Power equipment state evaluation method and device, electronic equipment and storage medium

Abstract

The invention provides a power equipment state evaluation method and device, electronic equipment and a readable storage medium, and relates to the technical field of power equipment operation inspection.The method comprises the steps that inspection records of power equipment are obtained, and the inspection records are records of the power equipment in a preset time period; prompt information corresponding to the power equipment is generated, the prompt information is used for indicating an evaluation model to carry out state evaluation on the power equipment according to a step sequence indicated by the prompt information, and the evaluation model is a model used for evaluating the state of the power equipment; and inputting the inspection record and the prompt information into the evaluation model, and evaluating the state of the power equipment according to the step sequence indicated by the prompt information based on the inspection record through the evaluation model to obtain a state evaluation result of the power equipment. According to the invention, the accuracy of power equipment state evaluation is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment operation and inspection, and in particular to a method, device, electronic equipment and storage medium for evaluating the state of power equipment. Background Art

[0002] Nowadays, Natural Language Processing (NLP) technology has been applied in many fields, and the field of power equipment operation and maintenance technology is no exception. NLP technology can help power equipment operation and maintenance personnel obtain equipment operation status information faster and more accurately in equipment fault diagnosis and prediction, maintenance management, and equipment performance evaluation, thereby improving the reliability and operation efficiency of power equipment.

[0003] In the prior art, a large language model is usually combined with a power inspection knowledge base to train a model capable of generating power equipment operating status scores, wherein inspection records can be directly input into the trained model to obtain a report on the power equipment operating status scores. Before training a model capable of generating power equipment operating status scores, large-scale data needs to be fine-tuned.

[0004] Therefore, there is a problem in the prior art that the accuracy of power equipment status assessment is relatively poor. Summary of the invention

[0005] The embodiments of the present invention provide a method and device for evaluating the state of electric equipment, an electronic device and a readable storage medium to solve the problem of poor accuracy in evaluating the state of electric equipment in the prior art.

[0006] To solve the above problems, the present invention is achieved as follows:

[0007] In a first aspect, an embodiment of the present invention provides a method for evaluating a state of an electric power device, comprising:

[0008] Obtaining inspection records of the power equipment, where the inspection records are records of the power equipment within a preset time period;

[0009] Generate prompt information corresponding to the electric power equipment, wherein the prompt information is used to instruct an evaluation model to perform a status evaluation on the electric power equipment according to a step sequence indicated by the prompt information, and the evaluation model is a model used to evaluate the status of the electric power equipment;

[0010] The inspection record and the prompt information are input into the evaluation model, and the evaluation model evaluates the status of the power equipment based on the inspection record and in the order of steps indicated by the prompt information to obtain a status evaluation result of the power equipment.

[0011] In a second aspect, an embodiment of the present invention further provides a device for evaluating the state of an electric power device, comprising:

[0012] An acquisition module is used to acquire inspection records of electric equipment, where the inspection records are records of electric equipment within a preset time period;

[0013] A generating module, used for generating prompt information corresponding to the electric power equipment, wherein the prompt information is used for instructing an evaluation model to perform a status evaluation on the electric power equipment according to a sequence of steps indicated by the prompt information, and the evaluation model is a model for evaluating the status of the electric power equipment;

[0014] A processing module is used to input the inspection record and the prompt information into the evaluation model, and evaluate the status of the power equipment through the evaluation model based on the inspection record and in the order of steps indicated by the prompt information to obtain the status evaluation result of the power equipment.

[0015] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps in the method for evaluating the status of electric power equipment as described in the first aspect above are implemented.

[0016] In a fourth aspect, an embodiment of the present invention further provides a readable storage medium for storing a program, wherein when the program is executed by a processor, the steps in the method for evaluating the state of electric power equipment as described in the first aspect above are implemented.

[0017] In an embodiment of the present invention, firstly, the inspection record of the power equipment is obtained, and the prompt information corresponding to the power equipment is generated. Then, the inspection record and the prompt information are input into an evaluation model, and the status of the power equipment is evaluated based on the inspection record through the evaluation model and in sequence according to the steps indicated by the prompt information, thereby obtaining an evaluation result of the status of the power equipment. The evaluation is performed step by step according to the prompt information, thereby improving the accuracy of the status evaluation of the electronic equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0019] Figure 1 This is one of the flow charts of a method for evaluating the state of electric equipment provided by an embodiment of the present invention;

[0020] Figure 2This is a second flowchart of a method for evaluating the state of electric power equipment provided by an embodiment of the present invention;

[0021] Figure 3 It is one of the example block diagrams provided by the embodiment of the present invention;

[0022] Figure 4 This is a second example block diagram provided by an embodiment of the present invention;

[0023] Figure 5 is a structural diagram of a power equipment status assessment device provided by an embodiment of the present invention;

[0024] Figure 6 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are 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 creative work are within the scope of protection of the present invention.

[0026] See also Figure 1 , Figure 1 is one of the flow charts of a method for evaluating the state of an electric power device provided by an embodiment of the present invention, such as Figure 1 As shown, the following steps are included:

[0027] Step 101: Obtain inspection records of power equipment, where the inspection records are records of the power equipment within a preset time period.

[0028] The above inspection record can be understood as a record of the abnormal state of the above-mentioned power equipment within a preset time period, wherein the above inspection record may include the number of the above-mentioned electronic device, the specific time when the abnormal state occurred and the measurement value corresponding to the above-mentioned electronic device when the abnormal state occurred, for example: "January 01, 2023, 03:23am, equipment number: A, a short circuit shock occurred, and the current measurement value was 20KA". In the above example, the abnormal state of device A was caused by a short circuit shock, and the corresponding measurement value in the inspection record is the current measurement value of 20KA.

[0029] It should be understood that the inspection record of the electronic device may include multiple items, for example, the inspection record may be as follows:

[0030] 1) January 1, 2023, 01:00am, equipment number: B, acetylene content 4μl / l, hydrogen content 100μl / l;

[0031] 2) January 02, 2023, 14:00am, equipment number: C, acetylene content 6μl / l, hydrogen content 152μl / l.

[0032] In the above example, it can be understood that the abnormal state of the electronic device is recorded when the preset time is two days. For the above preset time, relevant staff can set it according to actual conditions, and this embodiment of the present invention is not limited to this.

[0033] In addition, the above-mentioned inspection records may also include parameters such as the operating status, temperature, voltage and current corresponding to the above-mentioned power equipment. The specific parameters can be determined according to the type of the above-mentioned power equipment, and the collected operating status, temperature, voltage and current parameters of the above-mentioned power equipment can be stored in a database.

[0034] Step 102: Generate prompt information corresponding to the power equipment, wherein the prompt information is used to instruct an evaluation model to perform a status evaluation on the power equipment according to a step sequence indicated by the prompt information, and the evaluation model is a model for evaluating the status of the power equipment.

[0035] The above-mentioned evaluation model can be a deep learning model trained with a large amount of text data, such as a large language model (LLM). The embodiment of the present invention does not limit the selection of the deep learning model. The above-mentioned prompt information can be understood as a prompt word or a prompt template, which is used to input into the above-mentioned evaluation model to obtain better results. In an embodiment of the present invention, by generating the above-mentioned prompt information, the above-mentioned evaluation model can be instructed to perform status evaluation on the above-mentioned power equipment in the sequence of steps indicated by the above-mentioned prompt information, so as to obtain a better and more accurate evaluation result.

[0036] The above prompt information may be text content, and the above prompt information may record the various step instructions for guiding the above evaluation model. As an optional implementation method, the guidance steps of the above prompt information may be edited or designed in the following form: 1. Step decomposition; 2. Data comparison; 3. Condition determination; 4. Score calculation.

[0037] For example, the text template corresponding to the above prompt information is as follows:

[0038] a) [Step by step analysis]

[0039] b) [Data comparison] Calculate the relationship between the measured value and the rated value;

[0040] c) [Conditional determination] Determine which situation it belongs to;

[0041] d) [Score calculation] Calculate the deduction score.

[0042] As an optional implementation, the text template corresponding to the above prompt information is as follows:

[0043] a) Decompose the inspection records according to the time of fault occurrence to obtain several abnormal records, and evaluate the several abnormal records in turn;

[0044] b) comparing the first target data corresponding to the plurality of abnormal records with the second target data corresponding to the plurality of normal records to obtain a comparison result;

[0045] c) Determine the fault information corresponding to several abnormal records based on the comparison results;

[0046] d) Generate status assessment results based on fault information.

[0047] As another optional implementation, the text template corresponding to the above prompt information is as follows:

[0048] a) Decompose the inspection records according to the time of fault occurrence to obtain several abnormal records, and evaluate the several abnormal records in turn;

[0049] b) Determine the relationship between the corresponding measured value and rated value of the electrical equipment;

[0050] c) Make conditional judgment on the inspection record based on the relationship between the corresponding measured value and the rated value of the power equipment to obtain the target fault situation corresponding to the inspection record;

[0051] d) Obtain the weight coefficient and basic score corresponding to the target fault condition to obtain a total deduction score, which is obtained by multiplying the weight coefficient and the basic score, and generating a status assessment result of the power equipment based on the total deduction score.

[0052] Regarding the design and editing of the text content in the above prompt information, relevant personnel can set it according to actual working conditions and relevant inspection criteria, which is not limited in this embodiment of the present invention.

[0053] It should be noted that the above-mentioned evaluation model can be obtained by training the large language model LLM. The above-mentioned evaluation model is trained based on the understanding and reasoning ability of the large language model LLM combined with the external power inspection knowledge base, wherein the above-mentioned power inspection knowledge base may include the inspection process specifications corresponding to the above-mentioned power equipment and the power equipment operating status evaluation standards, thereby training a set of models for scoring the operating status of power equipment.

[0054] Step 103: input the inspection record and the prompt information into the evaluation model, and use the evaluation model to evaluate the status of the power equipment based on the inspection record and in the order of steps indicated by the prompt information to obtain a status evaluation result of the power equipment.

[0055] When the inspection records and the prompt information are input into the evaluation model, the inspection records and the prompt information can be simultaneously input into the evaluation model in the form of text. Of course, the inspection records and the prompt information can also be integrated into one text and then input into the evaluation model.

[0056] After the inspection record and the prompt information are input into the evaluation model, the evaluation model is used to evaluate the power equipment in sequence based on the inspection record and the steps indicated by the prompt information. The status evaluation result may be presented in the form of a report, and any fault or abnormality that occurs may be indicated in the report in the form of deductions. Finally, the status of the power equipment is evaluated in terms of the total score or the total deduction score.

[0057] Among them, the deduction points corresponding to faults of different severity may be different. For example, the more serious the abnormality of the power equipment, the worse the status assessment result generated by the above assessment model (the lower the total score / the more deduction points), and vice versa. This will not be elaborated.

[0058] See also Figure 2 , Figure 2 This is a second flow chart of a method for evaluating the state of an electric power device provided by an embodiment of the present invention. Figure 2 As shown, a large language model is trained based on a power inspection knowledge base to obtain an evaluation model in an embodiment of the present invention, and then the inspection records and prompt information are simultaneously input into the evaluation model to finally obtain a status evaluation result of the power equipment.

[0059] In this implementation scheme, the inspection records of the power equipment are first obtained, and prompt information corresponding to the power equipment is generated. The inspection records and prompt information are input into an evaluation model, and the status of the power equipment is evaluated based on the inspection records through the evaluation model and in sequence according to the steps indicated by the prompt information, thereby obtaining an evaluation result of the status of the power equipment. The evaluation is performed step by step according to the prompt information, thereby improving the accuracy of the status evaluation of the electronic equipment.

[0060] It should be noted that the method of using the input prompt information in the power equipment status assessment method in the field of power operation and inspection uses less sample data, improves the accuracy of the above-mentioned assessment model at no cost, and saves costs compared to the traditional large model fine-tuning method. At the same time, the embodiment of the present invention helps the inspection process to complete automation and standardization, further improving the efficiency and standardization of operation and inspection.

[0061] Optionally, obtaining inspection records of power equipment includes:

[0062] Collecting first inspection data of the electric equipment, wherein the first inspection data includes at least one of the following: operating status, temperature, voltage and current of the electric equipment;

[0063] The abnormal behavior of the electric power equipment within the preset time period is recorded according to the first inspection data, so as to obtain the inspection record for recording the abnormal behavior.

[0064] It should be understood that the above-mentioned power equipment includes but is not limited to power equipment such as generator sets, transformers, capacitors and distribution cabinets. Therefore, for different types of power equipment, the above-mentioned first inspection data collected also changes with the different types of power equipment. For example: when the power equipment is a transformer, then the above-mentioned first inspection data can be a measurement of the operating status, temperature, voltage and current of the transformer under abnormal conditions.

[0065] It should be noted that, in addition to the operating status, temperature, voltage and current of the above-mentioned power equipment, the above-mentioned first inspection data may also be the collection of other parameters in the above-mentioned power equipment, such as gas content.

[0066] If there is abnormal data in the first inspection data, the abnormal record behavior and the time point of occurrence can be recorded, and finally the equipment number corresponding to the power equipment is added to obtain the inspection record.

[0067] In addition, the above-mentioned preset time period can be set according to the actual inspection specifications. If the inspection specifications indicate that the inspection and evaluation of the above-mentioned power equipment are to be carried out in days, then the cycle of the above-mentioned preset time period can be set to 24 hours. If relevant personnel use one week as the inspection cycle based on the working conditions of the above-mentioned power equipment, then the above-mentioned preset time period can be set to one week. This embodiment of the present invention is not limited to this.

[0068] In this implementation scheme, the inspection record is determined by collecting multi-dimensional first inspection data. The collection of each category of power equipment is not limited to a single parameter, which increases the diversity of collected data. The inspection record can also record the abnormal status of the power equipment in more situations, thereby improving the accuracy of the evaluation of the status of the power equipment, reducing the impact of low-probability events on the evaluation results, and further improving the effect of the evaluation of the status of the power equipment.

[0069] Optionally, the prompt information is used to guide the evaluation model to complete the generation of the status evaluation result in accordance with the following steps in sequence:

[0070] Decomposing the inspection records according to the time when the fault occurred to obtain a number of abnormal records, and evaluating the several abnormal records in turn;

[0071] Compare the first target data corresponding to the plurality of abnormal records with the second target data corresponding to the plurality of normal records to obtain a comparison result, wherein the first target data represents the corresponding measurement value of the power equipment, and the second target data represents the corresponding rated value of the power equipment;

[0072] Determine the fault information corresponding to the plurality of abnormal records according to the comparison result;

[0073] The status assessment result is generated according to the fault information.

[0074] It should be understood that the above inspection records may be records of abnormalities of multiple power equipment. Therefore, the above inspection records can be first decomposed according to the time of fault occurrence, and the abnormal records can be evaluated one by one, and the evaluation results of each abnormal record can be displayed separately in the final status evaluation results.

[0075] The first target data indicates the measured value corresponding to the power equipment, and the second target data indicates the rated value corresponding to the power equipment. For example, if the power equipment is a transformer, and the rated maximum short-circuit current of the transformer is 25kA, and the short-circuit impact current is 20kA, then 20kA can be understood as the first target data, and 25kA can be understood as the second target data. That is, the comparison result is the comparison result between 20kA and 25kA.

[0076] The determination of the above fault information can determine that the above power equipment belongs to one of the situations in the power equipment operation status evaluation standard. Taking the above power equipment as a transformer, and the rated maximum short-circuit current of the transformer is 25kA, and the short-circuit impulse current is 20kA as an example, the above fault information can be expressed as follows: the measured value 20kA is lower than the rated value 25kA by 80%. Therefore, this short-circuit impulse current belongs to the second situation, that is, the short-circuit impulse current is between 70% and 90% of the allowable short-circuit current.

[0077] In general, the above-mentioned status assessment result can be a score to show the status of the above-mentioned power equipment, because the score system is more intuitive than other methods in the evaluation of the above-mentioned power equipment. Of course, other scoring mechanisms can also be adopted, such as: grade system, etc., which are not limited in this embodiment of the present invention. Continuing with the above-mentioned power equipment being a transformer, and the rated maximum short-circuit current of the transformer is 25kA, and the short-circuit impact current that occurs is 20kA. For example, the above-mentioned status assessment result can be expressed as follows according to the score system: When the short-circuit impact current is between 70% and 90% of the allowable short-circuit current, the deduction method for this case is to deduct points per time, with a weight of 3, a basic score of 4, and a single total of 3*4=12 points. Therefore, 12 points should be deducted for this short-circuit impact.

[0078] In this implementation scheme, the inspection records are first decomposed so that the evaluation model can analyze the abnormal records one by one, and then the first target data corresponding to several abnormal records are compared with the second target data corresponding to several normal records to obtain the comparison results, so as to determine which situation each abnormal record belongs to in the power equipment operation status evaluation standard, and finally obtain the status evaluation result according to the pre-established evaluation standard. The input of the prompt information improves the deconstruction and analysis capabilities of the evaluation model. The prompt information stimulates the reasoning ability of the evaluation model itself with appropriate prompt words or templates, thereby improving the accuracy of the power equipment status evaluation, and further improving the overall effect of the power equipment status evaluation.

[0079] It should be noted that when the above-mentioned status assessment results are displayed in the form of scores, the above-mentioned prompt information can help the above-mentioned assessment model better understand the structured scoring criteria, and effectively improve the accuracy and generalization ability of the above-mentioned assessment model for the above-mentioned power equipment status scores.

[0080] Optionally, the inspection record and the prompt information are input into the evaluation model, and the status of the power equipment is evaluated by the evaluation model based on the inspection record and in the order of steps indicated by the prompt information to obtain a status evaluation result of the power equipment:

[0081] Acquire a first text and a second text, wherein the first text is the text content of the inspection record of the power equipment, and the second text is the text content of the prompt information;

[0082] Merging the first text and the second text to obtain an input text;

[0083] The input text is input into the evaluation model to obtain a status evaluation result of the power equipment.

[0084] It should be understood that the first text and the second text correspond to the text content of the inspection record of the electric power equipment and the text content of the prompt information respectively, and both the inspection record and the prompt information can be input into the evaluation model in the form of text.

[0085] In this embodiment, the first text and the second text are merged to obtain the input text, and then the input text is directly input into the evaluation model. When the first text and the second text are input into the evaluation model separately at the same time, there may be a time error. Through this method, the probability of inaccurate status evaluation results due to operational errors is reduced, the accuracy of the status evaluation of the power equipment is improved, and then the overall effect of the status evaluation of the power equipment is improved.

[0086] Optionally, the inputting the inspection record and the prompt information into the evaluation model, and evaluating the status of the power equipment through the evaluation model based on the inspection record and in the order of steps indicated by the prompt information to obtain the status evaluation result of the power equipment, includes:

[0087] Decomposing the inspection records according to the time when the fault occurred to obtain a number of abnormal records, and evaluating the several abnormal records in turn;

[0088] Compare the first target data corresponding to the plurality of abnormal records with the second target data corresponding to the plurality of normal records to obtain a comparison result, wherein the first target data represents the corresponding measurement value of the power equipment, and the second target data represents the corresponding rated value of the power equipment;

[0089] Determine the fault information corresponding to the plurality of abnormal records according to the comparison result;

[0090] The status assessment result is generated according to the fault information.

[0091] In this implementation scheme, the inspection records are first decomposed so that the evaluation model can analyze the abnormal records one by one, and then the first target data corresponding to several abnormal records are compared with the second target data corresponding to several normal records to obtain the comparison results, so that it can be judged that each abnormal record belongs to the specific situation in the power equipment operation status evaluation standard, and finally the status evaluation result is obtained according to the pre-established evaluation standard. The input of the prompt information improves the deconstruction and analysis capabilities of the evaluation model. The prompt information stimulates the reasoning ability of the evaluation model itself with appropriate prompt words or templates, thereby improving the accuracy of the power equipment status evaluation, and further improving the overall effect of the power equipment status evaluation.

[0092] Embodiment 1:

[0093] See also Figure 3 , Figure 3 This is one of the example block diagrams provided by the embodiment of the present invention, such as Figure 3 As shown, this embodiment takes the evaluation of the short circuit condition of the main transformer as an example to generate the status evaluation result. The power inspection knowledge base includes the ledger information of the corresponding power equipment, wherein the ledger information includes the number of the power equipment and related parameters.

[0094] The power inspection knowledge base also includes the corresponding deduction standards for transformers in various situations. If the short-circuit impact current received by the transformer is between 50% and 70% of the allowable short-circuit current and the number of times reaches 6 times or more, 6 points will be deducted (weight coefficient (3) multiplied by basic score (2)); if the short-circuit impact current received by the transformer is between 70% and 90% of the allowable short-circuit current, 12 points will be deducted each time (weight coefficient (3) multiplied by basic score (4)); if the short-circuit impact current received by the transformer is more than 90% of the allowable short-circuit current, 24 points will be deducted each time (weight coefficient (3) multiplied by basic score (8)).

[0095] 1) Use the large language model (LLM) and the power inspection industry knowledge base to train a model for scoring the operating status of power equipment;

[0096] 2) The inspection and monitoring system is used to learn that a short circuit fault has occurred in the main transformer. The example data is "January 1, 2023, 03:23am, equipment number: BJZGZBYQ110A, a short circuit shock occurred, and the current measurement value was 20kA";

[0097] 3) Input the inspection records and prompt information in 2) into the evaluation model to obtain the status evaluation results and the status evaluation results obtained without adding prompt information, as shown in Table 1 below:

[0098] Table 1

[0099]

[0100]

[0101] As can be seen from Table 1 above, for the same inspection records and the same evaluation model, after adding prompt information, the logical analysis ability and correctness of the output results are greatly improved.

[0102] Embodiment 2:

[0103] See also Figure 4 , Figure 4 This is a second example block diagram provided by an embodiment of the present invention, such as Figure 4 As shown, this embodiment takes the evaluation of gas oil chromatography analysis in the main transformer oil as an example to generate a status evaluation result. The power inspection knowledge base includes the ledger information of the corresponding power equipment, wherein the ledger information includes the number of the power equipment and related parameters.

[0104] The power inspection knowledge base also includes the corresponding deduction standards for transformers in various situations. If the total acetylene content in the transformer oil is greater than 150 μl / l, 12 points will be deducted (weight coefficient (3) multiplied by the basic score (4)); if the total acetylene content in the transformer oil is greater than 150 μl / l, and the relative steam production rate is greater than 10% / month or the absolute steam production rate is greater than 12 ml / day, 30 points will be deducted (weight coefficient (3) multiplied by the basic score (10)); if the acetylene content in the transformer oil is greater than 5 μl / l, 30 points will be deducted (weight coefficient (3) multiplied by the basic score (10)); if the hydrogen content in the transformer oil is greater than 150 μl / l, 8 points will be deducted (weight coefficient (2) multiplied by the basic score (4)); if the hydrogen content in the transformer oil is greater than 150 μl / l, and the absolute steam production rate is greater than 10 ml / day, 16 points will be deducted (weight coefficient (2) multiplied by the basic score (8)).

[0105] 1) Use the large language model (LLM) and the power inspection industry knowledge base to train a model for scoring the operating status of power equipment;

[0106] 2) The inspection and monitoring system is used to learn that a short circuit fault has occurred in the main transformer. The sample data is as follows:

[0107] a) January 1, 2023, 00:00am, equipment number: BJZGZBYQ110A, hydrocarbon gas content: 130μl / l, acetylene content: 4μl / l, hydrogen content: 100μl / l;

[0108] b) January 2, 2023, 00:00am, equipment number: BJZGZBYQ110A, hydrocarbon gas content: 143μl / l, acetylene content: 6μl / l, hydrogen content: 152μl / l;

[0109] 3) Input the inspection records and prompt information in 2) into the evaluation model to obtain the status evaluation results and the status evaluation results obtained without adding prompt information, as shown in Table 2 below:

[0110] Table 2

[0111]

[0112]

[0113] As can be seen from Table 2 above, for the same inspection records and the same evaluation model, after adding prompt information, the logical analysis ability and correctness of the output results are greatly improved.

[0114] Optionally, the evaluation model is obtained by the following training method:

[0115] Acquire power inspection data of the power equipment, wherein the power inspection data includes inspection process specifications and operating status evaluation standards corresponding to the power equipment;

[0116] An initial model is trained based on the power inspection data to obtain an evaluation model, wherein the initial model is a large language model (LLM), and the evaluation model is a model for evaluating the status of the power equipment.

[0117] It should be understood that the above-mentioned power inspection data can be understood as professional knowledge in the field of power inspection, such as the above-mentioned inspection process specifications and the corresponding operating status evaluation standards of the above-mentioned power equipment. The large language model LLM is trained using the above-mentioned power inspection data to obtain the evaluation model in the embodiment of the present invention.

[0118] In this implementation scheme, firstly, the power inspection data matching the above-mentioned power equipment is obtained to ensure the accuracy of the evaluation of the above-mentioned power equipment, and then the above-mentioned initial model is trained using the above-mentioned power inspection data, that is, the large language model LLM is trained as a model capable of scoring the status of the power equipment. In essence, the above-mentioned evaluation model is still the large language model LLM. By inputting the above-mentioned inspection records and the above-mentioned prompt information into the above-mentioned evaluation model, the task of evaluating the status of the power equipment is converted into a text generation task in natural language processing, and large-scale text data is used for training, so that the above-mentioned evaluation model can be evaluated in the case of small samples or zero samples. The embodiment of the present invention improves the effect of evaluating the status of power equipment.

[0119] See also Figure 5 , Figure 5 is a structural diagram of an electronic device status evaluation device provided by an embodiment of the present invention, such as Figure 5 As shown, the power equipment status assessment device 500 includes:

[0120] The acquisition module 501 is used to acquire the inspection record of the power equipment, where the inspection record is the record of the power equipment within a preset time period;

[0121] A generating module 502, configured to generate prompt information corresponding to the electric power equipment, wherein the prompt information is used to instruct an evaluation model to perform a status evaluation on the electric power equipment according to a sequence of steps indicated by the prompt information, and the evaluation model is a model for evaluating the status of the electric power equipment;

[0122] The processing module 503 is used to input the inspection record and the prompt information into the evaluation model, and evaluate the status of the power equipment through the evaluation model based on the inspection record and in the order of steps indicated by the prompt information to obtain the status evaluation result of the power equipment.

[0123] Optionally, the acquisition module 501 includes:

[0124] A collection unit, used to collect first inspection data of the power equipment, wherein the first inspection data includes at least one of the following: operating status, temperature, voltage and current of the power equipment;

[0125] A recording unit is used to record the abnormal behavior of the power equipment within the preset time period according to the first inspection data, and obtain the inspection record for recording the abnormal behavior.

[0126] Optionally, the prompt information is used to guide the evaluation model to complete the generation of the status evaluation result in accordance with the following steps in sequence:

[0127] Decomposing the inspection records according to the time when the fault occurred to obtain a number of abnormal records, and evaluating the several abnormal records in turn;

[0128] Compare the first target data corresponding to the plurality of abnormal records with the second target data corresponding to the plurality of normal records to obtain a comparison result, wherein the first target data represents the corresponding measurement value of the power equipment, and the second target data represents the corresponding rated value of the power equipment;

[0129] Determine the fault information corresponding to the plurality of abnormal records according to the comparison result;

[0130] The status assessment result is generated according to the fault information.

[0131] Optionally, the processing module 503 includes:

[0132] An acquisition unit, configured to acquire a first text and a second text, wherein the first text is the text content of the inspection record of the power equipment, and the second text is the text content of the prompt information;

[0133] a merging unit, configured to merge the first text and the second text to obtain an input text;

[0134] The first generating unit is used to input the input text into the evaluation model to obtain the status evaluation result of the power equipment.

[0135] Optionally, the processing module 503 includes:

[0136] A decomposition unit, used to decompose the inspection record according to the fault occurrence time to obtain a plurality of abnormal records, and evaluate the plurality of abnormal records in turn;

[0137] A comparison unit, used to compare the first target data corresponding to the plurality of abnormal records with the second target data corresponding to the plurality of normal records, respectively, to obtain a comparison result, wherein the first target data represents a measurement value corresponding to the power equipment, and the second target data represents a rated value corresponding to the power equipment;

[0138] A determination unit, configured to determine the fault information corresponding to the plurality of abnormal records according to the comparison result;

[0139] The second generating unit is used to generate the status evaluation result according to the fault information.

[0140] The evaluation model is obtained by the following training method:

[0141] Acquire power inspection data of the power equipment, wherein the power inspection data includes inspection process specifications and operating status evaluation standards corresponding to the power equipment;

[0142] An initial model is trained based on the power inspection data to obtain an evaluation model, wherein the initial model is a large language model (LLM), and the evaluation model is a model for evaluating the status of the power equipment.

[0143] The electronic device status assessment device provided in the embodiment of the present invention can implement each process of each embodiment of the above-mentioned electronic device status assessment method, and the technical features correspond one to one and can achieve the same technical effect. To avoid repetition, it will not be described here.

[0144] It should be noted that the electronic device status assessment device in the embodiment of the present invention may be a device, or a component, an integrated circuit, or a chip in the electronic device.

[0145] The embodiment of the present invention further provides an electronic device, see Figure 6 , Figure 6 601, a processor 602, and a program or instruction stored in the memory 601 and executed by the processor 602. Figure 1 Any steps in the corresponding method embodiments and achieving the same beneficial effects will not be repeated here.

[0146] The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a graphics processing unit (GPU).

[0147] Those skilled in the art will appreciate that all or part of the steps of implementing the above-mentioned embodiment method can be completed by hardware associated with program instructions, and the program can be stored in a readable medium.

[0148] The embodiment of the present invention further provides a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above Figure 1 The corresponding steps in the electronic device status evaluation method embodiment can achieve the same technical effect, and will not be repeated here to avoid repetition. The storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0149] The terms "first", "second" etc. in the embodiments of the present invention are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. In addition, the terms "include" and "have" and any variation thereof are intended to cover non-exclusive inclusions, for example, the process, method, system, product or equipment comprising a series of steps or units need not be 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 equipment. In addition, "and / or" is used in the present application to represent at least one of the connected objects, such as A and / or B and / or C, indicating that A alone, B alone, C alone, and A and B all exist, B and C all exist, A and C all exist, and 7 situations in which A, B and C all exist.

[0150] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0151] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a second terminal device, etc.) to execute the methods of each embodiment of the present application.

[0152] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A method for evaluating the state of electric power equipment, characterized in that: include: Obtaining inspection records of the power equipment, where the inspection records are records of the power equipment within a preset time period; Generate prompt information corresponding to the electric power equipment, wherein the prompt information is used to instruct an evaluation model to perform a status evaluation on the electric power equipment according to a step sequence indicated by the prompt information, and the evaluation model is a model used to evaluate the status of the electric power equipment; The inspection record and the prompt information are input into the evaluation model, and the evaluation model evaluates the status of the power equipment based on the inspection record and in the order of steps indicated by the prompt information to obtain a status evaluation result of the power equipment.

2. The method for evaluating the state of electric power equipment according to claim 1, characterized in that: The obtaining of inspection records of electric power equipment includes: Collecting first inspection data of the electric equipment, wherein the first inspection data includes at least one of the following: operating status, temperature, voltage and current of the electric equipment; The abnormal behavior of the electric power equipment within the preset time period is recorded according to the first inspection data, so as to obtain the inspection record for recording the abnormal behavior.

3. The method for evaluating the state of electric power equipment according to claim 2, characterized in that: The prompt information is used to guide the evaluation model to complete the generation of the status evaluation result in accordance with the following steps in sequence: Decomposing the inspection records according to the time when the fault occurred to obtain a number of abnormal records, and evaluating the several abnormal records in turn; Compare the first target data corresponding to the plurality of abnormal records with the second target data corresponding to the plurality of normal records to obtain a comparison result, wherein the first target data represents the corresponding measurement value of the power equipment, and the second target data represents the corresponding rated value of the power equipment; Determine the fault information corresponding to the plurality of abnormal records according to the comparison result; The status assessment result is generated according to the fault information.

4. The method for evaluating the state of electric power equipment according to claim 1, characterized in that: The inspection record and the prompt information are input into the evaluation model, and the status of the power equipment is evaluated by the evaluation model based on the inspection record and in the order of steps indicated by the prompt information to obtain a status evaluation result of the power equipment: Acquire a first text and a second text, wherein the first text is the text content of the inspection record of the power equipment, and the second text is the text content of the prompt information; Merging the first text and the second text to obtain an input text; The input text is input into the evaluation model to obtain a status evaluation result of the power equipment.

5. The method for evaluating the state of electric power equipment according to claim 1, characterized in that: The step of inputting the inspection record and the prompt information into the evaluation model, evaluating the state of the power equipment through the evaluation model based on the inspection record and in the order of steps indicated by the prompt information, and obtaining the state evaluation result of the power equipment includes: Decomposing the inspection records according to the time when the fault occurred to obtain a number of abnormal records, and evaluating the several abnormal records in turn; Compare the first target data corresponding to the plurality of abnormal records with the second target data corresponding to the plurality of normal records to obtain a comparison result, wherein the first target data represents the corresponding measurement value of the power equipment, and the second target data represents the corresponding rated value of the power equipment; Determine the fault information corresponding to the plurality of abnormal records according to the comparison result; The status assessment result is generated according to the fault information.

6. The method for evaluating the state of electric power equipment according to claim 3, characterized in that: The evaluation model is obtained by the following training method: Acquire power inspection data of the power equipment, wherein the power inspection data includes inspection process specifications and operating status evaluation standards corresponding to the power equipment; An initial model is trained based on the power inspection data to obtain an evaluation model, wherein the initial model is a large language model (LLM), and the evaluation model is a model for evaluating the status of the power equipment.

7. A device for evaluating the state of electric power equipment, characterized in that: include: An acquisition module is used to acquire inspection records of electric equipment, where the inspection records are records of electric equipment within a preset time period; A generating module, used for generating prompt information corresponding to the electric power equipment, wherein the prompt information is used for instructing an evaluation model to perform a status evaluation on the electric power equipment according to a sequence of steps indicated by the prompt information, and the evaluation model is a model for evaluating the status of the electric power equipment; A processing module is used to input the inspection record and the prompt information into the evaluation model, and evaluate the status of the power equipment through the evaluation model based on the inspection record and in the order of steps indicated by the prompt information to obtain the status evaluation result of the power equipment.

8. The power equipment status assessment device according to claim 7, characterized in that: The acquisition module comprises: A collection unit, used to collect first inspection data of the power equipment, wherein the first inspection data includes at least one of the following: operating status, temperature, voltage and current of the power equipment; A recording unit is used to record the abnormal behavior of the power equipment within the preset time period according to the first inspection data, and obtain the inspection record for recording the abnormal behavior.

9. The power equipment status assessment device according to claim 8, characterized in that: The prompt information is used to guide the evaluation model to complete the generation of the status evaluation result in accordance with the following steps in sequence: Decomposing the inspection records according to the time when the fault occurred to obtain a number of abnormal records, and evaluating the several abnormal records in turn; Compare the first target data corresponding to the plurality of abnormal records with the second target data corresponding to the plurality of normal records to obtain a comparison result, wherein the first target data represents the corresponding measurement value of the power equipment, and the second target data represents the corresponding rated value of the power equipment; Determine the fault information corresponding to the plurality of abnormal records according to the comparison result; The status assessment result is generated according to the fault information.

10. The power equipment status assessment device according to claim 7, characterized in that: The processing module comprises: An acquisition unit, configured to acquire a first text and a second text, wherein the first text is the text content of the inspection record of the power equipment, and the second text is the text content of the prompt information; a merging unit, configured to merge the first text and the second text to obtain an input text; The first generating unit is used to input the input text into the evaluation model to obtain the status evaluation result of the power equipment.

11. The power equipment status assessment device according to claim 7, characterized in that: The processing module comprises: A decomposition unit, used to decompose the inspection record according to the fault occurrence time to obtain a plurality of abnormal records, and evaluate the plurality of abnormal records in turn; A comparison unit, used to compare the first target data corresponding to the plurality of abnormal records with the second target data corresponding to the plurality of normal records, respectively, to obtain a comparison result, wherein the first target data represents a measurement value corresponding to the power equipment, and the second target data represents a rated value corresponding to the power equipment; A determination unit, configured to determine the fault information corresponding to the plurality of abnormal records according to the comparison result; The second generating unit is used to generate the status evaluation result according to the fault information.

12. The power equipment status assessment device according to claim 9, characterized in that: The evaluation model is obtained by the following training method: Acquire power inspection data of the power equipment, wherein the power inspection data includes inspection process specifications and operating status evaluation standards corresponding to the power equipment; An initial model is trained based on the power inspection data to obtain an evaluation model, wherein the initial model is a large language model (LLM), and the evaluation model is a model for evaluating the status of the power equipment.

13. An electronic device, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps in the method for evaluating the state of electric power equipment as claimed in any one of claims 1 to 6.

14. A readable storage medium for storing a program, characterized in that: When the program is executed by a processor, the steps of the method for evaluating the state of electric power equipment according to any one of claims 1 to 6 are implemented.

Images