CN115757720A - Project information searching method, device, equipment and medium based on knowledge graph - Google Patents
Project information searching method, device, equipment and medium based on knowledge graph Download PDFInfo
- Publication number
- CN115757720A CN115757720A CN202211394299.4A CN202211394299A CN115757720A CN 115757720 A CN115757720 A CN 115757720A CN 202211394299 A CN202211394299 A CN 202211394299A CN 115757720 A CN115757720 A CN 115757720A
- Authority
- CN
- China
- Prior art keywords
- project
- question
- knowledge
- graph
- query
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The embodiment of the invention provides a project information searching method, a project information searching device, project information searching equipment and a storage medium based on a knowledge graph. The method comprises the following steps: determining a question type of the received project question; acquiring a query template associated with the question type; determining a query statement corresponding to the project question based on the query template; and searching answers of the project questions in a pre-constructed project knowledge graph based on the query statement. Compared with the traditional mode of searching through a relational database, the method and the system have the advantages that query sentences corresponding to project problems are constructed, answers of the problems are searched through the project knowledge graph, the project knowledge graph is stored in the graph database mode, and the graph database has higher searching efficiency and precision compared with general relational data.
Description
Technical Field
The embodiment of the invention relates to the technical field of computer data processing, in particular to a project information searching method, a project information searching device, project information searching equipment and a storage medium based on a knowledge graph.
Background
In project management, it is important to know project information in time. The project information may be information related to project management, such as project test information. Generally, a database connected to a website itself may be searched based on a keyword in a user question, and a large amount of searched item information related to the keyword may be fed back to the user through a web link. The traditional relational database is used in the searching mode, and the tables stored in the database need to be queried, so that when the structure of the data table is very complex and the number of fields is large, the relation among the data in the database is difficult to directly know, and the searching efficiency and the searching precision of the project information are undoubtedly reduced.
Disclosure of Invention
In order to solve the technical problems in the conventional technology, embodiments of the present invention provide a project information search method, apparatus, device and storage medium based on a knowledge graph.
In a first aspect, an embodiment of the present invention provides a method for searching item information based on a knowledge graph, including:
determining a question type of the received project question;
acquiring a query template associated with the question type;
determining a query statement corresponding to the project question based on the query template;
and searching answers of the project questions in a pre-constructed project knowledge graph based on the query statement.
In a second aspect, an embodiment of the present invention provides a knowledge-graph-based item information search apparatus, including:
the determining module is used for determining the problem type of the received project problem;
the acquisition module is used for acquiring the query template associated with the question type;
the determining module is further configured to determine a query statement corresponding to the item problem based on the query template;
and the processing module is used for searching answers of the project problems in a pre-constructed project knowledge graph based on the query statement.
In a third aspect, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of any one of the methods for searching knowledge-graph-based item information provided in the first aspect of the embodiment of the present invention when executing the program.
In a fourth aspect, the embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of any one of the methods for searching knowledge-graph-based item information provided in the first aspect of the embodiments of the present invention.
According to the technical scheme provided by the embodiment of the invention, the problem type of the received project problem is determined; acquiring a query template associated with the question type; determining a query statement corresponding to the project problem based on the query template; and searching answers of the project questions in a pre-constructed project knowledge graph based on the query statement. Compared with the traditional mode of searching through a relational database, the method and the system have the advantages that query sentences corresponding to project problems are constructed, answers of the problems are searched through the project knowledge graph, the project knowledge graph is stored in the graph database mode, and the graph database has higher searching efficiency and precision compared with general relational data.
Drawings
FIG. 1 is a schematic flow chart of a knowledge-graph-based project information search method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a query statement generating process according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating an entity extraction process according to an embodiment of the present invention;
FIG. 4 is a flow chart of a project knowledge graph building process provided by an embodiment of the invention;
FIG. 5 is a schematic structural diagram of a knowledge-graph-based item information search apparatus according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions in the embodiments of the present application are further described in detail by the following embodiments in combination with the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.
It should be noted that the execution subject of the method embodiments described below may be a knowledge-graph-based item information search apparatus, which may be implemented as part of or all of a computer device by software, hardware, or a combination of software and hardware. Optionally, the computer device may be a computer, a mobile phone, a tablet, or a portable device, and may also be an independent server or a server cluster, and the specific type of the computer device is not limited in this embodiment of the application.
Currently, item information is searched by a search engine of a keyword and a general relational database, and this method may cause reduction of efficiency and accuracy of searching item information when the keyword is ambiguous. Therefore, the technical scheme provided by the embodiment of the invention aims to solve the technical problems in the traditional mode, a project knowledge graph is constructed by processing multi-source data related to project management, the project knowledge graph is stored in a graph database, furthermore, a query statement corresponding to the project problem is formed according to the project problem input by a user, and the query statement is searched in the project knowledge graph stored in the graph database, so that the answer of the project problem is queried, and the search efficiency and precision of project information are greatly improved.
To facilitate understanding by those skilled in the art, concepts related to embodiments of the present invention will be described below.
Knowledge graph: the knowledge graph represents a connection mode between knowledge, the nodes and the relations form a graph to map and represent the knowledge known by people, and the mode of expressing the knowledge and the association between the knowledge in a 'graph' form can more naturally and efficiently represent real entities and relations.
Graph database: the graph database is a novel data storage mode, and the graph database does not refer to a database for storing pictures, but stores and queries data in a data structure of 'graph'. Data is stored in a graph database using graphs of nodes and edges, with the nodes in each graph representing entities and the directed edges connecting two nodes representing some relationship between the two nodes. Compared with the traditional relational database, the data model of the graph database is simpler, has better expressive force and higher computational efficiency.
Entity: specific words such as names of people, places, names of institutions and the like in the text are referred to, for example, "Wuhan" in "Wuhan is province of Hubei province" and "Hubei province" are entities.
Triplet: knowledge expressed in the form of entity-relation-entity, such as 'public accumulation fund system-responsible department-Wushu development department II', 'second generation payment transformation project of public accumulation fund system-demand time-2022 year, 1 month and 1 day', simply and directly shows the relation between entities.
Next, the technical solution provided by the embodiment of the present invention is elaborated in detail:
fig. 1 is a schematic flowchart of a method for searching item information based on a knowledge graph according to an embodiment of the present invention. As shown in fig. 1, the method may include:
s101, determining the problem type of the received project problem.
The user can input the project problem needing to be searched in the interactive page, and the computer equipment can analyze the project problem input by the user and understand the search intention of the user so as to determine the problem type of the project problem.
Illustratively, the project question "who the test manager for project A is" entered by the user, and by analyzing the project question, the type of question that results in the project question is a search for people. And if the project question is' which day the test of the project A requires ", the type of the question to obtain the project question is the search of the time after analysis.
Optionally, the S101 may include: constructing a target neural network based on the sample data set; and inputting the received project problems into a target neural network to obtain the problem types of the project problems. The sample data set comprises a sample question and a question type corresponding to the sample question. Alternatively, the target Neural network may be a Convolutional Neural Network (CNN) or a Deep Neural Network (DNN).
Specifically, a large number of sample problems are obtained, the problem types of the sample problems are labeled, then the labeled sample problems are used as input, the labeling result is used as a label, namely, the labeling result is expected to be output, the target neural network is trained through the preset loss function until the loss value of the preset loss function is stable and converged, and the trained target neural network is obtained. Further, after the project question input by the user is obtained, the project question is directly input into the target neural network, so that the question type of the project question can be determined.
The target neural network is trained through a large amount of sample data sets, the target neural network has self-adaptive learning capacity on nonlinear and irregular data, the search intention of a user is analyzed based on the target neural network, and the accuracy of an analysis result is greatly improved.
S102, obtaining a query template associated with the question type.
In specific implementation, a plurality of query templates can be preset, and different query templates correspond to different problem types. For example, the preset query templates may include a query template a, a query template B, a query template C, and the like, where the question type corresponding to the query template a is a search for people, the question type corresponding to the query template B is a search for time, and the question type corresponding to the query template C is a search for other objects.
In this way, after the question type of the project question input by the user is obtained, the query template associated with the question type can be determined from a plurality of preset query templates. For example, the query template may be an sql query statement to be filled, and the content to be filled may be obtained from a specific project question.
S103, determining a query statement corresponding to the project problem based on the query template.
After the query template corresponding to the project question is obtained, the project question may be processed to obtain filling content, and then the filling content is filled into a blank in the query template to generate a query statement corresponding to the project question.
And S104, searching answers of the project questions in a pre-constructed project knowledge graph based on the query statement.
The query statement can be identified by the project knowledge graph in the graph database, so that after the query statement is obtained, the graph database can be searched based on the query statement, namely, the query statement can be submitted to the project knowledge graph, and information with nodes in the query statement as the center is searched, so that the answer of the project question is obtained.
Further, the answers to the project questions may be presented in a preset manner. For example, the answer to the project question may be directly displayed in a text, visually displayed in a graphic manner, and output in a voice manner, which is not limited in this embodiment.
The project information searching method based on the knowledge graph provided by the embodiment of the invention determines the problem type of the received project problem; acquiring a query template associated with the question type; determining a query statement corresponding to the project problem based on the query template; and searching answers of the project questions in a pre-constructed project knowledge graph based on the query statement. Compared with the traditional mode of searching through a relational database, the method and the system have the advantages that query sentences corresponding to project problems are constructed, answers of the problems are searched through the project knowledge graph, the project knowledge graph is stored in the graph database mode, and the graph database has higher searching efficiency and precision compared with general relational data.
In an embodiment, optionally, as shown in fig. 2, the step S103 may specifically include:
s201, identifying entities in the project problem.
In embodiments of the present invention, entities include, but are not limited to: project name, testing department, responsible department, testing manager, testing workload, testing demand time and the like. In particular implementations, entities in the project problem may be identified through Named Entity Recognition (NER) techniques.
As an alternative implementation, as shown in fig. 3, identifying an entity in the project issue may include the steps of:
and S2011, acquiring a training sample and a test sample.
And S2012, marking the training samples, training the bidirectional long-term and short-term memory network model by taking the marked training samples as input and the marked results as labels, and obtaining a plurality of entity extraction models.
S2013, the plurality of entity extraction models are tested by the aid of the test samples, and the entity extraction model with the optimal test result is selected as the target entity extraction model.
S2014, identifying entities in the project problem by using the target entity extraction model.
Specifically, part of the corpus in the project management manual may be used as a training sample and a test sample. After the training samples and the test samples are obtained, the contents of the training samples and the test samples are labeled, the labeled training samples are used as input, and the labeled result is used as a label to train the bidirectional long-short term memory network model. The bidirectional long-short term memory network model can use the existing model. In this embodiment, a plurality of bidirectional long-short term memory network models may be trained simultaneously, and a plurality of entity extraction models may be obtained after the plurality of bidirectional long-short term memory network models are trained.
And after obtaining the plurality of entity extraction models, testing the plurality of entity extraction models by using the test sample. The procedure of the test may be: and taking the marked test samples as input, performing entity extraction on the test samples by using the entity extraction model, and selecting the entity extraction model with the optimal test result from the plurality of entity extraction models according to the extraction result of each entity extraction model to serve as a target entity extraction model for subsequent use.
And after the target entity extraction model is obtained, performing entity extraction on the project problem input by the user by using the target entity extraction model. As an example, the project question "who the test manager of project A is" is processed by the target entity extraction model, resulting in two entities, project A and test manager.
S202, filling a query template based on the entity to obtain a query statement of the project problem.
After the entities in the project problem are extracted, the extracted entities can be used for filling the blank in the query template, and therefore the filled result is used as a query statement of the project problem. Illustratively, the entity of item a is populated into the query template to form an sql query statement that can be identified by the graph database to search for the test manager corresponding to item a from the knowledge-graph of items stored in the graph database.
In the embodiment, the target entity extraction model can be constructed based on the training samples and the test samples, and then the target entity extraction model is used for identifying the entity in the project problem input by the user, so that the accuracy of entity identification is improved. Furthermore, a query statement is formed by using the query template associated with the project question and the identified entity, and then the query statement is used for searching answers from the project knowledge graph, so that the accuracy of the search result is ensured.
In one embodiment, a process for building a project knowledge graph is also provided. Optionally, before the foregoing S101, as shown in fig. 4, the method may further include:
s301, constructing a project extraction relation.
The project extraction relationship includes entities involved in the project information and relationships between the entities, that is, entity classes and relationships between the entities involved in the project information may be constructed in combination with actual requirements, for example, the entity classes involved in the constructed project information may include but are not limited to: project name, test manager, test demand time, test department, responsible department, test workload, and the like. After the plurality of entity classes are established, relationships between the entity classes may be established. As an example, a project-centered relationship is constructed as a responsible relationship between the project and the test manager, a time relationship between the project and the test requirement time, a production relationship between the project and the test workload, a responsible relationship between the project and the test department, a responsible relationship between the project and the responsible department, and the like.
S302, acquiring source data related to project management.
The source data may be structured data, semi-structured data, and unstructured data, among others. Structured data can generally be obtained directly from a relational database, and semi-structured data and unstructured data are mainly obtained from the internet or other knowledge sources. Aiming at the project information, the acquisition of source data can be carried out from listening websites, data records accumulated by each project group and other websites recording related information in the project management process.
S303, extracting knowledge of the source data according to the project extraction relation, and performing knowledge fusion on the extracted knowledge to obtain fusion data.
After the source data is obtained, the entities in each source data and the relationships between the entities may be extracted according to the above-constructed project extraction relationship, and the extracted entities are combined into one (entity, relationship, entity) triple. For example, the triple of the project and the test manager, the triple of the project and the responsible department, and the triple of the project and the test requirement time.
In consideration of the problems that source data from different sources have differences in data formats and data duplication also exists in the source data from different sources, knowledge fusion needs to be performed on extracted knowledge after knowledge extraction is performed on various source data. The essence of knowledge fusion here is to fuse together information about the same entity or concept from different knowledge sources, including unification of data formats and processing of data repetition. In the process of data fusion, in order to ensure the quality of data, data in a relational database can be taken as the main data, the data acquired by a website is used for supplementing the relational database, specifically, for the same entity data in two data sources, the entity data in the relational database is used in the process of fusion, and if the relational database does not contain part of entity data in the website, the part of entity data in the website is taken as the supplement to perfect the relational database.
And S304, constructing a project knowledge graph based on the fusion data.
After the fused data is obtained, the fused data (i.e., project information) can be imported into the graph database in the form of triples, thereby forming a project knowledge graph. Optionally, the project knowledge graph can be visualized, and entities and relationships thereof in the project knowledge graph are visualized through different graphs, such as a geometric graph, a battle graph, a ballistic graph, a theme river, a topographic map or a star-and-ball graph.
In the embodiment, the source data related to project management is acquired, knowledge extraction is performed on the source data according to the established project extraction relationship, the extracted knowledge is subjected to knowledge fusion to obtain fusion data, and a project knowledge graph is established based on the fusion data, so that the project knowledge graph can better express the relation among the data.
Fig. 5 is a schematic structural diagram of a knowledge-graph-based item information search apparatus according to an embodiment of the present invention. As shown in fig. 5, the apparatus may include: a determination module 401, an acquisition module 402 and a processing module 403.
Specifically, the determining module 401 is configured to determine a question type of the received project question;
the obtaining module 402 is configured to obtain a query template associated with the question type;
the determining module 401 is further configured to determine, based on the query template, a query statement corresponding to the item question;
the processing module 403 is configured to search for an answer to the project question in a pre-constructed project knowledge graph based on the query statement.
On the basis of the foregoing embodiment, optionally, the determining module 401 is specifically configured to identify an entity in the project issue; and filling the query template based on the entity to obtain a query statement of the project question.
On the basis of the foregoing embodiment, optionally, the determining module 401 is specifically configured to obtain a training sample and a testing sample; marking the training samples, taking the marked training samples as input, taking the marked result as a label, and training a bidirectional long-short term memory network model to obtain a plurality of entity extraction models; testing a plurality of entity extraction models by using the test sample, and selecting an entity extraction model with an optimal test result as a target entity extraction model; and identifying entities in the project problem by using the target entity extraction model.
On the basis of the foregoing embodiment, optionally, the processing module 403 is further configured to, before the determining the question type of the received project question, construct a project extraction relationship, where the project extraction relationship includes an entity related to the project information and a relationship between the entities; acquiring source data related to project management; performing knowledge extraction on the source data according to the project extraction relation, and performing knowledge fusion on the extracted knowledge to obtain fusion data; and constructing a project knowledge graph based on the fusion data.
On the basis of the foregoing embodiment, optionally, the determining module 401 is specifically configured to construct the target neural network based on a sample data set, where the sample data set includes a sample problem and a problem type corresponding to the sample problem; and inputting the received project problem into the target neural network to obtain the problem type of the project problem.
On the basis of the above embodiment, optionally, the target neural network is a CNN or a DNN.
On the basis of the above embodiment, optionally, the processing module 403 is further configured to display the answer according to a preset manner.
Fig. 6 is a schematic structural diagram of a computer apparatus according to an embodiment of the present invention, as shown in fig. 6, the apparatus includes a processor 510, a memory 520, an input device 530, and an output device 540; the number of the processors 510 in the device may be one or more, and one processor 510 is taken as an example in fig. 6; the processor 510, the memory 520, the input device 530 and the output device 540 of the apparatus may be connected by a bus or other means, and the connection by the bus is exemplified in fig. 5.
The memory 520 may be used as a computer-readable storage medium for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the method for searching for knowledge-graph-based item information in the embodiments of the present invention (e.g., the determining module 401, the obtaining module 402, and the processing module 403 in the apparatus for searching for knowledge-graph-based item information). The processor 510 executes various functional applications and data processing of the above-described apparatus by executing software programs, instructions, and modules stored in the memory 520, that is, implements the above-described knowledge-graph-based item information search method.
The memory 520 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 520 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 520 may further include memory located remotely from the processor 510, which may be connected to the device/terminal/server via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 530 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the above-described apparatus. The output device 540 may include a display device such as a display screen.
In one embodiment, there is also provided a storage medium containing computer-executable instructions which, when executed by a computer processor, perform a method of knowledge-graph based item information search, the method comprising:
determining a question type of the received project question;
acquiring a query template associated with the question type;
determining a query statement corresponding to the project question based on the query template;
and searching answers of the project questions in a pre-constructed project knowledge graph based on the query statement.
Of course, the storage medium containing the computer-executable instructions provided by the embodiments of the present invention is not limited to the method operations described above, and may also perform related operations in the method for searching for knowledge-graph-based item information provided by any embodiments of the present invention.
The knowledge-graph-based project information searching device, the knowledge-graph-based project information searching equipment and the storage medium which are provided by the embodiments can execute the knowledge-graph-based project information searching method provided by any embodiment of the invention, and have corresponding functional modules and beneficial effects for executing the method. Technical details that are not described in detail in the above embodiments may be referred to a method for searching for knowledge-graph-based item information provided in any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention or portions thereof contributing to the prior art may be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the above search apparatus, each included unit and module are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, the specific names of the functional units are only for the convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will appreciate that the present invention is not limited to the particular embodiments described herein, and that various obvious changes, rearrangements and substitutions will now be apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in some detail by the above embodiments, the invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the invention, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. A project information searching method based on knowledge graph is characterized by comprising the following steps:
determining a problem type of the received project problem;
acquiring a query template associated with the question type;
determining a query statement corresponding to the project question based on the query template;
and searching answers of the project questions in a pre-constructed project knowledge graph based on the query statement.
2. The method of claim 1, wherein determining the query statement for the project question based on the query template comprises:
identifying an entity in the project issue;
and filling the query template based on the entity to obtain a query statement of the project question.
3. The method of claim 2, wherein the identifying the entity in the project issue comprises:
acquiring a training sample and a test sample;
marking the training samples, taking the marked training samples as input, taking the marked result as a label, and training a bidirectional long-short term memory network model to obtain a plurality of entity extraction models;
testing a plurality of entity extraction models by using the test samples, and selecting the entity extraction model with the optimal test result as a target entity extraction model;
and identifying entities in the project problem by using the target entity extraction model.
4. The method of claim 1, prior to said determining a question type of the received project question, further comprising:
constructing a project extraction relation, wherein the project extraction relation comprises entities related to project information and relations among the entities;
acquiring source data related to project management;
performing knowledge extraction on the source data according to the project extraction relation, and performing knowledge fusion on the extracted knowledge to obtain fusion data;
and constructing a project knowledge graph based on the fusion data.
5. The method of claim 1, wherein determining the question type of the received project question comprises:
constructing a target neural network based on a sample data set, wherein the sample data set comprises a sample question and a question type corresponding to the sample question;
and inputting the received project problem into the target neural network to obtain the problem type of the project problem.
6. The method of claim 5, wherein the target neural network is a CNN or a DNN.
7. The method of any one of claims 1 to 6, further comprising:
and displaying the answer according to a preset mode.
8. A knowledge-graph-based item information search apparatus, comprising:
a determining module for determining a problem type of the received project problem;
the acquisition module is used for acquiring the query template associated with the question type;
the determining module is further configured to determine a query statement corresponding to the project question based on the query template;
and the processing module is used for searching answers of the project questions in a pre-constructed project knowledge graph based on the query statement.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of knowledge-graph based item information search according to any one of claims 1-7 when executing the program.
10. A computer-readable storage medium on which a computer program is stored, the program, when executed by a processor, implementing the knowledge-graph based project information search method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211394299.4A CN115757720A (en) | 2022-11-08 | 2022-11-08 | Project information searching method, device, equipment and medium based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211394299.4A CN115757720A (en) | 2022-11-08 | 2022-11-08 | Project information searching method, device, equipment and medium based on knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115757720A true CN115757720A (en) | 2023-03-07 |
Family
ID=85368581
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211394299.4A Pending CN115757720A (en) | 2022-11-08 | 2022-11-08 | Project information searching method, device, equipment and medium based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115757720A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116028597A (en) * | 2023-03-27 | 2023-04-28 | 南京燧坤智能科技有限公司 | Object retrieval method, device, nonvolatile storage medium and computer equipment |
-
2022
- 2022-11-08 CN CN202211394299.4A patent/CN115757720A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116028597A (en) * | 2023-03-27 | 2023-04-28 | 南京燧坤智能科技有限公司 | Object retrieval method, device, nonvolatile storage medium and computer equipment |
| CN116028597B (en) * | 2023-03-27 | 2023-07-21 | 南京燧坤智能科技有限公司 | Object retrieval method, device, nonvolatile storage medium and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109284363B (en) | Question answering method and device, electronic equipment and storage medium | |
| EP2947581B1 (en) | Interactive searching method and apparatus | |
| CN111125309A (en) | Natural language processing method and device, computing equipment and storage medium | |
| CN109947952B (en) | Retrieval method, device, equipment and storage medium based on English knowledge graph | |
| CN112115252B (en) | Intelligent auxiliary writing processing method and device, electronic equipment and storage medium | |
| CN111949800A (en) | Method and system for establishing knowledge graph of open source project | |
| CN110110090A (en) | Searching method, education search engine system and device | |
| CN113886567A (en) | Teaching method and system based on knowledge graph | |
| Dang et al. | MOOC-KG: A MOOC knowledge graph for cross-platform online learning resources | |
| CN114691831A (en) | Task-type intelligent automobile fault question-answering system based on knowledge graph | |
| CN111553138B (en) | Auxiliary writing method and device for standardizing content structure document | |
| CN110888989B (en) | Intelligent learning platform and construction method thereof | |
| CN112507076A (en) | Semantic analysis searching method and device and storage medium | |
| CN114911893A (en) | Method and system for automatically constructing knowledge base based on knowledge graph | |
| CN115757720A (en) | Project information searching method, device, equipment and medium based on knowledge graph | |
| CN113723853A (en) | Method and device for processing post competence demand data | |
| CN113610626A (en) | Bank credit risk identification knowledge graph construction method and device, computer equipment and computer readable storage medium | |
| CN116049376B (en) | Method, device and system for retrieving and replying information and creating knowledge | |
| CN112966076A (en) | Intelligent question and answer generating method and device, computer equipment and storage medium | |
| CN112069817A (en) | Student knowledge extraction and fusion method and device | |
| CN116595026A (en) | Information inquiry method | |
| CN115640403A (en) | Knowledge management and control method and device based on knowledge graph | |
| CN113157868B (en) | Method and device for matching answers to questions based on structured database | |
| CN115269862A (en) | Electric power question-answering and visualization system based on knowledge graph | |
| CN112015920A (en) | Intelligent auxiliary learning system based on knowledge graph and edge calculation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |