Fault processing method and device for medical imaging equipment, equipment, medium and product

Abstract

The invention relates to a fault processing method and device for medical imaging equipment, equipment, a medium and a product. The method is applied to an intelligent terminal, medical imaging equipment and the intelligent terminal are arranged locally, and the method comprises the following steps: receiving to-be-processed fault description information from a user; inputting the to-be-processed fault description information into a first model for key information extraction to obtain a fault description field; generating auxiliary information prompts according to the fault description fields and the fault knowledge base; receiving auxiliary fault description information sent by the user in response to the auxiliary information prompt, and determining a target fault processing strategy according to the fault description field and the auxiliary fault description information; the auxiliary fault description information is determined by a user according to auxiliary information prompt; the fault knowledge base comprises a corresponding relation between a fault field and a fault processing strategy. By using the fault processing method of the medical image equipment provided by the invention, the fault processing efficiency is relatively high.

Description

Technical Field

[0001] The present application relates to the field of industrial equipment technology, and in particular to a method, device, equipment, medium and product for troubleshooting medical imaging equipment. Background Art

[0002] With the rapid improvement of social productivity and the rapid rise of industries such as new energy, equipment manufacturing, and magnetic resonance equipment, the installation volume of industrial equipment has also increased rapidly, and the efficiency requirements for handling failures of various industrial equipment have become increasingly higher.

[0003] In traditional technology, when industrial equipment fails, people usually seek help from the equipment supplier, who will arrange engineers to go to the site to troubleshoot and resolve the problem.

[0004] However, the efficiency of fault handling using methods in traditional technologies is low. Summary of the invention

[0005] Based on this, it is necessary to provide a fault handling method, device, equipment, medium and product for medical imaging equipment that can improve fault handling efficiency in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for troubleshooting a medical imaging device, which is applied to a smart terminal. The medical imaging device and the smart terminal are set locally. The method includes:

[0007] receiving the pending fault description information sent by the user in response to the auxiliary information prompt; the pending fault description information includes at least one of text information, image information and voice information describing the fault of the medical imaging device;

[0008] Input the to-be-processed fault description information into the first model to extract key information and obtain the fault description field;

[0009] Generate auxiliary information prompts based on the fault description field and fault knowledge base;

[0010] Receive auxiliary fault description information from the user, and determine the target fault handling strategy according to the fault description field and the auxiliary fault description information; the auxiliary fault description information is determined by the user according to the auxiliary information prompt, and the fault knowledge base includes the correspondence between the fault field and the fault handling strategy.

[0011] In one embodiment, generating auxiliary information prompts according to the fault description field and the fault knowledge base includes:

[0012] Searching for a target fault field from a fault knowledge base; the target fault field indicates a fault field in the fault knowledge base corresponding to the fault description field;

[0013] If multiple target fault fields are found, auxiliary information prompts are generated according to the target fault fields.

[0014] In one embodiment, the method further comprises:

[0015] If the target fault field is not found, the fault information to be processed is input into the second model for strategy prediction to obtain the target fault processing strategy.

[0016] In one embodiment, determining a target fault handling strategy according to the fault description field and the auxiliary fault description information includes:

[0017] Determine a new fault field according to the auxiliary fault description information and multiple target fault fields;

[0018] A fault handling strategy corresponding to the new fault field is searched from the fault knowledge base, and the found fault handling strategy is determined as a target fault handling strategy.

[0019] In one embodiment, the method further comprises:

[0020] Receive a verification instruction from the user based on the target fault handling strategy, and if the verification instruction indicates that the target fault handling strategy has not passed the verification, organize and store the fault description fields, and package and send them to the remote maintenance terminal.

[0021] In one embodiment, the method further comprises:

[0022] Obtaining operation data of the medical imaging device corresponding to the fault description information to be processed;

[0023] The fault description information to be processed is input into the first model to extract key information and obtain the fault description field, including:

[0024] The operation data and the description information of the fault to be processed are input into the first model to extract key information and obtain the fault description field.

[0025] In a second aspect, an embodiment of the present application provides a fault handling device for a medical imaging device, which is applied to a smart terminal. The medical imaging device and the smart terminal are set locally. The device includes:

[0026] A receiving module, used for receiving description information of the pending fault from a user; the description information of the pending fault includes at least one of text information, image information and voice information describing the fault of the medical imaging device;

[0027] An input module, used for inputting the to-be-processed fault description information into the first model to extract key information and obtain a fault description field;

[0028] A generation module, used to generate auxiliary information prompts according to the fault description field and the fault knowledge base;

[0029] A determination module is used to receive auxiliary fault description information issued by the user in response to the auxiliary information prompt, and determine a target fault handling strategy based on the fault description field and the auxiliary fault description information; the auxiliary fault description information is determined by the user based on the auxiliary information prompt, and the fault knowledge base includes a correspondence between the fault field and the fault handling strategy.

[0030] In a third aspect, an embodiment of the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method provided in the first aspect when executing the computer program.

[0031] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method provided in the first aspect are implemented.

[0032] In a fifth aspect, an embodiment of the present application further provides a computer program product, including a computer program, characterized in that when the computer program is executed by a processor, the steps of the method provided in the first aspect are implemented.

[0033] The above-mentioned fault handling method, device, equipment, medium and product of the medical imaging device, the method obtains the relevant fault description field and auxiliary fault description information about the fault of the medical imaging device through the interaction between the intelligent terminal and the user, and searches in the fault knowledge base according to the fault description field and the auxiliary fault description information, so as to determine the target fault handling strategy. In this way, the target fault handling strategy for handling the fault of the medical imaging device can be quickly determined through the interaction between the user and the intelligent terminal, so that the medical imaging device can be quickly handled according to the target fault handling strategy. In addition, after the intelligent terminal obtains the fault description field according to the received fault description information to be processed, it will generate an auxiliary information prompt according to the fault description field and the fault knowledge base, so that the user can input the auxiliary fault description information based on the auxiliary information prompt; in this way, the intelligent terminal can obtain a more accurate and detailed description of the fault of the medical imaging device, so that the target fault handling strategy can be quickly and accurately determined according to the auxiliary fault description information and the fault description field. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 is a schematic diagram of the structure of a computer device in one embodiment;

[0035] Figure 2 A schematic diagram of a process flow of a method for troubleshooting a medical imaging device in one embodiment;

[0036] Figure 3 A schematic diagram of a process flow of a method for troubleshooting a medical imaging device in another embodiment;

[0037] Figure 4 A schematic diagram of a process flow of a method for troubleshooting a medical imaging device in another embodiment;

[0038] Figure 5 A schematic diagram of a process flow of a method for troubleshooting a medical imaging device in another embodiment;

[0039] Figure 6 A schematic diagram of a process flow of a method for troubleshooting a medical imaging device in another embodiment;

[0040] Figure 7 is a schematic diagram of the structure of a fault handling system for medical imaging equipment in one embodiment;

[0041] Figure 8 FIG. 4 is a schematic diagram of the structure of a fault handling device for medical imaging equipment in an embodiment. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0043] First of all, before specifically introducing the technical solutions of the embodiments disclosed in this application, the background technology or technical evolution context on which the embodiments of this application are based is introduced. With the rapid improvement of social productivity and the rapid rise of industries such as new energy, equipment manufacturing, and magnetic resonance equipment, the installation volume of industrial equipment has also increased rapidly, and the efficiency requirements for handling failures of various industrial equipment are getting higher and higher.

[0044] In traditional technology, when industrial equipment fails, the user usually seeks help from the equipment supplier. That is, the user calls the equipment manufacturer, describes the equipment failure phenomenon, and may take some photos of the failure. After receiving the call, the equipment supplier will first provide telephone support, then generate a work order and send it to the service engineer. After receiving the work order, the service engineer goes to the faulty equipment site. After arriving at the faulty equipment site, the service engineer will confirm the failure with the user again, and then based on the description and the situation seen on site, the service engineer will screen the errors based on experience and locate the problem. The following situations may occur in the process of locating the problem: In one case, the server engineer determines that a certain hardware is damaged after troubleshooting, but the service engineer does not carry the spare parts of the hardware, so the service engineer needs to leave the user site, wait for the spare parts to be delivered, and then go to the user site for replacement. However, this will cause the cost of going back and forth to the user site. In another case, when locating the equipment failure, the service engineer needs to obtain the error log and send it to the R&D engineer in the factory to locate the fault. However, the service engineer needs to wait until the user has finished using the machine before obtaining the log, which will cause a delay in locating the problem. It can be seen that the efficiency of fault handling in the conventional technology is low. To this end, the present application provides a method for handling faults of medical imaging equipment.

[0045] The technical solution of the present application and how the technical solution of the present application solves the technical problem are described in detail below with specific embodiments.

[0046] The medical imaging device troubleshooting method provided in this application can be applied to an intelligent terminal, which can be a computer device, which can be, but is not limited to, an industrial computer, a laptop computer, and a tablet computer. The internal structure diagram of the computer device can be as follows: Figure 1 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile 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 operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a fault handling method for a medical imaging device is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball or a touch pad set on the computer device housing, or an external keyboard, touch pad or mouse, etc.

[0047] In one embodiment, Figure 2 As shown, a method for troubleshooting medical imaging equipment is provided. This embodiment uses the example that this method can be applied to a smart terminal. Medical imaging equipment may include various devices used in hospitals to obtain medical images, such as magnetic resonance scanning equipment, electronic computer tomography equipment, computer X-ray systems, etc. This embodiment does not limit the types of medical imaging equipment. Both the smart terminal and the medical imaging equipment are set locally, that is, both the smart terminal and the medical imaging equipment are set at the user end. In this embodiment, the method includes the following steps:

[0048] Step 200: Receive pending fault description information from a user, where the pending fault description information includes at least one of text information, image information, and voice information describing the fault of the medical imaging device.

[0049] When a medical imaging device fails, the user will input the failure description information to be processed into the smart terminal locally installed with the medical imaging device, that is, some description information of the phenomenon of the failure of the medical imaging device by the user.

[0050] The pending fault description information may be at least one of text information, image information, and voice information. The pending fault description information may be text information describing the fault phenomenon input into the smart terminal by observing the fault phenomenon after the medical imaging device fails; or the user may take a photo of the fault phenomenon and input the photo to the smart terminal; or the fault phenomenon may be input into the smart terminal by voice. This embodiment does not limit the specific form of the pending fault description information input by the user, and the user may select it according to the actual application scenario or the specific fault of the medical imaging device.

[0051] In an optional embodiment, the display interface of the intelligent terminal includes an input control for the description of the fault to be processed. When the user clicks the input control, a selection interface pops up on the display interface; the selection interface includes a text input control, an image input control, and a voice input control, and the user can select one according to the actual application scenario. If the user clicks the text input control, a text input box will pop up on the display interface, and the user can enter text information describing the fault of the medical imaging device in the text input box; if the user clicks the image input control, an image input box will pop up on the display interface, and the user can enter a pre-captured image in the image input box; if the user clicks the voice input control, a prompt message will pop up on the display interface to instruct the user to enter voice information describing the fault of the medical imaging device.

[0052] The image information may include at least one of a system regular maintenance report, a service interface, the color of one or more types of indicator lights, a system parameter log, etc. Feature extraction of the image information can obtain the semantic features of the image information, i.e., the description information of the fault to be processed.

[0053] In an optional embodiment, the fault description information is image information, and the image information is specifically an indicator light image of a medical imaging device. Taking a magnetic resonance imaging system as an example, the indicator light categories may include MGP, PH, QPP and PS. Different colors of the indicator lights correspond to different functions, as shown in the following table:

[0054]

[0055] Step 210: Input the to-be-processed fault description information into the first model to extract key information and obtain a fault description field.

[0056] The first model may be a large language model that is pre-trained and stored in a storage device of the smart terminal. This embodiment does not limit the specific training method of the first model, as long as its function can be achieved.

[0057] In an optional embodiment, the first model may be obtained by training an initial model using a large number of fault description information samples and fault description fields corresponding to the fault description information.

[0058] After receiving the pending fault description information input by the user, the intelligent terminal will input the pending fault description information into the first model, and the first model will extract key information from the input pending fault description information to output the fault description field. In other words, the pending fault description information input by the user is a sentence, and the first model will extract the key information in this sentence, that is, the information related to the fault of the medical imaging device, to obtain the fault description field.

[0059] Assuming that the fault description information to be processed is "My magnetic resonance equipment suddenly stopped during the scanning process, and an error code E123 was displayed on the screen", after the fault description information to be processed is input into the first model, the first model extracts key information from the fault description information to be processed, and the obtained fault description field may include "magnetic resonance equipment, scanning process, error code E123".

[0060] In an optional embodiment, the fault description field may be obtained in the following manner:

[0061] Screening the fault description information to be processed to obtain intermediate fault description information, wherein the screening process includes, for example, removing stop words and modal particles in the fault description information to be processed;

[0062] The intermediate fault description information is segmented into different character string lengths using a word segmentation method to obtain multiple word segments;

[0063] The word segmentation method can be any one of an understanding-based word segmentation method, a mechanical word segmentation method, a forward maximum matching word segmentation algorithm, a reverse maximum matching analysis method, a bidirectional maximum matching word segmentation algorithm, a minimum segmentation word segmentation algorithm and a statistical-based method.

[0064] Entity fields are determined from multiple word segments, and the entity fields are aggregated to obtain fault description fields that can reflect semantic information.

[0065] Step 220: Generate auxiliary information prompts based on the fault description field and the fault knowledge base.

[0066] The fault knowledge base stores a large number of fault fields and the fault handling strategies corresponding to the fault fields. The fault handling strategy refers to the operations required to solve the fault corresponding to the fault field.

[0067] After obtaining the fault description field output by the first model, the intelligent terminal will search for the fault field corresponding to the fault description field in the fault knowledge base according to the fault description field, and generate an auxiliary information prompt according to the fault field found. In other words, if the corresponding fault handling strategy cannot be accurately found in the fault knowledge base according to the fault description field, and the user needs to enter more detailed and accurate fault description information, the intelligent terminal will generate an auxiliary information prompt. The auxiliary information prompt is used to prompt the fault description information that needs to be entered by the user, and indicates the content of the fault description information that needs to be entered by the user.

[0068] In an optional embodiment, auxiliary information prompts may be generated according to the fault description field and the fault knowledge base, including:

[0069] According to the fault description field and the fault knowledge base, multiple fault description fields to be processed are determined;

[0070] Input multiple to-be-processed fault description fields into each head of the multi-head attention model respectively, and obtain the prompt information feature vector output by each head;

[0071] Generate auxiliary information prompts based on the prompt information feature vectors output by each head.

[0072] In another optional embodiment, an auxiliary information prompt may be generated according to the fault description field, including:

[0073] Input the fault description field into each head of the multi-head attention model respectively, and obtain the prompt information feature vector output by each head;

[0074] Generate auxiliary information prompts based on the prompt information feature vectors output by each head.

[0075] The auxiliary information prompt may be displayed in a pop-up prompt box on the display interface of the smart terminal, or may be outputted in language. This embodiment does not limit the form of the auxiliary information prompt, as long as its function can be achieved.

[0076] Step 230, receiving auxiliary fault description information from the user, and determining a target fault handling strategy according to the fault description field and the auxiliary fault description information; the auxiliary fault description information is determined by the user according to the auxiliary information prompt, and the fault knowledge base includes the correspondence between the fault field and the fault handling strategy.

[0077] After receiving the auxiliary information prompt, the user will input the auxiliary fault description information to the smart terminal according to the auxiliary information prompt. After receiving the auxiliary fault description information, the smart terminal will find the corresponding fault field and the fault handling strategy corresponding to the fault field in the fault knowledge base based on the fault description field and the auxiliary fault description information obtained by extracting key information from the fault description information to be processed, and determine the fault handling strategy as the target fault handling strategy. The target fault handling strategy refers to the method used to solve the fault of the medical imaging equipment.

[0078] In an optional embodiment, after receiving the auxiliary fault description information, the intelligent terminal inputs the auxiliary fault description information into the first model, and the first model extracts key information from the auxiliary fault description information to obtain the auxiliary fault description field; the intelligent terminal searches for the corresponding fault field in the fault knowledge base according to the fault description field and the auxiliary fault description field, as well as the fault handling strategy corresponding to the fault field, and determines the found fault handling strategy as the target fault handling strategy.

[0079] In an optional embodiment, after determining the target fault handling strategy, the intelligent terminal will display the target fault handling strategy to the user, so that the user can solve the fault of the medical imaging device according to the target fault handling strategy. The intelligent terminal can display the target fault handling strategy on the display interface so that the user can see it, or directly read it out in the form of language so that the user can hear it.

[0080] In an optional embodiment, assume that the auxiliary information prompt generated by the smart terminal based on the fault description field and the fault knowledge base is "In order to better help you solve the problem, please provide the model of the device and whether any operation was performed before the fault occurred", and the auxiliary fault description information input by the user to the smart terminal based on the auxiliary information prompt is "My device model is MR-5000X, and I just changed a new set of scanning parameters before the fault occurred". The smart terminal inputs the received auxiliary fault description information into the first model, and the first model extracts key information from it, and can obtain the auxiliary fault description field "Device model MR-5000X, before the fault, the scanning parameters were changed". The smart terminal searches the fault knowledge base for the corresponding fault handling strategy, that is, the target fault handling strategy, based on the fault description field and the auxiliary fault description field. According to the target fault handling strategy, the smart terminal will display on the display interface or use language prompts: "Please check whether the scanning parameter settings you changed are correct. Incorrect parameters may cause the device to not work properly."

[0081] The fault handling method for medical imaging equipment provided in the embodiment of the present application obtains relevant fault description fields and auxiliary fault description information about the fault of the medical imaging equipment through the interaction between the intelligent terminal and the user, and searches in the fault knowledge base according to the fault description fields and the auxiliary fault description information, so as to determine the target fault handling strategy. In this way, the target fault handling strategy for handling the fault of the medical imaging equipment can be quickly determined through the interaction between the user and the intelligent terminal, so that the medical imaging equipment can be quickly handled according to the target fault handling strategy. In addition, after the intelligent terminal obtains the fault description field according to the received fault description information to be processed, it will generate an auxiliary information prompt according to the fault description field and the fault knowledge base, so that the user can input the auxiliary fault description information based on the auxiliary information prompt; in this way, the intelligent terminal can obtain a more accurate and detailed description of the fault of the medical imaging equipment, so as to quickly and accurately determine the target fault handling strategy according to the auxiliary fault description information and the fault description field.

[0082] In an optional embodiment, the pending fault description information may be linked to or accompanied by time series information, and the fault description field obtained by extracting key information from the pending fault description information may also be linked to or accompanied by time series information, and the time when the error or event occurred may be sorted or classified through the time series information. This makes it easy to discover information hidden in a large amount of data. Time series information is usually composed of data points arranged in chronological order, and each data point represents one or more observations of an event. In the context of error log analysis, time series information can be used to explore error patterns in the time dimension, thereby facilitating subsequent problem diagnosis, performance optimization, or prediction of the future.

[0083] In an optional embodiment, the method for determining the target fault handling strategy may include one or more combinations of the following:

[0084] Trend analysis: Count the frequency of errors or events based on the fault description field to detect whether there is an upward or downward trend within a specific time period; determine the target fault handling strategy based on the detection results.

[0085] Sliding window: By applying a sliding window on the timeline, the local characteristics of errors or events within a certain period of time, such as the average value and variance, can be determined based on the fault description field; the target fault handling strategy is determined based on the local characteristics.

[0086] In an optional embodiment, the method for obtaining the fault description field may include one or more of the following combinations:

[0087] Frequency domain analysis: Through Fourier transform and other methods, the time series information in the fault description information to be processed is converted to the frequency domain for analysis to obtain the fault description field. This can obtain information hidden in high-frequency or low-frequency fluctuations. For example: low-frequency target logs hidden in high-frequency non-target logs.

[0088] Time series clustering: Cluster similar time series based on the time series information in the fault description information to be processed, so as to conduct centralized analysis or comparison and determine the fault description field. For example, if medical imaging equipment has errors at similar time points, they may be affected by the same influencing factors. Before searching the error log database, similar time series can be clustered together for analysis based on the time series information to find the root cause of the error, that is, to determine the fault description field, so as to quickly determine the corresponding target fault handling strategy later.

[0089] Semantic search: Search the fault description information to be processed based on context and semantics to determine the fault description fields. For example, "crash" and "failure" may be synonyms in some contexts. This not only determines the fault description fields based on keywords or error codes, but also improves the accuracy and reliability of the determined fault description fields.

[0090] In this embodiment, the determination of the fault description field can be combined with multiple methods. Including natural language processing, word vectors, query intent and context understanding. For natural language processing methods, semantic search usually relies on natural language processing (NLP) technology to parse text data, including part-of-speech tagging, named entity recognition, dependency parsing, etc. for the fault description information to be processed. For word vectors, through word embeddings such as Word2Vec, GloVe or BERT, the words in the fault description information to be processed can be converted into vectors, so that the similarity between words can be quantified. For query intent, when performing language search on the fault description information to be processed, the user's query intent is taken into account, not limited to the specific words used in the fault description information to be processed. For context understanding, the meaning of the word in a specific context is determined by analyzing the position of the word in the text of the fault description information to be processed and its relationship with the surrounding words.

[0091] In another optional embodiment, when the fault description information to be processed includes an error log, the method for determining the fault description field according to the fault description information to be processed may include:

[0092] Identify relevant error messages; for example, if you search for "memory leak", semantic search will not only find log entries containing "memory leak", but may also find logs related to "resource exhaustion" or "OOM (Out of Memory)".

[0093] Eliminate false positives; based on semantic understanding, accurately identify whether a term really indicates a problem in a specific context or is just irrelevant information.

[0094] Automatic classification and labeling: Automatically identify which log entries may belong to the same issue and classify or label them for further analysis.

[0095] Time series analysis: Combined with semantic search and timestamps, it is possible to accurately track how errors evolve over time, thereby obtaining accurate fault description fields.

[0096] In one embodiment, Figure 3 As shown, it is related to an implementation method of generating auxiliary information prompts according to the fault description field and the fault knowledge base, and the steps of the implementation method include:

[0097] Step 300: Search for a target fault field from a fault knowledge base; the target fault field indicates a fault field in the fault knowledge base that corresponds to the fault description field.

[0098] After obtaining the fault description field output by the first model, the intelligent terminal searches for the fault field corresponding to the fault description field, ie, the target fault field, in the fault knowledge base. The number of the target fault fields found may be only one or more.

[0099] In an optional embodiment, the intelligent terminal may calculate the similarity between the fault description field and each fault field in the fault knowledge base; compare each similarity with a preset similarity threshold, and determine the fault field with a similarity greater than the preset similarity threshold as the target fault field.

[0100] Step 310: If multiple target fault fields are found, generate auxiliary information prompts according to the target fault fields.

[0101] If the number of target fault fields found by the intelligent terminal from the fault knowledge base is more than one, that is, the similarity between multiple fault fields in the fault knowledge base and the fault description field exceeds the preset similarity threshold, auxiliary information prompts will be generated according to the multiple target fault fields found. In other words, according to the different information generated in the multiple target fault fields, the user is asked which specific situation in the multiple target fault fields it is.

[0102] Assume that the fault description field obtained by the smart terminal is "magnetic resonance equipment, stopped working", and the target fault fields found in the fault knowledge base based on the fault description field may include "magnetic resonance equipment, stopped working before scanning", "magnetic resonance equipment, stopped working during scanning", and "magnetic resonance equipment, stopped working after scanning". The smart terminal will generate auxiliary information prompts based on the target fault field, indicating the working status of the magnetic resonance equipment before it stopped working.

[0103] In an optional embodiment, if the number of target fault fields found by the intelligent terminal from the fault knowledge base is only one, the fault processing strategy corresponding to the target fault field is directly determined as the target fault processing strategy.

[0104] Step 320: If the target fault field is not found, the fault information to be processed is input into the second model for strategy prediction to obtain the target fault processing strategy.

[0105] The second model may be a large language model that is pre-trained and stored in a storage device of the smart terminal. This embodiment does not limit the specific training method of the second model, as long as its function can be achieved.

[0106] In an optional embodiment, the second model may be obtained by training the initial model using a large number of fault description information samples and fault handling strategies corresponding to the fault description information samples.

[0107] If the intelligent terminal does not find the target fault field from the fault knowledge base, that is, the similarity between each fault field in the fault knowledge base and the fault description field is less than the preset similarity threshold, the intelligent terminal will directly input the fault information to be processed into the second model, and use the second model to predict the strategy of the fault information to be processed, and output the target fault processing strategy. There can be one or more target fault processing strategies obtained by the second model.

[0108] In an optional embodiment, the target fault handling strategies obtained by the second model include multiple ones, and the execution order of the multiple target fault handling strategies is different. Assuming that the fault information to be processed is a magnet refrigeration fault, the target fault handling strategies obtained by the second model and the execution order of the target fault handling strategies are as follows:

[0109] 1) Determine whether the helium compressor adsorber has exceeded its service life and needs to be replaced;

[0110] 2) Check whether the static pressure of the helium compressor is normal. If the static pressure is normal, replace the cold head; if the static pressure is abnormal, perform 3);

[0111] 3) Refill helium to the helium compressor;

[0112] 4) After replenishing helium, if the magnet indicators are abnormal, replace the cold head.

[0113] In this embodiment, the intelligent terminal searches for a fault field corresponding to the fault description field in the fault knowledge base, and adopts different methods to determine the target fault handling strategy according to different search results. In the case where multiple target fault fields are found, auxiliary information prompts are generated according to the multiple target fault fields; auxiliary fault description information corresponding to the auxiliary information prompts is received, and the target fault handling strategy is searched in the fault knowledge base according to the target fault field and the auxiliary fault description information. In the case where the target fault field is not found, the fault information to be processed is directly input into the second model to obtain the target fault handling strategy. This makes the fault handling method of medical imaging equipment more practical and reliable.

[0114] In one embodiment, Figure 4 As shown, an implementation method for determining a target fault handling strategy according to a fault description field and auxiliary fault description information includes the following steps:

[0115] Step 400: Determine a new fault field according to the auxiliary fault description information and multiple target fault fields.

[0116] After receiving the auxiliary fault description information obtained by the user based on the auxiliary information prompt and finding multiple target fault fields from the fault knowledge base, the intelligent terminal generates a new fault field according to the auxiliary fault description information and the multiple target fault fields. This embodiment does not limit the specific method of generating the new fault field as long as its function can be achieved.

[0117] In an optional embodiment, the intelligent terminal can input the auxiliary fault description information into the first model, extract key information through the first model, and obtain the auxiliary fault description field; search in multiple target fault fields according to the auxiliary fault description field, and obtain the target fault field including the auxiliary fault description field, and determine the target fault field as a new fault field.

[0118] In another optional embodiment, the intelligent terminal may directly search for a target fault field including the fault field in the auxiliary fault description information among multiple target fault fields according to the auxiliary fault description information, and determine the found target fault field as a new fault field.

[0119] Step 410: Search the fault handling strategy corresponding to the new fault field from the fault knowledge base, and determine the found fault handling strategy as the target fault handling strategy.

[0120] After determining the new fault field, the intelligent terminal searches for a fault handling strategy corresponding to the new fault field from the fault knowledge base, and determines the found fault handling strategy as a target fault handling strategy.

[0121] In an optional embodiment, the intelligent terminal can calculate the similarity between the new fault field and each fault field in the fault knowledge base; compare each similarity with a preset similarity threshold, and determine the fault handling strategy corresponding to the fault field greater than the preset similarity threshold as the target fault handling strategy.

[0122] In this embodiment, after obtaining the auxiliary fault description information, the intelligent terminal first determines a new fault field according to the auxiliary fault description information and the multiple target fault fields corresponding to the acquired fault description information to be processed, and searches in the fault knowledge base according to the new fault field to determine the target fault processing strategy. This method of determining the target fault processing strategy is fast and easy to implement, thereby improving the efficiency of processing the faults of medical imaging equipment.

[0123] In one embodiment, the fault handling method of the medical imaging device further includes:

[0124] Receive a verification instruction from the user based on the target fault handling strategy, and if the verification instruction indicates that the target fault handling strategy has not passed the verification, organize and store the fault description fields, and package and send them to the remote maintenance terminal.

[0125] After the smart terminal obtains the target fault handling strategy and displays it to the user, the user will perform fault handling on the medical imaging device according to the target fault handling strategy. If the fault of the medical imaging device is not resolved after the user uses the target fault handling strategy to resolve the fault, the user will send a verification instruction to the smart terminal, which indicates that the user has determined that the target fault handling strategy output by the smart terminal has failed to resolve the fault of the medical imaging device.

[0126] In an optional embodiment, if the user uses the target fault handling strategy to handle the fault of the medical imaging device, and the fault of the medical imaging device is resolved, the user will send a verification instruction to the smart terminal, which indicates that the user determines that the target fault handling strategy output by the smart terminal can solve the fault of the medical imaging device. In this case, the smart terminal can use the target fault handling strategy and the description information of the to-be-handled fault corresponding to the target fault handling strategy as training samples of the second model to train the second model.

[0127] After receiving the verification instruction of the target fault strategy input by the user indicating that it has not passed the verification (that is, the target fault strategy has not solved the fault of the doctor's imaging equipment), the smart terminal will organize the fault description fields corresponding to the target fault strategy, store them in the storage device, and package them and send them to the remote maintenance terminal.

[0128] That is to say, if the verification instruction received by the smart terminal indicates that the target fault handling strategy has not passed the verification, it means that the target fault handling strategy output by the smart terminal is inaccurate, and the supplier's professional engineers are required to locate and handle the fault. In this case, the smart terminal will organize the fault description fields (multiple target fault fields and auxiliary fault description information) in the process of determining the target fault handling strategy, for example, format the fault description field, or store the target fault handling strategy, fault description field, and the fault description information to be processed in the form of tags; then package them and send them to the remote maintenance terminal.

[0129] In an optional embodiment, the organized fault description fields may be packaged by encrypting them.

[0130] In this embodiment, when the intelligent terminal receives the verification instruction input by the user indicating that the target fault handling strategy has not passed the verification, it will sort out the fault description field and package it and send it to the remote maintenance terminal. In this way, the service engineer of the remote maintenance terminal can obtain the fault description information of the faulty medical imaging device without going to the fault site, thereby reducing the mistakes or inaccuracies in the manual description of the fault phenomenon, and thus enabling the service engineer to quickly and accurately locate the fault and provide a fault handling strategy.

[0131] In one embodiment, Figure 5 As shown, the steps of the troubleshooting method for medical imaging equipment also include:

[0132] Step 500: Obtain operation data of the medical imaging device corresponding to the fault description information to be processed.

[0133] The smart terminal and the medical imaging device can be connected in communication and can obtain the operating data of the medical imaging device. The operating data of the medical imaging device can be directly transmitted to the smart terminal after being generated during the operation process, or can be first stored in the storage device of the medical imaging device and periodically transmitted to the smart terminal, or can be first stored in the storage device of the medical imaging device and transmitted to the smart terminal after receiving the acquisition instruction sent by the smart terminal. This embodiment does not limit the specific method for the smart terminal to obtain the operating data of the medical imaging device, as long as its function can be achieved.

[0134] In one embodiment, the operating data of the medical imaging device is historical operating data, which can be obtained through historical maintenance reports and current error logs. The historical problems of the medical imaging device can be known through the historical maintenance reports; the current system problems and performance trends of the medical imaging device can be determined through the current error logs, and abnormal events can be predicted in advance.

[0135] In this case, the intelligent terminal inputs the to-be-processed fault description information into the first model to extract key information to obtain an implementation method of the fault description field, and the steps of the implementation method include:

[0136] Step 510: Input the operation data and the description information of the fault to be processed into the first model to extract key information and obtain the fault description field.

[0137] In the case where the intelligent terminal can obtain the operating data of the medical imaging device corresponding to the to-be-processed fault description information, the intelligent terminal will input the acquired operating data and the to-be-processed fault description information into the first model, extract key information through the first model, and obtain the fault description field. In other words, the obtained fault description field is not only the fault description field after the key information is extracted from the to-be-processed fault description information input by the user, but also includes the fault description field obtained after analyzing the operating data of the medical imaging device.

[0138] In this embodiment, the intelligent terminal can obtain the pending fault description information of the acquired medical imaging device and the fault description field corresponding to the operating data through the first model, which can improve the accuracy of the obtained fault description field, thereby improving the accuracy and efficiency of the determined target fault handling strategy, thereby making the fault handling method of the medical imaging device more practical and reliable.

[0139] See also Figure 6 An embodiment of the present application provides a method for troubleshooting a medical imaging device, which is applied to a smart terminal. The smart terminal and the medical imaging device are set locally. The method includes the following steps:

[0140] Step 600: receiving the to-be-processed fault description information input by the user; the to-be-processed fault description information includes at least one of text information, image information and voice information describing the fault of the medical imaging device;

[0141] Step 610: Input the to-be-processed fault description information into the first model to extract key information and obtain a fault description field;

[0142] Step 620: search for a target fault field from the fault knowledge base; the target fault field indicates a fault field corresponding to the fault description field in the fault knowledge base;

[0143] Step 630: if multiple target fault fields are found, generate auxiliary information prompts according to the target fault fields;

[0144] Step 640: receiving auxiliary fault description information sent by the user in response to the auxiliary information prompt; the auxiliary fault description information is determined by the user according to the auxiliary information prompt;

[0145] Step 650: Determine a new fault field according to the auxiliary fault description information and multiple target fault fields;

[0146] Step 660: Search the fault handling strategy corresponding to the new fault field from the fault knowledge base, and determine the found fault handling strategy as the target fault handling strategy.

[0147] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0148] In one embodiment, Figure 7 As shown, the present application provides a fault processing system 10 for medical imaging equipment, which includes an interactive interface 11, a model processing module 12, an intelligent diagnosis module 13, a fault knowledge base 14 and a storage device 15.

[0149] The user inputs the pending fault description information describing the fault of the medical imaging device in the interactive interface 11. The model processing module 12 is used to receive the pending fault description information input from the interactive interface 11, extract key information from the pending fault description information, and obtain the fault description field. The intelligent diagnosis module 13 is used to receive the fault description field output by the model processing module 12, and generate auxiliary information prompts according to the fault description field and the fault field in the fault knowledge base 14, and display the auxiliary information prompts on the interactive interface 11. The user inputs auxiliary fault description information on the interactive interface 11 based on the auxiliary information prompt; the model processing module 12 is also used to receive the auxiliary fault description information input from the interactive interface 11, extract key information from the auxiliary fault description information, and obtain the auxiliary fault description field. The intelligent diagnosis module 13 is used to receive the auxiliary fault description field output by the model processing module 12, and search for the corresponding fault handling strategy in the fault knowledge base 14 according to the auxiliary fault description field and the auxiliary description field, determine it as the target fault handling strategy, and display the target fault handling strategy on the interactive interface 11. The user inputs a verification instruction on the interactive interface 11, and the verification instruction is used to indicate whether the target fault handling strategy has passed the verification. The intelligent diagnosis module 13 stores the target fault processing strategy, and the to-be-processed fault description information and the auxiliary fault description information corresponding to the target fault processing strategy in the storage device 15 based on the verification instruction.

[0150] Based on the same inventive concept, the embodiment of the present application also provides a medical imaging device fault handling device for implementing the medical imaging device fault handling method mentioned above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the medical imaging device fault handling device provided below can refer to the limitations of the medical imaging device fault handling method mentioned above, and will not be repeated here.

[0151] In one embodiment, Figure 8 As shown, a fault processing device 20 for medical imaging equipment is provided, comprising: a receiving module 21, an input module 22, a generating module 23 and a determining module 24, wherein:

[0152] The receiving module 21 is used to receive the pending fault description information from the user; the pending fault description information includes at least one of text information, image information and voice information describing the fault of the medical imaging device.

[0153] The input module 22 is used to input the to-be-processed fault description information into the first model to extract key information and obtain a fault description field.

[0154] The generating module 23 is used to generate auxiliary information prompts according to the fault description field and the fault knowledge base.

[0155] The determination module 24 is used to receive the auxiliary fault description information sent by the user in response to the auxiliary information prompt, and determine the target fault handling strategy according to the fault description field and the auxiliary fault description information; the auxiliary fault description information is determined by the user according to the auxiliary information prompt, and the fault knowledge base includes the correspondence between the fault field and the fault handling strategy.

[0156] In one embodiment, the generation module 23 includes a search unit and a generation unit. The search unit is used to search for a target fault field from the fault knowledge base; the target fault field represents a fault field in the fault knowledge base corresponding to the fault description field; the generation unit is used to generate auxiliary information prompts according to the target fault field if multiple target fault fields are found.

[0157] In one embodiment, the generation module 23 further includes an input unit, and the input unit is used to input the to-be-processed fault information into the second model for strategy prediction to obtain the target fault processing strategy if the target fault field is not found.

[0158] In one embodiment, the determination module 24 is specifically used to determine a new fault field based on the auxiliary fault description information and multiple target fault fields; search for a fault handling strategy corresponding to the new fault field from the fault knowledge base, and determine the found fault handling strategy as the target fault handling strategy.

[0159] In one embodiment, the receiving module 21 is further used to receive a user's verification instruction based on the target fault handling strategy, and when the verification instruction indicates that the target fault handling strategy has not passed the verification, the fault description field is sorted and stored, and packaged and sent to the remote maintenance terminal.

[0160] In one embodiment, the fault handling device 20 of the medical imaging equipment also includes an acquisition module, which is used to obtain the operating data of the medical imaging equipment corresponding to the fault description information to be processed; the input module 22 is also used to input the operating data and the fault description information to be processed into the first model to extract key information and obtain the fault description field.

[0161] Each module in the above-mentioned fault handling device of medical imaging equipment can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0162] In one embodiment, a computer device is provided, whose internal structure diagram can be as follows: Figure 1 As shown. Those skilled in the art can understand that Figure 1 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0163] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0164] receiving a description of a pending fault from a user; the description of the pending fault includes at least one of text information, image information, and voice information describing the fault of the medical imaging device;

[0165] Input the to-be-processed fault description information into the first model to extract key information and obtain the fault description field;

[0166] Generate auxiliary information prompts based on the fault description field and fault knowledge base;

[0167] Receive auxiliary fault description information sent by the user in response to the auxiliary information prompt, and determine the target fault handling strategy according to the fault description field and the auxiliary fault description information; the auxiliary fault description information is determined by the user according to the auxiliary information prompt, and the fault knowledge base includes the correspondence between the fault field and the fault handling strategy.

[0168] In one embodiment, when the processor executes the computer program, the following steps are also implemented: searching for a target fault field from a fault knowledge base; the target fault field represents a fault field in the fault knowledge base corresponding to the fault description field; if multiple target fault fields are found, generating auxiliary information prompts based on the target fault fields.

[0169] In one embodiment, when the processor executes the computer program, the following steps are also implemented: if the target fault field is not found, the fault information to be processed is input into the second model for strategy prediction to obtain the target fault processing strategy.

[0170] In one embodiment, when the processor executes the computer program, the following steps are also implemented: determining a new fault field based on the auxiliary fault description information and multiple target fault fields; searching for a fault handling strategy corresponding to the new fault field from a fault knowledge base, and determining the found fault handling strategy as the target fault handling strategy.

[0171] In one embodiment, when the processor executes the computer program, it also implements the following steps: receiving a user's verification instruction based on the target fault handling strategy, and when the verification instruction indicates that the target fault handling strategy has not passed the verification, organizing and storing the fault description fields, and packaging and sending them to the remote maintenance terminal.

[0172] In one embodiment, when the processor executes the computer program, the following steps are also implemented: obtaining the operating data of the medical imaging device corresponding to the fault description information to be processed; inputting the operating data and the fault description information to be processed into the first model to extract key information and obtain the fault description field.

[0173] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0174] receiving a description of a pending fault from a user; the description of the pending fault includes at least one of text information, image information, and voice information describing the fault of the medical imaging device;

[0175] Input the to-be-processed fault description information into the first model to extract key information and obtain the fault description field;

[0176] Generate auxiliary information prompts based on the fault description field and fault knowledge base;

[0177] Receive auxiliary fault description information sent by the user in response to the auxiliary information prompt, and determine the target fault handling strategy according to the fault description field and the auxiliary fault description information; the auxiliary fault description information is determined by the user according to the auxiliary information prompt, and the fault knowledge base includes the correspondence between the fault field and the fault handling strategy.

[0178] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: searching for a target fault field from a fault knowledge base; the target fault field represents a fault field in the fault knowledge base corresponding to the fault description field; if multiple target fault fields are found, generating auxiliary information prompts based on the target fault fields.

[0179] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: if the target fault field is not found, the fault information to be processed is input into the second model for strategy prediction to obtain the target fault processing strategy.

[0180] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining a new fault field based on the auxiliary fault description information and multiple target fault fields; searching for a fault handling strategy corresponding to the new fault field from a fault knowledge base, and determining the found fault handling strategy as the target fault handling strategy.

[0181] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: receiving a user's verification instruction based on the target fault handling strategy, and when the verification instruction indicates that the target fault handling strategy has not passed the verification, organizing and storing the fault description fields, and packaging and sending them to the remote maintenance terminal.

[0182] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining the operating data of the medical imaging device corresponding to the fault description information to be processed; inputting the operating data and the fault description information to be processed into the first model to extract key information and obtain the fault description field.

[0183] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0184] receiving a description of a pending fault from a user; the description of the pending fault includes at least one of text information, image information, and voice information describing the fault of the medical imaging device;

[0185] Input the to-be-processed fault description information into the first model to extract key information and obtain the fault description field;

[0186] Generate auxiliary information prompts based on the fault description field and fault knowledge base;

[0187] Receive auxiliary fault description information sent by the user in response to the auxiliary information prompt, and determine the target fault handling strategy according to the fault description field and the auxiliary fault description information; the auxiliary fault description information is determined by the user according to the auxiliary information prompt, and the fault knowledge base includes the correspondence between the fault field and the fault handling strategy.

[0188] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: searching for a target fault field from a fault knowledge base; the target fault field represents a fault field in the fault knowledge base corresponding to the fault description field; if multiple target fault fields are found, generating auxiliary information prompts based on the target fault fields.

[0189] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: if the target fault field is not found, the fault information to be processed is input into the second model for strategy prediction to obtain the target fault processing strategy.

[0190] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining a new fault field based on the auxiliary fault description information and multiple target fault fields; searching for a fault handling strategy corresponding to the new fault field from a fault knowledge base, and determining the found fault handling strategy as the target fault handling strategy.

[0191] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: receiving a user's verification instruction based on the target fault handling strategy, and when the verification instruction indicates that the target fault handling strategy has not passed the verification, organizing and storing the fault description fields, and packaging and sending them to the remote maintenance terminal.

[0192] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining the operating data of the medical imaging device corresponding to the fault description information to be processed; inputting the operating data and the fault description information to be processed into the first model to extract key information and obtain the fault description field.

[0193] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0194] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0195] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for troubleshooting a medical imaging device, characterized in that: Applied to a smart terminal, the medical imaging device and the smart terminal are set locally, and the method includes: receiving pending fault description information from a user; the pending fault description information comprising at least one of text information, image information and voice information describing the fault of the medical imaging device; Inputting the to-be-processed fault description information into the first model to extract key information and obtain a fault description field; Generate auxiliary information prompts according to the fault description field and the fault knowledge base; Receive auxiliary fault description information issued by the user in response to the auxiliary information prompt, and determine a target fault handling strategy based on the fault description field and the auxiliary fault description information; the auxiliary fault description information is determined by the user based on the auxiliary information prompt, and the fault knowledge base includes a correspondence between fault fields and fault handling strategies.

2. The method according to claim 1, characterized in that The generating of auxiliary information prompt according to the fault description field and the fault knowledge base includes: Searching for a target fault field from the fault knowledge base; the target fault field represents a fault field in the fault knowledge base corresponding to the fault description field; If multiple target fault fields are found, the auxiliary information prompt is generated according to the target fault fields.

3. The method according to claim 2, characterized in that The method further comprises: If the target fault field is not found, the to-be-processed fault information is input into the second model for strategy prediction to obtain the target fault processing strategy.

4. The method according to claim 2, characterized in that: The determining a target fault handling strategy according to the fault description field and the auxiliary fault description information includes: Determining a new fault field according to the auxiliary fault description information and the multiple target fault fields; A fault handling strategy corresponding to the new fault field is searched from the fault knowledge base, and the found fault handling strategy is determined as the target fault handling strategy.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: A verification instruction from the user based on the target fault handling strategy is received, and when the verification instruction indicates that the target fault handling strategy has not passed the verification, the fault description fields are sorted and stored, and packaged and sent to the remote maintenance terminal.

6. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Acquire the operation data of the medical imaging device corresponding to the fault description information to be processed; The step of inputting the to-be-processed fault description information into the first model to extract key information and obtain the fault description field includes: The operation data and the to-be-processed fault description information are input into the first model to extract key information, and the fault description field is obtained.

7. A fault handling device for medical imaging equipment, characterized in that: Applied to a smart terminal, the medical imaging device and the smart terminal are set locally, and the device includes: A receiving module, configured to receive description information of a pending fault from a user; the description information of the pending fault includes at least one of text information, image information and voice information describing the fault of the medical imaging device; An input module, used for inputting the to-be-processed fault description information into the first model to extract key information and obtain a fault description field; A generating module, used for generating auxiliary information prompts according to the fault description field and the fault knowledge base; A determination module is used to receive the auxiliary fault description information issued by the user in response to the auxiliary information prompt, and determine the target fault handling strategy according to the fault description field and the auxiliary fault description information; the auxiliary fault description information is determined by the user according to the auxiliary information prompt, and the fault knowledge base includes the correspondence between the fault field and the fault handling strategy.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images