Method, system and device for realizing active noise reduction in treatment room and medium

Abstract

The embodiment of the invention provides a method, system and device for achieving active noise reduction in a treatment room and a medium, the treatment room comprises a treatment equipment group, and the method comprises the steps that independent noise generated when single treatment equipment in the treatment equipment group operates independently in an area to be subjected to noise reduction is collected; collecting mixed noise during operation of the treatment equipment group in the to-be-denoised area; the independent noise corresponding to the treatment equipment group is coupled to obtain coupled noise, and the coupled noise difference between the coupled noise and the mixed noise does not exceed a preset difference threshold value; and based on the coupled noise, active noise reduction is performed on the to-be-noise-reduced area during operation of the treatment equipment group.

Description

Technical Field

[0001] The present invention relates to the field of noise reduction, and in particular to a method, system, device and medium for realizing active noise reduction in a treatment room. Background Art

[0002] During radiotherapy, treatment equipment such as proton accelerators, energy reducers, multi-leaf collimators (or adaptive gratings) and other equipment will generate multi-field superposition noise during operation. For multi-field superposition noise, the method of installing damping materials in the treatment room is often used to reduce noise. This method is less versatile and cannot effectively reduce the complex noise in the actual radiotherapy process.

[0003] Therefore, it is hoped to provide a method, system, device and medium for realizing active noise reduction in the treatment room, which can effectively reduce the multi-sound field superposition noise in the treatment room, improve the patient's treatment experience, ensure smooth communication between doctors and patients during treatment or positioning, and assist in troubleshooting abnormal conditions of treatment equipment. Summary of the invention

[0004] One or more embodiments of the present specification provide a method for implementing active noise reduction in a treatment room, wherein the treatment room includes a group of treatment devices, and the method includes: collecting independent noise of a single treatment device in the group of treatment devices when it operates alone in an area to be noise reduced; the group of treatment devices includes at least two treatment devices; collecting mixed noise of the group of treatment devices in the area to be noise reduced when it operates; coupling the independent noise corresponding to the group of treatment devices to obtain coupled noise, wherein the difference between the coupled noise and the mixed noise does not exceed a preset difference threshold; and based on the coupled noise, performing active noise reduction on the area to be noise reduced when the group of treatment devices operates.

[0005] One or more embodiments of the present specification provide a system for implementing active noise reduction in a treatment room, the system comprising an acquisition module, a coupling module and a noise reduction module; the acquisition module is configured to acquire independent noise of a single treatment device in a treatment device group when operating alone and mixed noise of the treatment device group when operating in the area to be noise reduced; the coupling module is configured to couple the independent noise corresponding to the treatment device group to obtain coupled noise, wherein the difference between the coupled noise and the mixed noise does not exceed a preset difference threshold; the noise reduction module is configured to perform active noise reduction on the area to be noise reduced based on the coupled noise when the treatment device group is operating.

[0006] One or more embodiments of the present specification provide a device for implementing active noise reduction in a treatment room, the device comprising at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least part of the computer instructions to implement the method for implementing active noise reduction in the treatment room described in the above embodiments.

[0007] One or more embodiments of the present specification provide 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 for implementing active noise reduction in a treatment room as described in the above embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0009] Figure 1 is a schematic diagram of the platform structure of a system for realizing active noise reduction in a treatment room according to some embodiments of this specification;

[0010] Figure 2 is an exemplary flow chart of a method for implementing active noise reduction in a treatment room according to some embodiments of this specification;

[0011] Figure 3 is an exemplary flow chart of a round of coupling according to some embodiments of this specification;

[0012] Figure 4 is a schematic diagram of an exemplary process of determining abnormal devices according to some embodiments of this specification;

[0013] Figure 5 It is an exemplary schematic diagram of determining a preset period according to some embodiments of this specification. DETAILED DESCRIPTION

[0014] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly introduces the drawings required for describing the embodiments. The drawings do not represent all implementation methods.

[0015] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. If other words can achieve the same purpose, the words can be replaced by other expressions.

[0016] Unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0017] When the operations are performed according to the step description in the embodiments of this specification, unless otherwise specified, the order of the steps is interchangeable, the steps may be omitted, and other steps may be included in the operation process.

[0018] Figure 1 It is a schematic diagram of the platform structure of the system for implementing active noise reduction in the treatment room according to some embodiments of this specification.

[0019] like Figure 1 As shown, the active noise reduction implementation system 100 in the treatment room includes a collection module 110 , a coupling module 120 and a noise reduction module 130 .

[0020] The acquisition module is configured to acquire the independent noise of a single therapeutic device in the therapeutic device group when it is operating alone and the mixed noise of the therapeutic device group when it is operating in the noise reduction area. In some embodiments, the acquisition module includes a noise tester and the like.

[0021] The coupling module is configured to couple the independent noises corresponding to the treatment device group to obtain coupled noise, wherein the coupled noise difference between the coupled noise and the mixed noise does not exceed a preset difference threshold.

[0022] The noise reduction module is configured to actively reduce noise in the area to be reduced based on the coupled noise when the therapeutic device group is running. In some embodiments, the noise reduction module includes a sound generating device such as a sound generator that can generate anti-phase sound waves.

[0023] A treatment room is a space where patients are treated. The treatment room includes a treatment equipment group. The treatment equipment group includes at least two treatment devices. Treatment equipment refers to equipment that performs treatment methods such as radiotherapy or surgical treatment. For example, a proton accelerator, an energy reducer, a multi-leaf collimator, etc. Treatment equipment generates noise when treating patients, which may affect the treatment or the communication between doctors and patients during the treatment process.

[0024] In some embodiments, the active noise reduction implementation system 100 in the treatment room can represent each treatment device in the treatment device group by numbering or naming.

[0025] In some embodiments, the active noise reduction implementation system 100 in the treatment room further includes a processor and a memory. In some embodiments, the processor is configured to process information and / or data related to the active noise reduction implementation system 100 in the treatment room. In some embodiments, the processor includes a central processing unit (CPU), an application specific integrated circuit (ASIC), a digital signal processor (DSP), etc., or any combination thereof. The memory is configured to store information and / or data related to the active noise reduction implementation system 100 in the treatment room.

[0026] In some embodiments, the active noise reduction implementation system 100 in the treatment room collects the independent noise of a single treatment device in a treatment device group when operating alone and the mixed noise when the treatment device group is operating in the area to be noise reduced through the collection module, and then couples the independent noise corresponding to the treatment device group through the coupling module to obtain coupled noise. Based on the coupled noise, the noise reduction module sends an anti-phase sound wave to the area to be noise reduced when the treatment device group is operating, thereby achieving phase cancellation with the mixed noise and thus actively reducing noise.

[0027] For detailed description of the above, please refer to Figures 2 to 5 Related description.

[0028] By implementing active noise reduction in the treatment room, the system can effectively reduce the superimposed noise of multiple sound fields in the treatment room, improve the patient's treatment experience, and ensure smooth communication between doctors and patients during treatment or positioning.

[0029] It should be understood that Figure 1 The active noise reduction implementation system and its modules in the treatment room shown can be implemented in various ways. It should be noted that the above description of the active noise reduction implementation system and its modules in the treatment room is only for the convenience of description and cannot limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from this principle. In some embodiments, Figure 1 The acquisition module 110, coupling module 120 and noise reduction module 130 disclosed in the specification can be different modules in a system, or a module can realize the functions of two or more modules. For example, each module 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.

[0030] Figure 2 200 is an exemplary flow chart of a method for implementing active noise reduction in a treatment room according to some embodiments of this specification. In some embodiments, process 200 is performed by an active noise reduction implementation system in a treatment room (hereinafter referred to as a noise reduction system). Figure 2As shown, process 200 includes the following steps.

[0031] To ensure the noise reduction effect during the actual treatment process, the noise reduction system can perform steps 210-240 in the pre-acquisition stage to perform active noise reduction on the noise reduction area to simulate the active noise reduction during the actual treatment process and determine the noise reduction effect. The pre-acquisition stage refers to a period of time before the actual treatment process begins. The pre-acquisition stage is pre-set based on historical experience.

[0032] Step 210 , collecting independent noise of a single treatment device in the treatment device group when it operates independently in the area to be noise reduced.

[0033] Independent noise refers to the noise generated when a single treatment device in a treatment device group operates alone.

[0034] The area to be noise-reduced refers to the area in the treatment room where noise reduction is required. For example, the area where the patient receives treatment or the area where the patient communicates with the doctor. In some embodiments, the area to be noise-reduced is determined by the doctor based on actual treatment needs. The treatment needs include at least one of the treatment site, treatment duration, etc.

[0035] In some embodiments, the noise reduction system collects the independent noise of a single treatment device in a group of treatment devices when it operates alone in the area to be noise reduced through a collection module.

[0036] For a description of the active noise reduction system and its related modules in the treatment room, see Figure 1 and its related description.

[0037] Step 220: Collect the mixed noise of the treatment equipment group when they are running in the area to be de-noised.

[0038] Mixed noise refers to the noise generated by the superposition of multiple treatment devices in a treatment device group when they are in operation.

[0039] In some embodiments, if all treatment devices in the treatment room are used during the actual treatment process, the mixed noise includes the noise generated by the superposition of all treatment devices in the treatment device group when they are in operation.

[0040] In some embodiments, since different patients have different treatment needs, the working parameters of the treatment device in different treatment processes are also different. The noise reduction system can collect independent noise and mixed noise of the treatment device under different working parameters, and select the independent noise and mixed noise corresponding to the working parameters for coupling and active noise reduction during subsequent coupling and active noise reduction.

[0041] The operating parameters are determined by the doctor based on actual treatment needs, including at least one of the operating power and operating duration of the treatment device.

[0042] In some embodiments, the noise reduction system collects the mixed noise of the treatment equipment group when they are running in the area to be reduced through the collection module.

[0043] Step 230, coupling the independent noises corresponding to the treatment device group to obtain coupled noise.

[0044] Coupled noise refers to the noise obtained by coupling independent noise by the noise reduction system. In some embodiments, the noise reduction system couples the independent noise based on the coupling parameters through a preset coupling algorithm to obtain coupled noise. The preset coupling algorithm includes any feasible algorithm such as finite element analysis method, finite difference time domain method, spectral method, etc.

[0045] The coupling parameter refers to a parameter used for noise coupling. In some embodiments, the coupling parameter is represented by any feasible form such as a sequence, a matrix or a formula, including a plurality of coefficients corresponding to the acoustic wave characteristics. The acoustic wave characteristics include the frequency, phase and amplitude of the acoustic wave.

[0046] Exemplarily, the coupling parameters include (k1, k2, k3, ...), where k1 refers to a coefficient, vector or matrix for adjusting the frequency, k2 refers to a coefficient, vector or matrix for adjusting the phase, and k3 refers to a coefficient, vector or matrix for adjusting the amplitude. For more information about the coupling parameters, see Figure 3 and its related description.

[0047] In some embodiments, the difference between the coupled noise and the mixed noise does not exceed a preset difference threshold, which is preset based on historical experience.

[0048] In some embodiments, the coupling noise difference is used to characterize the degree of difference between the coupling noise and the mixed noise. The noise reduction system can construct feature vectors based on the coupled acoustic wave features and the mixed acoustic wave features, respectively, and calculate the similarity between the feature vectors corresponding to the two, and determine the coupling noise difference based on the similarity. The lower the similarity, the greater the coupling noise difference. Vector similarity is negatively correlated with vector distance. Vector distance includes Euclidean distance, etc.

[0049] The coupled acoustic wave characteristics refer to the acoustic wave characteristics of coupled noise. The mixed acoustic wave characteristics refer to the acoustic wave characteristics of mixed noise.

[0050] It can be understood that the mixed noise includes multiple sub-sound waves, each of which corresponds to the independent noise of a treatment device. Since the direct superposition of sound waves will cause mutual interference, resulting in changes in the sound wave characteristics of each sub-sound wave, it is impossible to obtain coupled noise by directly superimposing the independent noise corresponding to the treatment device group. By coupling the independent noise based on the coupling parameters, the mutual interference between multiple sub-sound waves in the mixed noise is simulated, and the coupling parameters are adjusted and coupled again based on the difference between the intermediate coupled noise and the mixed noise, finally a coupled noise is obtained in which the coupling noise difference does not exceed the preset difference threshold. At the same time, the coupled noise also includes multiple sub-sound waves, each of which corresponds to the independent noise of a treatment device. For an explanation of the intermediate coupled noise, see Figure 3 and its related description.

[0051] In order to assist in the subsequent investigation of abnormal devices, the noise reduction system can obtain the independent noise of a single treatment device separately and couple it to obtain coupled noise. Since multiple independent noises have simulated the mutual interference between sound waves when coupling, it is possible to directly couple the independent noise of some treatment devices and perform active noise reduction, and determine whether there are abnormal devices in some treatment devices based on the noise reduction effect. However, if the mixed noise is directly based on the inverted sound wave output for active noise reduction, each treatment device needs to be checked in turn to determine the abnormal device, which is inefficient. Therefore, it is more convenient to directly couple the independent noise of some treatment devices and perform active noise reduction, and determine whether there are abnormal devices in some treatment devices based on the noise reduction effect. For instructions on determining abnormal devices, see Figure 4 and its related description.

[0052] In some embodiments, the coupling of the independent noise by the noise reduction system includes multiple rounds of coupling. For a description of multiple rounds of coupling, see Figure 3 and its related description.

[0053] Step 240: Based on the coupled noise, active noise reduction is performed on the area to be noise reduced when the treatment device group is running.

[0054] Active noise reduction is a method of achieving noise reduction by emitting anti-phase sound waves (also called reverse sound waves) to cancel out the phase of mixed noise. Anti-phase sound waves refer to sound waves used to achieve noise reduction. The relationship between the sound wave characteristics of the anti-phase sound waves and the mixed sound wave characteristics of the mixed noise is that the waveforms of the anti-phase sound waves and the mixed noise are opposite. Specifically, the anti-phase sound waves and the mixed noise have the same frequency and amplitude but opposite phases.

[0055] In some embodiments, the noise reduction system can obtain an anti-phase sound wave based on the coupled noise in a variety of ways. For example, the noise reduction system reverses the phase of the coupled noise by 180 degrees to obtain an anti-phase sound wave. For another example, the noise reduction system reverses the phase of each sub-sound wave in the coupled noise by 180 degrees to obtain an anti-phase sub-sound wave, thereby obtaining an anti-phase sound wave.

[0056] It can be understood that since the coupled noise is obtained based on the mutual interference between multiple sub-acoustic waves in the simulated mixed noise, after the phases of the multiple sub-acoustic waves in the coupled noise are reversed, the frequency and amplitude in the coupled noise characteristics will not change, only the phase will change.

[0057] In some embodiments, the noise reduction system uses a sound-generating device in the noise reduction module to continuously emit anti-phase sound waves to the area to be noise reduced when the treatment device group is running, so as to achieve active noise reduction.

[0058] In some embodiments, the noise reduction system can also collect the first noise after active noise reduction, and determine the actual noise difference between the real-time noise of the area to be noise reduced and the first noise during the actual treatment process, and judge the noise reduction effect based on the actual noise difference.

[0059] The first noise refers to the noise in the area to be reduced noise after active noise reduction is performed on the area to be reduced noise in the pre-collection stage. In some embodiments, the noise reduction system can collect the noise in the area to be reduced noise as the first noise through the collection module after active noise reduction is performed on the area to be reduced noise.

[0060] Real-time noise refers to the noise in the area to be reduced after active noise reduction based on coupled noise during the actual treatment process. In some embodiments, the noise reduction system can collect the noise in the area to be reduced as real-time noise through the collection module during the actual treatment process.

[0061] The actual noise difference is used to characterize the difference between the real-time noise and the first noise. In some embodiments, the method of determining the actual noise difference is similar to the method of determining the coupling noise difference. The implementation method thereof refers to the method of determining the coupling noise difference in step 230.

[0062] In some embodiments, the noise reduction effect may be negatively correlated to the actual noise difference. If the actual noise difference is smaller, the noise reduction system determines that the noise reduction effect is better. The noise reduction effect may be represented by a numerical value or the like.

[0063] In some embodiments, in response to the noise reduction effect exceeding the effect threshold, the noise reduction system can continue to actively reduce noise in the noise reduction area during subsequent treatment. In response to the noise reduction effect not exceeding the effect threshold, the noise reduction system can issue a prompt to the doctor to remind the doctor that the current noise reduction effect is insufficient. The effect threshold is pre-set based on historical experience. The prompt method includes but is not limited to sound prompts or text prompts.

[0064] In some embodiments, in response to the actual noise difference satisfying the difference condition, the noise reduction system can determine an abnormal device based on the partial coupled noise and the second noise. Figure 4 and its related description.

[0065] The actual noise difference can accurately reflect the difference between the noise obtained by noise reduction during the actual treatment process and the noise after active noise reduction in the pre-acquisition stage. Through the actual noise difference, the noise reduction effect can be accurately judged, thereby achieving effective noise reduction during the treatment process.

[0066] By coupling independent noises, a coupled noise that is highly similar to the mixed noise can be obtained. At the same time, based on the coupled noise, effective noise reduction can be achieved in the noise reduction area, thereby improving the patient's treatment experience and ensuring smooth communication between doctors and patients during treatment or positioning.

[0067] In some embodiments, the noise reduction system may group the therapeutic device group into one or more device groups, wherein a single device group includes at least two therapeutic devices.

[0068] In some embodiments, for a single device group, the noise reduction system can collect part of the mixed noise in the area to be noise reduced when the single device group is running alone, and couple the independent noise corresponding to the single device group to obtain partial coupled noise. The noise reduction system can also perform active noise reduction in the area to be noise reduced based on the partial coupled noise when the single device group is running alone, and collect the second noise after the active noise reduction, and judge the noise reduction effect based on the second noise.

[0069] In some embodiments, the noise reduction system can group the therapeutic device groups in a variety of ways. For example, the noise reduction system can group the therapeutic device groups randomly. For another example, the noise reduction system can group the therapeutic device groups in a binary manner.

[0070] Exemplarily, the process of using the dichotomy method for grouping in the noise reduction system includes: dividing a part (such as half or nearly half) of the therapeutic devices in the therapeutic device group into a primary device group, and treating the other part of the therapeutic devices as another primary device group, and subsequently treating a part of the therapeutic devices in each primary device group as a secondary device group, and treating the other part of the therapeutic devices as another secondary device group, and repeating the above division operation for each secondary device group to obtain multiple tertiary device groups, until the number of therapeutic devices included in a single device group does not exceed a first preset number threshold, and is not less than a second preset number threshold. The first preset number threshold and the second preset number are preset based on historical experience. The second preset number threshold is less than the first preset number threshold.

[0071] Single device group independent operation means that only the treatment devices within a single device group are in operation.

[0072] Partial mixed noise refers to the noise generated when a single device group operates independently.

[0073] Partially coupled noise refers to the noise obtained by coupling the independent noise corresponding to a single device group. The independent noise corresponding to a single device group includes the independent noise collected by each treatment device in the single device group in step 210. Each device group corresponds to a partially mixed noise and a partially coupled noise.

[0074] In some embodiments, each level device group (such as a level one device group, a level two device group, etc.) corresponds to a partial mixed noise and a partial coupled noise.

[0075] In some embodiments, the group noise difference between the partial coupling noise and the partial mixed noise does not exceed a preset difference threshold. For an explanation of the preset difference threshold and coupling, see step 230 and its related description.

[0076] The group noise difference is used to characterize the difference between the partial coupling noise and the partial mixed noise. In some embodiments, the method of determining the group noise difference is similar to the method of determining the coupling noise difference. The implementation method thereof refers to the method of determining the coupling noise difference in step 230.

[0077] The second noise refers to the noise in the area to be reduced after active noise reduction is performed on the area to be reduced when a single device group is running alone based on partial coupling noise. In some embodiments, the noise reduction system can perform active noise reduction on the area to be reduced when a single device group is running alone based on partial coupling noise, and collect the noise in the area to be reduced as the second noise through the collection module.

[0078] In some embodiments, the noise reduction system may determine a partial noise difference between the second noise and a portion of the real-time noise based on the second noise, and determine the noise reduction effect based on the partial noise difference.

[0079] Partial real-time noise refers to the noise of the area to be reduced in the actual treatment process after active noise reduction is performed based on partial coupled noise. Partial noise difference is used to characterize the degree of difference between the second noise and the partial real-time noise. The noise reduction system can collect partial real-time noise after active noise reduction is performed on the area to be reduced based on partial coupled noise during the treatment process.

[0080] In some embodiments, the method of determining partial noise difference and judging the noise reduction effect based on the partial noise difference is similar to the method of determining actual noise difference and judging the noise reduction effect based on the actual noise difference. For its implementation method, see step 240 and its related description.

[0081] By grouping the treatment equipment groups, actively reducing noise for each equipment group and judging the noise reduction effect, it is possible to meet the noise reduction needs when only some treatment equipment is turned on, and it is also beneficial to subsequently identify abnormal equipment in the treatment equipment group.

[0082] In some embodiments, the noise reduction system may re-execute steps 210 - 230 at every preset period to update the coupling noise.

[0083] It is understandable that after a treatment device has been running for a long time, the acoustic wave characteristics of the mixed noise will change due to mechanical aging or errors, and the noise reduction effect of the anti-phase sound wave generated based on the past coupled noise will deteriorate. Therefore, it is necessary to re-collect the independent noise of each treatment device and couple it, and then determine the new anti-phase sound wave to ensure the noise reduction effect.

[0084] In some embodiments, the preset period can be preset based on historical experience, such as one week.

[0085] In some embodiments, the noise reduction system may also determine a preset period based on future noise in the future noise sequence that meets a preset screening condition. Figure 5 and its related description.

[0086] By periodically updating the coupling noise, it can be ensured that the anti-phase sound waves generated based on the coupling noise can continue to effectively reduce the noise in the area to be reduced.

[0087] In some embodiments, the noise reduction system may also determine the probability of failure corresponding to the therapeutic device group based on the historical independent noise corresponding to the therapeutic device group.

[0088] The historical independent noise corresponding to the treatment device group includes the historical independent noise of each treatment device in the treatment device group. The historical independent noise refers to the independent noise of the treatment device collected within multiple rounds of preset cycles.

[0089] In some embodiments, the noise reduction system can extract the acoustic wave features of independent noise within multiple preset cycles, construct a historical noise sequence in chronological order based on multiple acoustic wave features, and store the historical noise sequence as the historical independent noise of the treatment device in a memory.

[0090] The failure probability is used to characterize the probability of a treatment device failing at a first future time. The first future time is preset based on historical experience, for example, one month in the future.

[0091] The failure probability corresponding to the treatment device group includes the failure probability of each treatment device in the treatment device group.

[0092] In some embodiments, the noise reduction system can determine the fault probability corresponding to the treatment device group in a variety of ways based on the historical independent noise corresponding to the treatment device group. For example, the noise reduction system queries the preset probability table corresponding to the type of treatment device based on the historical noise sequence of the treatment device, and uses the reference fault probability corresponding to the historical noise sequence as the fault probability of the treatment device. The noise reduction system determines the fault probability of each treatment device in the treatment device group by the above method.

[0093] In some embodiments, a preset probability table is pre-constructed based on historical data, and each type of treatment device corresponds to a preset probability table. The preset probability table includes reference failure probabilities corresponding to the corresponding treatment device under multiple historical noise sequences. It is understandable that for a type of treatment device, multiple such treatment devices may be used or replaced during historical treatment. The noise reduction system can count the historical independent noise of the used treatment devices of this type and construct multiple historical noise sequences.

[0094] In some embodiments, the noise reduction system can determine the reference fault probability corresponding to the historical noise sequence based on the actual fault time of the treatment device corresponding to the historical noise sequence in the historical data. For example, if the actual fault time is within the preset historical time period corresponding to the treatment device, the reference fault probability is 1, if the actual fault time is later than the preset historical time period and earlier than the preset historical time point, the reference fault probability is between 1-0, and if the actual fault time is later than the preset historical time point, the reference fault probability is 0. Among them, the preset historical time period refers to a period of time after the independent noise of the treatment device is collected within the historical time. The preset historical time point is preset based on historical experience. The preset historical time point is later than the preset historical time period.

[0095] Exemplarily, the preset historical period is one month after the independent noise of the treatment device is collected, and the preset historical time point is one year after the independent noise of the treatment device is collected. If the actual failure time is within one month after the independent noise of the treatment device is collected, the reference failure probability is 1. If the actual failure time is between one month and one year after the independent noise of the treatment device is collected, the reference failure probability is between 1-0. If the actual failure time exceeds one year after the independent noise of the treatment device is collected, the reference failure probability is 0.

[0096] In some embodiments, if the actual fault time is later than the preset historical period and earlier than the preset historical time point, the closer the actual fault time is to the preset historical time point, the closer the reference fault probability is to zero.

[0097] For another example, the noise reduction system may also determine the failure possibility of each treatment device in the treatment device group through the first prediction model based on the historical independent noise corresponding to the treatment device group.

[0098] The first prediction model refers to a model used to determine the possibility of a fault. In some embodiments, the first prediction model may be a machine learning model. For example, the first prediction model includes any one or combination of a long short-term memory network (LSTM) model or other custom model structures.

[0099] In some embodiments, the input to the first predictive model may include historical independent noise of the treatment device and the output may include the probability of failure.

[0100] In some embodiments, the noise reduction system can train a first prediction model based on a large number of first training samples with first labels by a gradient descent method or the like. The first training sample includes sample historical independent noise of the sample treatment device, and the first label of the first training sample includes a reference fault probability corresponding to the sample treatment device. The first training sample is obtained based on historical data. The first label is determined in a manner similar to the above-mentioned manner of determining the reference fault probability.

[0101] In some embodiments, the first prediction model can be trained in the following manner: multiple first training samples with first labels are input into the initial first prediction model, a loss function is constructed by the first label and the prediction result of the initial first prediction model, the initial first prediction model is updated based on the iteration of the loss function, and the first prediction model training is completed when the loss function of the initial first prediction model meets the preset condition. The preset condition may be that the loss function converges, the number of iterations reaches a set value, etc.

[0102] In some embodiments, after determining the fault possibility corresponding to the treatment device group, the noise reduction system can send the fault possibility corresponding to the treatment device group to a technician for inspection and the like.

[0103] By predetermining the possibility of failure of treatment equipment, the treatment equipment that may fail can be repaired in a timely manner to ensure the normal use of the treatment equipment.

[0104] Figure 3 is an exemplary flow chart of a round of coupling according to some embodiments of this specification. In some embodiments, the coupling of independent noise by the noise reduction system includes multiple rounds of coupling, wherein the process of a round of coupling is as follows: Figure 3 As shown, process 300 includes the following steps.

[0105] Step 310 , coupling the independent noise based on the current round coupling parameters to obtain the intermediate coupled noise.

[0106] The current round coupling parameters are the coupling parameters used in this round of coupling. For a description of the coupling parameters, see Figure 2and its related description.

[0107] In some embodiments, the noise reduction system multiplies the independent noise corresponding to the treatment device group by the current round coupling parameter, so that the acoustic wave characteristics of the independent noise corresponding to the treatment device group are changed, and the independent noise corresponding to the treatment device group is coupled through a preset coupling algorithm to obtain an intermediate coupled noise. For a description of the acoustic wave characteristics and the preset coupling algorithm, see Figure 2 and its related description.

[0108] Intermediate coupling noise refers to the coupling noise obtained in a round of coupling. Each round of coupling can obtain an intermediate coupling noise.

[0109] Step 320 : determining whether a coupling stop condition is satisfied based on an intermediate noise difference between the intermediate coupling noise and the mixed noise.

[0110] The intermediate noise difference is used to characterize the difference between the intermediate coupling noise and the mixed noise. In some embodiments, the method of determining the intermediate noise difference is similar to the method of determining the coupling noise difference. The implementation method thereof is shown in FIG. Figure 2 The method for determining the difference in coupled noise in .

[0111] The coupling stop condition is used to determine whether to stop coupling. In some embodiments, the coupling stop condition includes that the intermediate noise difference does not exceed a preset difference threshold. For an explanation of the preset difference threshold, see Figure 2 and its related description.

[0112] In some embodiments, if the intermediate noise difference does not satisfy the coupling stop condition, the noise reduction system executes step 330 , and if the intermediate noise difference satisfies the coupling stop condition, the noise reduction system executes step 340 .

[0113] Step 330: Update the coupling parameters of this round and perform the next round of coupling.

[0114] In some embodiments, the noise reduction system updates the current round coupling parameters in a variety of ways. For example, the noise reduction system obtains new current round coupling parameters by manually adjusting and inputting coupling parameters by the doctor.

[0115] For another example, the noise reduction system searches for reference coupling parameters corresponding to the intermediate noise difference in a preset feature table based on the intermediate noise difference, and uses the reference coupling parameters as new current round coupling parameters. In some embodiments, the preset feature table is constructed based on experimental data.

[0116] Exemplarily, the experimental process includes: acquiring sample intermediate coupling noise and sample mixed noise based on historical data, and setting multiple coupling parameters based on the sample intermediate noise difference, coupling based on the multiple coupling parameters to obtain multiple coupling noises, and using the coupling parameter corresponding to the coupling noise with the smallest noise difference with the sample mixed noise among the multiple coupling noises as the reference coupling parameter corresponding to the sample intermediate noise difference, and recording the sample intermediate noise difference and the reference coupling parameter in a preset feature table.

[0117] For another example, the noise reduction system can also determine the target coupling parameters based on the intermediate coupling noise and the mixed noise through a parameter determination model. Based on the target coupling parameters, the noise reduction system can directly couple to obtain the intermediate coupling noise whose intermediate noise difference satisfies the coupling stop condition.

[0118] The parameter determination model refers to a model used to determine the target coupling parameters. In some embodiments, the parameter determination model may be a machine learning model. For example, the parameter determination model includes any one or combination of a convolutional neural network (CNN) model, a recurrent neural network (RNN) model, or other custom model structures.

[0119] In some embodiments, the input of the parameter determination model includes the intermediate coupling noise and the mixed noise, and the output includes the determined target coupling parameters.

[0120] In some embodiments, the noise reduction system can determine the model based on a large number of second training samples with second labels by training parameters such as gradient descent method. The second training samples include sample intermediate coupling noise and sample mixed noise, and the second labels of the second training samples include the current round coupling parameters actually used later.

[0121] In some embodiments, the second training sample and the second label can be obtained based on historical data. For example, the noise reduction system screens multiple historical coupling processes, and the coupling rounds are less than the number threshold of historical coupling processes, and the historical intermediate coupling noise and historical mixed noise of such historical coupling processes are used as the second training sample, and the current round coupling parameters actually used in the historical coupling process are used as the second label.

[0122] It can be understood that the smaller the number of coupling rounds is, the more effective the coupling parameters of this round are, and the coupling noise can be obtained faster.

[0123] In some embodiments, the training process of the parameter determination model is similar to the training process of the first prediction model, and its training process refers to the training process of the first prediction model.

[0124] Step 340: End the coupling and determine the intermediate coupling noise as coupling noise.

[0125] In some embodiments, if the intermediate noise difference satisfies the coupling stop condition, the noise reduction system ends the coupling and determines the intermediate coupling noise as the coupling noise.

[0126] By performing multiple rounds of coupling on independent noises based on coupling parameters and continuously adjusting the coupling parameters, it is eventually possible to obtain coupled noise with the smallest noise difference from the mixed noise, thereby ensuring the optimization of the noise reduction effect and improving the noise reduction accuracy and stability of the noise reduction system.

[0127] Figure 4 FIG. 1 is a schematic diagram of an exemplary process for determining abnormal devices according to some embodiments of this specification. Figure 4 As shown, process 400 includes the following steps.

[0128] Step 410: determine whether the actual noise difference between the real-time noise in the area to be de-noised and the first noise satisfies the difference condition. Figure 2 and its related description.

[0129] The difference condition refers to a condition for determining whether an abnormal device needs to be determined. In some embodiments, the difference condition includes that the actual noise difference is greater than a first abnormal threshold. The first abnormal threshold is preset based on historical experience.

[0130] In some embodiments, if the actual noise difference satisfies the difference condition, the noise reduction system performs step 420. If the actual noise difference does not satisfy the difference condition, the noise reduction system performs step 430.

[0131] Step 420: determining an abnormal device based on the portion of the real-time noise and the second noise.

[0132] Abnormal equipment refers to abnormal treatment equipment. It is understandable that if the treatment equipment is abnormal, the acoustic characteristics of the independent noise generated by the treatment equipment will change, resulting in a larger difference in actual noise and a reduced noise reduction effect. Among them, abnormality is different from failure. Abnormality includes equipment aging or errors exceeding the error threshold, while failure means that the treatment equipment cannot operate. The error threshold is pre-set based on historical experience.

[0133] In some embodiments, the noise reduction system can determine abnormal devices based on partial real-time noise and second noise. For example, the noise reduction system determines the partial noise difference between partial real-time noise and second noise based on the partial real-time noise and second noise corresponding to each primary device group, and in response to the partial noise difference being greater than the second abnormal threshold, it is determined that there is an abnormal device in the primary device group, and the secondary device group under the primary device group is searched for abnormal devices by repeating the above process until it is determined that the abnormal device exists in a device group whose number of devices is less than the number threshold. The number threshold is preset based on historical experience.

[0134] In some embodiments, if the noise reduction system determines that an abnormal device exists in a device group in which the number of devices is less than a threshold number, the real-time independent noise of each treatment device in the device group is collected during the treatment process, and the acoustic wave characteristics are compared with the independent noise corresponding to each treatment device. If the difference in the acoustic wave characteristics is greater than a characteristic difference threshold, the treatment device corresponding to the independent noise whose acoustic wave characteristics are greater than the characteristic difference threshold is determined as an abnormal device.

[0135] Real-time independent noise refers to the independent noise of the treatment device collected after the actual treatment is completed. The acquisition method is similar to the method of acquiring independent noise. The comparison of acoustic wave features is achieved by constructing feature vectors corresponding to the acoustic wave features and calculating vector similarity. The difference in acoustic wave features is represented by vector similarity. The feature difference threshold is pre-set based on historical experience.

[0136] For a description of device groups, partial real-time noise, secondary noise, and partial noise differences, see Figure 2 and its related description.

[0137] In some embodiments, if there are fewer treatment devices in the treatment device group, the noise reduction system can also compare the sound wave characteristics between the real-time independent noise and the independent noise of each treatment device in turn, and determine the treatment device corresponding to the different sound wave characteristics as an abnormal device.

[0138] Step 430: Determine the noise reduction effect based on the actual noise difference. Figure 2 and its related description.

[0139] By judging whether the actual noise difference meets the difference condition, it is possible to quickly determine whether there is an abnormal device to avoid affecting the treatment effect due to device problems. At the same time, compared with checking each treatment device, determining the abnormal device based on the partial real-time noise corresponding to different device groups and the second noise can improve the efficiency of determining the abnormal device.

[0140] In some embodiments, before determining the abnormal device, the noise reduction system can determine that there is no abnormal device based on the real-time noise, the first noise, and the historical independent noise corresponding to the treatment device group. For example, the noise reduction system determines that there is no abnormal device through an abnormality troubleshooting model based on the real-time noise, the first noise, and the historical independent noise corresponding to the treatment device group. A non-abnormal device refers to a device that does not have an abnormality.

[0141] The abnormality troubleshooting model refers to a model used to determine the devices without abnormalities. In some embodiments, the abnormality troubleshooting model can be a machine learning model. For example, the abnormality troubleshooting model includes any one or combination of a convolutional neural network (CNN) model or other customized model structures.

[0142] In some embodiments, the input of the abnormality troubleshooting model may include real-time noise, first noise, and historical independent noise corresponding to the treatment device group, and the output may include the number or name of the device without abnormality.

[0143] In some embodiments, the noise reduction system can train an abnormality detection model based on a large number of third training samples with third labels by gradient descent method or the like. The third training samples can include sample real-time noise of the sample treatment device group, sample first noise, and historical independent noise corresponding to the sample treatment device group, and the third label of the third training sample can be an actual non-abnormal device. The third training sample can be obtained based on historical data.

[0144] In some embodiments, the third label is determined by collecting independent noise again. For example, the noise reduction system collects independent noise again for each sample treatment device in the sample treatment device group, compares the acoustic wave characteristics of the newly collected independent noise with the independent noise collected when the treatment device was normal in the past, and determines the sample treatment device whose acoustic wave characteristic difference is less than the characteristic difference threshold as a normal device.

[0145] In some embodiments, the training process of the anomaly detection model is similar to the training process of the first prediction model, and its training process refers to the training process of the first prediction model.

[0146] By determining that there are no abnormal devices before determining abnormal devices, the workload of determining abnormal devices can be reduced and the efficiency of determining abnormal devices can be improved.

[0147] It should be noted that the above descriptions of process 200, process 300 and process 400 are only for example and illustration, and do not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0148] Figure 5 It is an exemplary schematic diagram of determining a preset period according to some embodiments of this specification.

[0149] In some embodiments, the noise reduction system can estimate the future noise sequence 530 based on the coupled noise 510 and the historical independent noise 520 corresponding to the treatment device group, and determine the preset period 550 based on the future noise 540 in the future noise sequence 530 that meets the preset screening condition. For an explanation of the coupled noise and the historical independent noise corresponding to the treatment device group, see Figure 2 and its related description.

[0150] The future noise sequence refers to a sequence composed of future noises. The future noise refers to the first noise predicted at the second future time after active noise reduction. In some embodiments, the second future time includes multiple future time periods, each future time period corresponding to a future noise. The second future time is preset based on historical experience, such as every day of the next week. The second future time is within the first future time. For an explanation of the first noise, see Figure 2 and its related description.

[0151] The second prediction model refers to a model for determining the future noise sequence. In some embodiments, the second prediction model may be a machine learning model. For example, the second prediction model may include any one or combination of a convolutional neural network (CNN) model or other custom model structures.

[0152] In some embodiments, the noise reduction system can train the second prediction model based on a large number of fourth training samples with fourth labels by gradient descent method, etc. The fourth training sample includes the sample coupled noise of the sample treatment device group at the second time point and the historical independent noise corresponding to the first time point, and the fourth label of the fourth training sample includes the future noise sequence corresponding to the sample treatment device group at the third time point. The first time point is earlier than the second time point, and the second time point is earlier than the third time point.

[0153] In some embodiments, the fourth training sample and the fourth label are determined based on historical data. For example, the noise reduction system uses the historical coupled noise at the first historical time in the historical data and the historical independent noise corresponding to the historical treatment device group as the fourth training sample, and uses multiple historical first noises after the second historical time as the future noise sequence corresponding to the fourth training sample. The second historical time is later than the first historical time.

[0154] The preset screening condition is used to screen the future noise in the future noise sequence. In some embodiments, the preset screening condition includes that the similarity between the future noise and the first noise is less than a preset similarity threshold. The noise reduction system constructs feature vectors based on the acoustic wave characteristics of the future noise and the acoustic wave characteristics of the first noise, respectively, and calculates the similarity between the feature vectors as the similarity between the future noise and the first noise. The preset similarity threshold is preset based on historical experience.

[0155] In some embodiments, the noise reduction system selects future noise that meets the preset screening condition in the future noise sequence, and determines the preset time period based on the future time period corresponding to the future noise. For example, the noise reduction system counts the future time period closest to the current time in the future time period corresponding to the future noise that meets the preset screening condition, and determines the duration between the start time of the future time period and the current time as the preset time period.

[0156] In some embodiments, the preset screening condition is related to the fault probability corresponding to the treatment device group. For example, the preset similarity threshold in the preset screening condition is positively correlated to the fault probability corresponding to the treatment device group.

[0157] In some embodiments, the noise reduction system can determine a preset similarity threshold value through a preset formula based on the failure probability of the treatment device group. Exemplarily, the preset formula is shown in the following formula (1): S=Σ (ki*Ai) (1)

[0158] Wherein, S represents a preset similarity threshold, Ai represents the failure possibility of the i-th treatment device, ki represents the coefficient of the i-th treatment device, i ranges from 1 to n, and n is the total number of treatment devices in the treatment device group.

[0159] When determining the preset similarity threshold, the possibility of failure of multiple treatment devices is taken into consideration, thereby increasing the preset similarity threshold and shortening the preset period, thereby ensuring the timely update of the coupled noise and the noise reduction effect during the treatment process.

[0160] By coupling the noise and the historical independent noise corresponding to the treatment equipment group, the future noise reduction effect of the area to be reduced is predicted, which is conducive to timely updating the coupling parameters when the noise reduction effect deteriorates to ensure a stable noise reduction effect.

[0161] Some embodiments of the present specification also provide a device for implementing active noise reduction in a treatment room, the device comprising at least one processor and at least one memory, the at least one memory being used to store computer instructions, and the at least one processor being used to execute at least part of the computer instructions to implement the method for implementing active noise reduction in the treatment room described in any of the above embodiments.

[0162] Some embodiments of the present specification also provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method for implementing active noise reduction in a treatment room as described in any of the above embodiments.

[0163] Furthermore, certain features, structures or characteristics in one or more embodiments of this specification may be appropriately combined.

[0164] In some embodiments, numbers describing the number of components and attributes are used. 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 specified, "about", "approximately" or "substantially" indicates that the numbers are allowed to vary by ±20%. Accordingly, if the descriptions, definitions, and / or use of terms in the referenced materials of this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

Claims

1. A method for implementing active noise reduction in a treatment room, characterized in that: The treatment room includes a group of treatment equipment, and the method includes: Collecting independent noise of a single therapeutic device in the therapeutic device group when it is operating alone in the area to be noise reduced; the therapeutic device group includes at least two therapeutic devices; Collecting mixed noise in the area to be noise-reduced when the group of treatment devices are operating; The independent noises corresponding to the treatment device group are coupled to obtain coupled noise, wherein a difference between the coupled noise and the coupled noise of the mixed noise does not exceed a preset difference threshold; Based on the coupled noise, active noise reduction is performed on the area to be noise reduced when the treatment device group is running.

2. The method according to claim 1, characterized in that The method further comprises: collecting the first noise after the active noise reduction, and determining the actual noise difference between the real-time noise of the area to be noise reduced and the first noise during the treatment process; The noise reduction effect is determined based on the actual noise difference.

3. The method according to claim 1, characterized in that The coupling includes multiple rounds of coupling, wherein a process of one round of coupling includes: The independent noise is coupled based on the current round coupling parameters to obtain intermediate coupled noise; determining whether a coupling stop condition is satisfied based on an intermediate noise difference between the intermediate coupling noise and the mixed noise; In response to not meeting the coupling stop condition, updating the current round coupling parameters and performing the next round of coupling; In response to the coupling stop condition being met, coupling is terminated, and the intermediate coupling noise is determined as the coupling noise.

4. The method according to claim 1, characterized in that The method further comprises: Grouping the therapeutic device group to obtain one or more device groups, wherein a single device group includes at least two therapeutic devices; For the single device group: Collecting part of the mixed noise in the area to be noise reduced when the single device group operates alone; The independent noise corresponding to the single device group is coupled to obtain partial coupled noise, wherein a group noise difference between the partial coupled noise and the partial mixed noise does not exceed the preset difference threshold; Based on the partial coupled noise, when the single device group operates alone, the active noise reduction is performed on the area to be noise reduced, and a second noise after the active noise reduction is collected; Based on the group noise difference, the noise reduction effect is determined.

5. The method according to claim 4, characterized in that The method further comprises: In response to the actual noise difference between the real-time noise of the area to be noise reduced and the first noise satisfying a difference condition, an abnormal device is determined based on part of the real-time noise and the second noise.

6. The method according to claim 1, characterized in that The method further comprises: The coupling noise is updated at every preset period.

7. The method according to claim 1, characterized in that The method further comprises: Based on the historical independent noise corresponding to the therapeutic device group, the failure probability corresponding to the therapeutic device group is determined.

8. A system for realizing active noise reduction in a treatment room, characterized in that: The system includes an acquisition module, a coupling module and a noise reduction module; The acquisition module is configured to acquire independent noise when a single therapeutic device in a therapeutic device group is operating alone and mixed noise when the therapeutic device group is operating in the area to be de-noised; The coupling module is configured to couple the independent noises corresponding to the treatment device group to obtain coupled noise, wherein a difference between the coupled noise and the coupled noise of the mixed noise does not exceed a preset difference threshold; The noise reduction module is configured to perform active noise reduction on the area to be reduced in noise based on the coupled noise when the therapeutic device group is in operation.

9. A device for realizing active noise reduction in a treatment room, characterized in that: The apparatus comprises at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is configured to execute at least part of the computer instructions to implement the method for implementing active noise reduction in a treatment room according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the method for implementing active noise reduction in a treatment room as described in any one of claims 1 to 7.

Images