Patent Application
20060285651
The present invention relates to the remote monitoring of a patient that incorporates the ability of that patient to call for help during emergency situations without carrying a specific device on their person. More specifically, the present invention relates to monitoring systems with acoustical devices and speech recognition that are capable of recognizing a patient's request for assistance and can automatically initiate a summons for help.
Systems are known that monitor a resident within a home as part of a home monitoring system. One such system has been disclosed in U.S. Pat. No. 6,402,691 B1 entitled “In-Home Patient Monitoring System issued Jun. 11, 2002. These systems save costs by physiological testing of the person and transmitting that information to a remote monitoring location. In addition, these systems can include an automated call function. Questions can be asked relative to the resident's condition and medications. Another such system has been disclosed in U.S. patent application Ser. No. 10/956,681, filed Oct. 1, 2004. The '681 application has been assigned to the assignee hereof and is incorporated herein by reference.
Known systems rely upon the resident having the mobility to use the system. This includes answering any telephone query that is automatically generated on a periodic basis. In some cases, these queries can be less than daily depending on the condition of the resident and his/her medications.
In a home monitoring system, a resident is monitored for physiological and other conditions indicative of health and well-being. The physiological monitoring can include the person's vital signs such as weight, blood pressure, pulse rate and oxygen saturation. The system may also incorporate medication control to support the health and well-being of the resident.
In the event that the physiological monitoring determines that an emergency situation is prevalent or the physiological measurement is not completed as scheduled or the medication is not taken as prescribed, a call can be initiated to a remote monitoring facility to provide an alert. The remote monitoring facility can respond by calling the resident or patient or by visiting the person. However, the follow-up call may find that no one answers the phone and therefore a visit is scheduled for a later time.
The resident may not be answering the phone because he/she went outside, could not hear the phone ring, or was not able to respond. Other reasons for not being able to respond include, the person fell down and cannot get up, or, had an earlier emergency and is now incapacitated or unavailable at the scheduled time. Because the cause is not certain, a routine follow-up call may be made. It therefore becomes extremely important to initiate a call at the first sign of an abnormal situation. Otherwise, a person that falls could be down for a very long time and need assistance. The person might also miss vital medications or monitoring.
There are also systems wherein the resident carries a device that can be activated send a signal for help if he/she falls or become demobilized. However, these systems rely upon the person having the transmitting device on their person at the time of the emergency. It is possible if not likely that the resident will remove the device and forget to put it back on under certain circumstances such as bathing, sleeping, or changing clothing. This raises the potential that the resident may not be able to summon help when demobilized by falling or by other reasons.
Therefore, there exists a need for improved systems for summoning help in situations where time can be important to survival or relief of discomfort.
While embodiments of this invention can take many different forms, specific embodiments thereof are shown in the drawings and will be described herein in detail with the understanding that the present disclosure is to be considered as an exemplification of the principles of the invention, as well as the best mode of practicing same, and is not intended to limit the invention to the specific embodiment illustrated.
In systems that embody the invention, acoustic transducers can be located in primary regions of a home. These acoustic transducers can be connected to a computer or similar device that incorporates software and that can perform a speech recognition function.
The speech of a resident may be used for as a basis for programming a speech recognition function such that the resident's speech can be recognized while other ambient noise or sounds are present. Some ambient sounds can come from a radio or TV that is running. The resident can enter specific sounds, words or word phrases that will be recognized by the home monitoring system. Some of these words could include “help, or help me, or other words descriptive of the situation such as “it hurts, etc.”
Instead of words, characteristics of the resident's speech could be programmed and recognized so that any high stress speech pattern will initiate a response. In addition, it is within the scope of this invention that the monitoring system could have control of the radio or TV and interrupt power or audio output from these devices if it recognizes the resident's speech. Different recognition techniques and methods can be used to identify a situation where the resident needs assistance.
In a residence, there may be a television or other source of sounds and voices that are not related to the patient's need for help. Speech recognition and system activation software may have problems determining if a stressful speech or sound is the patient's speech or a television or other audio system.
In order to distinguish the resident's speech from simultaneous, loud television or audio output, a sound transducer can be located at the output of these devices. The signals from these sound transducers can then be transmitted to the monitoring system wherein the software uses them to compensate the other sensors in the residence.
The transducers throughout the residence can each be compensated in software or hardware to minimize and cancel signals that relate to the television or other audio system. With this compensation, the transducers throughout the residence can have a high sensitivity to those sounds of interest. These would include the voice of the patient.
When the home monitoring system recognizes a situation that needs attention from the speech recognition, it automatically initiates a call to one or more preprogrammed remote locations to summon help. The message for help may include a speech recording of the resident describing the situation or the stored words that the system recognized for activating the automatic call for help.
The remote location can include a neighbor, a relative, a friend, or a central monitoring station having medical emergency response capabilities. The neighbor can be a very important person because of his/her close proximity to the resident and ability to respond in a very short time. The system may be configured such that it first calls certain locations and then calls others after some verification of the situation has been accomplished.
In an aspect of the invention, the system may relay messages from the remote location back to the resident or establish a two-way direct communication with the remote location. In this embodiment, speakers could be located strategically within the home. The resident can now have a dialog describing the situation through the transducers and speakers in the home.
In another aspect of the invention, the system could incorporate a verbal prompt to the resident to describe his/her situation in sufficient detail that it can determine the appropriate response and which locations to call first.
Control circuitry 12 is linked via a wired or wireless medium (or both) 14 to a plurality of audio input transducers, for example microphones, 18 and a plurality of audio output transducers, for example loud speakers, 20. In one embodiment the respective input, output transducers 18i, 20i could be packaged together in a single housing.
The input, output transducers such as 18i, 20i can be located in various locations or rooms of a residence where the resident would be present at least from time to time. These could include, without limitation, living rooms, kitchens, bathrooms, bedrooms, halls and the like.
The circuitry 12 could also be linked, via a wired, or wireless medium 16 to one or more remote monitoring stations. Software 12b can receive and initiate communications via medium 16.
Relative to the system 10, the acoustic input transducers, such as transducer 18i can be located in heavily used regions of a home or residence. The processor 12a and associated software 12b can carry out a speech recognition function based on previously received speech of the resident of a region or home where the system 10 has been installed.
Characteristics of the resident's speech can be incorporated or stored in the voice recognition software, the control circuitry 12. Advantageously, receive high stress speech patterns from the resident can be recognized and can initiate communications via medium 16 to a remote monitoring location, which could include a neighbor's or relative's house as well as a monitoring facility.
The control circuitry 12 can communicate directly with the resident via medium 14 and the audio output transducers 20. In addition, the software 12b can couple audio from the resident, via medium 14 to one or more remote locations via medium 16.
The audio input transducers 18 can be compensated to be able to distinguish a resident's speech from simultaneously present background audio such as from televisions, radios and the like all without limitation.
The ability to distinguish the voice of a resident from other sources of sounds within a residence is an important advantage of the system 10. A sound source such as a TV or RADIO can intermittently or continuously emit audio, such as A-T, A-R throughout the residence, see
The graphs of
As sound travels through the residence, it takes time due to its propagation rate. A corresponding signal will be produced at the other locations of acoustical sensors 18. Those signals will each have a different phase and amplitude.
In a first step, the phase of the signal 32 in
By using the zero crossings, the processor 12a does not yet have to consider the amplitude. Once the phase shift has been measured, it is stored for use in compensating the signal 30 shown in
One approach is then to invert the signal, see signal 32″,
Adjusting the amplitude of the signal 32″ in
The phase and amplitude information can be stored in memory, for example, EEPROM and used to dynamically adjust all acoustical input sensors 18 whenever the sound source, such as the TV or RADIO, is turned ON.
Once the acoustical sensor signals such as the signal 32, from the location associated with
This process will need to be repeated for each sound source such as TV, or RADIO in the residence that may interfere with the speech recognition of the system 10 due to signals received at each acoustical sensor location. The system processor 12a can automatically make these individual adjustments for each monitored sound source present in the residence such that it can even compensate for more than one source being turned ON at a time.
The above described process is dynamic. A new sound source that is not associated with a resident's voice can be automatically responded to by the system 10 and compensation provided for it. The adjustment of each non-resident sound source can take place within seconds if it has not already been measured and recorded in the memory of the processor 12.
After the acoustic sensor signals are nulled within the system 10, then the sounds from the resident will produce signals at least at one acoustical sensor 18j and possibly multiple acoustical sensors in the residence. The system 10 can also use the amplitude of the signals at multiple acoustical sensors to help locate the resident within the residence. This can be accomplished using amplitude information and phase relationships of the signals from the respective acoustical input sensors 18. It will be understood that the above described steps can be altered without departing from the spirit and scope of the invention.
From the foregoing, it will be observed that numerous variations and modifications may be effected without departing from the spirit and scope of the invention. It is to be understood that no limitation with respect to the specific apparatus illustrated herein is intended or should be inferred. It is, of course, intended to cover by the appended claims all such modifications as fall within the scope of the claims.
