Digitized intelligent operating room routing control software system

Abstract

The invention discloses a digital intelligent operating room route control software system, and relates to the technical field of medical informatization and intelligent operating rooms. The dynamic sensing mechanism collects five-dimensional data of operation progress, equipment alarm, voice instructions, network loads and operator identities in real time, and the current operation stage (including skin cutting, suturing and emergency intervention) is judged through a state machine engine. An intelligent decision closed-loop mechanism; the intelligent decision closed-loop mechanism detects state change every 200 milliseconds, automatically loads a preset strategy template, optimizes parameters through a genetic algorithm, and issues a flow table rule in real time through the SDN controller to form a'sensing-decision-execution-monitoring 'closed loop. The operation and maintenance efficiency is improved, IT personnel only need to maintain the strategy template library, and the daily intervention demand is reduced by 90%.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical informatization and intelligent operating room, and particularly relates to a digital intelligent operating room routing control software system. BACKGROUND

[0002] Modern intelligent operating rooms need to integrate tens of heterogeneous devices such as endoscopes, anesthesia machines, monitors, PACS images, robots, etc., to generate multi-modal real-time data such as video streams (4K / 3D), vital sign data, control instructions, etc.

[0003] The prior art mainly relies on hardware matrix switches or basic IP networks for data transmission, and has the following significant bottlenecks:

[0004] 1. Hardware matrix: poor scalability, low protocol compatibility (only supports HDMI / SDI), and inability to dynamically reconfigure paths;

[0005] 2. Traditional IP network: lack of service awareness, unable to guarantee low latency (<100ms) and zero packet loss requirements for critical traffic in surgery;

[0006] 3. Protocol island: private device protocols (such as endoscope manufacturer protocols) and standard protocols (DICOM) cannot directly interoperate;

[0007] 4. Manual configuration: routing strategies rely on pre-set by engineers, and cannot respond to sudden conditions in surgery (such as prioritizing vital sign transmission in case of heavy bleeding).

[0008] Therefore, a digital intelligent operating room routing control software system is needed to change this situation. SUMMARY

[0009] The purpose of the present application is to solve the problems in the prior art and provide a digital intelligent operating room routing control software system. Its advantages include improved operational efficiency, with IT personnel only needing to maintain a strategy template library, and a 90% reduction in daily intervention requirements.

[0010] To achieve the above purpose, the present application adopts the following technical solutions:

[0011] The digital intelligent operating room routing control software system includes a dynamic sensing mechanism. The dynamic sensing mechanism collects five-dimensional data of surgery progress, device alarms, voice instructions, network load, and operator identity in real time, and determines the current surgery stage (including skin incision, suture, and emergency intervention) through a state machine engine.

[0012] An intelligent decision-making closed-loop mechanism is provided. The intelligent decision-making closed-loop mechanism detects state changes every 200 milliseconds, automatically loads pre-set strategy templates, optimizes parameters through a genetic algorithm, and then issues flow table rules in real time through an SDN controller to form a "sensing-decision-execution-monitoring" closed loop.

[0013] The three-layer architecture of unified protocol conversion includes a protocol identification layer that automatically identifies 42 medical device proprietary protocols based on deep packet inspection (DPI) and a signature library; a data parsing layer that uses an FPGA-accelerated finite state machine to parse data structures of different protocols in parallel; and a standard encapsulation layer that converts data into JSON-LD format with precise timestamps and injects it into a unified data bus.

[0014] A three-level hierarchical security system includes CRITICAL (vital signs), with a rigid bandwidth guarantee of ≥20Mbps and latency ≤30ms, and priority resource preemption during network congestion; HIGH (surgical field video), with dual-path redundant transmission + forward error correction, and a frame loss rate of <0.1%; and LOW (management data), with dynamic bandwidth compression to 50% and a tolerance of 200ms latency.

[0015] Dynamic degradation mechanism: automatically reduces non-critical flow bandwidth in emergency situations, freeing up resources to ensure vital flow.

[0016] The present invention is further configured to include a voice control center for supporting voice commands of "displaying the laparoscope to screen No. 3" and "starting teaching recording", which are automatically parsed into routing strategies.

[0017] The present invention is further configured to include a policy template library for presetting a full set of routing rules for laparoscopic surgery and cardiac intervention scenarios, which can be loaded with one click.

[0018] The present invention is further configured to include a self-learning engine for recording the operator's operating habits and automatically optimizing the strategy template.

[0019] The present invention is further configured such that the routing control software system includes a dynamic bandwidth allocation algorithm, wherein the dynamic bandwidth allocation algorithm includes state machine modeling, defining a set of surgical stage states:

[0020] S={s1,s2,...,s n}={preparation, skin incision, separation, hemostasis, suturing, emergency intervention, teaching recording, ...}; each state s i Bind a bandwidth allocation strategy vector: Strategy(s i ) = [(stream type 1, priority 1, bandwidth range 1), (stream type 2, priority 2, bandwidth range 2), ...];

[0021] Stateful policy mapping formula:

[0022] f:S\rightarrow\mathbb{R}^m\quad\text{(m=number of stream types)};

[0023] f(s_i) = [b_{i1}, b_{i2},..., b_{im}];

[0024] where b ij represents the bandwidth allocation value of flow type j in state s i .

[0025] The application is further configured to include a state transition function in the dynamic bandwidth allocation algorithm, and the state transition is triggered by an event:

[0026] E = {e1, e2,..., e m} = {device alarm, voice instruction, timer timeout, operation step completion...};

[0027] State transition formula:

[0028] s_{t+1} = T(s_t, e_t) = \begin{cases}

[0029] s_{\text{emerg}} & \text{if} \exists a \in A: \text{severity}(a) > \theta_{\text{emerg}} \\

[0030] s_{\text{teach}} & \text{if} e_t = \text{"start_recording"} \\

[0031] s_{\text{normal}} & \text{otherwise}

[0032] \end{cases};

[0033] where: A = current active alarm set, θ em er g = emergency threshold (default 0.8).

[0034] The application is further configured to include a bandwidth allocation strategy in the dynamic bandwidth allocation algorithm, and the priority weighted allocation model:

[0035] BW_j = \frac{P_j^k \cdot D_j}{\sum_{i=1}^{n} P_i^k \cdot D_i} \times BW_{\text{total}};

[0036] where P j = priority of flow type j (1-10), D j = real-time demand coefficient of flow type j, k = priority amplification factor (default 2.0).

[0037] Demand factor calculation:

[0038] D_j = \alpha \cdot \frac{Q_{\text{current}}}{Q_{\text{max}}} + \beta \cdot \frac{\text{Latency}_{\text{current}}}{\text{Latency}_{\text{max}}} + \gamma \cdot \text{PriorityBoost}.

[0039] The application is further provided that the dynamic bandwidth allocation algorithm includes a dynamic adjustment mechanism, a real-time bandwidth fine-tuning algorithm:

[0040] \DeltaBW_j = \eta \cdot \left(\frac{\partialU}{\partialBW_j}\right) \cdot \Deltat;

[0041] wherein the utility function U is defined as:

[0042] U = \sum_{j=1}^{m} w_j \cdot \log(1 + \frac{BW_j}{BW_{j,\min}});

[0043] Gradient calculation:

[0044] \frac{\partialU}{\partialBW_j} = \frac{w_j}{BW_j + BW_{j,\min}}.

[0045] The application is further provided that the dynamic bandwidth allocation algorithm includes a state switching transition mechanism, a smooth transition algorithm:

[0046] BW_j(t) = BW_j^{\text{old}} \cdot e^{-\lambdat} + BW_j^{\text{new}} \cdot (1 - e^{-\lambdat});

[0047] wherein λ = transition rate factor (default 0.05 / ms); t = time elapsed after switching;

[0048] Transition constraint condition:

[0049] \left|\frac{dBW_j}{dt}\right| \leq \Gamma_j \quad \forall j;

[0050] wherein Γ jThe maximum allowed bandwidth variation rate for the flow type j.

[0051] The beneficial effects of the present application are:

[0052] 1. The digital smart operating room routing control software system, the system voice control, the operator directly issues "display endoscope to No. 3 screen" and the like instruction, the system responds in seconds (<1 second), without manual intervention. Strategy template preloading, automatically matching preset routing rules (such as "laparoscopic cholecystectomy template") according to operation scheduling, ready to use after starting. Operation and maintenance efficiency is improved: IT personnel only need to maintain the strategy template library, and the daily intervention demand is reduced by 90%.

[0053] 2. The digital smart operating room routing control software system, the platform protocol abstraction layer (PAL) supports 42+ kinds of medical device protocols (including HDMI / SDI / DICOM / private protocol, etc.), and the compatibility is ≥99.2%. FPGA hardware acceleration conversion, delay <5ms (traditional scheme >50ms), meeting the real-time requirement. No sense of access, when new equipment is accessed, the protocol is automatically identified and the analysis template is loaded, free of development and zero configuration.

[0054] 3. The digital smart operating room routing control software system, the state machine of the system makes real-time decisions, and quickly determines the operation stage (such as "emergency intervention") through device alarm, voice instruction and the like 200ms / time. Automatically trigger preset strategy (such as "vital sign flow bandwidth is increased to 20Mbps"), and the switching delay is ≤150ms. Dynamic resource allocation, in emergency state, the bandwidth of non-critical video stream is automatically degraded by 50%, and the life data is preferentially guaranteed. When teaching recording, the operating field video stream uses double-path redundancy, ensuring 4K quality and zero packet loss. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 The digital smart operating room routing control software system of the present application is a schematic diagram of a smart operating room;

[0056] Figure 2 The digital smart operating room routing control software system of the present application is a schematic diagram of a hardware system;

[0057] Figure 3 The digital smart operating room routing control software system of the present application is a schematic diagram of a software system;

[0058] Figure 4 The digital smart operating room routing control software system of the present application is a schematic diagram of a control software interface display. DETAILED DESCRIPTION

[0059] The technical solutions of the present application will be further described in detail in combination with specific embodiments.

[0060] Embodiments of the present patent are described below in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are only used to explain the present patent, and cannot be understood as a limitation on the present patent.

[0061] Referring to Figures 1-4 , the digital intelligent operating room routing control software system includes a dynamic perception mechanism; the dynamic perception mechanism collects five-dimensional data of operation progress, equipment alarm, voice instruction, network load and operator identity in real time, and judges the current operation stage (including skin incision, suture and emergency intervention) through a state machine engine;

[0062] An intelligent decision-making closed-loop mechanism; the intelligent decision-making closed-loop mechanism detects state changes every 200 milliseconds, automatically loads a preset strategy template, optimizes parameters through a genetic algorithm, and then issues flow table rules in real time through an SDN controller to form a "perception-decision-execution-monitoring" closed loop;

[0063] A protocol unified conversion three-layer architecture; including a protocol identification layer, based on deep packet inspection (DPI) and a feature signature library, automatically identifying 42 kinds of medical device private protocols; a data analysis layer using FPGA accelerated finite state machine, parallel analyzing different protocol data structures; a standard encapsulation layer, converting data into JSON-LD format with accurate time stamp, and injecting into a unified data bus;

[0064] A three-level hierarchical protection system; including a CRITICAL level (vital signs), a hard guarantee bandwidth ≥ 20 Mbps, a delay ≤ 30 ms, and a network congestion priority resource preemption; a HIGH level (operation field video), dual-path redundant transmission + forward error correction, frame loss rate < 0.1%; a LOW level (management data), bandwidth dynamically compressed to 50%, tolerant to 200 ms delay.

[0065] A dynamic degradation mechanism; in emergency state, automatically reduce the bandwidth of non-critical flow, release resources to protect vital signs flow.

[0066] In this embodiment, the voice control hub is used to support the "display endoscope to No. 3 screen" and "start teaching recording" voice instructions, and automatically analyze them into routing strategies; the strategy template library is used to preset a complete set of routing rules for laparoscopic surgery and cardiac intervention scenes, and one-key loading; the self-learning engine is used to record the operator's operation habits and automatically optimize the strategy template.

[0067] Further, the routing control software system includes a dynamic bandwidth allocation algorithm, which includes state machine modeling to define a set of operation stage states:

[0068] S={s1,s2,...,s n} = { preparation, skin incision, separation, hemostasis, suturing, emergency intervention, teaching recording,...}; each state s i Bind a bandwidth allocation strategy vector: Strategy(s i ) = [(flow type 1, priority 1, bandwidth range 1), (flow type 2, priority 2, bandwidth range 2),...];

[0069] State strategy mapping formula:

[0070] f: S -> Rm (m = number of flow types);

[0071] f(s_i) = [b_{i1}, b_{i2},..., b_{im}];

[0072] Where b ij represents the bandwidth allocation value of flow type j in state s i .

[0073] Dynamic bandwidth allocation algorithm includes state transition function, state transition triggered by event:

[0074] E = {e1, e2,..., e m} = {device alarm, voice instruction, timer timeout, operation step completion...};

[0075] State transition formula:

[0076] s_{t+1} = T(s_t, e_t) = \begin{cases}

[0077] s_{\text{emerg}} & \text{if} \exists a \in A: \text{severity}(a) > \theta_{\text{emerg}} \\

[0078] s_{\text{teach}} & \text{if} e_t = \text{"start_recording"} \\

[0079] s_{\text{normal}} & \text{otherwise}

[0080] \end{cases};

[0081] Where: A = current active alarm set, θ em er g = emergency threshold (default 0.8).

[0082] The dynamic bandwidth allocation algorithm includes a bandwidth allocation strategy, a priority weighted allocation model:

[0083] BW_j = \frac{P_j^k \cdot D_j}{\sum_{i=1}^{n} P_i^k \cdot D_i} \times BW_{total};

[0084] where P j = priority of flow type j (1-10), D j = real-time demand coefficient of flow type j, k = priority amplification factor (default 2.0);

[0085] Demand coefficient calculation:

[0086] D_j = \alpha \cdot \frac{Q_{current}}{Q_{max}} + \beta \cdot \frac{Latency_{current}}{Latency_{max}} + \gamma \cdot PriorityBoost.

[0087] The dynamic bandwidth allocation algorithm includes a dynamic adjustment mechanism, a real-time bandwidth fine-tuning algorithm:

[0088] \DeltaBW_j = \eta \cdot \left(\frac{\partial U}{\partial BW_j}\right) \cdot \Delta t;

[0089] where the utility function U is defined as:

[0090] U = \sum_{j=1}^{m} w_j \cdot \log(1 + \frac{BW_j}{BW_{j,min}});

[0091] Gradient calculation:

[0092] \frac{\partial U}{\partial BW_j} = \frac{w_j}{BW_j + BW_{j,min}}.

[0093] The dynamic bandwidth allocation algorithm includes a state switching transition mechanism, a smooth transition algorithm:

[0094] BW_j(t) = BW_j^{\text{old}}\cdot e^{-\lambdat} + BW_j^{\text{new}}\cdot (1 - e^{-\lambdat});

[0095] where λ = transition rate factor (default 0.05 / ms); t = time elapsed after switching;

[0096] Transition constraints:

[0097] \left|\frac{dBW_j}{dt}\right|\leq\Gamma_j\quad\forallj;

[0098] where Γ j is the maximum allowed bandwidth variation rate for flow type j.

[0099] The above algorithm realizes intelligent bandwidth allocation for critical scenarios in surgery through three mechanisms of state awareness, dynamic adjustment and smooth transition, which can improve bandwidth utilization by 35% and reduce critical flow delay by more than 40% compared with static allocation scheme.

[0100] Working principle: Deploy intelligent access gateway in the operating room, connect devices such as monitors and endoscopes, unify data formats through FPGA protocol conversion matrix, install dual SDN switch cluster, deploy master server to run routing control software; Real-time collection of device data, voice instructions and surgery scheduling information, determine the current surgery stage (such as skin incision, suture, emergency intervention) through state machine engine; Automatically match preset strategy templates (such as "give priority to vital signs flow in emergency state"); Routing optimization engine calculates the optimal path based on multi-objective algorithm, SDN controller issues flow table rules; Protocol abstraction layer (PAL) converts heterogeneous data in real time to ensure device interconnection; Visual interface displays network status and data flow in real time; QoS monitoring module dynamically adjusts bandwidth allocation, and switches to backup path within 10ms in case of failure.

[0101] The above is only the preferred specific embodiment of the present application, but the protection scope of the present application is not limited to this, any skilled person in the art can make equivalent replacement or change according to the technical solution and the inventive concept of the present application within the technical range disclosed by the present application, which should be covered in the protection scope of the present application.

Claims

1. Digital intelligent operating room routing control software system, characterized by: It includes a dynamic perception mechanism that collects five-dimensional data in real time: surgical progress, equipment alarms, voice commands, network load, and surgeon identity, and uses a state machine engine to determine the current surgical stage (including skin incision, suturing, and emergency intervention). Intelligent decision-making closed-loop mechanism: This mechanism detects state changes every 200 milliseconds, automatically loads a preset policy template, optimizes parameters using a genetic algorithm, and issues flow table rules in real time through the SDN controller, forming a "perception-decision-execution-monitoring" closed-loop. The three-layer architecture of unified protocol conversion includes a protocol identification layer that automatically identifies 42 medical device proprietary protocols based on deep packet inspection (DPI) and a signature library; a data parsing layer that uses an FPGA-accelerated finite state machine to parse data structures of different protocols in parallel. The standard encapsulation layer converts data into JSON-LD format with accurate timestamps and injects it into the unified data bus; Three-tiered security system; These include CRITICAL (vital signs) with guaranteed bandwidth ≥ 20Mbps, latency ≤ 30ms, and priority resource grabbing during network congestion; HIGH (surgical field video) with dual-path redundant transmission + forward error correction and a frame loss rate of < 0.1%. At the LOW level (for management data), the bandwidth is dynamically compressed to 50% and a 200ms delay is tolerated. Dynamic degradation mechanism: automatically reduces non-critical traffic bandwidth in an emergency, freeing up resources to ensure vital flow.

2. The digital intelligent operating room routing control software system according to claim 1 is characterized in that: It also includes a voice control center to support the voice commands of "display the laparoscope to screen 3" and "start teaching recording", which are automatically parsed into routing strategies.

3. The digital intelligent operating room routing control software system according to claim 2 is characterized in that: It also includes a policy template library for pre-setting a full set of routing rules for laparoscopic surgery and cardiac intervention scenarios, which can be loaded with one click.

4. The digital intelligent operating room routing control software system according to claim 3 is characterized in that: It also includes a self-learning engine to record the operator's operating habits and automatically optimize strategy templates.

5. The digital intelligent operating room routing control software system according to claim 1 is characterized in that: The routing control software system includes a dynamic bandwidth allocation algorithm, which includes state machine modeling and defines a set of surgical stage states: S={s1,s2,...,s n }={preparation, skin incision, separation, hemostasis, suturing, emergency intervention, teaching recording, ...}; each state s i Bind a bandwidth allocation strategy vector: Strategy(s i ) = [(stream type 1, priority 1, bandwidth range 1), (stream type 2, priority 2, bandwidth range 2), ...]; Stateful policy mapping formula: f:S\rightarrow\mathbb{R}^m\quad\text{(m=number of stream types)}; f(s_i)=[b_{i1},b_{i2},...,b_{im}]; Among them, b ij In state s i Bandwidth allocation value for downstream type j.

6. The digital intelligent operating room routing control software system according to claim 5 is characterized in that: The dynamic bandwidth allocation algorithm includes a state transition function, where the state transition is triggered by an event: E = {e1, e2, ..., em} = {device alarm, voice command, timer timeout, operation step completed...}; State transition formula: s_{t+1}=T(s_t,e_t)=\begin{cases} s_{\text{emerg}}&\text{if}\existsa\inA:\text{severity}(a)>\theta_{\text{emerg}}\\ s_{\text{teach}}&\text{if}e_t=\text{"start_recording"}\\ s_{\text{normal}}&\text{otherwise} \end{cases}; Where: A = current active alarm set, θ em erg = Emergency threshold (default 0.8).

7. The digital intelligent operating room routing control software system according to claim 6 is characterized in that: The dynamic bandwidth allocation algorithm includes a bandwidth allocation strategy and a priority weighted allocation model: BW_j=\frac{P_j^k\cdotD_j}{\sum_{i=1}^{n}P_i^k\cdotD_i}\timesBW_{\text{total}}; Among them, P j = Priority of flow type j (1-10), D j = real-time demand coefficient for flow type j, k = priority amplification factor (default 2.0); Demand factor calculation: D_j=\alpha\cdot\frac{Q_{\text{current}}}{Q_{\text{max}}}+\beta\cdot\frac{\text{Latency}_{\text{current}}}{\text{Lat ency}_{\text{max}}}+\gamma\cdot\text{PriorityBoost}.

8. The digital intelligent operating room routing control software system according to claim 7 is characterized in that: The dynamic bandwidth allocation algorithm includes a dynamic adjustment mechanism and a real-time bandwidth fine-tuning algorithm: \DeltaBW_j=\eta\cdot\left(\frac{\partialU}{\partialBW_j}\right)\cdot\Deltat; Among them, the utility function U is defined as: U=\sum_{j=1}^{m}w_j\cdot\log(1+\frac{BW_j}{BW_{j,\min}}); Gradient calculation: \frac{\partialU}{\partialBW_j}=\frac{w_j}{BW_j+BW_{j,\min}}.

9. The digital intelligent operating room routing control software system according to claim 8, characterized in that: The dynamic bandwidth allocation algorithm includes a state switching transition mechanism and a smooth transition algorithm: BW_j(t)=BW_j^{\text{old}}\cdote^{-\lambdat}+BW_j^{\text{new}}\cdot(1-e^{-\lambdat}); Where λ = transition rate factor (default 0.05 / ms); t = time elapsed after switching; Transition constraints: \left|\frac{dBW_j}{dt}\right|\leq\Gamma_j\quad\forallj; Among them, Γ j is the maximum allowed bandwidth change rate of flow type j.

Images