Large model-based campus work order transfer method, apparatus and device, and medium

Abstract

The invention discloses a large-model-based campus work order transfer method, device and equipment and a medium, relates to the field of work order processing, and is applied to a preset campus work order transfer system. Performing knowledge graph construction by using the obtained campus work order knowledge graph template, the historical campus work order information and the campus department responsibility information to obtain a target campus work order knowledge graph; performing vector conversion and historical campus work order retrieval on the to-be-processed campus work order through a preset deep learning large model and a vector database to obtain a retrieval result corresponding to the to-be-processed campus work order; and performing information analysis and department responsibility matching on the to-be-processed campus work order based on a preset deep learning large model, the retrieval result and the target campus work order knowledge graph, and completing work order transfer operation corresponding to the to-be-processed campus work order according to an obtained matching result. The work order processing quality is effectively improved, and the manual intervention cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of work order processing, and in particular to a campus work order transfer method, device, equipment and medium based on a large model. Background Art

[0002] With the continuous advancement of smart campus construction, campus service management is facing increasingly complex and diverse needs. The traditional work order transfer method mainly relies on manual judgment, which is not only inefficient but also prone to errors. Especially in large campus environments, with a large number of faculty and staff, detailed division of departmental responsibilities, and a variety of problem types, work order transfer becomes a tedious and arduous task.

[0003] However, most of the work order transfer systems currently used in campuses are still at the level of simple information entry and query, lacking intelligent matching and transfer functions. In addition, due to the lack of comprehensive understanding and in-depth analysis of campus service needs, these systems often find it difficult to accurately determine the processing department and responsible person of the work order, resulting in low work order processing efficiency and low user satisfaction. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a campus work order transfer method, device, equipment and medium based on a large model, which can effectively realize the intelligent analysis, accurate matching and efficient retrieval of campus work orders, thereby improving the quality of work order processing, reducing the cost of manual intervention, and further optimizing the user experience, and improving the efficiency and accuracy of campus service management. The specific scheme is as follows:

[0005] In a first aspect, the present application provides a campus work order transfer method based on a large model, which is applied to a preset campus work order transfer system, including:

[0006] Design a knowledge graph based on campus work order scenario information, and use the obtained campus work order knowledge graph template, historical campus work order information, and campus department responsibility information to construct a knowledge graph to obtain the target campus work order knowledge graph;

[0007] Perform vector conversion and historical campus work order retrieval on the campus work order to be processed by using a preset deep learning large model and a vector database to obtain retrieval results corresponding to the campus work order to be processed;

[0008] Based on the preset deep learning big model, the retrieval results and the target campus work order knowledge graph, the information of the pending campus work order is parsed and matched with department responsibilities, and the work order transfer operation corresponding to the pending campus work order is completed according to the obtained matching results.

[0009] Optionally, the knowledge graph design based on campus work order scenario information includes:

[0010] Obtain faculty and staff information, department information, work order problem type information, and work order attribute item information in the campus work order scenario to obtain campus work order scenario information;

[0011] Based on the campus work order scenario information, corresponding knowledge graph entity definition, entity relationship definition and entity attribute definition operations are performed to obtain a campus work order knowledge graph template.

[0012] Optionally, the corresponding knowledge graph entity definition, entity relationship definition, and entity attribute definition operations are performed based on the campus work order scenario information, including:

[0013] The faculty, staff, departments, work order problem types, and work orders are configured respectively through the campus work order scenario information to complete the corresponding knowledge graph entity definition operation;

[0014] The relationship between the faculty and the department, between the work order problem type and the department, between the work order and the work order problem type, and between the work order and the department is configured through the campus work order scenario information to complete the corresponding relationship definition operation;

[0015] The faculty and staff, the department, the work order problem type and the attributes of the work order are configured respectively through the campus work order scenario information to complete the corresponding attribute definition operation and obtain a campus work order knowledge graph template.

[0016] Optionally, the method of constructing a knowledge graph using the obtained campus work order knowledge graph template, historical campus work order information, and campus department responsibility information to obtain a target campus work order knowledge graph includes:

[0017] Collect current historical campus work order information, campus department responsibility information, historical campus emails, and student common questions;

[0018] Performing data cleaning, data deduplication, data segmentation, and stop word filtering on the historical campus work order information, the campus department responsibility information, the historical campus emails, and the student common problems, respectively, to complete corresponding data preprocessing operations and obtain preprocessed data;

[0019] Automatically identify and extract relevant information about entities and relationships between entities in the preprocessed data based on natural language processing technology to obtain extraction results;

[0020] A knowledge graph is constructed based on a preset knowledge graph construction tool, the extraction results and the obtained campus work order knowledge graph template to obtain a target campus work order knowledge graph.

[0021] Optionally, the method of performing vector conversion and historical campus work order retrieval on the campus work order to be processed by using a preset deep learning large model and a vector database to obtain a retrieval result corresponding to the campus work order to be processed includes:

[0022] Performing vector conversion on the campus work order to be processed by a preset deep learning large model to obtain first vector representation information corresponding to the campus work order to be processed;

[0023] Based on the first vector representation information, similarity calculation is performed on the historical campus work orders stored in the vector database to obtain a corresponding similarity score result;

[0024] The historical campus work orders are screened according to the similarity score results to obtain search results corresponding to the campus work orders to be processed.

[0025] Optionally, the information parsing and department responsibility matching of the to-be-processed campus work order based on the preset deep learning big model, the search results and the target campus work order knowledge graph includes:

[0026] Performing information analysis on the to-be-processed campus work order based on the preset deep learning big model and the search result to obtain an analysis result corresponding to the to-be-processed work order;

[0027] Based on the analysis results and the target campus work order knowledge graph, problem type matching and department responsibility matching operations are performed to obtain corresponding matching results, so that the matching results can be used to automatically transfer the pending campus work order to the target department, and the target responsible person in the target department can be notified of the work order processing.

[0028] Optionally, also include:

[0029] After completing the work order transfer, obtain the corresponding transfer score based on the work order feedback mechanism;

[0030] Sorting based on the transfer score to obtain a corresponding sorting result;

[0031] triggering a corresponding historical work order processing solution information acquisition operation according to the sorting result, and performing vector conversion on the obtained historical work order processing solution information to obtain corresponding second vector representation information;

[0032] The second vector representation information is stored in the vector database.

[0033] In a second aspect, the present application provides a campus work order transfer device based on a large model, which is applied to a preset campus work order transfer system, including:

[0034] The knowledge graph construction module is used to design the knowledge graph based on the campus work order scenario information, and to construct the knowledge graph using the obtained campus work order knowledge graph template, historical campus work order information, and campus department responsibility information to obtain the target campus work order knowledge graph;

[0035] A work order retrieval module is used to perform vector conversion and historical campus work order retrieval on the campus work order to be processed through a preset deep learning large model and a vector database to obtain a retrieval result corresponding to the campus work order to be processed;

[0036] The campus work order transfer module is used to perform information analysis and department responsibility matching on the pending campus work order based on the preset deep learning big model, the retrieval results and the target campus work order knowledge graph, and complete the work order transfer operation corresponding to the pending campus work order according to the matching results obtained.

[0037] In a third aspect, the present application provides an electronic device, including:

[0038] Memory, used to store computer programs;

[0039] The processor is used to execute the computer program to implement the steps of the aforementioned campus work order transfer method based on a large model.

[0040] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program, which, when executed by a processor, implements the steps of the aforementioned large-model-based campus work order dispatching method.

[0041] It can be seen that in this application, a knowledge graph is designed based on the campus work order scenario information by presetting the campus work order transfer system, and the knowledge graph is constructed using the obtained campus work order knowledge graph template and historical campus work order information and campus department responsibility information to obtain the target campus work order knowledge graph; the campus work order to be processed is vectorized and retrieved by presetting a large deep learning model and a vector database to obtain the retrieval results corresponding to the campus work order to be processed; based on the preset deep learning large model, the retrieval results and the target campus work order knowledge graph, the campus work order to be processed is parsed and matched with department responsibilities, and the work order transfer operation corresponding to the campus work order to be processed is completed according to the obtained matching results. That is, this application first designs a knowledge graph using the campus work order scenario information, and constructs a knowledge graph in combination with the historical campus work order information and campus department responsibility information to obtain the target campus work order knowledge graph. Then, the preset deep learning large model, vector database and the target campus work order knowledge graph are used to perform vector conversion and historical campus work order retrieval, information analysis and departmental responsibility matching on the to-be-processed campus work order, and the work order transfer operation corresponding to the to-be-processed campus work order is completed according to the obtained matching results. In this way, the application can effectively realize intelligent analysis, accurate matching and efficient retrieval of campus work orders, thereby improving the quality of work order processing, reducing the cost of manual intervention, and optimizing the user experience, and improving the efficiency and accuracy of campus service management. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0043] Figure 1 A flow chart of a campus work order transfer method based on a large model provided for this application;

[0044] Figure 2 A schematic diagram of the structure of a campus work order transfer device based on a large model provided in this application;

[0045] Figure 3 A structural diagram of an electronic device provided for this application. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] Most of the work order transfer systems currently used in campuses are still at the simple information entry and query level, lacking intelligent matching and transfer functions. In addition, due to the lack of comprehensive understanding and in-depth analysis of campus service needs, these systems often find it difficult to accurately determine the processing department and responsible person of the work order, resulting in low work order processing efficiency and low user satisfaction. To this end, this application provides a campus work order transfer solution based on a large model, which can effectively realize intelligent analysis, accurate matching and efficient retrieval of campus work orders, thereby improving the quality of work order processing and reducing the cost of manual intervention.

[0048] See also Figure 1 As shown, an embodiment of the present invention discloses a campus work order transfer method based on a large model, which is applied to a preset campus work order transfer system, including:

[0049] Step S11: Design a knowledge graph based on the campus work order scenario information, and use the obtained campus work order knowledge graph template, historical campus work order information, and campus department responsibility information to construct the knowledge graph to obtain the target campus work order knowledge graph.

[0050] Specifically, in this embodiment, it is necessary to first design a knowledge graph template for the campus work order scenario, and then fill in the data to construct the graph. Among them, regarding the template design, that is, the knowledge graph design based on the campus work order scenario information includes: obtaining the faculty and staff information, department information, work order problem type information and work order attribute item information in the campus work order scenario to obtain the campus work order scenario information; based on the campus work order scenario information, perform corresponding knowledge graph entity definition, entity relationship definition and entity attribute definition operations to obtain the campus work order knowledge graph template.

[0051] Further, regarding the specific implementation of each definition operation, in this embodiment, the corresponding knowledge graph entity definition, entity relationship definition and entity attribute definition operations are performed based on the campus work order scenario information, including: configuring the faculty, department, work order problem type and work order through the campus work order scenario information to complete the corresponding knowledge graph entity definition operation; configuring the relationship between the faculty and the department, between the work order problem type and the department, between the work order and the work order problem type, and between the work order and the department through the campus work order scenario information to complete the corresponding relationship definition operation; configuring the attributes of the faculty, department, work order problem type and work order through the campus work order scenario information to complete the corresponding attribute definition operation and obtain a campus work order knowledge graph template. The specific knowledge graph design steps are as follows:

[0052] 1) Entity definition.

[0053] ① Faculty and staff: including basic information such as name, work number, position, department, etc.

[0054] ② Department: including the names, responsibilities, contact information, etc. of the administrative departments, teaching departments, and service departments within the school, to facilitate the accurate transfer of work orders;

[0055] ③ Problem type (i.e. the work order problem type): Based on historical work order data, refine the problem classification, such as facility repair (specific to facility type), course consultation (distinguishing the nature of the course), activity application (activity type and scale), etc., to improve matching accuracy;

[0056] ④ Work order: including the work order number, submission time, submitter, problem description, processing status, etc.

[0057] 2) Relationship definition.

[0058] ① Faculty and Staff - Department: Clarify the department to which faculty and staff belong, and support role-based permission management and work order allocation;

[0059] ②Problem type-department: Establish a mapping relationship between problem type and responsible department to ensure that work orders can be accurately transferred to relevant departments;

[0060] ③ Work Order-Problem Type: Automatically classify according to the problem description to facilitate subsequent processing;

[0061] ④ Work Order-Department: Based on intelligent matching results, automatic transfer of work orders is realized.

[0062] 3) Attribute definition.

[0063] ① Faculty and staff attributes: such as name, work number, contact information, etc.;

[0064] ② Department attributes: such as department name, scope of responsibilities, contact information, etc.;

[0065] ③Problem type attributes: such as problem name, description, common solutions, etc.;

[0066] ④Work order attributes: such as submission time, processing status, processing results, etc.

[0067] In this embodiment, after completing the graph design, the obtained campus work order knowledge graph template is used to construct the graph, that is, the obtained campus work order knowledge graph template and historical campus work order information and campus department responsibility information are used to construct the knowledge graph to obtain the target campus work order knowledge graph, including: collecting the current historical campus work order information, campus department responsibility information, historical campus emails and student common problems; performing data cleaning, data deduplication, data segmentation and stop word filtering on the historical campus work order information, the campus department responsibility information, the historical campus emails and the student common problems, respectively, to complete the corresponding data preprocessing operations and obtain the preprocessed data; based on natural language processing technology, automatically identify and extract relevant information about the relationship between entities and entities in the preprocessed data to obtain extraction results; based on the preset knowledge graph construction tool, the extraction results and the obtained campus work order knowledge graph template, the knowledge graph is constructed to obtain the target campus work order knowledge graph. The specific knowledge graph construction steps are as follows:

[0068] 1) Data collection.

[0069] Collect structured and unstructured data such as historical emails, historical work orders, responsibilities of each department, and common student issues, and perform pre-processing such as cleaning, deduplication, word segmentation, and stop word filtering.

[0070] 2) Entity extraction.

[0071] ① Apply natural language processing (NLP) technology, such as named entity recognition (NER) and relationship extraction, to automatically identify and extract entities and relationships in texts to ensure the integrity and accuracy of the knowledge graph;

[0072] ②Introduce semi-automatic annotation tools to assist manual review and improve data quality.

[0073] 3) Knowledge graph construction.

[0074] ① Use the extracted data and knowledge graph construction tools (such as Neo4j) to build a knowledge graph to store entities, attributes and relationships to form a structured knowledge base;

[0075] ② Design reasonable indexing and query mechanisms to improve knowledge retrieval efficiency.

[0076] Step S12: Perform vector conversion and historical campus work order retrieval on the campus work order to be processed through a preset deep learning large model and a vector database to obtain retrieval results corresponding to the campus work order to be processed.

[0077] Specifically, in this embodiment, after determining the target campus work order knowledge graph, the campus work order can be transferred in combination with the large model. In the process of transfer, it is necessary to use the vector database for retrieval, that is, the campus work order to be processed is vectorized and retrieved by the preset deep learning large model and the vector database to obtain the retrieval result corresponding to the campus work order to be processed, including: vectorizing the campus work order to be processed by the preset deep learning large model to obtain the first vector representation information corresponding to the campus work order to be processed; similarity calculation is performed on the historical campus work orders stored in the vector database based on the first vector representation information to obtain the corresponding similarity score result; historical campus work orders are screened according to the similarity score result to obtain the retrieval result corresponding to the campus work order to be processed. That is to say, when a new work order (i.e., the campus work order to be processed) arrives, it is converted into a vector representation, and the most similar historical campus work order is retrieved in the vector database. According to the similarity score, the top few most similar historical campus work orders are selected for reference by the work order handler. In this way, by referring to the processing experience and solutions of similar historical campus work orders, the processing efficiency and quality of new work orders can be improved. Among them, the preset deep learning big model can be a deep learning big model. This embodiment can collect a large amount of campus work order data, perform annotation and preprocessing, and use it to train the deep learning big model. And through cross-validation, hyperparameter tuning and other technologies, the accuracy and generalization ability of the model can be improved.

[0078] It should be understood that, regarding the vector database, in this embodiment, the historical campus work order processing solutions and processing templates (after preprocessing and key information extraction) with higher scores are converted into vector representations according to the feedback mechanism and stored in the vector database. This process involves the use of NLP technology to convert text into vectors. That is, after completing the work order transfer, the corresponding transfer score is obtained based on the work order feedback mechanism; sorting is performed based on the transfer score to obtain the corresponding sorting result; the corresponding historical work order processing solution information acquisition operation is triggered according to the sorting result, and the obtained historical work order processing solution information is vectorized to obtain the corresponding second vector representation information; the second vector representation information is stored in the vector database.

[0079] Step S13: Based on the preset deep learning big model, the retrieval results and the target campus work order knowledge graph, the information of the pending campus work order is parsed and matched with the department responsibilities, and the work order transfer operation corresponding to the pending campus work order is completed according to the obtained matching results.

[0080] In this embodiment, the information analysis and department responsibility matching of the to-be-processed campus work order based on the preset deep learning big model, the search results and the target campus work order knowledge graph includes: information analysis of the to-be-processed campus work order based on the preset deep learning big model and the search results to obtain the analysis results corresponding to the to-be-processed work order; problem type matching and department responsibility matching operations are performed based on the analysis results and the target campus work order knowledge graph to obtain corresponding matching results, so as to automatically transfer the to-be-processed campus work order to the target department using the matching results, and notify the target responsible person in the target department to process the work order. That is, the preset deep learning big model combines the obtained search results to analyze the problem description in the to-be-processed campus work order submitted by the student to extract key information, such as problem type, urgency, etc. Then, combined with the relationship and attribute information in the target campus work order knowledge graph, the obtained analysis results are intelligently matched with the problem type and department responsibility to determine the most appropriate processing department and responsible person. Then, based on the matching results, the pending campus work order is automatically transferred to the responsible department, and a notification is sent on the system to the work order account and corporate WeChat of the person in charge of the relevant department, so as to realize the rapid forwarding and processing of the work order.

[0081] In addition, the preset campus work order transfer system in this embodiment adopts a microservice architecture to achieve modularity and scalability of the system, which is convenient for adding and optimizing subsequent functions. In addition, this embodiment uses database technology to store the target campus work order knowledge graph and the campus work order knowledge graph template, and combines data preprocessing technology (such as word segmentation, stop word removal, etc.) to process campus work order descriptions to provide high-quality data for model training and reasoning. It also monitors the processing status of campus work orders in real time, and by setting the maximum campus work order processing time, promptly reminds staff to process campus work orders that are about to time out and introduces an assessment mechanism.

[0082] In summary, in this embodiment, a vector database (such as Faiss, Milvus, etc.) is used to store and manage the vector representation of historical work orders to ensure efficient retrieval. A user feedback mechanism is established to collect user satisfaction evaluations on the work order processing results for optimizing the knowledge graph and model performance. At the same time, according to changes in campus service needs and organizational structure, the vector database, knowledge graph and large model are regularly updated to maintain the advancement and practicality of the system. The beneficial effects of the technical solution described in this embodiment are mainly reflected in the following aspects:

[0083] 1) Improve the efficiency of campus work order processing: Through automated identification and intelligent matching, the system can quickly transfer campus work orders to the most appropriate processing department, reducing the time for manual judgment and manual operation, and significantly improving the response speed and overall efficiency of campus work order processing;

[0084] 2) Improve the accuracy of campus work order processing: With the help of detailed knowledge graphs, the precise parsing capabilities of deep learning large models, and the reference of similar historical campus work orders provided by the vector database, the system can more accurately determine the problem type and responsible department of campus work orders, effectively reducing the transfer error rate, and providing more intelligent processing suggestions, further improving the accuracy of campus work order processing and user satisfaction;

[0085] 3) Enhanced user experience: The system provides a user-friendly interface and rich query functions, allowing users to easily submit work orders and understand the processing progress in real time, enhancing user participation and satisfaction;

[0086] 4) Reduce operating costs: By reducing manual intervention and improving processing efficiency, the system helps to reduce the operating costs of campus service management and achieve optimal allocation and efficient utilization of resources.

[0087] It can be seen that in the embodiment of the present application, a knowledge graph is designed based on the campus work order scenario information by presetting the campus work order transfer system, and the knowledge graph is constructed using the obtained campus work order knowledge graph template and historical campus work order information and campus department responsibility information to obtain the target campus work order knowledge graph; the campus work order to be processed is vectorized and retrieved by presetting the deep learning big model and the vector database to obtain the retrieval results corresponding to the campus work order to be processed; the campus work order to be processed is parsed based on the preset deep learning big model, the retrieval results and the target campus work order knowledge graph, and the work order transfer operation corresponding to the campus work order to be processed is completed according to the obtained matching results. That is, the present application first designs the knowledge graph using the campus work order scenario information, and constructs the knowledge graph in combination with the historical campus work order information and campus department responsibility information to obtain the target campus work order knowledge graph. Then, the preset deep learning large model, vector database and the target campus work order knowledge graph are used to perform vector conversion and historical campus work order retrieval, information analysis and departmental responsibility matching on the to-be-processed campus work order, and the work order transfer operation corresponding to the to-be-processed campus work order is completed according to the obtained matching results. In this way, the application can effectively realize intelligent analysis, accurate matching and efficient retrieval of campus work orders, thereby improving the quality of work order processing, reducing the cost of manual intervention, and optimizing the user experience, and improving the efficiency and accuracy of campus service management.

[0088] See also Figure 2 As shown, the embodiment of the present application also discloses a campus work order transfer device based on a large model, which is applied to a preset campus work order transfer system, including:

[0089] The knowledge graph construction module 11 is used to design a knowledge graph based on the campus work order scenario information, and to construct a knowledge graph using the obtained campus work order knowledge graph template, historical campus work order information, and campus department responsibility information to obtain a target campus work order knowledge graph;

[0090] The work order retrieval module 12 is used to perform vector conversion and historical campus work order retrieval on the campus work order to be processed through a preset deep learning large model and a vector database to obtain a retrieval result corresponding to the campus work order to be processed;

[0091] The campus work order transfer module 13 is used to perform information analysis and department responsibility matching on the pending campus work order based on the preset deep learning big model, the retrieval results and the target campus work order knowledge graph, and complete the work order transfer operation corresponding to the pending campus work order according to the matching results obtained.

[0092] Among them, for more specific working processes of the above-mentioned modules, please refer to the corresponding contents disclosed in the aforementioned embodiments, which will not be repeated here.

[0093] It can be seen that this application first designs a knowledge graph using the campus work order scenario information, and constructs a knowledge graph in combination with historical campus work order information and campus department responsibility information to obtain a target campus work order knowledge graph. Then, the preset deep learning large model, vector database, and the target campus work order knowledge graph are used to perform vector conversion and historical campus work order retrieval, information analysis, and department responsibility matching on the to-be-processed campus work order, and the work order transfer operation corresponding to the to-be-processed campus work order is completed based on the matching results obtained. In this way, this application can effectively realize intelligent analysis, precise matching, and efficient retrieval of campus work orders, thereby improving the quality of work order processing, reducing the cost of manual intervention, and optimizing the user experience, and improving the efficiency and accuracy of campus service management.

[0094] In some specific embodiments, the knowledge graph construction module 11 can be specifically used to: obtain faculty and staff information, department information, work order problem type information, and work order attribute item information in the campus work order scenario to obtain campus work order scenario information; perform corresponding knowledge graph entity definition, entity relationship definition, and entity attribute definition operations based on the campus work order scenario information to obtain a campus work order knowledge graph template.

[0095] In some specific embodiments, the knowledge graph construction module 11 can be specifically used to: configure the faculty, department, work order problem type and work order through the campus work order scenario information to complete the corresponding knowledge graph entity definition operation; configure the relationship between the faculty and the department, between the work order problem type and the department, between the work order and the work order problem type, and between the work order and the department through the campus work order scenario information to complete the corresponding relationship definition operation; configure the attributes of the faculty, department, work order problem type and work order through the campus work order scenario information to complete the corresponding attribute definition operation and obtain a campus work order knowledge graph template.

[0096] In some specific embodiments, the knowledge graph construction module 11 can be specifically used to: collect current historical campus work order information, campus department responsibility information, historical campus emails and student common problems; perform data cleaning, data deduplication, data segmentation and stop word filtering on the historical campus work order information, the campus department responsibility information, the historical campus emails and the student common problems, so as to complete the corresponding data preprocessing operations and obtain preprocessed data; automatically identify and extract relevant information on the relationship between entities and entities in the preprocessed data based on natural language processing technology to obtain extraction results; construct a knowledge graph based on a preset knowledge graph construction tool, the extraction results and the obtained campus work order knowledge graph template to obtain a target campus work order knowledge graph.

[0097] In some specific embodiments, the work order retrieval module 12 can be specifically used to: perform vector conversion on the campus work order to be processed through a preset deep learning large model to obtain first vector representation information corresponding to the campus work order to be processed; perform similarity calculation on the historical campus work orders stored in the vector database based on the first vector representation information to obtain corresponding similarity score results; and screen historical campus work orders according to the similarity score results to obtain retrieval results corresponding to the campus work order to be processed.

[0098] In some specific embodiments, the campus work order transfer module 13 can be specifically used to: perform information analysis on the pending campus work order based on the preset deep learning big model and the retrieval results to obtain analysis results corresponding to the pending work order; perform problem type matching and department responsibility matching operations based on the analysis results and the target campus work order knowledge graph to obtain corresponding matching results, so as to automatically transfer the pending campus work order to the target department using the matching results, and notify the target responsible person in the target department of work order processing.

[0099] In some specific embodiments, the campus work order transfer device based on the large model can also be used to: after completing the work order transfer, obtain the corresponding transfer score based on the work order feedback mechanism; sort based on the transfer score to obtain the corresponding sorting result; trigger the corresponding historical work order processing solution information acquisition operation according to the sorting result, and perform vector conversion on the obtained historical work order processing solution information to obtain the corresponding second vector representation information; store the second vector representation information in the vector database.

[0100] Furthermore, the present application also discloses an electronic device. Figure 3 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0101] Figure 3 A schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the campus work order transfer method based on a large model disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0102] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0103] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0104] The operating system 221 is used to manage and control the hardware devices and computer program 222 on the electronic device 20, which can be Windows Server, Netware, Unix, Linux, etc. In addition to the computer program that can be used to complete the campus work order transfer method based on the large model executed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks.

[0105] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the aforementioned large-model-based campus work order transfer method disclosed above is implemented. The specific steps of the method can refer to the corresponding contents disclosed in the aforementioned embodiments, and will not be repeated here.

[0106] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0107] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0108] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0109] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0110] The technical solution provided by the present application is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technicians in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A campus work order transfer method based on a large model, characterized in that: Applied to the preset campus work order transfer system, including: Design a knowledge graph based on campus work order scenario information, and use the obtained campus work order knowledge graph template, historical campus work order information, and campus department responsibility information to construct a knowledge graph to obtain the target campus work order knowledge graph; Perform vector conversion and historical campus work order retrieval on the campus work order to be processed by using a preset deep learning large model and a vector database to obtain retrieval results corresponding to the campus work order to be processed; Based on the preset deep learning big model, the retrieval results and the target campus work order knowledge graph, the information of the pending campus work order is parsed and matched with department responsibilities, and the work order transfer operation corresponding to the pending campus work order is completed according to the obtained matching results.

2. The campus work order transfer method based on a large model according to claim 1 is characterized in that: The knowledge graph design based on campus work order scenario information includes: Obtain faculty and staff information, department information, work order problem type information, and work order attribute item information in the campus work order scenario to obtain campus work order scenario information; Based on the campus work order scenario information, corresponding knowledge graph entity definition, entity relationship definition and entity attribute definition operations are performed to obtain a campus work order knowledge graph template.

3. The campus work order transfer method based on a large model according to claim 2 is characterized in that: The corresponding knowledge graph entity definition, entity relationship definition and entity attribute definition operations based on the campus work order scenario information include: The faculty, staff, departments, work order problem types, and work orders are configured respectively through the campus work order scenario information to complete the corresponding knowledge graph entity definition operation; The relationship between the faculty and the department, between the work order problem type and the department, between the work order and the work order problem type, and between the work order and the department is configured through the campus work order scenario information to complete the corresponding relationship definition operation; The faculty and staff, the department, the work order problem type and the attributes of the work order are configured respectively through the campus work order scenario information to complete the corresponding attribute definition operation and obtain a campus work order knowledge graph template.

4. The campus work order transfer method based on a large model according to claim 1 is characterized in that: The knowledge graph is constructed by using the obtained campus work order knowledge graph template, historical campus work order information, and campus department responsibility information to obtain the target campus work order knowledge graph, including: Collect current historical campus work order information, campus department responsibility information, historical campus emails, and student common questions; Performing data cleaning, data deduplication, data segmentation, and stop word filtering on the historical campus work order information, the campus department responsibility information, the historical campus emails, and the student common problems, respectively, to complete corresponding data preprocessing operations and obtain preprocessed data; Automatically identify and extract relevant information about entities and relationships between entities in the preprocessed data based on natural language processing technology to obtain extraction results; A knowledge graph is constructed based on a preset knowledge graph construction tool, the extraction results and the obtained campus work order knowledge graph template to obtain a target campus work order knowledge graph.

5. The campus work order transfer method based on a large model according to claim 1 is characterized in that: The method of performing vector conversion and historical campus work order retrieval on the campus work order to be processed by using the preset deep learning large model and the vector database to obtain the retrieval result corresponding to the campus work order to be processed includes: Performing vector conversion on the campus work order to be processed by a preset deep learning large model to obtain first vector representation information corresponding to the campus work order to be processed; Based on the first vector representation information, similarity calculation is performed on the historical campus work orders stored in the vector database to obtain a corresponding similarity score result; The historical campus work orders are screened according to the similarity score results to obtain search results corresponding to the campus work orders to be processed.

6. The campus work order transfer method based on a large model according to claim 1 is characterized in that: The information parsing and department responsibility matching of the to-be-processed campus work order based on the preset deep learning big model, the search results and the target campus work order knowledge graph includes: Performing information analysis on the to-be-processed campus work order based on the preset deep learning big model and the search result to obtain an analysis result corresponding to the to-be-processed work order; Based on the analysis results and the target campus work order knowledge graph, problem type matching and department responsibility matching operations are performed to obtain corresponding matching results, so that the matching results can be used to automatically transfer the pending campus work order to the target department, and the target responsible person in the target department can be notified of the work order processing.

7. The campus work order transfer method based on a large model according to any one of claims 1 to 6, characterized in that: Also includes: After completing the work order transfer, obtain the corresponding transfer score based on the work order feedback mechanism; Sorting based on the transfer score to obtain a corresponding sorting result; triggering a corresponding historical work order processing solution information acquisition operation according to the sorting result, and performing vector conversion on the obtained historical work order processing solution information to obtain corresponding second vector representation information; The second vector representation information is stored in the vector database.

8. A campus work order transfer device based on a large model, characterized in that: Applied to the preset campus work order transfer system, including: The knowledge graph construction module is used to design the knowledge graph based on the campus work order scenario information, and to construct the knowledge graph using the obtained campus work order knowledge graph template, historical campus work order information, and campus department responsibility information to obtain the target campus work order knowledge graph; A work order retrieval module is used to perform vector conversion and historical campus work order retrieval on the campus work order to be processed through a preset deep learning large model and a vector database to obtain a retrieval result corresponding to the campus work order to be processed; The campus work order transfer module is used to perform information analysis and department responsibility matching on the pending campus work order based on the preset deep learning big model, the retrieval results and the target campus work order knowledge graph, and complete the work order transfer operation corresponding to the pending campus work order according to the matching results obtained.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, used to execute the computer program to implement the campus work order dispatching method based on a large model as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, implements the campus work order dispatching method based on a large model as described in any one of claims 1 to 7.

Images