Information retrieval method and device

By determining business dimensions and configuration information, and using appropriate search methods to process structured, semi-structured and unstructured data, the problem of inefficient multi-dimensional information retrieval is solved, and efficient information acquisition and user experience improvement is achieved.

CN114780808BActive Publication Date: 2024-11-26BANK OF CHINA FINANCIAL TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210406788.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-04-18
Publication Date
2024-11-26
Estimated Expiration
2042-04-18

AI Technical Summary

Technical Problem

When facing multi-dimensional business information retrieval, the steps are complicated and inefficient, and it is difficult to obtain data information in multiple dimensions at the same time.

Method used

By determining the business dimensions and configuration information of the target business, the data types of each dimension are obtained, and the search methods corresponding to structured, semi-structured and unstructured data are adopted to achieve simultaneous acquisition of multi-dimensional data.

Benefits of technology

It improves the efficiency and user experience of information retrieval, simplifies the search process, and realizes the simultaneous acquisition of data from multiple dimensions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114780808B_ABST
    Figure CN114780808B_ABST
Patent Text Reader

Abstract

The present invention provides an information retrieval method and device, wherein the method includes: determining the business dimension of the target business according to the business type of the target business, and obtaining the configuration information of the business dimension; determining the intent information, dimension information and search keywords in the search information according to the search information for the target business; determining the method for obtaining the dimension information from the configuration information of the business dimension according to the intent information and the dimension information; obtaining the search result of the search information according to the search keywords and the method for obtaining the dimension information. The information retrieval method and device provided by the present invention achieve the acquisition of search information of each dimension by determining the intent information, dimension information, search keywords and the method for obtaining the information of each dimension in the search information of the user. A search process is realized, and data information of multiple dimensions can be obtained at the same time, which improves the search efficiency and the user experience of obtaining business information.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an information retrieval method and device. Background Art

[0002] The existing business search is that business personnel analyze the dimensions and keywords to be searched according to the needs, and then use different search modules to perform information search on the corresponding dimensions.

[0003] In the existing business search process, because information of different dimensions contains data in multiple data structures, such as structured, semi-structured and unstructured data, generally only a single business dimension is searched at a time. When facing the retrieval of business information containing multiple dimensions, different retrieval modules are required to realize information retrieval of different dimensions, which is complicated and inefficient. Summary of the invention

[0004] The present invention provides an information retrieval method and device to solve the technical problem in the prior art that when retrieving information for the same business containing multiple dimensions, information retrieval is performed separately for each different dimension, resulting in complicated steps and low efficiency.

[0005] The present invention provides an information retrieval method, comprising:

[0006] Determine the business dimension of the target business according to the business type of the target business, and obtain configuration information of the business dimension;

[0007] Determining, according to the search information for the target business, the intent information, the dimension information, and the search keyword in the search information;

[0008] Determining, according to the intent information and the dimension information, a method for acquiring the dimension information from the configuration information of the business dimension;

[0009] According to the search keyword and the method for obtaining the dimension information, a search result of the search information is obtained.

[0010] According to a method for retrieving information provided by the present invention, obtaining the retrieval result of the retrieval information according to the retrieval keyword and the method for obtaining the dimension information includes:

[0011] Determine the data type of the data to be obtained in the search information;

[0012] According to the data type, determining a search method corresponding to the data type;

[0013] According to the search keyword and the method for obtaining the dimension information, the search result of the search information is obtained according to the search method.

[0014] According to an information retrieval method provided by the present invention, determining, according to the data type, a retrieval method corresponding to the data type includes:

[0015] When the data type includes structured data, determining that the search method corresponding to the structured data is a search method of associated search;

[0016] When the data type includes semi-structured data, determining that the search method corresponding to the semi-structured data is a search method of DBpedia semantic search;

[0017] When the data type includes unstructured data, it is determined that the search method corresponding to the unstructured data is a sphinx full-text search search method.

[0018] According to an information retrieval method provided by the present invention, after obtaining the retrieval result of the retrieval information according to the retrieval method, the method further includes:

[0019] The search results are classified and displayed according to the data type.

[0020] According to a method for retrieving information provided by the present invention, determining a method for obtaining the dimension information from configuration information of the business dimension according to the intention information and the dimension information includes:

[0021] Determining a retrieval model for the retrieval information according to the intent information and the dimension information;

[0022] Determining a method for acquiring the dimension information according to the retrieval model;

[0023] The retrieval model is used to obtain information corresponding to the business dimension according to the business dimension configuration information.

[0024] According to an information retrieval method provided by the present invention, after obtaining the retrieval result of the retrieval information, the method further includes:

[0025] Based on the search results, a knowledge graph is constructed and stored in a graph database.

[0026] The present invention also provides an information retrieval device, comprising:

[0027] A dimension configuration module, used to determine the business dimension of the target business according to the business type of the target business, and obtain configuration information of the business dimension;

[0028] A search information processing module, used to determine the intent information, dimension information and search keywords in the search information according to the search information for the target business;

[0029] An information acquisition method determination module, used to determine the acquisition method of the dimension information from the configuration information of the business dimension according to the intention information and the dimension information;

[0030] The retrieval module is used to obtain the retrieval result of the retrieval information according to the retrieval keyword and the method for obtaining the dimensional information.

[0031] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-mentioned information retrieval methods when executing the computer program.

[0032] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any of the above-mentioned information retrieval methods.

[0033] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned information retrieval methods.

[0034] The information retrieval method and device provided by the present invention determine the method for obtaining information of each dimension in the target business by determining the configuration information of each business dimension in the target business. The acquisition of retrieval information of each dimension is achieved based on the intention information, dimension information, retrieval keywords and the method for obtaining information of each dimension in the user's retrieval information. Through a single retrieval, data information of multiple dimensions can be obtained simultaneously, which improves the retrieval efficiency and the user experience of obtaining business information. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly described below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 It is a flowchart of the information retrieval method provided by the present invention;

[0037] Figure 2 A schematic diagram of a flow chart of a method for retrieving information provided by the present invention;

[0038] Figure 3A schematic diagram of the structure of a device for applying the information retrieval method provided by the present invention;

[0039] Figure 4 It is a schematic diagram of the structure of the information retrieval device provided by the present invention;

[0040] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] Figure 1 A schematic diagram of the flow chart of the information retrieval method provided by the present invention. Figure 1 The information retrieval method provided by the present invention may include:

[0043] Step 110, determining the business dimension of the target business according to the business type of the target business, and acquiring configuration information of the business dimension;

[0044] Step 120, determining the intent information, dimension information and search keywords in the search information according to the search information for the target business;

[0045] Step 130, determining a method for acquiring the dimension information from the configuration information of the business dimension according to the intention information and the dimension information;

[0046] Step 140: Acquire the search result of the search information according to the search keyword and the method for acquiring the dimension information.

[0047] The execution subject of the information retrieval method provided by the present invention may be an electronic device, a component in an electronic device, an integrated circuit, or a chip. The electronic device may be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device may be a mobile phone, a tablet computer, a laptop computer, a PDA, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc., and the non-mobile electronic device may be a server, a network attached storage (NAS), or a personal computer (PC), etc., which is not specifically limited by the present invention.

[0048] The following takes the method for retrieving information provided by the present invention executed by a computer as an example to describe the technical solution of the present invention in detail.

[0049] In step 110, the target business is analyzed, and the business dimensions of the target business are determined according to the business type of the target business. After the business dimensions of the target business are obtained, the configuration information corresponding to each business dimension is determined.

[0050] Business dimensions refer to the hierarchical classification of each segment obtained after the business is split according to business type. For example, for asset investment business, after splitting according to business dimensions, the business dimensions obtained may include: industry data, investment type, market information, corporate relations, legal person relations, corporate public opinion and other data.

[0051] The data of each dimension can be composed of data of different data structure types. The data structure of specific data includes structured data, semi-structured data and unstructured data. For example, for the corporate public opinion dimension in the asset investment business, it can be composed of text information composed of structured data and pictures and audio information composed of unstructured data.

[0052] Data of different structural types in different dimensions of the same business are often stored in different locations. For example, structured data is often stored in relational databases, while unstructured and semi-structured data are often stored in graph databases or storage paths specified by the file system.

[0053] Therefore, when obtaining data in the same business, it is often necessary to obtain it from multiple different locations. Therefore, you can set the configuration information of the business dimension to determine the method of obtaining information in each business dimension. Among them, the configuration information of the business dimension refers to configuring the method of obtaining information in each business dimension for multiple different business dimensions in the business.

[0054] It is understandable that after determining the business dimensions of the target business, rapid acquisition of information of each dimension can be achieved based on the acquired configuration information of the business dimensions.

[0055] Optionally, the configuration information of the business dimension can be configured by means of a predefined parameter configuration table, and the configuration information of each dimension in the business can be configured. For dimensions not included in the parameter configuration table, the configuration of the dimension can be completed by a default configuration.

[0056] In step 120, the user's search information for the target business is received, and the intention information, dimension information, and search keywords in the search information are determined.

[0057] For the search information of the target business, the intent recognition is performed on the search information of the target business, and the result of the intent recognition is the intent information in the search information. The intent information reflects the specific information content in the dimension of the user's acquisition of the business. For example, if the search information is: "Get the profit part of the investment information of business A". Among them, "investment information" is a specific dimension, and "profit part of investment information" is the intent information.

[0058] With respect to the search information of the target business, the dimension information of the target business contained in the search information is extracted, and the dimension information of all dimensions contained in the search information is extracted.

[0059] For the search information of the target business, the search information is screened and processed, and unnecessary information in the search information is removed to screen out the search keywords related to the search content. For example, if the search information is: "Get the profit part of the investment information of business A". After screening the conjunctions and unnecessary words connecting the words in the sentence, the search keywords obtained are "business A", "investment information" and "profit part".

[0060] In step 130 , according to the intention information and dimension information in the search information obtained in step 120 , the method for obtaining the dimension information is determined from the configuration information of the business dimension determined in step 110 .

[0061] The intent information reflects the specific information content in the specific dimension of the business that the user obtains. For example, if the search information is: "Get the profit part of the investment information of business A", "investment information" is the specific dimension, and "profit part of investment information" is the intent information.

[0062] It is understandable that, according to the intent information and the dimension information, the content of the specific information required for the retrieval information can be obtained. The business dimension configuration information configures the method for obtaining the information of each dimension of the business. Therefore, according to the intent information and the dimension information, the method for obtaining the dimension information can be determined from the configuration information of the business dimension.

[0063] In step 140, after determining the method for obtaining the information of each business dimension, the information retrieval process is executed according to the search keyword to obtain the search results corresponding to the search information.

[0064] It is understandable that after determining the information of each dimension to be obtained and the method for obtaining the information of each dimension, the specific information to be obtained can be determined by executing the search process according to the search keyword.

[0065] The information retrieval method provided by the embodiment of the present invention determines the method for obtaining information of each dimension in the target business by determining the configuration information of each business dimension in the target business. The acquisition of retrieval information of each dimension is achieved based on the intention information, dimension information, retrieval keywords and the method for obtaining information of each dimension in the user's retrieval information. Through a single retrieval, data information of multiple dimensions can be obtained simultaneously, which improves the retrieval efficiency and the user experience of obtaining business information.

[0066] In one embodiment, according to the search keyword and the method for obtaining the dimension information, the search result of the search information is obtained, including: determining the data type of the data to be obtained in the search information; according to the data type, determining the search method corresponding to the data type; according to the search keyword and the method for obtaining the dimension information, obtaining the search result of the search information according to the search method.

[0067] The data type of the data to be obtained in the search information is determined. The data type may include structured data, semi-structured data, and unstructured data. For a specific data type, a corresponding search method is used to obtain data of the corresponding data type.

[0068] It is understandable that different types of data require different retrieval methods. For example, structured data is often stored in relational databases, while unstructured data and semi-structured data are often stored in graph databases or storage paths specified by file systems. Different storage locations and storage methods determine different retrieval methods.

[0069] The information retrieval method provided by the embodiment of the present invention realizes targeted acquisition of data by determining the data type of the data to be acquired and determining the corresponding retrieval method of the data type according to the data type.

[0070] In one embodiment, according to the data type, determining the retrieval method corresponding to the data type includes: when the data type includes structured data, determining that the retrieval method corresponding to the structured data is an association retrieval method; when the data type includes semi-structured data, determining that the retrieval method corresponding to the semi-structured data is a DBpedia semantic retrieval method; when the data type includes unstructured data, determining that the retrieval method corresponding to the unstructured data is a sphinx full-text retrieval method.

[0071] The data types include structured data, semi-structured data and unstructured data. The data to be acquired may include at least one of the three data types.

[0072] For structured data, the search method of associative search is used. Associative search refers to determining the search content through the correlation between keywords and data in the database. Structured data, also known as row data, is data logically expressed and implemented by a two-dimensional table structure. It strictly follows the data format and length specifications and is mainly stored and managed through relational databases. For structured data, you can directly obtain the corresponding data content from the relational database based on associative search.

[0073] For the semi-structured data, the DBpedia semantic search method is used. Compared with structured data, the data structure of semi-structured data varies greatly. DBpedia is a fixed-mode search method that uses semantic technology to query data.

[0074] For the unstructured data, we use the sphinx full-text search method. Unstructured data includes pictures, sounds, videos and other types of data. Sphinx is a full-text search engine that implements professional full-text search based on query statements.

[0075] The information retrieval method provided by the embodiment of the present invention determines the retrieval method of the corresponding data type by the data type, thereby realizing targeted and efficient acquisition of structured data, semi-structured data and unstructured data therein.

[0076] In one embodiment, after obtaining the search results of the search information according to the search method, the method further includes: classifying and displaying the search results according to the data type.

[0077] According to the data type, you can get the search results corresponding to different data types. You can classify and display the search results corresponding to different data types.

[0078] It is understandable that different types of search results can be obtained for different data types, such as search results in text form, image form, sound form, and video form. Different types of search results are classified and displayed.

[0079] The information retrieval method provided by the embodiment of the present invention increases the readability of information and the user-friendliness of the system by classifying and displaying the retrieval results according to data types.

[0080] In one embodiment, according to the intent information and the dimension information, a method for obtaining the dimension information is determined from the configuration information of the business dimension, including: determining a retrieval model for the retrieval information according to the intent information and the dimension information; determining a method for obtaining the dimension information according to the retrieval model; the retrieval model is used to obtain information corresponding to the business dimension according to the business dimension configuration information.

[0081] According to the intent information and dimension information, the retrieval model corresponding to the retrieval information is determined from multiple retrieval models. Among the multiple retrieval models, each retrieval model is responsible for determining the method of obtaining the retrieval information of part of the data. The data to be obtained is determined from the intent information and dimension information, and the data to be obtained is matched with the retrieval model to obtain the corresponding retrieval model.

[0082] According to the retrieval model, the method of obtaining information in the dimension information is determined. The retrieval model matches the dimension information with the corresponding configuration information in the business dimension configuration information according to the business dimension configuration information to determine the method of obtaining information in the dimension information.

[0083] The information retrieval method provided in the embodiment of the present invention determines a retrieval model through dimensional information and intent information, and determines the method for obtaining dimensional information based on the retrieval model, thereby providing a basis for the subsequent acquisition of retrieval results.

[0084] In one embodiment, after obtaining the retrieval results of the retrieval information, it also includes: constructing a knowledge graph based on the retrieval results, and storing the knowledge graph in a graph database.

[0085] After determining the search results, the relationship between the data in the search results can be determined through the knowledge graph.

[0086] A knowledge graph is a knowledge domain visualization or knowledge field mapping map. It is a series of various graphics that show the knowledge development process and structural relationship. It uses visualization technology to describe knowledge resources and their carriers, and to mine, analyze, construct, draw and display knowledge and their interrelationships.

[0087] After the retrieval structure is constructed into a knowledge graph and stored, it can be quickly called and viewed later as needed.

[0088] The information retrieval method provided by the embodiment of the present invention constructs a knowledge graph and stores the retrieval structure, so that the data correlation between the retrieval results is clearer. The stored knowledge graph can be quickly called and viewed as needed later, which improves the user's information viewing experience.

[0089] The following is a flow chart of a method for retrieving information provided by the present invention: Figure 2 Take the following as an example to illustrate the technical solution provided by the present invention:

[0090] Step 200, dimension configuration, split the business according to the business type to obtain the business dimensions of the business. According to the business dimension, obtain the configuration information of the corresponding business dimension. There are two ways to obtain configuration information. By default, the system will configure the parameters of the configuration information through the background dimension parameter configuration table. In addition, users can also customize the configuration information of the business dimension through the custom dimension configuration module on the front-end page. Among them, the configuration information supports adding, editing and deleting operations.

[0091] Step 210, data preprocessing, performs data preprocessing on the search information originally input by the user obtained from the front-end page. The data preprocessing may include: excluding common words, converting synonyms, and realizing normalization of the search information.

[0092] Step 220, natural language processing, performs natural language processing on the pre-processed search information based on the dynamic corpus, mainly performing syntactic analysis, intelligent word segmentation, word meaning association, word vector feature extraction and other processing on the search information, and through processing, determines the intent information, dimension information, and search keywords in the search information.

[0093] Step 230, intent recognition, in natural language processing, the user's intent is initially analyzed based on syntactic analysis, semantic analysis, disambiguation processing and other operations, and the specific intent information in the retrieved information is finally determined through the intent recognition model.

[0094] Step 240, dimension extraction, in natural language processing, the dimension information in the retrieval information is parsed according to operations such as word segmentation, synonym conversion, feature extraction, etc., so as to finally determine the specific dimension information.

[0095] Step 250, retrieval keyword extraction, in natural language processing, preliminary analysis using retrieval keywords is achieved based on operations such as word segmentation, word meaning analysis, feature extraction, etc., and specific retrieval keywords in the retrieval information are determined in combination with the dynamic corpus.

[0096] Step 260, matching the retrieval model, matching the retrieval model according to the dimension information and the user intention information, and completing the model parameter initialization, mainly including the specific user intention and the retrieval dimension information parameters. According to the retrieval model, determine the acquisition method of the dimension information.

[0097] Step 270, constructing a search instance, constructing a specific search instance according to the method of obtaining the dimension information and the search keywords determined by the search model, and executing the search task through the search instance.

[0098] Step 280, perform retrieval, and perform multiple retrievals of three branches according to the data type. Structured data uses the retrieval method of association retrieval, unstructured data uses the retrieval method of sphinx full-text retrieval, and semi-structured data uses the retrieval method of DBpedia semantic retrieval.

[0099] Step 290, information integration, integrates the search results of the three branches to facilitate subsequent result display on the web side.

[0100] The following is a schematic diagram of a device structure for applying the information retrieval method provided by the present invention as an example to illustrate the technical solution provided by the present invention:

[0101] like Figure 3 As shown, the device may include:

[0102] The dimension configuration module 310 is used to split the business according to the business type to obtain each business dimension of the business and obtain configuration information of the corresponding business dimension according to the business dimension.

[0103] The natural language processing module 320 is used to perform natural language processing on the search information input by the user, mainly through data preprocessing, Chinese and English word segmentation, disambiguation, semantic analysis, feature vector extraction and other processing to achieve the acquisition of search keywords and dimension information in the search information, which is subsequently used for processing by the information retrieval module. The acquisition method of the dimension information is determined based on the dimension information and search keywords parsed by the natural language processing module, which is subsequently used for retrieval by the information retrieval module.

[0104] The intention recognition module 330 is used to perform preliminary analysis of the user's intention based on operations such as syntactic analysis, semantic analysis, and disambiguation processing, and ultimately determine the specific intention information in the retrieved information through the intention recognition model.

[0105] The information retrieval module 340 is used to obtain the retrieval result of the retrieval information according to the retrieval keyword and the method for obtaining the dimension information.

[0106] The information integration module 350 is used to format and preprocess the information searched by the information retrieval module, and to construct a knowledge graph through knowledge extraction, knowledge fusion, and knowledge construction operations, and to store the data in a graph database. All integrated information will be used for subsequent result display.

[0107] The result display module 360 ​​is used to display the search results on the front-end page to the user, and the user can customize the required display information items.

[0108] Figure 4 A schematic diagram of the structure of the information retrieval device provided by the present invention, such as Figure 4 As shown, the device comprises:

[0109] The dimension configuration module 410 is used to determine the business dimension of the target business according to the business type of the target business, and obtain configuration information of the business dimension;

[0110] A search information processing module 420 is used to determine the intent information, dimension information and search keywords in the search information according to the search information for the target business;

[0111] An information acquisition method determination module 430, configured to determine an acquisition method of the dimension information from the configuration information of the business dimension according to the intention information and the dimension information;

[0112] The search module 440 is used to obtain the search result of the search information according to the search keyword and the method for obtaining the dimension information.

[0113] The information retrieval device provided in the embodiment of the present invention determines the method of obtaining information of each dimension in the target business by determining the configuration information of each business dimension in the target business. According to the intention information, dimension information, search keywords and the method of obtaining information of each dimension in the user's search information, the acquisition of search information of each dimension is realized. Through a single search, data information of multiple dimensions can be obtained simultaneously, which improves the search efficiency and the user experience of obtaining business information.

[0114] In one embodiment, the retrieval module 440 is specifically used to:

[0115] Acquiring a search result of the search information according to the search keyword and the method for acquiring the dimension information includes:

[0116] Determine the data type of the data to be obtained in the search information;

[0117] According to the data type, determining a search method corresponding to the data type;

[0118] According to the search keyword and the method for obtaining the dimension information, the search result of the search information is obtained according to the search method.

[0119] In one embodiment, the retrieval module 440 is further specifically configured to:

[0120] Determining, according to the data type, a search method corresponding to the data type, including:

[0121] When the data type includes structured data, determining that the search method corresponding to the structured data is a search method of associated search;

[0122] When the data type includes semi-structured data, determining that the search method corresponding to the semi-structured data is a search method of DBpedia semantic search;

[0123] When the data type includes unstructured data, it is determined that the search method corresponding to the unstructured data is a sphinx full-text search search method.

[0124] In one embodiment, the retrieval module 440 is further specifically configured to:

[0125] After obtaining the search results of the search information in the search method, the method further includes:

[0126] The search results are classified and displayed according to the data type.

[0127] In one embodiment, the information acquisition mode determination module 430 is specifically used to:

[0128] Determining, according to the intent information and the dimension information, a method for acquiring the dimension information from the configuration information of the business dimension, including:

[0129] Determining a retrieval model for the retrieval information according to the intent information and the dimension information;

[0130] Determining a method for acquiring the dimension information according to the retrieval model;

[0131] The retrieval model is used to obtain information corresponding to the business dimension according to the business dimension configuration information.

[0132] In one embodiment, the retrieval module 440 is further specifically configured to:

[0133] After obtaining the search result of the search information, the method further includes:

[0134] Based on the search results, a knowledge graph is constructed and stored in a graph database.

[0135] Figure 5An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5 As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the information retrieval method, which includes:

[0136] Determine the business dimension of the target business according to the business type of the target business, and obtain configuration information of the business dimension;

[0137] Determining, according to the search information for the target business, the intent information, the dimension information, and the search keyword in the search information;

[0138] Determining, according to the intent information and the dimension information, a method for acquiring the dimension information from the configuration information of the business dimension;

[0139] According to the search keyword and the method for obtaining the dimension information, a search result of the search information is obtained.

[0140] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0141] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, and when the program instructions are executed by a computer, the computer can execute the information retrieval method provided by the above methods, the method comprising:

[0142] Determine the business dimension of the target business according to the business type of the target business, and obtain configuration information of the business dimension;

[0143] Determining, according to the search information for the target business, the intent information, the dimension information, and the search keyword in the search information;

[0144] Determining, according to the intent information and the dimension information, a method for acquiring the dimension information from the configuration information of the business dimension;

[0145] According to the search keyword and the method for obtaining the dimension information, a search result of the search information is obtained.

[0146] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform the above-mentioned information retrieval method, the method comprising:

[0147] Determine the business dimension of the target business according to the business type of the target business, and obtain configuration information of the business dimension;

[0148] Determining, according to the search information for the target business, the intent information, the dimension information, and the search keyword in the search information;

[0149] Determining, according to the intent information and the dimension information, a method for acquiring the dimension information from the configuration information of the business dimension;

[0150] According to the search keyword and the method for obtaining the dimension information, a search result of the search information is obtained.

[0151] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0152] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0153] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for retrieving information, characterized in that: include: Determine the business dimension of the target business according to the business type of the target business, and obtain configuration information of the business dimension, wherein the business dimension refers to the hierarchical classification of each segment obtained after the business is split according to the business type; Determining, according to the search information for the target business, the intent information, the dimension information, and the search keyword in the search information; Determining, according to the intent information and the dimension information, a method for acquiring the dimension information from the configuration information of the business dimension; Acquire a search result of the search information according to the search keyword and the method for acquiring the dimension information; The obtaining of the search result of the search information according to the search keyword and the method for obtaining the dimension information includes: Determine the data type of the data to be obtained in the search information; According to the data type, determining a search method corresponding to the data type; According to the search keyword and the method for obtaining the dimension information, obtaining the search result of the search information according to the search method; The step of determining, according to the data type, a search method corresponding to the data type includes: When the data type includes structured data, determining that the search method corresponding to the structured data is a search method of associated search; When the data type includes semi-structured data, determining that the search method corresponding to the semi-structured data is a search method of DBpedia semantic search; When the data type includes unstructured data, it is determined that the search method corresponding to the unstructured data is a sphinx full-text search search method.

2. The information retrieval method according to claim 1, characterized in that: After obtaining the search result of the search information according to the search method, the method further includes: The search results are classified and displayed according to the data type.

3. The information retrieval method according to claim 1, characterized in that: The determining, according to the intent information and the dimension information, a method for acquiring the dimension information from the configuration information of the business dimension includes: Determining a retrieval model for the retrieval information according to the intent information and the dimension information; Determining a method for acquiring the dimension information according to the retrieval model; The retrieval model is used to obtain information corresponding to the business dimension according to the business dimension configuration information.

4. The information retrieval method according to claim 1, characterized in that: After obtaining the search result of the search information, the method further includes: Based on the search results, a knowledge graph is constructed and stored in a graph database.

5. An information retrieval device, characterized in that: include: A dimension configuration module, used to determine the business dimension of the target business according to the business type of the target business, and obtain configuration information of the business dimension, wherein the business dimension refers to the hierarchical classification of each segment obtained after the business is split according to the business type; A search information processing module, used to determine the intent information, dimension information and search keywords in the search information according to the search information for the target business; An information acquisition method determination module, used to determine the acquisition method of the dimension information from the configuration information of the business dimension according to the intention information and the dimension information; A search module, used to obtain the search result of the search information according to the search keyword and the method for obtaining the dimension information; The obtaining of the search result of the search information according to the search keyword and the method for obtaining the dimension information includes: Determine the data type of the data to be obtained in the search information; According to the data type, determining a search method corresponding to the data type; According to the search keyword and the method for obtaining the dimension information, obtaining the search result of the search information according to the search method; The step of determining, according to the data type, a search method corresponding to the data type includes: When the data type includes structured data, determining that the search method corresponding to the structured data is a search method of associated search; When the data type includes semi-structured data, determining that the search method corresponding to the semi-structured data is a search method of DBpedia semantic search; When the data type includes unstructured data, it is determined that the search method corresponding to the unstructured data is a sphinx full-text search search method.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the information retrieval method according to any one of claims 1 to 4 is implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the information retrieval method according to any one of claims 1 to 4 is implemented.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the information retrieval method according to any one of claims 1 to 4 is implemented.