Resume data automatic labeling method, system, medium and equipment

Abstract

The invention relates to a method, a system, a medium and equipment for automatically labeling resume data. The method comprises the following steps of: constructing a label system; obtaining new resume data, and performing fault knowledge extraction according to the tag system through the large language model to obtain extracted fault knowledge; judging whether the extracted fault knowledge is matched in a label library or not, and if yes, newly adding the extracted fault knowledge in the fault mode; and if not, generating a new tag through the large language model. According to the method, the label system of the resume is constructed, after the new resume data is generated, the resume data is automatically structured, the extracted label data is standardized through comparison of the knowledge base and is standardized in the resume, and new labels are automatically generated for labels which do not exist in the existing knowledge base; an effective fault knowledge base continuous updating mechanism is established, automatic analysis of resumes and fault knowledge extraction, accumulation and utilization are achieved, and the problems of data islands and the like are effectively solved.

Description

Technical Field

[0001] This invention relates to the technical field of equipment management, and more specifically, to a method, system, medium, and device for automatically labeling resume data. Background Technology

[0002] In the power industry, equipment is a company's core asset, and components are the smallest unit of equipment management. Maintaining the reliable operation of components is one of the key factors supporting the company's safety and production. Companies accumulate a wealth of experience and knowledge about components through daily operation, maintenance, and troubleshooting. However, this experience and knowledge is not transformed into effective data and stored, making it impossible to solidify and pass on expert experience, and hindering the company's ability to improve decision-making efficiency.

[0003] With the continuous development of digital technology, the transformation of enterprises towards digitalization and intelligence has become a mainstream trend. However, currently, the recording of component operation, maintenance, and defects is usually completed in different business systems. This results in a large amount of data being generated on the one hand, and data silos forming on the other, making it difficult to extract data and realize its value. The history data stored in the business systems requires manual analysis by analysts to obtain and accumulate fault data, which requires a lot of human and material resources and cannot achieve automated history analysis, fault knowledge extraction, accumulation, and utilization. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method, system, medium and device for automatic annotation of resume data, in view of the problems existing in the prior art.

[0005] The technical solution adopted by this invention to solve its technical problem is: to construct an automatic resume data annotation method, including the following steps:

[0006] Build a tag system;

[0007] New resume data is acquired, and fault knowledge is extracted using a large language model according to the aforementioned tag system to obtain the extracted fault knowledge.

[0008] Determine whether the extracted fault knowledge matches the tag library. If it matches, add the extracted fault knowledge to the fault mode.

[0009] If there is no match, a new label is generated using the large language model.

[0010] In the automatic resume data annotation method of the present invention, the construction of the tag system includes:

[0011] Obtain object information, fault information, fault mode handling information, and fault time;

[0012] Determine the code type and description type of the object information, the fault information, the fault mode handling information, and the fault time;

[0013] Generate corresponding tag information based on the code type and the description type;

[0014] The label system is formed based on the label information.

[0015] In the automatic resume data annotation method of the present invention, the object information includes: functional location, equipment and components;

[0016] The fault information includes: fault mode, fault symptoms, and fault root cause;

[0017] The fault mode processing information includes: a fault mode processing description;

[0018] The fault time includes: the time when the fault occurred.

[0019] In the automatic resume data annotation method of the present invention, the tag information includes:

[0020] Function location code: string;

[0021] Functional location description: Text description;

[0022] Device code: string;

[0023] Equipment description: Text description;

[0024] Equipment fault mode code: string;

[0025] Equipment failure mode description: textual description;

[0026] Equipment failure mode symptom code: string;

[0027] Equipment failure mode symptom description: textual description;

[0028] Component code: string;

[0029] Component description: Text description;

[0030] Component failure mode description: textual description;

[0031] Component failure mode symptom code: string;

[0032] Component failure mode symptom description: textual description;

[0033] Component root cause code: string;

[0034] Component root cause description: textual description;

[0035] Fault occurrence time: string;

[0036] Troubleshooting measures: textual description.

[0037] In the automatic resume data annotation method of the present invention, the new resume data includes: notification data, work order data, technical problem data, and experience feedback data.

[0038] In the automatic labeling method for resume data described in this invention, the step of determining whether the extracted fault knowledge matches in the tag library, and if it matches, adding the extracted fault knowledge to the fault mode, includes the following steps:

[0039] Step 1: Determine whether a functional location has been extracted from the extracted fault knowledge. If not, end the process. If a functional location has been extracted, extract the functional location description corresponding to the functional location and proceed to Step 2.

[0040] Step 2: Determine if the device description has been extracted; if extracted, proceed to Step 2.1; if not extracted, proceed to Step 3.

[0041] Step 2.1: Determine whether the knowledge base contains a fuzzy match for the device description under the functional location. If yes, proceed to step 2.2; otherwise, proceed to step 3.1.

[0042] Step 2.2: Obtain the device code corresponding to the device description in Step 2.1 through the configuration configuration library;

[0043] Step 2.3: Determine whether a device failure status description has been extracted. If yes, proceed to step 2.4; otherwise, proceed to step 2.7.

[0044] Step 2.4: Determine whether a fuzzy match has been found in the knowledge base for the device failure status. If so, obtain the device failure mode and its code from the fault knowledge and proceed to step 2.5; otherwise, generate a new device failure status and output it to the user.

[0045] Step 2.5: Determine if any signs of device failure mode have been detected. If yes, proceed to Step 2.6; otherwise, end the process.

[0046] Step 2.6: Determine whether a fuzzy match for the device fault mode symptom is found in the knowledge base. If yes, retrieve the device fault mode description and its code from the fault mode library; otherwise, generate a new device fault mode and output it to the user.

[0047] Step 2.7: Determine whether a description of the device failure mode symptoms has been extracted. If yes, proceed to step 2.8; otherwise, end the process.

[0048] Step 2.8: Determine whether a device failure mode symptom is found in the knowledge base. If so, retrieve the device failure mode symptom description and its code from the failure mode library and determine the device failure mode corresponding to the symptom. If not, generate a new device failure mode symptom and output it to the user.

[0049] Step 3: Determine if the component description has been extracted; if yes, proceed to step 3.1; if no, end the process.

[0050] Step 3.1: Determine whether the knowledge base has a fuzzy match for the functional location containing the component description. If yes, obtain the component description and code, and proceed to Step 3.2; otherwise, provide feedback to the user.

[0051] Step 3.2: Obtain the equipment code and description of the component by configuring the configuration library, then proceed to Step 3.3;

[0052] Step 3.3: Determine whether a component failure mode description has been extracted. If yes, proceed to step 3.4; otherwise, proceed to step 3.5.

[0053] Step 3.4: Determine whether the knowledge base matches a component with the fault mode description. If yes, retrieve the component fault mode description and its code from the knowledge base and proceed to steps 3.4.1 and 3.4.2 respectively. If no, generate a new component fault mode and output it to the user.

[0054] Step 3.4.1: Determine whether any component failure mode symptoms have been extracted. If yes, proceed to step 3.4.3; otherwise, end the process.

[0055] Step 3.4.2: Determine whether the root cause of the component failure has been extracted. If yes, proceed to step 3.4.4; otherwise, end the process.

[0056] Step 3.4.3: Determine whether a fuzzy match for a component failure mode symptom is found in the knowledge base. If yes, obtain the component failure mode symptom description and its code, and end the process; otherwise, generate a new component failure mode symptom and output it to the user.

[0057] Step 3.4.4: Determine whether a fuzzy match has been found in the knowledge base for the root cause of the component. If so, obtain the description of the component failure mode symptoms and its code; otherwise, generate a new root cause of the component failure and output it to the user.

[0058] Step 3.5: Determine whether any component failure mode symptoms have been extracted. If yes, proceed to step 3.5.1; otherwise, end the process.

[0059] Step 3.5.1: Determine whether a component failure mode symptom is found in the knowledge base. If so, obtain the component failure mode symptom description and its code, and determine the component failure mode to which the component failure mode symptom belongs. If not, generate a new component failure mode symptom and output it to the user.

[0060] In the automatic resume data annotation method of the present invention, the step of generating a new label if there is a mismatch includes:

[0061] If there is no match, the new label is generated using the large language model.

[0062] This invention also provides an automatic resume data annotation system, comprising:

[0063] System building units, used to construct the tag system;

[0064] The fault knowledge extraction unit is used to acquire history data and extract fault knowledge from the history data according to the tag system using a large language model to obtain the extracted fault knowledge.

[0065] The tag matching unit is used to determine whether the extracted fault knowledge matches in the tag library. If it matches, the extracted fault knowledge is added to the fault mode.

[0066] A tag generation unit is used to generate new tags when there is no matching fault knowledge in the tag library.

[0067] The present invention also provides a storage medium storing a computer program adapted for loading by a processor to perform the steps of the automatic resume data annotation method described above.

[0068] The present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the steps of the automatic resume data annotation method described above by calling the computer program stored in the memory.

[0069] The automatic resume data annotation method, system, medium, and device of this invention have the following beneficial effects: The method includes the following steps: constructing a tag system; acquiring new resume data and extracting fault knowledge according to the tag system using a large language model; determining whether the extracted fault knowledge matches the tag library; if it matches, adding the extracted fault knowledge to the fault mode; if it does not match, generating new tags using the large language model. This invention constructs a resume tag system and automatically structures the resume data after new resume data is generated. It standardizes the extracted tag data through comparison with the knowledge base and incorporates the standard tags into the resume. For tags not present in the existing knowledge base, it automatically generates new tags, establishing an effective continuous update mechanism for the fault knowledge base. This achieves automatic resume analysis, fault knowledge extraction, accumulation, and utilization, effectively solving problems such as data silos. Attached Figure Description

[0070] The present invention will be further described below with reference to the accompanying drawings and embodiments. In the accompanying drawings:

[0071] Figure 1 This is a flowchart illustrating the automatic resume data annotation method provided in an embodiment of the present invention;

[0072] Figure 2 This is a schematic diagram of the matching process of fault knowledge in the tag library provided in the embodiments of the present invention;

[0073] Figure 3 This is a logic block diagram of the automatic resume data annotation system provided in the embodiments of the present invention. Detailed Implementation

[0074] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0075] To address the current lack of effective automatic history annotation methods in the nuclear power field to support the annotation and accumulation of equipment component history data, and the ineffective extraction of fault knowledge from history data, this invention provides an automatic history data annotation method.

[0076] In a preferred embodiment, such as Figure 1 As shown, the automatic annotation method for resume data includes the following steps:

[0077] Step S101: Construct a tag system.

[0078] Specifically, constructing the tagging system includes: acquiring object information, fault information, fault mode handling information, and fault time; determining the code type and description type of the object information, fault information, fault mode handling information, and fault time; generating corresponding tag information based on the code type and description type; and forming the tagging system based on the tag information. Among these, object information includes: functional location, equipment, and components; fault information includes: fault mode, fault symptoms, and root cause; fault mode handling information includes: fault mode handling description; and fault time includes: fault occurrence time.

[0079] Optionally, in this embodiment of the invention, the constructed tag information is as follows:

[0080] Function location code: string;

[0081] Functional location description: Text description;

[0082] Device code: string;

[0083] Equipment description: Text description;

[0084] Equipment fault mode code: string;

[0085] Equipment failure mode description: textual description;

[0086] Equipment failure mode symptom code: string;

[0087] Equipment failure mode symptom description: textual description;

[0088] Component code: string;

[0089] Component description: Text description;

[0090] Component failure mode description: textual description;

[0091] Component failure mode symptom code: string;

[0092] Component failure mode symptom description: textual description;

[0093] Component root cause code: string;

[0094] Component root cause description: textual description;

[0095] Fault occurrence time: string;

[0096] Troubleshooting measures: textual description.

[0097] Step S102: Obtain new resume data and extract fault knowledge according to the label system using a large language model to obtain the extracted fault knowledge.

[0098] Optionally, in this embodiment of the invention, the large language model can be the Deepseek model. Using this Deepseek model, fault knowledge is extracted from the newly generated resume data according to the labeling system in step S101, thus achieving automatic extraction (structuring) of the resume data.

[0099] The new record data includes: notification data, work order data, technical issue data, and experience feedback data. In other words, the new record data may include, but is not limited to: notification data, work order data, technical issues, and experience feedback regarding nuclear power plant equipment technical issues.

[0100] Step S103: Determine whether the extracted fault knowledge matches the tag library. If it matches, add the extracted fault knowledge to the fault mode.

[0101] In this embodiment of the invention, the extracted fault knowledge is compared with data in an existing knowledge base to determine whether it can match in the tag library. If a match is found, it is added to the fault mode. The specific process is as follows: Figure 2 As shown. That is, determining whether the extracted fault knowledge matches the tag library; if it matches, adding the extracted fault knowledge to the fault mode includes the following steps:

[0102] Step 1: Determine whether the function location has been extracted from the fault knowledge. If not, end the process. If the function location has been extracted, extract the function location description corresponding to the function location and proceed to Step 2.

[0103] In this step, it is first determined whether the extracted fault knowledge contains a functional location. If not, the process ends. If a functional location is extracted, the corresponding functional location description is extracted from the configuration configuration library, and then the process proceeds to step 2. The configuration configuration library includes information on objects such as functional locations, equipment, and components, which, together with the fault mode library (including fault modes, fault symptoms, and root causes), constitute the knowledge base.

[0104] Step 2: Determine if the device description has been extracted; if extracted, proceed to Step 2.1; if not extracted, proceed to Step 3.

[0105] In this step, if no functional location is extracted from the extracted fault knowledge, it is further determined whether a device description is extracted. If a device description is extracted, proceed to step 2.1; otherwise, proceed to step 3.

[0106] Step 2.1: Determine whether there is a fuzzy match in the knowledge base that matches the device description under the function location. If yes, proceed to step 2.2; otherwise, proceed to step 3.1.

[0107] In this step, a fuzzy match is performed in the knowledge base to determine whether there is a description of the device under the function location. If yes, proceed to step 2.2; otherwise, proceed to step 3.1.

[0108] Step 2.2: Obtain the device code corresponding to the device description in Step 2.1 by configuring the configuration library.

[0109] Step 2.3: Determine whether a device failure status description has been extracted. If yes, proceed to step 2.4; otherwise, proceed to step 2.7.

[0110] In this step, after obtaining the device code corresponding to the device description through the configuration library in step 2.2, it is further determined whether the device failure state description (i.e., device failure mode analysis) is extracted from the extracted fault knowledge. If it is extracted, proceed to step 2.4; if the device failure state description is not extracted, proceed to step 2.7.

[0111] Step 2.4: Determine whether a fuzzy match for the device failure status is found in the knowledge base. If so, obtain the device failure mode and its code from the fault knowledge and proceed to step 2.5; otherwise, generate a new device failure status and output it to the user.

[0112] In this step, if the device failure status is extracted, a fuzzy match is performed in the knowledge base to determine if the device failure status is matched. If it is, the device failure mode and its code are matched in the fault knowledge, and the process proceeds to step 2.5. If no fuzzy match is found, a new device failure status is generated and output to the user. By outputting the feedback to the user, the user can confirm whether the device failure status is correct and proceed to the fault mode addition process in the fault management platform.

[0113] Step 2.5: Determine whether any signs of device failure mode have been extracted. If yes, proceed to step 2.6; otherwise, end the process.

[0114] Step 2.6: Determine whether a fuzzy match for the device fault mode symptom is found in the knowledge base. If yes, retrieve the device fault mode description and its code from the fault mode library; otherwise, generate a new device fault mode and output it to the user.

[0115] In this step, if a device fault mode symptom is extracted in step 2.5, it is further determined whether the device fault mode has this symptom in the knowledge base through fuzzy matching. If so, the description and code of the device fault mode symptom are obtained from the fault mode library, and the process ends. If not, a new device fault mode symptom is generated and output to the user, who then confirms whether the generated new device fault mode symptom is correct and enters the fault mode addition process of the fault management platform.

[0116] Step 2.7: Determine whether a description of the device failure mode symptoms has been extracted. If yes, proceed to step 2.8; otherwise, end the process.

[0117] Step 2.8: Determine whether a fuzzy match for a device fault mode symptom is found in the knowledge base. If yes, retrieve the device fault mode symptom description and its code from the fault mode library and determine the device fault mode corresponding to the symptom. If no, generate a new device fault mode symptom and output it to the user.

[0118] In this step, it is determined whether a fuzzy match can be found in the knowledge base that the device fault mode has this symptom. If so, the description and code of the device fault mode symptom are obtained from the fault mode library. By using the relationship between fault modes and symptoms in the knowledge base, the device fault mode to which the symptom belongs is determined. If not, a new device fault mode symptom is generated and feedback is sent to the user to confirm whether the new device fault mode symptom is correct, and the fault mode addition process of the fault management platform is entered.

[0119] Step 3: Determine whether the component description has been extracted; if yes, proceed to step 3.1; if no, end the process.

[0120] Step 3.1: Determine whether there is a component description under the function location in the knowledge base. If yes, obtain the component description and code, and proceed to Step 3.2; otherwise, output feedback to the user.

[0121] In this step, it is determined whether a component with the description can be found in the knowledge base under the functional location. If so, the tag should be a component tag. The component description and its code are obtained, and the process proceeds to step 3.2. If not, feedback is given to the engineer to confirm whether the equipment / component is missing from the equipment disassembly list, and the process of adding a fault mode in the fault management platform is initiated.

[0122] Step 3.2: Obtain the equipment code and description of the component by configuring the configuration library, and proceed to step 3.3.

[0123] Step 3.3: Determine whether a component failure mode description has been extracted. If yes, proceed to step 3.4; otherwise, proceed to step 3.5.

[0124] Step 3.4: Determine whether a component fault mode description is matched in the knowledge base. If so, retrieve the component fault mode description and its code from the knowledge base and proceed to steps 3.4.1 and 3.4.2 respectively. If not, generate a new component fault mode and output it to the user.

[0125] In this step, it is determined whether a description of a fault mode under the component can be found in the knowledge base. If so, the description and code of the component's fault mode are obtained from the knowledge base, and the process proceeds to steps 3.4.1 and 3.4.2 respectively. If not, a new component fault mode is generated and fed back to the engineer for confirmation of whether the new component fault mode is correct, and the process of adding a fault mode in the fault management platform is then initiated.

[0126] Step 3.4.1: Determine whether any component failure mode symptoms have been extracted. If yes, proceed to step 3.4.3; otherwise, end the process.

[0127] Step 3.4.2: Determine whether the root cause of the component failure has been extracted. If yes, proceed to step 3.4.4; otherwise, end the process.

[0128] Step 3.4.3: Determine whether a component failure mode symptom is found in the knowledge base. If yes, obtain the component failure mode symptom description and its code, and end the process. If no, generate a new component failure mode symptom and output it to the user.

[0129] In this step, it is determined whether a fuzzy match can be found in the knowledge base that the component failure mode has this symptom. If so, the description and code of the component failure mode symptom are obtained and the process ends. If not, a new component failure mode symptom is generated and fed back to the engineer for confirmation of whether the new component failure mode symptom is correct, and the process of adding a new failure mode in the fault management platform is entered.

[0130] Step 3.4.4: Determine whether a fuzzy match has been found in the knowledge base for the root cause of the component. If so, obtain the description of the component failure mode symptoms and its code; otherwise, generate a new root cause of the component failure and output it to the user.

[0131] In this step, it is determined whether a fuzzy match can be found in the knowledge base that the component failure mode has this root cause. If so, the symptom description and code of the component failure mode are obtained; if not, a new component failure mode root cause is generated and fed back to the engineer to confirm whether the new component failure mode root cause is correct, and then the failure mode addition process is entered into the fault management platform.

[0132] Step 3.5: Determine whether any component failure mode symptoms have been extracted. If yes, proceed to step 3.5.1; otherwise, end the process.

[0133] Step 3.5.1: Determine whether a component failure mode symptom is found in the knowledge base. If so, obtain the component failure mode symptom description and its code, and determine the component failure mode to which the component failure mode symptom belongs. If not, generate a new component failure mode symptom and output it to the user.

[0134] In this step, it is determined whether a fuzzy match can be found in the knowledge base that the component failure mode has this symptom. If so, the description and code of the component failure mode symptom are obtained, and the component failure mode to which the symptom belongs is determined by the relationship between failure modes and symptom in the knowledge base. If not, a new component failure mode symptom is generated and fed back to the engineer to confirm whether the new component failure mode feature is correct, and the process of adding a failure mode is entered into the fault management platform.

[0135] It should be noted that the fault mode addition process of the fault management platform referred to in this invention is the approval process of nuclear power plants. Therefore, the existing nuclear power plant fault mode approval process can be directly referred to, and will not be repeated here.

[0136] Step S104: If there is no match, generate a new label using the large language model.

[0137] Optionally, in this embodiment of the invention, generating a new label if there is no match includes: generating a new label through a large language model if there is no match.

[0138] refer to Figure 3 The present invention also provides an automatic resume data annotation system.

[0139] In a preferred embodiment, the automatic resume data annotation system includes:

[0140] System building unit 301 is used to build the tag system.

[0141] The fault knowledge extraction unit 302 is used to acquire history data and extract fault knowledge from the history data according to the tag system through a large language model to obtain the extracted fault knowledge.

[0142] The tag matching unit 303 is used to determine whether the extracted fault knowledge matches in the tag library. If it matches, the extracted fault knowledge is added to the fault mode.

[0143] The tag generation unit 304 is used to generate new tags when there is no matching fault knowledge in the tag library.

[0144] Specifically, the specific coordination process between the various units in the automatic resume data annotation system can be found in the automatic resume data annotation method described above, and will not be repeated here.

[0145] This invention constructs a resume tagging system and automatically structures new resume data upon its generation. Simultaneously, it standardizes extracted tag data through comparison with a knowledge base and incorporates these standards into the resume. Furthermore, it automatically generates new tags for tags not present in the existing knowledge base, establishing an effective mechanism for continuous updating the fault knowledge base.

[0146] Furthermore, an electronic device according to the present invention includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program to implement the automatic resume data annotation method as described above. Specifically, according to embodiments of the present invention, the processes described above with reference to the flowchart can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, when the computer program is downloaded, installed, and executed by an electronic device, it performs the functions defined in the methods of the embodiments of the present invention. The electronic device in the present invention can be a terminal such as a laptop, desktop computer, tablet computer, or smartphone, or it can be a server.

[0147] Furthermore, one type of storage medium of the present invention stores a computer program thereon, which, when executed by a processor, implements the automatic history data annotation method described above. Specifically, it should be noted that the storage medium described above in the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, wherein computer-readable program code is carried. The transmitted data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0148] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0149] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0150] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0151] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0152] The above embodiments are only for illustrating the technical concept and features of the present invention, and are intended to enable those skilled in the art to understand the content of the present invention and implement it accordingly. They do not limit the scope of protection of the present invention. All equivalent changes and modifications made within the scope of the claims of the present invention should fall within the scope of the claims of the present invention.

Claims

1. A method for automatically labeling resume data, characterized in that, Includes the following steps: Build a tag system; New resume data is acquired, and fault knowledge is extracted using a large language model according to the aforementioned tag system to obtain the extracted fault knowledge. Determine whether the extracted fault knowledge matches the tag library. If it matches, add the extracted fault knowledge to the fault mode. If there is no match, a new label is generated using the large language model.

2. The automatic resume data annotation method according to claim 1, characterized in that, The construction of the tag system includes: Obtain object information, fault information, fault mode handling information, and fault time; Determine the code type and description type of the object information, the fault information, the fault mode handling information, and the fault time; Generate corresponding tag information based on the code type and the description type; The label system is formed based on the label information.

3. The automatic resume data annotation method according to claim 2, characterized in that, The object information includes: functional location, equipment, and components; The fault information includes: fault mode, fault symptoms, and fault root cause; The fault mode processing information includes: a fault mode processing description; The fault time includes: the time when the fault occurred.

4. The automatic resume data annotation method according to claim 2, characterized in that, The label information includes: Function location code: string; Functional location description: Text description; Device code: string; Equipment description: Text description; Equipment fault mode code: string; Equipment failure mode description: textual description; Equipment failure mode symptom code: string; Equipment failure mode symptom description: textual description; Component code: string; Component description: Text description; Component failure mode description: textual description; Component failure mode symptom code: string; Component failure mode symptom description: textual description; Component root cause code: string; Component root cause description: textual description; Fault occurrence time: string; Troubleshooting measures: textual description.

5. The automatic resume data annotation method according to claim 1, characterized in that, The new resume data includes: notification data, work order data, technical issue data, and experience feedback data.

6. The automatic resume data annotation method according to claim 4, characterized in that, The step of determining whether the extracted fault knowledge matches the tag library, and if it matches, adding the extracted fault knowledge to the fault mode, includes the following steps: Step 1: Determine whether a functional location has been extracted from the extracted fault knowledge. If not, end the process. If a functional location has been extracted, extract the functional location description corresponding to the functional location and proceed to Step 2. Step 2: Determine if the device description has been extracted; if extracted, proceed to Step 2.1; if not extracted, proceed to Step 3. Step 2.1: Determine whether the knowledge base contains a fuzzy match for the device description under the functional location. If yes, proceed to step 2.2; otherwise, proceed to step 3.

1. Step 2.2: Obtain the device code corresponding to the device description in Step 2.1 through the configuration configuration library; Step 2.3: Determine whether a device failure status description has been extracted. If yes, proceed to step 2.4; otherwise, proceed to step 2.

7. Step 2.4: Determine whether a fuzzy match has been found in the knowledge base for the device failure status. If so, obtain the device failure mode and its code from the fault knowledge and proceed to step 2.5; otherwise, generate a new device failure status and output it to the user. Step 2.5: Determine if any signs of device failure mode have been detected. If yes, proceed to Step 2.6; otherwise, end the process. Step 2.6: Determine whether a fuzzy match for the device fault mode symptom is found in the knowledge base. If yes, retrieve the device fault mode description and its code from the fault mode library; otherwise, generate a new device fault mode and output it to the user. Step 2.7: Determine whether a description of the device failure mode symptoms has been extracted. If yes, proceed to step 2.8; otherwise, end the process. Step 2.8: Determine whether a device failure mode symptom is found in the knowledge base. If so, retrieve the device failure mode symptom description and its code from the failure mode library and determine the device failure mode corresponding to the symptom. If not, generate a new device failure mode symptom and output it to the user. Step 3: Determine if the component description has been extracted; if yes, proceed to step 3.1; if no, end the process. Step 3.1: Determine whether the knowledge base has a fuzzy match for the functional location containing the component description. If yes, obtain the component description and code, and proceed to Step 3.2; otherwise, provide feedback to the user. Step 3.2: Obtain the equipment code and description of the component by configuring the configuration library, then proceed to Step 3.3; Step 3.3: Determine whether a component failure mode description has been extracted. If yes, proceed to step 3.4; otherwise, proceed to step 3.

5. Step 3.4: Determine whether the knowledge base matches a component with the fault mode description. If yes, retrieve the component fault mode description and its code from the knowledge base and proceed to steps 3.4.1 and 3.4.2 respectively. If no, generate a new component fault mode and output it to the user. Step 3.4.1: Determine whether any component failure mode symptoms have been extracted. If yes, proceed to step 3.4.3; otherwise, end the process. Step 3.4.2: Determine whether the root cause of the component failure has been extracted. If yes, proceed to step 3.4.4; otherwise, end the process. Step 3.4.3: Determine whether a fuzzy match for a component failure mode symptom is found in the knowledge base. If yes, obtain the component failure mode symptom description and its code, and end the process; otherwise, generate a new component failure mode symptom and output it to the user. Step 3.4.4: Determine whether a fuzzy match has been found in the knowledge base for the root cause of the component. If so, obtain the description of the component failure mode symptoms and its code; otherwise, generate a new root cause of the component failure and output it to the user. Step 3.5: Determine whether any component failure mode symptoms have been extracted. If yes, proceed to step 3.5.1; otherwise, end the process. Step 3.5.1: Determine whether a component failure mode symptom is found in the knowledge base. If so, obtain the component failure mode symptom description and its code, and determine the component failure mode to which the component failure mode symptom belongs. If not, generate a new component failure mode symptom and output it to the user.

7. The automatic resume data annotation method according to claim 6, characterized in that, If there is no match, generating a new tag includes: If there is no match, the new label is generated using the large language model.

8. An automatic resume data annotation system, characterized in that, include: System building units, used to construct the tag system; The fault knowledge extraction unit is used to acquire history data and extract fault knowledge from the history data according to the tag system using a large language model to obtain the extracted fault knowledge. The tag matching unit is used to determine whether the extracted fault knowledge matches in the tag library. If it matches, the extracted fault knowledge is added to the fault mode. A tag generation unit is used to generate new tags when there is no matching fault knowledge in the tag library.

9. A storage medium, characterized in that, The storage medium stores a computer program adapted for loading by a processor to perform the steps of the automatic resume data annotation method as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, The method includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the steps of the automatic resume data annotation method as described in any one of claims 1 to 7 by calling the computer program stored in the memory.

Images