A method, device, equipment and storage medium for recommending search conditions
By generating and adjusting the recommendation methods of search conditions, the problem of inconvenience in inputting expansion words and classification numbers in search is solved, and the recommendation of optimized search conditions is realized, which improves the search efficiency and accuracy and enhances the user experience.
Patent Information
- Application Number
- CN201910824296.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2019-09-02
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2039-09-02
AI Technical Summary
In the existing patent search methods, it is difficult for searchers to effectively enter extension words and classification numbers, resulting in inaccurate search results and a lot of time is required to obtain the required patent documents.
Provide a recommendation method for search conditions, by obtaining the search conditions entered by the user, generating recommended search elements, including keywords and classification numbers, and generating optimized search conditions based on user adjustments to further optimize the search results.
It improves the search efficiency and accuracy, reduces the time and difficulties of users during the search process, and enhances the user's search experience.
Smart Images

Figure CN112445942B_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present invention relate to retrieval technology, and in particular to a method, device, equipment and storage medium for recommending retrieval conditions. Background Art
[0002] Retrieval is the core function of IT systems, search engines or SaaS applications that provide data services. The search result page generated for different search keywords or search formulas allows users to preview the results, operate or optimize the search formula for further search. Patent search is the process of selecting documents or information that meet a specific requirement from a large number of patent documents or patent databases based on one or more characteristics. It plays a vital role in the growth of enterprises and the saving and improvement of global productivity.
[0003] In the existing patent search, the search personnel can enter relevant keywords or a piece of patent document content as the search conditions to obtain relevant patent documents. Generally speaking, the patent documents obtained by the search personnel in the search are most likely not the patent documents that the search personnel want to obtain. This is because there are a large number of other extended words with similar semantics to the keywords. The search personnel also need to add these words to the search conditions, but this is not easy and inconvenient for the search personnel. In addition, keywords may have completely different meanings in different fields. The search personnel will also obtain a large number of patent documents that are not related to the field during the search. For this reason, it is also necessary to add classification numbers to the search conditions, but this is also not easy and inconvenient for the search personnel, especially for non-professional search personnel. Therefore, through the existing search methods, the search personnel may need to spend a lot of time to conduct a more comprehensive search and obtain the patent documents they want. Summary of the invention
[0004] The embodiments of the present invention provide a method, apparatus, device and storage medium for recommending search conditions, so as to realize the recommendation function of optimizing search conditions and enhance the user search experience.
[0005] To achieve this purpose, an embodiment of the present invention provides a method for recommending search conditions, the method comprising:
[0006] Obtaining a first search condition input by a user;
[0007] generating a first recommended search element according to the first search condition;
[0008] A second search condition is generated according to the user's adjustment of the first recommended search element.
[0009] Furthermore, the first recommended search element includes keywords and classification numbers.
[0010] Furthermore, generating a first recommended search element according to the first search condition includes:
[0011] Perform feature extraction on the first search condition to obtain a first keyword;
[0012] Acquire a first extended keyword related to the first keyword, and / or acquire a first classification number related to the first keyword and / or the first extended keyword;
[0013] The first recommended search element is generated according to the first keyword, the first extended keyword and / or the first classification code.
[0014] Furthermore, generating a first recommended search element according to the first search condition includes:
[0015] Perform feature extraction on the first search condition to obtain a first keyword, and generate a first search result according to the first keyword;
[0016] Acquire a first extended keyword related to the first search result, and / or acquire a first classification number related to the first search result and / or the first extended keyword;
[0017] A first recommended search element is generated according to the first keyword, the first extended keyword and / or the first classification code.
[0018] Further, the obtaining of a first extended keyword related to the first search result and / or the obtaining of a first classification number related to the first search result and / or the first extended keyword includes:
[0019] Sorting the first search results according to a preset rule, and confirming that a preset number of first search results ranked first are first recommended results;
[0020] Obtain a first extended keyword of the text content at the preset position of the first recommendation result, and / or a first classification number corresponding to the text content at the preset position of the first recommendation result, the first extended keyword matches the first keyword, and the technical field of the first classification number is the same or similar to the technical field of the text content at the preset position of the first recommendation result.
[0021] Furthermore, generating a second search condition according to the user's adjustment of the first recommended search element includes:
[0022] displaying the first recommended search element;
[0023] A second search condition is generated according to the user's selection of the first keyword, the first extended keyword and / or the first classification number.
[0024] Furthermore, generating a second search condition according to the user's adjustment of the first recommended search element includes:
[0025] displaying the first recommended search element;
[0026] A second search condition is generated according to the user's selection of the first recommended search element.
[0027] Furthermore, generating the second search condition according to the user's selection of the first keyword, the first extended keyword and / or the first classification number includes:
[0028] receiving a user's instruction to add and / or delete the first keyword, the first extended keyword and / or the first classification number;
[0029] Add and / or delete one or more of the first keyword, the first extended keyword and / or the first classification number based on the adding and / or deleting instruction;
[0030] A second search condition is generated based on the first keyword, the first extended keyword and / or the first classification number that are retained after the adding and / or deleting actions.
[0031] Furthermore, the generating of the second search condition according to the user's adjustment of the first recommended search element includes:
[0032] Generate a second search result according to the second search condition, and generate a second recommended search element according to the second search result;
[0033] generating a third search condition according to the user's adjustment of the second recommended search element;
[0034] A third search result is generated according to the third search condition.
[0035] Further, generating a second search result according to the second search condition, and generating a second recommended search element according to the second search result includes:
[0036] Perform feature extraction on the second search condition to obtain a second keyword, and generate a second search result according to the second keyword;
[0037] Sorting the second search results according to a preset rule, and confirming that a preset number of second search results ranked first are second recommended results;
[0038] Obtaining a second extended keyword of the text content at the preset position of the second recommendation result, and / or a second classification number corresponding to the text content at the preset position of the second recommendation result, wherein the second extended keyword matches the second keyword, and the technical field of the second classification number is the same or similar to the technical field of the text content at the preset position of the second recommendation result;
[0039] A second recommended search element is generated according to the second keyword, the second extended keyword and / or the second classification code.
[0040] Furthermore, generating a third search condition according to the user's adjustment of the second recommended search element includes:
[0041] displaying the second recommended search element;
[0042] A third search condition is generated according to the user's selection of the second keyword, the second extended keyword and / or the second classification number.
[0043] Furthermore, generating a third search condition according to the user's adjustment of the second recommended search element includes:
[0044] displaying the second recommended search element;
[0045] A third search condition is generated according to the user's selection of the second recommended search element.
[0046] Furthermore, generating a third search condition according to the user's selection of the second keyword, the second extended keyword and / or the second classification number includes:
[0047] receiving a user's instruction to add and / or delete the second keyword, the second extended keyword and / or the second classification number;
[0048] Add and / or delete one or more of the second keyword, the second extended keyword and / or the second classification number based on the adding and / or deleting instruction;
[0049] A third search condition is generated based on the second keyword, the second extended keyword and / or the second classification number that remain after the adding and / or deleting actions.
[0050] Further, generating a second search result according to the second search condition includes:
[0051] generating a first search formula according to the second search condition;
[0052] Perform a search according to the first search formula to obtain a second search result;
[0053] The second search result is displayed on the search result interface.
[0054] Further, generating a third search result according to the third search condition includes:
[0055] Generate a second search formula according to the third search condition;
[0056] Performing a search according to the second search formula to obtain the third search result;
[0057] The second search result and the third search result are displayed on the search result interface.
[0058] Further, obtaining the second search result and the third search result on the search result interface includes:
[0059] Displaying the second search result in a normal display on the search result interface;
[0060] The third search result is displayed in a highlighted manner on the search result interface.
[0061] Further, displaying the third search result in a highlighted manner on the search result interface includes:
[0062] highlighting the text of the third search result by a preset color, and / or
[0063] highlighting the text of the third search result by bolding it, and / or
[0064] highlighting the text of the third search result by italicizing, and / or
[0065] The background of the third search result is highlighted by a preset background color.
[0066] Furthermore, displaying the second search result and the third search result on the search result interface includes:
[0067] Displaying the third search result that is the same as the second search result in a normal display on the search result interface;
[0068] A third search result different from the second search result is displayed in a highlighted manner on the search result interface.
[0069] Furthermore, displaying the second search result and the third search result on the search result interface also includes:
[0070] A result filter control is further displayed on the search result interface, and the result filter control is used to select and display one or all of the second search result and the third search result.
[0071] On the one hand, an embodiment of the present invention further provides a device for recommending search conditions, the device comprising:
[0072] An acquisition module, used to acquire a first search condition input by a user;
[0073] A recommendation module, configured to generate a first recommended search element according to the first search condition;
[0074] An adjustment module is used to generate a second search condition according to the user's adjustment of the first recommended search element.
[0075] Furthermore, the first recommended search element includes keywords and classification numbers.
[0076] Furthermore, the recommendation module is also used for:
[0077] Perform feature extraction on the first search condition to obtain a first keyword;
[0078] Acquire a first extended keyword related to the first keyword, and / or acquire a first classification number related to the first keyword and / or the first extended keyword;
[0079] The first recommended search element is generated according to the first keyword, the first extended keyword and / or the first classification code.
[0080] Furthermore, the recommendation module is also used for:
[0081] Perform feature extraction on the first search condition to obtain a first keyword, and generate a first search result according to the first keyword;
[0082] Acquire a first extended keyword related to the first search result, and / or acquire a first classification number related to the first search result and / or the first extended keyword;
[0083] A first recommended search element is generated according to the first keyword, the first extended keyword and / or the first classification code.
[0084] Furthermore, the recommendation module is also used for:
[0085] Sorting the first search results according to a preset rule, and confirming that a preset number of first search results ranked first are first recommended results;
[0086] Obtain a first extended keyword of the text content at the preset position of the first recommendation result, and / or a first classification number corresponding to the text content at the preset position of the first recommendation result, the first extended keyword matches the first keyword, and the technical field of the first classification number is the same or similar to the technical field of the text content at the preset position of the first recommendation result.
[0087] Furthermore, the adjustment module is also used for:
[0088] displaying the first recommended search element;
[0089] A second search condition is generated according to the user's selection of the first keyword, the first extended keyword and / or the first classification number.
[0090] Furthermore, the adjustment module is also used for:
[0091] displaying the first recommended search element;
[0092] A second search condition is generated according to the user's selection of the first recommended search element.
[0093] Furthermore, the adjustment module is also used for:
[0094] receiving a user's instruction to add and / or delete the first keyword, the first extended keyword and / or the first classification number;
[0095] Add and / or delete one or more of the first keyword, the first extended keyword and / or the first classification number based on the adding and / or deleting instruction;
[0096] A second search condition is generated based on the first keyword, the first extended keyword and / or the first classification number that are retained after the adding and / or deleting actions.
[0097] Furthermore, a matching module is included.
[0098] The recommendation module is further used to generate a second recommended search element according to the second search result;
[0099] The adjustment module is further used to generate a third search condition according to the user's adjustment of the second recommended search element;
[0100] The matching module is used to generate a second search result according to the second search condition, and to generate a third search result according to the third search condition.
[0101] Furthermore, the matching module is further used to perform feature extraction on the second search condition to obtain a second keyword, and generate a second search result according to the second keyword;
[0102] The recommendation module is further used to sort the second search results according to a preset rule, and confirm that a preset number of second search results ranked first are second recommendation results;
[0103] Obtaining a second extended keyword of the text content at the preset position of the second recommendation result, and / or a second classification number corresponding to the text content at the preset position of the second recommendation result, wherein the second extended keyword matches the second keyword, and the technical field of the second classification number is the same or similar to the technical field of the text content at the preset position of the second recommendation result;
[0104] A second recommended search element is generated according to the second keyword, the second extended keyword and / or the second classification code.
[0105] Furthermore, the recommendation module is also used for:
[0106] displaying the second recommended search element;
[0107] A third search condition is generated according to the user's selection of the second keyword, the second extended keyword and / or the second classification number.
[0108] Furthermore, the recommendation module is also used for:
[0109] displaying the second recommended search element;
[0110] A third search condition is generated according to the user's selection of the second recommended search element.
[0111] Furthermore, the recommendation module is also used for:
[0112] receiving a user's instruction to add and / or delete the second keyword, the second extended keyword and / or the second classification number;
[0113] Add and / or delete one or more of the second keyword, the second extended keyword and / or the second classification number based on the adding and / or deleting instruction;
[0114] A third search condition is generated based on the second keyword, the second extended keyword and / or the second classification number that remain after the adding and / or deleting actions.
[0115] Furthermore, the matching module is also used for:
[0116] generating a first search formula according to the second search condition;
[0117] Perform a search according to the first search formula to obtain a second search result;
[0118] The second search result is displayed on the search result interface.
[0119] Furthermore, the matching module is also used for:
[0120] Generate a second search formula according to the third search condition;
[0121] Performing a search according to the second search formula to obtain the third search result;
[0122] The second search result and the third search result are displayed on the search result interface.
[0123] Furthermore, the matching module is also used for:
[0124] Displaying the second search result in a normal display on the search result interface;
[0125] The third search result is displayed in a highlighted manner on the search result interface.
[0126] Furthermore, the matching module is also used for:
[0127] highlighting the text of the third search result by a preset color, and / or
[0128] highlighting the text of the third search result by bolding it, and / or
[0129] highlighting the text of the third search result by italicizing, and / or
[0130] The background of the third search result is highlighted by a preset background color.
[0131] Furthermore, the matching module is also used for:
[0132] Displaying the third search result that is the same as the second search result in a normal display on the search result interface;
[0133] A third search result different from the second search result is displayed in a highlighted manner on the search result interface.
[0134] Furthermore, the matching module is also used for:
[0135] A result filter control is further displayed on the search result interface, and the result filter control is used to select and display one or all of the second search result and the third search result.
[0136] On the other hand, an embodiment of the present invention further provides a device for recommending search conditions, the device comprising:
[0137] one or more processors;
[0138] a storage device for storing one or more programs,
[0139] When the one or more programs are executed by the one or more processors, the one or more processors implement the recommendation method provided by any embodiment of the present invention.
[0140] On the other hand, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the recommendation method provided by any embodiment of the present invention.
[0141] The embodiment of the present invention obtains a first search condition input by a user; generates a first recommended search element based on the first search condition; and generates a second search condition based on the user's adjustment of the first recommended search element, thereby solving the problem of the inconvenience of inputting expansion words and classification numbers during the search, realizing a recommendation function for optimizing the search conditions and enhancing the user's search experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0142] Figure 1 It is a flowchart of a method for recommending search conditions provided in the first embodiment of the present invention;
[0143] Figure 2 It is a flowchart of a method for recommending search conditions provided in the second embodiment of the present invention;
[0144] Figure 3 This is a schematic diagram of a screen for initial refinement in a method for recommending search conditions provided in the second embodiment of the present invention;
[0145] Figure 4 This is a schematic diagram of a screen showing secondary refinement in a method for recommending search conditions provided in the second embodiment of the present invention;
[0146] Figure 5 It is a flowchart of a method for recommending search conditions provided in Embodiment 3 of the present invention;
[0147] Figure 6 This is a schematic diagram of a screen showing feedback refinement in a method for recommending search conditions provided in Embodiment 3 of the present invention;
[0148] Figure 7 It is a flowchart of a method for recommending search conditions provided by the fourth embodiment of the present invention;
[0149] Figure 8 It is a flowchart of a method for recommending search conditions provided in Embodiment 5 of the present invention;
[0150] Fig. 9 It is a flowchart of a method for recommending search conditions provided by Embodiment 6 of the present invention;
[0151] Fig.10 This is a schematic diagram of a recommended result interface in a method for recommending search conditions provided in Embodiment 6 of the present invention;
[0152] Fig.11This is a schematic diagram of a recommended result interface in a method for recommending search conditions provided in Embodiment 6 of the present invention;
[0153] Fig.12 is a structural schematic diagram of a recommended device provided in Embodiment 7 of the present invention;
[0154] Fig.13 A schematic diagram of the structure of a recommended device provided in Embodiment 8 of the present invention. DETAILED DESCRIPTION
[0155] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only the parts related to the present invention, rather than all structures, are shown in the accompanying drawings.
[0156] It should be mentioned before discussing the exemplary embodiments in more detail that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the steps as sequential processes, many of the steps therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the steps can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.
[0157] In addition, the terms "first", "second", etc. can be used in this article to describe various directions, actions, steps or elements, etc., but these directions, actions, steps or elements are not limited by these terms. These terms are only used to distinguish a first direction, action, step or element from another direction, action, step or element. For example, without departing from the scope of this application, the first search result can be referred to as the second search result, and similarly, the second search result can be referred to as the first search result. Both the first search result and the second search result are search results, but they are not the same search result. The terms "first", "second", etc. cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first" and "second" can expressly or implicitly include one or more of the features. In the description of the embodiment of the present invention, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.
[0158] Embodiment 1
[0159] like Figure 1 As shown, the first embodiment of the present invention provides a method for recommending search conditions, and the method includes:
[0160] S110: Obtain a first search condition input by a user.
[0161] In this embodiment, the first search condition may be one or more of a keyword, a keyword combination, and a text content input from the search input interface. When the first search condition is a keyword or a keyword combination, the keyword or keyword combination is set as a search formula. Specifically, the method for obtaining the keyword or keyword combination input by the user may be that the user manually inputs the keyword or keyword combination through an external device, for example, the user inputs the keyword or keyword combination by pressing a control on the keyboard, or the user inputs the keyword or keyword combination through voice, for example, the user inputs the keyword "toothbrush" through voice, obtains the voice input by the user, converts the voice input by the user into text form through voice recognition technology, and then obtains the keyword input by the user. The keyword or keyword combination input by the user may also be obtained through other methods, such as obtaining the keyword or keyword combination input by the user through gestures, etc. The embodiment of the present invention does not limit this.
[0162] S120: Generate a first recommended search element according to the first search condition.
[0163] In this embodiment, a first recommended search element can be generated based on the trained neural network model. The first recommended search element is one or more recommended keywords or recommended keyword combinations corresponding to one or more keywords or keyword combinations in the first search condition, as well as classification numbers corresponding to one or more keywords or keyword combinations, and classification numbers corresponding to one or more recommended keywords or recommended keyword combinations.
[0164] In addition, multiple options can be set to allow users to select and set the number of recommended keywords and / or classification numbers that need to be extracted, such as one option to recommend 10 recommended keywords and / or 5 classification numbers, one option to recommend 2 recommended keywords and / or 1 classification number, and an option to allow users to set the number of recommended keywords and / or classification numbers that need to be recommended according to their own needs. Another feasible implementation is to set multiple options for each keyword to allow users to select and set the number of recommended keywords and / or classification numbers that need to be extracted, such as one option to set the number of recommended keywords that need to be recommended for the first keyword, and one option to set the number of classification numbers that need to be recommended. The corresponding number of options can be set according to the number of keywords.
[0165] According to the above method, all recommended keywords or recommended keyword combinations and classification numbers are extracted, and the extracted identical recommended keyword combinations and classification numbers are ignored, and all recommended keywords or recommended keyword combinations and classification numbers are used as the first recommended search element. When the user clicks to generate the first recommended search element, or when the user commands to provide the first recommended search element through other means, a new pop-up window will be formed, one part of which displays the first search condition entered by the user, and the other part displays the first recommended search element. The first recommended search element may or may not include the first search condition, wherein the recommended keywords and classification numbers in the first recommended search element corresponding to the keywords in the first search condition can be highlighted with the same color as the text or background color, so as to facilitate the user to distinguish a certain keyword and its corresponding recommended keyword from other keywords. The embodiment of the present invention does not limit the method for achieving the distinction. For example, the keywords entered by the user include "toothbrush" and "vibration", the recommended keywords are "tooth tools" and "vibration", and the classification number is "A61C17 / 22". The text parts corresponding to "toothbrush" and "tooth tools" can be displayed in red, and the text parts corresponding to "vibration" and "vibration" and "A61C17 / 22" can be displayed in yellow.
[0166] In addition, when a keyword corresponds to multiple recommended keywords and multiple classification numbers, the keywords and the corresponding recommended keywords and multiple classification numbers can be arranged according to preset rules. For example, the keywords input by the user include "toothbrush" and "vibration", the recommended keywords are "toothbrush", "electric toothbrush", "vibration" and "mechanical vibration", and the classification numbers are "A61C17 / 22" and "A61C17 / 00". In the first vertical row, "toothbrush", "toothbrush" and "electric toothbrush" are displayed in order, in the second vertical row, "vibration", "vibration" and "mechanical vibration" are displayed in order, and in the third vertical row, "A61C17 / 22" and "A61C17 / 00" are displayed in order. Optionally, the background color of the keywords or recommended keywords in each vertical row is displayed in the same color. Similarly, similar settings can be made in the same horizontal row.
[0167] In an alternative embodiment, a pop-up window may not be generated. When the user clicks to generate the first recommended search element, or when the user provides the first recommended search element through other means, the first recommended search element is directly displayed on the interface where the user enters the first search condition.
[0168] S130: Generate a second search condition according to the user's adjustment of the first recommended search element.
[0169] In this embodiment, on the basis of the above display method, each keyword, recommended keyword and classification number includes an "X" option. When the user clicks or commands to use this option in other ways, the corresponding keyword, recommended keyword and classification number will be removed from the first recommended search element. In addition, the second part also includes an option to add keywords and / or classification numbers. When the user clicks or commands to use this option in other ways, a new small pop-up window will appear. The user can enter the recommended keyword, keyword combination or classification number in the small pop-up window. When the user confirms the input recommended keyword, keyword combination or classification number, the small pop-up window is closed, and the trained neural network model analyzes the relationship between the recommended keyword, keyword combination or classification number and the keywords and classification numbers in the current first recommended search element, and displays the recommended keywords and / or related classification numbers that are semantically similar to the keywords in the current first recommended search element at the bottom of the corresponding vertical row, and displays the recommended keywords that are not related to the keywords or classification numbers in the current first recommended search element in the new vertical row. In an alternative embodiment, the option to add keywords and / or classification numbers can also upload documents or texts organized by the user to import other keywords and / or classification numbers.
[0170] In an alternative embodiment, a new small pop-up window may not appear, and an input box for recommended keywords, keyword combinations and / or classification numbers may be directly displayed on the current page.
[0171] The embodiment of the present invention obtains a first search condition input by a user; generates a first recommended search element based on the first search condition; and generates a second search condition based on the user's adjustment of the first recommended search element, thereby solving the problem of the inconvenience of inputting expansion words and classification numbers during the search, realizing a recommendation function for optimizing the search conditions and enhancing the user's search experience.
[0172] Embodiment 2
[0173] like Figure 2 As shown, the second embodiment of the present invention is further optimized on the basis of the first embodiment of the present invention. The second embodiment of the present invention provides a method for recommending search conditions, and the recommendation method includes:
[0174] S210: Obtain a first search condition input by a user.
[0175] In this embodiment, when the first search condition is text content, the text content is set as the search formula. Specifically, the method for obtaining the text content input by the user can be that the user manually inputs the text content through an external device, for example, the user inputs the text content by pressing a control on a keyboard, or the user inputs the text content through voice, for example, the user inputs the text content "a toothbrush includes a vibrating head" through voice, obtains the voice input by the user, converts the voice input by the user into text form through voice recognition technology, and then obtains the text content input by the user. The text content input by the user can also be obtained through other methods, such as obtaining the text content input by the user through gestures, etc., and the embodiments of the present invention do not limit this.
[0176] S220: Perform feature extraction on the first search condition to obtain a first keyword.
[0177] In this embodiment, the text content needs to be processed first, that is, all the words "claims" and "characterized in that" are removed, and all the words "described" are extracted after "characterized in that", and the words "described" can also be extracted after all the words "embodiment", and the embodiment of the present invention is not limited to this. All the extracted words are used as the first keyword.
[0178] like Figure 3 As shown, in the search box of the search page, there is a split option. When the user clicks or uses the option through other means, a pop-up window will appear. The pop-up window includes a first part 210 and a second part 220. The first part 210 displays the text content entered by the user, and the second part 220 displays one or more first keywords after the split. Optionally, the first keyword in the second part 220 and the first keyword corresponding to the text content in the first part 210 are highlighted with the same color as the text or background color.
[0179] In addition, the pop-up window also includes a third part 230, and the third part 230 includes options for the previous step and the next step. When the user clicks or commands to use the previous step option in other ways, the user will return to the page for entering the first search condition. When the user clicks or commands to use the next step option in other ways, the search will be performed based on the first search formula converted from the multiple first keywords. Optionally, the third part 230 also includes description content, which is an explanation of the pop-up window. For example, the description content includes a title: "First refinement", including the description content "We split the following keywords for you based on the search text:", the second part 220 can be set directly below the third part 230, and the first part 210 can be set on the side of the second part 220 and the third part 230.
[0180] S230: Acquire a first extended keyword related to the first keyword, and / or acquire a first classification number related to the first keyword and / or the first extended keyword.
[0181] S240: Generate the first recommended search element according to the first keyword, the first extended keyword and / or the first classification number.
[0182] S250: Display the first recommended search element.
[0183] In this embodiment, multiple first extended keywords similar to the multiple first keywords can be generated according to the trained neural network model and / or a first classification number related to the first keyword and / or the first extended keyword can be obtained. Optionally, after the first keyword is vectorized, a first extended keyword with high semantic similarity is found in the vocabulary, and one or more classification numbers related to the multiple first keywords and / or corresponding to the first extended keyword are obtained according to the trained neural network model. Not every keyword necessarily has a corresponding classification number, and only the classification numbers of keywords with corresponding classification numbers are obtained.
[0184] In one embodiment, refer to Figure 4 , the first part 250 in the pop-up window is the first search condition input by the user, and the second part 260 in the pop-up window also includes an extended option. When the user clicks or commands to use the extended option through other methods, the first extended keyword and the first keyword will be displayed in the second part 260. When a first keyword corresponds to multiple first extended keywords, the first keyword and the corresponding first extended keyword can be arranged in the second part 260 according to a preset rule. For example, the first keyword obtained by splitting includes "toothbrush" and "vibration", and the first extended keywords are "toothbrush", "electric toothbrush", "vibration" and "mechanical vibration". "Toothbrush", "toothbrush" and "electric toothbrush" are displayed in order in the first vertical row, and "vibration", "vibration" and "mechanical vibration" are displayed in order in the second vertical row. Optionally, the background color of the first keyword or the first extended keyword in each vertical row is displayed as the same color.
[0185] In addition, when the user clicks or instructs to use the extended option in other ways, the second part 260 can also display the classification number 240. The classification number 240 in this embodiment can be the IPC classification number A61C17 / 22 and A61C17 / 34, or the CPC classification number A46B9 / 025 and A46B9 / 026. Figure 5Only IPC classification number (International Patent Classification) and CPC classification number (Cooperative Patent Classification) are used as examples, and other classification methods such as Locarno classification (Locarno Classification) can also be included. Classification number 240 is obtained by searching or other methods based on multiple first keywords, and can also be obtained based on multiple first keywords and / or multiple and first extended keywords. Classification number 240 includes multiple classification methods. Classification numbers 240 of each classification method can be displayed in the same horizontal row or the same vertical row. Classification numbers 240 of the same classification method can be highlighted with the same color for text or background color. The second part 260 also includes color examples of classification numbers 240 of different classification methods. Classification number 240 can only display the major category, or it can be displayed specifically to the minor category. When the user long presses or moves the mouse to a certain classification number 240 and stays there, a small pop-up window will appear to display the specific Chinese meaning of the classification number 240. For example, when the user long presses or moves the mouse to "A61C17 / 22" and stays there, the small pop-up window will display "A-Human life necessities, A61-Medicine or veterinary medicine; hygiene, A61C-Dentistry; devices or methods for oral or dental hygiene, A61C17 / 00-Device for cleaning, polishing, rinsing or drying teeth, dental cavities or prostheses, A61C17 / 22-With a brush, buffer, cup or the like". Similarly, each classification number 240 in the second part 260 includes an "X" option. When the user clicks or commands to use this option in other ways, the corresponding classification number 240 will be removed from the first search condition. In the section of classification number 240, there is also an option to add classification number 240. When the user clicks or uses this option in other ways, a new small pop-up window will appear. The user can enter the new classification number 240 in the small pop-up window. When the user confirms the input of the new classification number 240, the small pop-up window is closed, and the trained neural network model analyzes the relationship between the new classification number 240 and the current classification number 240, and displays the classification number 240 in the classification number 240 of the same classification method, and displays the same color, and displays the classification number 240 with the same meaning as the new classification number 240 in the classification number 240 of other classification methods. Optionally, the information of the same family of patents can also be displayed in the same display mode. In an alternative embodiment, the option of adding classification number 240 can also upload documents or texts sorted by the user to import other classification numbers 240. In an alternative embodiment, when the user clicks on any classification number 240, the keywords corresponding to the classification number 240 can be highlighted.
[0186] When the user clicks or commands to use the extended option through other means, the third part 270 will also change accordingly. For example, the description content includes the title: "Second Refinement" and the description content "We have expanded the following keywords and classification numbers for you based on the search text:".
[0187] In this embodiment, each first keyword in the second part 260 includes an option marked with an "X". When the user clicks or uses the option in other ways, the corresponding first keyword will be removed from the first search condition.
[0188] S260: Generate a second search condition according to the user's selection of the first keyword, the first extended keyword and / or the first classification number.
[0189] In this embodiment, on the basis of the above display method, each keyword or recommended keyword includes an "X" option. When the user clicks or commands to use this option in other ways, the corresponding keyword or recommended keyword will be removed from the first recommended search element. In addition, the second part 120 also includes an option to add keywords. When the user clicks or commands to use this option in other ways, a new small pop-up window will appear. The user can enter the recommended keyword or keyword combination in the small pop-up window. When the user confirms the input recommended keyword or keyword combination, the small pop-up window closes, and the trained neural network model analyzes the relationship between the recommended keyword or keyword combination and the keyword in the current first recommended search element, and displays the recommended keywords that are semantically similar to the keywords in the current first recommended search element at the bottom of the corresponding vertical row, and displays the recommended keywords that have nothing to do with the keywords in the current first recommended search element in a new vertical row. In an alternative embodiment, the option to add keywords can also upload documents or texts organized by the user to import other keywords.
[0190] In addition, the pop-up window also includes a third part 270, which includes options for the previous step and the next step. When the user clicks or commands to use the previous step option in other ways, the user will return to the page for entering the first search condition. When the user clicks or commands to use the next step option in other ways, the search will be converted into a second search formula based on the first recommended search element, wherein the relationship between the keywords in a single vertical row in the first recommended search element in the search formula is "OR", and the relationship between each vertical row and the keywords in other vertical rows in the search formula is "AND". For example, when the keywords in the first vertical row in the recommended search formula are "toothbrush" and "toothbrush head", and the keywords in the second vertical row are "vibration" and "vibration", the search formula of the second search condition is ((toothbrush or toothbrush head) and (vibration or vibration)). In an alternative embodiment, the keyword relationship between the first vertical row and the second vertical row can also be adjusted when necessary according to a preset control or menu, and the second part 260 can be set directly below the third part 270, and the first part 260 can be set on the side of the second part 260 and the third part 270. In an alternative embodiment, the interfaces of the first part 260, the second part 260 and the third part 270 can be independent window controls, and the positional relationship between the three can also be flexibly adjusted as needed. For example, the second part 260 can be set directly above the third part 270, and the first part 260 can be set above the second part 260 and the third part 270.
[0191] In an alternative embodiment, the pop-up window or small pop-up window may not appear, but the search condition may be directly displayed in other areas of the page where the user inputs the first search condition.
[0192] The embodiment of the present invention solves the problem of inconvenience in inputting expansion words and classification number 240 during retrieval by splitting and expanding text content and expanding the retrieval number during the initial retrieval, thereby optimizing the retrieval function and enhancing the user's retrieval experience.
[0193] Embodiment 3
[0194] like Figure 5 As shown, the third embodiment of the present invention is further optimized on the basis of the first embodiment of the present invention. The third embodiment of the present invention provides a method for recommending search conditions, and the recommendation method includes:
[0195] S310: Obtain a first search condition input by a user.
[0196] In this embodiment, when the first search condition is text content, the text content is set as the search formula. Specifically, the method for obtaining the text content input by the user can be that the user manually inputs the text content through an external device, for example, the user inputs the text content by pressing a control on a keyboard, or the user inputs the text content through voice, for example, the user inputs the text content "a toothbrush includes a vibrating head" through voice, obtains the voice input by the user, converts the voice input by the user into text form through voice recognition technology, and then obtains the text content input by the user. The text content input by the user can also be obtained through other methods, such as obtaining the text content input by the user through gestures, etc., and the embodiments of the present invention do not limit this.
[0197] S320: Perform feature extraction on the first search condition to obtain a first keyword, and generate a first search result according to the first keyword.
[0198] S330: Sort the first search results according to a preset rule, and confirm that a preset number of first search results that are ranked top are first recommended results.
[0199] In this embodiment, the patent document library may include all published patent documents or patent application documents, or may be a paper, or may be other structured documents, which are not limited in this embodiment of the present invention. In this embodiment, the first search result may be obtained by directly searching the patent document library according to the search formula of the keyword or keyword combination, and the first search result includes all published patent documents or patent application documents in the patent document library that are related to the keyword or keyword combination.
[0200] In one embodiment, the relevance matching degree of the disclosed patent documents related to the keyword or keyword combination can be simultaneously displayed in the first search result, and the interval range of the relevance matching degree is 0%-100%. A feasible implementation method is that only the disclosed patent documents with a relevance matching degree of more than 50% are displayed by default. In addition, multiple options can be set to allow users to select and set the interval range of the displayed relevance matching degree, for example, one option is to display the disclosed patent documents with a relevance matching degree of more than 80%, one option is to display the disclosed patent documents with a relevance matching degree of more than 20%, and an option is also included to allow users to set the relevance matching degree of the disclosed patent documents to be displayed according to their own needs. Another feasible implementation is that multiple options can be set to allow the user to choose to set the number of published patent documents displayed in the first search result, for example, one option is to display 10 published patent documents, wherein the 10 published patent documents displayed are the first 10 published patent documents sorted from high to low in terms of relevance matching degree, for example, one option is to display 100 published patent documents, wherein the 100 published patent documents displayed are the first 100 published patent documents sorted from high to low in terms of relevance matching degree, and also includes an option that allows the user to set the number of published patent documents to be displayed or the sorting method according to their own needs.
[0201] When the keyword or keyword combination input by the user includes a preset formula, a search is performed according to the formula to obtain a first search result. If the keyword or keyword combination input by the user does not include a preset formula, the relationship between the keywords or keyword combinations can be analyzed by a trained neural network model, and a search formula can be given. A search is performed according to the search formula to obtain the first search result. For example, when the keyword combination input by the user is "toothbrush", "toothbrush head" and "vibration", the trained neural network model is used to analyze that "toothbrush" and "toothbrush head" are keywords with similar semantics, and the search formula is ((toothbrush or toothbrush head) and vibration).
[0202] S340, obtaining the first extended keyword of the text content at the preset position of the first recommendation result, and / or the first classification number corresponding to the text content at the preset position of the first recommendation result, the first extended keyword matches the first keyword, and the technical field of the first classification number is the same as or similar to the technical field of the text content at the preset position of the first recommendation result.
[0203] In this embodiment, in addition to the method provided in the second embodiment of the present invention, the extraction method can also use word frequency, tfidf, text-rank and its variants to achieve the expansion of keywords to obtain multiple recommended keywords and multiple recommended classification codes. A feasible implementation method is to extract recommended keywords only in a specific part of the patent document, for example, only obtain the recommended keywords in the "claims". A feasible implementation method is to determine whether to use the classification code as a recommended classification code based on the frequency of occurrence of the classification code corresponding to the keyword and the recommended keyword. For example, first obtain the classification code corresponding to all keywords. When a classification code accounts for more than 50% of all classification codes, the classification code is used as a recommended classification code. Optionally, it can also be determined whether to use the classification code as a recommended classification code based on the hierarchical relationship of the classification code. For example, first obtain the classification code corresponding to all keywords. When more than 50% of the classification codes belong to the first category, the first category is used as a recommended classification code. Optionally, a model can also be trained based on the co-occurrence relationship between the classification codes in the patent database to expand more classification codes related to a classification code. The co-occurrence relationship can be simply understood as the relationship between the co-occurrence of keywords. In bibliometrics, the co-occurrence method of keywords is often used to determine the relationship between the various topics in the discipline represented by the document set. In this embodiment, the co-occurrence relationship can also be used in the classification number.
[0204] S350: Generate a first recommended search element according to the first keyword, the first extended keyword and / or the first classification number.
[0205] S360: Display the first recommended search element.
[0206] S370: Receive a user's instruction to add and / or delete the first keyword, the first extended keyword and / or the first classification number.
[0207] S380, adding and / or deleting one or more of the first keyword, the first extended keyword and / or the first classification number based on the adding and / or deleting instruction;
[0208] S390: Generate a second search condition based on the first keyword, the first extended keyword and / or the first classification number retained after the adding and / or deleting action.
[0209] In this embodiment, based on the above display method, refer to Figure 6, the first part 310 is the first search condition input by the user, and each keyword or recommended keyword includes an "X" option. When the user clicks or commands to use this option in other ways, the corresponding keyword or recommended keyword will be removed from the recommended search condition. In addition, the second part 320 also includes an option to add keywords. When the user clicks or commands to use this option in other ways, a new small pop-up window will appear. The user can enter recommended keywords or keyword combinations in the small pop-up window. When the user confirms the input recommended keywords or keyword combinations, the small pop-up window closes, and the trained neural network model analyzes the relationship between the recommended keywords or keyword combinations and the keywords in the current recommended search conditions, and displays the recommended keywords that are semantically similar to the keywords in the current recommended search conditions at the bottom of the corresponding vertical row, and displays the recommended keywords that have nothing to do with the keywords in the current recommended search conditions in a new vertical row. In an alternative embodiment, the option to add keywords can also upload documents or texts organized by the user to import other keywords.
[0210] In addition, the pop-up window also includes a third part 330, which includes options for the previous step and the next step. When the user clicks or commands to use the previous step option through other methods, the user will return to the page displaying the first search result. When the user clicks or commands to use the next step option through other methods, the recommended search condition will be converted to a second search formula for retrieval, wherein the relationship between the keywords in a single vertical row in the recommended search condition is "OR" in the search formula, and the relationship between each vertical row and the keywords in other vertical rows in the search formula is "AND". For example, when the keywords in the first vertical row in the recommended search formula are "toothbrush" and "toothbrush head", and the keywords in the second vertical row are "vibration" and "vibration", the search formula of the second search condition is ((toothbrush or toothbrush head) and (vibration or vibration)). In an alternative embodiment, the keyword relationship between the first vertical row and the second vertical row can also be adjusted when necessary according to a preset control or menu. Optionally, the third part 330 also includes description content, which is an explanation of the pop-up window. For example, the description content includes a title: "Feedback refinement", including the description content "We recommend the following extended information for you based on patents related to the search text: ", the second part 320 can be set directly below the third part 330, and the first part 330 can be set on the side of the second part 320 and the third part 330. In an alternative embodiment, the interfaces of the first part 330, the second part 320 and the third part 330 can be independent window controls, and the positional relationship between the three can also be flexibly adjusted as needed. For example, the second part 320 can be set directly above the third part 330, and the first part 330 can be set above the second part 320 and the third part 330.
[0211] In an alternative embodiment, the pop-up window or small pop-up window may not appear, but the search condition may be directly displayed in other areas of the page where the user inputs the first search condition.
[0212] The embodiment of the present invention solves the problem of inconvenient input of expansion words and classification numbers during retrieval by generating a first search recommendation element for the first search result and extracting keywords and classification numbers according to the above method, thereby optimizing the search function and enhancing the user's search experience.
[0213] Embodiment 4
[0214] like Figure 7 As shown, the fourth embodiment of the present invention is further optimized on the basis of the first embodiment of the present invention. The fourth embodiment of the present invention provides a method for recommending search conditions, and the recommendation method includes:
[0215] S410: Acquire a first search condition input by a user, generate a first recommended search element according to the first search condition, and generate a second search condition according to an adjustment made by the user to the first recommended search element.
[0216] S420: Generate a second search result according to the second search condition, and generate a second recommended search element according to the second search result.
[0217] S430: Generate a third search condition according to the user's adjustment of the second recommended search element.
[0218] S440: Generate a third search result according to the third search condition.
[0219] The steps in this embodiment are the same as the implementation method of any of the above embodiments of the present invention. The only difference is that in the third embodiment of any of the above embodiments, the first search result is generated according to the first search condition, the first recommended search element is generated according to the first search result, the second search condition is generated according to the user's adjustment of the first recommended search element, and the second search result is generated according to the second search condition. The embodiment of the present invention generates the second search result according to the second search condition, generates the second recommended search element according to the second search result, generates the third search condition according to the user's adjustment of the second recommended search element, and generates the third search result according to the third search condition. Although the names are different, the implementation methods are the same and one-to-one corresponding. If the user is not satisfied with the second search result, the second recommended search element can be obtained according to the second search result, and the third search result can be further obtained. Optionally, the user can continue to obtain the recommended search element according to the obtained search result until the desired search result is obtained.
[0220] The embodiment of the present invention further solves the problem of inconvenience in entering expansion words and classification numbers during retrieval and the problem that the retrieval results cannot meet user needs by generating a second search recommendation element for the second search result and extracting keywords and classification numbers according to the above method, thereby further optimizing the retrieval function and enhancing the user's retrieval experience.
[0221] Embodiment 5
[0222] like Figure 8 As shown, the fifth embodiment of the present invention is further optimized on the basis of the third embodiment of the present invention. The third embodiment of the present invention provides a method for recommending search conditions, and the recommendation method includes:
[0223] S510: Acquire a first search condition input by a user, generate a first recommended search element according to the first search condition, and generate a second search condition according to an adjustment made by the user to the first recommended search element.
[0224] S520: Perform feature extraction on the second search condition to obtain a second keyword, and generate a second search result according to the second keyword.
[0225] S530: Sort the second search results according to a preset rule, and confirm that a preset number of second search results that are ranked first are second recommended results.
[0226] S540, obtaining a second extended keyword of the text content at the preset position of the second recommendation result, and / or a second classification number corresponding to the text content at the preset position of the second recommendation result, the second extended keyword matches the second keyword, and the technical field of the second classification number is the same or similar to the technical field of the text content at the preset position of the second recommendation result.
[0227] S550: Generate a second recommended search element according to the second keyword, the second extended keyword and / or the second classification number.
[0228] S560: Display the second recommended search factor.
[0229] S570: Receive a user's instruction to add and / or delete the second keyword, the second extended keyword and / or the second classification number.
[0230] S580: Add and / or delete one or more of the second keyword, the second extended keyword and / or the second classification number based on the adding and / or deleting instruction.
[0231] S590: Generate a third search condition based on the second keyword, the second extended keyword and / or the second classification number retained after the adding and / or deleting action.
[0232] S600: Generate a third search result according to the third search condition.
[0233] The steps in this embodiment are the same as the implementation method of any of the above embodiments of the present invention. The only difference is that in the third embodiment of any of the above embodiments, the first search result is generated according to the first search condition, the first recommended search element is generated according to the first search result, the second search condition is generated according to the user's adjustment of the first recommended search element, and the second search result is generated according to the second search condition. The embodiment of the present invention generates the second search result according to the second search condition, generates the second recommended search element according to the second search result, generates the third search condition according to the user's adjustment of the second recommended search element, and generates the third search result according to the third search condition. Although the names are different, the implementation methods are the same and one-to-one corresponding. If the user is not satisfied with the second search result, the second recommended search element can be obtained according to the second search result, and the third search result can be further obtained. Optionally, the user can continue to obtain the recommended search element according to the obtained search result until the desired search result is obtained.
[0234] The embodiment of the present invention further solves the problem of inconvenience in entering expansion words and classification numbers during retrieval and the problem that the retrieval results cannot meet user needs by generating a second search recommendation element for the second search result and extracting keywords and classification numbers according to the above method, thereby further optimizing the retrieval function and enhancing the user's retrieval experience.
[0235] Embodiment 6
[0236] like Fig. 9 As shown, the sixth embodiment of the present invention is further optimized on the basis of the fourth embodiment of the present invention and the fifth embodiment of the present invention. The sixth embodiment of the present invention provides a method for recommending search conditions, and the recommendation method includes:
[0237] S610: Acquire a first search condition input by a user, generate a first recommended search element according to the first search condition, and generate a second search condition according to an adjustment made by the user to the first recommended search element.
[0238] S620: Generate a first search formula according to the second search condition.
[0239] S630: Perform a search according to the first search formula to obtain a second search result.
[0240] S640: Display the second search result on the search result interface.
[0241] S650: Generate a second recommended search factor according to the second search result.
[0242] S660: Generate a third search condition according to the user's adjustment of the second recommended search element.
[0243] S670: Generate a second search formula according to the third search condition.
[0244] S680: Perform a search according to the second search formula to obtain the third search result.
[0245] S690: Display the second search result and the third search result on the search result interface.
[0246] In one embodiment, refer to Fig.10 , step S690 can be to display the second search result in a normal display on the search result interface; and to display the third search result in a highlighted display on the search result interface. The text of the third search result is highlighted by a preset color, and / or the text of the third search result is highlighted by a bold format, and / or the text of the third search result is highlighted by an italic format, and / or the background of the third search result is highlighted by a preset background color. This facilitates the user to compare the first search result with the second search result.
[0247] In this embodiment, both the first search result and the second search result are multiple patent documents. The search result interface includes two parts. The first part 410 is the first search result, and the second part 420 is the second search result. The first part 410 and the second part 420 can be displayed on the left and right sides of the search result interface, or can be displayed as shown in FIG. Figure 8 The upper and lower sides are shown, and the embodiment of the present invention is not limited to this. A feasible implementation is that a split line 430 is set between the first part 410 and the second part 420, and the user can drag or command the split line 430 to drag in other ways to adjust the display area size of the first part 410 and the second part 420 in the search result interface. In an alternative embodiment, the first search result and the second search result can also be displayed in combination, but the first search result is displayed in a normal display to highlight the display of the second search result that is different from the first search result.
[0248] In one embodiment, refer to Fig.11 , step S690 may be to display the third search result that is the same as the second search result in a normal display on the search result interface; and to display the third search result that is different from the second search result in a highlighted display on the search result interface. Furthermore, a result filter control is further displayed on the search result interface, and the result filter control is used to select and display one or all of the second search result and the third search result.
[0249] In this embodiment, the first search result and the second search result are both a plurality of patent documents, and the search result interface includes two parts, the first part 510 is the first search result, and the second part 520 is the second search result. The first part 510 and the second part 520 can be displayed on the left and right sides of the search result interface, or can be displayed on the top and bottom sides. The embodiment of the present invention does not limit this. A feasible implementation is that a split line 540 is provided in the first part 510 and the second part 520, and the user can drag or command the split line 540 to be dragged by other means to adjust the display area size of the first part 510 and the second part 520 in the search result interface. The search result interface can also include a third part 530, and the third part 530 includes description content and result filtering controls. For example, the description content includes a title: "Search results", including description content "We provide you with the following search results based on the search text:". When the user clicks or commands the use of the result filtering control by other means, a small pop-up window will pop up with three options, respectively showing "show only the first search result", "show only the second search result" and "show all". When the user selects "show only the first search result", the search result interface will only display the first search result; when the user selects "show only the second search result", the search result interface will only display the second search result; when the user selects "show all", the search result interface will display the first search result and the second search result at the same time in the above manner. The third part 530 can be set on top of the first part 510 and the second part 520, or can be set to be displayed in the first part 510 or the second part 520 in the form of a floating window, and the user can drag the floating window to prevent the floating window from blocking the search results.
[0250] The third part 530 also includes options for the previous step and the next step. When the user clicks or commands to use the option of the previous step through other means, the user will return to the "second refinement" page. When the user clicks or commands to use the option of the next step through other means, the user will enter the "third refinement" page based on the second search result for further expansion and refinement.
[0251] The embodiment of the present invention solves the problem that there are multiple search results without comparison or the comparison method is not obvious enough in the search, by displaying the second search result that is the same as the first search result in a normal display on the search result interface, displaying the second search result that is different from the first search result in a highlighted display on the search result interface, and further displaying a result filter control on the search result interface, wherein the result filter control is used to select and display one or all of the first search result and the second search result. This optimizes the search function and enhances the user's search experience.
[0252] Embodiment 7
[0253] like Fig.12 As shown, the seventh embodiment of the present invention provides a device 100 for recommending search conditions. The device 100 corresponds to any method for recommending search conditions provided in the embodiments of the present invention and has the beneficial effects corresponding to the method. The device 100 includes:
[0254] An acquisition module 200 is used to acquire a first search condition input by a user;
[0255] A recommendation module 300, configured to generate a first recommended search element according to the first search condition;
[0256] The adjustment module 400 is used to generate a second search condition according to the user's adjustment of the first recommended search element.
[0257] Furthermore, the first recommended search element includes a keyword and a classification number. The recommendation module 300 is further used to: perform feature extraction on the first search condition to obtain a first keyword; obtain a first extended keyword related to the first keyword, and / or obtain a first classification number related to the first keyword and / or the first extended keyword; generate the first recommended search element according to the first keyword, the first extended keyword and / or the first classification number.
[0258] Furthermore, the recommendation module 300 is also used to: perform feature extraction on the first search condition to obtain a first keyword, and generate a first search result based on the first keyword; obtain a first extended keyword related to the first search result, and / or obtain a first classification number related to the first search result and / or the first extended keyword; generate a first recommended search element based on the first keyword, the first extended keyword and / or the first classification number.
[0259] Furthermore, the recommendation module 300 is also used to: sort the first search results according to preset rules, and confirm that a preset number of first search results in the top order are the first recommended results; obtain the first extended keyword of the text content at the preset position of the first recommendation result, and / or the first classification number corresponding to the text content at the preset position of the first recommendation result, the first extended keyword matches the first keyword, and the technical field of the first classification number is the same or similar to the technical field of the text content at the preset position of the first recommendation result.
[0260] Furthermore, the adjustment module 400 is also used to: display the first recommended search element; and generate a second search condition according to the user's selection of the first keyword, the first extended keyword and / or the first classification number.
[0261] Furthermore, the adjustment module 400 is further configured to: display the first recommended search element; and generate a second search condition according to the user's selection of the first recommended search element.
[0262] Furthermore, the adjustment module 400 is also used to: receive a user's add and / or delete instructions for the first keyword, the first extended keyword and / or the first classification number; add and / or delete one or more of the first keyword, the first extended keyword and / or the first classification number based on the add and / or delete instructions; and generate a second search condition based on the first keyword, the first extended keyword and / or the first classification number retained after the add and / or delete action.
[0263] Furthermore, it also includes a matching module 500, and the recommendation module 300 is also used to generate a second recommended search element based on the second search result; the adjustment module 400 is also used to generate a third search condition based on the user's adjustment of the second recommended search element; the matching module 500 is used to generate a second search result based on the second search condition, and generate a third search result based on the third search condition.
[0264] Furthermore, the matching module 500 is also used to perform feature extraction on the second search condition to obtain a second keyword, and generate a second search result based on the second keyword; the recommendation module 300 is also used to sort the second search results according to a preset rule, and confirm that a preset number of second search results that are ranked first are second recommended results; obtain a second extended keyword of the text content at a preset position of the second recommendation result, and / or a second classification number corresponding to the text content at a preset position of the second recommendation result, the second extended keyword matches the second keyword, and the technical field of the second classification number is the same or similar to the technical field of the text content at the preset position of the second recommendation result; generate a second recommended search element based on the second keyword, the second extended keyword and / or the second classification number.
[0265] Furthermore, the recommendation module 300 is also used to: display the second recommended search element; and generate a third search condition according to the user's selection of the second keyword, the second extended keyword and / or the second classification number.
[0266] Furthermore, the recommendation module 300 is also used to: display the second recommended search element; and generate a third search condition according to the user's selection of the second recommended search element.
[0267] Furthermore, the recommendation module 300 is also used to: receive the user's addition and / or deletion instructions for the second keyword, second extended keyword and / or second classification number; add and / or delete one or more of the second keyword, second extended keyword and / or second classification number based on the addition and / or deletion instructions; and generate a third search condition based on the second keyword, second extended keyword and / or second classification number retained after the addition and / or deletion action.
[0268] Furthermore, the matching module 500 is also used to: generate a first search formula according to the second search condition; perform a search according to the first search formula to obtain a second search result; and display the second search result on a search result interface.
[0269] Furthermore, the matching module 500 is also used to: generate a second search formula according to the third search condition; perform a search according to the second search formula to obtain the third search result; and display the second search result and the third search result on the search result interface.
[0270] Furthermore, the matching module 500 is further configured to: display the second search result in a normal display on the search result interface; and display the third search result in a highlighted display on the search result interface.
[0271] Furthermore, the matching module 500 is also used to: highlight the text of the third search result by a preset color, and / or highlight the text of the third search result by a bold format, and / or highlight the text of the third search result by an italic format, and / or highlight the background of the third search result by a preset background color.
[0272] Furthermore, the matching module 500 is also used to: display the third search result that is the same as the second search result in a normal display on the search result interface; and display the third search result that is different from the second search result in a highlighted display on the search result interface.
[0273] Furthermore, the matching module 500 is also used to: further display a result filter control on the search result interface, and the result filter control is used to select and display one or all of the second search result and the third search result.
[0274] Embodiment 8
[0275] Fig.13 A schematic diagram of the structure of a device provided in Embodiment 8 of the present invention. Fig.13 A block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention is shown. Fig.13The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.
[0276] like Fig.13 As shown, the computer device 12 is in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).
[0277] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.
[0278] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.
[0279] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Fig.12 not shown, usually called a "hard drive"). Although Fig.13 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.
[0280] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.
[0281] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may communicate with one or more devices that enable a user to interact with the computer device 12, and / or may communicate with any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the computer device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the computer device 12, including, but not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0282] The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28, for example, implementing the recommended method provided in the embodiment of the present invention:
[0283] Obtaining a first search condition input by a user;
[0284] generating a first recommended search element according to the first search condition;
[0285] A second search condition is generated according to the user's adjustment of the first recommended search element.
[0286] Embodiment 9
[0287] Embodiment 9 of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the recommended method provided in all embodiments of the present invention is implemented:
[0288] Obtaining a first search condition input by a user;
[0289] generating a first recommended search element according to the first search condition;
[0290] A second search condition is generated according to the user's adjustment of the first recommended search element.
[0291] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.
[0292] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0293] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
[0294] Computer program code for performing the operations of the present invention may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0295] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims
1. A method for recommending search conditions. It is characterized in that include: Obtaining a first search condition input by a user; generating a first recommended search element according to the first search condition; generating a second search condition according to the user's adjustment of the first recommended search element; The step of generating a first recommended search element according to the first search condition includes: Extracting features from the first search condition to obtain a first keyword, and generating a first search result based on the first keyword; the first search result includes published patent documents or patent application documents related to the first keyword in a patent document library; Sorting the first search results according to a preset rule, and confirming that a preset number of first search results ranked first are first recommended results; Obtaining a first extended keyword of the text content at the preset position of the first recommendation result, and / or a first classification number corresponding to the text content at the preset position of the first recommendation result, wherein the first extended keyword matches the first keyword, and the technical field of the first classification number is the same as or similar to the technical field of the text content at the preset position of the first recommendation result; the first classification number is determined based on the frequency of occurrence of the classification number corresponding to the first keyword and the first extended keyword, or based on the hierarchical relationship between the first keyword and the classification number corresponding to the first extended keyword, or based on a model trained based on the co-occurrence relationship between classification numbers in a patent database; Generate the first recommended search element according to the first keyword, the first extended keyword and / or the first classification number; The step of generating the second search condition according to the user's adjustment of the first recommended search element comprises: Generate a second search result according to the second search condition, and generate a second recommended search element according to the second search result; generating a third search condition according to the user's adjustment of the second recommended search element; Generate a third search result according to the third search condition; The step of generating a first search result according to the first keyword includes: If the keyword or keyword combination input by the user includes a preset formula, searching is performed according to the preset formula to obtain the first search result; If the keyword or keyword combination input by the user does not include the preset formula, the relationship between the keywords or keyword combinations is analyzed by a trained neural network model, and a retrieval formula is given, and the first retrieval result is obtained by searching according to the retrieval formula.
2. The recommendation method according to claim 1, It is characterized in that Generating a first recommended search element according to the first search condition includes: Perform feature extraction on the first search condition to obtain a first keyword; Acquire a first extended keyword related to the first keyword, and / or acquire a first classification number related to the first keyword and / or the first extended keyword; The first recommended search element is generated according to the first keyword, the first extended keyword and / or the first classification code.
3. The recommendation method according to any one of claims 1 or 2, It is characterized in that Generating the second search condition according to the user's adjustment of the first recommended search element includes: displaying the first recommended search element; A second search condition is generated according to the user's selection of the first keyword, the first extended keyword and / or the first classification number.
4. The recommendation method according to claim 3, It is characterized in that Generating the second search condition according to the user's selection of the first keyword, the first extended keyword and / or the first classification number comprises: receiving a user's instruction to add and / or delete the first keyword, the first extended keyword and / or the first classification number; Add and / or delete one or more of the first keyword, the first extended keyword and / or the first classification number based on the adding and / or deleting instruction; A second search condition is generated based on the first keyword, the first extended keyword and / or the first classification number that are retained after the adding and / or deleting actions.
5. A device for recommending search conditions, It is characterized in that include: An acquisition module, used to acquire a first search condition input by a user; A recommendation module, configured to generate a first recommended search element according to the first search condition; An adjustment module, configured to generate a second search condition according to the user's adjustment of the first recommended search element; The recommendation module is specifically used to extract features from the first search condition to obtain a first keyword, and generate a first search result according to the first keyword; the first search result includes published patent documents or patent application documents related to the first keyword in the patent document library; the first search result is sorted according to a preset rule, and a preset number of first search results that are ranked first are confirmed as the first recommendation result; the first extended keyword of the text content at the preset position of the first recommendation result and / or the first classification number corresponding to the text content at the preset position of the first recommendation result are obtained, the first extended keyword matches the first keyword, and the technical field of the first classification number is the same or similar to the technical field of the text content at the preset position of the first recommendation result; the first classification number is determined based on the frequency of occurrence of the classification number corresponding to the first keyword and the first extended keyword, or based on the hierarchical relationship between the first keyword and the classification number corresponding to the first extended keyword, or based on a model trained based on the co-occurrence relationship between the classification numbers in the patent database; the first recommended search element is generated according to the first keyword, the first extended keyword and / or the first classification number; Wherein, the recommendation module is further used to generate a second recommended search element according to the second search result; The adjustment module is further used to generate a third search condition according to the user's adjustment of the second recommended search element; Wherein, the matching module is used to generate a second search result according to the second search condition, and generate a third search result according to the third search condition; Among them, the recommendation module is specifically used to, if the keywords or keyword combinations input by the user include a preset formula, perform a search according to the preset formula to obtain the first search result; if the keywords or keyword combinations input by the user do not include the preset formula, analyze the relationship between the keywords or keyword combinations through a trained neural network model, and give a search formula, and perform a search according to the search formula to obtain the first search result.
6. A device for recommending search conditions, It is characterized in that include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the recommendation method as described in any one of claims 1 to 4.
7. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the recommendation method as claimed in any one of claims 1 to 4 is implemented.
