessly or by wire. (Item 4) 4. The multifunctional assistance system according to any one of items 1 to 3, wherein the control and communication unit is configured to check whether it is connected to a local power supply network and, if not, to trigger an alert according to a predetermined alert sequence. (Item 5) 5. The multifunctional assistance system according to any one of items 1 to 4, wherein the control and communication unit is configured to communicate with the sensors via various communication protocols, in particular by at least some of the following protocols: Wi-Fi, Bluetooth, Zigbee, Z-Wave, 6LoWPAN, RFID, cellular IoT protocols, NB-IOT, 5G, NFC, LoRaWAN, LTE, Infrared Data Association (IrDA) protocols, and IR remote control protocols from consumer electronic products. (Item 6) 6. The multifunctional assistance system according to any one of items 1 to 5, wherein the control and communication unit has a microphone, a loudspeaker, and a display, preferably a touch display. (Item 7) 7. The multifunctional assistance system according to any one of items 1 to 6, wherein the sensors include sensors from at least two of the following types of sensors: motion sensor, presence sensor, fall sensor, temperature sensor, door open sensor, window open sensor, current sensor for a specific electrical device, weight sensor, infrared sensor, ultrasonic sensor, LIDAR sensor, blood pressure sensor, blood glucose sensor, medicine cabinet sensor, refrigerator sensor, toothbrush sensor, smoke detector, and CO2 sensor. (Item 8) 8. The multifunctional assistance system according to any one of items 1 to 7, wherein the evaluation unit has non-sensor-based data from the database when determining an abnormality, and is configured to output any change in the non-sensor-based data as a condition of the abnormality when an abnormality is detected. (Item 9) 9. The multifunctional assistance system according to any one of items 1 to 8, wherein the evaluation unit is configured to use a self-learning algorithm for evaluation. (Item 10) 10. The multifunctional assistance system according to any one of items 1 to 9, wherein the control and communication unit is configured to couple with a smart home control device. (Item 11) 11. The multifunctional assistance system according to any one of claims 1 to 10, comprising at least one mobile communication device that may be connected to the evaluation unit and / or the control and communication unit and through which information about the person and / or the living area released to a user of the mobile communication device can be displayed. (Item 12) Item 12. The multi-functional assistance system of item 11, wherein the mobile communication device is part of at least one of the at least two alert sequences. (Item 13) Item 10, and the multifunctional assistance system described in any one of items 11 or 12, wherein the mobile communication device is configured to control the smart home control device after corresponding authorization by the person using the multifunctional assistance system. (Item 14) 14. The multifunctional assistance system according to any one of items 1 to 13, wherein the control and communication unit is configured to communicate with the person according to predefined or variable criteria. (Item 15) 15. The multifunctional support system according to any one of items 1 to 14, wherein the multifunctional support system is configured so that the person can communicate with the multifunctional support system in natural language. (Item 16) 16. The multifunctional assistant system of any one of items 14 or 15, wherein the communication with the person relates to at least one topic from the following list of topics: queries about detected abnormalities, reminders for specific appointments and actions, rehabilitation measures, preventive measures, positive psychology interventions, errand requests. (Item 17) 17. The multifunctional assistance system according to any one of items 14 to 16, wherein the variable criteria are learned from previous actions and / or states of the person. (Item 18) 18. The multifunctional assistance system according to any one of claims 1 to 17, wherein the control and communication unit has its own communication module and energy storage unit in order to be able to communicate with the evaluation unit in case of disconnection from the local electrical network or a failure of the electrical network. (Item 19) 19. The multifunctional assistance system according to any one of items 1 to 18, wherein the evaluation unit is configured to constantly or intermittently check the functionality of the control and communication unit and, if a malfunction is detected, to trigger an alert according to a predetermined alert sequence. (Item 20) 20. The multifunctional assistance system according to any one of items 1 to 19, wherein the control and communication unit is configured to constantly or intermittently check the functionality of the sensor, and if a malfunction is detected, trigger an alert according to a predetermined alert sequence. (Item 21) 21. The multifunctional assistance system according to any one of items 1 to 20, wherein the evaluation unit is configured to draw conclusions from current and historical sensor data about at least some of the following conditions and capabilities of the person using the multifunctional assistance system: health state, emotional state, cognitive ability, ability to live independently. (Item 22) 22. The multifunctional assistance system according to any one of items 1 to 21, wherein the control and communication unit is configured to be used as a telephone and / or a video telephone. (Item 23) 23. The multifunctional assistance system according to any one of items 1 to 22, wherein the at least one alert sequence is a continuously updated alert sequence. (Item 24) A control and communication unit for a multifunctional assistance system according to any one of items 1 to 23.

Claims

1. A multifunctional assistance system, especially for people living alone, comprising: a plurality of sensors distributed in the living area of ​​the person using the multifunctional assistance system for monitoring predefined activities and predefined parameters; a control and communication unit provided in said living area for communicating with said sensors and said person; a database having non-sensor-based information about the person and at least two different alert sequences; and an evaluation unit for evaluating the sensor data transmitted via the control and communication unit; wherein the evaluation unit is capable of accessing the database; - detecting potential anomalies in the person's behavior and / or condition from the sensor data; categorizing the abnormalities into at least two categories; Triggering an alert based on said categorization according to at least one of said at least two alert sequences. A multi-function assistance system configured as follows.

2. 2. The multifunctional assistance system of claim 1, wherein the control and communication unit is configured to set up a local wireless communication network through which it can communicate with at least some of the sensors.

3. The multifunctional assistance system according to claim 1 , wherein the evaluation unit is configured as a non-local computing unit with which the control and communication unit communicates wirelessly or by wire.

4. 2. The multifunctional assistance system of claim 1, wherein the control and communication unit is configured to check whether it is connected to a local power supply network and, if not, trigger an alert according to a predetermined alert sequence.

5. 2. The multifunctional assistance system of claim 1, wherein the control and communication unit is configured to communicate with the sensors via various communication protocols, in particular by at least some of the following protocols: Wi-Fi, Bluetooth, Zigbee, Z-Wave, 6LoWPAN, RFID, Cellular IoT protocols, NB-IOT, 5G, NFC, LoRaWAN, LTE, Infrared Data Association (IrDA) protocols, and IR remote control protocols from consumer electronic products.

6. 2. The multifunctional assistance system according to claim 1, wherein the control and communication unit comprises a microphone, a loudspeaker and a display, preferably a touch display.

7. The sensors may be of the following types: motion sensors, presence sensors, fall sensors, temperature sensors, door open sensors, window open sensors, current sensors for specific electrical devices, weight sensors, infrared sensors, ultrasonic sensors, LIDAR sensors, blood pressure sensors, blood glucose sensors, medicine cabinet sensors, refrigerator sensors, toothbrush sensors, smoke detectors, CO ２ The multifunctional assistance system of claim 1 , comprising a sensor from at least two of the sensors.

8. 2. The multifunctional assistance system of claim 1, wherein the evaluation unit has non-sensor-based data from the database when determining an anomaly, and is configured to output any change in the non-sensor-based data as the anomaly condition when an anomaly is detected.

9. The multifunctional assistance system according to claim 1 , wherein the evaluation unit is configured to use a self-learning algorithm for the evaluation.

10. The multifunctional assistance system of claim 1 , wherein the control and communication unit is configured to couple with a smart home control device.

11. 11. The multifunctional assistance system of claim 10, further comprising at least one mobile communication device that may be connected to the evaluation unit and / or the control and communication unit and through which information about the person and / or the living area released to a user of the mobile communication device may be displayed.

12. The multifunctional assistance system of claim 11 , wherein the mobile communication device is part of at least one of the at least two alert sequences.

13. The multifunctional assistance system of claim 11 , wherein the mobile communication device is configured to control the smart home control device after corresponding authorization by the person using the multifunctional assistance system.

14. The multifunctional assistance system of claim 1 , wherein the control and communication unit is configured to communicate with the person according to predefined or variable criteria.

15. The multi-functional assistance system of claim 1 , wherein the multi-functional assistance system is configured to allow the person to communicate with the multi-functional assistance system in natural language.

16. 15. The multifunctional assistant system of claim 14, wherein the communication with the person relates to at least one topic from the following list of topics: queries about detected abnormalities, reminders for specific appointments and actions, rehabilitation strategies, preventative strategies, positive psychology interventions, and errand requests.

17. The multifunctional assistance system according to claim 14 , wherein the variable criteria are learned criteria from previous actions and / or states of the person.

18. 2. The multifunctional assistance system according to claim 1, wherein the control and communication unit has its own communication module and energy storage unit in order to be able to communicate with the evaluation unit in the event of a disconnection from the local electrical network or a failure of the electrical network.

19. 2. The multifunctional assistance system according to claim 1, wherein the evaluation unit is configured to constantly or intermittently check the functionality of the control and communication unit and to trigger an alert if a malfunction is detected according to a predetermined alert sequence.

20. 2. The multifunctional assistance system of claim 1, wherein the control and communication unit is configured to constantly or intermittently check the functionality of the sensors and, if a malfunction is detected, trigger an alert according to a predetermined alert sequence.

21. 2. The multifunctional assistance system of claim 1, wherein the evaluation unit is configured to draw conclusions from current and historical sensor data about at least some of the following conditions and capabilities of the person using the multifunctional assistance system: health state, emotional state, cognitive ability, ability to live independently.

22. 10. The multifunctional assistance system of claim 1, wherein the control and communication unit is configured for use as a telephone and / or a video telephone.

23. The multi-functional assistance system of claim 1 , wherein the at least one alert sequence is a continuously updated alert sequence.

24. A control and communication unit for a multifunctional assistance system according to any one of claims 1 to 23.

Images