Power equipment related information sending method and device, electronic equipment and medium

Abstract

The embodiment of the invention discloses a power equipment related information sending method and device, electronic equipment and a medium. A specific embodiment of the method comprises the following steps: in response to received equipment security detection information, acquiring power equipment information as target power equipment information; determining at least one piece of power equipment specification information; screening out a power equipment information set; setting a multi-modal working feature set and a power basic feature set; in response to determining that the number of the power equipment information is greater than a preset number, executing clustering processing to generate a power equipment information cluster; according to the power equipment information cluster set, generating current power equipment operation information and a corresponding equipment safety detection result; and sending the current power equipment operation information and the equipment safety detection result to the power equipment information submitting end. According to the embodiment of the invention, on the premise of ensuring the detection accuracy, the operation state detection and the equipment safety detection of the power equipment can be quickly and efficiently realized, and the equipment fault problem is avoided.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a method, device, electronic device, and medium for transmitting information related to power equipment. Background Art

[0002] How to effectively perform operation and safety tests on power equipment has become an important issue that needs to be solved urgently. For operation and safety tests on power equipment, the usual method is to manually perform operation and safety tests on power equipment through insulation resistance tests.

[0003] However, when the above method is used to perform operation detection and safety detection of power equipment, the following technical problems often occur: For the massive amount of power equipment in rural and remote areas, the efficiency of manual inspection is too low, and the inspection results are often not effectively guaranteed. In addition, if local faults are not handled in time, they may spread to the entire power system, causing a larger power outage or equipment damage (such as transformer burnout, line short circuit, etc.), voltage fluctuations, harmonic interference and other problems in power equipment, affecting the normal operation of precision equipment (such as medical instruments and data centers).

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0005] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0006] Some embodiments of the present disclosure propose methods, devices, electronic devices and media for transmitting information related to power equipment to solve one or more of the technical problems mentioned in the above background technology section.

[0007] In a first aspect, some embodiments of the present disclosure provide a method for sending information related to electric power equipment, comprising: in response to receiving equipment safety detection information corresponding to a target electric power equipment sent by an electric power equipment information submission terminal, obtaining electric power equipment information corresponding to the above-mentioned target electric power equipment as the target electric power equipment information, wherein the above-mentioned target electric power equipment information includes: target electric power equipment specification information and equipment multimodal working status information in a current time period; determining at least one electric power equipment specification information that matches the above-mentioned target electric power equipment specification information; screening out an electric power equipment information group corresponding to the above-mentioned at least one electric power equipment specification information and the above-mentioned target electric power equipment specification information from an electric power equipment information library, wherein the electric power equipment information includes: target electric power equipment specification information and equipment multimodal working status information in a current time period; determining at least one electric power equipment specification information that matches the above-mentioned target electric power equipment specification information; screening out an electric power equipment information group corresponding to the above-mentioned at least one electric power equipment specification information and the above-mentioned target electric power equipment specification information from an electric power equipment information library, The backup information group is the power equipment information corresponding to the power equipment in each historical time period; a multimodal working feature set and a power basic feature set are set for the power equipment; in response to determining that the number of power equipment information corresponding to the above power equipment information group set is greater than a preset number, according to the multimodal working feature set and the above power basic feature set, clustering processing is performed on the above power equipment information group set and the above target power equipment information to generate a power equipment information cluster set; according to the above power equipment information cluster set, the current power equipment operation information corresponding to the above target power equipment and the corresponding equipment safety detection result are generated; the above current power equipment operation information and the above equipment safety detection result are sent to the above power equipment information submission terminal.

[0008] In a second aspect, some embodiments of the present disclosure provide a device for sending information related to electric power equipment, including: an acquisition unit, configured to, in response to receiving equipment safety detection information corresponding to the target electric power equipment sent by the electric power equipment information submission terminal, acquire the electric power equipment information corresponding to the above-mentioned target electric power equipment as the target electric power equipment information, wherein the above-mentioned target electric power equipment information includes: target electric power equipment specification information and equipment multimodal working status information in the current time period; a determination unit, configured to determine at least one electric power equipment specification information that matches the above-mentioned target electric power equipment specification information; a screening unit, configured to screen out a set of electric power equipment information groups corresponding to the above-mentioned at least one electric power equipment specification information and the above-mentioned target electric power equipment specification information from the electric power equipment information library, wherein the electric power equipment information group is The power equipment information corresponding to the power equipment in each historical time period; a setting unit, configured to set a multimodal working feature set and a power basic feature set for the power equipment; an execution unit, configured to, in response to determining that the number of power equipment information corresponding to the above-mentioned power equipment information set is greater than a preset number, perform clustering processing on the above-mentioned power equipment information set and the above-mentioned target power equipment information according to the multimodal working feature set and the above-mentioned power basic feature set to generate a power equipment information cluster set; a generation unit, configured to generate the current power equipment operation information and the corresponding equipment safety detection result corresponding to the above-mentioned target power equipment according to the above-mentioned power equipment information cluster set; a sending unit, configured to send the above-mentioned current power equipment operation information and the above-mentioned equipment safety detection result to the above-mentioned power equipment information submission terminal.

[0009] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner in the first aspect.

[0010] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner in the first aspect is implemented.

[0011] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the power equipment related information sending method of some embodiments of the present disclosure, the operation status detection and equipment safety detection of the power equipment can be realized quickly and efficiently under the premise of ensuring the detection accuracy, so as to avoid the occurrence of equipment failure problems. Specifically, the reason why the relevant operation status detection and equipment safety detection are not accurate and efficient is that the efficiency of manual detection of massive power equipment in rural and remote areas is too low, and the detection results are often not effectively guaranteed. In addition, if the local fault is not handled in time, it may spread to the entire power system, resulting in a larger range of power outages or equipment damage (such as transformer burning, line short circuit, etc.), voltage fluctuations, harmonic interference and other problems in the power equipment, affecting the normal operation of precision equipment (such as medical instruments, data centers). Based on this, the power equipment related information sending method of some embodiments of the present disclosure, first, in response to receiving the equipment safety detection information corresponding to the target power equipment sent by the power equipment information submission terminal, the power equipment information corresponding to the above target power equipment is obtained as the target power equipment information. Among them, the above target power equipment information includes: target power equipment specification information and equipment multimodal working status information in the current time period. Here, the target power equipment information obtained is used to facilitate the subsequent matching of similar power equipment data, so as to quickly determine the operating status while ensuring the accuracy of the operating status determination. Then, at least one power equipment specification information that matches the above-mentioned target power equipment specification information is determined, so as to facilitate the subsequent acquisition of power equipment data that matches the equipment specifications corresponding to the target power equipment. Next, a power equipment information group set corresponding to the above-mentioned at least one power equipment specification information and the above-mentioned target power equipment specification information is screened out from the power equipment information library as a similar power equipment information set, which can quickly screen out power equipment information with similar information content corresponding to the target power equipment information. Among them, the power equipment information group is the power equipment information corresponding to the power equipment in each historical time period. Furthermore, a multimodal working feature set and a power basic feature set for the power equipment are set as clustering features for subsequent clustering processing, so as to facilitate the grouping of power equipment information with the same features. Next, in response to determining that the number of electric power equipment information corresponding to the electric power equipment information set is greater than a preset number, clustering processing is performed on the electric power equipment information set and the target electric power equipment information according to the multimodal working feature set and the electric power basic feature set to generate an electric power equipment information cluster. Here, through clustering processing, electric power equipment information with similar information content to the target electric power equipment information can be quickly determined. Furthermore, according to the electric power equipment information cluster, the current electric power equipment operation information and the corresponding equipment safety detection results corresponding to the target electric power equipment can be quickly and accurately generated.Finally, the above current power equipment operation information and the above equipment safety detection results are sent to the above power equipment information submission terminal. In summary, through clustering processing, the matching of power equipment information similar to the target power equipment information can be achieved quickly and accurately, so as to quickly and accurately generate the corresponding current power equipment operation information and the corresponding equipment safety detection results. On this basis, the local faults corresponding to the power equipment are handled in a timely manner to avoid spreading to the entire power system, a larger range of power outages or equipment damage (such as transformer burnout, line short circuit, etc.), and avoid voltage fluctuations, harmonic interference and other problems in power equipment, which affect the normal operation of precision equipment (such as medical equipment, data centers). BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0013] Figure 1 is a flowchart of some embodiments of the method for sending information related to electric power equipment according to the present disclosure; Figure 2 is a schematic diagram of the structure of some embodiments of the device for sending information related to electric power equipment according to the present disclosure; Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0014] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0015] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0016] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0017] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0018] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0019] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0020] refer to Figure 1 , shows a process 100 of some embodiments of the method for sending information related to electric power equipment according to the present disclosure. The method for sending information related to electric power equipment comprises the following steps: Step 101, in response to receiving equipment safety detection information corresponding to a target electric equipment sent by an electric equipment information submitting terminal, acquiring electric equipment information corresponding to the target electric equipment as the target electric equipment information.

[0021] In some embodiments, in response to receiving the equipment safety detection information corresponding to the target power equipment sent by the power equipment information submission terminal, the execution subject (for example, electronic device) of the above-mentioned power equipment related information transmission method can obtain the power equipment information corresponding to the above-mentioned target power equipment through a wired connection method or a wireless connection method as the target power equipment information. Among them, the power equipment information submission terminal can be a terminal for submitting power equipment related information. In practice, the power equipment information submission terminal can be a mobile terminal held by a power maintenance personnel. The power equipment information submission terminal supports the submission operation of the relevant information of the power equipment. The power equipment related information may include: equipment safety detection information and power equipment information of the power equipment to be detected. The target power equipment may be a power equipment to be tested for operation and safety. For example, the target power equipment may be a transformer or a generator. The equipment safety detection information may be information representing the safety detection of the power equipment. For example, the equipment safety detection information may be a request for safety detection of the power equipment. The power equipment information may be the equipment related information of the power equipment. The above-mentioned target power equipment information includes: target power equipment specification information and equipment multimodal working state information in the current time period. The target power equipment specification information may be the equipment specification corresponding to the target power equipment. For example, if the target power equipment is a transformer, the corresponding equipment specification may be "single-phase transformer, capacity: 100VA, input voltage: 220V, output voltage: 110V". In addition, the target power equipment specification information may also include: the service life of the equipment corresponding to the target power equipment. For example, the service life of the equipment corresponding to the target power equipment is 5 years. The current time period may be a predetermined time period before the current time. For example, the current time is "April 10th 11 o'clock", and the current time period may be "April 9th ​​11 o'clock - April 10th 11 o'clock". The multimodal working status information of the device can characterize the working status of the power equipment under the multimodal representation. In practice, the multimodal representation may include: image modal representation and video modal representation.

[0022] Step 102: Determine at least one piece of electric power equipment specification information that matches the target electric power equipment specification information.

[0023] In some embodiments, the execution entity may determine at least one piece of power device specification information that matches the target power device specification information.

[0024] As an example, the execution subject may determine at least one piece of power equipment specification information that is the same as the target power equipment specification information, wherein the brand corresponding to the at least one piece of power equipment specification information is different from the brand corresponding to the target power equipment specification information.

[0025] As another example, first, the execution subject may determine at least one key power equipment specification. Then, determine the power equipment specification information that corresponds to at least one key power equipment specification that is the same as the target power equipment specification information, and obtain at least one power equipment specification information. The key power equipment specification may be a predetermined power equipment specification with the highest importance.

[0026] Step 103: Filter out, from the electric power equipment information library, an electric power equipment information set corresponding to the at least one electric power equipment specification information and the target electric power equipment specification information.

[0027] In some embodiments, the execution subject may filter out a set of power equipment information groups corresponding to the at least one power equipment specification information and the target power equipment specification information from the power equipment information library. The power equipment information group is the power equipment information corresponding to the power equipment in each historical time period. For example, the equipment corresponding to the power equipment information group corresponds to the at least one power equipment specification information and a certain power equipment specification information in the target power equipment specification information. Each power equipment information group has a corresponding power equipment, and the power equipment information group may be the power equipment information of the corresponding power equipment in each historical time period. For example, the power equipment is transformer A, and the current time is 10:00 on April 10. The power equipment information group may include: power equipment information corresponding to transformer A under "10:00 on April 6-10:00 on April 7", power equipment information corresponding to transformer A under "10:00 on April 7-10:00 on April 8", and power equipment information corresponding to transformer A under "10:00 on April 8-10:00 on April 9". The at least one power equipment specification information and the target power equipment specification information have power equipment specification information that is the same as the equipment specification information corresponding to transformer A.

[0028] Step 104: Setting a multi-modal working feature set and a basic power feature set for the power equipment.

[0029] In some embodiments, the above-mentioned execution subject may set a multimodal working feature set and a basic power feature set for the power equipment. Among them, the multimodal working feature set may be a feature set related to the working process in a multimodal form. The basic power feature set may be a basic feature set of the power equipment. The basic power features may be the conventional operating features of the power equipment during operation and the attribute features of the equipment itself. There are no identical features in the basic power feature set and the multimodal working feature set.

[0030] In some optional implementations of some embodiments, the above-mentioned setting of the multi-modal working feature set and the power basic feature set for the power equipment may include the following steps: The first step is to determine the first multimodal feature set corresponding to the target power equipment specification information and the second multimodal feature set corresponding to the at least one power equipment specification information. Among them, the first multimodal feature set can be a feature attribute set under each mode set under the target power equipment specification information. The second multimodal feature set can be a feature attribute set under each mode set under at least one power equipment specification information. Each power equipment specification information has a corresponding second multimodal feature subset. At least one second multimodal feature subset constitutes a second multimodal feature set.

[0031] In the second step, the first multimodal feature set and the second multimodal feature set are deduplicated and fused to obtain the multimodal working feature set.

[0032] The third step is to extract the basic power feature set corresponding to the target power equipment specification information. The basic power feature set may include: electrical feature set, mechanical feature set, and chemical feature set. The electrical feature set may include: voltage, current, and power. The mechanical feature set may include: vibration, noise, and temperature. The chemical feature set may be the composition and content of chemical substances such as gas, liquid, etc. generated by the power equipment during operation.

[0033] Step 105, in response to determining that the number of power equipment information corresponding to the above-mentioned power equipment information set is greater than a preset number, clustering processing is performed on the above-mentioned power equipment information set and the above-mentioned target power equipment information according to the multimodal working feature set and the above-mentioned power basic feature set to generate a power equipment information cluster set.

[0034] In some embodiments, in response to determining that the number of electric power equipment information corresponding to the electric power equipment information set is greater than a preset number, the execution subject may perform clustering processing on the electric power equipment information set and the target electric power equipment information according to the multimodal working feature set and the electric power basic feature set to generate an electric power equipment information cluster set. Among them, each electric power equipment information in the electric power equipment information cluster has similar feature content in the multimodal working feature and the electric power basic feature. There are significant differences in the feature content of the multimodal working feature and the electric power basic feature between each electric power equipment information cluster.

[0035] In some optional implementations of some embodiments, the clustering process for the power equipment information group set and the target power equipment information is performed according to the multimodal working feature set and the power basic feature set to generate a power equipment information cluster set, which may include the following steps: In the first step, for each electric device information group in the electric device information group set, the following first generation step is performed: Sub-step 1: extracting a multimodal operating feature information set corresponding to the multimodal operating feature set from the power equipment information group as a first multimodal operating feature information set. There is a one-to-one correspondence between the multimodal operating features in the multimodal operating feature set and the multimodal operating feature information in the multimodal operating feature information set. The multimodal operating feature information may be the feature content of the power equipment under the corresponding multimodal feature.

[0036] Sub-step 2: extracting the power basic feature information set corresponding to the power basic feature set from the power equipment information group as the first power basic feature information set. There is a one-to-one correspondence between the power basic feature and the power basic feature information. The power basic feature information may be the feature content of the power equipment under the corresponding power basic feature.

[0037] The second step is to extract a multimodal operating characteristic information set corresponding to the multimodal operating characteristic set from the target power equipment information as a second multimodal operating characteristic information set. The specific explanation of the second multimodal operating characteristic information is omitted.

[0038] The third step is to extract the power basic feature information set corresponding to the power basic feature set from the target power equipment information as the second power basic feature information set. The specific explanation of the second power basic feature information is omitted.

[0039] In the fourth step, based on the obtained multiple first multimodal working characteristic information sets, multiple first power basic characteristic information sets, the above second multimodal working characteristic information sets and the above second power basic characteristic information sets, a clustering algorithm is used to generate a power equipment information cluster set. The clustering algorithm may be K-Means clustering.

[0040] Step 106: Generate current power equipment operation information and corresponding equipment safety detection results corresponding to the target power equipment according to the power equipment information cluster.

[0041] In some embodiments, the execution subject may generate the current power equipment operation information and the corresponding equipment safety detection result corresponding to the target power equipment according to the power equipment information cluster. The current power equipment operation information may be the operation status corresponding to the power equipment at the current time. The equipment safety detection result may be the safety detection result of the power equipment at the current time.

[0042] In some optional implementations of some embodiments, the generating of the current power equipment operation information and the corresponding equipment safety detection result corresponding to the target power equipment according to the power equipment information cluster may include the following steps: The first step is to select the power equipment information cluster where the target power equipment information is located from the power equipment information cluster set as the target power equipment information cluster.

[0043] In the second step, the power equipment information whose information proximity relationship with the target power equipment information satisfies the preset relationship condition is selected from the target power equipment information cluster as the adjacent power equipment information, and at least one adjacent power equipment information is obtained. Among them, the information proximity relationship can be the distance between two power equipment information in the target power equipment information cluster. The preset relationship condition can be that the distance between the power equipment information is less than the target value. The distance between two power equipment information can be determined by the cosine distance between the feature information.

[0044] In the third step, in response to determining that the at least one adjacent power device information does not include the cluster center corresponding to the target power device information cluster, the cluster center corresponding to the target power device information cluster is merged with the at least one adjacent power device information to generate a candidate power device information set.

[0045] The fourth step is to determine the historical power equipment operation information of each candidate power equipment information in the candidate power equipment information set in the historical time period corresponding to the candidate power equipment information. The historical power equipment operation information may be the operation content of the power equipment in the historical time period. The operation content may include: various operation parameters and various operation status descriptions.

[0046] The fifth step is to determine the above-mentioned current power equipment operation information and the above-mentioned equipment safety detection result based on the obtained historical power equipment operation information set.

[0047] As an example, the execution subject may classify each historical power equipment operation information in the historical power equipment operation information set to determine the number of information under each operation type. Then, the operation content of the operation type with the largest number of corresponding information is determined as the current power equipment operation information, and the equipment safety detection result of the operation type is generated. Among them, the equipment safety detection result may be matched one by one with the operation type.

[0048] Step 107, sending the current power equipment operation information and the equipment safety detection result to the power equipment information submission terminal.

[0049] In some embodiments, the execution entity may send the current power equipment operation information and the equipment safety detection result to the power equipment information submission terminal.

[0050] In some optional implementations of some embodiments, the multi-modal working state information of the device includes: an infrared image of the device operation, wherein the infrared image of the device operation may be an infrared image of the power device during operation.

[0051] Optionally, after step 107, the steps further include: In the first step, in response to determining that the number of electric device information corresponding to the electric device information set is less than or equal to the preset number, the device operation infrared image corresponding to each electric device information in the electric device information set is determined as a candidate device operation infrared image, and a candidate device operation infrared image set is obtained. The preset number may be a predetermined number. The preset number here may be determined based on the number requirement of the clustering algorithm.

[0052] In the second step, the infrared images of the above equipment are run to perform semantic segmentation of power equipment to generate segmented infrared images.

[0053] As an example, the execution subject may input the device operation infrared image into a pre-trained semantic segmentation model to generate a segmented infrared image. In practice, the semantic segmentation model may be a U-net model. The segmented infrared image may be a segmented infrared image including the target power device.

[0054] The third step is to perform power equipment semantic segmentation on each candidate device operation infrared image in the above candidate device operation infrared image set to generate a candidate segmented infrared image and obtain a candidate segmented infrared image set. For the explanation of the candidate segmented infrared image, please refer to the explanation of the segmented infrared image.

[0055] The fourth step is to determine the average pixel value corresponding to the above segmented infrared image as the first pixel average value, and determine the average pixel value corresponding to each candidate segmented infrared image in the above candidate segmented infrared image set as the second pixel average value.

[0056] In the fifth step, at least one candidate segmentation infrared image is selected from the candidate segmentation infrared image set, wherein the value difference between the corresponding second pixel average value and the first pixel average value is within a predetermined numerical range. The value difference between the pixel average values ​​can provide feedback on the pixel similarity between the two images. The predetermined numerical range can be each numerical range set for the target similarity range in each similarity range. Each similarity range can be each range between 0 and 1. The target similarity range can be an interval greater than the target similarity value. For example, the target similarity value can be 0.5.

[0057] In step 6, in response to determining that the at least one candidate segmented infrared image is not empty, determine whether there is a target candidate segmented infrared image in the at least one candidate segmented infrared image whose corresponding color region distribution is the same as the color region distribution corresponding to the segmented infrared image. The color region distribution can represent the similarity of the infrared contents between the two infrared images. The higher the similarity of the infrared contents, the more similar the contents of the two infrared images are.

[0058] The seventh step is to generate the above-mentioned current power equipment operation information and the above-mentioned equipment safety detection result according to the obtained at least one target candidate segmented infrared image in response to the determination of existence.

[0059] As an example, first, the execution subject may input the at least one target candidate segmented infrared image into the power equipment operation information generation model to generate at least one power equipment operation information. Then, the execution subject may classify each power equipment operation information in the at least one power equipment operation information to determine the number of information under each operation type. Then, the operation content of the operation type corresponding to the largest number of information is determined as the current power equipment operation information, and the equipment safety detection result of the operation type of the operation type is generated. Among them, the equipment safety detection result may be matched one by one with the operation type.

[0060] As another example, the execution subject may generate a generation instruction for generating current power equipment operation information and equipment safety detection results according to at least one target candidate segmented infrared image. Then, the generation instruction is input into the large language model to generate the current power equipment operation information and the equipment safety detection results.

[0061] Optionally, performing semantic segmentation of power equipment on the infrared image of the above-mentioned device operation to generate a segmented infrared image includes: The first step is to obtain a full set of power equipment specification information corresponding to the target power equipment as the first full set of power equipment specification information, wherein the first full set of power equipment specification information may represent all specification information sets related to the target power equipment on the market.

[0062] The second step is to determine the first infrared image feature information corresponding to each first full amount of electric power equipment specification information in the above-mentioned first full amount of electric power equipment specification information set, and obtain the first infrared image feature information set.

[0063] In the third step, for each first full amount of power equipment specification information, determine the first image device size information corresponding to the first full amount of power equipment specification information at a target shooting distance. The first image device size information may be an outer bounding box of the device under the first full amount of power equipment specification information in the image taken at the target shooting distance.

[0064] In the fourth step, deduplication processing is performed on the obtained first image device size information set to generate a first deduplication-free image device size information set.

[0065] The fifth step is to determine the associated equipment information group with which the target power equipment has a direct connection relationship.

[0066] Step 6: For each piece of associated device information in the associated device information group, perform the following information generation steps: Sub-step 1: determine the full power equipment specification information set corresponding to the above-mentioned associated equipment information as the second full power equipment specification information set. The explanation corresponding to the second full power equipment specification information set can refer to the explanation of the first full power equipment specification information set.

[0067] Sub-step 2: determining the second infrared image feature information corresponding to each second full amount of electric power equipment specification information in the second full amount of electric power equipment specification information set to obtain the second infrared image feature information set.

[0068] Sub-step 3, for each second full amount of power equipment specification information in the above-mentioned second full amount of power equipment specification information set, determine the second image device size information corresponding to the above-mentioned second full amount of power equipment specification information at a shooting distance of the target distance. The second image device size information can be an outer bounding box of the device under the second full amount of power equipment specification information in the image taken at the shooting distance of the target distance.

[0069] Sub-step 4: performing deduplication processing on the obtained second image device size information set to generate a second deduplicated image device size information group.

[0070] The seventh step is to generate a target power device tag for the first deduplicated image device size information set and an associated device tag corresponding to the second deduplicated image device size information set. The target power device tag can indicate that the first deduplicated image device size information set belongs to the outer enclosure corresponding to the target power device. The associated device tag can indicate that the second deduplicated image device size information set belongs to the outer enclosure corresponding to the target power device.

[0071] The eighth step is to generate a first image generation instruction representing the generation of a segmented infrared image based on the first deduplicated image device size information set, the target power device tag, the second deduplicated image device size information group set and the associated device tag.

[0072] The ninth step is to generate a second image generation instruction for generating a segmented infrared image by using a segmentation model representing image segmentation based on an outer bounding box.

[0073] In the tenth step, the first image generation instruction and the second image generation instruction are input into a pre-trained large language model (LLM) to generate a segmented infrared image.

[0074] As one of the invention points, it solves another technical problem: "the problem of inaccuracy in the segmentation process of infrared image segmentation based on infrared technology, so that the segmented object obtained subsequently is not the target power equipment, resulting in the inability to obtain accurate infrared feature information corresponding to the target power equipment." Based on this, the present application obtains the outer bounding box set under each device specification corresponding to the target power equipment and the outer bounding box set under each device specification corresponding to the associated power equipment. Based on the outer bounding box sets of the two, accurate first generation instructions and second generation instructions are generated. Through the first generation instruction and the second generation instruction, it can be instructed that the subsequent large language model can accurately realize the segmentation of the target power equipment in the infrared image by utilizing the image segmentation model based on the outer bounding box and multiple outer bounding box sets with representative labels, so that more accurate infrared feature information corresponding to the target power equipment can be obtained subsequently.

[0075] Optionally, the multi-modal working state information of the device further includes: a device operation spectrum diagram, wherein the device operation spectrum diagram may be a spectrum diagram of the power device during operation.

[0076] Optionally, the generating of the current power equipment operation information and the equipment safety detection result according to the obtained at least one target candidate segmented infrared image may include the following steps: The first step is to determine the equipment operation spectrum graph corresponding to each electric equipment information in the above electric equipment information group set as the candidate equipment operation spectrum graph, and obtain the candidate equipment operation spectrum graph set.

[0077] In the second step, each candidate device operation spectrum in the above candidate device operation spectrum set is input into the spectrum feature information extraction layer based on the attention mechanism to generate the first spectrum feature information and obtain the first spectrum feature information set. The spectrum feature information extraction layer can be a network layer that extracts the spectrum feature information in the image. In practice, the spectrum feature information extraction layer based on the attention mechanism can be a multi-head attention mechanism module in Transformer. The first spectrum feature information can be a vector in vector form that represents the semantic features of the spectrum.

[0078] The third step is to input the above-mentioned device operation spectrum diagram into the above-mentioned spectrum feature information extraction layer to generate the second spectrum feature information.

[0079] In the fourth step, for each first spectrum feature information in the first spectrum feature information set, the first spectrum feature information and the second spectrum feature information are input into a spectrum similarity generation layer based on a convolution layer to generate spectrum similarity. The spectrum similarity generation layer may be a network layer for generating spectrum similarity. The spectrum similarity may be the degree of similarity of spectrum content in an image. The spectrum similarity generation layer based on a convolution layer may be a network layer for generating spectrum similarity by connecting multiple convolution layers in series.

[0080] Step 5: Select the candidate device operation spectrum graphs whose corresponding spectrum similarity is greater than a preset similarity from the above candidate device operation spectrum graph set, and obtain at least one candidate device operation spectrum graph. The preset similarity can be a predetermined similarity value. For example, the spectrum similarity can be 0.5.

[0081] In a sixth step, in response to the at least one candidate device operation spectrum diagram being not empty, the current power device operation information and the device safety detection result are generated according to the at least one candidate device operation spectrum diagram and the at least one target candidate segmented infrared diagram.

[0082] As an example, first, the above-mentioned execution subject can input the above-mentioned at least one target candidate segmented infrared image and at least one target candidate segmented infrared image into the power equipment operation information generation model to generate at least one first power equipment operation information and at least one second power equipment operation information. Then, the above-mentioned execution subject can classify each power equipment operation information in the at least one first power equipment operation information and the at least one second power equipment operation information to determine the number of information under each operation type. Then, the operation content of the operation type with the largest number of corresponding information is determined as the current power equipment operation information, and the equipment safety detection result of the operation type of the operation type is generated. Among them, the equipment safety detection result can be matched one by one with the operation type.

[0083] As another example, the execution subject may generate a generation instruction for generating current power equipment operation information and equipment safety detection results based on the at least one candidate equipment operation spectrum diagram and the at least one target candidate segmented infrared diagram. Then, the generation instruction is input into the large language model to generate the current power equipment operation information and the equipment safety detection results.

[0084] Optionally, the generating of the current power equipment operation information and the equipment safety detection result according to the at least one candidate equipment operation spectrum diagram and the at least one target candidate segmented infrared diagram may include the following steps: The first step is to determine at least one power device information corresponding to the at least one candidate device operation spectrum diagram as at least one first power device information, and determine at least one power device corresponding to the at least one target candidate segmentation infrared diagram as at least one second power device information. Among them, the first power device information in the at least one first power device information has a one-to-one correspondence with the candidate device operation spectrum diagram in the at least one candidate device operation spectrum diagram. The second power device Western Sydney in the at least one second power device information has a one-to-one correspondence with the at least one target candidate segmentation infrared diagram.

[0085] The second step is to determine whether there is the same power equipment information between the at least one first power equipment information and the at least one second power equipment information.

[0086] In the third step, in response to determining existence, for each piece of identical power equipment information among the at least one identical power equipment information obtained, determine the historical power equipment operation information in the historical time period corresponding to the above identical power equipment information as the identical power equipment operation information.

[0087] The fourth step is to generate the above-mentioned current power equipment operation information and the above-mentioned equipment safety detection result based on the obtained at least one identical power equipment operation information.

[0088] As an example, first, the execution subject may classify each of the same power equipment operation information in at least one of the same power equipment operation information to determine the number of information under each operation type. Then, the operation content of the operation type with the largest number of corresponding information is determined as the current power equipment operation information, and the equipment safety detection result of the operation type of the operation type is generated. Among them, the equipment safety detection result may be matched one by one with the operation type.

[0089] As another example, the execution subject may generate a generation instruction for generating current power equipment operation information and equipment safety detection results based on at least one identical power equipment operation information. Then, the generation instruction is input into the large language model to generate the current power equipment operation information and the equipment safety detection results.

[0090] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the power equipment related information sending method of some embodiments of the present disclosure, the operation status detection and equipment safety detection of the power equipment can be realized quickly and efficiently under the premise of ensuring the detection accuracy, so as to avoid the occurrence of equipment failure problems. Specifically, the reason why the relevant operation status detection and equipment safety detection are not accurate and efficient is that the efficiency of manual detection of massive power equipment in rural and remote areas is too low, and the detection results are often not effectively guaranteed. In addition, if the local fault is not handled in time, it may spread to the entire power system, resulting in a larger range of power outages or equipment damage (such as transformer burning, line short circuit, etc.), voltage fluctuations, harmonic interference and other problems in the power equipment, affecting the normal operation of precision equipment (such as medical instruments, data centers). Based on this, the power equipment related information sending method of some embodiments of the present disclosure, first, in response to receiving the equipment safety detection information corresponding to the target power equipment sent by the power equipment information submission terminal, the power equipment information corresponding to the above target power equipment is obtained as the target power equipment information. Among them, the above target power equipment information includes: target power equipment specification information and equipment multimodal working status information in the current time period. Here, the target power equipment information obtained is used to facilitate the subsequent matching of similar power equipment data, so as to quickly determine the operating status while ensuring the accuracy of the operating status determination. Then, at least one power equipment specification information that matches the above-mentioned target power equipment specification information is determined, so as to facilitate the subsequent acquisition of power equipment data that matches the equipment specifications corresponding to the target power equipment. Next, a power equipment information group set corresponding to the above-mentioned at least one power equipment specification information and the above-mentioned target power equipment specification information is screened out from the power equipment information library as a similar power equipment information set, which can quickly screen out power equipment information with similar information content corresponding to the target power equipment information. Among them, the power equipment information group is the power equipment information corresponding to the power equipment in each historical time period. Furthermore, a multimodal working feature set and a power basic feature set for the power equipment are set as clustering features for subsequent clustering processing, so as to facilitate the grouping of power equipment information with the same features. Next, in response to determining that the number of electric power equipment information corresponding to the electric power equipment information set is greater than a preset number, clustering processing is performed on the electric power equipment information set and the target electric power equipment information according to the multimodal working feature set and the electric power basic feature set to generate an electric power equipment information cluster. Here, through clustering processing, electric power equipment information with similar information content to the target electric power equipment information can be quickly determined. Furthermore, according to the electric power equipment information cluster, the current electric power equipment operation information and the corresponding equipment safety detection results corresponding to the target electric power equipment can be quickly and accurately generated.Finally, the current power equipment operation information and the equipment safety detection results are sent to the power equipment information submission terminal. In summary, through clustering processing, the power equipment information similar to the target power equipment information can be matched quickly and accurately, so as to quickly and accurately generate the corresponding current power equipment operation information and the corresponding equipment safety detection results.

[0091] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a device for sending information related to electric power equipment. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the device for sending information related to electric power equipment can be specifically applied to various electronic devices.

[0092] like Figure 2 As shown, a device 200 for sending information related to electric power equipment includes: an acquisition unit 201, a determination unit 202, a screening unit 203, a setting unit 204, an execution unit 205, a generation unit 206 and a sending unit 207. The acquisition unit 201 is configured to, in response to receiving equipment safety detection information corresponding to the target electric power equipment sent by the electric power equipment information submission terminal, acquire the electric power equipment information corresponding to the above target electric power equipment as the target electric power equipment information, wherein the above target electric power equipment information includes: target electric power equipment specification information and equipment multimodal working status information in the current time period; the determination unit 202 is configured to determine at least one electric power equipment specification information matching the above target electric power equipment specification information; the screening unit 203 is configured to screen out a set of electric power equipment information corresponding to the above at least one electric power equipment specification information and the above target electric power equipment specification information from the electric power equipment information library, wherein the electric power equipment information group is the electric power equipment specification information corresponding to the electric power equipment in each historical time period. Power equipment information; a setting unit 204, configured to set a multimodal working feature set and a power basic feature set for the power equipment; an execution unit 205, configured to, in response to determining that the number of power equipment information corresponding to the above-mentioned power equipment information set is greater than a preset number, perform clustering processing on the above-mentioned power equipment information set and the above-mentioned target power equipment information according to the multimodal working feature set and the above-mentioned power basic feature set to generate a power equipment information cluster set; a generation unit 206, configured to generate the current power equipment operation information and the corresponding equipment safety detection result corresponding to the above-mentioned target power equipment according to the above-mentioned power equipment information cluster set; a sending unit 207, configured to send the above-mentioned current power equipment operation information and the above-mentioned equipment safety detection result to the above-mentioned power equipment information submission terminal.

[0093] It can be understood that the units recorded in the power equipment related information sending device 200 are similar to the reference Figure 1Therefore, the operations, features and beneficial effects described above for the method are also applicable to the power equipment related information sending device 200 and the units contained therein, and will not be described in detail here.

[0094] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device (eg, an electronic device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0095] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 to a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0096] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0097] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0098] It should be noted that the computer-readable medium in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0099] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with 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"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0100] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist independently without being installed in the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: in response to receiving the equipment safety detection information corresponding to the target electric equipment sent by the electric equipment information submission terminal, obtain the electric equipment information corresponding to the above-mentioned target electric equipment as the target electric equipment information, wherein the above-mentioned target electric equipment information includes: target electric equipment specification information and equipment multimodal working status information in the current time period; determine at least one electric equipment specification information that matches the above-mentioned target electric equipment specification information; filter out the electric equipment information group corresponding to the above-mentioned at least one electric equipment specification information and the above-mentioned target electric equipment specification information from the electric equipment information library. , wherein the power equipment information group is the power equipment information corresponding to the power equipment in each historical time period; a multimodal working feature set and a power basic feature set are set for the power equipment; in response to determining that the number of power equipment information corresponding to the above power equipment information group set is greater than a preset number, clustering processing is performed on the above power equipment information group set and the above target power equipment information according to the multimodal working feature set and the above power basic feature set to generate a power equipment information cluster set; based on the above power equipment information cluster set, the current power equipment operation information corresponding to the above target power equipment and the corresponding equipment safety detection result are generated; the above current power equipment operation information and the above equipment safety detection result are sent to the above power equipment information submission terminal.

[0101] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0102] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0103] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be set in a processor, for example, it may be described as: a processor includes an acquisition unit, a determination unit, a screening unit, a setting unit, an execution unit, a generation unit and a sending unit. Among them, the names of these units do not constitute a limitation on the unit itself under certain circumstances. For example, the determination unit may also be described as "a unit for determining at least one power device specification information that matches the above-mentioned target power device specification information".

[0104] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that may be used include, without limitation, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0105] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A method for sending information related to electric power equipment, comprising: In response to receiving the equipment safety detection information corresponding to the target electric equipment sent by the electric equipment information submitting terminal, acquiring the electric equipment information corresponding to the target electric equipment as the target electric equipment information, wherein the target electric equipment information includes: specification information of the target electric equipment and multi-modal working state information of the equipment in the current time period; determining at least one electric device specification information matching the target electric device specification information; Filtering out a set of electric power equipment information groups corresponding to the at least one electric power equipment specification information and the target electric power equipment specification information from an electric power equipment information library, wherein the electric power equipment information group is electric power equipment information corresponding to the electric power equipment in each historical time period; Setting a multi-modal working feature set and a basic power feature set for power equipment; In response to determining that the number of electric device information corresponding to the electric device information set is greater than a preset number, clustering processing is performed on the electric device information set and the target electric device information according to the multimodal working feature set and the electric power basic feature set to generate an electric device information cluster set; Generating current power equipment operation information and corresponding equipment safety detection results corresponding to the target power equipment according to the power equipment information cluster; The current power equipment operation information and the equipment safety detection result are sent to the power equipment information submission terminal.

2. The method according to claim 1, wherein: The setting is for a multi-modal working feature set and a basic power feature set of the power equipment, including: Determine a first multimodal feature set corresponding to the target power device specification information and a second multimodal feature set corresponding to the at least one power device specification information; De-duplication and fusion are performed on the first multimodal feature set and the second multimodal feature set to obtain the multimodal working feature set; Extracting a basic power feature set corresponding to the target power equipment specification information.

3. The method according to claim 1, wherein: The performing of clustering processing on the power equipment information set and the target power equipment information according to the multimodal working feature set and the power basic feature set to generate a power equipment information cluster set includes: For each electric device information group in the electric device information group set, the following first generation step is performed: Extracting a multimodal operating feature information set corresponding to the multimodal operating feature set from the power equipment information group as a first multimodal operating feature information set; Extracting a power basic feature information set corresponding to the power basic feature set from the power equipment information group as a first power basic feature information set; Extracting a multimodal operating feature information set corresponding to the multimodal operating feature set from the target power equipment information as a second multimodal operating feature information set; Extracting a power basic feature information set corresponding to the power basic feature set from the target power equipment information as a second power basic feature information set; According to the obtained multiple first multimodal operating characteristic information sets, multiple first electric power basic characteristic information sets, the second multimodal operating characteristic information set and the second electric power basic characteristic information set, a clustering algorithm is used to generate an electric power equipment information cluster set.

4. The method according to claim 1, wherein: The generating, according to the electric power equipment information cluster, current electric power equipment operation information and corresponding equipment safety detection result corresponding to the target electric power equipment comprises: Filtering out the electric device information cluster where the target electric device information is located from the electric device information cluster set as the target electric device information cluster; Filtering out, from the target power equipment information cluster, power equipment information whose information proximity relationship with the target power equipment information satisfies a preset relationship condition as adjacent power equipment information, and obtaining at least one adjacent power equipment information; In response to determining that the at least one adjacent power device information does not include the cluster center corresponding to the target power device information cluster, fusing the cluster center corresponding to the target power device information cluster with the at least one adjacent power device information to generate a candidate power device information set; For each piece of candidate electric equipment information in the candidate electric equipment information set, determining historical electric equipment operation information in a historical time period corresponding to the candidate electric equipment information; The current power equipment operation information and the equipment safety detection result are determined based on the obtained historical power equipment operation information set.

5. The method according to claim 1, wherein: The multi-modal working status information of the device includes: an infrared image of the device operation; and The method further comprises: In response to determining that the number of electric device information corresponding to the electric device information set is less than or equal to the preset number, determining the device operation infrared map corresponding to each electric device information in the electric device information set as a candidate device operation infrared map, and obtaining a candidate device operation infrared map set; Performing semantic segmentation of power equipment on the infrared image of the device operation to generate a segmented infrared image; Performing power equipment semantic segmentation on each candidate device operation infrared image in the candidate device operation infrared image set to generate a candidate segmented infrared image, thereby obtaining a candidate segmented infrared image set; Determine an average value of pixel values ​​corresponding to the segmented infrared image as a first pixel average value, and determine an average value of pixels corresponding to each candidate segmented infrared image in the candidate segmented infrared image set as a second pixel average value; Filtering out at least one candidate segmentation infrared image corresponding to a difference between a second pixel average value and the first pixel average value in a predetermined value range from the candidate segmentation infrared image set; In response to determining that the at least one candidate segmented infrared image is not empty, determining whether there is a target candidate segmented infrared image in the at least one candidate segmented infrared image with the same color region distribution as that of the segmented infrared image; In response to determining the existence, the current power equipment operation information and the equipment safety detection result are generated according to the obtained at least one target candidate segmented infrared image.

6. The method according to claim 5, wherein: The device multi-modal working state information also includes: a device operation spectrum diagram; and The step of generating the current power equipment operation information and the equipment safety detection result according to the obtained at least one target candidate segmentation infrared image comprises: Determine the device operation spectrum graph corresponding to each piece of electric device information in the electric device information group set as a candidate device operation spectrum graph, and obtain a candidate device operation spectrum graph set; Inputting each candidate device operation spectrum graph in the candidate device operation spectrum graph set into a spectrum feature information extraction layer based on an attention mechanism to generate first spectrum feature information, thereby obtaining a first spectrum feature information set; Inputting the device operation spectrum diagram into the spectrum feature information extraction layer to generate second spectrum feature information; For each first spectrum feature information in the first spectrum feature information set, inputting the first spectrum feature information and the second spectrum feature information into a spectrum similarity generation layer based on a convolution layer to generate spectrum similarity; Filter out candidate device operation spectrum graphs whose corresponding spectrum similarity is greater than a preset similarity from the candidate device operation spectrum graph set, and obtain at least one candidate device operation spectrum graph; In response to the at least one candidate device operation spectrum diagram being not empty, the current power device operation information and the device safety detection result are generated according to the at least one candidate device operation spectrum diagram and the at least one target candidate segmented infrared diagram.

7. The method according to claim 6, wherein: The generating the current power equipment operation information and the equipment safety detection result according to the at least one candidate equipment operation spectrum diagram and the at least one target candidate segmented infrared diagram comprises: Determine at least one piece of power equipment information corresponding to the at least one candidate device operation spectrum diagram as at least one piece of first power equipment information, and determine at least one piece of power equipment corresponding to the at least one target candidate segmented infrared diagram as at least one piece of second power equipment information; determining whether the at least one first power device information and the at least one second power device information have the same power device information; In response to determining that there is, for each piece of identical electric device information among the obtained at least one identical electric device information, determining historical electric device operation information in a historical time period corresponding to the identical electric device information as the identical electric device operation information; The current power equipment operation information and the equipment safety detection result are generated according to the obtained at least one identical power equipment operation information.

8. A device for transmitting information related to electric power equipment, comprising: The acquiring unit is configured to, in response to receiving the equipment safety detection information corresponding to the target electric equipment sent by the electric equipment information submitting terminal, acquire the electric equipment information corresponding to the target electric equipment as the target electric equipment information, wherein the target electric equipment information includes: specification information of the target electric equipment and multi-modal working state information of the equipment in the current time period; a determining unit configured to determine at least one electric device specification information matching the target electric device specification information; A screening unit is configured to screen out a set of electric device information groups corresponding to the at least one electric device specification information and the target electric device specification information from the electric device information library, wherein the electric device information group is electric device information corresponding to the electric device in each historical time period; A setting unit configured to set a multi-modal working feature set and a power basic feature set for the power equipment; an execution unit, configured to, in response to determining that the number of electric device information corresponding to the electric device information set is greater than a preset number, perform clustering processing on the electric device information set and the target electric device information according to the multimodal working feature set and the electric power basic feature set to generate an electric device information cluster set; A generating unit, configured to generate current power equipment operation information and corresponding equipment safety detection result corresponding to the target power equipment according to the power equipment information cluster; The sending unit is configured to send the current power equipment operation information and the equipment safety detection result to the power equipment information submission terminal.

9. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images