Signal recognition method and related apparatus

Abstract

The application provides a signal identification method and related device, the method is applied to an electronic device, the method comprises the following steps: obtaining a target drop signal of a current infusion process; obtaining a preset abnormal drop event set; detecting whether a drop abnormality occurs in the current infusion process according to the target drop signal and the abnormal drop event set, and obtaining a drop state detection result; if it is detected that the drop state detection result indicates that the current infusion process occurs drop abnormality, outputting alarm information. Through the above method, the accuracy of signal identification can be improved, and false positives and false negatives of abnormal drop events can be reduced.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of signal recognition, and particularly relates to a signal recognition method and related device. BACKGROUND

[0002] In the current clinical use scenario, the traditional drop signal detection has low accuracy and is prone to miss or false alarm abnormal drop events, etc., which affects the user experience through traditional filtering and signal recognition. SUMMARY

[0003] The present application provides a signal recognition method and related device to improve the accuracy of signal recognition.

[0004] In a first aspect, an embodiment of the present application provides a signal recognition method, which is applied to an electronic device, and the method comprises:

[0005] obtaining a target drop signal of a current infusion process;

[0006] obtaining a preset abnormal drop event set, the abnormal drop event set comprising at least one abnormal event and a characteristic parameter combination corresponding to the at least one abnormal event, the abnormal event being an event causing drop abnormality in the infusion process, and the characteristic parameter combination comprising at least one of the following: a reference drop signal under the corresponding abnormal event condition, and a characteristic parameter for representing the characteristics of the reference drop signal;

[0007] detecting whether the current infusion process has drop abnormality according to the target drop signal and the abnormal drop event set, to obtain a drop state detection result;

[0008] if it is detected that the drop state detection result indicates that the current infusion process has drop abnormality, outputting an alarm information.

[0009] In a second aspect, an embodiment of the present application provides a signal recognition device, which comprises:

[0010] The first acquisition unit is configured to acquire a target drip signal of a current infusion process; the second acquisition unit is configured to acquire a preset abnormal drip event set, the abnormal drip event set including at least one abnormal event and a characteristic parameter combination corresponding to the at least one abnormal event, the abnormal event being an event causing abnormal drip in the infusion process, and the characteristic parameter combination including at least one of a reference drip signal in a corresponding abnormal event and a characteristic parameter used to represent a characteristic of the reference drip signal; the detection unit is configured to detect whether the current infusion process has abnormal drip according to the target drip signal and the abnormal drip event set, and obtain a drip state detection result; and the output unit is configured to output an alarm information when it is detected that the drip state detection result indicates that the current infusion process has abnormal drip.

[0011] In a third aspect, an electronic device is provided, which includes a processor, a memory, a communication interface, and one or more programs stored in the memory and configured to be executed by the processor, the program including instructions for performing the steps in the first aspect.

[0012] In a fourth aspect, a computer storage medium is provided, which stores a computer program for electronic data exchange, and the computer program causes a computer to perform some or all of the steps described in the first aspect.

[0013] In a fifth aspect, a computer program product is provided, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform some or all of the steps described in the first aspect. The computer program product can be a software installation package.

[0014] As can be seen, in the embodiments of the present application, the target drip signal of the current infusion process is first acquired, then the preset abnormal drip event set is acquired, and then whether the current infusion process has abnormal drip is detected according to the target drip signal and the abnormal drip event set, to obtain a drip state detection result. Finally, if it is detected that the drip state detection result indicates that the current infusion process has abnormal drip, an alarm information is output. In this way, by comparing the correlation of two signals to determine whether an abnormal drip event occurs, the accuracy of signal identification can be improved, the false positives and false negatives of abnormal drip events can be reduced, and the user experience can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0016] Figure 1a is a system architecture schematic diagram provided by an embodiment of the present application;

[0017] Figure 1b is a structural block diagram of an electronic device provided by an embodiment of the present application;

[0018] Figure 2 is a flowchart of a signal recognition method provided by an embodiment of the present application;

[0019] Figure 3 is a signal waveform comparison diagram after filtering processing provided by an embodiment of the present application;

[0020] Figure 4 is a signal waveform diagram after baseline unification and zero processing provided by an embodiment of the present application;

[0021] Figure 5 is a correlation coefficient diagram between two signal segments provided by an embodiment of the present application;

[0022] Figure 6 is a schematic diagram of a captured partial signal sequence provided by an embodiment of the present application;

[0023] Figure 7 is a functional unit composition block diagram of a signal recognition device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the person skilled in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments only constitute some embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0025] The terms "first", "second", and the like in the description and in the claims of the present application and above-described drawings are used to distinguish different objects, and are not used to describe a particular order. In addition, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to these processes, methods, products, or devices.

[0026] Reference herein to "embodiments" means that a particular feature, structure, or characteristic described in connection with an embodiment can be included in at least one embodiment of the application. The appearance of the phrase in various places in the specification does not necessarily all refer to the same embodiment, nor is it necessarily independent or alternative embodiments to other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0027] The related terms involved in the present application will be introduced first.

[0028] Matrix Profile (MP): a data structure for time series analysis, which can reduce the computational load for anomaly and trend analysis of time series, and the signal characteristics of a signal sequence can be trained by MP machine learning algorithm.

[0029] Filtering: filtering is an operation of filtering out specific waveband frequencies in a signal, which is an important measure to suppress and prevent interference.

[0030] Data normalization: normalization is to limit the data to be processed within a certain range after processing (through a certain algorithm) to facilitate subsequent data processing and speed up the convergence of program running.

[0031] At present, in the clinical scene, the number of abnormal drop events is large and complex, for example, in the process of nutrient solution infusion, pump pipe blockage, incorrect installation of pump pipe, abnormal water column of nutrient solution and other situations, the traditional drop signal detection through traditional filtering and signal recognition has low accuracy, which is easy to produce false negative or false positive abnormal drop event, affecting the user experience.

[0032] To solve the above problems, the embodiment of the present application provides a signal identification method, which can be applied to an electronic device, in particular, an electronic device connected to an infusion pump, so as to detect the drip condition in the infusion pump and identify abnormal events. The present application sets reference drip signals corresponding to various abnormal drip events, compares the target drip signal of the current drip process with the reference drip signal, and judges whether an abnormal drip event occurs, thereby improving the accuracy of signal identification in the infusion process. The present application can be applied to various scenarios requiring drip signal identification, including but not limited to the application scenarios mentioned above.

[0033] The system architecture related to the embodiment of the present application is introduced below.

[0034] Please refer to Figure 1a , Figure 1a is a system architecture diagram provided by the embodiment of the present application. As shown in Figure 1a , the system architecture 10 includes an electronic device 11 and a server 12, the electronic device 11 is used to execute the signal identification method provided by the embodiment of the present application, and send the output alarm information to the server 12, the server 12 is used to receive the alarm information sent from the electronic device 11. Wherein, the electronic device 11 can be a terminal connected to an infusion pump, a tablet computer, a notebook computer or a cloud, etc., the server 12 can be a server cluster or a cloud server.

[0035] As shown in Figure 1b , Figure 1b is a structural block diagram of an electronic device provided by the embodiment of the present application. As shown in Figure 1b , the electronic device 11 can include one or more of the following components: a processor 111, a memory 112 coupled to the processor 111, wherein the memory 112 can store one or more computer programs, and the one or more computer programs can be configured to be executed by the one or more processors 111 to implement the method described in the above embodiments.

[0036] The processor 111 can include one or more processing cores. The processor 111 connects various parts within the entire electronic device 11 with various interfaces and lines, performs various functions of the electronic device 11 and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 112, and calling data stored in the memory 112. Alternatively, the processor 111 can be implemented in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), a programmable logic array (PLA). The processor 111 can integrate a combination of one or several of a central processing unit (CPU), a graphics processor (GPU), and a modem. Among them, the CPU mainly processes an operating system, a user interface, and an application program; the GPU is responsible for rendering and drawing display content; and the modem is used for processing wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 111, but can be realized by a separate communication chip.

[0037] The memory 112 can include a random access memory (RAM) and can also include a read-only memory (ROM). The memory 112 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 112 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-mentioned various method embodiments, etc. The data storage area can also store data created by the electronic device 11 in use, etc.

[0038] It can be understood that the electronic device 11 can include more or less structural elements than the above-mentioned structural block diagram, for example, including a power module, a physical key, a WiFi (Wireless Fidelity) module, a speaker, a Bluetooth module, a sensor, etc., which are not limited here.

[0039] Please refer to Figure 2 , Figure 2 is a flowchart of a signal recognition method provided by an embodiment of the present application, and the method is applied to an electronic device. As shown in the figure, the signal recognition method includes:

[0040] Step 201, obtaining a target drip signal of a current infusion process.

[0041] The target drip signal of the current infusion process can be a normal drip signal, i.e., there is no abnormal drip event, or a drip signal corresponding to an abnormal drip event, or a drip signal corresponding to a combination of multiple abnormal drip events.

[0042] Step 202, obtaining a preset abnormal drip event set.

[0043] The abnormal drip event set includes at least one abnormal event and a characteristic parameter combination corresponding to the at least one abnormal event. The abnormal event refers to an event that causes drip abnormality in the infusion process. The characteristic parameter combination includes at least one of the following: a reference drip signal under the corresponding abnormal event condition, and a characteristic parameter for characterizing the characteristics of the reference drip signal.

[0044] Step 203, detecting whether the current infusion process has a drip abnormality according to the target drip signal and the abnormal drip event set, to obtain a drip state detection result.

[0045] The target drip signal is processed so that it can be matched with the reference drip signal characteristics, so that subsequent correlation comparison can be performed to detect whether the current infusion process has a drip abnormality. The drip state detection result is used to indicate whether the current infusion process has a drip abnormality. For example, the processing method of the target drip signal can be filtering, baseline unification and zero processing, or data normalization processing.

[0046] Step 204, if it is detected that the drip state detection result indicates that the current infusion process has a drip abnormality, outputting an alarm information.

[0047] After detecting that the current infusion process has a drip abnormality, the preset algorithm can be used to form an alarm information. The alarm information can be an alarm signal that triggers an alarm device in a specific area of a hospital, or a broadcast content output according to the detected abnormal drip event. The present embodiment is not limited in this regard.

[0048] It can be seen that, in the present example, the target drip signal of the current infusion process is first acquired, the preset abnormal drip event set is then acquired, and then whether the current infusion process has an abnormal drip is detected according to the target drip signal and the abnormal drip event set to obtain a drip state detection result. Finally, if it is detected that the drip state detection result indicates that the current infusion process has an abnormal drip, an alarm information is output. In this way, by comparing the correlation of two signals to determine whether an abnormal drip event has occurred, the accuracy of signal recognition can be improved, false positives and false negatives of abnormal drip events can be reduced, and user experience can be improved.

[0049] In one possible example, before the preset abnormal drip event set is acquired, the method further includes: presetting the reference drip signal and a feature parameter used to represent the characteristics of the reference drip signal, the feature parameter including a waveform, a sampling period, a baseline and an acceptable variance value of the reference drip signal; and pre-storing the reference drip signal and the feature parameter.

[0050] The feature parameter combination can be obtained by training an MP machine learning algorithm, and the feature parameter combination is stored for subsequent retrieval and used for correlation comparison with the acquired target drip signal. The acceptable variance value is a measurement standard for the correlation comparison.

[0051] It can be seen that, in the present example, by presetting and storing the feature parameter combination, a reference signal in the signal recognition process is formed, which is prepared for subsequent correlation comparison with the target drip signal acquired in the drip process to detect whether the drip process has an abnormal drip event to obtain a drip state detection result. The above-mentioned preset feature parameter combination can be obtained by training an MP machine learning algorithm.

[0052] In one possible example, the detection of whether the current infusion process has an abnormal drip according to the target drip signal and the abnormal drip event set to obtain a drip state detection result includes: processing the target drip signal to obtain a target abnormal signal matched with the reference drip signal characteristics; performing correlation comparison on the target abnormal signal and the reference drip signal to obtain a correlation coefficient; and detecting whether the current infusion process has an abnormal drip according to the correlation coefficient to obtain a drip state detection result.

[0053] The feature matching includes waveform matching, same baseline and same sampling period, and the correlation comparison includes comparing the similarity of the waveforms under the premise that the baseline and the sampling period are the same, and the correlation coefficient is used to indicate the similarity.

[0054] The correlation comparison can be achieved by the MP machine learning algorithm, the correlation coefficient can be calculated by the MP machine learning algorithm through a preset calculation logic when comparing the correlation of two signals, and the correlation coefficient graph can be generated by the MP machine learning algorithm.

[0055] It can be seen that, in this example, the target droplet signal is processed so that it can be compared with the reference droplet signal in terms of correlation, and the correlation comparison strategy can be adjusted according to different application scenarios to improve the accuracy of signal recognition.

[0056] In one possible example, the processing of the target droplet signal to obtain a target abnormal signal matched with the reference droplet signal includes: performing filtering processing on the target droplet signal to obtain a first abnormal signal; performing baseline unification and zeroing processing on the first abnormal signal to obtain a second abnormal signal; selecting a signal sequence in the sampling period in the second abnormal signal to obtain a third abnormal signal; and performing data normalization processing on the third abnormal signal to obtain the target abnormal signal.

[0057] The waveform of the first abnormal signal matches the waveform of the reference droplet signal, the waveform of the second abnormal signal matches the waveform of the reference droplet signal, the baseline of the second abnormal signal is the same as the baseline of the reference droplet signal, the waveform of the third abnormal signal matches the waveform of the reference droplet signal, the baseline and sampling period of the third abnormal signal are the same as the baseline and sampling period of the reference droplet signal, the waveform of the target abnormal signal matches the waveform of the reference droplet signal, the baseline and sampling period of the target abnormal signal are the same as the baseline and sampling period of the reference droplet signal, and the target abnormal signal can be compared with the reference droplet signal in terms of correlation.

[0058] For example, the filtering processing can be processing the target droplet signal using a Gaussian smoothing filtering algorithm, please refer to Figure 3 , Figure 3 is a signal waveform comparison graph after filtering processing provided by an embodiment of the present application. As shown in Figure 3 , waveform W1 is the original waveform of the target droplet signal in the example, and waveform W2 is the waveform of the signal after Gaussian smoothing filtering processing.

[0059] For example, the baseline unification and zeroing processing can be achieved by using an existing algorithm, please refer to Figure 4 , Figure 4 is a signal waveform graph after baseline unification and zeroing processing provided by an embodiment of the present application. As shown in Figure 4As shown, it can be seen that the signal waveform of the first abnormal signal after baseline unification and zero processing has approximately the same zero baseline and floats within a certain range.

[0060] Exemplarily, the signal sequence in the sampling period in the second abnormal signal can be a signal sequence from the start of sampling of the second abnormal signal to a fixed sampling period T, and the fixed sampling period T is the sampling period of the preset reference droplet signal. In this way, it can be determined that the sampling periods of the two signals are the same.

[0061] Exemplarily, the data normalization processing can be realized by an existing algorithm. Through this processing step, the data processing process in the system can be simplified, the response speed can be accelerated, and the optimal solution can be quickly found for subsequent correlation comparison.

[0062] As can be seen, in this example, the target droplet signal is processed to have characteristics that can be compared with the reference droplet signal for correlation, thereby improving the accuracy of signal recognition.

[0063] In one possible example, the detection of whether the current infusion process has a droplet anomaly according to the correlation coefficient to obtain a droplet state detection result includes: if the similarity indicated by the correlation coefficient is within the preset acceptable variance value range, a first droplet state detection result is obtained; and if the similarity indicated by the correlation coefficient is outside the preset acceptable variance value range, a second droplet state detection result is obtained.

[0064] The first droplet state detection result is used to indicate that the current infusion process does not have a droplet anomaly, and the second droplet state detection result is used to indicate that the current infusion process has a droplet anomaly. Exemplarily, the acceptable variance value for the pump pipe blockage abnormal droplet event obtained by the MP machine learning algorithm is 8.5, and the acceptable variance value for the pump pipe not correctly installed abnormal droplet event is also 8.5. In the current infusion process, the similarity indicated by the correlation coefficient of the target droplet signal and the first reference droplet signal is 8, and the similarity indicated by the correlation coefficient of the target droplet signal and the second reference droplet signal is 9, the first reference droplet signal is used to indicate that the abnormal droplet event is pump pipe blockage, and the second reference droplet signal is used to indicate that the abnormal droplet event is pump pipe not correctly installed. Therefore, in the current infusion process, no pump pipe blockage abnormal droplet event occurs, but there can be a pump pipe not correctly installed abnormal droplet event.

[0065] As can be seen, in this example, whether an abnormal droplet event occurs in the current infusion process is detected by comparing the similarity indicated by the correlation coefficient with the preset acceptable variance value, thereby improving the accuracy of signal recognition.

[0066] In one possible example, if the detection result of the drip status indicates that a drip abnormality has occurred in the current infusion process, the step of outputting alarm information includes: capturing a partial signal sequence in the target abnormal signal according to the correlation coefficient, the partial signal sequence being used to indicate abnormal features, the abnormal features being used to indicate the abnormal event corresponding to the abnormal features; and outputting alarm information according to the abnormal event.

[0067] Specifically, the MP machine learning algorithm can be used to generate a correlation coefficient map between the target anomalous signal and the reference droplet signal based on the correlation coefficient, and to capture a portion of the signal sequence from the target anomalous signal. For example, please refer to... Figure 5 , Figure 5 This is a correlation coefficient diagram between two signal segments provided in an embodiment of this application. For example... Figure 5 As shown, this graph can be generated using the MP machine learning algorithm based on the correlation coefficients. The black dots pointed to by each arrow in the graph represent the correlation coefficient distribution between the target abnormal signal and the second reference droplet signal in this example. Please refer to [link / reference]. Figure 6 , Figure 6 This is a schematic diagram of a captured partial signal sequence provided in an embodiment of this application. For example... Figure 6 As shown in the figure, the remaining waveform is a partial signal sequence in the target abnormal signal captured according to the correlation coefficient. This partial signal sequence can form a corresponding abnormal feature according to the similarity, and the abnormal feature is used to indicate the corresponding abnormal event.

[0068] As can be seen, in this example, the correlation coefficient is used to capture a portion of the signal sequence in the target abnormal signal and form abnormal features to indicate the abnormal event that has occurred, thereby improving the accuracy of signal recognition.

[0069] In one possible example, the method further includes: sending the alarm information to a hospital electronic information system, the hospital electronic information system being connected to at least one hospital broadcast; and broadcasting the alarm information through the at least one hospital broadcast.

[0070] The hospital electronic information system can be a hardware device comprised of the aforementioned server 12. The connection can be wired or wireless. The at least one hospital broadcast can be configured according to actual needs. For example, in a ward with high light intensity, a broadcast specifically for reporting abnormal dripping events affected by light intensity can be set up, or a broadcast specifically for reporting specific abnormal dripping events can be set up in a specific ward. This example can be applied to various scenarios, including but not limited to the application scenarios mentioned above.

[0071] It can be seen that in the present example, the alarm information can be effectively output by the above method, which is beneficial to reduce the alarm fatigue of medical staff.

[0072] In accordance with the above-mentioned embodiments, please refer to Figure 7 , Figure 7 is a functional unit composition block diagram of a signal recognition device provided by the embodiment of the present application, the signal recognition device 700 comprises: a first acquisition unit 701, configured to acquire a target drip signal of a current infusion process; a second acquisition unit 702, configured to acquire a preset abnormal drip event set, the abnormal drip event set comprising at least one abnormal event and a characteristic parameter combination corresponding to the at least one abnormal event one by one, the abnormal event refers to an event that causes drip abnormality in the infusion process, and the characteristic parameter combination comprises at least one of the following: a reference drip signal under the corresponding abnormal event condition, and a characteristic parameter for representing the characteristics of the reference drip signal; a detection unit 703, configured to detect whether the current infusion process has a drip abnormality according to the target drip signal and the abnormal drip event set, and obtain a drip state detection result; and an output unit 704, configured to output alarm information when it is detected that the drip state detection result indicates that the current infusion process has a drip abnormality.

[0073] In one possible example, the signal recognition device 700 is further configured to: before the acquisition of the preset abnormal drip event set, preset the reference drip signal and the characteristic parameter for representing the characteristics of the reference drip signal, and the characteristic parameter comprises a waveform, a sampling period, a baseline and an acceptable variance value of the reference drip signal; and prestore the reference drip signal and the characteristic parameter.

[0074] In one possible example, in the aspect of detecting whether the current infusion process has a drip abnormality according to the target drip signal and the abnormal drip event set, and obtaining a drip state detection result, the detection unit 703 is specifically configured to: process the target drip signal to obtain a target abnormal signal matched with the characteristics of the reference drip signal, wherein the characteristic matching comprises waveform matching, baseline same and sampling period same; compare the correlation of the target abnormal signal and the reference drip signal to obtain a correlation coefficient, wherein the correlation comparison comprises comparing the similarity of the waveforms under the premise that the baseline and the sampling period are the same, and the correlation coefficient is used to indicate the similarity; and detect whether the current infusion process has a drip abnormality according to the correlation coefficient to obtain a drip state detection result.

[0075] In a possible example, in the processing of the target drop signal, the signal recognition device 700 is further configured to: filter the target drop signal to obtain a first abnormal signal, the waveform of the first abnormal signal matches the waveform of the reference drop signal; perform baseline unification and zeroization processing on the first abnormal signal to obtain a second abnormal signal, the waveform of the second abnormal signal matches the waveform of the reference drop signal, and the baseline of the second abnormal signal is the same as the baseline of the reference drop signal; select a signal sequence in the second abnormal signal within the sampling period to obtain a third abnormal signal, the waveform of the third abnormal signal matches the waveform of the reference drop signal, and the baseline and sampling period of the third abnormal signal are the same as the baseline and sampling period of the reference drop signal; and perform data normalization processing on the third abnormal signal to obtain the target abnormal signal, the waveform of the target abnormal signal matches the waveform of the reference drop signal, the baseline and sampling period of the target abnormal signal are the same as the baseline and sampling period of the reference drop signal, and the target abnormal signal can be compared with the reference drop signal in correlation.

[0076] In a possible example, in the detection of the drop state of the current infusion process according to the correlation coefficient, the detection unit 703 is specifically configured to: if the similarity indicated by the correlation coefficient is within the preset acceptable variance value range, obtain a first drop state detection result, the first drop state detection result is used to indicate that the current infusion process does not occur drop abnormality; and if the similarity indicated by the correlation coefficient is outside the preset acceptable variance value range, obtain a second drop state detection result, the second drop state detection result is used to indicate that the current infusion process occurs drop abnormality.

[0077] In a possible example, in the output of the alarm information if it is detected that the drop state detection result indicates that the current infusion process occurs drop abnormality, the output unit 704 is specifically configured to: capture part of the signal sequence in the target abnormal signal according to the correlation coefficient, the part of the signal sequence is used to indicate an abnormal feature, and the abnormal feature is used to indicate an abnormal event corresponding to the abnormal feature; and output alarm information according to the abnormal event

[0078] In a possible example, the signal recognition device 700 is further configured to: send the alarm information to a hospital electronic information system, the hospital electronic information system is connected to at least one hospital broadcast; and broadcast the alarm information through the at least one hospital broadcast.

[0079] It can be understood that, since the method embodiments and the device embodiments are different presentation forms of the same technical concept, the content of the method embodiments part in the present application should be adapted to the device embodiments part synchronously, and details are not described herein.

[0080] The above-described embodiments can be implemented in part or in whole through software, hardware, firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When loaded and executed by a computer, the computer instructions or computer programs cause the computer to perform all or part of the processes or functions described in the embodiments of the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center through a wired or wireless manner. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. containing a set of one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid state disk.

[0081] The embodiments of the present application also provide a computer storage medium, which stores a computer program for electronic data exchange, and the computer program causes a computer to perform some or all of the steps of any method described in the above method embodiments.

[0082] The embodiments of the present application also provide a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform some or all of the steps of any method described in the above method embodiments.

[0083] It should be understood that, in various embodiments of the present application, the size of the sequence number of each process does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0084] In several embodiments provided in the present application, it should be understood that the disclosed method, device and system can be implemented in other manners. For example, the described device embodiments are merely illustrative; for example, the division of the units is merely logical function division; in actual implementation, other division manners can be adopted; for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0085] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments.

[0086] In addition, each functional unit in the embodiments of the present application can be integrated in a processing unit, or each unit can be a physical unit independently, or two or more units can be integrated in a unit. The integrated unit can be in the form of hardware, or in the form of hardware plus software function unit.

[0087] The integrated unit implemented in the form of software functional units can be stored in a computer readable storage medium. The software functional unit is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute part of the steps of the method described in various embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a magnetic disk, an optical disk, a volatile memory or a non-volatile memory. The non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) can be used, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM) and direct rambus RAM (DRRAM). Various media that can store program codes.

[0088] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements without departing from the spirit and scope of the present application, and various modifications can be made, including combinations of different functions and implementation steps, including software and hardware implementations, which are all within the protection scope of the present application.

Claims

1. A signal recognition method characterized by, The method is applied to an electronic device, and the method comprises: obtaining a target drip signal of a current infusion process; obtaining a preset abnormal drip event set, the abnormal drip event set comprising at least one abnormal event and a characteristic parameter combination corresponding to the at least one abnormal event, the abnormal event being an event causing drip abnormality in the infusion process, and the characteristic parameter combination comprising at least one of a reference drip signal under the corresponding abnormal event, and a characteristic parameter for representing a characteristic of the reference drip signal, the characteristic parameter comprising a waveform, a sampling period, a baseline, and an acceptable variance value of the reference drip signal; detecting whether the current infusion process has drip abnormality according to the target drip signal and the abnormal drip event set, to obtain a drip state detection result; if it is detected that the drip state detection result indicates that the current infusion process has drip abnormality, outputting an alarm information; the detection of whether the current infusion process has drip abnormality according to the target drip signal and the abnormal drip event set to obtain the drip state detection result comprises: if a correlation coefficient indicates that a similarity is within a preset acceptable variance value range, obtaining a first drip state detection result, the first drip state detection result being used to indicate that the current infusion process does not have drip abnormality; and if the correlation coefficient indicates that the similarity is outside the preset acceptable variance value range, obtaining a second drip state detection result, the second drip state detection result being used to indicate that the current infusion process has drip abnormality, the correlation coefficient being obtained by performing correlation comparison on the target drip signal and the reference drip signal by using an MP machine learning algorithm.

2. The method of claim 1, wherein, the detection of whether the current infusion process has drip abnormality according to the target drip signal and the abnormal drip event set to obtain the drip state detection result comprises: processing the target drip signal to obtain a target abnormal signal matched with a characteristic of the reference drip signal, the characteristic matching comprising waveform matching, baseline being the same, and sampling period being the same; performing correlation comparison on the target abnormal signal and the reference drip signal to obtain a correlation coefficient, the correlation comparison comprising comparing similarity of the waveforms under the premise that the baseline and the sampling period are the same, the correlation coefficient being used to indicate the similarity; detecting whether the current infusion process has drip abnormality according to the correlation coefficient to obtain the drip state detection result.

3. The method of claim 2, wherein, the processing of the target drip signal to obtain the target abnormal signal matched with the characteristic of the reference drip signal, the characteristic matching comprising waveform matching, baseline being the same, and sampling period being the same, comprises: performing filtering processing on the target drip signal to obtain a first abnormal signal, a waveform of the first abnormal signal being matched with a waveform of the reference drip signal; performing baseline unification and zero processing on the first abnormal signal to obtain a second abnormal signal, a waveform of the second abnormal signal being matched with the waveform of the reference drip signal, and a baseline of the second abnormal signal being the same as a baseline of the reference drip signal; selecting a signal sequence in the sampling period from the second abnormal signal to obtain a third abnormal signal, a waveform of the third abnormal signal matching a waveform of the reference drop signal, a baseline and a sampling period of the third abnormal signal being same as a baseline and a sampling period of the reference drop signal; performing data normalization processing on the third abnormal signal to obtain the target abnormal signal, a waveform of the target abnormal signal matching a waveform of the reference drop signal, a baseline and a sampling period of the target abnormal signal being same as a baseline and a sampling period of the reference drop signal, and the target abnormal signal being capable of being compared in correlation with the reference drop signal.

4. The method of claim 3, wherein, If it is detected that the drop state detection result indicates that the current infusion process occurs drop abnormality, the alarm information is output, including: According to the correlation coefficient, a part of signal sequences in the target abnormal signal are captured, the part of signal sequences being used for indicating abnormal features, the abnormal features being used for indicating abnormal events corresponding to the abnormal features; According to the abnormal events, alarm information is output.

5. The method of claim 1, wherein, The method further includes: The alarm information is sent to a hospital electronic information system, the hospital electronic information system being connected with at least one hospital broadcast; The alarm information is broadcasted through the at least one hospital broadcast.

6. A signal recognition apparatus, characterized by The device includes: A first acquisition unit is configured to acquire a target drop signal of a current infusion process; A second acquisition unit is configured to acquire a preset abnormal drop event set, the abnormal drop event set including at least one abnormal event and a characteristic parameter combination corresponding to the at least one abnormal event, the abnormal event being an event causing drop abnormality in an infusion process, the characteristic parameter combination including at least one of a reference drop signal under a corresponding abnormal event condition and a characteristic parameter used for representing a characteristic of the reference drop signal, the characteristic parameter including a waveform, a sampling period, a baseline and an acceptable variance value of the reference drop signal; A detection unit is configured to detect whether the current infusion process occurs drop abnormality according to the target drop signal and the abnormal drop event set to obtain a drop state detection result; An output unit is configured to output alarm information when it is detected that the drop state detection result indicates that the current infusion process occurs drop abnormality; The detection of whether the current infusion process occurs drop abnormality according to the target drop signal and the abnormal drop event set to obtain a drop state detection result includes: if a similarity indicated by a correlation coefficient is within a preset acceptable variance value range, a first drop state detection result is obtained, the first drop state detection result being used for indicating that the current infusion process does not occur drop abnormality; if the similarity indicated by the correlation coefficient is outside the preset acceptable variance value range, a second drop state detection result is obtained, the second drop state detection result being used for indicating that the current infusion process occurs drop abnormality, and the correlation coefficient being obtained by performing correlation comparison between the target drop signal and the reference drop signal through an MP machine learning algorithm.

7. An electronic device, comprising: A computer program product comprising a computer readable medium having stored thereon the program of claim 6.

8. A computer-readable storage medium, characterized in that, A computer program for electronic data interchange, wherein the computer program causes a computer to perform the method of any of claims 1-5.

Images