CN117435700A - Data searching method, device, computer equipment and storage medium - Google Patents
Data searching method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117435700A CN117435700A CN202311250826.9A CN202311250826A CN117435700A CN 117435700 A CN117435700 A CN 117435700A CN 202311250826 A CN202311250826 A CN 202311250826A CN 117435700 A CN117435700 A CN 117435700A
- Authority
- CN
- China
- Prior art keywords
- search
- data
- target
- current
- matching data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000004590 computer program Methods 0.000 claims description 40
- 238000012549 training Methods 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 12
- 238000005457 optimization Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000007499 fusion processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/338—Presentation of query results
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to a data searching method, a data searching device, computer equipment and a storage medium. The method comprises the following steps: determining search keywords of the current search problem according to the current search problem input by the user; searching matching data corresponding to the search keywords from candidate data of a knowledge base through a target search model, and integrating the matching data according to semantic information of the matching data to obtain target search results corresponding to the current search problem; and outputting target search results. Compared with the mode of outputting all the matching data corresponding to the search problem in the prior art, the method has the advantages that a user does not need to further search for required data from all the matching data, so that the output target search result is more accurate and reasonable, and the convenience of user search is further improved.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a data searching method, apparatus, computer device, and storage medium.
Background
With the development of computer technology, an online search tool is presented, which can help a user search out data required by the user from massive data and display the data required by the user to the user. Although the data required by the user can be searched in the mode, when the data quantity is large, the user still cannot accurately acquire the data required by the user when facing more searched data, and therefore the problem of low searching precision exists.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a data search method, apparatus, computer device, and storage medium capable of improving search accuracy.
In a first aspect, the present application provides a data searching method. The method comprises the following steps:
determining search keywords of the current search problem according to the current search problem input by the user;
searching matching data corresponding to the search keywords from candidate data of a knowledge base through a target search model, and integrating the matching data according to semantic information of the matching data to obtain target search results corresponding to the current search problem;
and outputting target search results.
In one embodiment, according to semantic information of the matching data, integrating the matching data to obtain a target search result corresponding to the current search problem, including:
performing natural language analysis processing on the matching data to obtain semantic information of the matching data;
screening the matched data according to semantic information and search keywords of the matched data, and extracting key sentences from the screened matched data;
and integrating the key sentences to obtain target search results corresponding to the current search problem.
In one embodiment, integrating the key sentences to obtain a target search result corresponding to the current search problem includes:
integrating the key sentences to obtain initial search results corresponding to the current search problem;
and formatting the initial search result according to a result display template configured by a user to obtain a target search result corresponding to the current search problem.
In one embodiment, the method further comprises:
determining a problem theme corresponding to the current search problem according to the search keyword;
and searching out a target search model from the candidate search models according to the problem theme.
In one embodiment, a method for training a candidate search model includes:
obtaining general sample data and field sample data corresponding to each candidate search model, wherein the general sample data and the field sample data both contain sample search problems and sample search results corresponding to the sample search problems;
preprocessing the universal sample data and the sample data in each field;
training each candidate search model based on the preprocessed general sample data, and optimizing the corresponding candidate search model after training based on the sample data of each field to obtain each candidate search model after optimization.
In one embodiment, the method further comprises:
acquiring feedback information of a user based on a target search result;
and adjusting the target search result according to the fed back information, and storing the current search problem and the adjusted target search result into a historical search set of a target search model, wherein the historical search set of the target search model is used for updating the target search model.
In a second aspect, the present application further provides a data searching apparatus. The device comprises:
the key determining module is used for determining search keywords of the current search problem according to the current search problem input by the user;
the result determining module is used for searching matching data corresponding to the search keywords from candidate data of the knowledge base through the target search model, and integrating the matching data according to semantic information of the matching data to obtain target search results corresponding to the current search problem;
and the result output module is used for outputting target search results.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
determining search keywords of the current search problem according to the current search problem input by the user;
searching matching data corresponding to the search keywords from candidate data of a knowledge base through a target search model, and integrating the matching data according to semantic information of the matching data to obtain target search results corresponding to the current search problem;
and outputting target search results.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
determining search keywords of the current search problem according to the current search problem input by the user;
searching matching data corresponding to the search keywords from candidate data of a knowledge base through a target search model, and integrating the matching data according to semantic information of the matching data to obtain target search results corresponding to the current search problem;
and outputting target search results.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:
determining search keywords of the current search problem according to the current search problem input by the user;
searching matching data corresponding to the search keywords from candidate data of a knowledge base through a target search model, and integrating the matching data according to semantic information of the matching data to obtain target search results corresponding to the current search problem;
and outputting target search results.
According to the data searching method, the data searching device, the computer equipment and the storage medium, based on the fact that the user inputs the search keywords corresponding to the current search problem, the matching data corresponding to the search keywords are searched out through the target search model, and the matching data are integrated to obtain the final target search result. Compared with the mode of outputting all the matching data corresponding to the search problem in the prior art, the method has the advantages that a user does not need to further search for required data from all the matching data, so that the output target search result is more accurate and reasonable, and the convenience of user search is further improved.
Drawings
Fig. 1 is an application environment diagram of a data searching method provided in this embodiment;
fig. 2 is a flow chart of a first data searching method according to the present embodiment;
fig. 3 is a schematic flow chart of obtaining a target search result according to the present embodiment;
fig. 4 is a schematic flow chart of a training candidate search model according to the present embodiment;
fig. 5 is a flowchart of a second data searching method according to the present embodiment;
fig. 6 is a block diagram of a first data searching apparatus according to the present embodiment;
fig. 7 is a block diagram of a first data searching apparatus according to the present embodiment;
fig. 8 is a block diagram of a first data searching apparatus according to the present embodiment;
fig. 9 is a block diagram of a first data search device according to the present embodiment;
fig. 10 is a block diagram of a first data search device according to the present embodiment;
fig. 11 is an internal structure diagram of a computer device according to the present embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The data searching method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in FIG. 1. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is for storing target search result data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a data search method.
In one embodiment, as shown in fig. 2, a data searching method is provided, and the method is applied to the computer device in fig. 1 for illustration, and includes the following steps:
s201, determining search keywords of the current search question according to the current search question input by the user.
Among them, the current search question may be a question for retrieving data required by the user. The search keywords may be words that characterize key information in the current search question, such as financial, loan, etc.
Optionally, the current search question input by the user is parsed, and the vocabulary identical to the preset keyword is searched from the current search question and used as the search keyword of the current search question.
S202, searching matching data corresponding to the search keywords from candidate data of a knowledge base through a target search model, and integrating the matching data according to semantic information of the matching data to obtain target search results corresponding to the current search problem.
The target search model may be a model for searching a current search problem input by a user and integrating the searched matching data. The knowledge base may be a database for storing candidate data. The candidate data may be data for solving various types of search problems, such as a technical document, and the like. The matching data may be candidate data having the highest degree of matching with the search keyword of the current search question. The target search result may be a search result for solving the current search problem, optionally integrated based on at least one matching data.
Optionally, selecting a target search model according to the search keyword, inputting the current search problem into the target search model, searching candidate data with the matching degree exceeding a preset matching threshold value with the current search problem from a knowledge base by the target search model to serve as matching data, analyzing the matching data to obtain semantic information of each matching data, and carrying out fusion processing on each semantic information to generate a target search result corresponding to the current search problem.
It should be noted that, in this embodiment, a plurality of search models for different topics may be set to search for a search problem, so as to improve accuracy of a target search result, so that when there are a plurality of search models, in this embodiment, a problem topic corresponding to a current search problem may also be determined according to a search keyword; and searching out a target search model from the candidate search models according to the problem theme. The problem topic may be a topic in the technical field to which the search keyword belongs, such as a financial topic. Optionally, determining, according to the search keyword, a preset technical field to which the search keyword belongs, using the technical field as a problem topic corresponding to the current search problem, and according to the problem topic, searching out candidate search models identical to the problem topic from model topics of the candidate search models as target search models.
S203, outputting target search results.
Optionally, after obtaining the target search result, the target search result may be output to the user through a terminal or interface (e.g., application Programming Interface, API) manner.
According to the data searching method, based on the fact that the user inputs the search keywords corresponding to the current search problem, the matching data corresponding to the search keywords are searched out through the target search model, and the matching data are integrated to obtain the final target search result. Compared with the mode of outputting all the matching data corresponding to the search problem in the prior art, the method has the advantages that a user does not need to further search for required data from all the matching data, so that the output target search result is more accurate and reasonable, and the convenience of user search is further improved.
FIG. 3 is a flow diagram of obtaining target search results in one embodiment. On the basis of the above embodiment, in order to accurately obtain the target search result, this embodiment provides an alternative way of obtaining the target search result, including the following steps:
s301, performing natural language analysis processing on the matching data to obtain semantic information of the matching data.
Optionally, natural language analysis processing is performed on each matching data, so as to analyze the actual meaning of the data content in each matching data, and the actual meaning is used as semantic information of the matching data.
S302, screening the matched data according to semantic information and search keywords of the matched data, and extracting key sentences from the screened matched data.
Optionally, the semantic information of the search keywords and each matching data is matched, the search keywords and the semantic information with higher matching degree are further screened out, and sentences containing the search keywords are extracted from the matching data corresponding to the semantic information to serve as key sentences.
S303, integrating the key sentences to obtain target search results corresponding to the current search problem.
Optionally, integrating the key sentences to obtain initial search results corresponding to the current search problem; and formatting the initial search result according to a result display template configured by a user to obtain a target search result corresponding to the current search problem.
Specifically, after fusion processing is performed on each key sentence, an initial search result corresponding to the current search problem is obtained, meanwhile, a result display template configured by a user is obtained, formatting processing is performed on the initial search result based on the result display template, and the initial search result is displayed according to the style of the result display template, so that a target search result corresponding to the current search problem is obtained.
According to the method for obtaining the target search result, the semantic information of the matching data is obtained through natural language analysis processing of the matching data, the key sentences are extracted from the matching data according to the semantic information of the matching data and the search keywords, and finally the key sentences are integrated to obtain the target search result corresponding to the current search problem. The method can integrate the matching data with higher matching degree with the current search problem to obtain a more reasonable and accurate target search result.
FIG. 4 is a flow diagram of training candidate search models in one embodiment. In order to ensure the accuracy of determining the target search result through the target search model, the present embodiment may set candidate search models of different topics, so how to train the candidate search models is important, and the present embodiment provides an alternative way of training the candidate search models, which includes the following steps:
s401, acquiring general sample data and field sample data corresponding to each candidate search model.
The universal sample data may be data for training candidate search models, including data information of various fields. The domain sample data may be data containing data information of only a single domain. The general sample data and the field sample data both comprise sample search problems and sample search results corresponding to the sample search problems. Alternatively, the sample data may include technical documents and question and answer text.
Optionally, general sample data and field sample data corresponding to each candidate search model may be obtained through a network or a user uploading manner.
S402, preprocessing the general sample data and the sample data in each field.
Optionally, the mode of preprocessing the universal sample data and the sample data in each field may be to remove the invalid data from the universal sample data and the sample data in each field according to a preset invalid information template; the method can be that repeated data in the general sample data are removed, and repeated data in the sample data in each field are removed; the universal sample data and the sample data in each field can be formatted (e.g. normalized); the method can also preprocess the general sample data and the sample data in all fields in the modes of removing invalid information, removing repeated data, formatting and the like.
S403, training each candidate search model based on the preprocessed general sample data, and optimizing the corresponding candidate search model after training based on the sample data of each field to obtain each candidate search model after optimization.
Optionally, the preprocessed general sample data is input into each candidate search model for training, the training candidate search model is used as a general search model, and each general search model is trained by using the preprocessed field sample data, namely the field sample data of one field is used for training one general search model, so that the candidate search model after training based on the field sample data is obtained.
According to the method for training the candidate search model, the universal sample data and the sample data in each field are obtained and preprocessed, after the candidate search model is trained based on the universal sample data, the candidate search model is trained based on the field sample data, and each candidate search model after final optimization is obtained.
It should be noted that, in order to ensure accuracy of determining the target search result by the target search model, the embodiment may further obtain feedback information of the user based on the target search result; and adjusting the target search result according to the fed back information, and storing the current search problem and the adjusted target search result into a historical search set of the target search model. The historical search set of the target search model is used for updating the target search model. Optionally, after determining the target search result, feedback information fed back by the user based on the target search result may be obtained, the target search result may be adjusted according to the feedback information, the adjusted target search result may be obtained, and the adjusted target search result and the current search question may be stored in the historical search set of the target search model. This has the advantage that data support can be provided for subsequent updates to the target search model by the historical corpus.
In one embodiment, this embodiment provides an alternative way of searching data, and the method is applied to a server for illustration. As shown in fig. 5, the method comprises the steps of:
s501, determining search keywords of a current search question according to the current search question input by a user.
S502, determining a problem theme corresponding to the current search problem according to the search keyword.
S503, searching out a target search model from the candidate search models according to the problem theme.
S504, searching matching data corresponding to the search keywords from candidate data of the knowledge base through a target search model, and carrying out natural language analysis processing on the matching data to obtain semantic information of the matching data.
S505, screening the matched data according to semantic information and search keywords of the matched data, and extracting key sentences from the screened matched data.
S506, integrating the key sentences to obtain initial search results corresponding to the current search problem.
S507, formatting the initial search results according to the result display template configured by the user to obtain target search results corresponding to the current search problem.
S508, outputting the target search result.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a data searching device for realizing the above related data searching method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in one or more embodiments of the data searching device provided below may refer to the limitation of the data searching method hereinabove, and will not be repeated herein.
In one embodiment, as shown in fig. 6, there is provided a data search apparatus 1 including: a key determination module 10, a result determination module 11, and a result output module 12, wherein:
the key determining module 10 is configured to determine a search keyword of a current search question according to the current search question input by the user;
the result determining module 11 is configured to search matching data corresponding to the search keyword from candidate data in the knowledge base through a target search model, and integrate the matching data according to semantic information of the matching data to obtain a target search result corresponding to the current search problem;
and a result output module 12 for outputting the target search result.
In one embodiment, as shown in fig. 7, the result determining module 11 in fig. 6 includes:
the semantic determining unit 110 is configured to perform natural language parsing on the matching data to obtain semantic information of the matching data;
a sentence determining unit 111, configured to screen the matching data according to semantic information and search keywords of the matching data, and extract key sentences from the screened matching data;
the result determining unit 112 is configured to integrate the key sentences to obtain a target search result corresponding to the current search problem.
In one embodiment, the result determination unit 112 in fig. 7 includes:
the result determining subunit is used for integrating the key sentences to obtain initial search results corresponding to the current search problems;
and the result format subunit is used for formatting the initial search result according to the result display template configured by the user to obtain a target search result corresponding to the current search problem.
In one embodiment, as shown in fig. 8, the data searching apparatus 1 in fig. 6 further includes:
the model searching module 14 is used for determining a problem theme corresponding to the current search problem according to the search keyword; and searching out a target search model from the candidate search models according to the problem theme.
In one embodiment, as shown in fig. 9, the data searching apparatus 1 in fig. 6 further includes:
the model training module 15 is configured to obtain general sample data and field sample data corresponding to each candidate search model, where the general sample data and the field sample data both include a sample search problem and a sample search result corresponding to the sample search problem; preprocessing the universal sample data and the sample data in each field; training each candidate search model based on the preprocessed general sample data, and optimizing the corresponding candidate search model after training based on the sample data of each field to obtain each candidate search model after optimization.
In one embodiment, as shown in fig. 10, the data searching apparatus 1 in fig. 6 further includes:
a model updating module 16, configured to obtain feedback information of the user based on the target search result; and adjusting the target search result according to the fed back information, and storing the current search problem and the adjusted target search result into a historical search set of a target search model, wherein the historical search set of the target search model is used for updating the target search model.
The respective modules in the above-described data search device may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure thereof may be as shown in fig. 11. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a data search method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 11 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the computer device to which the present application applies, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
determining search keywords of the current search problem according to the current search problem input by the user;
searching matching data corresponding to the search keywords from candidate data of a knowledge base through a target search model, and integrating the matching data according to semantic information of the matching data to obtain target search results corresponding to the current search problem;
and outputting target search results.
In one embodiment, the processor when executing the computer program further performs the steps of:
performing natural language analysis processing on the matching data to obtain semantic information of the matching data;
screening the matched data according to semantic information and search keywords of the matched data, and extracting key sentences from the screened matched data;
and integrating the key sentences to obtain target search results corresponding to the current search problem.
In one embodiment, the processor when executing the computer program further performs the steps of:
integrating the key sentences to obtain initial search results corresponding to the current search problem;
and formatting the initial search result according to a result display template configured by a user to obtain a target search result corresponding to the current search problem.
In one embodiment, the processor when executing the computer program further performs the steps of:
determining a problem theme corresponding to the current search problem according to the search keyword;
and searching out a target search model from the candidate search models according to the problem theme.
In one embodiment, the processor when executing the computer program further performs the steps of:
obtaining general sample data and field sample data corresponding to each candidate search model, wherein the general sample data and the field sample data both contain sample search problems and sample search results corresponding to the sample search problems;
preprocessing the universal sample data and the sample data in each field;
training each candidate search model based on the preprocessed general sample data, and optimizing the corresponding candidate search model after training based on the sample data of each field to obtain each candidate search model after optimization.
In one embodiment, the processor when executing the computer program further performs the steps of:
acquiring feedback information of a user based on a target search result;
and adjusting the target search result according to the fed back information, and storing the current search problem and the adjusted target search result into a historical search set of a target search model, wherein the historical search set of the target search model is used for updating the target search model.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
determining search keywords of the current search problem according to the current search problem input by the user;
searching matching data corresponding to the search keywords from candidate data of a knowledge base through a target search model, and integrating the matching data according to semantic information of the matching data to obtain target search results corresponding to the current search problem;
and outputting target search results.
In one embodiment, the computer program when executed by the processor further performs the steps of:
performing natural language analysis processing on the matching data to obtain semantic information of the matching data;
screening the matched data according to semantic information and search keywords of the matched data, and extracting key sentences from the screened matched data;
and integrating the key sentences to obtain target search results corresponding to the current search problem.
In one embodiment, the computer program when executed by the processor further performs the steps of:
integrating the key sentences to obtain initial search results corresponding to the current search problem;
and formatting the initial search result according to a result display template configured by a user to obtain a target search result corresponding to the current search problem.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining a problem theme corresponding to the current search problem according to the search keyword;
and searching out a target search model from the candidate search models according to the problem theme.
In one embodiment, the computer program when executed by the processor further performs the steps of:
obtaining general sample data and field sample data corresponding to each candidate search model, wherein the general sample data and the field sample data both contain sample search problems and sample search results corresponding to the sample search problems;
preprocessing the universal sample data and the sample data in each field;
training each candidate search model based on the preprocessed general sample data, and optimizing the corresponding candidate search model after training based on the sample data of each field to obtain each candidate search model after optimization.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring feedback information of a user based on a target search result;
and adjusting the target search result according to the fed back information, and storing the current search problem and the adjusted target search result into a historical search set of a target search model, wherein the historical search set of the target search model is used for updating the target search model.
In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:
determining search keywords of the current search problem according to the current search problem input by the user;
searching matching data corresponding to the search keywords from candidate data of a knowledge base through a target search model, and integrating the matching data according to semantic information of the matching data to obtain target search results corresponding to the current search problem;
and outputting target search results.
In one embodiment, the computer program when executed by the processor further performs the steps of:
performing natural language analysis processing on the matching data to obtain semantic information of the matching data;
screening the matched data according to semantic information and search keywords of the matched data, and extracting key sentences from the screened matched data;
and integrating the key sentences to obtain target search results corresponding to the current search problem.
In one embodiment, the computer program when executed by the processor further performs the steps of:
integrating the key sentences to obtain initial search results corresponding to the current search problem;
and formatting the initial search result according to a result display template configured by a user to obtain a target search result corresponding to the current search problem.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining a problem theme corresponding to the current search problem according to the search keyword;
and searching out a target search model from the candidate search models according to the problem theme.
In one embodiment, the computer program when executed by the processor further performs the steps of:
obtaining general sample data and field sample data corresponding to each candidate search model, wherein the general sample data and the field sample data both contain sample search problems and sample search results corresponding to the sample search problems;
preprocessing the universal sample data and the sample data in each field;
training each candidate search model based on the preprocessed general sample data, and optimizing the corresponding candidate search model after training based on the sample data of each field to obtain each candidate search model after optimization.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring feedback information of a user based on a target search result;
and adjusting the target search result according to the fed back information, and storing the current search problem and the adjusted target search result into a historical search set of a target search model, wherein the historical search set of the target search model is used for updating the target search model.
The data (including, but not limited to, data for analysis, data stored, data displayed, etc.) referred to in this application are information and data authorized by the user or sufficiently authorized by each party.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. A data searching method, the method comprising:
determining search keywords of a current search problem according to the current search problem input by a user;
searching matching data corresponding to the search keywords from candidate data of a knowledge base through a target search model, and integrating the matching data according to semantic information of the matching data to obtain target search results corresponding to the current search problem;
and outputting the target search result.
2. The method of claim 1, wherein integrating the matching data according to semantic information of the matching data to obtain the target search result corresponding to the current search question comprises:
performing natural language analysis processing on the matching data to obtain semantic information of the matching data;
screening the matching data according to the semantic information of the matching data and the search keyword, and extracting key sentences from the screened matching data;
and integrating the key sentences to obtain target search results corresponding to the current search problem.
3. The method of claim 2, wherein the integrating the key sentences to obtain the target search results corresponding to the current search problem comprises:
integrating the key sentences to obtain initial search results corresponding to the current search problems;
and formatting the initial search result according to the result display template configured by the user to obtain a target search result corresponding to the current search problem.
4. The method according to claim 1, wherein the method further comprises:
determining a problem theme corresponding to the current search problem according to the search keyword;
and searching out a target search model from the candidate search models according to the problem theme.
5. The method of claim 4, wherein the training method of the candidate search model comprises:
obtaining general sample data and field sample data corresponding to each candidate search model, wherein the general sample data and the field sample data both comprise sample search problems and sample search results corresponding to the sample search problems;
preprocessing the universal sample data and the sample data in each field;
training each candidate search model based on the preprocessed general sample data, and optimizing the corresponding candidate search model after training based on the sample data of each field to obtain each candidate search model after optimization.
6. The method according to any one of claims 1 to 5, further comprising:
acquiring feedback information of the user based on the target search result;
and adjusting the target search result according to the fed back information, and storing the current search problem and the adjusted target search result into a historical search set of the target search model, wherein the historical search set of the target search model is used for updating the target search model.
7. A data search device, the device comprising:
the key determining module is used for determining search keywords of the current search problem according to the current search problem input by a user;
the result determining module is used for searching matching data corresponding to the search keywords from candidate data of a knowledge base through a target search model, and integrating the matching data according to semantic information of the matching data to obtain target search results corresponding to the current search problem;
and the result output module is used for outputting the target search result.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311250826.9A CN117435700A (en) | 2023-09-26 | 2023-09-26 | Data searching method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311250826.9A CN117435700A (en) | 2023-09-26 | 2023-09-26 | Data searching method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117435700A true CN117435700A (en) | 2024-01-23 |
Family
ID=89556035
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311250826.9A Pending CN117435700A (en) | 2023-09-26 | 2023-09-26 | Data searching method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117435700A (en) |
-
2023
- 2023-09-26 CN CN202311250826.9A patent/CN117435700A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210081611A1 (en) | Methods and systems for language-agnostic machine learning in natural language processing using feature extraction | |
| CN111666401B (en) | Document recommendation method, device, computer equipment and medium based on graph structure | |
| CN111753198A (en) | Information recommendation method and device, electronic equipment and readable storage medium | |
| CN111797214A (en) | FAQ database-based problem screening method and device, computer equipment and medium | |
| CN112819023B (en) | Sample set acquisition method, device, computer equipment and storage medium | |
| CN111626048A (en) | Text error correction method, device, equipment and storage medium | |
| JP6693582B2 (en) | Document abstract generation method, device, electronic device, and computer-readable storage medium | |
| CN111651552B (en) | Structured information determining method and device and electronic equipment | |
| CN112614559A (en) | Medical record text processing method and device, computer equipment and storage medium | |
| CN115795030A (en) | Text classification method and device, computer equipment and storage medium | |
| CN115525757A (en) | Contract abstract generation method and device and contract key information extraction model training method | |
| CN117077679B (en) | Named entity recognition method and device | |
| CN113033912A (en) | Problem solving person recommendation method and device | |
| CN111950265A (en) | Domain lexicon construction method and device | |
| CN117332766A (en) | Flow chart generation method, device, computer equipment and storage medium | |
| CN115952266A (en) | Question generation method and device, computer equipment and storage medium | |
| CN115048536A (en) | Knowledge graph generation method and device, computer equipment and storage medium | |
| CN115329083A (en) | Document classification method and device, computer equipment and storage medium | |
| CN117435700A (en) | Data searching method, device, computer equipment and storage medium | |
| CN110414006B (en) | Text theme labeling method and device, electronic equipment and storage medium | |
| Borin et al. | Swe-Clarin: Language resources and technology for digital humanities | |
| CN117931858B (en) | Data query method, device, computer equipment and storage medium | |
| CN116992875B (en) | Text generation method, apparatus, computer device and storage medium | |
| CN117891531B (en) | System parameter configuration method, system, medium and electronic equipment for SAAS software | |
| KR102682244B1 (en) | Method for learning machine-learning model with structured ESG data using ESG auxiliary tool and service server for generating automatically completed ESG documents with the machine-learning model |
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 |