Medical inquiry answering equipment
Through voice recognition technology, audio signals are converted into natural language data streams for medical database query, which solves the problem of obtaining information related to drug use and medical device operation, realizes users to easily obtain accurate information and remote database updates, and improves the system Responsiveness and security.
Patent Information
- Application Number
- CN201880065495.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2017-10-10
- Filing Date
- 2018-10-09
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2039-05-11
AI Technical Summary
The prior art is difficult to effectively provide medical information inquiries, especially for user inquiries related to drug use and medical device operation, and it is difficult to update and maintain medical databases, and user information is not obtained in a timely or inaccurate manner.
Through voice recognition technology, audio signals are converted into natural language data streams, user voice commands are determined, and they are converted into medical database queries, obtain responses, and provide responses through auxiliary query response facilities when necessary to ensure that users obtain accurate information, Also allows remote database updates and user authentication.
It realizes that users can easily obtain information related to drug use and medical device operation through voice commands, ensuring the accuracy and timeliness of information, and at the same time solves the problems of database updates and user identity verification, improving the security and response capabilities of the system.
Smart Images

Figure CN111183488B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to providing medical information in response to a query and, in particular, but not exclusively, to a method of querying a medical database using speech recognition. Background Art
[0002] A patient information leaflet (PIL) or package insert is typically provided with licensed drugs to inform the drug user how to take the drug, the drug's potential side effects and how the drug may interact with other medications or pre-existing medical conditions, and to provide any other information considered useful to the user. Summary of the invention
[0003] According to one aspect of the present invention, there is provided a method for providing medical information, comprising: converting a detected audio signal into a natural language data stream; determining from the natural language data stream whether a user has issued a voice command for information related to a medical device or medication; in response to a positive determination, converting at least a portion of the natural language data stream into a query for querying a medical database; supplying the query to the medical database and receiving a response therefrom; and providing an audio output based at least in part on the response from the medical database. This allows a user to request and be provided with information related to their medication or medical device.
[0004] The method may further comprise transmitting the query to a data server comprising the medical database, the data server being remotely located from the user. This allows querying of a large medical database to determine a response. It also allows the medical database to be kept up to date without requiring the user to download updates.
[0005] The method may also include determining whether there is an appropriate response to the query in the medical database; and in the event of a negative determination, transmitting the query to an auxiliary query answering facility. Transmitting the query to an auxiliary query answering facility may allow responses to queries that do not have responses in the medical database.
[0006] The method may include: receiving a new response from the assisted query answering facility; and providing an audio output based at least in part on the new response from the assisted query answering facility. This allows responses to queries that have no answers in the medical database.
[0007] Optionally, the new response is generated at the auxiliary query answering facility in text format and the audio output is created from the new response using a text-to-speech process.
[0008] The method may further comprise: transmitting the new response to the medical database; and storing the new response in the medical database together with metadata related to the query. This is a direct method of providing a response from an assisted medical response.
[0009] The response may include video data and the method further includes: transmitting the response to a display device; and providing a video output on the display device based at least in part on the video data in the response. Providing video data as part of the response may allow for a more detailed answer to the query, particularly when providing instructions for how to use a medical device or medicament.
[0010] The method may further comprise: determining a user identity; retrieving user data from a user database using the user identity; and modifying the audio output based at least in part on the user data. This allows the query response to be customized for the user supplying the query. In particular, it may allow the user to be informed of interactions with medications the user is taking.
[0011] For increased security, the method may further comprise verifying the user identity before retrieving the user data from the user database.
[0012] The method may also include creating a log of the queries, the log including the user identity, an identifier of the query and an identifier of the provided response, and storing the log in the medical database. This may provide a record of what information has been supplied to a particular user.
[0013] The determining whether the user has issued the voice command may include: identifying one or more potential voice commands in the natural language data stream; calculating a confidence level for each of the identified potential voice commands; selecting a potential voice command based on the calculated confidence level; comparing the confidence level of the selected voice command to a predefined threshold confidence level; and making a positive determination that the selected voice command exists if the confidence level of the selected voice command is above the predefined threshold confidence level. Using confidence levels when determining whether a voice command exists can help prevent incorrectly identifying queries.
[0014] The method may also include providing a request to the user to repeat the voice command, where a positive determination has been made that there is more than one selected voice command. This may prevent incorrect information from being supplied in response to a query.
[0015] The query may be selected from a predetermined list of allowed queries. This may result in a more accurate query determination.
[0016] According to one aspect of the present disclosure, there is provided a device comprising a processor; and a memory, wherein the memory comprises a computer program code, which, when executed by the at least one processor, causes the device to perform the method of any one of the above aspects.
[0017] According to one aspect of the present disclosure, a system for executing any of the above methods is provided, the system comprising: a speaker; a microphone; a processor component; and a medical database.
[0018] These and other aspects will be apparent from and elucidated with reference to the embodiments described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] Embodiments will now be described, by way of example only, with reference to the accompanying drawings, in which:
[0020] Figure 1 is an overview of an interactive medical inquiry system according to a first embodiment;
[0021] Figure 2 is a schematic representation of the electronic system of a medical query answering device according to the system of the first embodiment;
[0022] Figure 3 is a flow chart of a method of providing medical information in response to a query; and
[0023] FIG. 4 is an overview diagram showing further functionality of the interactive medical inquiry system. DETAILED DESCRIPTION
[0024] Embodiments provide a system and method for answering user queries related to medical information, particularly user queries related to medications and / or medical devices.
[0025] about Figure 1 , shows an overview of an interactive medical inquiry system according to a first embodiment. Figure 2 , shows a schematic representation of the electronic system of a device according to a first embodiment. In the embodiment shown in the form of a "smart speaker", a medical query answering device 10 is provided, with which a user can interact using voice commands.
[0026] If the medication user 12 is unable to fully read the PIL, it may leave the medication user 12 lacking information about the medication or unsure how to properly administer the medication. Furthermore, even if the user does fully read the PIL, he or she may have further inquiries about the medication. Verifying that the user has been informed of the contents of the PIL is also useful to the manufacturer.
[0027] In addition, the user 12 may not be able to fully read the instructions of the medical device, which may lead to user errors when using the device. Even if fully read, the user may have further queries about the device, such as queries about troubleshooting.
[0028] The device 10 comprises a microphone 14 for receiving audio signals. The microphone 14 comprises a transducer for converting sound into an electrical audio signal which can then be processed.
[0029] The device also includes a processor component 38 configured to perform speech recognition on an audio signal received by the microphone 14. When the microphone 14 receives the audio signal, the processor component 38 can convert the audio signal into a natural language stream, and then further process the natural language stream to determine whether there is a voice command in the audio signal. The voice command may include a predefined command, such as an activation command for the device or a predefined query, or a question about medication, medication administration, medical device, personal medication history, or expiration date.
[0030] The device further comprises a speaker 14 for transmitting audio signals in the form of sound to the user 12. The orientation of the speaker 14 may support a spatially natural sound rendering.
[0031] A network interface 50 is also provided on the device to connect the device to a network. The network interface 50 may be provided, for example, by one or more of the following: a Wi-Fi interface; an Ethernet interface; a Bluetooth transceiver; and / or a USB interface. The 10 may be connected to a local area network (LAN) and / or the Internet via the network interface device 50, thereby allowing it to exchange data with other components of the network. The device may also use a network interface to directly connect to an additional device, for example, using a Bluetooth connection.
[0032] The device may include a display 18. Optionally, the display 18 has touch screen functionality. The display 18 may provide a visual indication of the device status, such as the mode the device is in, the battery status, and / or whether a power source is connected. The display 18 may also be used to convey messages to the user. The display 18 may be in the form of a liquid crystal display (LCD), a light emitting diode (LED), or an organic light emitting diode (OLED) screen, or the like.
[0033] The device may also include a projector 20 to project information and / or instructions to the user, for example, a new message may be projected onto a wall near the device. Thus, the device may include an adjustable projector 20, which in some embodiments is in the form of an LED projector. In some embodiments, the projector 20 may replace the external display device 22 to display a video clip providing instructions or information.
[0034] In some embodiments, the display 18 may include touch screen functionality, allowing the display 18 to receive user input. The touch screen functionality may be used to support installation and troubleshooting procedures. Alternatively or additionally, the display 18 may be accompanied by one or more buttons or keys near the display, allowing the user to interact with the device, such as by navigating a cursor through a collection of menus and options on the display 18. A remote control for interacting with the device may also be provided.
[0035] The device may include a motion sensor 24. The motion sensor 24 may be provided in the form of an infrared sensor, an ultrasonic sensor, or may be integrated with the microphone 14. The motion sensor 24 may allow the device to react when motion is detected nearby (such as the movement of the user 12 in the room where the device is located), for example by "waking up" from standby mode and beginning to listen for voice commands. In addition, the detection of motion by the motion sensor 24 may be used as a trigger for the device to provide a voice reminder to the user related to medication. Such a reminder may include a reminder that a dose of medication is about to be taken.
[0036] In some embodiments, the device 10 may include an RFID reader 25, or more generally, a near field communication transceiver. The device 10 can then read the RFID tag. The reader 25 may alternatively or additionally include a QR code reader, a bar code reader, or other optical code readers. The reader 25 may allow the medication being used by the user to be registered. This may provide information related to the user's medication inventory, such as the amount of medication or medication batch number provided to the user.
[0037] The device may be provided in a variety of forms, including but not limited to: a smart speaker; a mobile device, such as a smartphone or tablet running an application; a laptop; or a personal computer. In some embodiments, it may be provided as a collection of separate components distributed throughout a location and / or integrated with other user devices in the location.
[0038] Connected to a data server including a medical database via a network interface device 50 1 26. Through this connection, the device can share data with the data server 26 in a two-way manner. The data server 26 can be located remotely from the device 10, such as at a data center controlled by a drug supplier or device manufacturer. Alternatively, the data center 26 can be part of a distributed computer system such as the "cloud". In some embodiments, the data server 26 can be located locally on the device on the same local area network.
[0039] The medical database contains predefined responses to medical queries, such as queries related to medications and / or medical devices. In some embodiments, it may also contain personal medical details related to one or more users of the system, such as a list of medications the user is currently taking and any past or current medical conditions. This may allow responses to user queries to be customized for the specific user to whom the query relates.
[0040] __________________________
[0041] In some embodiments, the network interface can also be used to connect to additional devices on the same local area network as the device. Examples of additional devices include a display device 22 (such as a television or tablet), additional speakers 28 and microphones 30 and / or a projector 32 or a medical device 34.
[0042] In some embodiments, the network interface may include a telephone interface. This may allow the device 10 to dial an emergency number or hotline based on a voice request from the user 12. In some embodiments, data from a medical device 34 connected via the network interface device 50 may serve as a trigger to dial an emergency number or hotline. For example, if a medical device reading such as a blood sugar level is detected to be critical, the device 10 may request a response from the user 12. In the absence of a response, the device 10 may automatically dial a hotline to request help for the user 12.
[0043] The data server 26 is also supported by an auxiliary query answering facility 36, such as a contact center, connected to a network that includes both the data server 26 and the device 10. The auxiliary query answering facility 36 can communicate with both the data server 26 and the device 10. The auxiliary query answering facility 36 can be manually operated by a human agent who can manually add additional query responses to the medical database when no appropriate response to the query is found, and can additionally transmit the new response to the device 10.
[0044] like Figure 2 As best seen, the electronic system includes a processor assembly 38. The processor assembly 38 and other hardware components may be connected via a system bus (not shown). Each hardware component may be connected to the system bus directly or via an interface. A power supply 40 is arranged to provide power to the electronic system. In some embodiments, a battery may also be provided to enable the use of the device without a power connection to a mains power source. The battery may be rechargeable.
[0045] The processor component 38 controls the operation of other hardware components of the electronic system. The processor component 38 can be any type of integrated circuit. The processor component 38 can be, for example, a general-purpose processor. The general-purpose processor can be a single-core device or a multi-core device. The processor component 38 can be a central processing unit (CPU) or a general-purpose processing unit (GPU). Alternatively, the processor component can be a more specialized unit, such as a RISC processor or programmable hardware with embedded firmware. Multiple processors can be included. The processor component 38 can be referred to as a processing device.
[0046] The electronic system includes a working or volatile memory 42. The processor component 38 can access the volatile memory 42 to process data and can control the storage of data in the memory. The volatile memory 42 can be any type of RAM, such as static RAM (SRAM), dynamic RAM (DRAM), or the volatile memory can be a flash memory, such as an SD card. Multiple volatile memories can be included, but are omitted in the figure.
[0047] The electronic system includes a non-volatile memory 44. The non-volatile memory 44 stores a set of operating instructions 46 for controlling the normal operation of the processor assembly 38. The non-volatile memory 44 can be any type of memory, such as read-only memory (ROM), flash memory, or magnetic drive memory. Other non-volatile memories may be included, but are omitted from the figure.
[0048] The processor component 38 operates under the control of the operating instructions 46. The operating instructions 46 may include code related to the hardware components of the electronic system (i.e., drivers), as well as code related to the basic operation of the device. The operating instructions 46 may also cause the activation of one or more software modules stored in the non-volatile memory 44. In general, the processor component 38 executes one or more instructions in the operating instructions 36 that are permanently or semi-permanently stored in the non-volatile memory 44, using the volatile memory 42 to temporarily store data generated during the execution of the operating instructions 46.
[0049] The processor assembly 38, volatile memory 42 and non-volatile memory 44 may be provided as separate integrated circuit chips connected by an off-chip bus, or they may be provided on a single integrated circuit chip. The processor assembly 38, volatile memory 42 and non-volatile memory 44 may be provided as a microcontroller.
[0050] The electronic system includes a clock 48. The clock 48 may be a clock crystal, such as a quartz crystal oscillator. The clock 48 may be a component separate from the processor assembly 38 that is configured to provide a clock signal to the processor assembly. The processor assembly may be configured to provide a real-time clock based on a signal from the clock 48. Alternatively, the clock 48 may be a clock crystal that is provided on a single integrated circuit chip with the processor assembly 38. Other possibilities include a radio-controlled clock or time adjustment via an Internet connection.
[0051] The electronic system includes one or more network interfaces 50. The network interfaces 50 facilitate connection of the device to one or more computer networks and the bidirectional exchange of information between the device and other components of the networks.
[0052] These networks may include the Internet, a local area network, or any other network required for the device to communicate with the data center and / or contact center. The network interface 50 includes a network interface controller, such as an Ethernet adapter, a Wi-Fi adapter, and / or a Bluetooth adapter. The network interface 50 is associated with one or more network addresses to identify the device on the network. The one or more network addresses may be in the form of an IP address, a MAC address, and / or an IPX address.
[0053] The electronic system comprises a microphone 14. The microphone 14 is operable to receive input in the form of sound and convert the sound into an electronic audio signal capable of being processed in the digital domain.
[0054] The processor component 38 is configured to convert any audio signal detected by the microphone 14 into a natural language data stream. The processor component 38 can execute a speech-to-text algorithm to convert the audio signal into a natural language stream. Such algorithms may include hidden Markov models, dynamic time warping, or neural networks. The processor component 38 is also configured to analyze the natural language data stream to determine whether there are voice commands in the natural language data stream. The processing component 38 can achieve this by identifying potential voice commands in the natural language data stream and assigning a confidence level to each potential voice command.
[0055] The processor component 38 is also configured to create an audio output based at least in part on the response received by the device from the medical database 26. This may involve decoding or decompressing the response.
[0056] The electronic system also includes a speaker 16. The speaker is an embodiment of an audio transducer. The speaker 16 can be operated to provide an audio output in the form of speech or more generally any sound. The processor component 38 operates the speaker 16 to provide an audio output based on a response received from the medical database 26 and / or based on conditions present in the operating instructions 46 of the processing component.
[0057] The electronic system may include a display driver 52. The display driver 52 may be provided as a separate integrated circuit chip to the processor assembly 38 connected via an off-chip bus. Alternatively, the display driver 52 may be provided with the processor assembly 38 on a single integrated circuit chip.
[0058] The electronic system may include a display 18 for a user interface. The display 18 may be operated by the processing component 38 via a display driver to provide one or more visual notifications to the user. The display 18 may provide a visual indication of the device status, such as which mode the device is in, the battery status, and / or whether a power source is connected. In some embodiments, the display 18 is in the form of a touch screen display.
[0059] The processor component 38 may check the state of charge of one or more batteries (not shown) included in the packaging assembly. If the state of charge is determined to be low, the display may be operated to show a low battery warning.
[0060] The electronic system may also include a motion sensor 24. The motion sensor 24 may be a dedicated motion sensing device (such as an infrared detector or an ultrasonic detector), or may be integrated with a microphone. The processing component 38 monitors the motion sensor 24 to obtain a signal indicating that the motion has been detected. Such a signal can be used to wake the device from a standby mode and put the device into a listening state. The signal can also serve as a trigger for the processing component to control the speaker 16 to output a reminder to the user 12, such as a reminder that the user is about to take a dose of medication.
[0061] In some embodiments, the processor component 38 in the device may not be powerful enough to perform one or more of the above functions. Instead, the processing component 38 is configured to communicate with an additional computer system with more available computing power via a network interface 50. The processor component 38 can transfer data from the device to the additional computer system, where it can be processed using the additional computing power of the additional computer system. The additional computer system can return the results of the processing to the processor component 38 for further processing. The additional computing system can be, for example, part of a remote computer system, a distributed computer system, or a data center.
[0062] The electronic system may include a wired (non-wireless) data interface 54. The wired data interface 54 provides a means for making a wired connection with an external device. The external device may include, for example, a medical device or a personal computer, such as a laptop computer, a desktop computer, a tablet computer, etc. In some embodiments, the battery in the device 10 can be charged via the data interface 54. The wired data interface 54 can be in the form of a universal serial bus (USB) port, such as a micro USB or USB-C port.
[0063] about Figure 3 , shows a flow chart of a method for providing medical information according to an embodiment. The method is executed by a medical query system, for example Figure 1 In its default state, referred to as the listening state 56, the device 10 monitors audio signals input via one or more microphones 14 present in the system to listen for any potential voice commands. In some embodiments, the default state may alternatively be a standby state in which the device 10 is not actively listening for voice commands and is in a low-power mode, wherein the listening state 56 is activated only after a trigger is detected (such as if a motion sensor 24 detects motion near a microphone in the system).
[0064] The audio signal input into the system via the microphone 14 is converted into a natural language data stream using, for example, a speech-to-text algorithm. The natural language data stream is then analyzed to determine whether the input audio signal includes a voice command 58 from the user 12. Potential voice commands in the audio stream are identified and each is assigned a confidence score. The confidence score can be, for example, based on the degree of match between the potential voice command and the predetermined voice command. The confidence score is used to select one or more of the potential voice commands for further analysis. If the confidence level of one or more selected voice commands is higher than a certain threshold confidence level, the voice command is identified in the audio stream. Typically, the voice command with the highest confidence score higher than the threshold confidence level is determined to be the voice command present in the natural language data stream. However, in the case where multiple voice commands in the audio stream are identified with similar confidence scores higher than the threshold, the system may instruct the user to repeat the voice command via a speaker near the user. The system then returns to the listening state.
[0065] If it is determined that there is no voice command, the system returns to the listening state 56.
[0066] If it is determined that a voice command is present in the natural language stream, the system attempts to convert at least a portion of the natural language stream into a query 60 for the medical database 26. A confidence level for the query generated in this manner may also be determined. For example, a query may be selected from a predefined list of allowed queries, where the confidence level is determined based on how well the natural language stream matches the predefined query. In this manner, the system generates a query from the voice command 62.
[0067] If the confidence level falls below a predetermined threshold confidence level, the system instructs the user 12 via a speaker near the microphone 14 inputting the audio signal to repeat the command 64. The system then returns to the listening state 56.
[0068] If the confidence level is above a predetermined threshold confidence level, the generated query is transmitted 66 to the data server 26. The data server 26 uses the generated query to query a medical database 68 to determine a response to the voice command entered by the user 12. If a response to the query exists in the database, the response is transmitted 70 back to the user's local system portion, such as a query about the patient's condition. Figure 1 and Figure 2 A medical query answering device 10 is described.
[0069] The system uses the determined response to provide an audio output 72, which can be communicated to the user 12 via a speaker 16 in the system. The audio output 72 is determined at least in part based on the response to the query received from the medical database, and optionally also based on additional user information stored in the system. Such additional information may, for example, include information related to the user's identity, the user's medical history, or the user's medication regimen. In some embodiments, the audio output 72 is generated from the response using a text-to-speech algorithm.
[0070] In some embodiments, the response can include video data. If there is video data in the response, the user can be provided with a portion of video data 74 or video data that can be streamed to the display device that is connected to the system and can play back the video. The display device can also provide the audio output associated with the video derived from the response. When the query is relevant to the use of medical equipment, or when the user first uses the medical equipment, it may be particularly useful to provide a video stream to the display device. In the embodiment where a display is provided on the medical query answering device, the video data can be presented on the device display. In the embodiment where the equipment includes an LED projector, the video data can be projected onto a wall or screen near the equipment.
[0071] If no response to the query is found in the medical database 2, the system may transmit the query 76 to an auxiliary query answering facility 36, such as a contact center. For example, the transmission may be performed by automatically creating an email containing the query at the medical database and then sending the email to the contact center. At the contact center, a contact center agent may read the query and manually enter a new response 78 to the query into the system. Typically, this newly generated response will be entered by the agent via a keyboard in text format, although alternatively it may be entered by voice.
[0072] The newly generated response to the query may be transmitted to a medical database where it may be stored along with the query for future reference 80. The response may be stored along with metadata associated with the request, such as the confidence level of the query, the time and / or date of the query, the time and / or date the new response was created, the identity of the call center agent that created the response, and / or the medication or medical device associated with the request. In some embodiments, the metadata may include a geographic location associated with the response, for example to allow the response to be customized according to any regulations in force in the user's location. The metadata may allow the response to be identified when the user provides a similar query in the future.
[0073] The newly generated response may be modified before being stored in the medical database. The modification may include, for example, changing the format of the response, compressing the response for more efficient storage, and / or adding metadata to the response. The modification of the newly generated response may occur at the data server 26. The modification of the newly generated response may alternatively or additionally occur at the contact center, for example as part of a quality control or validation process. After the stored response has been stored in the medical database, it may also be accessed for modification, for example, to correct errors or update the response with new information.
[0074] ___________________________
[0075] The newly generated response is then transmitted 70 to the portion of the system local to the user 12 as if it had always existed in the database and communicated to the user 12 as described above.
[0076] In some embodiments, there is an option for the contact center agent to initiate an audio link with the user 12 via the system. The user 12 and the contact center agent can then communicate verbally to resolve the query. Using this feature can allow particularly complex or ambiguous queries to be answered, and provide the user 12 with the opportunity to provide additional information and / or context related to the query.
[0077] In all cases, a log of queries and responses may be stored in the medical database along with metadata about the queries, such as the identity of the user 12 and / or the time of the query. This may provide evidence that a particular piece of information has been provided to the user 12 from the PIL.
[0078] In some embodiments, audio input may be used to identify the user 12 issuing the voice command. A speaker identification algorithm may be used to determine the identity of the user 12 based on the user's voice characteristics input into the system as part of the audio stream. Alternatively, the user 12 may identify themselves and verify their identity through an interface with the system (such as a touch screen display), for example using a username and password.
[0079] Identifying the user entering the voice command allows the response to the query to be customized for the identified user 12 using previously stored information about that user 12. For example, the medical record of the user 12 can be used to determine whether additional information or warnings need to be included in the response, such as whether the medication the user is querying about interacts with any other medication the user is taking or any conditions the user may have. The medical record may also include a schedule for when the user is scheduled to take medication doses, which can be used to send a reminder to the user to take the medication at the required time.
[0080] For example, if the identified user 12 queries for information about the dosage of a medication, the system may check the medication regimen of the identified user stored in a database or other memory to find out what the user's dosage of the medication should be. The dosage is then used to determine a response to the user's query, which includes the required dosage of the medication queried by the user. If the system finds that the medication queried by the user is not part of the user's medication regimen, the response to the user's query may include a warning that the user does not need to take the medication.
[0081] Additionally, the system may check the user's medical records or medication regimen and discover that the medication the user is querying has an adverse reaction or conflict with one or more other medications in the user's medication regimen and / or a medical condition the user has. In this case, the response to the query may include a warning to the user not to take the medication they are querying. In some embodiments, it may also include instructions in the response about what to do if the user is already taking the conflicting medication, such as instructions to contact the user's doctor immediately.
[0082] In some embodiments, the system may also use the user identity to send reminders to the user 12. If the user 12 is identified, the response to the user query may include, for example, a reminder to take medication. The system may query the user's medication schedule and compare the scheduled time for the user to take the medication with the current time. If the current time is within a predefined window of the scheduled time for the user 12 to take the medication, the response to the user query may additionally include a reminder to the user 12 that they should be preparing to take or should have taken the scheduled medication. The reminder may alternatively or additionally be given when the user 12 is identified without the user 12 having to provide a query to the system.
[0083] In some embodiments, the system may provide messages or updates related to the medication or medical device to the user 12 in response to the user 12 requesting whether there are any messages. For example, if the user 12 requests "new messages", the system may provide messages about the medication or medical device via a speaker or display device. The messages or updates may be provided by the medication manufacturer, regulator, medication agent, and / or a defined newsletter forum.
[0084] In some embodiments, the system may read to user 12 email messages that have been provided by a medical practitioner (such as a physician or manufacturer) regarding administration or dosage of a medication.
[0085] In some embodiments, the user medical record can be accessed by an authorized third party such as a medical practitioner / doctor. The third party can update the user medical record. The updated user record can then be used to respond to inquiries from the user 12. For example, a doctor can define the correct dosage of a medication in the user's record, and then use the record to answer the user's inquiries regarding the user's dosage regimen. In some embodiments, the updated user information can be communicated to the user after the user's presence is identified.
[0086] Providing system access to a user's medical records may require further verification of the user's identity due to the sensitivity and privacy of the records. The user's identity may be verified by requiring the user to enter a password when a query requiring access to the user's medical records is made. The user may speak the password to the system via a microphone. Alternatively or additionally, it may be manually entered into the device by the user using a touch screen display, a set of keys, or a remote control.
[0087] In some embodiments, the reader 25 can be used to register the user's medication. When it is detected that the user 12 is using the medication for the first time, the device can read the PIL and / or instructions for use to the user. The instructions can be read in the native language of the user 12 determined by the user record. This can provide an indicator that the user 12 has been informed of the verification of the PIL.
[0088] Although claims have been made for specific feature combinations in this application, it should be understood that the scope of the present disclosure also includes any novel feature or any novel feature combination disclosed herein, whether or not it relates to the same subject matter as currently claimed in any claim, and whether or not it alleviates any or all of the same technical problems as the present disclosure. The applicant hereby gives notice that new claims may be made for such features and / or feature combinations during the examination of this application or any further application derived therefrom.
[0089] While several embodiments have been shown and described, it will be appreciated by those skilled in the art that changes may be made to these embodiments without departing from the principles of the present disclosure, the scope of which is defined by the claims.
[0090] Those skilled in the art will appreciate that modifications (additions and / or removals) may be made to the various components / components of the APIs, formulations, apparatuses, methods, systems and embodiments described herein without departing from the full scope and spirit of the present disclosure, and that the present disclosure encompasses such modifications and any and all equivalents thereof.
Claims
1. A method for providing medical information, comprising: Converting the detected audio signal into a natural language data stream; determining, based on the natural language data stream, whether a user has issued a voice command for information related to a medical device or medication; In response to an affirmative determination, converting at least a portion of the natural language data stream into a query for querying a medical database; supplying the query to the medical database and receiving a response therefrom; generating an audio output based at least in part on the response from the medical database; determining a user identity of the user; retrieving user data from a user database using the user identity; modifying the audio output based at least in part on the user data; providing said audio output; creating a log of the queries, the log comprising the user identity, an identifier of the queries, and an identifier of the responses provided; as well as The log is stored in the medical database.
2. The method of claim 1, further comprising transmitting the query to a data server comprising the medical database, the data server being located remotely from the user.
3. The method according to claim 1, further comprising: determining whether an appropriate response to the query exists in the medical database; as well as In the event of a negative determination, the query is transmitted to an auxiliary query answering facility.
4. The method according to claim 3, further comprising: receiving a new response from said auxiliary query answering facility; as well as An audio output is provided based at least in part on the new response from the auxiliary query answering facility.
5. The method of claim 4, wherein the new response is generated at the auxiliary query answering facility in a text format and the audio output is created from the new response using a text-to-speech process.
6. The method according to claim 4 or 5, further comprising: transmitting the new response to the medical database; as well as The new response is stored in the medical database along with metadata related to the query.
7. The method of any one of claims 1-5, wherein the response comprises video data, and the method further comprises: transmitting the response to a display device; as well as A video output is provided on the display device based at least in part on the video data in the response.
8. The method according to any one of claims 1-5, further comprising verifying the user identity before retrieving the user data from the user database.
9. The method according to any one of claims 1 to 5, wherein the determining whether the user has issued the voice command comprises: identifying one or more potential voice commands in the natural language data stream; calculating a confidence level for each of the identified potential voice commands; selecting a potential voice command based on the calculated confidence level; comparing the confidence level of the selected voice command to a predefined threshold confidence level; as well as In the event that the confidence level of the selected voice command is above the predefined threshold confidence level, a positive determination is made that the selected voice command exists.
10. The method of claim 9, further comprising providing a request to the user to repeat the voice command, wherein an affirmative determination has been made that there is more than one selected voice command.
11. The method according to any one of claims 1-5, wherein the query is selected from a predefined list of allowed queries.
12. A device for providing medical information, comprising: processor; and A memory comprising computer program code which, when executed by the at least one processor, causes the apparatus to perform a method according to any one of claims 1 to 11.
13. A system for providing medical information by executing the method according to any one of claims 1 to 11, the system comprising: speaker; Microphone;Processor assembly; and medical databases.
