Method, device, electronic device and storage medium for determining target maintenance users

Abstract

The present invention discloses a method, device, electronic device, and storage medium for determining a target maintenance user. The method includes: obtaining device-related data corresponding to the device to be repaired; determining a maintenance question text based on the device-related data; processing the maintenance question text based on a large language model to obtain maintenance reply information; determining the target maintenance attributes of each to-be-selected maintenance user based on the maintenance reply information and maintenance-related information of at least one to-be-selected maintenance user, and sending the maintenance reply information and target maintenance attributes to a target terminal, so that a management user corresponding to the target terminal can determine the target maintenance user based on the maintenance reply information and the target maintenance attributes. This method solves the problem of subjectively allocating maintenance users, resulting in a low maintenance success rate and affecting user safety, and achieves the effect of improving the compatibility of the selected target maintenance user with the fault of the device to be repaired, improving the success rate of equipment maintenance, and ensuring the safety of the target maintenance user.

Description

Technical Field

[0001] The present invention relates to the field of computer processing technology, and in particular to a method, device, electronic device and storage medium for determining a target maintenance user. Background Art

[0002] In order to ensure the stability and security of the power grid system, technicians are required to carry out timely and effective repairs on faulty power equipment in the power grid. This kind of maintenance work is a job with high technical requirements and high risk level, and needs to be assigned to appropriate technicians to ensure that the maintenance tasks can be handled smoothly.

[0003] In current maintenance operations, managers usually subjectively assign maintenance tasks to technicians based on their own experience and the qualifications of all technicians. This subjective method of assigning technicians to perform maintenance involves subjective judgment, resulting in a low degree of match between the selected technicians and the maintenance tasks, thereby reducing the safety of the technicians and leading to unsuccessful maintenance. Summary of the Invention

[0004] The present invention provides a method, device, electronic device and storage medium for determining a target maintenance user, so as to improve the compatibility between the selected target maintenance user and the fault of the equipment to be repaired, improve the success rate of equipment maintenance, ensure the safety of the target maintenance user, and thus achieve the technical effect of improving the stability and safety of the power grid system operation.

[0005] According to one aspect of the present invention, a method for determining a target maintenance user is provided, the method comprising:

[0006] Acquire device-related data corresponding to the device to be repaired; wherein the device-related data includes device operation data, fault description data, and image data containing the device to be repaired;

[0007] Determining a maintenance question text based on the device-related data;

[0008] Processing the maintenance question text based on a large language model to obtain maintenance response information; wherein the large language model is trained based on a knowledge base containing theoretical knowledge and maintenance knowledge of power equipment;

[0009] Based on the maintenance reply information and maintenance-related information of at least one maintenance user to be selected, target maintenance attributes of each of the maintenance users to be selected are determined, and the maintenance reply information and the target maintenance attributes are sent to a target terminal, so that a management user corresponding to the target terminal determines a target maintenance user based on the maintenance reply information and the target maintenance attributes.

[0010] According to another aspect of the present invention, there is provided a device for determining a target maintenance user, the device comprising:

[0011] A data acquisition module, configured to acquire device-related data corresponding to the device to be repaired; wherein the device-related data includes device operation data, fault description data, and image data of the device to be repaired;

[0012] A question text determination module, configured to determine a maintenance question text based on the equipment-related data;

[0013] a reply information determination module, configured to process the maintenance question text based on a large language model to obtain maintenance reply information; wherein the large language model is trained based on a knowledge base containing theoretical knowledge and maintenance knowledge of power equipment;

[0014] a target maintenance user determination module, configured to determine a target maintenance attribute for each of the maintenance users to be selected based on the maintenance reply information and maintenance-related information of at least one maintenance user to be selected, and to send the maintenance reply information and the target maintenance attribute to a target terminal, so that a management user corresponding to the target terminal determines a target maintenance user based on the maintenance reply information and the target maintenance attribute.

[0015] According to another aspect of the present invention, an electronic device is provided, comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to perform the method for determining a target maintenance user according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining a target maintenance user according to any embodiment of the present invention when executed.

[0020] The technical solution of the embodiment of the present invention obtains equipment-related data such as equipment operation data, fault description data and image data of the equipment to be repaired, corresponding to the equipment to be repaired; determines a maintenance question text based on the equipment-related data; processes the maintenance question text based on a large language model to obtain maintenance reply information; determines the target maintenance attributes of each user to be selected for maintenance based on the maintenance reply information and maintenance-related information of at least one user to be selected for maintenance, and sends the maintenance reply information and the target maintenance attributes to the target terminal, so that the management user corresponding to the target terminal determines the target maintenance user based on the maintenance reply information and the target maintenance attributes, thereby solving the problem of subjective allocation of maintenance users in the prior art, resulting in a low maintenance success rate and affecting user safety, and realizing a multi-dimensional equipment closing The maintenance question text is determined by connecting data, and then the theoretical knowledge and maintenance knowledge of the equipment to be maintained are parsed through a large language model to determine the maintenance reply information related to the equipment to be maintained. Then, based on the maintenance reply information and the maintenance-related information of the user to be selected for maintenance, the target maintenance attributes of the equipment to be maintained by the user to be selected for maintenance are evaluated, thereby improving the authenticity and accuracy of the maintenance attribute evaluation, so that the target maintenance attributes are adapted to the user to be selected for maintenance when repairing the equipment to be maintained. Then, the management user determines the target maintenance user based on the maintenance reply information and the target maintenance attributes, which not only improves the adaptability of the selected target maintenance user to the fault of the equipment to be maintained and improves the success rate of equipment maintenance, but also ensures the safety of the target maintenance user, thereby achieving the technical effect of improving the stability and security of the power grid system operation.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 This is a flowchart of a method for determining a target maintenance user provided in accordance with the first embodiment of the present invention;

[0024] Figure 2 This is a flowchart of a method for determining a target maintenance user provided in accordance with a second embodiment of the present invention;

[0025] Figure 32 is a schematic diagram of a device for determining a target maintenance user according to a third embodiment of the present invention;

[0026] Figure 4 It is a structural diagram of an electronic device for implementing the method for determining a target maintenance user according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Example 1

[0030] Figure 1 This is a flow chart of a method for determining a target maintenance user according to a first embodiment of the present invention. This embodiment is applicable to the case of determining a target maintenance user for a faulty device. The method can be executed by a device for determining a target maintenance user. The device for determining a target maintenance user can be implemented in the form of hardware and / or software. The device for determining a target maintenance user can be configured in a computing device. Figure 1 As shown, the method includes:

[0031] S110: Acquire device-related data corresponding to the device to be repaired.

[0032] The equipment to be repaired may refer to equipment requiring repair, and may include electrical equipment such as power generation equipment (e.g., power plant boilers, steam turbines, gas turbines, hydraulic turbines, generators, transformers, etc.) or power supply equipment (e.g., transmission lines of various voltage levels, transformers, contactors, etc.), without specific limitations. The equipment-related data includes equipment operating data, fault description data, and image data containing the equipment to be repaired.

[0033] In practical applications, when an electrical device fails, it can be designated as a device to be repaired. Operational information of the device before and during the failure can then be collected as device operation data. Images of the device under repair from different viewing angles can be captured using a camera to obtain image data containing the device. The device under repair can also be fed back to the corresponding user, allowing the user to identify the device's failure and provide feedback. When the system receives user feedback describing the device's failure, it can be considered to have received fault description data. Accordingly, device-related data for the device under repair can be obtained from the device operation data, fault description data, and image data.

[0034] S120: Determine a maintenance question text based on the device-related data.

[0035] In this embodiment, semantic analysis of device-related data can be performed to obtain the questions required to repair the device to be repaired, which can be used as maintenance question text. This maintenance question text can be a textual paragraph, such as "When device A fails, which power engineer with which skill level should be recommended for repair, and what knowledge should the engineer possess?" when communicating with the AI. It can also be a parameter description in a specific format, such as describing the relevant drawing parameters when instructing the AI ​​to draw according to a specific format.

[0036] Considering that the image data contains equipment images, the equipment images may contain fault conditions of the equipment to be repaired, such as a broken transformer wire or a welded joint. In order to more clearly understand the condition of the equipment to be repaired in the equipment image, the image scene can be represented in text form to determine the maintenance question text.

[0037] In this embodiment, the maintenance question text is determined based on the equipment association data, including: determining the descriptive information corresponding to the equipment image in the image data; determining the equipment comprehensive information based on the equipment operation data, fault description data and descriptive information; and determining the maintenance question text based on the equipment comprehensive information according to a predetermined prompt word template.

[0038] The image data may include one or more device images. The prompt word template may include multiple positions to be filled in, so that specific content is filled in the positions to be filled in to generate a maintenance question text.

[0039] Specifically, a deep learning-based image description algorithm can be used to process device images and generate text describing the device image content as the description information. Optionally, the image description algorithm can be a NIC (Neural Image Caption) algorithm or a review network (image description generation) algorithm. For example, the input is a device image, and the output can be a sentence describing the image content, such as "Transformer disconnected." Furthermore, device operating data, fault description data, and description information are combined to obtain comprehensive device information. The semantics of this comprehensive device information are analyzed, and the corresponding content is filled into the prompt word template according to the prompt word template to generate the maintenance question text. For example, the prompt word template is: [To be filled] When the following device fault occurs, 1. Device information is: [To be filled]; 2. External fault condition is: [To be filled], which skill level engineer is recommended for repair, what knowledge does the engineer need to master, and what other devices have similar faults to the [To be filled] device? [To be filled] represents the position to be filled.

[0040] S130: Process the maintenance question text based on the large language model to obtain maintenance response information.

[0041] Among them, the Large Language Model (LLM) can be a language model based on a neural network with large-scale parameters, which is trained based on a knowledge base containing theoretical knowledge and maintenance knowledge of power equipment to meet the needs of equipment maintenance in the field of power grid maintenance.

[0042] Specifically, the maintenance question text can be input as a prompt into the large language model. The large language model uses contextual information, associated knowledge, and logical reasoning mechanisms to perform semantic understanding and reasoning analysis on the maintenance question text, and provides a response content specific to the maintenance question text as maintenance response information. For example, the maintenance question text is input into the large language model to ask the question, and the large language model provides a corresponding response. For example, the maintenance response information includes the skill level required to repair the fault (such as assistant engineer, junior power engineer, senior power engineer, or senior power engineer), multiple essential maintenance knowledge A, multiple knowledge items that are prone to errors B, and other power equipment similar to the repair fault, etc., which is related to the repair of the equipment fault.

[0043] On the basis of the above technical solution, a large language model can also be pre-trained, and its implementation method can be: obtaining power equipment data corresponding to the power grid maintenance field; performing text segmentation processing on the power equipment data to obtain multiple segmented texts; encoding the segmented texts to obtain text vectors; determining a training sample set based on the text vectors of the multiple segmented texts; and training a large language model based on the training sample set.

[0044] Power equipment data includes both theoretical data and maintenance data. Theoretical data can include basic theoretical knowledge about power equipment, such as how to reverse a DC motor, how the circuitry of an asynchronous motor consists of stator and rotor windings, and the thermal and demagnetizing effects of eddy currents. Maintenance data includes knowledge about equipment maintenance, such as the use of undercurrent relays for field-weakening protection in DC motors.

[0045] In this embodiment, theoretical data of power equipment and maintenance data of various power equipment during historical maintenance by the power grid can be collected from different collection dimensions, such as instruction manuals of power generation equipment, work orders for power grid maintenance of power equipment, equipment knowledge, teaching materials, reference books, etc. on power grid technology forums. In order to improve the analysis ability of the large language model, the equipment maintenance information of the repaired equipment in the maintenance data within the preset maintenance time can also be determined to determine the maintenance result based on the equipment maintenance information; the maintenance result includes a successful maintenance or a failed maintenance; the maintenance result is updated to the maintenance data to update the power equipment data. For example, for a work order for historical maintenance of power equipment in the maintenance data, if the same fault does not recur within 30 days (i.e., the preset maintenance time), it is considered a successful maintenance, otherwise it is considered a failed maintenance, and the maintenance result is also written into the maintenance data to update the power equipment data.

[0046] Furthermore, considering that there is an upper limit on the amount of context required when asking questions using a large language model, a text segmenter such as Text Splitter can be used to segment the text in the power equipment data while ensuring the semantic integrity of the sentences as much as possible, thereby obtaining multiple segmented texts. Furthermore, a vectorization tool such as One Hot can be used to encode the segmented text, that is, to encode the segmented text into a text vector word embedding, which can then be stored in a knowledge base. When training a large language model, the text vectors of the multiple segmented texts in the knowledge base can be used to determine the training sample set, and then the large language model can be trained based on the training sample set. The technical solution provided in this embodiment acquires theoretical knowledge and maintenance knowledge of power equipment in the field of power grid maintenance to construct a knowledge base, and then trains a large language model through a knowledge base training sample set. The large language model is used to parse the knowledge points of power equipment maintenance based on a large amount of knowledge and learn the required knowledge. This enables the large language model to perform better in tasks such as question-answering and text generation for equipment maintenance in the field of power grid maintenance, and can provide more accurate responses, thereby improving the accuracy of the evaluation of power equipment maintenance, making the evaluation have a factual basis and objective results, thereby improving the safety of target maintenance users.

[0047] S140: Determine a target maintenance attribute of each user to be selected for maintenance based on the maintenance reply information and maintenance-related information of at least one user to be selected for maintenance.

[0048] The maintenance user to be selected may refer to a maintenance technician, and the maintenance-related information may include but is not limited to the user's maintenance capability, maintenance experience, historical maintenance data, etc. The target maintenance attribute may be used to characterize the risk difficulty of the user in handling the equipment failure.

[0049] In this embodiment, the maintenance response information provided by the large language model can be used to analyze the maintenance-related information of the selected maintenance user, assess the risk associated with the selected maintenance user addressing the equipment failure, and obtain the target maintenance attributes corresponding to the selected maintenance user. For example, the maintenance attributes can be represented by a numerical value, such as a higher numerical value indicates a lower handling risk coefficient, and vice versa. Alternatively, the maintenance attributes can be represented by the degree of risk or difficulty of the handling process, such as an easy maintenance difficulty indicates a low risk, or a moderate maintenance difficulty indicates a moderate risk.

[0050] S150: Send the maintenance reply information and the target maintenance attribute to the target terminal, so that the management user corresponding to the target terminal determines the target maintenance user according to the maintenance reply information and the target maintenance attribute.

[0051] Specifically, the maintenance response information and target maintenance attributes can be pushed to a target terminal, which can be a computer, mobile phone, laptop, tablet, or other device. After viewing the management user, the target terminal's management user can combine the maintenance response information and target maintenance attributes to select a user from the candidate maintenance users who is suitable for handling the equipment failure as the target maintenance user. For example, the candidate maintenance user with the lowest maintenance risk can be selected as the target maintenance user, or the candidate maintenance user with the lowest maintenance risk among those with skill level A can be selected as the target maintenance user. This allows for the scientific allocation of target maintenance users to carry out maintenance work on power equipment, thereby improving maintenance safety.

[0052] On the basis of the above technical solution, after the management user corresponding to the target terminal determines the target maintenance user based on the maintenance reply information and the target maintenance attributes, the management user can also provide feedback to the target maintenance user through the target terminal or other terminals to notify the target maintenance user of relevant maintenance information, such as the knowledge points and precautions required for maintenance, so as to help the target maintenance user better handle the fault.

[0053] Optionally, if a target maintenance user is received from the target terminal, the maintenance reply information is sent to the terminal device corresponding to the target maintenance user; if current maintenance information of the equipment to be repaired is received from the target maintenance user, the equipment association data is updated based on the current maintenance information, and the steps of determining the maintenance question text and determining the maintenance reply information are re-executed based on the updated equipment association data to send the re-determined maintenance reply information to the terminal device.

[0054] In this embodiment, the maintenance response information and target maintenance attributes can be pushed to the target terminal of the management user. When the management user approves the target maintenance user to repair the equipment to be repaired, the maintenance response information can be pushed to the target maintenance user's terminal device. During the maintenance process, the target maintenance user can use various instruments to collect operating information of the equipment to be repaired, determine the fault condition of the equipment to be repaired, and capture image data of the equipment to be repaired from different perspectives. This data can be used as the target maintenance user's current maintenance information for the equipment to be repaired. Upon receiving the current maintenance information, the system can update the device-associated data associated with the equipment to be repaired using the current maintenance information. Based on the new device-associated data, the system can return to steps S120 and S130 to determine new maintenance response information. The new maintenance response information can be pushed to the target maintenance user's terminal device for reference. This improves the efficiency and safety of fault repairs and increases the success rate of repairs by updating information on-site. Furthermore, upon receiving a query request for associated maintenance response information from the target maintenance user, the retrieved associated information can be pushed to the terminal device. For example, when a target maintenance user clicks on knowledge point A or knowledge point B in the maintenance reply information, the large language model can provide the target maintenance user with historical maintenance work orders for the same or similar power equipment for reference.

[0055] The technical solution of this embodiment obtains device-related data such as device operation data, fault description data, and image data of the device to be repaired corresponding to the device to be repaired; determines a maintenance question text based on the device-related data; processes the maintenance question text based on a large language model to obtain maintenance reply information; determines the target maintenance attributes of each user to be selected for maintenance based on the maintenance reply information and maintenance-related information of at least one user to be selected for maintenance, and sends the maintenance reply information and the target maintenance attributes to the target terminal, so that the management user corresponding to the target terminal determines the target maintenance user based on the maintenance reply information and the target maintenance attributes, thereby solving the problem of subjective allocation of maintenance users in the prior art, resulting in a low maintenance success rate and affecting user safety, and realizing multi-dimensional device association. The data determines the maintenance question text, and then the theoretical knowledge and maintenance knowledge of the equipment to be maintained are parsed through the large language model to determine the maintenance reply information related to the equipment to be maintained, so as to evaluate the target maintenance attributes of the equipment to be maintained by the user to be selected based on the maintenance reply information and the maintenance-related information of the user to be selected, thereby improving the authenticity and accuracy of the maintenance attribute evaluation, so that the target maintenance attributes are adapted to the user to be selected when repairing the equipment to be maintained, and then the management user determines the target maintenance user based on the maintenance reply information and the target maintenance attributes, which not only improves the adaptability of the selected target maintenance user to the fault of the equipment to be maintained, improves the success rate of equipment maintenance, but also ensures the safety of the target maintenance user, thereby achieving the technical effect of improving the stability and security of the power grid system operation.

[0056] Example 2

[0057] Figure 2 This is a flowchart of a method for determining target maintenance users according to the second embodiment of the present invention. Based on the previous embodiment, S130 is further refined, with the maintenance response information including the maintenance requirement level and theoretical maintenance knowledge. For detailed implementation details, please refer to the technical solution of this embodiment. Technical terms that are identical or corresponding to those in the previous embodiment are not repeated here.

[0058] like Figure 2 As shown, the method specifically includes the following steps:

[0059] S210. Determine the theoretical maximum attribute and the theoretical minimum attribute according to a predetermined evaluation standard, based on the maintenance demand level and maintenance theoretical knowledge.

[0060] Among them, the maintenance demand level refers to the skill level required to handle the equipment failure. Maintenance theoretical knowledge can include various types of theoretical knowledge, such as must-haves and common mistakes. The evaluation criteria include skill evaluation criteria and knowledge evaluation criteria. The skill evaluation criteria may refer to the scoring criteria for skill levels. For example, assuming that the skill levels are divided into four levels, from low to high, they can be divided into: elementary, intermediate, advanced, and senior. The score can be reduced by 10 for each lower level. The knowledge evaluation criteria may refer to the scoring criteria for whether the knowledge is possessed. For example, if the corresponding theoretical knowledge is possessed, 5 points will be added, and if not, 5 points will be subtracted. The theoretical highest attribute can be used to reflect the theoretical highest score of the equipment to be repaired, and the theoretical lowest attribute can be used to reflect the theoretical lowest score of the equipment to be repaired.

[0061] In this embodiment, the theoretical highest attribute can be determined by taking the maintenance requirement level in the maintenance reply information as the highest skill level, determining a base score based on this skill level, and then adjusting the base score based on the knowledge assessment criteria, assuming all maintenance knowledge in the maintenance reply information is possessed, to obtain the theoretical highest score, i.e., the theoretical highest attribute. For example, assuming the base score is 60 and there are five maintenance knowledge areas, 5 points are added for each area possessed, resulting in a theoretical highest attribute of 60 + 5 × 5 = 85. For example, the theoretical lowest attribute can be determined by taking the maintenance requirement level in the maintenance reply information as the highest skill level, determining a base score based on this skill level, and then adjusting the base score based on the knowledge assessment criteria, assuming not all maintenance knowledge in the maintenance reply information is possessed, to obtain the theoretical lowest score, i.e., the theoretical lowest attribute. For example, assuming the base score is 60 and there are five maintenance knowledge areas, 5 points are subtracted for each area not possessed, resulting in a theoretical lowest attribute of 60 - 5 × 5 = 35. It should be noted that if there are multiple types of maintenance knowledge, different scoring criteria can be set for each type to improve the accuracy of the assessment.

[0062] S220 : For each maintenance user to be selected, determine a maintenance attribute to be processed corresponding to the maintenance user to be selected based on the evaluation criteria, the maintenance reply information, and the maintenance-related information of the maintenance user to be selected.

[0063] In this embodiment, the implementation method for determining the pending maintenance attributes corresponding to each user to be selected for maintenance is the same, and the determination of the pending maintenance attributes of any user to be selected for maintenance can be used as an example for introduction. Taking a user to be selected for maintenance as an example, the user's maintenance skill level, work orders for historically repaired power equipment, etc. can be retrieved as maintenance-related information. The historically repaired power equipment can be power equipment of the same type as the equipment to be repaired or other power equipment of similar types; or, it can be power equipment with the same fault as the equipment to be repaired or other power equipment with similar faults. Furthermore, by comparing the maintenance demand level with the maintenance skill level of the user to be selected for maintenance, a score for maintenance skills can be determined based on skill evaluation standards; by analyzing maintenance-related information to analyze whether the user has mastered or not mastered maintenance theory knowledge, a score for knowledge mastery can be determined based on the analysis results according to the knowledge evaluation standards; and then, by integrating the score for maintenance skills and the score for knowledge mastery, the pending maintenance attributes of the user to be selected for maintenance can be determined. Alternatively, the rating of maintenance skills may be used as a basic rating; and then, through analysis of the user's mastery or non-mastery of maintenance theory knowledge, the basic rating may be adjusted according to the knowledge assessment standard, and the adjusted rating may be used as the maintenance attribute to be processed.

[0064] In this embodiment, according to the evaluation criteria, based on the maintenance reply information and the maintenance-related information of the user to be selected for maintenance, the pending maintenance attributes corresponding to the user to be selected for maintenance are determined, including: according to the skill evaluation criteria, based on the maintenance demand level and the maintenance skill level in the maintenance-related information, the basic maintenance attributes are determined; wherein the maintenance-related information also includes historical maintenance data and user processing type; based on the historical maintenance data, the possession result of maintenance theoretical knowledge is determined; based on the possession result and the user processing type, the basic maintenance attributes are processed according to the knowledge evaluation criteria to obtain the pending maintenance attributes corresponding to the user to be selected for maintenance.

[0065] The user processing type may represent the type of processing performed by the user when handling equipment failure tasks, such as main repair (mainly performing maintenance), auxiliary repair (assisting in processing as an auxiliary), and learning (learning as a learner).

[0066] In practical applications, the maintenance skill level of the user to be selected for maintenance can be compared with the maintenance need level to obtain a basic score, which serves as the basic maintenance attribute. For example, if the maintenance skill level of the user to be selected for maintenance is equal to the maintenance need level given by the large language model, the basic score is 60 points. For each level lower than the maintenance need level, 10 points are subtracted from the 60-point score; for each level higher than the maintenance need level, 10 points are added to the 60-point score. Furthermore, historical maintenance data can be input into the large language model, which analyzes whether the user to be selected for maintenance possesses the relevant maintenance theoretical knowledge. Based on the possessed knowledge, the user's processing type, and the knowledge assessment criteria, the basic maintenance attribute is adjusted to obtain the adjusted attribute value as the maintenance attribute to be processed. For example, the model analyzes whether the user has mastered maintenance theoretical knowledge A and whether they have made mistakes in maintenance theoretical knowledge B. Then, based on the user's processing type, the basic maintenance attribute is added or subtracted to obtain the final score, which is the maintenance attribute to be processed.

[0067] For example, if the user to be selected for maintenance has mastered theoretical knowledge A as the main personnel, 5 points will be added; if the user to be selected for maintenance has mastered theoretical knowledge A as the learner, 2 points will be added; if the user to be selected for maintenance has made a mistake in theoretical knowledge B as the main personnel, 5 points will be deducted; if the user to be selected for maintenance has made a mistake in theoretical knowledge B as the learner, 2 points will be deducted.

[0068] It should be noted that a user's historical maintenance data may include both failed and successful maintenance data. Considering that a failed maintenance data may be due to the user's lack of certain maintenance knowledge, which may affect the user's maintenance assessment, and considering that a successful maintenance data may be due to the user's mastery of certain theoretical knowledge, which may also affect the user's maintenance assessment, different historical maintenance data can be analyzed to determine which maintenance knowledge the user possesses and which they lack, thereby conducting a maintenance assessment. Optionally, the maintenance knowledge in the successful maintenance data and / or failed maintenance data in the historical maintenance data may include essential knowledge and / or error-prone knowledge. Determining the possession of maintenance knowledge based on the historical maintenance data includes: if the successful maintenance data determines that the user to be selected for maintenance possesses the essential knowledge, then determining possession of the essential knowledge; if the failed maintenance data determines that the user to be selected for maintenance does not possess error-prone knowledge, then determining possession of the error-prone knowledge.

[0069] In this embodiment, the successful repair data can be analyzed to determine whether the user to be selected for repair possesses the required knowledge. If so, the possessed result for the required knowledge is determined to be possessed; if not, the possessed result for the required knowledge is determined to be not possessed. The failed repair data can also be analyzed to determine whether the user to be selected for repair possesses fallible knowledge. If not, the possessed result for fallible knowledge is determined to be not possessed. For example, in the successful repair data, if the user to be selected for repair possesses required knowledge A, the possessed result for required knowledge A is determined to be possessed. In the failed repair data, if the user to be selected for repair makes a mistake with fallible knowledge B, the possessed result for fallible knowledge B is determined to be not possessed.

[0070] In this embodiment, if it is impossible to determine in the historical maintenance data whether the user to be selected for maintenance has mastered the necessary knowledge or has made mistakes in the knowledge that is easy to fall into error, then other knowledge points similar to the necessary knowledge and the knowledge that is easy to fall into error are searched based on the large language model, and the mastery of the necessary knowledge and the knowledge that is easy to fall into error is judged based on the other knowledge points.

[0071] It should be noted that a limit can be set on the number of times maintenance theory knowledge can be analyzed. For example, for the same required knowledge, a score can be calculated based on a maximum of three results, thereby increasing the impact of the frequency of knowledge points on skills. It should also be noted that the above steps S210 to S220 can be performed sequentially or in parallel, and the specific execution order is not limited. The above order is only the order in which the technical solutions in each step are explained, not the execution order of each step.

[0072] S230: Determine a target maintenance attribute corresponding to the maintenance user to be selected based on the theoretical maximum attribute, the theoretical minimum attribute, and the maintenance attribute to be processed.

[0073] It should be noted that different equipment failures require different design knowledge points, and the theoretical upper and lower limits of scores are also different. For example, some simple failures, such as tripping, may be caused by excessive voltage loads in the vicinity, which can be solved with a simple investigation, and the theoretical maximum score may be only 80 points; some complex failures, such as a circuit breaker failure that causes a power outage, require a switching operation, and the theoretical maximum score may be 120 points. The scoring standards for different equipment failures are not constant. For a simple failure, getting 70 points means something different than getting 70 points for a complex failure. Based on this, in order to improve the accuracy of the maintenance attribute evaluation for users who choose maintenance, the maintenance attributes to be processed can be normalized by the theoretical maximum attribute and theoretical minimum attribute corresponding to the equipment failure, and the maintenance attributes to be processed can be normalized to a set range for evaluation, such as a 100-point range.

[0074] Specifically, the theoretical maximum and minimum attributes are substituted into the Min-Max Scaling function to normalize the attributes to be repaired, mapping them to the [0, 100] segment to obtain a final score. This final score can be used as the target repair attribute, or it can be used to determine the risk difficulty of the selected repair user when repairing the device to be repaired, using the risk difficulty as the target repair attribute. For example, if the final score is between (90, 100], the repair difficulty for the selected repair user is determined to be easy, with low risk; if the final score is between (80, 90], the repair difficulty is determined to be average, with average risk; if the final score is between (70, 80], the repair difficulty is determined to be difficult, with controllable risk; and if the final score is between [0, 70], the risk is high, and the selected repair user is prohibited from repairing the device to be repaired, thereby ensuring the safety of the repair user while also ensuring the success rate of the repair.

[0075] The technical solution of this embodiment determines the theoretical maximum attribute and the theoretical minimum attribute based on the maintenance requirement level and maintenance theoretical knowledge through predetermined evaluation criteria. At the same time, based on the evaluation criteria, the maintenance requirement level and maintenance theoretical knowledge, as well as the maintenance-related information of the user to be selected for maintenance, the pending maintenance attributes of the user to be selected for maintenance are analyzed. Then, by normalizing the pending maintenance attributes based on the theoretical maximum attribute and the theoretical minimum attribute, the target maintenance attributes are obtained, ensuring that the target maintenance attributes under different faults are within the same standard, thereby improving the accuracy of the user maintenance attribute evaluation.

[0076] Example 3

[0077] Figure 3 Schematic diagram of a device for determining a target maintenance user according to the third embodiment of the present invention. Figure 3 As shown, the device includes: a data acquisition module 310 , a question text determination module 320 , a reply information determination module 330 and a target maintenance user determination module 340 .

[0078] Among them, the data acquisition module 310 is used to obtain equipment-related data corresponding to the equipment to be repaired; wherein the equipment-related data includes equipment operation data, fault description data and image data containing the equipment to be repaired; the question text determination module 320 is used to determine the maintenance question text based on the equipment-related data; the reply information determination module 330 is used to process the maintenance question text based on a large language model to obtain maintenance reply information; wherein the large language model is trained based on a knowledge base containing theoretical knowledge and maintenance knowledge of power equipment; the target maintenance user determination module 340 is used to determine the target maintenance attributes of each of the maintenance users to be selected based on the maintenance reply information and the maintenance-related information of at least one maintenance user to be selected, and send the maintenance reply information and the target maintenance attributes to the target terminal, so that the management user corresponding to the target terminal determines the target maintenance user based on the maintenance reply information and the target maintenance attributes.

[0079] The technical solution of this embodiment obtains device-related data such as device operation data, fault description data, and image data of the device to be repaired corresponding to the device to be repaired; determines a maintenance question text based on the device-related data; processes the maintenance question text based on a large language model to obtain maintenance reply information; determines the target maintenance attributes of each user to be selected for maintenance based on the maintenance reply information and maintenance-related information of at least one user to be selected for maintenance, and sends the maintenance reply information and the target maintenance attributes to the target terminal, so that the management user corresponding to the target terminal determines the target maintenance user based on the maintenance reply information and the target maintenance attributes, thereby solving the problem of subjective allocation of maintenance users in the prior art, resulting in a low maintenance success rate and affecting user safety, and realizing multi-dimensional device association. The data determines the maintenance question text, and then the theoretical knowledge and maintenance knowledge of the equipment to be maintained are parsed through the large language model to determine the maintenance reply information related to the equipment to be maintained, so as to evaluate the target maintenance attributes of the equipment to be maintained by the user to be selected based on the maintenance reply information and the maintenance-related information of the user to be selected, thereby improving the authenticity and accuracy of the maintenance attribute evaluation, so that the target maintenance attributes are adapted to the user to be selected when repairing the equipment to be maintained, and then the management user determines the target maintenance user based on the maintenance reply information and the target maintenance attributes, which not only improves the adaptability of the selected target maintenance user to the fault of the equipment to be maintained, improves the success rate of equipment maintenance, but also ensures the safety of the target maintenance user, thereby achieving the technical effect of improving the stability and security of the power grid system operation.

[0080] On the basis of the above device, optionally, the question text determination module 320 includes a description information determination unit, a comprehensive information determination unit and a question text determination unit.

[0081] a description information determining unit, configured to determine description information corresponding to the device image in the image data;

[0082] a comprehensive information determining unit, configured to determine comprehensive device information based on the device operation data, the fault description data, and the description information;

[0083] The question text determination unit is used to determine the maintenance question text based on the equipment comprehensive information according to a predetermined prompt word template.

[0084] Based on the above device, optionally, the maintenance reply information includes the maintenance requirement level and maintenance theoretical knowledge, and the target maintenance user determination module 340 includes a highest and lowest attribute determination unit, a pending maintenance attribute determination unit and a target maintenance attribute determination unit.

[0085] a maximum and minimum attribute determination unit, configured to determine a theoretical maximum attribute and a theoretical minimum attribute based on the maintenance requirement level and the maintenance theoretical knowledge according to a predetermined evaluation standard; wherein the evaluation standard includes a skill evaluation standard and a knowledge evaluation standard;

[0086] a pending maintenance attribute determination unit configured to determine, for each of the pending maintenance users, a pending maintenance attribute corresponding to the pending maintenance user based on the evaluation criteria, the maintenance reply information, and the maintenance-related information of the pending maintenance user;

[0087] The target maintenance attribute determination unit is configured to determine a target maintenance attribute corresponding to the maintenance user to be selected based on the theoretical maximum attribute, the theoretical minimum attribute, and the maintenance attribute to be processed.

[0088] On the basis of the above device, optionally, the pending maintenance attribute determination unit includes a basic maintenance attribute determination subunit, a possess result determination subunit and a pending maintenance attribute determination subunit.

[0089] a basic maintenance attribute determination subunit, configured to determine basic maintenance attributes based on the skill assessment criteria, the maintenance requirement level, and the maintenance skill level in the maintenance-related information; wherein the maintenance-related information also includes historical maintenance data and user processing type;

[0090] a possession result determination subunit, configured to determine a possession result of the maintenance theoretical knowledge based on the historical maintenance data;

[0091] The to-be-processed maintenance attribute determination subunit is configured to process the basic maintenance attributes according to the knowledge evaluation standard based on the possessing result and the user processing type, and obtain the to-be-processed maintenance attributes corresponding to the to-be-selected maintenance user.

[0092] On the basis of the above-mentioned device, optionally, the historical maintenance data includes maintenance success data and / or maintenance failure data, and the maintenance theoretical knowledge includes essential knowledge and / or error-prone knowledge; the possession result determination subunit is used to determine the possession result of the essential knowledge if it is determined based on the maintenance success data that the user to be selected for maintenance has mastered the essential knowledge; if it is determined based on the maintenance failure data that the user to be selected for maintenance does not master the error-prone knowledge, then determine the non-possession result of the error-prone knowledge.

[0093] Based on the above device, optionally, the device also includes: a large language model determination module, which includes a power equipment data acquisition unit, a segmented text determination unit, a text vector determination unit, a training sample set determination unit and a model training unit.

[0094] An electric power equipment data acquisition unit, configured to acquire electric power equipment data; wherein the electric power equipment data includes equipment theoretical data and maintenance data;

[0095] A segmented text determination unit, configured to perform text segmentation processing on the power equipment data to obtain a plurality of segmented texts;

[0096] A text vector determination unit, configured to encode the segmented text to obtain a text vector;

[0097] a training sample set determining unit, configured to determine a training sample set based on the text vectors of the plurality of segmented texts;

[0098] A model training unit is used to train the large language model based on the training sample set.

[0099] On the basis of the above device, optionally, the device further includes: an electric equipment data updating module, and the electric equipment data updating module includes a maintenance result determining unit and an electric equipment data updating unit.

[0100] a maintenance result determination unit, configured to determine equipment maintenance information of the repaired equipment in the maintenance data within a preset maintenance time, and determine a maintenance result based on the equipment maintenance information; wherein the maintenance result includes a maintenance success or a maintenance failure;

[0101] The power equipment data updating unit is configured to update the maintenance result into the maintenance data to update the power equipment data.

[0102] Based on the above device, optionally, the device further includes: a target maintenance user receiving module and an equipment associated data updating module.

[0103] a target maintenance user receiving module, configured to send the maintenance reply information to a terminal device corresponding to the target maintenance user upon receiving the target maintenance user fed back by the target terminal;

[0104] The device-associated data updating module is configured to update the device-associated data based on the current maintenance information received from the target maintenance user for the device to be repaired, and to re-execute the steps of determining the maintenance question text and determining the maintenance reply information based on the updated device-associated data, so as to send the re-determined maintenance reply information to the terminal device.

[0105] The device for determining a target maintenance user provided by an embodiment of the present invention can execute the method for determining a target maintenance user provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0106] Example 4

[0107] Figure 4 1 is a schematic diagram of the structure of an electronic device that implements the method for determining a target maintenance user of an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0108] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0109] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0110] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for determining a target maintenance user.

[0111] In some embodiments, the method for determining a target maintenance user may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for determining a target maintenance user described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to execute the method for determining a target maintenance user in any other appropriate manner (e.g., via firmware).

[0112] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0113] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0114] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0115] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0116] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0117] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0118] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0119] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for determining target maintenance users, characterized in that: include: Acquire device-related data corresponding to the device to be repaired; wherein the device-related data includes device operation data, fault description data, and image data containing the device to be repaired; Determining a maintenance question text based on the device-related data; Processing the maintenance question text based on a large language model to obtain maintenance response information; wherein the large language model is trained based on a knowledge base containing theoretical knowledge and maintenance knowledge of power equipment; determining a target maintenance attribute for each of the to-be-selected maintenance users based on the maintenance reply information and maintenance-related information of at least one to-be-selected maintenance user, and sending the maintenance reply information and the target maintenance attribute to a target terminal, so that a management user corresponding to the target terminal determines a target maintenance user based on the maintenance reply information and the target maintenance attribute; The maintenance response information includes a maintenance requirement level and maintenance theoretical knowledge; and determining a target maintenance attribute of each of the to-be-selected maintenance users based on the maintenance response information and maintenance-related information of at least one to-be-selected maintenance user includes: Determining a theoretical maximum attribute and a theoretical minimum attribute based on the maintenance demand level and the maintenance theoretical knowledge according to predetermined evaluation criteria; wherein the evaluation criteria include a skill evaluation criteria and a knowledge evaluation criteria; For each of the maintenance users to be selected, determining a pending maintenance attribute corresponding to the maintenance user to be selected according to the evaluation criteria, based on the maintenance reply information and the maintenance-related information of the maintenance user to be selected; Based on the theoretical maximum attribute, the theoretical minimum attribute, and the to-be-processed maintenance attribute, a target maintenance attribute corresponding to the to-be-selected maintenance user is determined.

2. The method according to claim 1, characterized in that The determining of the maintenance question text based on the device-related data includes: determining descriptive information corresponding to the device image in the image data; Determining comprehensive device information based on the device operation data, the fault description data, and the description information; The maintenance question text is determined based on the equipment comprehensive information according to a predetermined prompt word template.

3. The method according to claim 1, characterized in that The determining, according to the evaluation criteria and based on the maintenance reply information and the maintenance-related information of the user to be selected for maintenance, a pending maintenance attribute corresponding to the user to be selected for maintenance includes: Determining basic maintenance attributes based on the skill assessment criteria, the maintenance requirement level, and the maintenance skill level in the maintenance-related information; wherein the maintenance-related information also includes historical maintenance data and user processing type; Determining the results of possessing the maintenance theoretical knowledge based on the historical maintenance data; Based on the possessing result and the user processing type, the basic maintenance attributes are processed according to the knowledge evaluation standard to obtain the maintenance attributes to be processed corresponding to the maintenance user to be selected.

4. The method according to claim 3, characterized in that The historical maintenance data includes maintenance success data and / or maintenance failure data, and the maintenance theoretical knowledge includes essential knowledge and / or error-prone knowledge; and determining the possession result of the maintenance theoretical knowledge based on the historical maintenance data includes: If it is determined based on the maintenance success data that the to-be-selected maintenance user possesses the necessary knowledge, determining whether the necessary knowledge is possessed; If it is determined based on the maintenance failure data that the user to be selected for maintenance does not possess the error-prone knowledge, then it is determined that the user does not possess the error-prone knowledge.

5. The method according to claim 1, wherein Also includes: Train to obtain a large language model; The training obtains a large language model, including: Acquiring power equipment data; wherein the power equipment data includes equipment theoretical data and maintenance data; Performing text segmentation processing on the power equipment data to obtain multiple segmented texts; Encoding the segmented text to obtain a text vector; Determine a training sample set based on the text vectors of the plurality of segmented texts; The large language model is obtained by training based on the training sample set.

6. The method according to claim 4, characterized in that Also includes: Determining equipment maintenance information of the repaired equipment in the maintenance data within a preset maintenance time, and determining a maintenance result based on the equipment maintenance information; wherein the maintenance result includes a repair success or a repair failure; The maintenance result is updated into the maintenance data to update the electric equipment data.

7. The method according to claim 1, characterized in that Also includes: If the target maintenance user fed back by the target terminal is received, the maintenance reply information is sent to the terminal device corresponding to the target maintenance user; If the current maintenance information of the target maintenance user on the equipment to be repaired is received, the equipment-related data is updated based on the current maintenance information, and the steps of determining the maintenance question text and determining the maintenance reply information are re-executed based on the updated equipment-related data to send the re-determined maintenance reply information to the terminal device.

8. A device for determining target maintenance users, characterized in that: include: A data acquisition module, configured to acquire device-related data corresponding to the device to be repaired; wherein the device-related data includes device operation data, fault description data, and image data of the device to be repaired; A question text determination module, configured to determine a maintenance question text based on the equipment-related data; a reply information determination module, configured to process the maintenance question text based on a large language model to obtain maintenance reply information; wherein the large language model is trained based on a knowledge base containing theoretical knowledge and maintenance knowledge of power equipment; a target maintenance user determining module, configured to determine a target maintenance attribute for each of the maintenance users to be selected based on the maintenance reply information and maintenance-related information of at least one maintenance user to be selected, and to send the maintenance reply information and the target maintenance attribute to a target terminal, so that a management user corresponding to the target terminal determines a target maintenance user based on the maintenance reply information and the target maintenance attribute; The maintenance reply information includes the maintenance requirement level and maintenance theoretical knowledge; the target maintenance user determination module includes: a maximum and minimum attribute determination unit, configured to determine a theoretical maximum attribute and a theoretical minimum attribute based on the maintenance requirement level and the maintenance theoretical knowledge according to a predetermined evaluation standard; wherein the evaluation standard includes a skill evaluation standard and a knowledge evaluation standard; a pending maintenance attribute determination unit configured to determine, for each of the pending maintenance users, a pending maintenance attribute corresponding to the pending maintenance user based on the evaluation criteria, the maintenance reply information, and the maintenance-related information of the pending maintenance user; The target maintenance attribute determination unit is configured to determine a target maintenance attribute corresponding to the maintenance user to be selected based on the theoretical maximum attribute, the theoretical minimum attribute, and the maintenance attribute to be processed.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining a target maintenance user according to any one of claims 1 to 7 when executed.

Images