Retrieval method and device, computer equipment and storage medium

Abstract

The invention relates to a retrieval method and device, computer equipment and a storage medium, and belongs to the technical field of data analysis, and the method comprises the steps of obtaining to-be-retrieved content based on a displayed first target window; in response to a received triggering instruction of the retrieval operation, analyzing the to-be-retrieved content according to the analysis step, and displaying information which comprises an analysis step label and is generated by an analysis result corresponding to the analysis step label in other target windows; wherein the analysis step labels comprise at least one of the following items: technical information arrangement and extraction, retrieval element recommendation and retrieval formula construction, and the analysis step labels and the analysis steps are in one-to-one correspondence. According to the method and the device, the analysis results corresponding to the analysis steps are displayed on the basis of the multiple analysis steps, the to-be-retrieved content is automatically and intelligently analyzed, the analysis results are displayed, the retrieval efficiency can be improved, the accuracy and comprehensiveness of the retrieval results can be improved, the analysis results are visually displayed to the user, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of data analysis technology, and in particular to a retrieval method, apparatus, computer equipment, and storage medium. Background Art

[0002] Patent search, a crucial aspect of the intellectual property field, aims to help inventors, businesses, or researchers quickly and accurately locate patent information related to specific technical topics. However, patent documents often utilize highly specialized technical and legal terminology. Understanding these terms and accurately constructing search formulas is a significant challenge for non-professionals. Furthermore, in practice, developing an effective search strategy requires comprehensive consideration of multiple factors, including the technical topic, search scope, and search time. For complex technical topics, it can be difficult to quickly construct a reasonable search formula. Furthermore, patent classification systems vary across countries and regions, and the same classification system can contain multiple sub-fields and cross-classifications. This complicates searchers' understanding and use of the classification system, potentially preventing them from accurately selecting classification codes and potentially missing relevant patents. After retrieving a large number of patent documents, searchers are unable to quickly and accurately analyze and evaluate the relevance, novelty, and inventiveness of these documents. This can hinder searchers' ability to intuitively extract valuable content from the vast amount of information. These issues not only impact search efficiency but can also reduce the accuracy and comprehensiveness of search results. Summary of the Invention

[0003] Based on this, it is necessary to provide a retrieval method, apparatus, computer equipment and storage medium that can improve retrieval efficiency and improve the accuracy and comprehensiveness of retrieval results in response to the above technical problems.

[0004] In a first aspect, a search method is provided, comprising:

[0005] Obtaining content to be retrieved based on the displayed first target window;

[0006] In response to receiving a trigger instruction for a search operation, parsing the searched content according to the parsing steps, and displaying information including parsing step labels and parsing results corresponding to the parsing step labels in other target windows, wherein the other target windows and the first target window are located on the same display interface;

[0007] The parsing step labels include at least one of the following: technical information organization and refinement, recommended search elements, and search formula construction. The parsing step labels correspond to the parsing steps one by one.

[0008] Optionally, also include:

[0009] Based on the display interface, display the technical information sorting and refining results of the content to be searched, and / or, the search elements generated based on the technical information sorting and refining results and the keyword phrases and / or classification numbers associated with the search elements, and / or, the search formula constructed based on the keyword phrases and / or classification numbers;

[0010] Among them, the search elements and search formula contents can be dynamically adjusted on the display interface.

[0011] Optionally, also include:

[0012] In response to receiving a trigger instruction to search using a search element, displaying search results matching the search element based on the second target window;

[0013] and / or,

[0014] In response to receiving a trigger instruction to search using a search formula, displaying search results matching the search formula based on the third target window;

[0015] The search results include a list of documents corresponding to the content to be searched.

[0016] Optional methods for organizing and refining technical information of the search content include:

[0017] Based on the similarity algorithm, the similarity between the content to be retrieved and the document content in the database is calculated to obtain the similarity calculation result;

[0018] Determine the target document based on the similarity calculation results;

[0019] Determine the technical field corresponding to the content to be searched based on the technical field description information in the target document;

[0020] Based on the differences between the content to be searched and the content of the target document, determine the core invention points corresponding to the content to be searched;

[0021] Determine the corresponding technical problems and technical effects based on the core invention points;

[0022] After sorting and refining the technical information of the search content, the methods include:

[0023] The descriptions of the technical fields, core invention points, technical problems and technical effects corresponding to the searched content are displayed under the corresponding tags.

[0024] Optional search query construction methods include:

[0025] Based on the Boolean logic search mechanism, a Boolean logic search is performed on the first target search element to generate a first limited result;

[0026] Based on the content to be searched and the semantic search mechanism, semantically sorting the first limited results to obtain the second limited results;

[0027] Compare the content of the second limited result with the description content corresponding to the technical problem and technical effect respectively;

[0028] In response to the comparison result meeting the preset criteria, defining the first target search element as a first necessary search element;

[0029] Generate a first block search formula based on the keyword phrase and / or classification number associated with the first necessary search element and a logical operator;

[0030] Generate a first combined search formula based on the plurality of first block search formulas and the logical operator;

[0031] and / or,

[0032] Perform NOT processing on the second target search element, and perform semantic search on the search content based on the semantic search mechanism to obtain the third limited result;

[0033] In response to the absence of content corresponding to the description of the technical problem and technical effect corresponding to the to-be-searched content in the third restricted result, defining the second target search element as the second necessary search element;

[0034] generating a second block search formula based on the keyword phrase and / or classification number associated with the second necessary search element and a logical operator;

[0035] generating a second combined search formula based on the plurality of second block search formulas and the logical operator;

[0036] and / or,

[0037] Based on the fourth target window of the display interface, a third combined search formula generated based on the user input information is obtained.

[0038] Optionally, after generating search elements and keyword phrases and / or classification codes associated with the search elements based on the technical information sorting and refining results, the method further includes:

[0039] A search factor table is generated based on the search factors generated from the results of the technical information collation and refinement, as well as the keyword phrases and / or classification numbers associated with the search factors. The search factor table can be exported.

[0040] Optionally, also include:

[0041] The keyword group in the analysis result corresponding to the analysis step label is highlighted in the display interface.

[0042] In a second aspect, a retrieval device is provided, comprising:

[0043] An acquisition module, configured to acquire content to be retrieved based on the displayed first target window;

[0044] a parsing module, configured to, in response to receiving a trigger instruction for a search operation, parse the content to be searched according to the parsing steps, and display information including parsing step labels and parsing results corresponding to the parsing step labels in other target windows, wherein the other target windows are located on the same display interface as the first target window;

[0045] The parsing step labels include at least one of the following: technical information organization and refinement, recommended search elements, and search formula construction. The parsing step labels correspond to the parsing steps one by one.

[0046] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are performed:

[0047] Obtaining content to be retrieved based on the displayed first target window;

[0048] In response to receiving a trigger instruction for a search operation, parsing the searched content according to the parsing steps, and displaying information including parsing step labels and parsing results corresponding to the parsing step labels in other target windows, wherein the other target windows and the first target window are located on the same display interface;

[0049] The parsing step labels include at least one of the following: technical information organization and refinement, recommended search elements, and search formula construction. The parsing step labels correspond to the parsing steps one by one.

[0050] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0051] Obtaining content to be retrieved based on the displayed first target window;

[0052] In response to receiving a trigger instruction for a search operation, parsing the searched content according to the parsing steps, and displaying information including parsing step labels and parsing results corresponding to the parsing step labels in other target windows, wherein the other target windows and the first target window are located on the same display interface;

[0053] The parsing step labels include at least one of the following: technical information organization and refinement, recommended search elements, and search formula construction. The parsing step labels correspond to the parsing steps one by one.

[0054] In a fifth aspect, a computer program product is provided, the computer program product comprising a computer program, wherein when the computer program is executed by a processor, the following steps are implemented:

[0055] Obtaining content to be retrieved based on the displayed first target window;

[0056] In response to receiving a trigger instruction for a search operation, parsing the searched content according to the parsing steps, and displaying information including parsing step labels and parsing results corresponding to the parsing step labels in other target windows, wherein the other target windows and the first target window are located on the same display interface;

[0057] The parsing step labels include at least one of the following: technical information organization and refinement, recommended search elements, and search formula construction. The parsing step labels correspond to the parsing steps one by one.

[0058] The above-mentioned retrieval method, apparatus, computer equipment and storage medium include: obtaining the content to be retrieved based on the displayed first target window; in response to receiving a trigger instruction of a retrieval operation, parsing the content to be retrieved according to the parsing step, and displaying the parsing step label and the information generated by the parsing result corresponding to the parsing step label in other target windows, wherein the other target windows and the first target window are located on the same display interface; wherein the parsing step label includes at least one of the following: technical information organization and refinement, recommended retrieval elements and construction of retrieval formulas, and the parsing step label and the parsing step correspond one to one. This application is based on multiple parsing steps and the parsing results corresponding to the parsing steps for display. By automatically and intelligently analyzing the content to be retrieved and displaying the analysis results, the retrieval efficiency and the accuracy and comprehensiveness of the retrieval results can be improved, and the analysis results can be intuitively displayed to the user to enhance the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A diagram of an application environment of a retrieval method in one embodiment;

[0060] Figure 2 1 is a flow chart of a retrieval method in one embodiment;

[0061] Figure 3 A schematic diagram of a display interface of a search method in one embodiment;

[0062] Figure 4 A schematic diagram of another display interface of a retrieval method in one embodiment;

[0063] Figure 5 is a structural block diagram of a retrieval device in one embodiment;

[0064] Figure 6 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0065] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0066] It should be understood that in the description of this application, unless the context clearly requires otherwise, words such as "include", "comprises", and the like throughout the specification should be interpreted as inclusive rather than exclusive or exhaustive; that is, as "including but not limited to".

[0067] It should also be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, the meaning of "plurality" is two or more.

[0068] It should be noted that the terms "S1", "S2", etc. are used only for the purpose of describing the steps and do not specifically refer to the order or sequence, nor are they used to limit this application. They are merely for the convenience of describing the method of this application and should not be understood as indicating the order of the steps. In addition, the technical solutions between the various embodiments can be combined with each other, but this must be based on the fact that ordinary technicians in this field can implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0069] The search method provided in this application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with a data processing platform provided on the server 104 via a network. The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0070] In one embodiment, Figure 2 As shown, a retrieval method is provided, which is applied to Figure 1 The following steps are used as an example to illustrate the terminal:

[0071] S1: Based on the displayed first target window, obtain the content to be retrieved;

[0072] S2: In response to receiving a trigger instruction for a search operation, the search content is parsed according to the parsing steps, and information including parsing step labels and parsing results corresponding to the parsing step labels are displayed in other target windows, wherein the other target windows and the first target window are located on the same display interface; wherein the parsing step labels include at least one of the following: technical information organization and refinement, recommended search elements, and construction of search formulas, and the parsing step labels and parsing steps correspond one to one.

[0073] It should be noted that if Figure 3 As shown, the target window refers to the area in the user display interface for displaying and operating applications, files, folders and other contents. The first target window refers to the area for receiving and displaying the content to be retrieved. The content to be displayed refers to the initial technical solution description content input by the user (such as patent text, paper text, etc.), such as "a water storage flower pot that does not require frequent watering and is easy to use... The water storage flower pot of the present invention can reduce the number of times the flower pot is watered, and the flower pot is easy to use". The first target window also displays the number of words and the limited number of words corresponding to the initial solution description content, as well as the search operation label (such as re-refining the search elements, etc.). Clicking the search operation label can trigger the corresponding instruction; the size of the first target window can be dynamically adjusted; the parsing step label and the parsing step The information generated by the analysis results corresponding to the step label is displayed in its corresponding window; technical information collation and refinement refers to the disassembly of the initial technical solution description content to extract information such as technical fields, technical solutions, technical problems and core invention points; recommended search elements refer to the use of AI to recommend search elements and keyword phrases and / or classification numbers associated with the search elements, including extracting components, connection relationships or method steps closely related to the technical solution to form search elements based on the relevant content of the technical field and core invention points, and refining and expanding keywords and classification numbers for each search element; constructing a search formula refers to a search formula constructed based on the search elements and keyword phrases and / or classification numbers associated with the search elements, or a search formula generated by instructions entered by the user.

[0074] In the above method, by analyzing the content of the initial technical solution description through the above parsing steps, the corresponding search formula can be quickly determined, thereby improving the efficiency of patent search.

[0075] In some embodiments, the method further comprises:

[0076] Based on the display interface, display the technical information sorting and refining results of the content to be searched, and / or, the search elements generated based on the technical information sorting and refining results and the keyword phrases and / or classification numbers associated with the search elements, and / or, the search formula constructed based on the keyword phrases and / or classification numbers;

[0077] Among them, the search elements and search formula contents can be dynamically adjusted on the display interface.

[0078] Specifically, such as Figure 3 As shown, the technical information collation and refinement results may include descriptions of the technical field, core invention points, technical problems and technical effects. For example, if the technical field is a water storage flower pot, the search factor may be a flower pot, etc. The keyword group associated with the search factor refers to the factor word, and the classification number may be an IPC classification number, where the factor words include pot, flower container, etc., and the IPC classification number includes A01G9 / 02, etc. The search formula may include "(inner pot or internal pot or "inner pot") / TAC", etc. The above-mentioned technical information collation and refinement results, the search factors generated based on the technical information collation and refinement results, the keyword groups and / or classification numbers associated with the search factors, and the search formula constructed based on the keyword groups and / or classification numbers are displayed in different windows respectively.

[0079] In some embodiments, the method further comprises:

[0080] In response to receiving a trigger instruction to search using a search element, displaying search results matching the search element based on the second target window;

[0081] and / or,

[0082] In response to receiving a trigger instruction to search using a search formula, displaying search results matching the search formula based on the third target window;

[0083] The search results include a list of documents corresponding to the content to be searched.

[0084] Specifically, the second target window and the third target window can be the same window or different windows. The specific interface window layout can be set according to actual needs, such as Figure 4 As shown, the trigger instruction for searching by search elements refers to the instruction triggered by the user clicking on the search elements or the keyword phrases and / or classification numbers associated with the search elements. For example, by clicking A01G9 / 02, a second target window will pop up to display a list of patent documents related to the content to be searched. The trigger instruction for searching by search formula refers to the instruction triggered by the user clicking on the search formula construction, and a third target window will pop up to display a list of patent documents related to the content to be searched. The search results are previewed based on the second target window and the third target window.

[0085] In some specific implementations, the method for organizing and refining technical information of the searched content includes:

[0086] Based on a similarity algorithm, the similarity between the content to be retrieved and the document content in the database is calculated to obtain a similarity calculation result. The similarity algorithm may include a sentence vector representation method, that is, representing the text as a vector and using the distance between the vectors to measure the text similarity. Other similarity algorithms for measuring text similarity may also be used for calculation. The above method is a commonly used method, and its specific calculation process will not be repeated here.

[0087] Determine the target document based on the similarity calculation results, that is, compare and sort the similarity calculation results between multiple documents and the content to be searched, and define the document with the greatest similarity as the target document;

[0088] Determine the technical field corresponding to the content to be searched based on the technical field description information in the target document;

[0089] Based on the differences between the content to be searched and the content of the target document, the core invention point corresponding to the content to be searched is determined. The differences here can be determined by inputting the content to be searched and the content of the target document into a trained large model (such as a text language large model - LLM, etc.), and the output of the large model is used to determine the differences, and the core invention point corresponding to the content to be searched is defined as the difference;

[0090] According to the core invention point, the corresponding technical problem and technical effect are determined. The corresponding technical problem and technical effect can be inferred based on the core invention point and the initial solution. For example, the core invention point is that a water storage cavity is left between the bottom of the inner basin and the bottom of the outer basin, a water absorption strip is installed in the cavity, and a water permeable hole is set in the bottom of the inner basin. The technical problem is that the flower pot is frequently watered and inconvenient to use. The technical effect is that the flower pot is watered less frequently and is more convenient to use.

[0091] After sorting and refining the technical information of the search content, the method includes:

[0092] The description content of the technical field, core invention point, technical problem and technical effect corresponding to the search content is displayed under the corresponding label. The label refers to the technical field, core invention point, technical problem and technical effect, and its description content is the decomposition result of the search content.

[0093] In some specific embodiments, the method for constructing a search formula includes:

[0094] Based on a Boolean logic search mechanism, a Boolean logic search is performed on the first target search element to generate a first limited result. The Boolean logic search mechanism is a method of connecting various search terms using Boolean logic operators and then having a computer perform corresponding logical operations to find the required information. This is a commonly used method, and therefore, the specific process of performing the Boolean logic search on the first target search element will not be described in detail here.

[0095] Based on the content to be retrieved and the semantic retrieval mechanism, the first limited results are semantically sorted to obtain the second limited results, wherein the semantic retrieval mechanism refers to the technology of using natural language processing (NLP) and artificial intelligence (AI) to understand the semantics of the search query to provide more accurate and relevant search results. Its specific retrieval method is a common method, and the specific retrieval process is not repeated here. This step is specifically based on Boolean retrieval, for the retrieval results (i.e., the first limited results), selecting a suitable semantic benchmark and performing semantic sorting. Using a semantic engine, all the retrieval results are sorted according to a certain benchmark, so that the highly relevant content is ranked first and the irrelevant content is ranked last, so as to obtain the second limited results, which include multiple documents with high relevance;

[0096] Comparing the content of the second limited results with the descriptions of the technical problems and technical effects respectively, wherein the specific comparison method includes: calculating similarities between the technical problems obtained by decomposing the content to be searched and the documents in the second limited results, or calculating similarities between the technical effects obtained by decomposing the content to be searched and the documents in the second limited results, respectively, to obtain corresponding first similarity calculation results and second similarity calculation results;

[0097] In response to the comparison result meeting a preset standard, defining the first target search element as a first necessary search element, wherein the preset standard includes that the second similarity calculation result is greater than a first preset value, and / or, both the first similarity calculation result and the second similarity calculation result are greater than a second preset value, and / or, the average value of the sum of the first similarity calculation result and the second similarity calculation result is greater than a third preset value, wherein the first preset value, the second preset value, and the third preset value can all be set according to actual needs, such as 98%, 80%, and 60%, that is, when the second similarity calculation result is greater than 98%, and / or, both the first similarity calculation result and the second similarity calculation result are greater than 80%, and / or, the average value of the sum of the first similarity calculation result and the second similarity calculation result is greater than 60%, defining the first target search element as the first necessary search element;

[0098] generating a first block search formula based on the keyword phrase and / or classification number associated with the first necessary search element and a logical operator, wherein the logical operator may include "AND", "NOT", "OR", etc., and a search formula may be constructed for the keyword phrase and / or classification number through the logical operator to generate a block search formula;

[0099] Based on the plurality of first block search expressions and the logical operators, a first combined search expression is generated, that is, the block search expressions are arranged and combined using the logical operators to generate the combined search expression;

[0100] and / or,

[0101] Perform NOT processing on the second target search element, and perform semantic search on the search content based on the semantic search mechanism to obtain the third limited result. NOT processing refers to the negation of a condition or statement in data processing and analysis. Here, it refers to NOTing the second target search element to semantically sort the search content;

[0102] In response to the absence of content corresponding to the description of the technical problem and technical effect corresponding to the to-be-searched content in the third restricted results, the second target search element is defined as the second necessary search element, that is, if the description of the corresponding technical problem and technical effect does not exist in the semantic ranking results, the second necessary search element is the search element that needs to be selected;

[0103] generating a second block search formula based on the keyword phrase and / or classification number associated with the second necessary search element and a logical operator, wherein the logical operator may include "AND", "NOT", "OR", etc., and a search formula may be constructed for the keyword phrase and / or classification number through the logical operator to generate a block search formula;

[0104] Based on the plurality of second block search expressions and the logical operators, a second combined search expression is generated, that is, the block search expressions are arranged and combined using the logical operators to generate the combined search expression;

[0105] and / or,

[0106] Based on the fourth target window of the display interface, a third combined search formula generated based on the user input information is obtained, wherein, Figure 3As shown, the fourth target window includes a search input box, and its corresponding input modes include command search and advanced search. Command search is generally a search method provided for users with rich search experience, and advanced search is generally a search method provided for people with less search experience. Users can choose the search input method independently, or the system can recommend a corresponding mode based on the user's years of use and / or the number of times the search method is used, including: obtaining a user login ID and a user terminal ID, determining a first duration for the target user to use the target search method and a second duration for the target search method to be used on the target user terminal, in response to the first duration and the second duration being greater than a preset value, giving priority to displaying and recommending the target search method, in response to the first duration being greater than the preset value and the second duration being less than or equal to the preset value, giving priority to displaying and recommending the target search method, in response to the first duration being less than or equal to the preset value and the second duration being greater than the preset value If a value is set, other search methods except the target search method are recommended for display. In response to the first time length being less than or equal to the preset value and the second time length being less than or equal to the preset value, other search methods except the target search method are recommended for display. In response to the first time length being equal to 0 and the second time length being greater than the preset value, the target search method is recommended for display. The preset value is a non-zero constant and is less than half of the total time length of the search system being used. The specific value can be set according to actual needs. For example, if the same user has used the system for more than 3 years and / or the number of times the command search has been used exceeds 200 times, the command search interface will be displayed in priority on the display interface. The user can also select the simplified mode and the intelligent recommendation mode according to needs. A third combined search formula can be generated according to the information input by the user. The first combined search formula, the second combined search formula and the third combined search formula generated above can all be edited according to needs.

[0107] In some specific embodiments, after generating search elements and keyword phrases and / or classification codes associated with the search elements based on the technical information sorting and refining results, the method further includes:

[0108] like Figure 3 As shown, a search element table is generated based on the search elements generated based on the results of technical information collation and refinement, as well as the keyword phrases and / or classification numbers associated with the search elements. The search element table can be exported, and the export button is the "Export Search Element Table" in the display interface.

[0109] In some embodiments, the method further comprises:

[0110] The keyword group in the analysis result corresponding to the analysis step label is highlighted in the display interface, such as Figure 3 As shown, the keyword group may include water storage flower pots, etc., and the keyword group is highlighted to increase the speed of disassembling the technical solution and provide users with more intuitive information prompts.

[0111] The above-mentioned retrieval method includes: obtaining the content to be retrieved based on the displayed first target window; in response to receiving the trigger instruction of the retrieval operation, parsing the content to be retrieved according to the parsing step, and displaying the parsing step label and the information generated by the parsing result corresponding to the parsing step label in other target windows, wherein the other target windows and the first target window are located on the same display interface; wherein the parsing step label includes at least one of the following: technical information organization and refinement, recommended search elements and construction of search formulas, and the parsing step label and the parsing step correspond one to one. This application is based on multiple parsing steps and the parsing results corresponding to the parsing steps for display. By automatically and intelligently analyzing the content to be retrieved and displaying the analysis results, the retrieval efficiency and the accuracy and comprehensiveness of the retrieval results can be improved, and the analysis results can be intuitively displayed to the user to enhance the user experience.

[0112] It should be understood that although Figure 2 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 2 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0113] In one embodiment, Figure 5 As shown, a retrieval device is provided, including: an acquisition module and a parsing module, wherein:

[0114] An acquisition module, configured to acquire content to be retrieved based on the displayed first target window;

[0115] a parsing module, configured to, in response to receiving a trigger instruction for a search operation, parse the content to be searched according to the parsing steps, and display information including parsing step labels and parsing results corresponding to the parsing step labels in other target windows, wherein the other target windows are located on the same display interface as the first target window;

[0116] The parsing step labels include at least one of the following: technical information organization and refinement, recommended search elements, and search formula construction. The parsing step labels correspond to the parsing steps one by one.

[0117] As a preferred implementation, in an embodiment of the present invention, the retrieval device further includes a display module, which is specifically configured to:

[0118] Based on the display interface, display the technical information sorting and refining results of the content to be searched, and / or, the search elements generated based on the technical information sorting and refining results and the keyword phrases and / or classification numbers associated with the search elements, and / or, the search formula constructed based on the keyword phrases and / or classification numbers;

[0119] Among them, the search elements and search formula contents can be dynamically adjusted on the display interface.

[0120] As a preferred implementation, in the embodiment of the present invention, the display module is further used to:

[0121] In response to receiving a trigger instruction to search using a search element, displaying search results matching the search element based on the second target window;

[0122] and / or,

[0123] In response to receiving a trigger instruction to search using a search formula, displaying search results matching the search formula based on the third target window;

[0124] The search results include a list of documents corresponding to the content to be searched.

[0125] As a preferred implementation, in an embodiment of the present invention, the parsing module is specifically used to:

[0126] Based on the similarity algorithm, the similarity between the content to be retrieved and the document content in the database is calculated to obtain the similarity calculation result;

[0127] Determine the target document based on the similarity calculation results;

[0128] Determine the technical field corresponding to the content to be searched based on the technical field description information in the target document;

[0129] Based on the differences between the content to be searched and the content of the target document, determine the core invention points corresponding to the content to be searched;

[0130] Determine the corresponding technical problems and technical effects based on the core invention points;

[0131] After sorting and refining the technical information of the search content, the methods include:

[0132] The descriptions of the technical fields, core invention points, technical problems and technical effects corresponding to the searched content are displayed under the corresponding tags.

[0133] As a preferred implementation, in an embodiment of the present invention, the parsing module is further configured to:

[0134] Based on the Boolean logic search mechanism, a Boolean logic search is performed on the first target search element to generate a first limited result;

[0135] Based on the content to be searched and the semantic search mechanism, semantically sorting the first limited results to obtain the second limited results;

[0136] Compare the content of the second limited result with the description content corresponding to the technical problem and technical effect respectively;

[0137] In response to the comparison result meeting the preset criteria, defining the first target search element as a first necessary search element;

[0138] Generate a first block search formula based on the keyword phrase and / or classification number associated with the first necessary search element and a logical operator;

[0139] Generate a first combined search formula based on the plurality of first block search formulas and the logical operator;

[0140] and / or,

[0141] Perform NOT processing on the second target search element, and perform semantic search on the search content based on the semantic search mechanism to obtain the third limited result;

[0142] In response to the absence of content corresponding to the description of the technical problem and technical effect corresponding to the to-be-searched content in the third restricted result, defining the second target search element as the second necessary search element;

[0143] generating a second block search formula based on the keyword phrase and / or classification number associated with the second necessary search element and a logical operator;

[0144] generating a second combined search formula based on the plurality of second block search formulas and the logical operator;

[0145] and / or,

[0146] Based on the fourth target window of the display interface, a third combined search formula generated based on the user input information is obtained.

[0147] As a preferred implementation, in an embodiment of the present invention, the parsing module is further configured to:

[0148] A search factor table is generated based on the search factors generated from the results of the technical information collation and refinement, as well as the keyword phrases and / or classification numbers associated with the search factors. The search factor table can be exported.

[0149] As a preferred implementation, in the embodiment of the present invention, the display module is further used to:

[0150] The keyword group in the analysis result corresponding to the analysis step label is highlighted in the display interface.

[0151] The specific definition of the retrieval device can be found in the definition of the retrieval method above and will not be repeated here. The various modules in the above-mentioned retrieval device can be implemented in whole or in part through software, hardware, or a combination thereof. The above-mentioned modules can be embedded in or independent of the processor of the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each of the above modules.

[0152] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a retrieval method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0153] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0154] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are performed:

[0155] S1: Based on the displayed first target window, obtain the content to be retrieved;

[0156] S2: In response to receiving a trigger instruction for a search operation, parsing the searched content according to the parsing steps, and displaying information including parsing step labels and parsing results corresponding to the parsing step labels in other target windows, wherein the other target windows and the first target window are located on the same display interface;

[0157] The parsing step labels include at least one of the following: technical information organization and refinement, recommended search elements, and search formula construction. The parsing step labels correspond to the parsing steps one by one.

[0158] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0159] Based on the display interface, display the technical information sorting and refining results of the content to be searched, and / or, the search elements generated based on the technical information sorting and refining results and the keyword phrases and / or classification numbers associated with the search elements, and / or, the search formula constructed based on the keyword phrases and / or classification numbers;

[0160] Among them, the search elements and search formula contents can be dynamically adjusted on the display interface.

[0161] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0162] In response to receiving a trigger instruction to search using a search element, displaying search results matching the search element based on the second target window;

[0163] and / or,

[0164] In response to receiving a trigger instruction to search using a search formula, displaying search results matching the search formula based on the third target window;

[0165] The search results include a list of documents corresponding to the content to be searched.

[0166] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0167] Based on the similarity algorithm, the similarity between the content to be retrieved and the document content in the database is calculated to obtain the similarity calculation result;

[0168] Determine the target document based on the similarity calculation results;

[0169] Determine the technical field corresponding to the content to be searched based on the technical field description information in the target document;

[0170] Based on the differences between the content to be searched and the content of the target document, determine the core invention points corresponding to the content to be searched;

[0171] Determine the corresponding technical problems and technical effects based on the core invention points;

[0172] After sorting and refining the technical information of the search content, the methods include:

[0173] The descriptions of the technical fields, core invention points, technical problems and technical effects corresponding to the searched content are displayed under the corresponding tags.

[0174] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0175] Based on the Boolean logic search mechanism, a Boolean logic search is performed on the first target search element to generate a first limited result;

[0176] Based on the content to be searched and the semantic search mechanism, semantically sorting the first limited results to obtain the second limited results;

[0177] Compare the content of the second limited result with the description content corresponding to the technical problem and technical effect respectively;

[0178] In response to the comparison result meeting the preset criteria, defining the first target search element as a first necessary search element;

[0179] Generate a first block search formula based on the keyword phrase and / or classification number associated with the first necessary search element and a logical operator;

[0180] Generate a first combined search formula based on the plurality of first block search formulas and the logical operator;

[0181] and / or,

[0182] Perform NOT processing on the second target search element, and perform semantic search on the search content based on the semantic search mechanism to obtain the third limited result;

[0183] In response to the absence of content corresponding to the description of the technical problem and technical effect corresponding to the to-be-searched content in the third restricted result, defining the second target search element as the second necessary search element;

[0184] generating a second block search formula based on the keyword phrase and / or classification number associated with the second necessary search element and a logical operator;

[0185] generating a second combined search formula based on the plurality of second block search formulas and the logical operator;

[0186] and / or,

[0187] Based on the fourth target window of the display interface, a third combined search formula generated based on the user input information is obtained.

[0188] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0189] A search factor table is generated based on the search factors generated from the results of the technical information collation and refinement, as well as the keyword phrases and / or classification numbers associated with the search factors. The search factor table can be exported.

[0190] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0191] The keyword group in the analysis result corresponding to the analysis step label is highlighted in the display interface.

[0192] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0193] S1: Based on the displayed first target window, obtain the content to be retrieved;

[0194] S2: In response to receiving a trigger instruction for a search operation, parsing the searched content according to the parsing steps, and displaying information including parsing step labels and parsing results corresponding to the parsing step labels in other target windows, wherein the other target windows and the first target window are located on the same display interface;

[0195] The parsing step labels include at least one of the following: technical information organization and refinement, recommended search elements, and search formula construction. The parsing step labels correspond to the parsing steps one by one.

[0196] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0197] Based on the display interface, display the technical information sorting and refining results of the content to be searched, and / or, the search elements generated based on the technical information sorting and refining results and the keyword phrases and / or classification numbers associated with the search elements, and / or, the search formula constructed based on the keyword phrases and / or classification numbers;

[0198] Among them, the search elements and search formula contents can be dynamically adjusted on the display interface.

[0199] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0200] In response to receiving a trigger instruction to search using a search element, displaying search results matching the search element based on the second target window;

[0201] and / or,

[0202] In response to receiving a trigger instruction to search using a search formula, displaying search results matching the search formula based on the third target window;

[0203] The search results include a list of documents corresponding to the content to be searched.

[0204] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0205] Based on the similarity algorithm, the similarity between the content to be retrieved and the document content in the database is calculated to obtain the similarity calculation result;

[0206] Determine the target document based on the similarity calculation results;

[0207] Determine the technical field corresponding to the content to be searched based on the technical field description information in the target document;

[0208] Based on the differences between the content to be searched and the content of the target document, determine the core invention points corresponding to the content to be searched;

[0209] Determine the corresponding technical problems and technical effects based on the core invention points;

[0210] After sorting and refining the technical information of the search content, the methods include:

[0211] The descriptions of the technical fields, core invention points, technical problems and technical effects corresponding to the searched content are displayed under the corresponding tags.

[0212] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0213] Based on the Boolean logic search mechanism, a Boolean logic search is performed on the first target search element to generate a first limited result;

[0214] Based on the content to be searched and the semantic search mechanism, semantically sorting the first limited results to obtain the second limited results;

[0215] Compare the content of the second limited result with the description content corresponding to the technical problem and technical effect respectively;

[0216] In response to the comparison result meeting the preset criteria, defining the first target search element as a first necessary search element;

[0217] Generate a first block search formula based on the keyword phrase and / or classification number associated with the first necessary search element and a logical operator;

[0218] Generate a first combined search formula based on the plurality of first block search formulas and the logical operator;

[0219] and / or,

[0220] Perform NOT processing on the second target search element, and perform semantic search on the search content based on the semantic search mechanism to obtain the third limited result;

[0221] In response to the absence of content corresponding to the description of the technical problem and technical effect corresponding to the to-be-searched content in the third restricted result, defining the second target search element as the second necessary search element;

[0222] generating a second block search formula based on the keyword phrase and / or classification number associated with the second necessary search element and a logical operator;

[0223] generating a second combined search formula based on the plurality of second block search formulas and the logical operator;

[0224] and / or,

[0225] Based on the fourth target window of the display interface, a third combined search formula generated based on the user input information is obtained.

[0226] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0227] A search factor table is generated based on the search factors generated from the results of the technical information collation and refinement, as well as the keyword phrases and / or classification numbers associated with the search factors. The search factor table can be exported.

[0228] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0229] The keyword group in the analysis result corresponding to the analysis step label is highlighted in the display interface.

[0230] In one embodiment, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the following steps:

[0231] S1: Based on the displayed first target window, obtain the content to be retrieved;

[0232] S2: In response to receiving a trigger instruction for a search operation, parsing the searched content according to the parsing steps, and displaying information including parsing step labels and parsing results corresponding to the parsing step labels in other target windows, wherein the other target windows and the first target window are located on the same display interface;

[0233] The parsing step labels include at least one of the following: technical information organization and refinement, recommended search elements, and search formula construction. The parsing step labels correspond to the parsing steps one by one.

[0234] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0235] Based on the display interface, display the technical information sorting and refining results of the content to be searched, and / or, the search elements generated based on the technical information sorting and refining results and the keyword phrases and / or classification numbers associated with the search elements, and / or, the search formula constructed based on the keyword phrases and / or classification numbers;

[0236] Among them, the search elements and search formula contents can be dynamically adjusted on the display interface.

[0237] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0238] In response to receiving a trigger instruction to search using a search element, displaying search results matching the search element based on the second target window;

[0239] and / or,

[0240] In response to receiving a trigger instruction to search using a search formula, displaying search results matching the search formula based on the third target window;

[0241] The search results include a list of documents corresponding to the content to be searched.

[0242] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0243] Based on the similarity algorithm, the similarity between the content to be retrieved and the document content in the database is calculated to obtain the similarity calculation result;

[0244] Determine the target document based on the similarity calculation results;

[0245] Determine the technical field corresponding to the content to be searched based on the technical field description information in the target document;

[0246] Based on the differences between the content to be searched and the content of the target document, determine the core invention points corresponding to the content to be searched;

[0247] Determine the corresponding technical problems and technical effects based on the core invention points;

[0248] After sorting and refining the technical information of the search content, the methods include:

[0249] The descriptions of the technical fields, core invention points, technical problems and technical effects corresponding to the searched content are displayed under the corresponding tags.

[0250] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0251] Based on the Boolean logic search mechanism, a Boolean logic search is performed on the first target search element to generate a first limited result;

[0252] Based on the content to be searched and the semantic search mechanism, semantically sorting the first limited results to obtain the second limited results;

[0253] Compare the content of the second limited result with the description content corresponding to the technical problem and technical effect respectively;

[0254] In response to the comparison result meeting the preset criteria, defining the first target search element as a first necessary search element;

[0255] Generate a first block search formula based on the keyword phrase and / or classification number associated with the first necessary search element and a logical operator;

[0256] Generate a first combined search formula based on the plurality of first block search formulas and the logical operator;

[0257] and / or,

[0258] Perform NOT processing on the second target search element, and perform semantic search on the search content based on the semantic search mechanism to obtain the third limited result;

[0259] In response to the absence of content corresponding to the description of the technical problem and technical effect corresponding to the to-be-searched content in the third restricted result, defining the second target search element as the second necessary search element;

[0260] generating a second block search formula based on the keyword phrase and / or classification number associated with the second necessary search element and a logical operator;

[0261] generating a second combined search formula based on the plurality of second block search formulas and the logical operator;

[0262] and / or,

[0263] Based on the fourth target window of the display interface, a third combined search formula generated based on the user input information is obtained.

[0264] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0265] A search factor table is generated based on the search factors generated from the results of the technical information collation and refinement, as well as the keyword phrases and / or classification numbers associated with the search factors. The search factor table can be exported.

[0266] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0267] The keyword group in the analysis result corresponding to the analysis step label is highlighted in the display interface.

[0268] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0269] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0270] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the scope of the present application, and such modifications and improvements are all within the scope of protection of the present application.

Claims

1. A retrieval method, characterized in that: The method comprises: Obtaining content to be retrieved based on the displayed first target window; In response to receiving a trigger instruction for a search operation, parsing the content to be searched according to the parsing step, and displaying information including a parsing step label and parsing results corresponding to the parsing step label in another target window, wherein the other target window and the first target window are located on the same display interface; The parsing step labels include at least one of the following: technical information organization and refinement, recommended search elements, and search formula construction, and the parsing step labels correspond to the parsing steps in a one-to-one manner.

2. The retrieval method according to claim 1, wherein The method further comprises: Based on the display interface, display the technical information sorting and refining results of the content to be searched, and / or the search elements generated based on the technical information sorting and refining results and the keyword phrases and / or classification numbers associated with the search elements, and / or the search formula constructed based on the keyword phrases and / or classification numbers; The search elements and the content of the search formula can be dynamically adjusted on the display interface.

3. The retrieval method according to claim 1, wherein: The method further comprises: In response to receiving a trigger instruction to search using the search element, displaying search results matching the search element based on the second target window; and / or, In response to receiving a trigger instruction to perform a search using the search formula, displaying search results matching the search formula based on a third target window; The search results include a list of documents corresponding to the content to be searched.

4. The retrieval method according to claim 1 or 2, characterized in that The method for collating and refining technical information of the content to be retrieved includes: Calculate the similarity between the content to be retrieved and the document content in the database based on a similarity algorithm to obtain a similarity calculation result; Determining a target document according to the similarity calculation result; Determine the technical field corresponding to the content to be searched based on the technical field description information in the target document; Determining the core invention point corresponding to the content to be retrieved based on the differences between the content to be retrieved and the content of the target document; Determine the corresponding technical problems and technical effects based on the core invention points; After collating and refining the technical information of the content to be retrieved, the method includes: The description of the technical field, core invention point, technical problem and technical effect corresponding to the content to be retrieved is displayed under the corresponding label.

5. The retrieval method according to claim 2, wherein: The method for constructing the search formula includes: Based on the Boolean logic search mechanism, a Boolean logic search is performed on the first target search element to generate a first limited result; Semantically sorting the first limited results based on the content to be searched and the semantic search mechanism to obtain second limited results; Comparing the content of the second limited result with the description content corresponding to the technical problem and technical effect respectively; In response to the comparison result meeting a preset standard, defining the first target search element as a first necessary search element; Generate a first block search formula based on the keyword phrase and / or classification number associated with the first necessary search element and a logical operator; generating a first combined search formula based on the plurality of first block search formulas and logical operators; and / or, Performing NOT processing on the second target search element, and performing semantic search on the content to be searched based on the semantic search mechanism to obtain a third limited result; In response to the absence of content corresponding to the description of the technical problem and technical effect corresponding to the to-be-searched content in the third restricted result, defining the second target search element as a second necessary search element; generating a second block search formula based on the keyword phrase and / or classification number associated with the second necessary search element and a logical operator; generating a second combined search formula based on the plurality of second-block search formulas and logical operators; and / or, Based on the fourth target window of the display interface, a third combined search formula generated based on user input information is obtained.

6. The retrieval method according to claim 2, wherein: After generating search elements and keyword phrases and / or classification codes associated with the search elements based on the technical information sorting and refining results, the method further includes: A search factor table is generated based on the search factors generated from the results of the technical information sorting and refining, and the keyword phrases and / or classification numbers associated with the search factors. The search factor table can be exported.

7. The search method according to claim 1, wherein: The method further comprises: The keyword group in the analysis result corresponding to the analysis step label is highlighted on the display interface.

8. A search device, characterized in that: The device comprises: An acquisition module, configured to acquire content to be retrieved based on the displayed first target window; a parsing module, configured to, in response to receiving a trigger instruction for a search operation, parse the content to be searched according to the parsing steps, and display information including parsing step labels and parsing results corresponding to the parsing step labels in another target window, wherein the other target window and the first target window are located on the same display interface; The parsing step labels include at least one of the following: technical information organization and refinement, recommended search elements, and search formula construction, and the parsing step labels correspond to the parsing steps in a one-to-one manner.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

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

Images