Intelligent control method and system

Abstract

An intelligent control method and system. The intelligent control method comprises: acquiring a first speech signal (1502), wherein the first speech signal (1502) is generated by a first speech device (940) by means of performing detection on first user speech; performing speech recognition on the first speech signal (1502), so as to obtain a speech recognition result (1504); on the basis of the speech recognition result (1504), determining whether the first user speech includes a control instruction (1506) for a target device; and in response to it being determined that the first user speech includes the control instruction (1506) for the target device, controlling the target device on the basis of the control instruction (1506).

Description

Intelligent control method and system

[0001] Cross-references

[0002] This application claims priority to Chinese patent application No. 202311028614.6 filed on August 15, 2023, entitled “A method and system for intelligent display of a surgical screen”, priority to Chinese patent application No. 202311028926.7 filed on August 15, 2023, entitled “A method for X-ray imaging”, and priority to Chinese patent application No. 202311863887.2 filed on December 29, 2023, entitled “A voice intercom system”. The entire contents of the above applications are incorporated herein by reference. Technical Field

[0003] This specification relates to the field of intelligent control, and in particular to an intelligent control method and system for use in the medical field. Background Art

[0004] In medical scenarios, such as DSA examinations and X-ray scans in hospitals, doctors and technicians often need to manually operate equipment in the examination room, such as display devices and imaging equipment. However, manual operation is time-consuming and labor-intensive, resulting in inefficient execution of medical procedures and the potential for operational errors to disrupt the normal progress of the medical process.

[0005] Therefore, an intelligent control method and system are provided to assist doctors in accurately and automatically controlling the equipment in the examination room through voice, thereby improving the execution efficiency and accuracy of medical processes.

[0006] Summary of the Invention

[0007] One embodiment of this specification provides an intelligent control method. The method may include obtaining a first voice signal. The first voice signal may be generated by a first voice device by detecting a first user's voice. The method may include performing voice recognition on the first voice signal to obtain a voice recognition result. The method may include determining, based on the voice recognition result, whether the first user's voice contains a control instruction for a target device. The method may also include, in response to determining that the first user's voice contains a control instruction for the target device, controlling the target device based on the control instruction.

[0008] One embodiment of this specification provides an intelligent control system, comprising an acquisition module, a recognition module, a determination module, and a control module. The acquisition module is configured to acquire a first voice signal, where the first voice signal is generated by a first voice device by detecting a first user's voice. The recognition module is configured to perform voice recognition on the first voice signal to obtain a voice recognition result. The determination module is configured to determine, based on the voice recognition result, whether the first user's voice contains a control instruction for a target device. The control module is configured to, in response to determining that the first user's voice contains a control instruction for a target device, control the target device based on the control instruction.

[0009] One embodiment of this specification provides an intelligent control system. The system may include a storage device and a processor. The storage device may store computer instructions; the processor is connected to the storage device. When executing the computer instructions, the processor causes the system to perform the following operations: obtaining a first voice signal, where the first voice signal is generated by a first voice device by detecting a first user's voice; performing voice recognition on the first voice signal to obtain a voice recognition result; based on the voice recognition result, determining whether the first user's voice contains a control instruction for a target device; and in response to determining that the first user's voice contains a control instruction for the target device, controlling the target device based on the control instruction.

[0010] One embodiment of this specification provides a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the intelligent control method. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, the same numbers represent the same structures, wherein:

[0012] FIG1A is a schematic diagram of an application scenario of an exemplary intelligent control system according to some embodiments of this specification;

[0013] FIG1B is a schematic diagram of an exemplary X-ray imaging apparatus according to some embodiments of the present specification;

[0014] FIG1C is an exemplary schematic diagram of an exemplary voice device according to some embodiments of the present specification;

[0015] FIG1D is an exemplary schematic diagram of an exemplary microphone according to some embodiments of the present specification;

[0016] FIG1E is an exemplary schematic diagram of an exemplary speaker according to some embodiments of the present specification;

[0017] FIG2 is a block diagram of an exemplary processing device according to some embodiments of the present specification;

[0018] FIG3 is a flowchart of an exemplary intelligent control process according to some embodiments of this specification;

[0019] FIG4 is a flowchart of an exemplary speech recognition process according to some embodiments of this specification;

[0020] FIG5 is an exemplary flow chart of an intelligent control process of a display device according to some embodiments of this specification;

[0021] FIG6A is an exemplary schematic diagram of a display interface of a display device according to some embodiments of this specification;

[0022] FIG6B is an exemplary schematic diagram of an update display interface according to some embodiments of this specification;

[0023] FIG7 is a flowchart of an exemplary collision detection process according to some embodiments of the present specification;

[0024] FIG8A is an exemplary schematic diagram of controlling the movement of one or more components of an X-ray imaging device according to some embodiments of the present specification;

[0025] 8B is an exemplary schematic diagram of yet another method for controlling the movement of one or more components of an X-ray imaging device according to some embodiments of the present specification;

[0026] FIG9 is a schematic diagram of an exemplary intelligent control system according to some embodiments of the present specification;

[0027] FIG10 is a schematic diagram of an exemplary intelligent control system according to some embodiments of the present specification;

[0028] FIG11 is a schematic diagram of an exemplary intelligent control system according to some embodiments of the present specification;

[0029] FIG12 is a schematic diagram of an exemplary intelligent control system according to some embodiments of the present specification;

[0030] FIG13 is a schematic diagram of an exemplary intelligent control system according to some embodiments of the present specification;

[0031] FIG14 is a schematic diagram of an exemplary intelligent control system according to some embodiments of the present specification;

[0032] FIG15 is a schematic diagram of a voice interaction process between a first voice device and a second voice device according to some embodiments of this specification;

[0033] FIG16 is a flowchart of an exemplary process of controlling a medical device according to some embodiments of this specification. DETAILED DESCRIPTION

[0034] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0035] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0036] As used in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but also include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0037] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that preceding or following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0038] FIG1A is a schematic diagram of an application scenario of an exemplary intelligent control system according to some embodiments of this specification.

[0039] As shown in FIG1A , intelligent control system 100 may include medical device 110, network 120, processing device 130, storage device 140, voice device 150, image acquisition device 160, and display device 170. The components of intelligent control system 100 may be connected in various ways. For example, medical device 110 and processing device 130 may be connected or communicated via network 120. In another example, processing device 130 may be directly connected to medical device 110.

[0040] The medical device 110 may be a device for performing a medical procedure, which may be installed in an examination room (such as an operating room or a scanning room). For example, the medical device 110 may include a medical scanning device for performing a medical scanning procedure (for example, an X-ray imaging device, an ultrasound scanner, a computed tomography (CT) scanner, a magnetic resonance imaging (MRI) scanner, a positron emission tomography (PET) scanner, an X-ray imaging-magnetic resonance imaging (X-ray-MRI) scanner, a positron emission tomography-X-ray imaging (PET-X-ray) scanner, a positron emission tomography-computed tomography (PET-CT) scanner, etc.). For another example, the medical device 110 may include a device for performing a surgery (such as a digital subtraction angiography (DSA) surgery, a radiotherapy surgery, etc.). The above-mentioned medical devices are for illustrative purposes only and are not intended to limit the scope of this specification.

[0041] As an example only, the medical device 110 may be an X-ray imaging device. The X-ray imaging device may be used to scan a target area of ​​a target object using X-rays and generate a medical image (e.g., a scanned image). The target object may include a biological object (e.g., a human body, an animal, etc.), a non-biological object (e.g., a phantom), etc. In some embodiments, the target area of ​​the target object may include a specific part, organ, and / or tissue of the target object. For example, the target area of ​​the target object may include the head, chest, legs, etc., or any combination thereof, without limitation. In some embodiments, the target area of ​​the target object may include a specific part, organ, and / or tissue of the target object and other organs and / or tissues within a certain range around it. The target object may also be referred to as a patient hereinafter.

[0042] In some embodiments, the X-ray imaging device may include one or more components. For example, the X-ray imaging device may be a C-arm X-ray imaging device, which includes a robotic arm, a robotic arm, a C-arm frame, a bed plate, and the like. In some embodiments, during the movement of one or more components of the X-ray imaging device, pressure sensors may be installed on one or more components of the X-ray imaging device to provide timely collision warnings. As an example, FIG1B illustrates an X-ray imaging device in which pressure sensors may be installed at the tail of the robotic arm, the lower edge of the robotic arm, the lower edge of the robotic arm, the tail of the conduit package, the upper edge of the C-arm outer arc, the lower edge of the C-arm outer arc, the bed bottom, the flat panel detector (FD) housing, and the tube housing. In some embodiments, when a collision occurs at a location where a pressure sensor is installed, and the collision pressure exceeds a pressure threshold, the X-ray imaging device transmits a collision warning to the processing device 130 via the network 120. For more information on collision warnings, see FIG7 and its related description.

[0043] The network 120 may include any suitable network that facilitates information and / or data exchange with the intelligent control system 100. In some embodiments, one or more components of the intelligent control system 100 (e.g., the medical device 110, the processing device 130, the storage device 140, or the voice device 150) may transmit information and / or data to one or more other components of the intelligent control system 100 via the network 120. For example, the processing device 130 may obtain a medical image of a target object (e.g., a patient) from the medical device 110 via the network 120. In some embodiments, the network 120 may be any one or more of a wired network or a wireless network. In some embodiments, the network may be a point-to-point, shared, centralized, or other topological structure, or a combination of multiple topological structures.

[0044] The processing device 130 can process data and / or information obtained from the medical device 110, the storage device 140, and / or the voice device 150. In some embodiments, the processing device 130 can be configured to process voice signals to obtain control instructions for controlling a target device. For example, the processing device 130 can obtain a first voice signal. In another example, the processing device 130 can perform voice recognition on the first voice signal to obtain a voice recognition result. In another example, based on the voice recognition result, the processing device 130 can determine whether the first user's voice contains a control instruction for a target device in the examination room. In another example, in response to determining that the first user's voice contains a control instruction for the target device in the examination room, the processing device 130 can control the target device based on the control instruction. In some embodiments, the target device can include a display device 170 and / or the medical device 110. The display device 170 can be configured to determine the display content and display mode of the display device 170 based on a portion of the control instruction. The medical device 110 can be configured to control the operation of the medical device 110 based on at least the remaining portion of the control instruction.

[0045] In some embodiments, the processing device 130 can be a single server or a server group. The server group can be centralized or distributed. In some embodiments, the processing device 130 can be local or remote. The processing device 130 can be directly connected to the medical device 110, the storage device 140, and the voice device 150 to access stored or acquired information and / or data. In some embodiments, the processing device 130 can be implemented on a cloud platform. By way of example only, the cloud platform can include private clouds, public clouds, hybrid clouds, community clouds, distributed clouds, internal clouds, multi-layer clouds, etc., or any combination thereof.

[0046] The storage device 140 can store data and / or instructions. In some embodiments, the storage device 140 can store data obtained from the medical device 110, the terminal 130 and / or the processing device 130. For example, the storage device 140 can store medical images obtained by the medical device 110, etc. In some embodiments, the storage device 140 can store data and / or instructions that the processing device 130 can execute or use to execute the exemplary methods described in this specification. For example, the storage device 140 can store instructions for the processing device 130 to execute the methods shown in the various flowcharts. In some embodiments, the storage device 140 may include a large-capacity storage device, a removable storage device, a volatile read-write memory, a read-only memory (ROM), etc., or any combination thereof. In some embodiments, the storage device 140 can be implemented on a cloud platform.

[0047] In some embodiments, the storage device 140 can be connected to the network 120 to communicate with one or more components of the intelligent control system 100 (e.g., the medical device 110, the processing device 130, the voice device 150, etc.). One or more components of the intelligent control system 100 can access data or instructions stored in the storage device 140 via the network 120. In some embodiments, the storage device 140 can be directly connected to or communicate with one or more components of the intelligent control system 100. In some embodiments, the storage device 140 can be part of the processing device 130.

[0048] In some embodiments, the processing device 130 and / or the storage device 140 may be part of the medical device 110 .

[0049] The voice device 150 can be used to implement voice interaction between the user and the intelligent control system 100. For example, the voice device 150 can be configured to detect the user's voice and convert the detected user's voice into a voice signal. In some embodiments, the voice device 150 may include a voice input component (such as a microphone) and a voice output component (such as a speaker), wherein the microphone is used to receive the user's voice (for example, the first user's voice, the second user's voice), and the speaker is used to play the feedback voice. Exemplary microphones may include dynamic microphones, condenser microphones, electret microphones, silicon micromicrophones, liquid microphones, laser microphones, etc., or any combination thereof. Exemplary speakers may include dynamic (electric) speakers, condenser (electrostatic) speakers, piezoelectric (crystal or ceramic) speakers, electromagnetic (compression spring) speakers, ionic speakers, pneumatic speakers, etc., or any combination thereof.

[0050] In some embodiments, the microphone and speaker can be integrated into the same voice device 150. For example, as shown in FIG1C , the microphone 152 and the speaker 154 can be arranged in an integrated manner on the voice device 150. That is, the microphone 152 and the speaker 154 can be an integrated structure. In some embodiments, the microphone and the speaker can be independent devices. For example, the voice device 150 can include one or more microphone devices as shown in FIG1D and one or more speaker devices as shown in FIG1E .

[0051] In some embodiments, the number and type of microphones and / or speakers can be determined according to actual conditions. For example, in an inspection room, four microphones and one speaker can be arranged separately; in a control room, four microphones and one speaker can be arranged in one piece. For another example, when the ambient noise is greater than a noise threshold (for example, 100 decibels (dB)), and the distance between the user and the microphone is less than a first distance threshold (for example, 10 cm, 20 cm, 30 cm, 50 cm, etc.), a gooseneck microphone can be used. For another example, when the ambient noise is greater than the noise threshold, and the distance between the user and the microphone is greater than a second distance threshold (for example, 1 meter, 2 meters, 3 meters, 5 meters, etc.), multiple microphones (for example, 128 microphones) can be used for sound directional enhancement, thereby enhancing the sound in a specific area and weakening the surrounding noise.

[0052] In some embodiments, multiple microphones (or speakers) can be arranged in a certain array. For example, four microphones can be arranged equidistantly in the manner shown in Figure 1C. For another example, multiple microphones (or speakers) can be arranged in a regular (for example, circular, rectangular, square, triangular, elliptical, etc.) or irregular shape. In some embodiments, the arrangement of the microphones and speakers needs to meet certain conditions. For example, the minimum spacing between the microphone and the speaker needs to be greater than a third distance threshold (for example, 5 cm, 10 cm, 15 cm, etc.). For another example, the central axis of the multiple microphones and the central axis of the speaker need to be placed vertically or approximately vertically. As an example only, as shown in Figure 1C, the projection of the voice device 150 can be approximately rectangular, the central axis of the microphone 152 (as shown by the dotted line A) is parallel to the long side of the rectangle, and the central axis of the speaker 154 (as shown by the dotted line B) is parallel to the short side of the rectangle.

[0053] In some embodiments, the voice device 150 may be a part of the processing device 130. For example, the voice device 150 may be integrated into the processing device 130 as an operating console for the medical device 110.

[0054] In some embodiments, the voice device 150 may include multiple sub-devices. For example, the voice device may include a first voice device and / or a second voice device. The first voice device may be located in an examination room, on one or more of the display device 170 or the medical device 110. The second voice device may be located in a control room. The second voice device may be communicatively connected to the first voice device. For more information about the first and second voice devices, see Figures 9-14 and their descriptions.

[0055] The image acquisition device 160 can be used to acquire real-time optical images of the inspection room (e.g., a first real-time optical image, a second real-time optical image, a third real-time optical image). The image acquisition device 160 may include a camera. In some embodiments, the image acquisition device 160 may include multiple devices, which are installed in different positions to acquire real-time optical images of the same area at different shooting angles and / or different areas. The image acquisition device 160 may include cameras (e.g., digital cameras, analog cameras, depth cameras, structured light cameras, etc.), sensors (e.g., red, green, and blue (RGB) sensors, RGB depth (RGB-D) sensors, etc.), laser imaging devices (e.g., phase laser acquisition devices, point laser acquisition devices, etc.), and other various devices that can acquire optical image data of the target object.

[0056] The display device 170 can be used to display relevant information of each medical link in the medical process. For example, the display device 170 can display real-time optical images. For another example, the display device 170 can display medical images of patients in the medical process, change information or graphs of physiological indicators (such as blood pressure, heart rate, etc.). For another example, the display device 170 can display feedback information (for example, the content of feedback voice) after executing a control instruction. The display device 170 may include a liquid crystal display (LCD), a display based on a light emitting diode (LED), a flat panel display, a curved display, a television device, a cathode ray tube (CRT), etc., or any combination thereof. In some embodiments, the display device 170 and the medical device 110 can be arranged adjacent to each other.

[0057] In some embodiments, the voice device 150, the image acquisition device 160 and / or the display device 170 may be integrated into the same device. In some embodiments, the voice device 150, the image acquisition device 160 and the display device 170 may be different devices.

[0058] In some embodiments, the audio device 150, the image acquisition device 160, and / or the display device 170 can be installed at any position in the examination room. For example, the audio device 150, the image acquisition device 160, and / or the display device 170 can be fixed to a fixed position (e.g., the ceiling) in the examination room by a detachable or non-detachable connection. For another example, the examination room can be equipped with a slide rail, and the audio device 150, the image acquisition device 160, and / or the display device 170 can be installed on the slide rail by a detachable or non-detachable connection, so that the position of the audio device 150, the image acquisition device 160, and / or the display device 170 can be flexibly adjusted according to the user's position.

[0059] In some embodiments, the intelligent control system 100 may further include a system control device (not shown). The system control device refers to a device used to control target devices (e.g., the medical device 110, the voice device 150, the image acquisition device 160, and / or the display device 170). In some embodiments, the system control device may include a system controller unit (SCU) for executing control instructions related to the target devices. For example, the system control device may control the movement of the medical device 110's frame to a specific position and adjust one or more parameters of the medical device 110 (e.g., a radiation switch, etc.) through the system control unit.

[0060] In some embodiments, the system control device may include multiple system control units configured for different medical procedures. For example, the system control device may include a system control unit for X-ray imaging, a system control unit for DSA examinations, and the like. Different system control units may include different sets of control instructions, which may be predetermined according to the medical procedure (e.g., pre-set according to a scanning protocol). The system control unit of the system control device executes one or more control instructions to implement the operation of the target device. In some embodiments, the system control device may be part of the medical device 110. In some embodiments, the system control device and the processing device 130 may be integrated into one device.

[0061] In some embodiments, the various components of the intelligent control system 100 can be located in the same room. For example, as shown in FIG1A , the medical device 110, network 120, processing device 130, storage device 140, audio device 150, image acquisition device 160, and display device 170 can be located in an examination room. In some embodiments, some components of the intelligent control system 100 can be located in different rooms. For more information on the arrangement of some components of the intelligent control system in different rooms, see FIG9-14 and their descriptions.

[0062] It should be noted that the intelligent control system 100 is provided for illustrative purposes only and is not intended to limit the scope of this application. A person skilled in the art can make various modifications or variations based on the description of this specification. For example, the intelligent control system 100 may further include a database, an information source, and the like. For another example, the intelligent control system 100 may be implemented on other devices to achieve similar or different functions. However, such changes and modifications do not deviate from the scope of this specification.

[0063] 2 is a block diagram of an exemplary processing device according to some embodiments of the present specification. The processing device 130 may include an acquisition module 210 , an identification module 220 , a determination module 230 , and a control module 240 .

[0064] Acquisition module 210 can be used to acquire a first voice signal. The first voice signal can be generated by a first voice device by detecting a first user's voice. The first voice device can be installed in the examination room. For more information about acquiring the first voice signal, please refer to step 310 of Figure 3 and the related description.

[0065] The recognition module 220 can be used to perform speech recognition on the first speech signal to obtain a speech recognition result. For more information about obtaining the speech recognition result, please refer to step 320 of Figure 3 and its related description.

[0066] Determination module 230 can be configured to determine, based on the speech recognition results, whether the first user's speech contains control instructions for a target device in the examination room. The target device may include a display device (e.g., display device 170) and / or a medical device (e.g., medical device 110) installed in the examination room. For more information on determining whether the first user's speech contains control instructions for a target device in the examination room, please refer to step 330 of FIG. 3 and the related description thereof.

[0067] The control module 240 can be used to control the target device in the examination room based on the control instruction in response to determining that the first user's voice contains a control instruction for the target device in the examination room. For more information about controlling the target device, please refer to step 340 of Figure 3 and its related description.

[0068] Each module in the processing device 130 may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0069] It should be noted that the above description of the processing device 130 and its modules is for convenience of description only and does not limit this specification to the scope of the embodiments cited. It is understandable that for those skilled in the art, after understanding the principle of the processing device 130, it is possible to arbitrarily combine the various modules, or form sub-devices to connect with other modules without deviating from this principle. For example, the acquisition module 210, identification module 220, determination module 230 and control module 240 disclosed in Figure 2 can be different modules in a system, or a module can realize the functions of the above two modules. For another example, the modules in the processing device 130 can share a storage module, or each module can have its own storage module. Such variations are all within the scope of protection of this specification.

[0070] FIG3 is a flow chart of an exemplary intelligent control process according to some embodiments of this specification. In some embodiments, process 300 can be executed by intelligent control system 100. For example, process 300 can be stored in a storage device (e.g., storage device 140) in the form of an instruction set (e.g., an application). In some embodiments, processing device 130 (e.g., one or more modules shown in FIG2 ) can execute the instruction set and accordingly instruct one or more components of intelligent control system 100 to execute process 300.

[0071] Medical procedures usually require the collaboration of multiple people. For example, doctors in examination rooms (e.g., scanning rooms or operating rooms) need to manually operate the control box and / or touch panel of medical equipment to control the medical equipment while performing an examination or operation. This can easily interrupt the examination or operation and even affect the safety of the patient in an emergency. For another example, doctors need to communicate with technicians to assist in completing the relevant operations of the medical process, which places high demands on the technicians' professional skills, proficiency, and degree of cooperation with doctors. In addition, each operation in the medical process requires multiple rounds of feedback from doctors and technicians, which greatly affects the efficiency and safety of the execution of the medical process.

[0072] Therefore, it is necessary to provide an intelligent control method to assist users in controlling target devices through voice, thereby improving the efficiency and safety of medical procedures. In some embodiments, intelligent control can be achieved by executing the following operations of process 300.

[0073] In step 310 , the processing device 130 (eg, the acquisition module 210 ) may acquire a first speech signal.

[0074] The first voice signal can be generated by a first voice device by detecting the first user's voice. The first voice device can be installed in an examination room. For more description of the voice device, please refer to Figures 1A, 1C-1E and 9-14 and their descriptions.

[0075] The first user voice refers to a voice uttered by at least one user in the examination room (also referred to as the first user). The at least one user can include a physician performing a medical procedure (e.g., a primary surgeon), a nurse, a technician (e.g., a technician assisting the primary surgeon, a technician providing voice commands), or any combination thereof. In some embodiments, the first user voice is uttered before or during the medical procedure.

[0076] A medical process may be a scanning process, a surgical process, a treatment process, etc., which may include multiple medical links. As an example only, a medical process may include a preparation link for a scan plan, a scan execution link, a preparation link for treatment or surgery, an execution link for treatment or surgery, a postoperative treatment link, etc., or any combination thereof. Medical processes are of different types, which may be determined based on different medical scenarios (such as the scanned area of ​​interest, the type of surgery). For example, a DSA surgical scenario corresponds to a DSA medical process. In some embodiments, the medical links included in different types of medical processes may be predetermined.

[0077] The first voice signal may be a digital signal. For example, the first voice device may detect or collect the first user's voice and convert the first user's voice into a first voice signal for subsequent processing. For another example, the first voice device may detect or collect the first user's voice and convert the first user's voice into an initial voice signal, and then process the initial voice signal to generate a voice signal. The processing may include at least noise reduction processing.

[0078] It can be understood that various types of noise may exist in a voice detection environment (for example, an examination room), such as various types of equipment noise (such as mechanical noise, etc.), environmental noise (such as traffic noise, etc.), etc. The initial voice signal refers to the initial digital signal generated after converting the first user's voice. Noise reduction processing refers to the process of removing the noise signal from the initial voice signal. Noise reduction processing can be performed based on various audio noise reduction algorithms such as time domain filtering algorithms and frequency domain filtering algorithms. For example, the first voice device can perform noise reduction processing on the initial voice signal. In some embodiments, the first voice device can also perform noise reduction processing on the first user's voice it receives, and then convert the noise-reduced voice into a first voice signal.

[0079] By performing noise reduction processing on the first user's voice through the first voice device, the computing load of the processing device 130 can be reduced compared to performing noise reduction processing on the processing device 130 .

[0080] In some embodiments, the processing device 130 may obtain the first voice signal from a first voice device (e.g., voice device 150). Alternatively, the processing device 130 may obtain the first voice signal from a storage device (e.g., storage device 140, an external storage device, etc.) storing the first voice signal.

[0081] In step 320 , the processing device 130 (eg, the recognition module 220 ) may perform speech recognition on the first speech signal to obtain a speech recognition result.

[0082] The speech recognition result may be in the form of text, which may indicate the speech content of the first user's speech. In some embodiments, the processing device 130 may process the first speech signal through various speech recognition technologies to obtain a speech recognition result. For example, the processing device 130 may process the first speech signal through a language processing model to obtain a speech recognition result. The language processing model includes one or a combination of acoustic models such as a hidden Markov neural network (HMM), a BERT (Bidirectional Encoder Representations from Transformer) model, a GPT (Generative Pre-Trained Transformer) model, and the like. In some embodiments, the language processing model may be a large language model.

[0083] In some embodiments, language processing models can be trained separately for different medical procedures or different medical scenarios. For example, a language processing model can include a model for a DSA surgery scenario, a model for a lung tumor resection surgery scenario, etc. It can also be a model for a particular surgeon (such as the lead surgeon) or a technician (such as a call technician) in a medical scenario (such as a DSA surgery scenario). It is understood that training different language processing models for different medical procedures and different users can improve the accuracy of speech recognition.

[0084] In some embodiments, the speech recognition result may be in other forms recognizable by the processing device 130 , such as an electrical signal, a code, an encoded instruction, etc. indicating the speech content of the first user's speech.

[0085] In some embodiments, the speech recognition results may include control instructions related to the target device. As an example, the speech recognition result may include "Move the rack to the left position." The speech recognition results may also include other communication content, such as instructions from a doctor to a patient or daily exchanges between medical staff.

[0086] In some embodiments, the speech recognition result may indicate the target user's speech content. The target user is a pre-defined user who is allowed to control the medical procedure. For example, the target user may be a user who is allowed to adjust the parameters of the scanning device, a user who is allowed to control the start or stop of the medical scan, etc. In some embodiments, the target user may be determined based on a medical protocol related to the medical procedure (e.g., a scanning protocol, an examination protocol, etc.).

[0087] In some embodiments, the processing device 130 may determine, based on the first voice signal, first voiceprint information of at least one user corresponding to the first voice signal; determine, based on the first voiceprint information of the at least one user, whether the at least one user includes a target user; in response to determining that the at least one user includes the target user, determine a target voice signal corresponding to the target user; and perform voice recognition on the target voice signal to obtain a voice recognition result. For more information on performing voice recognition on the target voice signal to obtain a voice recognition result, see FIG. 4 and its description.

[0088] In step 330 , the processing device 130 (eg, the determination module 230 ) may determine, based on the speech recognition result, whether the first user's speech contains a control instruction for a target device in the examination room.

[0089] The target device refers to the device that the user (eg, target user) wants to control. For example, the target device may include one or more of the medical device 110, the voice device 150, the image acquisition device 160, and the display device 170 in FIG1A.

[0090] A control instruction refers to an instruction for controlling a target device to perform a specific operation. For example, when the target device includes a display device installed in an examination room, the control instruction may include an instruction for switching a display image on the display device, an instruction for playing or pausing a display image on the display device, an instruction for switching a display mode (such as a road map mode) of the display device, an instruction for setting display parameters (such as image size, resolution, and presentation angle) of a display image on the display device, an instruction for processing a display image on the display device, an instruction for setting a display area division method of the display device, an instruction for causing the display interface to jump to a user configuration interface, or any combination thereof. Exemplarily, the processing of the display image includes saving the display image, sending the display image to a user terminal, performing noise reduction processing on the display image, performing subtraction operation on the display image, etc.

[0091] For another example, when the target device includes a medical device installed in an examination room (for example, an X-ray imaging device), the control instructions may include instructions for motion control of components of the medical device (such as a rack, a bed), instructions for the medical device to perform a medical procedure on a target area of ​​a target object, instructions for switching or setting the working mode of the medical device (such as a DSA mode, a GCT mode), instructions for setting relevant parameters of the medical procedure corresponding to the medical device (such as scanning parameters, radiotherapy parameters, etc.), instructions for the medical device to start or stop a medical procedure, etc., or any combination thereof.

[0092] For another example, when the target device includes an image acquisition device (e.g., image acquisition device 160) installed in an examination room, the control instructions may include instructions for motion control of the image acquisition device, instructions for adjusting shooting parameters of the image acquisition device (e.g., focal length, exposure time, etc.), instructions for causing the image acquisition device to send captured real-time optical images, etc., or any combination thereof.

[0093] For another example, when the target device includes a voice device installed in an examination room (e.g., voice device 150), the control instructions may include instructions for motion control of the voice device, instructions for adjusting the acquisition parameters of the voice device (e.g., the position, orientation, noise reduction, etc. of the microphone), instructions for adjusting the playback parameters of the voice device (e.g., the position, orientation, volume, etc. of the speaker), etc., or any combination thereof.

[0094] In some embodiments, the processing device 130 may pre-process the speech recognition results. For example, the processing device 130 may process the speech recognition results based on information extraction technology to determine the keywords contained in the speech recognition results, and then determine whether the speech recognition results contain control instructions related to the target device. Keywords may include the target device and one or more of its components. For another example, the processing device 130 may compare the speech recognition results with preset keywords corresponding to a target device. If the speech recognition results contain preset keywords, it can be determined that the first user's speech contains control instructions for the target device.

[0095] In some embodiments, the processing device 130 may further perform structured processing on the speech recognition result to determine a structured control instruction, and then determine whether the speech recognition result contains a control instruction based on a preset control instruction set and the structured control instruction corresponding to the speech recognition result. For more information on determining whether the speech recognition result contains a control instruction, see FIG. 16 and its description.

[0096] If it is determined that the first user voice contains a control instruction for the target device in the examination room, processing device 130 may execute step 340. If it is determined that the first user voice does not contain a control instruction for the target device in the examination room, processing device 130 may execute step 350 or end process 300.

[0097] In step 340 , the processing device 130 (eg, the control module 240 ) may control the target device based on the control instruction.

[0098] For example, the control instruction is a control instruction for the display device 170, and the processing device 130 can control the display device 170 based on the control instruction. Accordingly, in response to the control instruction, the display device 170 can perform at least one of the following operations: switching the display image on the display device 170, playing or pausing the display image on the display device 170, switching the display mode of the display device 170, setting display parameters of the display image on the display device 170, processing the display image on the display device 170, setting the display area division method of the display device 170, causing the display interface to jump to the user configuration interface, etc. For more description of controlling the display device 170 based on the control instruction, please refer to Figures 5-6B and their descriptions.

[0099] For another example, the control instruction is a control instruction for the medical device 110. The processing device 130 can control the medical device 110 based on the control instruction. Accordingly, in response to the control instruction, the medical device 110 can perform at least one of the following operations: controlling the movement of a component of the medical device 110, performing a medical procedure on a target area of ​​a target object, setting an operating mode of the medical device 110, setting parameters related to the medical procedure corresponding to the medical device 110, starting or stopping the medical procedure, etc. For more information on controlling the medical device 110 based on the control instruction, please refer to Figures 7-8B and their descriptions.

[0100] In some embodiments, based on the control instruction, the processing device 130 may further control the display device 170 to display the operation performed by the medical device 110. For example, in response to the control instruction, the display device 170 may display the medical procedure performed by the medical device 110.

[0101] In some embodiments, the processing device 130 may determine whether the first user's voice contains a wake-up word based on the voice recognition result. The wake-up word may indicate that the first user's voice is related to the voice control mode. Among them, the wake-up word may be a preset word used to distinguish the content of daily communication, for example, A01, B02, etc. The description of the wake-up word here is only an example and is not intended to limit the form of the wake-up word. If it is determined that the first user's voice contains a wake-up word and contains a control instruction for the target device, the processing device 130 may control the target device in response based on the control instruction. In other words, the user needs to issue the wake-up word and the control instruction at the same time to control the target device. In this way, the security risk of control can be increased.

[0102] In some embodiments, after voice control mode is enabled, or within a preset time period after a user issues a wake-up word, the user can control the target device by simply issuing a control command without issuing the wake-up word. This avoids repeated wake-up operations and improves control efficiency.

[0103] In some embodiments, the processing device 130 may send a control instruction to the system control device to enable the system control device to control the target device (eg, medical device). For more information on enabling the system control device to control the medical device, see FIG. 16 and its description.

[0104] In step 350 , the processing device 130 (eg, the control module 240 ) may control the first voice device to play the feedback voice.

[0105] Feedback audio refers to audio that contains information about the execution status of a control instruction. For example, the feedback audio may include feedback about whether the control instruction has been executed (e.g., the first audio device plays "Control instruction has been executed" or "Control instruction execution failed"), feedback audio containing prompt information for the next step (e.g., the first audio device plays "Control instruction has been executed, do you want to proceed with imaging?" or "Control instruction execution failed, confirm whether the target device is abnormal"), etc., or any combination thereof.

[0106] In some embodiments, the processing device 130 can determine the security level of the control instruction based on the voice recognition results, and then determine the content of the feedback voice based on the security level. Furthermore, the processing device 130 can control the first voice device to play the feedback voice based on the content of the feedback voice. For example, the types of security levels and the control instructions and feedback voice content corresponding to each security level can be predetermined, and this correspondence can be stored in the form of a comparison table. The processing device 130 can determine the security level of the control instruction and the feedback voice content in the voice recognition results based on the comparison table.

[0107] As an example, the corresponding security level and voice feedback content can be determined based on the security risk of the device operation corresponding to each control instruction and the device's feedback. For example, the security levels can be divided into four categories: A, B, C, and D. Category A corresponds to control instructions with high security risks and no protective measures, such as radiation unlocking and motion unlocking. The voice feedback content corresponding to Category A control instructions can be a request for user voice confirmation (such as "Please confirm whether to launch the ray"). Category B corresponds to control instructions with high security risks but with protective measures, such as the modification of relevant parameters such as motion, radiation, and protocols. The voice feedback content corresponding to Category B control instructions can be a repetitive control instruction (such as "Adjust the C-arm to the normal position") to ensure that the user is aware of the upcoming operation. Category C corresponds to control instructions with low security risks but less obvious feedback, such as a prompt indicating the modification of relevant device parameters or the completion of line payout. The voice feedback content corresponding to Category C control instructions can be a prompt tone for successful execution or a prompt tone for failed execution. Category D corresponds to control instructions with low security risks and obvious feedback, such as canceling an alarm. The voice feedback content corresponding to Category D control instructions can be no additional prompt.

[0108] In some embodiments, the processing device 130 may also control the display device to display the content of the feedback voice. For example, the processing device 130 may send the feedback voice content to the display device to control the display device to display the content of the feedback voice in the form of text, image, color, etc.

[0109] In some embodiments, the feedback speech may also include a response to a question in the first user's speech. For example, processing device 130 may determine whether the first user's speech contains a question based on the speech recognition results. If the first user's speech contains a question, processing device 130 may determine the response information corresponding to the question and control the first voice device to play the response information. In some embodiments, processing device 130 may also control a display device to display the response information.

[0110] In some embodiments, the feedback voice may also include a prompt indicating an abnormal situation. For example, the processing device 130 may obtain abnormal characteristic information of the target object and control the first voice device to play the abnormal characteristic information. In some embodiments, the processing device 130 may also control a display device to display the abnormal characteristic information.

[0111] In some embodiments of this specification, intelligent voice control of a target device can be achieved by determining whether a first user's voice contains control instructions for the target device. This allows doctors to directly interact with the target device through voice without having to manually control the device, thereby reducing the number of medical personnel required for medical procedures, improving the efficiency and accuracy of medical procedures, and ensuring a smoother execution of the medical process.

[0112] It should be noted that the above description of process 300 is provided for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art may make various changes and modifications under the guidance of this specification. However, such changes and modifications do not depart from the scope of this specification. In some embodiments, process 300 may be completed by one or more additional operations not described and / or by omitting one or more operations discussed above.

[0113] For example, before step 310, process 300 may further include step 302, in which processing device 130 may enable voice control mode. Specifically, processing device 130 may obtain a second voice signal and determine whether the second user's voice contains a wake-up word. If it is determined that the second user's voice contains a wake-up word, processing device 130 may enable voice control mode. The second voice signal may be generated by the first voice device by detecting the second user's voice.

[0114] FIG4 is a flow chart of an exemplary speech recognition process according to some embodiments of the present specification. In some embodiments, operation 320 in FIG3 can be implemented by executing process 400.

[0115] In step 410 , the processing device 130 (eg, the recognition module 220 ) may determine, based on the first voice signal, first voiceprint information of at least one user corresponding to the first voice signal.

[0116] The first voiceprint information refers to the voice feature information of at least one user who makes the first user voice, which can be used to determine the identity of the at least one user, for example, a specific doctor, technician, nurse, etc.

[0117] In some embodiments, the processing device 130 may perform voiceprint feature extraction processing on the first voice signal based on voiceprint recognition technology, etc., to obtain first voiceprint information of at least one user corresponding to the first voice signal.

[0118] In step 420 , the processing device 130 (eg, the recognition module 220 ) may determine whether the at least one user includes a target user based on the first voiceprint information of the at least one user.

[0119] In some embodiments, the processing device 130 can obtain the target voiceprint information corresponding to the target user. The target voiceprint information refers to the voiceprint information of the target user (such as a voiceprint feature vector). For example, the processing device 130 can obtain the target voiceprint information corresponding to the target user from a voiceprint feature library. The voiceprint feature library can store the voiceprint information of multiple users (such as doctors, nurses, technicians, etc. in a hospital). Exemplarily, the voices of different doctors, medical staff, etc. can be collected in advance, and the voiceprint information corresponding to each user can be generated based on the voiceprint extraction technology, thereby generating a voiceprint feature library based on the identity information of each user (such as name, work number, etc.) and its corresponding voiceprint information. The voiceprint feature library can be stored on the storage device 140, or on an independent storage device.

[0120] In some embodiments, the processing device 130 can determine whether the at least one user includes a target user by comparing the first voiceprint information of the at least one user with the target voiceprint information. For example, the processing device 130 can perform voiceprint matching processing on the first voiceprint information of each user in the at least one user with the target voiceprint information to determine whether the user is the target user. Exemplarily, the processing device 130 can separately determine the similarity between the first voiceprint information of each user and the target voiceprint information, and whether the voiceprint similarity exceeds a preset similarity threshold. If the similarity between the first voiceprint information of a user and the target voiceprint information of a target user exceeds the preset similarity threshold, the user is determined to be the target user.

[0121] In some embodiments, for each user in at least one user, the processing device 130 can determine the identity information of the user based on the first voiceprint information, and determine the speech weight of the user based on the identity information of the user. Furthermore, the processing device 130 can determine whether the user is a target user based on the speech weight of the user. For example, the processing device 130 can pre-determine the speech weight of each user based on the user's work information (e.g., position, years of work, number of surgeries performed, etc.), and store it in a storage device (e.g., storage device 140, independent storage device). After determining the identity information of each user in at least one user based on the first voiceprint information, the speech weight of each user can be determined, as well as whether the speech weight is greater than a preset authority threshold. If the user's speech weight is greater than the preset authority threshold, the user is determined to be a target user.

[0122] If it is determined that the at least one user includes the target user, processing device 130 may execute step 430. If it is determined that the at least one user does not include the target user, processing device 130 may terminate process 400. In some embodiments, if it is determined that the at least one user does not include the target user, processing device 130 may determine that the first user's voice does not include any control instructions for the target device in the examination room.

[0123] In step 430 , the processing device 130 (eg, the recognition module 220 ) may determine a target speech signal corresponding to the target user.

[0124] In some embodiments, processing device 130 may determine the voice signal corresponding to the target user as the target voice signal. For example, if the at least one user group includes only the target user, processing device 130 may determine the first voice signal as the target voice signal. For another example, if the at least one user group includes the target user and other users, processing device 130 may use a voice signal extraction algorithm to extract the voice signal corresponding to the target user from the first voice signal and determine the voice signal corresponding to the target user as the target voice signal.

[0125] In step 440 , the processing device 130 (eg, the recognition module 220 ) may perform speech recognition on the target speech signal to obtain a speech recognition result.

[0126] In some embodiments, the processing device 130 may process the target speech signal using various speech recognition technologies to obtain a speech recognition result. For more description of speech recognition technologies, please refer to step 320.

[0127] In some embodiments of this specification, the speaker's identity is identified through voiceprint analysis, and only the target user's voice signal is extracted for voice recognition. This prevents the impact of non-target users' voices on medical process control, improves the accuracy and safety of medical equipment operation control, and ensures smoother medical procedures.

[0128] FIG5 is an exemplary flow chart of an intelligent control process of a display device according to some embodiments of the present disclosure. In some embodiments, process 500 is a specific embodiment of process 300.

[0129] In the medical process, it is often necessary to use a display device to display the display content corresponding to each medical link (such as before execution, during execution, etc.) to assist doctors in performing medical activities (such as medical scanning, surgery). However, the display configuration, display content, etc. of the display interface are often more complicated, and adjustments are often more frequent. In addition, the usage habits and configuration preferences of different users (such as doctors) are very different, and manual adjustments are often time-consuming and laborious. In particular, for relevant medical staff who are not familiar with the functions or functional interfaces of the display interface, it is necessary to spend a lot of time to train on the use of the system. In the tense medical activity process, adjustments are often prone to errors, which may seriously affect the normal progress of medical activities. Therefore, it is necessary to provide an effective system and method for intelligently controlling display devices. In some embodiments, the display device can be intelligently controlled by executing the following operations of process 500.

[0130] In step 510 , the processing device 130 (eg, the acquisition module 210 ) may acquire a second speech signal.

[0131] The second voice signal is generated by the first voice device by detecting the second user's voice. The second voice signal can be obtained in a similar manner to the first voice signal, and will not be described in detail here.

[0132] The second user voice refers to a voice uttered by at least one second user participating in the medical procedure. For example, the second user voice may be a voice uttered by a person such as a doctor, nurse, or technician participating in the medical procedure.

[0133] In some embodiments, the second user voice signal is emitted before the medical procedure is performed. The second voice signal can be used to initially configure the display interface of a display device (e.g., display device 170) before the medical procedure is performed. The initial configuration may include determining initialization parameters for the display interface and generating an initial display interface. For details about the initial display interface, see FIG. 6A and its description.

[0134] In step 520 , the processing device 130 (eg, the determination module 230 ) may determine, based on the second voice signal, second voiceprint information of at least one second user corresponding to the second voice signal.

[0135] The second voiceprint information refers to voice feature information of at least one second user, which can be used to determine the identity of the at least one second user. In some embodiments, the processing device 130 can perform voiceprint feature extraction processing on the second voice signal based on voiceprint recognition technology to obtain the second voiceprint information corresponding to the second voice signal.

[0136] In step 530 , the processing device 130 (eg, the control module 240 ) may determine initial display parameters of the display device based on the second voiceprint information.

[0137] The initial display parameters refer to parameters used to determine the initial display interface of the display device.

[0138] In some embodiments, the processing device 130 may present different initial display interfaces based on different user display preferences. The initial display interface may include an initial segmentation scheme for the screen, which includes parameter configurations such as the number, size, and arrangement of the initial display areas in the screen. Among them, the user display preferences may include display parameters that the user is interested in. It can be understood that users have different preferences for parameters such as the background, color, display area division, and arrangement of the display interface. For example, users of different ages, genders, and vision have different preferences for the size (such as length, width), position (such as left, middle, top, etc.) of the display area of ​​interest, the font of the displayed content, and its size.

[0139] In some embodiments, the processing device 130 can record and store historical display interface configurations of different users (such as the display configurations of medical links before the execution of various types of medical procedures), and determine the display preferences of each user based on the historical display interface configurations (such as the most frequently used configuration records).

[0140] In some embodiments, the processing device 130 can determine the identity of at least one second user based on the second voiceprint information, and determine the display preferences of at least one second user based on the identity, thereby determining initial display parameters related to the display interface to complete the initialization of the display interface. In some embodiments, the processing device 130 can determine the identity of at least one second user based on the second voiceprint information, and determine the medical procedure to be performed based on the identity of at least one second user. Further, the processing device 130 can determine initial display parameters related to the display interface based on the medical procedure to be performed to complete the initialization of the display interface.

[0141] In some embodiments, the processing device 130 can determine whether the at least one second user includes a target user based on the second voiceprint information. The target user refers to a user who has operational authority over the display device among the at least one second user participating in the medical procedure. In some embodiments, different operating permissions can be configured for different target users; for the same operating permissions, different speech weights can be configured for different target users, and instructions from target users with greater speech weights are prioritized. In some embodiments, the method for determining whether the at least one second user includes the target user can be similar to the method for determining whether the at least one first user includes the target user described in step 420.

[0142] If it is determined that the at least one second user includes the target user, the processing device 130 may determine the initial display parameters of the display device based on the identity information of the target user. If it is determined that the at least one second user does not include the target user, the processing device 130 may end process 500.

[0143] In step 540 , the processing device 130 (eg, the acquisition module 210 ) may acquire a first speech signal.

[0144] The first voice signal may be generated by the first voice device by detecting the first user's voice. In some embodiments, the first voice signal is detected during a medical procedure (e.g., a scan or surgery). For more information about obtaining the first voice signal, see FIG. 3 and its description.

[0145] In step 550 , the processing device 130 (eg, the determination module 230 ) may determine whether the first user voice includes a control instruction for the display device.

[0146] The processing device 130 may execute step 320 to determine the speech recognition result; and determine whether the first user's speech contains a control instruction for the display device based on the method described in step 330 .

[0147] In response to determining that the first user voice includes a control instruction for the display device, the processing device 130 may execute step 560 to control the display device based on the control instruction.

[0148] For example, the processing device 130 can determine the updated display parameters related to the display interface based on the voice recognition results, so as to update the display interface. The updated display parameters refer to the display parameters and their corresponding parameter values ​​used to adjust one or more display areas of the display interface. For example, the updated display parameters can be used to enlarge or reduce a certain display area (adjust the length or width), translate (position coordinates), rotate, set transparency, hide / show, etc. The updated display parameters can also be used to adjust or process the display content in the display area, such as switching, sending, selecting, playing, rotating, scaling, etc. of the displayed image, adjusting the color and font size of the text in the display area, etc. As an example only, for a DSA surgical scene (DSA medical process), the updated display parameters may include saving the perspective sequence, sending a reference, selecting a specific sequence, playing / pausing, switching between upper and lower frames, switching between upper and lower sequences, switching between subtraction original images, etc. However, it is not limited to this, and the method of updating the display parameters and the updated display parameters can be determined arbitrarily as needed.

[0149] In some embodiments, for each first voice signal, the processing device 130 can determine the identity of the sender of the voice signal through voiceprint analysis, and determine whether the sender is the target user described in step 530. If the sender of a first voice signal is the target user (such as the doctor or technician in charge of the operation), the first voice signal will be used as the target voice signal to determine the updated display parameters.

[0150] In some embodiments, the processing device 130 can also determine to update the display parameters based on the speech weight. For example, the speech weight of the surgeon can be set to be larger, the speech weight of the assisting medical staff can be smaller, and the speech weight of the user specified in the non-medical process can be set to 0. The processing device 130 can determine to update the display parameters based on the user identity corresponding to the first voice signal and its speech weight. For example, the first voice signal corresponding to the maximum speech weight needs to be processed first; if the speech weight is 0, no response is given. In this way, the accuracy and efficiency of updating the display interface can be improved, and the waste of computing resources and time caused by unnecessary updates can be avoided.

[0151] In some embodiments, the processing device 130 may also generate predicted display parameters based on the adjustment of the display interface by updating the display parameters. Typically, updates of different display areas in the display interface are linked, and adjustments to one display area may affect other display areas. For example, display area A is adjacent to display area B on the left and right. If display area A is enlarged (such as increasing the horizontal width), display area B can be reduced. The processing device 130 can determine the predicted display parameters based on the linkage relationship between the areas. For example, in response to the enlargement of display area A, the predicted display parameters may be to reduce display area B, or reduce its transparency or hide it.

[0152] In some embodiments, the predicted display parameters may also be related to user display preference parameters. For example, the display parameter adjustment record of the target user may be used to determine the display parameters preferred by the target user. In some embodiments, the predicted display parameters may also be related to the overall aesthetics of the display interface.

[0153] By predicting display parameters, the target user can be assisted in configuring the display interface, thereby reducing the user's overall adjustment workload and adjustment time for the display interface and improving the user experience.

[0154] In some embodiments, the processing device 130 can determine feedback information (for example, feedback voice, feedback display information, etc.) based on the predicted display parameters. Feedback information can be used to provide users with update suggestions for interface parameters. In some embodiments, feedback information can also include other types of information. For example, equipment usage problems (product introduction), operating process problems (such as instructions for a certain process in the system), equipment failures (such as software exception information), etc. As an example only, when updating the display interface, if the processing device 130 detects software or hardware failure information, it can remind the user through feedback information. For example, feedback information is played through the first voice device, feedback display information is displayed through the display device, etc. In some embodiments of this specification, human-computer interaction can be achieved through feedback information, and targeted suggestions or feedback can be provided to users to enhance user experience.

[0155] In some embodiments, the display device includes a target display area configured to display characteristic information of a target object. The processing device 130 can obtain abnormal characteristic information of the target object and, based on the abnormal characteristic information, update the display mode of the target display area. For example, when the updated content and / or data (such as key data such as blood pressure, blood sugar, and heart rate) in the target display area is abnormal data below or above a threshold, the abnormal data in the target display area can be highlighted or flashed to attract the user's attention. In some embodiments, the processing device 130 can also control the first voice device or a wearable device worn by the target user to issue an alert message. For example, the processing device 130 can play an alert message through the first voice device to notify the user, allowing the user to promptly be aware of the abnormal situation without having to constantly monitor the screen. For another example, the processing device 130 can send the alert message to the user's headphones, dedicated wristband, mobile phone, etc., which can issue the alert in the form of voice broadcast, vibration, ringing, text message, etc. This allows doctors and medical staff to focus more on their work, reducing the burden on technicians and doctors and improving the quality of their work.

[0156] In some embodiments, processing device 130 can acquire other voice signals emitted by the user during a medical procedure. For example, processing device 130 can receive a third voice signal emitted by the user to adjust a component of an imaging device and adjust the position of the component based on the third voice signal. For another example, processing device 130 can receive a voice query emitted by the user, determine the corresponding response, and control the first voice device to play the response.

[0157] In some embodiments, the processing device 130 may identify a control instruction related to a user configuration interface based on the fourth voice signal. The user configuration interface may display user configuration parameters. Upon detecting a control instruction related to the user configuration interface, the processing device 130 may control the display device to jump to the user configuration interface and determine updated user configuration parameters in the user configuration interface based on the fourth voice signal to update or adjust the user configuration parameters in the user configuration interface. Exemplary user configuration parameters may include display parameters, exposure parameters, system parameters, print setting parameters, and other parameters.

[0158] In some embodiments of the present specification, by acquiring a fourth voice signal emitted by a user during the execution of a medical procedure, it is possible to quickly and automatically jump to a corresponding user configuration interface and automatically complete the setting of user configuration parameters in the user configuration interface.

[0159] In some embodiments, steps 510-530 may be omitted, and processing device 130 may determine the initial display parameters of the display device based on other methods. For example, the initial display parameters of the display device may be system default configuration parameters. For another example, when the first voice signal includes a control instruction corresponding to the target user, processing device 130 may determine the display parameters preferred by the target user as the initial display parameters.

[0160] FIG6A is an exemplary schematic diagram of a display interface of a display device according to some embodiments of this specification.

[0161] The display interface 600A is an initial display interface determined according to the initial display parameters. As shown in Figure 6A, the display interface 600A may include a display area 610, a display area 620, a display area 630, and a display area 640. Different display areas can be used to present different display contents in the medical process. For example, the display area 610 can present a menu, the display area 620 can be used to present a real-time surgical screen, the display area 630 can be used to present the patient's various physiological indicators (such as blood pressure, heart rate, etc.), and the display area 640 can be used to present other content (such as surgical instructions or warnings, etc.).

[0162] FIG6B is an exemplary schematic diagram of a display interface according to some embodiments of this specification.

[0163] Display interface 600B is the updated display interface based on the updated display parameters. As shown in FIG6B , display area 610 (not shown) is configured to be hidden; the horizontal length of display area 620 is increased so that it covers the original display area 610; the vertical height of display area 630 is reduced; and the vertical height of display area 640 is increased.

[0164] In some embodiments, the user can adjust the display interface from 600A to 600B by issuing user voices such as "hide the menu bar" or "minimize the menu bar". The intelligent control system 100 can process the voice signal corresponding to the user voice through a trained language processing model to generate a corresponding semantic text. The semantic text may include an operation subject and an update parameter. For example, the operation subject "menu bar" corresponds to the display area 610, and the update parameter is "hide". Further, the intelligent control system 100 can generate corresponding program instructions based on the semantic text. For example, the program instruction can be used to set the parameters of the display area 610 to be hidden (such as setting the display attribute to false).

[0165] FIG. 7 is a flowchart of an exemplary collision detection process according to some embodiments of the present specification.

[0166] Medical equipment (e.g., X-ray imaging equipment) often requires frequent movement of one or more components (e.g., C-arm gantry) during the medical process to observe the target area at different angles and achieve more accurate scanning or treatment. However, since positioning takes a long time, it will lead to problems such as increased duration of the entire medical process and increased ineffective radiation. In the process of moving components, the components of the medical equipment may also collide with objects or people in the examination room, increasing the safety risks in the medical process. Therefore, it is necessary to provide an effective system and method for collision detection.

[0167] As shown in FIG3 , before or during a medical procedure, the processing device 130 may detect a user-initiated control instruction for controlling the medical device. For example, the control instruction may include a control instruction such as "Scan the patient's head position" to scan a target area of ​​a target object. Another example may include a control instruction such as "Move the C-arm to spider position" or "Angle the C-arm 45° to the left" to move one or more components of the medical device.

[0168] In response to the control instruction, the processing device 130 can control one or more components of the medical device to move to the target position to scan the target area of ​​the target object. The target position refers to the position to which one or more components of the medical device need to be moved. The target area refers to the organ and / or tissue of the target object that needs to be scanned and imaged. For example, when the control instruction is "scan the patient's head position", the processing device 130 can first determine whether the patient's head position is in the center of the field of view of the medical device (or the scanning center). If the patient's head position is in the center of the field of view of the medical device, the processing device 130 can control the medical device to scan the patient's head position. If the patient's head position is not in the center of the field of view of the medical device, the processing device 130 can control the components of the medical device (for example, the C-arm frame) to move so that the patient's head position is in the center of the field of view of the medical device, and then scan the patient's head position.

[0169] By way of example only, when the control instruction is to scan a target area of ​​a target object, the processing device 130 may obtain a third real-time optical image of the medical device and the target object, captured by an image acquisition device installed in the examination room, and determine planned motion information of a component of the medical device based on the third real-time optical image. Furthermore, the processing device 130 may control the movement of the component of the medical device based on the planned motion information to perform a medical procedure on the target area.

[0170] Planned motion information refers to the motion information of each component predetermined before executing the control instruction. The motion information includes the motion parameters involved in each component during the motion process. For example, the motion parameters may include the type of moving component (e.g., robotic arm forearm, robotic arm upper arm, C-arm gantry, bed plate, etc.), the movement angle, the movement distance, the movement time, the movement speed, etc. For example, the processing device 130 may generate a three-dimensional object model of the target object based on the third real-time optical image and determine the position of the target area of ​​the target object based on the three-dimensional object model. The processing device 130 may then obtain the current position of the component of the medical device (e.g., from the parameters of the medical device or the third real-time optical image); and determine the planned motion information of the component of the medical device based on the position of the target area and the current position of the component of the medical device. Furthermore, the processing device 130 may determine the type of target area to be scanned (e.g., head, liver, etc.) based on the control instruction; determine the position information of the target area (e.g., the three-dimensional coordinate information of the center point of the head) based on the type of the target area and the three-dimensional object model of the target object; determine the planned motion information of one or more components of the medical device based on the position information of the target area; and control the movement of the one or more components of the medical device based on the planned motion information. For another example, the processing device 130 may determine movement parameters of one or more of a bed, a detector, a radiation source, etc., so as to align the imaging isocenter of the medical device with the center point of the target area.

[0171] In some embodiments, before controlling the movement of a component based on planned movement information, the processing device 130 may perform a virtual collision detection to verify the planned motion information. Specifically, if no collision occurs in the virtual collision detection, the processing device 130 may control the movement of the component based on the planned motion information. If a collision occurs in the virtual collision detection, the processing device 130 may update the planned motion information until the updated planned motion information passes the virtual collision detection. For more description of virtual collision detection, please see below. By performing virtual collision detection on the planned motion information, the potential collision risk during the movement of the component can be determined in advance, thereby eliminating the potential collision risk and improving the safety of the medical process.

[0172] During movement of components of the medical device, the processing device 130 may execute the process 700 to perform collision detection.

[0173] In step 710 , during the movement of a component of the medical device, the processing device 130 (eg, the acquisition module 210 ) may acquire a first real-time optical image related to the medical device captured by an image acquisition device.

[0174] The first real-time optical image refers to an image related to the medical device (e.g., medical device 110, X-ray imaging device) and other objects in the examination room (e.g., target object) during the movement of the components of the medical device, which can reflect the real-time status of each object in the examination room.

[0175] The first real-time optical image may be captured by an image acquisition device (eg, image acquisition device 160) installed in the examination room. For more information about the image acquisition device, please refer to FIG. 1A and its related description.

[0176] In step 720 , the processing device 130 (eg, the determination module 230 ) may determine whether a collision will occur during the movement of the component based on the first real-time optical image.

[0177] For example, the processing device 130 may determine the relative position (e.g., the closest distance) between the component and another component or external object (e.g., the voice device 150, the display device 170, at least one user, a target object, etc.) based on the first real-time optical image. If the relative position is less than a fourth distance threshold, the processing device 130 may determine that a collision will occur during the movement of the component.

[0178] For another example, the processing device 130 may determine whether the motion trajectory of the component overlaps with other components or external objects based on the first real-time optical image. If the motion trajectory overlaps with other components or external objects, the processing device 130 may determine that a collision will occur during the motion of the component.

[0179] In some embodiments, the processing device 130 may also determine whether one or more components of the medical device collide during movement using other methods. As an example, the processing device 130 may determine current motion information based on the first real-time optical image and perform virtual collision detection based on this current motion information. Current motion information refers to the motion information of each component during the execution of a control instruction (e.g., when capturing the first real-time optical image). For example, the processing device 130 may generate a virtual imaging system based on the characteristic information of the medical device components and / or the real-time optical image. The virtual imaging system includes virtual representations of each component of the medical device (e.g., a detector, a radiation source, a gantry, etc.). This virtual imaging system can be used to perform virtual collision detection. For example, the movement trajectory of each component's corresponding virtual representation can be calculated based on the current motion information of each component, and a determination can be made as to whether the movement trajectory of each component's corresponding virtual representation will collide with the virtual representation of another component. Taking the detector and bed as an example, the processing device 130 may determine whether the current distance between the detector and the bed is less than a fourth distance threshold based on the positions of the detector model and the bed model in the virtual imaging system. If the distance is less than the fourth distance threshold, a collision is determined to be likely at the current moment. For another example, the processing device 130 can predict the distance between the detector and the bed at the next moment or time period based on the detector model and the bed model in the virtual imaging system, and whether the distance is less than a fourth threshold. If it is less than the fourth distance threshold, it is determined that there may be a risk of collision in the future. In some embodiments, virtual collision detection can be established based on a twin digital system. For example, the twin digital system can display in real time on a display device the virtual representation of each component of the medical equipment (such as a detector, a radiation source, a rack, etc.), the virtual representation of the user in the detection room, etc. It should be understood that in some embodiments, the processing device 130 can also directly identify the detector and the bed from the real-time optical image and make a distance judgment.

[0180] For another example, if a pressure sensor is installed on one or more components of a medical device (e.g., a robotic arm forearm, a robotic arm upper arm, a conduit bag, a C-arm outer arc, a bed base, a flat-panel detector, a tube, etc.), and a collision occurs at the location where the pressure sensor is installed, and the collision pressure exceeds a pressure threshold, the processing device 130 determines that the location has collided. The pressure threshold may be a default value, a pre-set value, or the like.

[0181] In some embodiments, in order to improve the safety of one or more components of the medical device during movement, when the processing device 130 detects that a component of the medical device is about to collide with other objects or people during movement, the processing device 130 can reduce the movement speed of the component.

[0182] If it is determined that no collision will occur during the movement of the component, the processing device 130 may control the movement of one or more components of the medical device based on the motion information; if it is determined that a collision will occur during the movement of the component, the processing device 130 may execute step 730.

[0183] In step 730 , the processing device 130 (eg, the control module 240 ) may control the first voice device to issue a collision warning.

[0184] For example, the processing device 130 may send an instruction to play a collision warning to the first voice device to control the first voice device to issue a collision warning. For example, the voice broadcast may be "The tail of the robotic arm may collide with the infusion stand."

[0185] In some embodiments, the processing device 130 may also display a virtual collision warning on the display device. For example, the processing device 130 may display the part where a collision is about to occur and / or has occurred on the display device 170. The display device 170 may indicate the part where a collision is about to occur and / or has occurred by a special mark. For example, the display device 170 may select the part where a collision is about to occur and / or has occurred by framing it in a red box. For another example, the display device 170 may mark the part where a collision is about to occur and / or has occurred with a red exclamation mark. In some embodiments, the processing device 130 may determine possible collision events with different levels of urgency (such as corresponding to different collision probabilities and different collision severities), and indicate these collision events with different special marks. For example, the components involved in collision events with different levels of urgency may be marked with boxes of different colors.

[0186] In some embodiments, the processing device 130 may also issue an alert message on a wearable device worn by the target user.

[0187] In some embodiments of this specification, not only can the location of an impending and / or already occurring collision be displayed on a display device, but a collision warning can also be broadcast by voice through a first voice device, thereby providing the user with multi-dimensional collision location prompts, allowing the user to promptly detect collision risks and make quick judgments.

[0188] In step 740 , the processing device 130 (eg, the acquisition module 210 ) may acquire a third speech signal.

[0189] The third voice signal is generated by the first voice device by detecting the third user's voice.

[0190] In some embodiments, after the first voice device issues a collision warning, the first voice device may detect a third user voice of a user (e.g., the target user) to generate a third voice signal. For example, the third user voice may include "Ignore this collision warning," "Re-perform virtual collision detection," "Move the robotic arm 20 centimeters to the right," etc.

[0191] In step 750 , the processing device 130 (eg, the determination module 230 ) may determine a collision response strategy based on the third voice signal.

[0192] For example, processing device 130 may determine a collision response strategy based on the control instruction in the third voice signal. For example, in response to the third target voice signal being "Ignore this collision warning," processing device 130 may continue to execute the movement control instruction. For another example, in response to the third target voice signal being "Move the robotic arm 20 centimeters to the right," processing device 130 may control the robotic arm to move 20 centimeters to the right.

[0193] As an example, as shown in FIG8A , the user first selects the Open CBCT acquisition protocol via voice. The processing device 130 determines whether a 3D object model of the target object has been established. If a 3D object model of the target object has not been established, normal operation is entered, and the user manually controls the movement of one or more components of the X-ray imaging device. If a 3D object model has been established, the processing device 130 receives a control instruction input by the target user via voice, such as "scan the patient's liver." After the user long-presses the "APC" button, the processing device 130 first controls the C-arm gantry to move to the exposure start position (i.e., automatically placing the liver in the center of the field of view). It then determines movement parameters based on the 3D object model of the target object and the control instruction, and performs virtual collision detection based on these movement parameters. If a potential collision is detected, a virtual collision warning is issued via the display device and / or the first voice device. After the obstacle is removed, virtual collision detection is performed again. If no collision is detected, one or more components of the X-ray imaging device are controlled to move to scan and image the target area of ​​the target object. In some embodiments, the processing device 130 may also perform virtual collision detection before or during the process of controlling the C-arm gantry to move to the exposure start position. For example, the processing device 130 may determine the planned motion information of the C-arm gantry according to the current position and the exposure start position of the C-arm gantry, and perform virtual collision detection based on the planned motion information.

[0194] By way of example only, when a user inputs a control command via voice input, "Scan the patient's liver position," the processing device 130 can obtain the control command via voice recognition. In response to the control command, the processing device 130 can obtain a real-time optical image of the medical device and the target object captured by an image acquisition device installed in the examination room, model the target object and the medical device based on the real-time optical image to generate a three-dimensional object model of the target object, and determine the position (e.g., center point) of the target area of ​​the target object based on the three-dimensional object model. The processing device 130 can then obtain the current position of the components of the medical device (e.g., through parameters of the medical device or the real-time optical image), and determine the planned motion information for moving the center of the medical device's field of view to the exposure start position (i.e., placing the liver position at the center of the field of view) based on the position of the target area and the current position of the components of the medical device. In some embodiments, the processing device 130 can perform virtual collision detection based on the planned motion information. Once the liver position is placed at the center of the medical device's field of view, the processing device 130 can control the medical device to perform a scanning operation.

[0195] In some embodiments, when the control instruction is a control instruction for moving one or more components of the X-ray imaging device, the storage device 140 may pre-store the correspondence between different control instructions and movement parameters. After the first voice device receives the control instruction input by the target user, it sends the control instruction to the processing device 130. The processing device 130 may access the storage device 140 based on the determined control instruction, determine the motion information through the correspondence, and control the movement of one or more components of the X-ray imaging device based on the motion information. In some embodiments, the processing device 130 may process the control instruction using a voice processing model to obtain the semantic text corresponding to the control instruction, and determine the motion information based on the semantic text. In some embodiments, the language processing model includes a large language model (LLM), which may be various deep learning models trained using a large amount of text data.

[0196] In some embodiments, to improve the safety of moving one or more components of the X-ray imaging device system, the processing device 130 can identify the identity of at least one user based on the control instructions of the at least one user and determine whether there is a target user (e.g., an operator of the X-ray imaging device) among the at least one user. If there is a target user among the at least one user, the processing device 130 executes the control instructions input by the target user; if there is no target user among the at least one user, the processing device 130 determines whether the user has control authority. If not, a prompt is given through the first voice device (e.g., playing a voice message "no control authority").

[0197] For another example, as shown in FIG8B , the user can turn on voice control of the X-ray imaging device through the voice wake-up function. If the device cannot be woken up, normal operation is entered, and the user manually controls the movement of one or more components of the X-ray imaging device. If the device is successfully woken up, the processing device 130 obtains the control instruction input by the user through the first voice device, such as "C-arm left angle 45°". The processing device 130 can recognize the control instruction. Recognizing a control instruction refers to processing the control instruction to determine its corresponding text and determining the movement parameters based on the text. If the corresponding text can be recognized and the motion information can be determined based on the text, the recognition is successful, otherwise the recognition fails. If the processing device 130 cannot recognize the control instruction, the user is prompted to re-enter the control instruction through the first voice device. If the processing device 130 successfully recognizes the control instruction, when the user triggers the motion control button, the processing device 130 controls the movement of one or more components of the X-ray imaging device based on the motion information corresponding to the control instruction.

[0198] As an example, during a common percutaneous coronary intervention (PCI) procedure, the C-arm must frequently switch between eight clinical angles to better observe the patient's left and right coronary artery lesions. This results in lengthy positioning times and increased ineffective radiation exposure for both the patient and the doctor. By using voice control commands, the user can quickly and accurately direct the C-arm to the target position, enabling more precise treatment and significantly improving C-arm positioning efficiency during surgery, reducing radiation exposure.

[0199] In some embodiments of the present specification, one or more components of a medical device are moved quickly and accurately to a target position through voice control commands. This not only facilitates doctors to observe the examination conditions of the patient's target area at different angles and improves the accuracy of the test, but also greatly improves the efficiency of positioning components of medical devices in the medical process and reduces radiation damage caused by multiple adjustments to the positioning angle of components due to human operational errors and other situations.

[0200] In some embodiments, in order to improve the safety of one or more components of the medical device during movement and avoid collisions between components and other objects or personnel during movement, the processing device receives the control instruction input by the user to determine the motion information and then enters the waiting state for movement trigger. When the user further confirms the movement instruction, the processing device 130 sends the motion information to the medical device to control one or more components of the medical device to move to the target position.

[0201] There are various ways for the user to further confirm the movement instruction. For example, the user can trigger a motion control button to further confirm the movement instruction. For another example, the user can use the first voice device to voice input "confirm movement" to further confirm the movement instruction.

[0202] In some embodiments, while one or more components are being moved, the processing device 130 may update the real-time optical image and issue a collision warning based on the updated real-time optical image. For example, the processing device 130 may repeat steps 710-750 until the components of the medical device are moved to the target location.

[0203] In some embodiments of the present specification, updated real-time optical images and / or pressure sensors are used to detect whether one or more components of a medical device will collide during movement, thereby promptly detecting movement collision problems and improving safety in medical procedures.

[0204] In some embodiments of this specification, real-time optical images and voice control commands are used to control medical equipment to scan a patient's target area and detect collisions during movement. This not only automatically controls the movement of medical equipment components, allowing them to quickly and accurately reach the target location for scanning and imaging, reducing ineffective radiation doses, but also effectively avoids collisions during movement, improving safety during surgery. Furthermore, by combining the advantages of optical anti-collision monitoring over a wide range with the convenience and simplicity of voice control, the accuracy and efficiency of intelligent control can be further improved.

[0205] In some embodiments, process 700 may further include one or more other steps.

[0206] For example, before detecting the first voice signal, the processing device 130 (e.g., the control module 240) may acquire a second real-time optical image of the medical device captured by an image acquisition device installed in the examination room. The second real-time optical image, captured by the image acquisition device (e.g., the image acquisition device 160) installed in the examination room, may reflect the state of various objects in the examination room before the first voice signal was detected. For example, the second real-time optical image may display positional information of the target object to be scanned and one or more components of the medical device.

[0207] Furthermore, the processing device 130 can control the display device to display a target interface based on the second real-time optical image. The target interface refers to an interface used to reflect the real-time status of the target object and the medical device. The real-time status of the target object and the medical device may include the positional relationship between the target object and the medical device, for example, the minimum distance between the target object and the medical device. For example, the second real-time optical image can be displayed in the target interface. For another example, the processing device 130 can reconstruct the second real-time optical image to obtain one or more of a three-dimensional object model of the target object, a three-dimensional device model of the medical device, a three-dimensional object model of other people (such as a doctor) or objects (such as a voice device 150, a display device 170, a surgical light) in the examination room, and display these three-dimensional models in the target interface.

[0208] In some embodiments, before the first voice signal is detected, the second real-time optical image can be continuously updated, and accordingly, the target interface (e.g., the real-time status of the target object and medical equipment) can also be continuously updated, so that the user can understand the real-time dynamics of the examination room.

[0209] While the user is controlling the movement of components of the medical device through voice control, the processing device 130 can update the target interface based on the first real-time optical image. For example, the processing device 130 can present the first real-time optical image in the target interface. Alternatively, the processing device 130 can reconstruct the first real-time optical image to obtain one or more of a three-dimensional object model of the target object, a three-dimensional device model of the medical device, a three-dimensional object model of other people (such as a doctor) or objects (such as the voice device 150, the display device 170, the surgical light) in the examination room, and send these three-dimensional models to the display device 170 for display or to update the target interface. When a possible collision is detected, the processing device 130 can control the display device to present a collision warning in the target interface.

[0210] Figure 9 is a schematic diagram of an exemplary intelligent control system according to some embodiments of this specification. Intelligent control system 900 is a variation of intelligent control system 100. Some components thereof have the same or similar functions and / or structures as corresponding components in intelligent control system 100.

[0211] 9 , the intelligent control system 900 may include a processing device 130, a network 920, a system control device 930, a first voice device 940, and a second voice device 950. Different components of the intelligent control system 900 may be arranged in different rooms.

[0212] The processing device 130 can process data and / or information obtained from the system control device 930, the first voice device 940, and the second voice device 950. For example, the processing device 130 can process voice signals obtained from the first voice device 940 and the second voice device 950. In some embodiments, the processing device 130 can be in communication with the first voice device 940 and the second voice device 950, respectively, and can thereby obtain voice signals collected by the first voice device 940 and / or the second voice device 950.

[0213] In some embodiments, the processing device 130 can process the voice signal. For example, the processing device 130 can perform voiceprint recognition on the voice signal to determine the identity information of the speaking user (such as a doctor, technician, etc.). For another example, the processing device 130 can perform voice recognition on the voice signal (for example, a first voice signal) to determine whether the voice signal contains control instructions related to medical equipment. In some embodiments, the processing device 130 can send control instructions related to medical equipment (such as X-ray imaging equipment, DSA equipment, etc.) to the system control device 930, so that the system control device 930 performs one or more medical equipment-related control operations in a medical process (such as X-ray imaging, DSA examination, etc.). For more information about voice recognition, see Figure 3 and its description. In some embodiments, the processing device 130 can extract a target voice signal corresponding to the target user from the voice signal (for example, the first voice signal). For more description of extracting the target voice signal, see Figure 4 and its related description.

[0214] As shown in Figure 9, the processing device 130 can be deployed in an equipment room. The term "equipment room" refers to a room used to house various devices, including but not limited to the processing device 130 and the system control device 930. In some embodiments, the processing device 130 can also be deployed in a control room or an inspection room. In some embodiments, the processing device 130 or a portion thereof can also be distributed across a combination of the equipment room, the control room, and the inspection room. In some embodiments, the processing device 130 can also be remote. For example, the processing device 130 can be implemented on a cloud platform.

[0215] The network 920 may include any suitable network that facilitates the exchange of information and / or data within the intelligent control system 900. In some embodiments, one or more components of the intelligent control system 900 (e.g., the processing device 130, the system control device 930, the first voice device 940, and the second voice device 950) may communicate information and / or data with one or more other components of the intelligent control system 900 via the network 920. In some embodiments, the network 920 may be an Ethernet network, which may be implemented using a network switch. The network switch may be configured to facilitate communication between the processing device 130 and the first voice device 940, as well as between the processing device 130 and the second voice device 940.

[0216] In some embodiments, the network switching device (not shown) may be one or more network data switching / forwarding devices, which may be deployed in an equipment room or other suitable location (such as a control room, an inspection room, etc.). For example, it may be a network switch, a router, or a combination thereof. The network switching device may include one or more access points for enabling connections and data exchange between one or more other components of the intelligent control system 900 (such as the first voice device 940, the second voice device 950, etc.).

[0217] In some embodiments, the network switching device can be used to implement voice interaction between the first voice device 940 and the second voice device 950. This voice interaction process can be referred to as voice intercom. For example, the voice signal of the first voice device 940 can be sent to the processing device 130 via the network switching device; further, the processing device 130 can send the voice signal to the second voice device 950 via the network switching device, so that the second voice device 950 can play the voice signal through its voice output component (such as a speaker), thereby implementing a voice intercom process from the first voice device 940 to the second voice device 950.

[0218] Similarly, the voice signal of the second voice device 950 can be sent to the processing device 130 through the network switching device. Furthermore, the processing device 130 can send the voice signal to the first voice device 940 through the network switching device, so that the first voice device 940 can play the voice signal through its voice output component (such as a speaker). This completes a voice intercom process from the second voice device 950 to the first voice device 940.

[0219] The system control device 930 is a device used to control the medical device. For more information about the system control device, see FIG1A and its related description.

[0220] Voice devices can be used to implement voice interaction between multiple users. The first voice device 940 refers to a voice device deployed in the examination room. The second voice device 950 refers to a voice device deployed in the control room. The control room is where the control personnel of the medical process are located. The control personnel can issue control instructions related to the medical process (such as control instructions for medical equipment) in the control room, observe and monitor the execution process of the medical process, and guide patients or other users in the examination room. The examination room is a place where medical procedures are performed, in which medical equipment (CT equipment, DSA equipment, radiotherapy equipment, etc.) can be deployed. In addition, patients undergoing medical procedures, technicians performing medical procedures, etc. can be located in the examination room.

[0221] Personnel in the control room and those in the examination room can communicate with each other via the first voice device 940 and the second voice device 950. Hereinafter, one or more personnel in the examination room may be referred to as first-category users, and one or more personnel in the control room may be referred to as second-category users. First-category users and second-category users may include doctors, technicians, or other medical staff. First-category users may also include patients. For example, during a scan, the second-category user may be a doctor, and the first-category user may be a scanning technician or patient.

[0222] Voice devices can also be used to implement voice control of devices. For example, the first type of user and / or the second type of user can issue voice control instructions through their corresponding voice devices to intelligently control the equipment in the examination room, control room, and equipment room. As an example only, the doctor in the examination room can control the medical equipment in the examination room and the display device in the control room through voice. Therefore, through the intelligent control system 900 including the processing device 130 and the voice device (for example, the first voice device 940 and the second voice device 950), the user can interact with the target device (such as medical equipment, display device, etc.). For example, the processing device 130 can perform voice recognition on the voice collected by the voice device to obtain control instructions, and realize the control of the target device through the control instructions.

[0223] Hereinafter, the voice of the first user is referred to as the first user voice, and the signal related to the first voice is referred to as the first voice signal. The voice of the second user is referred to as the third user voice, and the signal related to the third voice is referred to as the third voice signal.

[0224] 9 , the first voice device 940 may include a first voice input component 941, a first voice output component 942, and a first voice processing component 943. The second voice device 950 may include a second voice input component 951, a second voice output component 952, and a second voice processing component 953.

[0225] The voice input component can be used to collect or detect user voice, which can include various sound collection devices such as microphones and voice recorders.

[0226] The voice output component can be used to play sound, which can include various sound output devices such as speakers, audio equipment, and loudspeakers.

[0227] The voice processing component can be used to convert and process voice signals. In some embodiments, the voice processing component may include an audio signal codec for encoding the user's voice (i.e., analog signal) detected by the voice input component into a voice signal (i.e., digital signal) and transmitting it to the processing device 130 for voice recognition and other processing; or decoding the voice signal into an analog signal for playback via the voice output component. In some embodiments, the voice processing component may also include various sound processing-related components such as filters and noise reducers.

[0228] Taking the first voice device 940 as an example, the first voice input component 941 is configured to detect the first voice of the first type of user, and the first voice output component 942 is configured to play the second voice of the second type of user. The first voice processing component 943 can be configured to convert the first voice into a first voice signal, convert the third voice signal into a playable second voice, and process the first voice signal and / or the third voice signal (such as noise reduction, sound amplification, etc.).

[0229] In some embodiments, the voice input component and voice output component in each voice device are respectively connected to its voice processing component, and the voice processing component is further connected to the network 920.

[0230] In some embodiments, the intelligent control system 900 may further include other devices, such as a medical device 110, a storage device 140, an image acquisition device 160, a display device 170, etc. For more description of the medical device, storage device, image acquisition device, and display device, see FIG1A and its related description.

[0231] FIG10 is a schematic diagram of an exemplary intelligent control system according to some embodiments of the present specification.

[0232] Intelligent control system 1000 is similar to intelligent control system 900, except that it includes a first network 921 and a second network 922. First network 921 is used to facilitate data communication between processing device 130 and first and second voice devices 940 and 950. Second network 922 is used to facilitate data communication between processing device 130 and system control device 930. In some embodiments, first network 921 can be connected to a first and second voice processing components 943 and 953.

[0233] In some embodiments of this specification, the first network 921 is used to transmit data related to the voice intercom scenario, and the second network 922 is used to transmit data related to the control scenario of the medical device. This can avoid the mutual influence between the two types of data transmission, ensure that each type of data has sufficient transmission bandwidth, and improve data transmission efficiency.

[0234] The first network 921 and the second network 922 can be of the same type or different types. As an example only, the intelligent control system 1100 shown in FIG11 is a specific embodiment of the intelligent control system 1000. As shown in FIG11, the first network 921 is implemented by cables 923 and 924, and the second network 922 is implemented by a network switch 925.

[0235] The cable 923 is configured to establish a communication connection between the processing device 130 and the first voice device 940. The cable 923 can be of various types and can be determined based on the interface type of the processing device 130 or the first voice device 940. In some embodiments, the processing device 130 can include various different types of interfaces, such as one or a combination of multiple USB (Universal Serial Bus) interfaces and TRS (Tip Ring Sleeve) audio interfaces. The cable 923 can be a USB cable, a TRS cable, or the like that connects the first voice device 940 to the processing device 130.

[0236] The cable 924 is configured to realize a communication connection between the processing device 130 and the second voice device 950. Similar to the cable 923, the cable 924 can also be various types of cables (such as a USB cable).

[0237] The network switch 925 refers to a network switching device for implementing network data forwarding between the processing device 130 and the system control device 930. For relevant details about the network switching device, see FIG9 and its description.

[0238] In some embodiments of this specification, the processing device 130 is directly connected to the first voice device 940 and the second voice device 950 through cables (such as cable 923 and cable 924), so that direct data transmission between the processing device 130 and the first voice device 940 and the second voice device 950 can be achieved, thereby improving the efficiency of voice intercom between the first voice device 940 and the second voice device 950.

[0239] FIG12 is a schematic diagram of an exemplary intelligent control system according to some embodiments of the present specification.

[0240] Intelligent control system 1200 is similar to intelligent control system 1000 in Figure 10 , except that the structure of second voice device 950 is different. As shown in Figure 12 , second voice device 950 may include a second voice input component 951, a second voice output component 952, a second voice processing component 953, a control component 954, and a user interaction component 955. Control component 954 is communicatively connected to second voice output component 952, second voice input component 951, second voice processing component 953, and user interaction component 955, respectively.

[0241] The control component 954 is configured to control the on / off states of the second voice output component 952 and the second voice input component 951. For example, the control component 954 is provided with on / off buttons for the second voice input component 951 and the second voice output component 952, and the user can use these buttons to turn on or off the second voice input component 951 and the second voice output component 952. In some embodiments, the control component 954 may include a keypad.

[0242] The user interaction component 955 can be configured to transmit the on / off status of the second voice input component 951 and the second voice output component 952 to the system control device 930. As shown in FIG12 , the user interaction component 955 is further communicatively connected to the system control device 930 and configured to transmit the on / off status of the second voice input component 951 and the second voice output component 952 to the system control device 930. The system control device 930 can transmit the on / off status to the processing device 130 via the second network 922. The processing device 130 is further configured to control the connection between it and the second voice device 950 based on the on / off status. By way of example only, when the second voice input component 951 or the second voice output component 952 is on, the processing device 130 can establish a connection with the second voice device 950 and receive voice signals collected by the second voice device 950 or transmit voice signals to the second voice device 950. When the second voice input component 951 or the second voice output component 952 is off, the processing device 130 can disconnect the connection between it and the second voice device 950.

[0243] In some embodiments, the user interaction component 955 can be communicatively connected to the system control device 930 via a controller area network (CAN) bus.

[0244] The above description is for illustrative purposes only, and actual application scenarios may vary. For example, the user interaction component 955 can be configured to communicate directly with the processing device 130 via the second network 922, so that the switch status of the second voice input component 951 and the second voice output component 952 can be sent to the processing device 130. For another example, the structure of the first voice device 940 can be similar to the second voice device 950, also including a control component and a user interaction component. Specifically, the control component of the first voice device 940 can be communicated with the voice output component 942 and the voice input component 941, and is configured to control the switch status of the voice output component 942 and the voice input component 941. The user interaction component of the first voice device 940 can be communicated with the control component of the first voice device 940 and the processing device 130, and is configured to send the switch status of the voice output component 942 and the voice input component 941 to the processing device 130. Therefore, the processing device 130 may be further configured to control the connection state between it and the first voice device 940 based on the switch states of the voice output component 942 and the voice input component 941 .

[0245] FIG13 is a schematic diagram of an exemplary intelligent control system according to some embodiments of the present specification.

[0246] As shown in Figure 13, the intelligent control system 1300 may include a processing device 130, a network 920, a system control device 930, a first voice device 940, and a second voice device 950. The processing device 130 and the system control device 930 may be located in an equipment room or other suitable location (such as a control room), the first voice device 940 may be located in an examination room, and the second voice device 950 may be located in the control room. The second voice device 950 may include a second voice input component 951, a second voice output component 952, and a second voice processing component 953. The first voice device 940 may include a first voice input component 941 and a first voice output component 942, but may not include a voice processing component.

[0247] The processing device 130, network 920, system control device 930, and second voice device 950 can be similar to the processing device 130, network 920, system control device 930, and second voice device 940 in the intelligent control system 900 shown in Figure 9, and will not be repeated here.

[0248] The second voice device 950 is communicatively connected to the processing device 130, and the first voice device 940 is communicatively connected to the second voice device 950. For example, as shown in FIG13 , the second voice device 950 and the processing device 130 are communicatively connected via a network 920. The first voice input component 941 and the first voice output component 942 in the first voice device 940 can be communicatively connected to the second voice processing component 953 in the second voice device 950 via a cable 926 and a cable 927, respectively.

[0249] In some embodiments, when the distance between the control room and the inspection room is less than a preset distance threshold, the first voice device 940 can be directly connected to the second voice device 950 in a manner as shown in FIG13 . The preset distance threshold can be 20 m or other suitable value.

[0250] In some embodiments, the first voice device 940 can be considered as part of the second voice device 950. For example, when building the intelligent control system 1300, one of the multiple microphones of the second voice device 950 can be placed in the examination room as the first voice input component 941; and one of the multiple speakers of the second voice device 950 can be placed in the examination room as the first voice output component 942.

[0251] In some embodiments, the second voice device 950 can be configured to detect a third user voice to generate a third voice signal, and send the third voice signal to the processing device 130. The processing device 130 is configured to send the third voice signal to the first voice device 940. The first voice device 940 is configured to convert the third voice signal into a user voice and output the user voice. The first voice device 940 is further configured to detect the first user voice and send the detected first user voice to the second voice device 950. The second voice device 950 is configured to convert the first voice signal into a user voice and output the user voice. In this embodiment, the first voice device 940 is only used for sound collection and sound output, while voice processing (such as noise reduction processing) is performed by the second voice processing component 953 of the second voice device 950.

[0252] The first user voice refers to the user voice corresponding to one or more users in the examination room, and the first voice signal is the voice signal corresponding to the first user voice. The third user voice refers to the user voice corresponding to one or more users in the control room, and the third voice signal is the voice signal corresponding to the third user voice. For more information about user voices and voice signals, see Figure 3 and its description.

[0253] In some embodiments, the system control device 930 can be used to execute preset control instructions related to the medical device, and the system control device 930 is communicatively connected to the processing device 130.

[0254] In some embodiments, the processing device 130 is further configured to perform speech recognition on the first voice signal to obtain a speech recognition result; based on the speech recognition result, determine whether the first voice signal contains a control instruction; and, in response to the first voice signal containing a control instruction, transmit the speech recognition result to the system control device 930, so that the system control device 930 controls the medical device. For more information on the speech recognition result and control instructions, see FIG. 15 and its description, which will not be repeated here.

[0255] In some embodiments, the processing device 130 can extract the target voice signal emitted by the target user from the first voice signal and send it to the second voice device 950. For more information about the target voice signal extraction, please refer to FIG4 and its description, which will not be repeated here.

[0256] In some embodiments of the present specification, it is only necessary to set up voice input components such as microphones and voice output components such as speakers in the inspection room. The voice signal of the inspection room can be directly received and processed (such as noise reduction processing) by the second voice device 950 through cables, which can save the consumption of network data. At the same time, it also makes the overall structural setting of the intelligent control system simpler and easier to maintain.

[0257] FIG14 is a schematic diagram of an exemplary intelligent control system according to some embodiments of the present specification.

[0258] Intelligent control system 1400 is similar to intelligent control system 1300, except that it includes a first network 921 and a second network 922. As shown in FIG14 , first network 921 is used to implement data communication between processing device 130 and second voice device 950. Second network 922 is used to implement data communication between processing device 130 and system control device 930.

[0259] The above description of the intelligent control system is for illustrative purposes only. Actual intelligent control systems may vary. For example, the connection method of the various components in the intelligent control system may be changed. For another example, taking intelligent control system 1300 as an example, it may also include a voice signal encoding device and a voice signal decoding device. The voice signal encoding device and the voice signal decoding device may be arranged between the first network 921 and the processing device 130 to transmit or convert voice signals.

[0260] FIG15 is a schematic diagram of a voice interaction process between a first voice device and a second voice device according to some embodiments of this specification. In some embodiments, process 1500 may be executed by the processing device 130.

[0261] As shown in FIG15 , the processing device 130 may receive a first voice signal 1502 from the first voice device 940. For example, the processing device 130 may obtain the first voice signal 1502 via the network 920 or the first network 921. The processing device 130 may perform voice recognition on the first voice signal 1502 to obtain a voice recognition result 1504. For more information on obtaining the voice recognition result, see FIG4 and its related description. Based on the voice recognition result 1504, the processing device 130 may determine a control instruction 1506 (or target voice signal) corresponding to the first voice signal 1502 and send the control instruction 1506 (or target voice signal) to the second voice device 950. For more information on determining the control instruction, see FIG3 and its related description. In some embodiments, the second voice device 940 may play the control instruction 1506 (or target voice signal). In some embodiments, the first voice signal 1502 may be sent to the second voice device 940 together with the control instruction 1506 (or target voice signal), and the second voice device 940 may play the first voice signal 1502.

[0262] Similarly, the processing device 130 can receive a third voice signal through the second voice device 950. The processing device 130 can perform voice recognition on the third voice signal to obtain a voice recognition result. Based on the voice recognition result, the processing device 130 can determine the control instruction (or target voice signal) corresponding to the third voice signal and send the control instruction (or target voice signal) to the first voice device 940.

[0263] FIG16 is a flowchart of an exemplary process of controlling a medical device according to some embodiments of this specification.

[0264] In some embodiments, operation 340 in FIG3 may be implemented by process 1600. In some embodiments, process 1600 may be performed by processing device 130.

[0265] In step 1610 , the processing device 130 may perform structured processing on the control instruction to generate a structured control instruction.

[0266] The structured control instructions have a preset data structure. The preset data structure can be determined by a medical protocol. Medical protocols corresponding to different medical processes can define different data structures of control instructions. For example, the preset data structure may include medical device type, component type, and operating parameters. The medical device type may include the type of medical equipment in the examination room (such as CT equipment, DSA equipment), etc. The component type may refer to the target component that needs to be operated on the medical device (such as the DSA rack, etc.), and the operating parameters may include specific operations on the target component (such as the moving distance, the rotation angle, etc.).

[0267] In some embodiments, the processing device 130 may perform structured processing on the speech recognition result to determine a structured control instruction.

[0268] In step 1620 , the processing device 130 may send the structured control instruction to the system control device so that the system control device controls the medical device.

[0269] The processing device 130 can determine whether the control instruction is a control instruction of the target type based on the structured control instruction and the preset control instruction set. The preset control instruction set may include one or more preset control instructions related to the medical device. Each preset control instruction in the control instruction set has a preset data structure (i.e., a structured control instruction). Exemplarily, the processing device 130 can determine whether the medical device type and component type in the structured control instruction corresponding to the control instruction are consistent with the medical device type and component type of the preset control instruction. If inconsistent, it means that the control instruction corresponding to the speech recognition result is not a control instruction of the target type. If consistent, it means that the control instruction corresponding to the speech recognition result contains a control instruction of the target type.

[0270] In response to determining that the control instruction is a target-type control instruction, the processing device 130 may send the structured control instruction to the system control device, so that the system control device controls the medical device.

[0271] Compared to the original voice recognition results / control instructions, the content of structured control instructions is more concise and accurate, so sending structured control instructions can improve the accuracy and efficiency of medical device control. In response to the voice recognition result not containing the target type of control instructions, the processing device 130 does not need to send the voice recognition result to the system control device 930, and can generate a notification message and send it to the first voice device 940 and / or the second voice device 950 to inform relevant personnel so that they know that no control instructions related to the medical device were generated in this voice intercom. Relevant personnel can reorganize the voice content according to actual needs (such as whether this voice intercom is expected to complete the control of the medical device or just communicate with the examination room staff). Among them, the notification message can be in various forms such as text (such as a message displayed on a display device) and voice (such as feedback played by the speaker of the first voice device 940).

[0272] In some embodiments, the processing device 130 can extract the target voice signal from the first voice signal and then determine whether the target voice signal contains a control instruction of the target type. In this way, the control instruction issued by the target user to control the medical device can be accurately identified and the medical device can be accurately controlled accordingly.

[0273] In some embodiments of the present specification, (1) the user's voice signal is processed through voice recognition to achieve intelligent voice control of the target device and automated control of the medical device operation, so that doctors can interact with the medical device by voice without manually controlling the medical device, thereby reducing the number of medical staff required in the medical process, improving the execution efficiency and accuracy of the medical process, and ensuring that the medical process proceeds more smoothly; (2) the identity of the speaking user is identified through voiceprint information analysis, and only the target voice signal corresponding to the target user is identified and processed, which can avoid the influence of the voice of non-target users on the control of the medical process and improve the accuracy and safety of the operation control of the medical device. , thereby ensuring that the medical process proceeds more smoothly; (3) Through intelligent voice control, the display interface of the display device is automatically personalized, and the display parameters of the display interface are adjusted through the user's voice commands, thereby improving the execution efficiency of the medical process and enhancing the user experience; (4) Through real-time optical images and voice control commands, the medical device is controlled to scan the target area of ​​the patient and detect collision problems during movement. It not only realizes the automatic control of the movement of the components of the medical device, quickly and accurately reaches the target position to scan and image the target area, reduces the measurement of invalid radiation, but also effectively avoids the problem of mobile collision and improves the safety during the operation.

[0274] Some embodiments of this specification also provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions, the computer executes the intelligent control method described in this specification. For more technical details, please refer to the relevant descriptions of Figures 1A to 16, which will not be repeated here.

[0275] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit this specification. Although not explicitly stated herein, various modifications, improvements, and revisions to this specification may be made by those skilled in the art. Such modifications, improvements, and revisions are suggested in this specification and remain within the spirit and scope of the exemplary embodiments of this specification.

[0276] This specification also uses specific terms to describe the embodiments of this specification. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "one embodiment," "an embodiment," or "an alternative embodiment" two or more times in different locations in this specification do not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of this specification may be appropriately combined.

[0277] In addition, unless expressly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the spirit and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0278] Similarly, it should be noted that, in order to simplify the presentation of this specification and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this specification sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this specification requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single disclosed embodiment.

[0279] In some embodiments, numbers are used to describe the quantity of components and attributes. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, which may change according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0280] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, and documents, cited in this specification is hereby incorporated by reference in its entirety. This includes application history documents that are inconsistent with or conflict with the content of this specification, as well as documents (currently or subsequently attached to this specification) that limit the broadest scope of the claims of this specification. It should be noted that if the descriptions, definitions, and / or terminology used in the accompanying materials are inconsistent or conflicting with the content of this specification, the descriptions, definitions, and / or terminology used in this specification will control.

[0281] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. An intelligent control method, characterized in that: include: Acquire a first voice signal, where the first voice signal is generated by a first voice device by detecting a first user's voice; Performing speech recognition on the first speech signal to obtain a speech recognition result; Based on the speech recognition result, determining whether the first user speech contains a control instruction for the target device; In response to determining that the first user voice includes a control instruction for the target device, the target device is controlled based on the control instruction.

2. The intelligent control method according to claim 1, characterized in that: The target device includes a display device installed in an examination room, and the control instruction includes at least one of the following instructions: An instruction to switch a display image on the display device; An instruction to play or pause the display image on the display device; An instruction for switching a display mode of the display device; An instruction for setting display parameters of a display image on the display device; An instruction for processing a display image on the display device; An instruction for setting a display area division method of the display device; An instruction for causing the display interface to jump to a user configuration interface.

3. The intelligent control method according to claim 1 or 2, characterized in that: The target device includes a medical device installed in an examination room, and the control instruction includes at least one of the following instructions: instructions for controlling motion of components of the medical device; instructions for causing the medical device to perform a medical procedure on a target area of ​​a target subject; An instruction for setting the working mode of the medical device; Instructions for setting relevant parameters of the medical procedure corresponding to the medical device; Instructions for the medical device to start or stop a medical procedure.

4. The intelligent control method according to any one of claims 1 to 3, characterized in that: The method further comprises: Control the first voice device to play feedback voice.

5. The intelligent control method according to claim 4, characterized in that: The controlling the first voice device to play the feedback voice comprises: Determining a security level of the control instruction based on the speech recognition result; Based on the security level, determining the content of the feedback voice; Based on the content of the feedback voice, control the first voice device to play the feedback voice.

6. The intelligent control method according to claim 1, characterized in that: Before acquiring the first speech signal, the method further includes: Acquire a second voice signal, where the second voice signal is generated by the first voice device by detecting a second user's voice; Determining whether the second user's voice contains a wake-up word; and In response to determining that the second user voice contains a wake-up word, a voice control mode is turned on.

7. The method according to any one of claims 1 to 5, characterized in that The method further includes: determining whether the first user's voice contains a wake-up word based on the voice recognition result; In response to determining that the first user voice contains a control instruction for the target device, controlling the target device based on the control instruction includes: in response to determining that the first user voice contains a wake-up word and contains a control instruction for the target device, controlling the target device based on the control instruction.

8. The intelligent control method according to claim 3, characterized in that: The medical device is a C-arm X-ray imaging device.

9. The intelligent control method according to any one of claims 1 to 8, characterized in that: Performing speech recognition on the first speech signal to obtain a speech recognition result includes: Based on the first voice signal, determining first voiceprint information of at least one user corresponding to the first voice signal; Based on the first voiceprint information of the at least one user, determining whether the at least one user includes a target user; In response to determining that the at least one user includes the target user, determining a target speech signal corresponding to the target user; and Performing speech recognition on the target speech signal to obtain the speech recognition result.

10. The intelligent control method according to claim 9, characterized in that: Based on the first voiceprint information of the at least one user, determining whether the at least one user includes the target user includes: Obtaining target voiceprint information corresponding to the target user; By comparing the first voiceprint information of the at least one user with the target voiceprint information, it is determined whether the at least one user includes the target user.

11. The intelligent control method according to claim 9, characterized in that: Based on the first voiceprint information of the at least one user, determining whether the at least one user includes the target user includes: For each of said users, Determining the identity information of the user based on the first voiceprint information; Determine the speech weight of the user based on the identity information of the user; and Based on the speech weight of the user, it is determined whether the user is the target user.

12. The intelligent control method according to claim 6, characterized in that: The target device includes a display device installed in an examination room. Before acquiring the first voice signal, the method further includes: Based on the second user voice, determining second voiceprint information corresponding to the second user voice; Based on the second voiceprint information, initial display parameters of the display device are determined.

13. The intelligent control method according to any one of claims 1 to 12, characterized in that: The method further comprises: Based on the speech recognition result, determining whether the first user's speech contains a question; In response to the first user voice containing a query, determining answer information corresponding to the query; Control the first voice device to play the answer information.

14. The intelligent control method according to claim 1, characterized in that: The target device includes a display device, the display device includes a target display area configured to display feature information of the target object, and the method further includes: Acquire abnormal characteristic information of the target object; Based on the abnormal feature information, updating the display mode of the target display area; and Control the first voice device or the wearable device worn by the target user to issue a warning message.

15. The intelligent control method according to claim 3, characterized in that: The control instruction is an instruction for controlling the motion of a component of the medical device, and the method further comprises: During the movement of the component, a first real-time optical image related to the medical device is acquired, wherein the first real-time optical image is taken by an image acquisition device installed in the examination room; Based on the first real-time optical image, it is determined whether a collision will occur during the movement of the component.

16. The intelligent control method according to claim 15, characterized in that: The method further comprises: Before acquiring the first voice signal, acquiring a second real-time optical image related to the medical device taken by the image acquisition device; based on the second real-time optical image, controlling a display device to display a target interface, wherein the target interface is used to reflect the real-time status of the target object and the medical device; During the movement of the component, the target interface is updated based on the first real-time optical image.

17. The intelligent control method according to claim 15, characterized in that: The method further comprises: In response to determining that a collision will occur during the movement of the component, controlling the first voice device to issue a collision warning; Acquire a third voice signal, where the third voice signal is generated by the first voice device by detecting a third user's voice; Based on the third voice signal, a collision response strategy is determined.

18. The intelligent control method according to claim 3, characterized in that: The control instruction is an instruction for causing the medical device to perform a medical procedure on a target area of ​​a target object, and the method further comprises: Acquire a third real-time light image related to the medical device and the target object taken by an image acquisition device installed in the examination room. Learn images; determining planned motion information of a component of the medical device based on the third real-time optical image; Based on the planned motion information, components of the medical device are controlled to move so as to perform the medical procedure on the target area.

19. The intelligent control method according to claim 1, characterized in that: The target device includes a medical device installed in an examination room, and the controlling the target device includes: The control instruction is sent to a system control device so that the system control device controls the medical device.

20. The intelligent control method as claimed in claim 19, characterized in that: Sending the control instruction to a system control device so that the system control device controls the medical device includes: Performing structural processing on the control instruction to generate a structured control instruction, wherein the structured control instruction has a preset data structure; The structured control instruction is sent to the system control device so that the system control device controls the medical device.

21. The intelligent control method according to claim 1, characterized in that: The target device includes a medical device and a display device installed in an examination room, wherein controlling the target device based on the control instruction includes: In response to the control instruction, the display device is controlled to display the medical procedure performed by the medical device.

22. The intelligent control method according to any one of claims 1 to 21, characterized in that: The method further comprises: The first voice signal is sent to a second voice device installed in a control room, so that the second voice device plays the first user voice.

23. An intelligent control system, comprising an acquisition module, an identification module, a determination module and a control module: The acquisition module is used to acquire a first voice signal, where the first voice signal is generated by a first voice device by detecting a first user's voice; The recognition module is used to perform speech recognition on the first speech signal to obtain a speech recognition result; The determination module is used to determine whether the first user voice contains a control instruction for the target device based on the voice recognition result; The control module is configured to, in response to determining that the first user voice contains a control instruction for the target device, control the target device based on the control instruction.

24. An intelligent control system, characterized in that: include: storage devices, which store computer instructions; A processor is connected to the storage device, and when executing the computer instructions, the processor causes the system to perform the following operations: Acquire a first voice signal, where the first voice signal is generated by a first voice device by detecting a first user's voice; Performing speech recognition on the first speech signal to obtain a speech recognition result; Based on the speech recognition result, determining whether the first user speech contains a control instruction for the target device; In response to determining that the first user voice includes a control instruction for the target device, the target device is controlled based on the control instruction.

25. A computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method according to any one of claims 1 to 22.

Images