A method and device for determining target search information

Abstract

The present application provides a method and device for determining target search information, which relates to the field of computer technology. The method includes: in response to a target user triggering a target search information selection operation for a target text, displaying at least one target search information set, wherein the target search information set includes at least two different target search words, each of which is part of the text information in the target text, and any two of the target search words in each of the target search information sets are not located continuously in the target text; in response to a search operation triggered by the target user for any of the target search information sets, searching is performed based on the target search words in the target search set. The needs of the target user can be met through one search, which improves the efficiency of the search, provides convenience for the target user, and enhances the user experience of the target user.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and device for determining target search information. Background Art

[0002] With the development of computer technology and network technology, search needs are everywhere. Users can usually enter search statements that reflect their own information acquisition needs through applications that provide information search services, triggering the application to search in the information database available on the Internet according to the search statement, obtain corresponding search results and display them, in order to obtain information that meets their needs.

[0003] In the related art, in addition to the above-mentioned search methods, users can also search in common reading scenarios, for example, after reading an article, the user searches for a word of interest.

[0004] In the reading scenario in the related art, the user's search demand for a single search word can be met, but the user's search demand for querying multiple search words in an article cannot be met. Summary of the invention

[0005] The embodiments of the present application provide a method and device for determining target search information, which are used to meet the search needs of users for querying multiple search terms in an article.

[0006] On the one hand, an embodiment of the present application provides a method for determining target search information, the method comprising:

[0007] In response to a target user triggering a target search information selection operation for a target text, at least one target search information set is displayed, wherein the target search information set includes at least two different target search words, each of which is part of text information in the target text, and any two of the target search words in each of the target search information sets are not located consecutively in the target text;

[0008] In response to a search operation triggered by the target user for any of the target search information sets, a search is performed based on the target search terms in the target search set.

[0009] On the one hand, an embodiment of the present application provides a target search information determination device, including:

[0010] A target search information set display unit, configured to display at least one target search information set in response to a target user triggering a target search information selection operation for a target text, wherein the target search information set includes at least two different target search words, each of which is part of text information in the target text, and any two of the target search words in each of the target search information sets are not located consecutively in the target text;

[0011] A search unit is configured to perform a search based on the target search terms in the target search set in response to a search operation triggered by the target user for any of the target search information sets.

[0012] Optionally, the device further includes a target search information set determining unit, and the target search information set determining unit is used to:

[0013] Obtaining a set of search terms to be selected, wherein the set of search terms to be selected includes at least two target search terms, and each target search term is located at a discontinuous position in the target text;

[0014] Determining the recommendation degree of the candidate search word set based on a first historical frequency of searches for the candidate search word set within a first set time period and a second historical frequency of searches for each target search word;

[0015] If it is determined that the recommendation degree matches the recommendation degree threshold, the set of search terms to be selected is used as the target search information set.

[0016] Optionally, the target search information set determination unit is further used to:

[0017] Remove stop words from the target text to obtain the target text to be segmented;

[0018] Perform word segmentation on the target text to be segmented and obtain the word segmentation result;

[0019] Take each noun in the word segmentation result as a candidate search term;

[0020] The historical search frequency of each candidate search word in the word segmentation result being searched within the second set time period is determined, and each candidate search word whose historical search frequency is greater than the search frequency threshold is used as a target search word.

[0021] Optionally, the target search information set determination unit is further used to:

[0022] It is determined that the similarity between the semantics of the candidate search word set and the semantics of the target text is greater than a semantic similarity threshold.

[0023] Optionally, the target search information set determination unit is specifically used to:

[0024] Convert each target search word in the candidate search word set into a corresponding N-dimensional word vector, and add the i-th dimension word vector of each target search word to obtain a first semantic vector of the candidate search word set, where N is greater than or equal to 1, and i belongs to N;

[0025] Determine the N-dimensional word vector corresponding to each text information in the target text, and add the i-th dimension word vector of each text information to obtain the second semantic vector of the target text;

[0026] The similarity between the semantics of the candidate search word set and the semantics of the target text is determined according to the first semantic vector and the second semantic vector.

[0027] Optionally, the target search information set determination unit is specifically used to:

[0028] Acquire a search log within a first set time period, determine a first historical frequency in which all target search terms in the set of to-be-searched terms in the search log are searched at the same time, and determine a second historical frequency in which each target search term in the search log is searched;

[0029] The first target value is determined based on the product of the first search number and the number of target search terms in the search log, the second target value is determined based on the product of the second historical frequency of searches for each target search term in the set, and the recommendation level of the selected search term set is determined based on the quotient of the first target value and the second target value.

[0030] Optionally, the target search information set determination unit is further used to:

[0031] Obtaining the number of operations for obtaining search results obtained after searching the candidate search word set within the first set time period;

[0032] Determining a historical click rate of the set of search terms to be selected according to the number of operations corresponding to the set of search terms to be selected and a first historical frequency of searching the set of search terms to be selected;

[0033] The recommendation degree of the candidate search word set is determined according to the quotient of the first target value and the second target value and the historical click rate of the candidate search word set.

[0034] On the one hand, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the target search information determination method when executing the program.

[0035] On the one hand, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program executable by a computer device. When the program runs on the computer device, the computer device executes a target search information determination method.

[0036] On the one hand, an embodiment of the present application provides a computer program product, including a computer program or instructions, which, when executed, enables at least one processor to execute a target search information determination method.

[0037] In an embodiment of the present application, in response to a target search information selection operation triggered by a target user for a target text, at least one target search information set is displayed to the user, and each target search information set includes at least two different target search terms; that is, when the target user needs to search for some of the target search terms in the target text, what is displayed to the user is not any target search term in the target text, but multiple target search information sets, and the target user can select any target search information set for search.

[0038] Further, in an embodiment of the present application, when the target user determines a target search information set that needs to be searched, a search operation for the target search information set is responded to and a search is performed based on target search terms in the target search information set.

[0039] That is to say, in an embodiment of the present application, when the target user needs to search for part of the information in the target text, multiple target search information sets can be provided to the target user, and each target search information set includes at least two different target search terms, which means that the target user's need to search for at least two target search terms in the target text can be met, thereby meeting the target user's needs through one search, improving the search efficiency, providing convenience for the target user, and enhancing the user experience of the target user. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0041] Figure 1 A schematic diagram showing target search information in the related art;

[0042] Figure 2 A schematic diagram of an application scenario provided for an embodiment of the present application;

[0043] Figure 3 A schematic diagram of an application scenario provided for an embodiment of the present application;

[0044] Figure 4A flowchart of a method for determining target search information provided in an embodiment of the present application;

[0045] Figure 5 A schematic diagram of the structure of a target search information determination device provided in an embodiment of the present application;

[0046] Figure 6 A schematic diagram of the structure of a computer device provided in an embodiment of the present application;

[0047] Figure 7 A schematic diagram of the structure of a Word2Ve model provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described below in conjunction with the drawings in the embodiment of the present application. Obviously, the described embodiment is only a part of the embodiment of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application. In the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other arbitrarily. In addition, although the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in an order different from that here.

[0049] In addition, it should be understood that the terms "system" and "network" in the embodiments of the present application can be used interchangeably. "At least one" refers to one or more, and "multiple" refers to two or more. "And / or" describes the association relationship of the associated objects, indicating that there can be three relationships, for example, A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one of the following (individuals)" or similar expressions thereof refer to any combination of these items, including any combination of single items (individuals) or plural items (individuals). For example, at least one of a, b or c (individuals) can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple. And, unless otherwise specified, the ordinal words such as "first" and "second" mentioned in the embodiments of the present application are used to distinguish multiple objects, and are not used to limit the order, timing, priority or importance of multiple objects. For example, the first set value and the second set value are only used to distinguish the numerical representations of different sets, but do not represent the difference in priority or importance of the two set values.

[0050] For ease of understanding, the terms involved in the embodiments of the present application are explained below.

[0051] Target text: any text information displayed in the interface, which is composed of at least one word, which can be called the target search term; in the embodiment of the present application, the target text can be a short sentence in an article, that is, each short sentence constituting the article can be the target text, or in the embodiment of the present application, the target text is all the text information displayed in the interface, which can be multiple articles or part of the information in an article, which is not limited here.

[0052] Target users: refers to the users who browse the target text. Target users can browse through any interface, and the content they browse is the target text.

[0053] After introducing the above terms, the concept of the present application will now be described based on the problems existing in the related art.

[0054] With the development of the Internet and mobile communication networks, information content is becoming increasingly rich, and there are more and more ways to search for information.

[0055] Users can enter search statements that reflect their own information acquisition needs through applications that provide information search services, triggering the application to search in the information database accessible on the Internet according to the search statements, obtain corresponding search results and display them, in order to obtain information that meets their needs.

[0056] For example, a user may enter a search term in any search engine application, determine the search content corresponding to the search term through the search engine, and display the search content in the interface.

[0057] In the related art, in addition to the above search methods, users can also search in common reading scenarios, such as searching for a word of interest after reading an article. For example, when a user uses an instant messaging application, in an article reading scenario, the user can search for a word of interest in the article.

[0058] There are many specific search methods, such as voice control, gesture control, etc., or by long pressing the article with the user's fingertips to trigger the search operation. For example, when a user reads an article through an instant messaging application and is interested in a certain word in the article, the user long presses the position of the word in the display interface to trigger the search display interface. For example, Figure 1 shown.

[0059] exist Figure 1In the example, the user's interface for reading articles is shown. The article content displayed in the interface is the definition of the patent. The user searches by long pressing the word "utility model"; Figure 1 In the example, after the user long presses the word "utility model", a menu bar is displayed, which includes a search function menu. The user can search by clicking search.

[0060] However, in the related art, when a user needs to search for multiple words of interest in a displayed article at the same time, the user's search needs cannot be met. For example, when a user searches for "invention" and "utility model" at the same time in a displayed patent definition article, the user needs to perform a combined search by himself instead of searching through the search function menu in the menu bar.

[0061] Based on the problems existing in the related technology, an embodiment of the present application provides a method and device for determining target search information, which can display at least one target search information set in response to a target search information selection operation triggered by a target user for a target text, wherein the target search information set includes at least two different target search words, each target search word is partial text information in the target text, and the positions of any two target search words in each target search information set in the target text are not continuous.

[0062] Further, in response to a search operation triggered by a target user for any target search information set, a search is performed based on the target search terms in the target search set.

[0063] In an embodiment of the present application, in response to a target search information selection operation triggered by a target user for a target text, at least one target search information set is displayed to the user, and each target search information set includes at least two different target search terms; that is, when the target user needs to search for some of the target search terms in the target text, what is displayed to the user is not any target search term in the target text, but multiple target search information sets, and the target user can select any target search information set for search.

[0064] Further, in an embodiment of the present application, when the target user determines a target search information set that needs to be searched, a search operation for the target search information set is responded to and a search is performed based on target search terms in the target search information set.

[0065] That is to say, in an embodiment of the present application, when the target user needs to search for part of the information in the target text, multiple target search information sets can be provided to the target user, and each target search information set includes at least two different target search terms, which means that the target user's need to search for at least two target search terms in the target text can be met, thereby meeting the target user's needs through one search, improving the search efficiency, providing convenience for the target user, and enhancing the user experience of the target user.

[0066] After introducing the inventive concept of the present application, a system architecture diagram applicable to the present application is first introduced. Figure 2 As shown, the system architecture includes at least one terminal device 201, a plurality of applications can be run in the terminal device 201, and target text information can be displayed in at least one application.

[0067] In the embodiment of the present application, the client of each application can be installed in the terminal device 201. The client in the terminal device 201 can be an application client such as a browser client store, etc.; the terminal device 201 can also run the applets of each application, and the so-called applets are an application that can be used without downloading and installing. In order to provide users with more diversified business services, developers can develop corresponding applets for the applications of the terminal device 201 (such as instant messaging applications, shopping applications, email applications, etc.), and the applets can be embedded in the applications of the terminal device 201 as sub-applications, and can provide users with corresponding business services by running the sub-applications in the applications (i.e., the corresponding applets).

[0068] The client in the terminal device 101 is the client of each application, that is, each controllable object can be run through the terminal device 101, and the status information data of each controllable object in the terminal device 101 can be reported to the server 102.

[0069] The terminal device 201 can display at least one target search information set in response to a target search information selection operation triggered by the target user for the target text, wherein the target search information set includes at least two different target search words, each target search word is partial text information in the target text, and the positions of any two target search words in each target search information set are not continuous in the target text.

[0070] Furthermore, the terminal device 201 may perform a search based on a target search term in the target search set in response to a search operation triggered by a target user for any target search information set.

[0071] Optionally, in the embodiment of the present application, the terminal device 201 may search in a local search manner, that is, search in the records locally stored in the terminal device 201. In another optional embodiment, the terminal device 201 may send a search request to the server 202 in response to a search operation triggered by a target user for any target search information set, and obtain the search content determined by the server 202. Therefore, in the embodiment of the present application, the system architecture also includes the server 202.

[0072] Further, in an embodiment of the present application, the terminal device 201 can display a target search information request to the server 202 in response to the target user triggering a target search information selection operation for the target text, and the server 202 sends the determined target search information set to the terminal device 201 for display.

[0073] Therefore, in the embodiment of the present application, the server 202 can also determine the target search information set in the target text.

[0074] Furthermore, in an embodiment of the present application, the information of the target search information set sent by the server 202 to the terminal device 201 may be determined by the server 202 after receiving the target search information request, or may be determined by the server 202 before receiving the target search information request, which is not elaborated here.

[0075] The terminal device 201 may include one or more processors 2011, a memory 2012, an I / O interface 2013 for interacting with the server 202, and a display panel 2014, etc. The terminal device 201 may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto.

[0076] The server 202 is a terminal device that provides computing power. The server 202 may include one or more processors 2021, a memory 2022, and an I / O interface 2023 that interacts with the terminal device 201. In addition, the server 202 may also be configured with a database 2024. The server 202 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. The terminal device 201 and the server 202 may be directly or indirectly connected via wired or wireless communication, and this application is not limited here.

[0077] Exemplarily, in the system architecture of the embodiment of the present application, there are multiple terminal devices 201, each terminal device 201 can run an instant messaging application, the instant messaging application has a reading function, and the user browses the target text information through the instant messaging application.

[0078] When the target user triggers a target search information operation for target text information, the terminal device 201 sends a target search information acquisition request to the server 202, which is an instant messaging application server. After receiving the target search information acquisition request, the server 202 determines a target search information set for the target text, and the terminal device 201 displays the target search information set.

[0079] The above process is exemplified as follows Figure 3 As shown, in Figure 3 In the example, after the user long presses the target text "patents are divided into three types: invention, utility model and design", the terminal device 201 sends a target search information acquisition request to the server 202.

[0080] Upon receiving the target search information obtaining request, the server 202 determines a target search information set for the target text, and the terminal device 201 displays the target search information set.

[0081] exist Figure 3 In the search results, the target search information sets displayed are "patent, invention", "patent, utility model", "patent, design", etc.

[0082] When the target user performs a click operation on any of the above target search information sets, a search is performed on the target search terms in the target search information set.

[0083] Of course, the above embodiment is only an exemplary introduction to a method for determining target search information. There are other methods for determining target search information, which are not limited here.

[0084] Based on the above design ideas and the above application scenarios, the target search information determination method of the embodiment of the present application is specifically introduced below.

[0085] like Figure 4 As shown, the embodiment of the present application provides a method for determining target search information, which specifically includes:

[0086] Step S401, in response to a target search information selection operation triggered by a target user for a target text, at least one target search information set is displayed, the target search information set including at least two different target search terms, each target search term is partial text information in the target text, and the positions of any two target search terms in each target search information set are not continuous in the target text.

[0087] In an embodiment of the present application, the executing entity of the target search information determination method may be a target search information determination device, which may be any device in a terminal device, any device in a server, or an application running in a terminal device or a server, without limitation herein.

[0088] In an embodiment of the present application, there are multiple ways of triggering the target text to select a target search information operation. It can be triggered by voice, for example, the target user triggers the target search information selection operation by saying "select target search information" by voice, or the target user can trigger the target search information selection operation by gesture; or the target user can trigger the setting control or a combination of setting controls in the terminal device to trigger the target search information selection operation.

[0089] There is also an optional embodiment, the target user triggers the target search information selection operation by pressing the target text for a set time, for example, when the target user continuously presses the target text for 5 seconds, the target search information selection operation is triggered for the target text. Of course, in the embodiment of the present application, 5 seconds is only an exemplary time setting method, and there are other methods for setting the set time, which will not be described here.

[0090] In the embodiment of the present application, the target text may be the entire content of the article browsed by the user, that is, all text information displayed in the display interface is the target text; the target text may also be part of the content of the article browsed by the user, for example, a short sentence or a paragraph of text information displayed in the display interface is the target text. Of course, there are other ways to define the target text, which will not be elaborated here.

[0091] In an embodiment of the present application, when responding to a target search information selection operation triggered by a target user for a target text, at least one target search information set can be displayed. Specifically, the target search information set includes at least two different target search words, each target search word is partial text information in the target text, and the positions of any two target search words in each target search information set are not continuous in the target text.

[0092] That is to say, in the embodiment of the present application, when the target user needs to search for the target search information of interest in the target text, the determined target search information set will be displayed and recommended to the target user as recommended content.

[0093] Specifically, the number of target search information sets displayed to the target user is not limited, and at least one target search information set is displayed. The number of target search information sets displayed can be a default setting or can be set by the target user when browsing, which will not be elaborated here.

[0094] In an embodiment of the present application, the target search information set includes at least two different target search terms, facilitating the target user to perform combined searches based on at least two different target search terms. Specifically, the number of target search terms in the target search set is not limited, including at least two target search terms. The specific number can be set by default or set by the target user during browsing, which will not be elaborated here.

[0095] In an embodiment of the present application, since the target user triggers the operation of selecting target search information for the target text, the search terms in the target search information set are also partial text information in the target text.

[0096] In an embodiment of the present application, the target search term can be any character or a word composed of multiple characters. Exemplarily, the target search term can be "patent" or "right", and the target search term can also be "patent". Of course, there are other definition methods for the target search term, which will not be elaborated here.

[0097] Further, in an embodiment of the present application, since the related art can implement the function of searching for the text information selected by the user, in an embodiment of the present application, any two target search terms in each target search information set are not consecutive in the target text.

[0098] Exemplarily, the text information browsed by the target user is composed of multiple short sentences, and each short sentence can be the target text corresponding to the target user. Specifically, the text information browsed by the target user is composed of short sentence A, short sentence B, and short sentence C. When the target user triggers the operation of selecting target search information for short sentence C, the target search information set for short sentence C is displayed.

[0099] Specifically, short sentence C includes target search term 1, target search term 2, target search term 3, and target search term 4, and the order of each target search term in short sentence C is target search term 1, target search term 2, target search term 3, and target search term 4.

[0100] The target search information set displayed for short sentence C is composed of the above-mentioned at least two non-consecutive target search terms. Exemplarily, the target search information set displayed for short sentence C includes set 1, set 2, and set 3. The content of set 1 is target search term 1 and target search term 3; the content of set 2 is target search term 1 and target search term 4; the content of set 3 is target search term 2 and target search term 4.

[0101] Of course, the above is only an exemplary method for displaying target search information, and there are other methods for displaying target search information, which will not be elaborated here.

[0102] In an embodiment of the present application, in order to be able to promptly display at least one target search information set in response to the target user triggering the target text selection target search information operation, it is also necessary to determine the target search information set before responding to the target user triggering the target text selection target search information operation.

[0103] In the embodiments of the present application, the execution subject for determining the target search information set is not limited. The execution subject may be a target search information determination device, which may be any device in a terminal device or any device in a server, or may be an application running in a terminal device or a server, which is not limited here.

[0104] The following is an introduction on how to determine the target search information set without limiting the execution subject.

[0105] In an embodiment of the present application, when determining a target search information set corresponding to a target text, it is first necessary to obtain a set of candidate search terms, the set of candidate search terms including at least two target search terms, and the position of each target search term in the target text is not continuous.

[0106] In the embodiment of the present application, each set of candidate search terms includes at least two target search terms, and the specific number of target search terms is not limited herein, wherein the target search terms are text information with discontinuous positions in the target text.

[0107] In an embodiment of the present application, in order to meet the search needs of the target user, multiple target search words in the displayed target search information set have search correlation, that is, to meet the target user's needs for jointly searching for multiple information in the target text. When it is determined that multiple target search words in the candidate search word set have search correlation, or the search correlation meets the search correlation condition requirements, the candidate search word set can be determined as the target search information set, and the multiple target search words in the target search information set can meet the target user's search needs for simultaneously searching at least two discontinuous text information in the target text.

[0108] Therefore, in the embodiment of the present application, it is first necessary to determine whether the set of candidate search terms is the target search set. The specific method is to determine the search correlation between different target search terms in the set of candidate search terms.

[0109] Before introducing the method of determining the search relevance between different target search terms, it is first necessary to determine the target search terms in the target text.

[0110] In the embodiment of the present application, since the probability of punctuation information and other stop words in the target text being used as target search words is relatively small, all punctuation information and other stop words in the target text may be removed first.

[0111] Then, the target search term is determined in the target text after all punctuation marks are removed. In the embodiment of the present application, for the convenience of description, the target text after all punctuation marks are removed is used as the target text to be segmented.

[0112] In an embodiment of the present application, all words in the target text to be segmented may be used as target search words, or some words in the target text to be segmented that meet the search conditions may be used as target search words.

[0113] In an optional embodiment, the search conditions can be determined according to the type of words searched by the target user. For example, the type of words searched by the target user is noun, so the target text to be segmented can be segmented to obtain segmentation results; each noun in the segmentation result is used as a candidate search word.

[0114] Of course, the above embodiment is only an optional method for determining the candidate search words. The candidate search words in the target text to be segmented can also be determined based on the set field words or set context words searched by the target user as search conditions.

[0115] For example, if the target user needs to search for medical terms, all medical terms in the target text to be segmented can be used as candidate search terms; or if the target user needs to search for addresses, all words representing addresses in the target text to be segmented can be used as candidate search terms.

[0116] Of course, there are other methods for determining the search terms to be selected in the target text to be segmented, which will not be elaborated here.

[0117] Furthermore, in the embodiment of the present application, after obtaining the candidate search term, it is also necessary to determine whether the candidate search term is a commonly used search term. If it is not a commonly used search term, it is considered that the search term does not meet the user's search needs.

[0118] Therefore, in an optional embodiment, the historical search frequency of each candidate search word in the word segmentation result being searched within the second set time period is determined, and each candidate search word with a historical search frequency greater than the search frequency threshold is used as a target search word.

[0119] In the above embodiment, the second set time period refers to a time period information that can be defined. The time period can be any set time period information, such as 5 minutes, 10 minutes, 1 hour, 24 hours, etc., and no specific time period information is limited here.

[0120] In an embodiment of the present application, after the target text to be segmented is determined for segmentation processing and the segmentation results are obtained, the historical search frequency of each noun in each segmentation result being searched within the second set time period is determined. Optionally, in an embodiment of the present application, the historical search frequency of each noun being searched within the second set time period can be determined based on the search records generated within the second set time period.

[0121] If it is determined that the historical search frequency of a noun is greater than the search frequency threshold, the corresponding noun can be used as a target search term. If it is determined that the historical search frequency of a noun is not greater than the search frequency threshold, it can be considered that the corresponding noun cannot be used as a target search term.

[0122] Of course, the above embodiment is only an optional method for determining whether each word in the word segmentation result can be used as a target search word. There are other methods, which will not be described here.

[0123] The processing procedures of the above steps are combined below to exemplarily describe a method for determining each target search term from a target text.

[0124] Specifically, in the embodiment of the present application, the target text is "Patents literally refer to proprietary rights and interests". First, stop words in the target text are removed to obtain the target text to be segmented "Patents literally refer to proprietary rights and interests".

[0125] Use a public segmentation tool (such as jieba) to perform word segmentation, and the resulting segmentation result is that patent literally refers to proprietary rights and interests.

[0126] Furthermore, each noun "patent", "literal", "proprietary", "right", and "interest" in the above word segmentation results is used as a candidate search term.

[0127] Furthermore, the search records within one month are obtained, and the search frequency of each of the above-mentioned candidate search terms is determined based on the search records. If the search frequency of "literal" and "proprietary" is not greater than the search frequency threshold, then other nouns are used as target search terms.

[0128] After each target search word is determined, each set of search words to be selected can be determined based on each target search word. Specifically, each target search word that is not in a continuous position in the target text constitutes a set of information to be searched.

[0129] Furthermore, in an embodiment of the present application, in order to ensure that the semantics between the information set to be searched and the target text are the same or similar, that is, to ensure that the semantics between the information set to be searched and the target text are not offset, after determining each information set to be searched, it is also necessary to determine whether the similarity between the semantics of the selected search term set and the semantics of the target text is greater than the semantic similarity threshold.

[0130] In an embodiment of the present application, there are multiple methods for determining whether the similarity between the semantics of the candidate search word set and the semantics of the target text is greater than a semantic similarity threshold, such as converting the semantics of the candidate search word set into a vector, and determining through the distance between the vectors that the similarity between the semantics of the candidate search word set and the semantics of the target text is greater than a semantic similarity threshold.

[0131] Specifically, in an embodiment of the present application, each target search word in the set of candidate search words is converted into a corresponding N-dimensional word vector, and the i-th dimensional word vector of each target search word is added to obtain a first semantic vector of the set of candidate search words, where N is greater than or equal to 1 and i belongs to N; the N-dimensional word vector corresponding to each text information in the target text is determined, and the i-th dimensional word vector of each text information is added to obtain a second semantic vector of the target text; the similarity between the semantics of the set of candidate search words and the semantics of the target text is determined based on the first semantic vector and the second semantic vector.

[0132] That is to say, the set of candidate search terms includes multiple target search terms. Each target search term is converted into an N-dimensional word vector, and then each dimension of the N-dimensional word vector is added to obtain the first semantic vector of the set of candidate search terms. The same principle is used to obtain the N-dimensional word vector corresponding to each text information in the target text, and the i-th dimension word vector of each text information is added to obtain the second semantic vector of the target text.

[0133] In an embodiment of the present application, the similarity between the semantics of the selected search word set and the semantics of the target text can be determined by converting the word vector to a Word2Vec model.

[0134] Specifically, the Word2Ve model is a neural network model that is trained to reconstruct linguistic word texts. The Word2Vec model can determine that each target search word in the candidate search word set is represented as an N-dimensional semantic vector using a dictionary. Similarly, the Word2Vec model can convert each word in the target text into an N-dimensional semantic vector and add them together to obtain the N-dimensional semantic vector corresponding to the target text.

[0135] The following exemplary combinations Figure 7 Introducing the Word2Vec model, Figure 7 The Word2Vec model includes an input layer, a hidden layer, and an output layer.

[0136] First, in the input layer, the input words or text information are one-hot encoded based on the vocabulary obtained from the training. Suppose 10,000 unique and non-repeating words are extracted from the training document to form a vocabulary. We one-hot encode these 10,000 words, and each word obtained is a 10,000-dimensional vector. The value of each dimension of the vector is only 0 or 1. If the word ants appears in the vocabulary as the third position, then the vector of ants is a 10,000-dimensional vector with the third dimension value of 1 and other dimensions as 0 (ants = [0,0,1,0,...,0]).

[0137] In an embodiment of the present application, in the hidden layer, all one-hot codes are multiplied by a shared input weight matrix to obtain an initial vector, and then the initial vectors are added and averaged as the hidden layer vector.

[0138] In the output layer, the obtained hidden layer vector is linearly processed by the activation function to obtain a probability distribution, in which the word or text information indicated by the largest probability is the middle result predicted by the output layer.

[0139] If the input of the Word2Vec model is a 10,000-dimensional vector, then the output is also a 10,000-dimensional vector, which contains 10,000 probabilities, each of which represents the probability that the current word is the output word or text information in the input sample (that is, the input word or text information).

[0140] Then, based on any method for determining the distance between vectors, the similarity between the semantics of the search word set and the semantics of the target text can be determined. Optionally, cosine distance, Euclidean distance or other methods for determining the similarity between vectors can be used, which are not limited here.

[0141] Exemplarily, the set of search terms to be selected includes a target search term A and a target search term B. The target search term A is converted into a 32-dimensional vector through the Word2Vec model, and the target search term B is converted into a 32-dimensional vector. The first-dimensional vector of the target search term A is added to the first-dimensional vector of the target search term B, and the second-dimensional vector of the target search term A is added to the second-dimensional vector of the target search term B, and so on. The 32-dimensional vector of the target search term A is added to the 32-dimensional vector of the target search term B to obtain a first semantic vector.

[0142] Based on the same principle, the target text includes target search word A, target search word B, target search word C and target search word D. The target search word A is converted into a 32-dimensional vector, the target search word B is converted into a 32-dimensional vector, the target search word C is converted into a 32-dimensional vector, and the target search word D is converted into a 32-dimensional vector through the Word2Vec model.

[0143] Add the first-dimensional vector of target search word A to the first-dimensional vectors of target search word B, target search word C, and target search word D, add the second-dimensional vector of target search word A to the second-dimensional vectors of target search word B, target search word C, and target search word D, and so on. Add the 32nd-dimensional vector of target search word A to the 32nd-dimensional vectors of target search word B, target search word C, and target search word D to obtain the second semantic vector.

[0144] Then, the cosine distance between the first semantic vector and the second semantic vector is determined, and the similarity between the semantics of the search word set and the semantics of the target text is determined based on the cosine distance. If it is determined that the similarity is not greater than the semantic similarity threshold, it can be considered that the candidate search word set does not meet the search needs of the target user, and the candidate search word set is deleted, and it is no longer determined whether the candidate search word set is the target search set.

[0145] After the above-mentioned determination of the set of search terms to be selected is introduced, it is still necessary to determine whether the set of search terms to be selected is a target search information set.

[0146] In the embodiment of the present application, whether the set of candidate search words is a target search information set is determined by determining the search relevance between different target search words in the set of candidate search words.

[0147] In the embodiment of the present application, there are multiple methods for determining the search relevance between different target search terms in the set of candidate search terms. The following exemplifies several methods for determining the search relevance between different target search terms in the set of candidate search terms.

[0148] In an optional embodiment, the search correlation between different target search terms can be determined based on the semantic correlation between different target search terms. It can be considered that when the semantic correlation between different target search terms meets the set correlation condition, it can be indicated that the search correlation between different target search terms is also met.

[0149] Specifically, in an embodiment of the present application, different target search words may be vectorized to obtain a word vector corresponding to each target search word, and then the similarity between the word vectors may be determined, and the similarity may ensure semantic relevance.

[0150] Further, in the embodiment of the present application, the higher the similarity, the higher the semantic relevance can be determined; the lower the similarity, the lower the speech relevance can be determined.

[0151] In an embodiment of the present application, there are multiple methods for determining the similarity between vectors. In one optional method, the Euclidean distance between different vectors is determined. When the Euclidean distance is greater than the set distance, it can be determined that the similarity between the two vectors is small; when the Euclidean distance is less than the set distance, it can be determined that the similarity between the two vectors is large.

[0152] In another optional method, the similarity between different vectors can be measured by Manhattan distance, Chebyshev distance, Mahalanobis distance, etc., which will not be described in detail.

[0153] In another optional method, the similarity between different vectors is determined by the correlation coefficient between different vectors. The larger the absolute value of the correlation coefficient is, the higher the similarity between the same vectors is.

[0154] Of course, the above are just a few optional methods for determining the similarity between different vectors. There are other methods, which will not be described here.

[0155] After introducing the method of determining the search relevance between different target search terms in the above embodiment, there is another method of determining the search relevance between different target search terms.

[0156] Specifically, in an embodiment of the present application, the recommendation degree of the candidate search word set is determined based on the first historical frequency of the candidate search word set being searched within a first set time period, and the second historical frequency of each target search word being searched; if it is determined that the recommendation degree matches the recommendation degree threshold, the candidate search word set is used as the target search information set.

[0157] The first set time in the above embodiment refers to any set time period, for example, it can be 1 day, or it can be 10 days, or it can be 30 days, etc., and is not specifically limited here.

[0158] The above embodiment determines the recommendation degree of the set of candidate search terms based on the frequency of simultaneous search of different target search terms and the frequency of separate search of different target search terms, that is, the search correlation between different target search terms. The higher the recommendation degree, the higher the search correlation between different target search terms.

[0159] Optionally, in an embodiment of the present application, the first historical frequency and the second historical frequency can be determined based on search records, that is, first obtain all search records generated within a first set time period, and based on the search records, determine the first historical frequency of the selected search word set being searched, and the second historical frequency of each target search word being searched.

[0160] Optionally, the search record may be a search record generated by the target user in an application with a search function, or a search record generated by the target user in multiple applications with a search function, or a search record generated by multiple users in the same application with a search function, or a search record generated by different users in different applications with a search function, without any specific limitation here.

[0161] Further, in the embodiment of the present application, the recommendation degree of the candidate search word set can be determined by the co-occurrence algorithm PMI. Specifically, the definition of PMI is explained by taking the candidate search word set including two target search words as an example, as shown in Formula 1:

[0162]

[0163] In Formula 1, x represents the first target search word in the set of search words, y represents the second target search word in the set of search words, p(x, y) represents the frequency of the two target search words being searched at the same time, p(x) represents the frequency of the first target search word being searched alone, and p(y) represents the frequency of the second target search word being searched alone.

[0164] According to the knowledge of probability, if x and y in formula 1 are unrelated, then the relationship between p(x, y) and p(x) and p(y) can be represented by formula 2, specifically:

[0165] p(x,y)=p(x)p(y) Formula 2

[0166] The greater the correlation between p(x) and p(y), the greater the ratio of p(x, y) to p(x) and p(y).

[0167] It can be seen from the above embodiment that the closer the result in Formula 1 is to 1, the higher the recommendation degree is, so the search relevance between different target search terms can be determined based on Formula 1.

[0168] For example, in the embodiment of the present application, the set of search terms to be selected includes two target search terms, namely search term A and search term B. In the search records within the first set time period, the number of times search term A and search term B are searched at the same time is 5000, search term A is searched 6000 times as an independent search term, and search term B is searched 1000 times as an independent search term. Then, the recommendation degree can be determined based on formula 1 as

[0169] Furthermore, in the embodiment of the present application, when determining the frequency of search terms A and B, it is also possible to consider how many search terms have been searched within the first set time period, which can more accurately represent the search frequency within the first set time period.

[0170] Specifically, the recommendation degree can be represented as Wherein N represents that N search terms have been searched within the first set time period.

[0171] Of course, the above is only an exemplary method for determining the search relevance between different target search terms in the set of candidate search terms. There are other methods, which will not be elaborated here.

[0172] In an embodiment of the present application, after determining the search relevance between different target search terms in the candidate search term set, the recommendation degree of the candidate search term set can also be determined by determining the operations performed on different target search terms in each candidate search term set after the search.

[0173] In the embodiment of the present application, the operation performed after the search refers to the operation performed by the target user or other users on the search information after the search information is obtained. The operation can be a click operation or a sharing operation, etc., which is not specifically limited here.

[0174] In summary, in an embodiment of the present application, the number of operations on the search results obtained after the selected search word set is searched within a first set time period is obtained; the historical click-through rate of the selected search word set is determined based on the number of operations corresponding to the selected search word set and the first historical frequency of the selected search word set being searched; after determining the historical click-through rate, the recommendation degree of the selected search word set is determined in combination with the search relevance between different target search words.

[0175] Exemplarily, in the embodiment of the present application, according to the number of operations corresponding to the candidate search word set and the first historical frequency of searching the candidate search word set, a specific method for determining the historical click rate of the candidate search word set can be shown in Formula 3, which is:

[0176] CTR(Q)= Number of clicks(Q) / Number of searches(Q) Formula 3

[0177] Among them, CTR(Q) can represent the historical click-through rate of each target search word in the set of candidate search words, or CTR(Q) can represent the historical click-through rate of all target search words in the set of candidate search words.

[0178] If CTR(Q) can represent the historical click-through rate of all target search terms in the set of candidate search terms, then the number of clicks (Q) in Formula 3 is the total number of clicks for all target search terms in the set of candidate search terms, that is, the sum of the number of operations; the number of searches (Q) represents the total number of searches for all target search terms in the set of candidate search terms.

[0179] After determining the historical click rates of the candidate search word set, the recommendation degree of the candidate search word set may be determined in combination with the search relevance between different target search words in the candidate search word set.

[0180] Specifically, in the embodiment of the present application, the CTR(Q) obtained in Formula 3 and the PMI obtained in Formula 1 may be combined to determine the recommendation degree of the set of words to be searched.

[0181] Optionally, the sum of CTR(Q) and the PMI in Formula 1 may be used as the recommendation degree of the set of words to be searched.

[0182] Alternatively, the product of CTR(Q) and the PMI in Formula 1 may be used as the recommendation degree of the set of words to be searched.

[0183] Alternatively, the average value between CTR(Q) and PMI in Formula 1 may be used as the recommendation degree of the set of words to be searched.

[0184] Of course, there are other methods for comprehensively determining the recommendation degree of the to-be-searched word set by combining CTR(Q) and the PMI in Formula 1, which will not be elaborated here.

[0185] In an embodiment of the present application, after the recommendation degree of the search word set is determined, it can be determined whether the search word set is a target search information set based on the recommendation degree of each search word set; in an optional embodiment, if the recommendation degree of each search word set matches the recommendation degree threshold, the search word set can be considered to be the target search information set.

[0186] In the embodiment of the present application, the recommendation degree of each search word set matches the recommendation degree threshold, which means that the recommendation degree of each search word set is greater than the recommendation degree threshold, or the difference between the recommendation degree of each search word set and the recommendation degree threshold is less than the set threshold, which is not limited here.

[0187] In an embodiment of the present application, all target search information sets can be displayed, or a display quantity threshold can be set to sort the recommendation degrees corresponding to each target search information set from high to low, and the target search information sets of a number matching the display quantity threshold can be displayed to the target user.

[0188] Step S402: In response to a search operation triggered by a target user for any of the target search information sets, a search is performed based on a target search term in the target search set.

[0189] In the embodiment of the present application, after determining the target search information set, the target user will trigger a search operation on the target search information set, and then perform a search based on each target search term in the target search information set.

[0190] In the embodiment of the present application, the search based on the target search term in the target search set may be performed by the terminal or by a server communicating with the terminal, which will not be elaborated here.

[0191] In an embodiment of the present application, in response to a target search information selection operation triggered by a target user for a target text, at least one target search information set is displayed to the user, and each target search information set includes at least two different target search terms; that is, when the target user needs to search for some of the target search terms in the target text, what is displayed to the user is not any target search term in the target text, but multiple target search information sets, and the target user can select any target search information set for search.

[0192] Further, in an embodiment of the present application, when the target user determines a target search information set that needs to be searched, a search operation for the target search information set is responded to and a search is performed based on target search terms in the target search information set.

[0193] That is to say, in an embodiment of the present application, when the target user needs to search for part of the information in the target text, multiple target search information sets can be provided to the target user, and each target search information set includes at least two different target search terms, which means that the target user's need to search for at least two target search terms in the target text can be met, thereby meeting the target user's needs through one search, improving the search efficiency, providing convenience for the target user, and enhancing the user experience of the target user.

[0194] Based on the same technical concept, the embodiment of the present application provides a target search information determination device 500, such as Figure 5 As shown, including:

[0195] The target search information set display unit 501 is used to display at least one target search information set in response to a target user triggering a target search information selection operation for a target text, wherein the target search information set includes at least two different target search words, each target search word is part of text information in the target text, and any two target search words in each target search information set are not located continuously in the target text;

[0196] The search unit 502 is configured to perform a search based on a target search term in the target search set in response to a search operation triggered by a target user for any target search information set.

[0197] Optionally, the apparatus 500 further includes a target search information set determining unit 503, and the target search information set determining unit 503 is used to:

[0198] Obtaining a set of search terms to be selected, wherein the set of search terms to be selected includes at least two target search terms, and each target search term is located at a discontinuous position in the target text;

[0199] Determining the recommendation degree of the candidate search word set based on a first historical frequency of searches for the candidate search word set within a first set time period and a second historical frequency of searches for each target search word;

[0200] If it is determined that the recommendation degree matches the recommendation degree threshold, the set of search terms to be selected is used as the target search information set.

[0201] Optionally, the target search information set determining unit 503 is further configured to:

[0202] Remove stop words from the target text to obtain the target text to be segmented;

[0203] Perform word segmentation on the target text to be segmented and obtain the word segmentation result;

[0204] Take each noun in the word segmentation result as a candidate search term;

[0205] The historical search frequency of each candidate search word in the word segmentation result being searched within the second set time period is determined, and each candidate search word whose historical search frequency is greater than the search frequency threshold is used as a target search word.

[0206] Optionally, the target search information set determining unit 503 is further configured to:

[0207] It is determined that the similarity between the semantics of the candidate search word set and the semantics of the target text is greater than a semantic similarity threshold.

[0208] Optionally, the target search information set determining unit 503 is specifically configured to:

[0209] Convert each target search word in the candidate search word set into a corresponding N-dimensional word vector, and add the i-th dimension word vector of each target search word to obtain a first semantic vector of the candidate search word set, where N is greater than or equal to 1, and i belongs to N;

[0210] Determine the N-dimensional word vector corresponding to each text information in the target text, and add the i-th dimension word vector of each text information to obtain the second semantic vector of the target text;

[0211] The similarity between the semantics of the candidate search word set and the semantics of the target text is determined according to the first semantic vector and the second semantic vector.

[0212] Optionally, the target search information set determining unit 503 is specifically configured to:

[0213] Acquire a search log within a first set time period, determine a first historical frequency in which all target search terms in the set of to-be-searched terms in the search log are searched at the same time, and determine a second historical frequency in which each target search term in the search log is searched;

[0214] The first target value is determined based on the product of the first search number and the number of target search terms in the search log, the second target value is determined based on the product of the second historical frequency of searches for each target search term in the set, and the recommendation level of the selected search term set is determined based on the quotient of the first target value and the second target value.

[0215] Optionally, the target search information set determining unit 503 is further configured to:

[0216] Obtaining the number of operations for obtaining search results obtained after searching the candidate search word set within the first set time period;

[0217] Determining a historical click rate of the set of search terms to be selected according to the number of operations corresponding to the set of search terms to be selected and a first historical frequency of searching the set of search terms to be selected;

[0218] The recommendation degree of the candidate search word set is determined according to the quotient of the first target value and the second target value and the historical click rate of the candidate search word set.

[0219] Based on the same technical concept, the embodiment of the present application provides a computer device, such as Figure 6 As shown, it includes at least one processor 601 and a memory 602 connected to the at least one processor. The specific connection medium between the processor 601 and the memory 602 is not limited in the embodiment of the present application. Figure 6 For example, the processor 601 and the memory 602 are connected via a bus. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0220] In the embodiment of the present application, the memory 602 stores instructions that can be executed by at least one processor 601. The at least one processor 601 can execute the steps included in the aforementioned target search information determination method by executing the instructions stored in the memory 602.

[0221] Among them, the processor 601 is the control center of the computer device, which can use various interfaces and lines to connect various parts of the computer device, and create a virtual machine by running or executing instructions stored in the memory 602 and calling data stored in the memory 602. Optionally, the processor 601 may include one or more processing units, and the processor 601 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 601. In some embodiments, the processor 601 and the memory 602 may be implemented on the same chip, and in some embodiments, they may also be implemented separately on independent chips.

[0222] Processor 601 can be a general-purpose processor, such as a central processing unit (CPU), a digital signal processor, an application-specific integrated circuit (ASIC), a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, and can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application. A general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware processor for execution, or can be executed by a combination of hardware and software modules in the processor.

[0223] The memory 602 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The memory 602 may include at least one type of storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory, a random access memory (Random Access Memory, RAM), a static random access memory (Static Random Access Memory, SRAM), a programmable read-only memory (Programmable Read Only Memory, PROM), a read-only memory (Read Only Memory, ROM), an electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), a magnetic memory, a disk, an optical disk, etc. The memory 602 is any other medium that can be used to carry or store a desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 602 in the embodiment of the present application can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.

[0224] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program that can be executed by a computer device. When the program runs on the computer device, the computer device executes the steps of the target search information determination method.

[0225] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0226] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0227] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0228] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0229] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for determining target search information, characterized in that: The method comprises: Using some words that meet the search conditions in the target text after all punctuation marks are removed as target search words, wherein the search conditions are determined according to the type of words searched by the target user; Obtaining a plurality of candidate search word sets, each candidate search word set including at least two of the target search words, and each of the target search words being located in a discontinuous position in the target text; For each candidate search word set, based on a first historical frequency of searches for the candidate search word set within a first set time period and a second historical frequency of searches for each target search word, a recommendation degree of the candidate search word set is determined; if it is determined that the recommendation degree matches a recommendation degree threshold, the candidate search word set is used as a target search information set; In response to a target user triggering a target search information selection operation for a target text, displaying a plurality of target search information sets; In response to a search operation triggered by the target user for any of the target search information sets, a search is performed based on the target search terms in the target search information set.

2. The method according to claim 1, characterized in that The target text with all punctuation marks removed and the words that meet the search conditions are used as target search words, including: Removing stop words from the target text to obtain a target text to be segmented; Performing word segmentation processing on the target text to be segmented to obtain a word segmentation result; Taking each noun in the word segmentation result as the candidate search word; Determine the historical search frequency of each candidate search word in the word segmentation result being searched within a second set time period, and use each candidate search word whose historical search frequency is greater than a search frequency threshold as the target search word.

3. The method according to claim 2, characterized in that Also includes: It is determined that the similarity between the semantics of the candidate search word set and the semantics of the target text is greater than a semantic similarity threshold.

4. The method according to claim 3, characterized in that: The determining the similarity between the semantics of the candidate search word set and the semantics of the target text includes: Convert each of the target search words in the set of candidate search words into a corresponding N-dimensional word vector, and add the i-th dimension word vectors of each of the target search words to obtain a first semantic vector of the set of candidate search words, where N is greater than or equal to 1 and i belongs to N; Determine an N-dimensional word vector corresponding to each text information in the target text, and add the i-th dimension word vector of each text information to obtain a second semantic vector of the target text; The similarity between the semantics of the candidate search word set and the semantics of the target text is determined according to the first semantic vector and the second semantic vector.

5. The method according to claim 1, characterized in that The determining the recommendation degree of the set of candidate search terms based on a first historical frequency of searches for the set of candidate search terms within a first set time period and a second historical frequency of searches for each of the target search terms includes: Acquire the search log within the first set time period, determine the first historical frequency at which all the target search terms in the set of candidate search terms in the search log are searched at the same time, and determine the second historical frequency at which each of the target search terms in the search log is searched; A first target value is determined based on the product of the first historical frequency and the number of target search terms in the search log, a second target value is determined based on the product of the second historical frequency at which each of the target search terms in the set is searched, and a recommendation level of the set of candidate search terms is determined based on the quotient of the first target value and the second target value.

6. The method according to claim 5, characterized in that After determining the first target value according to the product of the first historical frequency and the number of target search terms in the search log, and determining the second target value according to the product of the second historical frequency of searches for each target search term in the set, the method further includes: Obtaining the number of operations for obtaining search results obtained after searching the candidate search word set within the first set time period; Determining a historical click rate of the set of search terms to be selected according to the number of operations corresponding to the set of search terms to be selected and a first historical frequency of searching the set of search terms to be selected; The recommendation degree of the candidate search word set is determined according to the quotient of the first target value and the second target value and the historical click rate of the candidate search word set.

7. A target search information determination device, characterized in that: include: A target search information set display unit, used to use part of the words that meet the search conditions in the target text without all punctuation marks as target search words, wherein the search conditions are determined according to the type of words searched by the target user; Obtaining a plurality of candidate search word sets, each candidate search word set including at least two of the target search words, and each of the target search words being located in a discontinuous position in the target text; For each candidate search word set, based on a first historical frequency of searches for the candidate search word set within a first set time period and a second historical frequency of searches for each target search word, a recommendation degree of the candidate search word set is determined; if it is determined that the recommendation degree matches a recommendation degree threshold, the candidate search word set is used as a target search information set; In response to a target user triggering a target search information selection operation for a target text, displaying a plurality of target search information sets; A search unit is configured to perform a search based on the target search terms in the target search information set in response to a search operation triggered by the target user for any of the target search information sets.

8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of any method described in claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that: It stores a computer program executable by a computer device, and when the program is run on the computer device, the computer device executes the steps of any method described in claims 1 to 6.

Images