Information retrieval method and device, equipment and storage medium

Abstract

The invention relates to the technical field of data processing, and discloses an information retrieval method and device, equipment and a storage medium. The method comprises the steps that a current user retrieval text input by a terminal is acquired, and a current feature vector matched with the current user retrieval text is determined according to the corresponding relation between industry terms and vector codes; according to the current feature vector, two or more retrieval items of a feature vector library are retrieved to obtain a corresponding retrieval result, and the feature vector library is generated after mapping conversion from a plurality of metadatabases to an industry term library; and after analyzing and sorting the obtained two or more retrieval results, outputting corresponding retrieval results to the terminal. In this way, multiple databases can be inquired concurrently, and the retrieval efficiency is greatly improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, for example, to methods, devices, equipment and storage media for information retrieval. Background Art

[0002] With the development of science and technology, all walks of life need to carry out technological research and development and innovation. In the research and development and innovation activities, first of all, you need to be familiar with the technological status of the industry you are concerned about. This is inseparable from the public information in the research field such as literature and patents. You need to search for patents in the patent database, and then search for literature in the literature database; next, you need to learn about the current market recognition of the technology and the company's investment hotspots. You need to go to the paper library and information library to search for papers and the latest information reports; finally, if you confirm the technical maturity and market recognition of the industry, you need to find out the information of the mainstream companies and scientific research institutes in the market, so as to facilitate subsequent communication and development or cooperative research and development of new products. This requires searching for relevant resources in the company database and university scientific research institution database. Each of the above links requires manual retrieval, which is time-consuming, labor-intensive, inefficient, and lacks a good evaluation system for comprehensive research and judgment.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0004] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0005] The embodiments of the present disclosure provide a method, apparatus, device and storage medium for information retrieval to solve the technical problem of low efficiency of information retrieval.

[0006] In some embodiments, the method comprises:

[0007] Obtaining the current user search text input by the terminal, and determining the current feature vector matching the current user search text according to the correspondence between the industry terminology and the vector code;

[0008] According to the current feature vector, two or more search items of the feature vector library are searched to obtain corresponding search results, wherein the feature vector library is generated after mapping and transforming multiple metadata libraries into industry term libraries;

[0009] After analyzing and sorting the two or more search results obtained, the corresponding search results are output to the terminal.

[0010] In some embodiments, it also includes:

[0011] According to the correspondence between industry terms and vector codes, metadata databases such as information, patents, documents, and company information are mapped and transformed into industry terminology libraries to generate corresponding feature vector libraries.

[0012] In some embodiments, determining a current feature vector matching the current user search text includes:

[0013] Segment the current user's search text to obtain one or more segmented words;

[0014] When one or more of the obtained word segments exist in the industry term library, the vector code corresponding to each word segment is determined according to the correspondence between the stored industry terms and the vector code, and the corresponding current feature vector is obtained;

[0015] When none of the obtained word segments exists in the industry terminology database, the current user search text is corrected with industry terminology to obtain the corrected user search text, and a current feature vector matching the corrected user search text is determined.

[0016] In some embodiments, obtaining the modified user search text includes:

[0017] According to the obtained word segmentation, a metadata database search is performed, and the word segmentation search results involving industry terms are sent to the terminal, so that the user modifies the current user search text according to the word segmentation search results, and inputs the modified user search text into the terminal;

[0018] Gets the modified user search text sent by the terminal.

[0019] In some embodiments, it also includes:

[0020] Configure the search term weight matrix and set the quantity.

[0021] In some embodiments, outputting the corresponding search results to the terminal includes:

[0022] Generate a result similarity matrix based on two or more search results;

[0023] According to the result similarity matrix and the search item weight matrix, the total score matrix is ​​obtained and sorted in reverse order;

[0024] According to the sorting order of the total score matrix, a set number of search results are output to the terminal.

[0025] In some embodiments, the apparatus comprises:

[0026] an acquisition module configured to acquire a current user search text input by a terminal and determine a current feature vector matching the current user search text based on a correspondence between industry terms and vector codes;

[0027] A search module is configured to search two or more search items of a feature vector library according to the current feature feature vector to obtain corresponding search results, wherein the feature vector library is generated after mapping and transforming multiple metadata libraries into industry term libraries;

[0028] The output module is configured to analyze and sort the two or more search results obtained, and then output the corresponding search results to the terminal.

[0029] In some embodiments, the apparatus for information retrieval includes a processor and a memory storing program instructions, and the processor is configured to execute the above-mentioned method for information retrieval when executing the program instructions.

[0030] In some embodiments, the device includes: a device body; the above-mentioned device for information retrieval is installed in the device body.

[0031] In some embodiments, the storage medium stores program instructions, and when the program instructions are run, the above-mentioned method for information retrieval is executed.

[0032] The method, apparatus and device for information retrieval provided by the embodiments of the present disclosure can achieve the following technical effects:

[0033] After multiple metadata databases are mapped and transformed into industry terminology libraries to generate feature vector libraries, user search texts are obtained and corresponding feature vectors are generated. Thus, searches can be performed based on the feature vector library to obtain corresponding search results and output them. In this way, multiple databases can be queried concurrently, greatly improving the efficiency of searches.

[0034] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0036] Figure 1 is a structural diagram of an information retrieval system provided by an embodiment of the present disclosure;

[0037] Figure 2 is a flowchart of an information retrieval method provided by an embodiment of the present disclosure;

[0038] Figure 3 is a flowchart of an information retrieval method provided by an embodiment of the present disclosure;

[0039] Figure 4 is a structural schematic diagram of an information retrieval device provided by an embodiment of the present disclosure;

[0040] Figure 5 is a structural schematic diagram of an information retrieval device provided by an embodiment of the present disclosure;

[0041] Figure 6 is a structural schematic diagram of an information retrieval device provided by an embodiment of the present disclosure;

[0042] Figure 7 It is a schematic diagram of a device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0043] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0044] The terms "first", "second", etc. in the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so that the embodiments of the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0045] Unless otherwise stated, the term "plurality" means two or more.

[0046] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0047] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0048] In the disclosed embodiments, each industry has corresponding industry terms. For example, in the home appliance industry, the corresponding industry terms include: refrigerators, washing machines, air conditioners, temperature control, etc. Therefore, based on big data search and computer technology, multiple metadata databases such as information, patents, documents, and company information can be mapped and transformed into industry terminology libraries according to the contained industry terms, and the corresponding relationship between industry terms and vector codes is configured, thereby obtaining a feature vector library corresponding to the industry terminology library. After obtaining the user search text and generating the corresponding feature feature vector, the feature vector library can be searched to obtain the corresponding search results and output them. In this way, multiple databases can be queried concurrently, greatly improving the efficiency of the search. In addition, the user search text can be corrected, the user input can be optimized, and the accuracy of the search can be improved. In addition, the priority sorting and comprehensive judgment of the query results have been added, which is a creative application of artificial intelligence in the process of research and development and innovation, and further improves the intelligence of information retrieval.

[0049] Figure 1 Schematic diagram of a structure of an information retrieval system provided by an embodiment of the present disclosure. Figure 1 As shown, the system includes: a cloud server 100, a plurality of metadata library devices 200 and a terminal 300.

[0050] In the disclosed embodiment, the meta-database may include: information, patents, documents, company information and other meta-databases. Among them, each piece of information in the information database may include: title, text, etc. Each piece of information in the patent database may include: title, text, claims, drawings, etc. Each piece of information in the document database may include: title, text, drawings, etc. And each piece of information in the company information database may include: introduction, business scope, etc. Among them, the introduction can extract the company title, and the business scope can extract the company text. Therefore, each piece of information in the company information database may also include: title, text, etc.

[0051] One metadata library may be located in one metadata library device 200, or two or more metadata libraries may be located in one metadata library device 200. Alternatively, one metadata library may be located in two or more devices 200.

[0052] The cloud server 100 can communicate with multiple metadata database devices 200, and can map and transform metadata databases such as information, patents, documents, and company information into industry terminology databases according to the corresponding relationship between industry terms and vector codes, and generate corresponding feature vector libraries. The industry terminology database includes industry terms in the industry, such as refrigerators, washing machines, air conditioners, temperature control, etc. in the home appliance industry. Each industry term corresponds to a vector code. In this way, the cloud server 100 can search for each piece of information including industry terms in multiple metadata databases based on big data search and computer technology, and can map it into corresponding feature vectors, thereby forming a feature vector library.

[0053] For example, a piece of information found in an information metadata database may include industry terms such as air conditioning and temperature control. Therefore, it can be mapped and transformed into an industry terminology database to generate a corresponding feature vector of [00010, 10202]. That is, as long as the information in multiple metadata databases such as information, patents, documents, and company information includes industry terms, the corresponding feature vectors can be obtained and constitute a feature vector library.

[0054] In this way, when the user searches for information through the terminal 300, the terminal 300 sends the current user search text input by the user to the cloud server 100. Thereby, the cloud server 100 determines the current feature vector that matches the current user search text based on the correspondence between industry terms and vector codes, and then searches the feature vector library based on the current feature vector to obtain the corresponding search results and output them to the terminal 300.

[0055] Generally, the information in the metadata database includes: title, text, summary, drawings, etc., which can correspond to two or more search items. Therefore, the generated feature vector library can also include two or more search items. In this way, in some embodiments, in order to improve the accuracy of the search, the cloud server 100 can search two or more search items in the feature vector library to obtain corresponding search results, and after analyzing and sorting the two or more search results obtained, output the corresponding search results to the terminal 300. In this way, the priority sorting and comprehensive judgment of the query results are increased, which is a creative application of artificial intelligence in the process of research and development and innovation, and further improves the accuracy and intelligence of information retrieval.

[0056] Figure 2 FIG. 1 is a flow chart of an information retrieval method provided by an embodiment of the present disclosure. Figure 2 As shown, the process used for information retrieval includes:

[0057] Step 201: obtaining the current user search text input by the terminal, and determining the current feature vector matching the current user search text according to the correspondence between the industry terminology and the vector code.

[0058] The user can input the search information to the terminal by touch, voice, gesture, etc., so that the terminal can convert and obtain the corresponding user search text and send it to the cloud server. Among them, the current moment corresponds to the current user search text.

[0059] In this way, the cloud server can determine the current feature vector that matches the current user search text based on the correspondence between the industry terminology and the vector code. In some embodiments, determining the current feature vector that matches the current user search text includes: segmenting the current user search text to obtain one or more segmented words; in the case where one or more segmented words among the obtained segmented words exist in the industry terminology library, determining the vector code corresponding to each segmented word based on the correspondence between the stored industry terminology and the vector code, and obtaining the corresponding current feature vector; in the case where none of the segmented words among the obtained segmented words exist in the industry terminology library, performing industry terminology correction on the current user search text to obtain a corrected user search text, and determining the current feature vector that matches the corrected user search text.

[0060] Through the word segmentation software in the relevant technology, the cloud server can segment the current user's search text. If the current user's search text is not separable, the entire current user's search text can be determined as one word segmentation, that is, one word segmentation is obtained. If the current user's search text is separable, two or more word segments are obtained.

[0061] Then, the obtained word segmentation is compared with the industry terminology library. No matter whether the obtained word segmentation is one, two or more, only one or more word segmentation exists in the industry terminology library. Then, the vector code corresponding to each word segmentation can be determined according to the correspondence between the saved industry terms and the vector code, and the corresponding current feature vector can be obtained. For example: the input text information is "control the compressor of the air conditioner according to the indoor temperature", and the obtained words can be: indoor temperature, air conditioning, compressor, control, and it can be determined that these word segmentations exist in the corresponding home appliance industry terminology library. Then, according to the correspondence between the industry terms and the vector code, the current feature vector can be determined to be [002, 3125, 3663, ****] and so on.

[0062] If none of the obtained word segments exists in the industry terminology library, in order to reduce the probability of missed detection, the current user search text may be corrected by industry terminology, and after obtaining the corrected user search text, the current feature vector matching the corrected user search text is determined according to the above method. In some embodiments, obtaining the corrected user search text includes: performing a metadata library search based on the obtained word segments, and sending the word segmentation search results involving industry terminology to the terminal, so that the user modifies the current user search text according to the word segmentation search results, and inputs the modified corrected user search text into the terminal; and obtaining the corrected user search text sent by the terminal.

[0063] None of the obtained word segments exist in the industry terminology library. Therefore, the cloud server can search the metadata library based on the obtained word segments, and send the search results involving industry terms in the retrieved structure to the terminal, that is, send the word segmentation search results involving industry terms to the terminal. After the terminal displays it, the user can make a selection and modify the current user search text. In this way, the terminal obtains the corresponding modified user search text and can send it to the cloud server. As a result, the cloud server obtains the modified user search text sent by the terminal.

[0064] The server can continue to segment the modified user search text, and one or more of the obtained segmented words exist in the industry terminology library. Therefore, based on the correspondence between the stored industry terms and the vector codes, the vector code corresponding to each segmented word can be determined, and the corresponding current feature vector can be obtained.

[0065] Step 202: searching two or more search items of a feature vector library according to the current feature vector to obtain corresponding search results, wherein the feature vector library is generated after mapping and transforming multiple metadata libraries into industry term libraries.

[0066] In the disclosed embodiment, the cloud server needs to be configured with a feature vector library, that is, according to the correspondence between industry terms and vector codes, the metadata library such as information, patents, documents, company information, etc. is mapped and transformed into the industry terminology library to generate the corresponding feature vector library.

[0067] The metadata database may include information, patents, documents, company information, etc. Based on big data search and computer technology, the cloud server can search for each piece of information including industry terms in multiple metadata databases, and map them into corresponding feature vectors, thereby generating a feature vector library.

[0068] In this way, the cloud server searches the feature vector library according to the current feature vector, obtains the corresponding search result and outputs it to the terminal.

[0069] The information in the metadata database includes: title, text, summary, illustrations, etc., which may correspond to two or more search items. Therefore, the generated feature vector library may also include two or more search items. In this way, in some embodiments, in order to improve the accuracy of the retrieval, the cloud server can retrieve two or more search items in the feature vector library based on the current feature vector to obtain corresponding search results.

[0070] For example, the cloud server can search the title of the feature vector library according to the current feature vector to obtain the first search result. In parallel, the cloud server can search the text of the feature vector library according to the current feature vector to obtain the second search result. In parallel, the cloud server can search the summary of the feature vector library according to the current feature vector to obtain the third search result, that is, the search items include: title, text and summary.

[0071] Step 203: After analyzing and sorting the two or more search results obtained, the corresponding search results are output to the terminal.

[0072] The cloud server can configure the weight coefficient corresponding to each search item, thus forming a search item weight matrix. There may be many search structures, so a set number can be configured, so that the corresponding search results output to the terminal include: generating a result similarity matrix based on two or more search results; obtaining a total score matrix based on the result similarity matrix and the search item weight matrix and arranging them in reverse order; outputting a set number of search results to the terminal according to the sorting order of the total score matrix.

[0073] It can be seen that in the disclosed embodiment, after multiple metadata databases are mapped and transformed into industry terminology databases to generate feature vector databases, the cloud server obtains the user search text and generates corresponding feature vectors based on the correspondence between industry terminology and vector encoding. It can search based on the feature vector database to obtain corresponding search results and output them. In this way, multiple databases can be queried concurrently, greatly improving the efficiency of retrieval. In addition, the user search text can be corrected, the user input is optimized, the probability of missed detection is reduced, and the priority sorting and comprehensive judgment of the query results are increased. It is a creative application of artificial intelligence in the process of research and development innovation, which further improves the accuracy and intelligence of information retrieval.

[0074] The operation flow is collected into a specific embodiment below to illustrate the information retrieval process provided by the embodiment of the present invention.

[0075] In this embodiment, Figure 1As shown, the cloud server can communicate with the metadata database device and the terminal respectively. In addition, the cloud server maps and transforms the metadata database such as information, patents, documents, and company information to the home appliance industry terminology database based on the correspondence between the home appliance industry terminology and the vector code, and generates the corresponding feature vector library. At the same time, the search item weight matrix and the set quantity are also configured. Among them, the search items include: title and text.

[0076] Figure 3 FIG. 1 is a flow chart of an information retrieval method provided by an embodiment of the present disclosure. Figure 3 As shown, the information retrieval process includes:

[0077] Step 301: The cloud server obtains the current user search text input by the terminal.

[0078] Step 302: The cloud server performs word segmentation on the current user search text to obtain one or more word segments.

[0079] Step 303: Determine whether one or more of the obtained segmented words exist in the home appliance industry terminology library. If yes, execute step 304; otherwise, execute step 305.

[0080] Step 304 : The cloud server determines the vector code corresponding to each word segmentation according to the correspondence between the stored home appliance industry terms and the vector codes, obtains the corresponding current feature vector, and proceeds to step 307 .

[0081] Step 305: The cloud server performs a metadata database search based on the obtained word segmentation through the metadata database device, and sends the word segmentation search results related to home appliance industry terms to the terminal.

[0082] In this way, the terminal can present the word segmentation search results, and the user can modify the current user search text according to the word segmentation search results and input the modified user search text into the terminal.

[0083] Step 306 : The cloud service server obtains the corrected user search text sent by the terminal, and determines it as the current user detection text, and returns to step 302 .

[0084] Step 307: The cloud server searches the feature vector library for the title and the text in parallel according to the current feature vector, and obtains the corresponding first search result and second search result.

[0085] Step 308: The cloud server generates a result similarity matrix according to the first search result and the second search result, and obtains a total score matrix according to the result similarity matrix and the search item weight matrix.

[0086] Step 309: The cloud server sorts the total score matrix in reverse order, and outputs a set number of search results to the terminal according to the sorting order and the mapping with the metadata database.

[0087] It can be seen that in this embodiment, after multiple metadata databases are mapped and transformed into home appliance industry terminology databases to generate feature vector databases, the cloud server obtains the user search text and generates corresponding feature vectors based on the correspondence between home appliance industry terminology and vector codes. It can search based on the feature vector database to obtain corresponding search results and output them. In this way, multiple databases can be queried concurrently, greatly improving the efficiency of retrieval. In addition, the user search text can be corrected, the user input is optimized, the probability of missed detection is reduced, and the priority sorting and comprehensive judgment of the query results are increased. It is a creative application of artificial intelligence in the R&D and innovation process of the home appliance industry, which further improves the accuracy and intelligence of information retrieval in the home appliance industry.

[0088] According to the above process for information retrieval, a device for information retrieval can be constructed.

[0089] Figure 4 Schematic diagram of a structure of an information retrieval device provided by an embodiment of the present disclosure. Figure 4 As shown, the information retrieval device 400 includes: an acquisition module 410, a retrieval module 420 and an output module 430.

[0090] The acquisition module 410 is configured to acquire the current user search text input by the terminal, and determine the current feature vector matching the current user search text according to the correspondence between the industry terminology and the vector code.

[0091] The search module 420 is configured to search two or more search items of a feature vector library according to the current feature vector to obtain corresponding search results, wherein the feature vector library is generated after mapping and transforming multiple metadata libraries into industry term libraries.

[0092] The output module 430 is configured to analyze and sort the two or more search results obtained, and then output the corresponding search results to the terminal.

[0093] In some embodiments, it also includes: a mapping generation module, which is configured to map and transform metadata databases such as information, patents, documents, and company information into industry terminology libraries based on the correspondence between industry terms and vector codes, and generate corresponding feature vector libraries.

[0094] In some embodiments, the acquisition module 410 includes:

[0095] The word segmentation unit is configured to segment the current user search text to obtain one or more segmented words.

[0096] The determination unit is configured to determine the vector code corresponding to each word segmentation according to the correspondence between the stored industry terms and the vector code, and obtain the corresponding current feature vector when one or more word segments among the obtained word segments exist in the industry terminology library.

[0097] The correction unit is configured to correct the current user search text with industry terms when none of the obtained word segments exists in the industry term library to obtain the corrected user search text, and determine the current feature vector matching the corrected user search text.

[0098] In some embodiments, the correction unit is specifically configured to perform a metadata database search based on the obtained segmented words, and send the segmented word search results involving industry terms to the terminal, so that the user modifies the current user search text based on the segmented word search results, and inputs the modified user search text into the terminal;

[0099] Gets the modified user search text sent by the terminal.

[0100] In some embodiments, the method further includes: a configuration module configured to configure a search term weight matrix and set a quantity.

[0101] In some embodiments, the output module 430 is specifically configured to generate a result similarity matrix based on two or more search results; obtain a total score matrix based on the result similarity matrix and the search item weight matrix and arrange it in reverse order; and output a set number of search results to the terminal based on the sorting order of the total score matrix.

[0102] The following will illustrate the process of information retrieval by the information retrieval device provided by the embodiment of the present invention with reference to specific embodiments.

[0103] In this embodiment, the cloud server can communicate with the metadata database device and the terminal respectively. The search items include: title and text.

[0104] Figure 5 Schematic diagram of a structure of an information retrieval device provided by an embodiment of the present disclosure. Figure 5 As shown, the information retrieval device 400 includes: an acquisition module 410, a retrieval module 420, an output module 430, a mapping generation module 440 and a configuration module 450. In addition, the acquisition module 410 includes: a word segmentation unit 411, a determination unit 412 and a correction unit 413.

[0105] Through big data retrieval and computer technology, the mapping generation module 440 in the information retrieval device applied to the cloud server maps and transforms the metadata database such as information, patents, documents, and company information to the home appliance industry terminology database according to the corresponding relationship between the home appliance industry terminology and the vector code, and generates the corresponding feature vector library. In addition, the configuration module 450 also configures the search item weight matrix corresponding to the title and text, and sets the quantity.

[0106] In this way, when the user needs to search, the acquisition module 410 can obtain the current user search text input by the terminal, and the word segmentation unit 411 segment the current user search text to obtain one or more word segments. And when it is determined that one or more of the obtained word segments exist in the industry terminology library, the determination unit 412 determines the vector code corresponding to each word segment according to the corresponding relationship between the stored home appliance industry terms and the vector code, and obtains the corresponding current feature vector.

[0107] If none of the obtained word segments exist in the industry terminology library, the correction unit 413 performs a metadata database search through the metadata database device based on the obtained word segments, and sends the word segmentation search results involving home appliance industry terms to the terminal, so that the user can modify the current user search text according to the word segmentation search results, and input the corrected user search text into the terminal. In this way, the correction unit 413 obtains the corrected user search text sent by the terminal, so that the acquisition module 410 can continue the word segmentation and determine the corresponding current feature vector.

[0108] The retrieval module 420 searches the title and the text in parallel from the feature vector library according to the current feature vector, and obtains the corresponding first and second search results. Thus, the output module 430 can generate a result similarity matrix according to the first and second search results, and obtain a total score matrix according to the result similarity matrix and the search item weight matrix, and sort the total score matrix in reverse order, and output a set number of search results to the terminal according to the sorting order and the mapping with the metadata database.

[0109] It can be seen that in this embodiment, after multiple metadata databases are mapped and transformed into home appliance industry terminology databases to generate feature vector databases, the device for information retrieval obtains the user search text, and generates corresponding feature vectors according to the correspondence between home appliance industry terminology and vector codes. It can be searched according to the feature vector database to obtain corresponding search results and output them. In this way, multiple databases can be queried concurrently, greatly improving the efficiency of retrieval. In addition, the user search text can be corrected, the user input can be optimized, the probability of missed detection can be reduced, and the priority sorting and comprehensive judgment of the query results can be increased. It is a creative application of artificial intelligence in the process of research and development and innovation in the home appliance industry, which further improves the accuracy and intelligence of information retrieval in the home appliance industry.

[0110] Combination Figure 6 The present disclosure embodiment provides a device 600 for information retrieval, including:

[0111] The processor 1000 and the memory 1001 may also include a communication interface 1002 and a bus 1003. The processor 1000, the communication interface 1002, and the memory 1001 may communicate with each other through the bus 1003. The communication interface 1002 may be used for information transmission. The processor 1000 may call the logic instructions in the memory 1001 to execute the method for information retrieval of the above embodiment.

[0112] In addition, the logic instructions in the above-mentioned memory 1001 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0113] The memory 1001 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the methods in the embodiments of the present disclosure. The processor 1000 executes functional applications and data processing by running the program instructions / modules stored in the memory 1001, that is, implements the method for information retrieval in the above method embodiment.

[0114] The memory 1001 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 1001 may include a high-speed random access memory and may also include a non-volatile memory.

[0115] An embodiment of the present disclosure provides an information retrieval device, including: a processor and a memory storing program instructions, wherein the processor is configured to execute an information retrieval method when executing the program instructions.

[0116] Combination Figure 7, the embodiment of the present disclosure provides a device 700, which can be a cloud server, including: a device body, and the above-mentioned information retrieval device 400 (600). The information retrieval device 400 (600) is installed on the device body. The installation relationship described here is not limited to placement inside the product, but also includes installation connections with other components of the product, including but not limited to physical connections, electrical connections or signal transmission connections. It can be understood by those skilled in the art that the information retrieval device 400 (600) can be adapted to a feasible device body, thereby realizing other feasible embodiments.

[0117] An embodiment of the present disclosure provides a storage medium storing program instructions, which, when run, execute the above-mentioned method for information retrieval.

[0118] An embodiment of the present disclosure provides a computer program product, which includes a computer program stored on a storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the above-mentioned method for information retrieval.

[0119] The above-mentioned storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0120] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes, or a transient storage medium.

[0121] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, individual components and functions are optional, and the order of operation may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments of the present disclosure includes the entire scope of the claims, and all available equivalents of the claims. When used in this application, although the terms "first", "second", etc. may be used in this application to describe each element, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, without changing the meaning of the description, the first element can be called the second element, and similarly, the second element can be called the first element, as long as all occurrences of the "first element" are renamed consistently and all occurrences of the "second element" are renamed consistently. The first element and the second element are both elements, but may not be the same element. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and claims, unless the context clearly indicates, the singular forms "a", "an" and "the" are intended to include the plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of one or more associated listings. In addition, when used in this application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups of these. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the presence of other identical elements in the process, method or device including the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0122] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0123] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. 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 units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0124] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for information retrieval, characterized in that include: Obtaining the current user search text input by the terminal, and determining the current feature vector matching the current user search text according to the correspondence between the industry terminology and the vector code; According to the current feature vector, two or more search items of the feature vector library are searched to obtain corresponding search results, wherein the feature vector library is generated after mapping and transforming multiple metadata libraries into industry term libraries; After analyzing and sorting the two or more search results obtained, the corresponding search results are output to the terminal.

2. The method according to claim 1, characterized in that Also includes: According to the correspondence between industry terms and vector codes, metadata databases such as information, patents, documents, and company information are mapped and transformed into industry terminology libraries to generate corresponding feature vector libraries.

3. The method according to claim 1, characterized in that Determining the current feature vector matching the current user search text includes: Segment the current user's search text to obtain one or more segmented words; When one or more of the obtained word segments exist in the industry term library, the vector code corresponding to each word segment is determined according to the correspondence between the stored industry terms and the vector code, and the corresponding current feature vector is obtained; When none of the obtained word segments exists in the industry terminology database, the current user search text is corrected with industry terminology to obtain the corrected user search text, and a current feature vector matching the corrected user search text is determined.

4. The method according to claim 3, characterized in that The modified user search text comprises: According to the obtained word segmentation, a metadata database search is performed, and the word segmentation search results involving industry terms are sent to the terminal, so that the user modifies the current user search text according to the word segmentation search results, and inputs the modified user search text into the terminal; Gets the modified user search text sent by the terminal.

5. The method according to any one of claims 1 to 4, characterized in that: Also includes: Configure the search term weight matrix and set the quantity.

6. The method according to claim 5, characterized in that Outputting the corresponding search results to the terminal includes: Generate a result similarity matrix based on two or more search results; According to the result similarity matrix and the search item weight matrix, the total score matrix is ​​obtained and sorted in reverse order; According to the sorting order of the total score matrix, a set number of search results are output to the terminal.

7. A device for information retrieval, characterized in that: include: an acquisition module configured to acquire a current user search text input by a terminal and determine a current feature vector matching the current user search text based on a correspondence between industry terms and vector codes; A search module is configured to search two or more search items of a feature vector library according to the current feature feature vector to obtain corresponding search results, wherein the feature vector library is generated after mapping and transforming multiple metadata libraries into industry term libraries; The output module is configured to analyze and sort the two or more search results obtained, and then output the corresponding search results to the terminal.

8. A device for information retrieval, the device comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to perform the method for information retrieval according to any one of claims 1 to 6 when executing the program instructions.

9. A device, characterized in that: include: Equipment body; The device for information retrieval as claimed in claim 7 or 8 is installed in the device body.

10. A storage medium storing program instructions, characterized in that: When the program instructions are executed, the method for information retrieval as described in any one of claims 1 to 6 is executed.

Images