CN115512823A

CN115512823A - Equipment exception handling method and device, exception handling system and equipment

Info

Publication number: CN115512823A
Application number: CN202211181891.6A
Authority: CN
Inventors: 何青民; 程瑞豪
Original assignee: Shenzhen United Imaging Research Institute of Innovative Medical Equipment
Current assignee: Shenzhen United Imaging Research Institute of Innovative Medical Equipment
Priority date: 2022-09-27
Filing date: 2022-09-27
Publication date: 2022-12-23

Abstract

The application relates to a method and a device for processing equipment exception, an exception processing system and equipment. The method is applied to a medical equipment system; the medical equipment system comprises medical equipment and a back-end operating system connected with the medical equipment; the method comprises the following steps: receiving scene reporting data transmitted by a back-end operating system; carrying out feature statistics on the reported scene data to obtain scene feature data; generating potential problem subsystem information based on the scene characteristic data and the mapping form; the potential problem subsystem information is used for representing the range of subsystems with potential faults of the medical equipment; outputting a relevant file of the problem scene based on the potential problem subsystem information; the association file is used for providing equipment exception reference information for generating the current solution. By adopting the method, the solving efficiency of the abnormal problem of the equipment can be improved.

Description

Equipment exception handling method and device, exception handling system and equipment

Technical Field

The present application relates to the technical field of large medical devices, and in particular, to a device exception handling method, apparatus, exception handling system, and device.

Background

With the development of large medical equipment, medical equipment is widely applied to modern medical services. For example, magnetic Resonance Imaging (MRI), positron Emission Computed Tomography (PET/CT), medical Imaging equipment such as a Positron Emission Magnetic Resonance imager (PET/MR) generally comprises complex subsystems and components, and relates to a plurality of fields such as electronics, machinery, biomedicine, computers and the like. Furthermore, it brings certain difficulties to on-site status investigation, system diagnosis, and fault location of medical equipment systems related to large-scale medical equipment.

In the traditional technology, a professional technical engineer who needs to be trained for a long time often diagnoses and inspects the unsatisfactory state or fault condition of a medical equipment system during on-site problem investigation, positions the original problem scene source of the medical equipment and provides a corresponding technical scheme. However, the current device exception handling method or the traditional method has the problem of low problem solving efficiency.

Disclosure of Invention

In view of the above, it is necessary to provide a device exception handling method, apparatus, exception handling system, device, and storage medium capable of improving the problem solving efficiency.

In a first aspect, the present application provides a device exception handling method. The method is applied to a medical equipment system; the medical equipment system comprises medical equipment and a back-end operating system connected with the medical equipment; the method comprises the following steps:

receiving scene reporting data transmitted by a back-end operating system; the scene reported data comprises scene description information of problem scenes aiming at the medical equipment;

carrying out feature statistics on the reported scene data to obtain scene feature data;

generating potential problem subsystem information based on the scene characteristic data and the mapping form; the potential problem subsystem information is used for representing the range of subsystems with potential faults of the medical equipment;

outputting a relevant file of the problem scene based on the potential problem subsystem information; the association file is used for providing equipment exception reference information for generating the current solution.

In one embodiment, before the step of receiving the scene report data transmitted by the backend operating system, the method further includes the steps of:

if a scene reporting request of a back-end operating system is received, outputting a display command; the display command is used for instructing the back-end operating system to display the scene description guiding information based on the scene description form; the scene description guide information is used for guiding a back-end user to input scene description information.

In one embodiment, the scene feature data comprises scene text feature data and scene image feature data; the method comprises the steps of carrying out feature statistics on scene reported data to obtain scene feature data, and comprises the following steps:

classifying the scene description information to obtain text information and image information;

extracting characteristic words and counting word frequency of the text information to obtain scene text characteristic data;

and carrying out image text recognition and image feature statistics on the image information to obtain scene image feature data.

In one embodiment, the step of generating the potential problem subsystem information based on the scene characteristic data and the mapping form comprises:

querying a historical solution database, and matching the scene characteristic data to obtain a matching result;

if the matching result is the associated historical solution which is not matched with the scene characteristic data, generating the subsystem information of the potential problems based on the scene characteristic data and the mapping form;

the method further comprises the following steps:

and if the current solution is newly added in the historical solution database, updating the processing state mark of the problem scene.

In one embodiment, the step of generating the potential problem subsystem information based on the scene feature data and the mapping form further includes:

if the matching result is that the association history solution is matched, sending the association history solution to a back-end operating system;

if a feedback result of the back-end operating system for the associated historical solution is received, updating the processing state mark of the problem scene;

and if the processing state marks of the problem scenes before and after updating are the same, generating the potential problem subsystem information based on the scene characteristic data and the mapping form.

In one embodiment, the mapping form comprises a mapping relation between the key feature words and the potential failure subsystems of the medical equipment; the key characteristic words are determined by characteristic word extraction and word frequency statistics; outputting a correlation file of the problem scene based on the potential problem subsystem information, wherein the correlation file comprises:

and screening the system files in the medical equipment system according to the mapping relation between the subsystem information of the potential problems and the system files in the medical equipment system to obtain the associated files.

In a second aspect, the present application also provides a device abnormality processing apparatus, which is applied to a medical device system; the medical equipment system comprises medical equipment and a back-end operating system connected with the medical equipment; the device comprises:

the scene reporting unit is used for receiving scene reporting data transmitted by a back-end operating system; the scene reported data comprises scene description information of problem scenes aiming at the medical equipment;

the characteristic statistical unit is used for carrying out characteristic statistics on the scene reported data to obtain scene characteristic data;

the range determining unit is used for generating potential problem subsystem information based on the scene characteristic data and the mapping form; the potential problem subsystem information is used for representing the range of subsystems with potential faults of the medical equipment;

the file output unit is used for outputting the associated file of the problem scene based on the potential problem subsystem information; the association file is used for providing equipment exception reference information for generating the current solution.

In a third aspect, the present application further provides an exception handling apparatus. The exception handling apparatus comprises a memory storing a computer program and a processor implementing the steps of the method described above when executing the computer program.

In a fourth aspect, the present application further provides an exception handling system. The abnormality processing system comprises a medical equipment system and an abnormality processing device connected with the medical equipment system; the medical equipment system comprises medical equipment and a back-end operating system connected with the medical equipment;

the exception handling device comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the method when executing the computer program.

In a fifth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.

According to the equipment exception handling method, the equipment exception handling device, the exception handling system, the equipment and the storage medium, the scene report data including the scene description information aiming at the problem scene of the medical equipment is transmitted through the back-end operating system, so that the problem scene can be reported quickly by combining the actual experience of a back-end user, and the communication cost is reduced; furthermore, the subsystem range related to the problem scene is reduced through the mapping form, the associated file of the problem scene is output, the interested range of a technical engineer can be reduced, the technical engineer is helped to quickly locate the problem source of the original scene, a technical scheme is timely and efficiently provided, and the processing efficiency of equipment abnormity is improved.

Drawings

FIG. 1 is a flow diagram illustrating a method for handling device exceptions, according to an embodiment;

FIG. 2 is a flowchart illustrating the exception handling steps of the apparatus according to one embodiment;

FIG. 3 is a flowchart illustrating the exception handling steps of the apparatus according to another embodiment;

FIG. 4 is a flowchart illustrating the exception handling steps of the apparatus in yet another embodiment;

FIG. 5 is a flowchart illustrating a method for handling device exceptions in a specific embodiment;

FIG. 6 is a flowchart illustrating the exception handling steps of the apparatus in one embodiment;

FIG. 7 is a block diagram of a device exception handling system in a specific example;

FIG. 8 is a block diagram showing the configuration of a device exception handling apparatus according to one embodiment;

FIG. 9 is a diagram showing an internal structure of an exception handling apparatus in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.

At present, various large-scale medical equipment systems have generally provided some basic system diagnosis and analysis functions. However, in situations where the field user may find the system status undesirable during use of the system, it may be difficult for the field user to accurately locate and feedback system component information based on existing system diagnostic information due to the complexity of large medical device systems that typically involve multiple components, multiple software subsystems, and the lack of knowledge of the field user about the various system subcomponents. In such cases, field support from technical engineers is often required to continue the medical diagnostic service or other system-related work, and the shelving of services for large medical equipment systems results in considerable operational and maintenance costs. The scheme of the application is expected to cover a certain scene, the communication cost from scene sites to technical support seeking is reduced, and the data storage pressure brought by traditional collection and storage system files according to time periods is relieved.

In one embodiment, as shown in FIG. 1, a method for device exception handling is provided. The method is applied to a medical equipment system; the medical equipment system comprises medical equipment and a back-end operating system connected with the medical equipment; the method comprises the following steps:

step 110, receiving scene report data transmitted by a back-end operating system; the scene reporting data comprises scene description information aiming at a problem scene of the medical equipment;

it should be noted that, due to the complexity of a large medical device system, multiple components and multiple software subsystems are usually involved, and the diagnostic information reported by the medical device system is usually fault-dependent, that is, diagnosing a fault by a component located at the front end of a workflow often causes a fault to be reported by a component located at the back end of the workflow, even though the component located at the back end of the workflow may not have a fault. The back-end users using the back-end operating system include but are not limited to hospital technicians, clinical engineers, system test engineers, and the like, in the actual use scenario, problems may occur to the medical equipment system, or the system problems are not reflected in the system problems only appearing as non-ideal system states, and the back-end users often do not have the initial system diagnosis capability.

Specifically, if a back-end user encounters a problem scene that the system state of the medical device is not ideal or the medical device cannot be used normally, the back-end user can complete the input of the scene description information by interacting with the back-end operating system according to the problem scene of the medical device currently encountered, for example, the back-end operating system can interact with the back-end user based on a preset scene description form, and the scene description form can be set correspondingly by combining the use experience of the back-end user; accordingly, the back-end operating system can acquire scene description information for the problem scene of the medical device based on the scene description form. The scene reported data including the scene description information transmitted by the back-end operating system can provide required data support for the analysis of the subsequent scene reported data and the abnormal positioning of the medical equipment, and a technical engineer does not need to arrive at the site to reappear the corresponding system scene and then make corresponding technical judgment and provide a technical solution, so that the reporting period of the problem scene is shortened, and the communication cost between a back-end user and the technical engineer is reduced.

In some examples, the medical device may include a medical imaging device, and the problem scenario for the medical imaging device may include a problem scenario in which the medical image is an artifact. The scenario description form may include guidance information, e.g., question information for guiding answers, pre-designed to reflect the scenario of a question of the medical device based on the system diagnostic experience of the technical engineer. Further, the acquired scene description information may include scene description information for the problem scene of the medical device in the form of textual description information, image recording information, and the like.

Step 120, carrying out feature statistics on the scene reported data to obtain scene feature data;

specifically, feature statistics may be performed on the scene report data by using a corresponding feature statistics algorithm, for example, feature statistics may be performed on the textual description information by using a word segmentation and word frequency statistics manner, and feature statistics may be performed on the image record information by using a conventional manner such as an image moment and a color feature, or a manner such as a Scale-invariant feature transform (SIFT) algorithm based on machine learning, a Speeded Up Robust Feature (SURF) algorithm, or a manner such as a Convolutional Neural Network (CNN) algorithm based on deep learning, so as to filter redundant data in the scene report data and select key data of feature information for reflecting a problem scene of the medical device.

Step 130, generating potential problem subsystem information based on the scene characteristic data and the mapping form; the potential problem subsystem information is used for representing the range of subsystems with potential faults of the medical equipment;

specifically, since a large-scale medical device system relates to a plurality of subsystems, potential problem subsystem information may be generated according to scenario characteristic data and a preset mapping table, where the mapping table may include a mapping relationship between the scenario characteristic data and a potentially faulty subsystem of the medical device, and the potential problem subsystem information may be used to characterize a range of subsystems in the medical device where a fault may exist, that is, the potential problem subsystem information may include one or more potentially faulty subsystems. By generating the subsystem information of the potential problems, the range of subsystems of the medical equipment, which are possibly abnormal or failed, can be narrowed, so that the interested range of a technical engineer is further narrowed, and the subsequent technical engineer can conveniently and quickly locate the original problem scene source of the medical equipment.

In some examples, the mapping table may be a table preset based on experience of a technical engineer, that is, the mapping relationship between the scene characteristic data and the potentially faulty subsystem of the medical device may be preset based on experience of the technical engineer.

Step 140, outputting a relevant file of the problem scene based on the potential problem subsystem information; the association file is used for providing equipment exception reference information for generating the current solution.

Specifically, through guidance of the subsystem information of the potential problem, a correlation file of a problem scene required for technical engineers to query and analyze can be output, wherein the correlation file of the problem scene corresponds to a subsystem range, represented by the subsystem information of the potential problem, of the potential fault of the medical equipment. The technical engineer can form a current solution for a problem scene based on the equipment abnormity reference information provided by the associated file, does not need to check the diagnostic data of a plurality of subsystems one by one, and improves the equipment abnormity processing efficiency.

In some examples, the type of association file may include a Digital Imaging and Communications in Medicine (DICOM) file, a raw data file, a system log file, or an intermediate system file generated during actual application of the medical Imaging system. The associated files can be packaged and encapsulated, and the association relationship between the scene description form and the image recording information is established for technical engineers to inquire and analyze. Technical engineers can inquire the problem scene to be solved through a user interaction interface provided by the technical support subsystem, generate and give a technical solution through the visual input module, and store the technical solution in the historical solution database. The technical support subsystem can be a system connected with a back-end operating system.

The method and the device can transmit the scene report data comprising the scene description information aiming at the problem scene of the medical equipment through the back-end operating system, can combine the actual experience of a back-end user to quickly report the problem scene, and reduce the communication cost; furthermore, the subsystem range related to the problem scene is reduced through the mapping form, the associated file of the problem scene is output, the interested range of a technical engineer can be reduced, the technical engineer is helped to quickly position the problem source of the original scene, a technical scheme is timely and efficiently provided, and the processing efficiency of equipment abnormity is improved.

Specifically, if a back-end user encounters a problem scene that the system state of the medical equipment is not ideal or cannot be used normally, a corresponding scene reporting request can be sent through a back-end operating system; corresponding display commands can be output to a back-end operating system according to the received scene reporting request, for example, scene description guide information is displayed through a user interaction interface based on a scene description form, and then a back-end user is guided to input the scene description information, so that the text description information, the image recording information and the like aiming at the problem scene are obtained, wherein the text description information can include guiding question and answer information. By outputting the display command, the back-end operating system receives the display command, displays the scene description guiding information based on the scene description list, guides the back-end user to input the scene description information aiming at the problem scene, can provide required data support for the analysis of the reported data of the following scene and the abnormal positioning of the medical equipment, does not need a technical engineer to arrive at the site to reproduce the corresponding system scene and then make corresponding technical judgment and provide a technical solution, shortens the reporting period of the problem scene, and reduces the communication cost between the back-end user and the technical engineer.

In some examples, the textual description information for the problem scenario may be obtained as follows: the back-end operating system may display scene description guidance information such as "please briefly describe a scene that you need to report", and the scene description information received from the back-end user may be textual description information for a problem scene, such as "when a scan protocol package is imported using the system tool XX, the import of a part of the protocol package fails" or "when an XX clinical sequence is used to image the abdomen of a human body, an asymmetric artifact occurs in imaging under XX sequence parameters". The guided question-answering information for the question scene can be obtained by adopting the following modes: the back-end operating system may display guidance questions such as "what kind of scenes you want to solve belongs to", and may also provide guidance options evaluated by system technicians, such as "image artifact problem", "system function problem", "system performance problem", and further, for the problem scene classification selected by the back-end user, a series of related guidance questions may be provided or pushed, such as a user feedback tag for "image artifact problem", and the next question may be "what kind of questions you want to solve appears only in a specific sequence or has related performance in a plurality of family-like sequences? "and" do you describe a question appear only in the current system environment, or have a relevant performance in other system environments? "and the like. Guiding image recording information input by a back-end user, collecting regional image information which is expected to be selected by the back-end user by using an image capturing tool provided by a back-end operating system for the back-end user, and collecting scene information which is collected by other conventional screen capturing tools for the back-end user; the back-end user may also be guided to develop a description of the selected recording image through the scene description form, for example, the back-end operating system may display guidance questions such as "which part of the text information in the scene shown by the image is considered to be possibly related to the problem that you encounter, e.g., please pick up", or "which hardware subsystem or software subsystem is related in the scene shown by the image is considered by you", and the like, so as to obtain the image recording information including the recording image and the related text description of the recording image. The detailed scene description guiding information is provided for the back-end user through the back-end operating system based on the scene description form, the back-end user can be timely, accurately and comprehensively guided to describe the problem scene, the scene characteristic data comprising the scene description information is obtained by combining the actual experience of the back-end user, the subsequent process of communication and investigation when a technical engineer arrives at the site is omitted, the problem scene is reported quickly, the communication cost is reduced, and the processing efficiency of equipment abnormity is improved.

In one embodiment, as shown in fig. 2, the scene feature data includes scene text feature data and scene image feature data; the method for carrying out feature statistics on the scene reported data to obtain the scene feature data comprises the following steps:

step 210, classifying the scene description information to obtain text information and image information;

step 220, extracting characteristic words and counting word frequency of the text information to obtain scene text characteristic data;

and step 230, performing image text recognition and image feature statistics on the image information to obtain scene image feature data.

Specifically, since the scene description information may include different forms of information such as textual description information and image recording information, text information and image information may be obtained by classifying the scene description information, where the text information may include a description of a relevant character of a recorded image in the image recording information; accordingly, the scene feature data may include scene text feature data and scene image feature data. The scene text characteristic data is used for reflecting the characteristics of the text information; word division of text information, extraction of characteristic words based on division results and word frequency statistics of the characteristic words can be realized by adopting text semantic analysis, text matrixing and other character analysis algorithms; the characteristic words can be words with discrimination selected from the text information, and can be extracted through corresponding algorithms such as semantic analysis and the like; the word frequency may be the number of times a feature word appears in the text message. The scene image feature data is used for reflecting features of image information, and the image text Recognition may be implemented by using various Recognition algorithms of an OCR (Optical Character Recognition), including but not limited to a conventional image algorithm, a deep learning algorithm, and the like, and characters in the image information may be detected and recognized and converted into an electronic text, so as to facilitate image feature statistics. Image characteristic data such as image brightness, contrast, covariance and the like can be obtained by carrying out image characteristic statistics on the image information. By acquiring the text information and the image information in the scene description information and performing corresponding processing, the information dimensionality of the scene description information can be enriched, sufficient data support can be provided for the subsequent scene data analysis, and the robustness of the data analysis is improved, wherein the necessary image information connection is increased, so that the final technical scheme is more visual, and the readability of the subsequent technical scheme is improved. The scene text characteristic data and the scene image characteristic data are obtained by respectively processing the text information and the image information, so that sufficient data support can be provided for generating subsystem information with potential problems, and the subsystem range of the medical equipment, which is possible to generate abnormity or faults, can be conveniently and accurately positioned.

In some examples, the word segmentation may be performed by a word segmentation algorithm according to a dictionary, according to a statistic, according to a meaning (based on rules) or according to a solution (performing syntax and semantic analysis while segmenting words, and processing ambiguity phenomena by using syntax information and semantic information) in a conventional text semantic analysis, or may be a word segmentation method integrated in a scene description form, that is, a systematic word description is obtained by a series of rules to guide a problem. The word frequency statistical method can be a word frequency statistical algorithm realized based on a text matrixing method. The image text recognition can adopt traditional image algorithms, including image algorithms such as preprocessing (for example, binaryzation, affine transformation and the like), character recognition, post-processing correction and the like on the image; the image text recognition can also adopt a character recognition scheme developed by a deep learning algorithm; the related text description of the recorded image in the image recording information can also be directly acquired, namely, the description information for the recorded image, which is input by a back-end user guided by a scene description form, is acquired. Image feature statistics can be performed by means of obtaining similarity between image information and historical scene record images to obtain scene image feature data, wherein the scene image feature data can include but is not limited to feature data such as image brightness, contrast, covariance and the like. The scene text characteristic data and the scene image characteristic data obtained by the method have stronger robustness in the aspect of reflecting the subsystem range of the medical equipment which is possible to generate abnormity or faults.

In one embodiment, as shown in fig. 3, the step of generating the subsystem information of the potential problem based on the scene feature data and the mapping form includes:

step 310, querying a historical solution database, and performing matching processing on the scene characteristic data to obtain a matching result;

step 320, if the matching result is the associated history solution which is not matched with the scene characteristic data, generating the subsystem information of the potential problems based on the scene characteristic data and the mapping form;

the method further comprises the following steps:

In particular, the scene feature data may include scene text feature data and scene image feature data, and the historical solution database may include a plurality of historical solutions for solving different problem scenes of the medical device, and the historical solution database may be queried to match historical solutions having the same or similar features as the associated historical solution for the scene feature data, based on the scene text feature data and the scene image feature data. And if the matching result is that the associated historical solution is not matched, and the characterization historical solution database cannot provide the solution of the current problem scene for the back-end user, generating potential problem subsystem information based on the scene characteristic data and the mapping form so as to seek corresponding technical support for a technical engineer. If the technical engineer has provided corresponding technical support, the current solution is updated into the historical solution database. If the historical solution database is queried to add a new current solution, the processing state flag of the problem scene is updated, for example, the processing state flag of the problem is updated to be 'processed'. By preferentially matching the existing historical solutions in the historical solution database and regenerating the potential problem subsystem information under the condition that the historical solution data can not provide the solutions aiming at the current problem scenes, the resources of the historical solution database can be utilized to the maximum extent, the workload of technical engineers is reduced, and the processing efficiency of equipment abnormity is improved. And the processing mark of the problem scene is updated, so that whether the problem scene is solved or not can be indicated, and the problem of equipment abnormity is prevented from being shelved for a long time or being processed repeatedly.

In some examples, image feature statistics may be used to match the recorded images of the problem scene against typical historical scene recorded images in a historical technical solution database, and optionally, structured Similarity Index (SSIM) may be selected to evaluate their similarity.

In one embodiment, as shown in fig. 4, the step of generating the subsystem information of the potential problem based on the scene feature data and the mapping table further includes:

step 410, if the matching result is that the correlation history solution is matched, sending the correlation history solution to a back-end operating system;

step 420, if a feedback result of the back-end operating system for the associated historical solution is received, updating a processing state flag of the problem scene;

and step 430, if the processing state marks of the problem scenes before and after updating are the same, generating potential problem subsystem information based on the scene characteristic data and the mapping table.

Specifically, the matching process may include feature word matching for scene text feature data, and similarity matching for scene image feature data; the scene text feature data and the historical solution database can be matched with feature words, similarity matching between the scene image feature data and the historical solution database is combined to query historical solutions with the same or similar features, for example, the historical solutions with the similarity larger than a set threshold and matched with feature words with higher importance can be used as the associated historical solutions of the scene feature data and can be provided for the back-end user in time.

Further, if the matching result is that the association history solution is matched, it is expected that the association history solution can be directly used for solving the equipment abnormity problem in the current problem scene, and the association history solution is sent to a back-end operating system, and the association history solution can be used for providing equipment abnormity solution information for a back-end user; the back-end user can perform relevant operations based on the association history solution, and can also send a feedback result through a back-end operating system based on the operation effect; if the feedback result is received, the processing state flag of the problem scene is updated correspondingly, for example, the processing state flag is updated to be "unprocessed" or "processed". If the processing state marks of the problem scenes before and after updating are the same, for example, the processing state marks are still "unprocessed", that is, the back-end user cannot solve the equipment abnormal problem in the current problem scene based on the associated history solution, the potential problem subsystem information is generated based on the scene feature data and the mapping table, so as to further seek corresponding technical support for a technical engineer. The existing historical solutions are preferentially matched in the historical solution database, and the matched associated historical solutions are sent to the back-end operating system, so that corresponding solutions can be provided for the back-end user in time, the situation that the back-end user cannot continue to operate under equipment failure for a long time or continuously operate under equipment abnormity is avoided, and a feedback result sent by the back-end user through the back-end operating system can be received in time, so that whether technical support needs to be sought for a technical engineer or not is further judged.

In some examples, similarity matching may be performed by comparing similarity between image information represented by the statistical scene image feature data and historical scene record images in each historical solution with a preset threshold. Similarity matching may include matching image structured similarity of image brightness, contrast, covariance, etc. feature data. After the image structural similarity between the recorded image of the problem scene and the recorded image of the historical scene is obtained, the recorded images of the historical scene can be arranged according to the size of the image structural similarity, and a corresponding scene image similarity list is obtained. Further, the feature words may be sorted according to importance, and whether the important feature words can be found is determined in the scene image similarity list according to the sequence of similarity from large to small, for example, whether a first important feature word can be found in a historical solution corresponding to a historical scene record image with the highest similarity is determined, where the first important feature word may be a feature word with the first importance sort; if the matching score can be found, adding the corresponding matching score to the historical scene corresponding to the historical scene record image, for example, finding 50 scores of the first important feature word plus the matching score, finding 30 scores of the second important feature word plus the matching score, finding 20 scores of the third important feature word plus the matching score, and so on. And if the corresponding important feature words are not found, directly calculating the matching total score of the historical solution, and processing the next historical solution until all the historical solutions in the scene image similarity list are traversed. And finally, outputting a list of the associated historical solutions according to the total matching scores of the historical solutions, for example, outputting the historical solutions with the total matching scores larger than the preset score as the associated historical solutions so as to provide the historical solutions with higher matching degrees for the user to inquire and refer. If the matching fails or the user selects the associated historical solution and does not solve the related scene problem, and the back end is used for confirming to continue reporting, the potential problem subsystem information can be generated based on the mapping form according to the importance ranking of the feature words, so that the technical engineer can be further searched for corresponding technical support.

In one embodiment, the mapping form comprises a mapping relation between the key feature words and the potential failure subsystem of the medical equipment; the key characteristic words are determined by characteristic word extraction and word frequency statistics; outputting a correlation file of the problem scene based on the potential problem subsystem information, wherein the correlation file comprises:

Specifically, the key feature words may be obtained by dividing according to the importance (S, signifiance) of the feature words, where the importance of the feature words may be quantitatively determined according to a corresponding rule. The information of the potential problem subsystem can be generated according to the mapping relation between the key feature words and the potential failure subsystem of the medical equipment, wherein the key feature words can be keywords which are determined after feature word extraction and word frequency statistics are carried out on the text information and are directly associated with the potential failure subsystem of the medical equipment. Further, the system files in the medical equipment system can be obtained according to the mapping relation between the subsystem information of the potential problems and the system files in the medical equipment system, and the system files are correspondingly screened and packaged to obtain an associated file used for providing equipment abnormal reference information for generating the current solution aiming at the problem scene. The system files are screened according to the mapping relation between the potential problem subsystem information and the system files in the medical equipment system to obtain the associated files, wherein the associated files of the problem scene correspond to the subsystem range of the potential fault of the medical equipment represented by the potential problem subsystem information, the associated files can provide equipment abnormity reference information for technical engineers, the technical engineers can form a current solution aiming at the problem scene according to the associated files, diagnosis data of a plurality of subsystems are not required to be checked one by one, and the equipment abnormity processing efficiency is improved.

In some examples, the key feature words may be divided according to the Frequency (F) of occurrence of each feature word in the text information, or may be divided according to the Probability (P) of characterizing the potential problem subsystem information for the feature words after being determined by the related user experience. For example, a corresponding guide information "do you feel you most likely associate the scene that you desire to report with which system modules are provided by setting a scene description form? According to the most likely, suspected, uncertain, impossible and least likely sequential selection ", according to the likelihood P selected by the back end user, the frequency F of the appeared feature words is weighted (for example, from most likely to least likely, the likelihood weighting factors are respectively set to 1,0.8,0.6,0.4,0.2), the importance of the feature words is obtained based on S = F x P, the key feature words are determined, and the potential fault subsystem of the medical equipment can be further determined according to the mapping form through the obtained key feature words, so that the subsystem range of the medical equipment, which is likely to have abnormity or fault, is reduced.

In a specific embodiment, as shown in fig. 5, a method for handling an exception of a device is provided, where the method includes:

step 502, based on the scene description form, displaying scene description guidance information through the user interaction interface, and guiding a back-end user to input scene description information for the current problem scene to obtain scene report data. Specifically, the display of the scene description guidance information may be triggered by receiving a scene reporting request sent by a back-end user for a current problem scene; the user interactive interface can be an interactive interface provided for a back-end user through a back-end operating system, and can also be a user interactive interface provided by the technical support subsystem.

And step 504, counting key feature words and/or image features according to the reported data of the scene. Specifically, scene feature data can be obtained by performing feature statistics on the scene reported data, and accordingly, the scene feature data can include scene text feature data and scene image feature data; the feature statistics may include at least one of keyword feature statistics and image feature statistics, the scene text feature data may include key feature words, and the scene image feature data may include image features.

Step 506, matching the historical solutions in the historical solution database according to the key feature words and/or the image features. Specifically, historical solutions in the historical solution database may be queried based on key feature words and/or image features to match historical solutions with the same or similar features as the associated historical solution.

If the associated historical solution is matched or the matching degree is larger than the threshold value, step 508, step 510 is executed, otherwise, step 516 is executed. Specifically, the matching degree may include feature similarity of the queried historical solution based on the key feature words and/or the image features, or may be a matching score between the historical solution and the scene feature data obtained based on the corresponding rule. If the association history solution is matched or the matching degree is greater than the threshold value, the association history solution can be provided for the back-end user reference. And if the association history solution is not matched and the matching degree is less than the threshold value, generating the subsystem information of the potential problems according to the mapping relation between the key characteristic words and the subsystem of the potential faults of the medical equipment.

At step 510, a correlation history solution is provided. Specifically, the association history solution can be provided to the backend user through the user interaction interface of the backend operating system or the user interaction interface of the technical support subsystem.

In step 512, if the user selects the scenario in which the current problem is solved and stops reporting, step 514 is executed, otherwise, step 516 is executed. Specifically, if the user selects the scenario in which the current problem is solved, it is not necessary to continue to match the associated historical solution or generate the current solution; if the user does not select the scenario in which the current problem is solved, or the user still receives a scenario reporting request, the user needs to search for corresponding technical support from a technical engineer.

Step 514, archiving, setting the current problem scenario state as solved (association history solution is queried). Specifically, the scene report data and the associated historical solution can be filed in a corresponding storage mode.

And 516, generating the subsystem information of the potential problems according to the mapping relation between the key characteristic words and the subsystem of the potential faults of the medical equipment. By generating potentially problematic subsystem information, the range of subsystems of the medical device where abnormalities or faults may occur may be narrowed.

And 518, screening and acquiring the associated files according to the mapping relation between the subsystem information of the potential problems and the system files, and packaging the associated files to obtain the technical file package. In particular, the technical document package corresponds to a range of subsystems for which the medical device is potentially faulty as characterized by potentially problematic subsystem information.

And step 520, encapsulating the scene reported data and the technical file package, and storing the scene reported data and the technical file package into a technical support subsystem for technical engineers to inquire and analyze. Specifically, the technical engineer may query the scene report data and the technical document package through an interactive interface provided by the technical support subsystem, and may further query the associated historical solution or generate the current solution based on the scene report data and the technical document package.

At step 522, archive, set the current problem scenario state as resolved (associated historical solutions queried). Specifically, the scene report data and the associated historical solution can be filed in a corresponding storage mode.

Step 524, instructing the technical engineer to intervene, generate the current solution, store it in the historical solution database, archive it, and set the current problem scenario state as solved (a new solution has been generated). Specifically, the technical engineer may generate a current solution according to a result of further querying the associated historical solution, the queried scene report data, and the technical document package, and store the current solution in the historical solution database when the current problem scene is solved.

The method can quickly report the problem scene, and reduce the communication cost between the back-end user and the technical engineer; the method has the advantages of reducing the interested range of the technical engineer, helping the technical engineer to quickly position the source of the original scene problem, timely and efficiently providing a technical scheme and improving the processing efficiency of equipment abnormity.

In a particular embodiment, as illustrated in FIG. 6, there is provided a step of matching association history solutions, the steps comprising:

step 602, processing the image information of the problem scene and each historical scene record image to obtain a plurality of corresponding image structured similarities. Specifically, matching the image information of the problem scene with each historical scene record image one by one may obtain a corresponding image structural similarity, where the image structural similarity may include a similarity matching feature data such as image brightness, contrast, and covariance, and the image structural similarity may be a weighted average of the above similarities.

And step 604, sequencing the historical scene record images according to the image structural similarity to obtain a scene image similarity list. Specifically, the values of the structured similarity of the images may be sorted from high to low to obtain a scene image similarity list including corresponding sequence numbers of the historical scene record images.

In step 606, for the historical solutions corresponding to the scene image similarity list, if the first important feature word is found, the matching score is increased by 50, step 608 is executed, otherwise, step 612 is executed. Specifically, according to various feature words corresponding to a current problem scene, including a first important feature word, a second important feature word, a third important feature word and the like obtained in a word frequency statistics manner, an importance ranking manner and the like, in a scene image similarity list, keyword search is performed in a historical solution corresponding to a historical scene (a historical scene corresponding to a historical scene recording image) under a current processing sequence number, and if the first important feature word is searched in the historical solution, a matching score of the historical solution is increased by 50; and if the first important characteristic word is not found in the historical solution, counting the matching score of the historical solution.

In step 608, if the second important feature word is found, the matching score is increased by 30, and step 610 is executed, otherwise, step 612 is executed. Specifically, on the basis of finding the first important feature word, if the second important feature word is found in the historical solution, the matching score of the historical solution is increased by 30; and if the second important characteristic word is not found in the historical solution, counting the matching score of the historical solution.

Step 610, if the third important feature word is found, the matching score is increased by 20, step 612 is executed, otherwise, step 612 is directly executed. Specifically, on the basis of finding the second important feature word, if the third important feature word is found in the historical solution, the matching score of the historical solution is increased by 20; and if the third important characteristic word is not found in the historical solution, counting the matching score of the historical solution.

Step 612, the matching scores of the historical solutions are counted. Specifically, the matching scores obtained by searching for the feature words in the historical solution over the past may be added to obtain the final matching score of the historical solution.

In step 614, if the historical solutions in the scene image similarity list are traversed, step 618 is executed, otherwise, step 616 is executed. Specifically, traversing each historical solution in the scene image similarity list to obtain a matching score corresponding to each historical solution.

In step 616, the historical solution corresponding to the next bit in the scene image similarity list is processed in step 606. Specifically, if not traversing each historical solution in the scene image similarity list, the matching score of the historical solution corresponding to the next bit in the scene image similarity list is obtained and counted.

In step 618, if there is a history solution with a matching score greater than 50, then step 620 is performed, otherwise step 622 is performed. Specifically, if a historical solution with a matching score greater than 50 exists, the degree of matching of the historical solution with the current problem scenario is considered to reach the expectation, otherwise, no historical solution with the expected degree of matching with the current problem scenario is considered to reach the expectation.

At step 620, the history solutions with matching scores greater than 50 are output as associated history solutions. Specifically, a history solution whose matching degree with the current problem scenario is expected may be output as the associated history solution.

Step 622, indicating that no association history solution is matched.

According to the method, the historical solutions can be comprehensively and quickly matched in the historical solution database by combining the image structural similarity and the important feature words, the historical solutions meeting the matching degree requirement are output as the associated historical solutions, the workload of technical engineers is reduced, the associated historical solutions can be directly provided for the back-end users, and the problem of equipment failure or abnormality in the current problem scene can be effectively solved.

To further illustrate the present solution, a specific example is described below. Fig. 7 is a schematic diagram of an architecture of the device exception handling system according to the present application. The equipment exception handling system can comprise a scene reporting module, a data analysis processing module, a data matching module, a data collecting module, a data transferring module and a technical support subsystem.

The scene reporting module may be configured to provide a graphical display interface, and based on the scene description form, may display scene description guidance information to interact with a back-end user through the graphical display interface, so as to guide the back-end user to input scene description information, where the scene description information may include text input information and image input information.

Further, the data analysis processing module may include a text information analysis module and an image information analysis module, the text information analysis module may be configured to perform feature word extraction and feature word statistics on text input information in sequence to obtain scene text feature data, and the image information analysis module may be configured to perform image character recognition and image feature statistics on image input information respectively to obtain scene image feature data, where an image character recognition result of the image information analysis module may be used for the text information analysis module to perform feature word extraction.

The data matching module can perform matching processing on the scene text characteristic data and the scene image characteristic data, the matching processing comprises characteristic word matching aiming at the scene text characteristic data and image characteristic matching aiming at the scene image characteristic data, and a matching result is obtained based on a historical solution database. If the matching result is that the association history solution is matched, providing the association history solution to a back-end user; and if the matching result is that the associated historical solution is not matched, generating and outputting the information of the potential problem subsystem based on the mapping form of the system module, wherein the mapping form of the system module can comprise the mapping relation between the scene characteristic data and the potential fault subsystem.

The data collection module may be configured to screen the technical portfolio in a system documentation database based on the potentially problematic subsystem information. The data collection module may include a DICOM file collection module for collecting DICOM files for medical images, a raw data collection module for collecting various unprocessed data, a system log collection module for collecting system logs, and other system file collection modules for collecting files other than the above files in the system file database.

The data unloading module can be used for storing the technical file package, and can also be used for respectively storing a scene description form, a scene picture record and an input technical scheme, wherein the technical scheme is a current solution and can be synchronously updated into a historical solution database.

The technical support subsystem can provide a graphical display interface and a visual input module, wherein the graphical display interface can be used for providing a display interface for querying a scene description form, a scene picture record, a technical file package and a technical scheme for a technical engineer, and the visual input module can provide software and hardware support for the technical engineer to input the technical scheme into the data transfer module.

The modules in the device exception handling system may be implemented in whole or in part by software, hardware, and combinations thereof. By the framework of the equipment exception handling system, problem scenes can be reported quickly, and the communication cost between a back-end user and a technical engineer is reduced; the method has the advantages of reducing the interested range of the technical engineer, helping the technical engineer to quickly position the source of the original scene problem, timely and efficiently providing a technical scheme and improving the processing efficiency of equipment abnormity.

It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.

Based on the same inventive concept, the embodiment of the present application further provides a device exception handling apparatus for implementing the above-mentioned device exception handling method. The implementation scheme for solving the problem provided by the apparatus is similar to the implementation scheme described in the above method, so the specific limitations in one or more embodiments of the apparatus for processing the device exception provided below may refer to the limitations on the method for processing the device exception in the above description, and are not described herein again.

In one embodiment, as shown in fig. 8, there is provided a device abnormality processing apparatus, which is applied to a medical device system; the medical equipment system comprises medical equipment and a back-end operating system connected with the medical equipment; the device comprises:

a scene reporting unit 810, configured to receive scene reporting data transmitted by a backend operating system; the scene reporting data comprises scene description information aiming at a problem scene of the medical equipment;

a feature statistics unit 820, configured to perform feature statistics on the scene reported data to obtain scene feature data;

a range determination unit 830, configured to generate potential problem subsystem information based on the scene feature data and the mapping table; the potential problem subsystem information is used for representing the range of subsystems with potential faults of the medical equipment;

a file output unit 840, configured to output a relevant file of the problem scenario based on the potential problem subsystem information; the association file is used for providing equipment exception reference information for generating the current solution.

In one embodiment, the apparatus further comprises:

the reporting guide module is used for outputting a display command if receiving a scene reporting request of a back-end operating system; the display command is used for instructing the back-end operating system to display the scene description guiding information based on the scene description form; the scene description guide information is used to guide the back-end user to input the scene description information.

In one embodiment, the feature statistics unit 820 includes:

the description information classification unit is used for classifying the scene description information to obtain text information and image information;

the text information analysis unit is used for extracting characteristic words and counting word frequency of the text information to obtain scene text characteristic data;

and the image information analysis unit is used for carrying out image text recognition and image characteristic statistics on the image information to obtain scene image characteristic data.

In one embodiment, the range determining unit 830 includes:

the data matching unit is used for inquiring the historical solution database and matching the scene characteristic data to obtain a matching result;

the first range determining unit is used for generating the subsystem information of the potential problems based on the scene characteristic data and the mapping form if the matching result is the associated historical solution which is not matched with the scene characteristic data;

the device still includes:

and the first state updating unit is used for updating the processing state mark of the problem scene if the current solution is newly added in the historical solution database.

In one embodiment, the range determining unit 830 further includes:

the data unloading unit is used for sending the association history solution to a back-end operating system if the matching result is that the association history solution is matched;

the second state updating unit is used for updating the processing state mark of the problem scene if a feedback result of the back-end operating system for the associated historical solution is received;

and the second range determining unit is used for generating the potential problem subsystem information based on the scene characteristic data and the mapping table if the processing state marks of the problem scenes before and after updating are the same.

In one embodiment, the file output unit 840 is further configured to filter system files in the medical device system according to the mapping relationship between the subsystem information of the potential problem and the system files in the medical device system, so as to obtain an association file.

The units in the device exception handling apparatus may be wholly or partially implemented by software, hardware, or a combination thereof. The units can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the units.

In one embodiment, an exception handling apparatus is provided. The exception handling apparatus comprises a memory storing a computer program and a processor implementing the steps of the method described above when executing the computer program.

In one embodiment, an exception handling device is provided, which may be a terminal, and an internal structure diagram thereof may be as shown in fig. 9. The exception handling apparatus includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Wherein the processor of the exception handling apparatus is operable to provide computational and control capabilities. The memory of the exception handling device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The communication interface of the exception handling device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a device exception handling method. The display screen of the abnormality processing device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the abnormality processing device can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the abnormality processing device, an external keyboard, a touch pad or a mouse and the like.

Those skilled in the art will appreciate that the structure shown in fig. 9 is a block diagram of only a portion of the structure related to the present application, and does not constitute a limitation on the exception handling apparatus to which the present application is applied, and a specific exception handling apparatus may include more or less components than those shown in the drawings, or combine some components, or have a different arrangement of components.

In one embodiment, an exception handling system is provided. The abnormality processing system comprises a medical equipment system and an abnormality processing device connected with the medical equipment system; the medical equipment system comprises medical equipment and a back-end operating system connected with the medical equipment;

In one embodiment, a computer-readable storage medium is provided. The computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), magnetic Random Access Memory (MRAM), ferroelectric Random Access Memory (FRAM), phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases involved in the embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A device abnormality processing method is characterized in that the method is applied to a medical device system; the medical equipment system comprises medical equipment and a back-end operating system connected with the medical equipment; the method comprises the following steps:

receiving scene reporting data transmitted by the back-end operating system; the scene reporting data comprises scene description information of a problem scene aiming at the medical equipment;

carrying out feature statistics on the scene reported data to obtain scene feature data;

generating potential problem subsystem information based on the scene characteristic data and a mapping form; the potential problem subsystem information is used for representing the range of subsystems with potential faults of the medical equipment;

outputting a relevant file of the problem scene based on the potential problem subsystem information; the association file is used for providing equipment abnormity reference information for generating the current solution.

2. The method according to claim 1, wherein before the step of receiving the scene report data transmitted by the backend operating system, further comprising the steps of:

if a scene reporting request of the back-end operating system is received, outputting a display command; the display command is used for instructing the back-end operating system to display scene description guiding information based on a scene description form; the scene description guiding information is used for guiding a back-end user to input the scene description information.

3. The method of claim 1 or 2, wherein the scene feature data comprises scene text feature data and scene image feature data; the step of performing feature statistics on the scene reported data to obtain scene feature data includes:

and performing image text recognition and image feature statistics on the image information to obtain the scene image feature data.

4. The method of claim 3, wherein the step of generating potential problem subsystem information based on the scene feature data and a mapping form comprises:

if the matching result is that the associated historical solution of the scene characteristic data is not matched, generating the subsystem information of the potential problems based on the scene characteristic data and a mapping form;

the method further comprises the following steps:

5. The method of claim 4, wherein the step of generating potential problem subsystem information based on the scene feature data and a mapping form further comprises:

if the matching result is that the association history solution is matched, sending the association history solution to the back-end operating system;

if a feedback result of the back-end operating system for the associated historical solution is received, updating a processing state mark of the problem scene;

6. The method of claim 5, wherein the mapping form comprises a mapping of key feature words and potentially malfunctioning sub-systems of the medical device; the key characteristic words are determined through the characteristic word extraction and the word frequency statistics; the step of outputting the associated file of the problem scenario based on the potential problem subsystem information includes:

7. An equipment exception handling device is characterized in that the device is applied to a medical equipment system; the medical equipment system comprises medical equipment and a back-end operating system connected with the medical equipment; the device comprises:

a scene reporting unit, configured to receive scene reporting data transmitted by the backend operating system; the scene reporting data comprises scene description information of a problem scene aiming at the medical equipment;

the file output unit is used for outputting a relevant file of the problem scene based on the potential problem subsystem information; the association file is used for providing equipment abnormity reference information for generating the current solution.

8. An exception handling apparatus comprising a memory and a processor, the memory storing a computer program, wherein the processor when executing the computer program implements the steps of the method of any one of claims 1 to 6.

9. An exception handling system, comprising a medical device system and an exception handling device connected to the medical device system; the medical equipment system comprises medical equipment and a back-end operating system connected with the medical equipment;

the exception handling apparatus comprising a memory storing a computer program and a processor implementing the steps of the method of any one of claims 1 to 6 when the computer program is executed.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.