An information search method, apparatus, device, storage medium, and program product

Abstract

The application provides an information search method and device, equipment, storage medium and program product, which are applied to various information search scenes such as cloud technology, artificial intelligence, intelligent transportation and vehicle-mounted devices. The information search method comprises the following steps: displaying a search area in an information input state, wherein the information input state refers to a state of receiving information input; in response to an input operation on the search area, displaying input information, displaying search candidate information corresponding to the input information, and displaying recommended search information corresponding to the search candidate information, wherein the search candidate information is candidate information related to the semantic information of the input information, and the recommended search information is to-be-recommended information determined based on the search candidate information and independent of the semantic information of the search candidate information; and in response to a selection operation on the recommended search information, displaying information search results searched based on the recommended search information. Through the application, the information search effect can be improved.

Description

Technical Field

[0001] This application relates to information processing technology in the field of computer applications, and more particularly to an information search method, apparatus, device, storage medium, and program product. Background Technology

[0002] Generally, when a user inputs data into the search box of a target application, search candidate information is displayed in both the search candidate area of ​​the search box and the keyboard candidate area. This search candidate information is usually the completion information of the input corresponding to the input operation. Therefore, the search candidate information is limited. Consequently, when searching for information based on this search candidate information, the search scope is small, resulting in poor information search performance. Summary of the Invention

[0003] This application provides an information search method, apparatus, device, computer-readable storage medium, and computer program product, which can improve the information search effect.

[0004] The technical solution of this application embodiment is implemented as follows: This application provides an information search method, including: The search area is displayed in the information input state, where the information input state refers to the state of receiving information input; In response to an input operation on the search area, input information is displayed, along with search candidate information corresponding to the input information and recommended search information corresponding to the search candidate information. The search candidate information is semantically related to the input information, and the recommended search information is information to be recommended that is determined based on the search candidate information and is semantically independent of the search candidate information. In response to a selection operation based on the recommended search information, the search results are displayed.

[0005] This application provides an information search device, including: The area display module is used to display the search area in the information input state, wherein the information input state refers to the state of receiving information input; An information input module is used to respond to an input operation for the search area, display input information, and display search candidate information corresponding to the input information and recommended search information corresponding to the search candidate information, wherein the search candidate information is candidate information semantically related to the input information, and the recommended search information is information to be recommended determined based on the search candidate information and semantically independent of the search candidate information; The information search module is used to display the information search results based on the recommended search information in response to the selection operation of the recommended search information.

[0006] In this embodiment of the application, the relationship between the recommended search information and the search candidate information includes at least one of the following: the recommended search information and the search candidate information belong to the same category; the recommended search information and the search candidate information have a similar relationship, wherein the similar relationship means that the probability of different information being converted on the same object is greater than a specified probability.

[0007] In this embodiment of the application, when the recommended search information and the search candidate information belong to the same category, the information search device further includes a combination construction module, which is used to classify multiple strings to be processed to obtain a set of strings to be processed corresponding to each category; and to determine a first specified number of strings to be processed selected from the set of strings to be processed as a combination of strings of the same type, and to obtain each combination of strings of the same type corresponding to each category.

[0008] In this embodiment of the application, the information input module is further configured to respond to the input operation for the search area, perform string matching in each of the same type of string combinations based on the search candidate information corresponding to the input information; in the matched same type of string combinations, determine the strings to be processed other than the search candidate information as the recommended search information, and display the input information, the search candidate information, and the recommended search information.

[0009] In this embodiment of the application, the information input module is further configured to display the input information and the search candidate information when the string matching result indicates that the search candidate information does not match any of the combinations of the same type of strings.

[0010] In this embodiment, when the recommended search information and the search candidate information have a similar relationship, the information search device further includes a combination construction module for obtaining multiple conversion records, wherein each conversion record includes at least two conversion strings corresponding to the target object; obtaining a first specified number of different information from the multiple conversion records to obtain conversion string combinations that are converted on the same target object, and obtaining the number of target objects corresponding to the conversion string combinations; determining the similarity probability corresponding to the conversion string combinations based on the comparison result between the number of target objects and the number of records in the multiple conversion records; and combining the conversion string combinations whose similarity probability is greater than a specified probability to obtain various similarity string combinations.

[0011] In this embodiment of the application, the information input module is further configured to respond to the input operation for the search area, perform string matching in each of the same-interest string combinations based on the search candidate information corresponding to the input information; in the matched same-interest string combinations, determine the converted string other than the search candidate information as the recommended search information, and display the input information, the search candidate information, and the recommended search information.

[0012] In this embodiment, the input information includes at least one of key information, search information to be input, and search information already input. The key information is the information corresponding to the key triggered by the input operation; the search information to be input is the information corresponding to the key information determined based on the input information type; and the search information already input is the information in the search area. The search candidate information includes at least one of input candidate information and search information to be input. The input candidate information is candidate information generated based on the input search information, and the search information to be input refers to candidate information generated based on candidate criteria information, which includes at least one of the key information, the search information to be input, and the search information already input.

[0013] In this embodiment, the information input module is further configured to respond to the input operation triggered by the input control for the search area, display the input information, and display the search candidate information corresponding to the input information and the recommended search information corresponding to the search candidate information in the input candidate area of ​​the input control; wherein, the input control is configured to obtain the information to be searched for the search area, and the input candidate area is configured to display the information generated based on the key information corresponding to the input control.

[0014] In this embodiment of the application, when the input information includes input search information, the information input module is further configured to respond to the input operation for the search area by displaying the input information in the search area, and displaying the search candidate information corresponding to the input information and the recommended search information corresponding to the search candidate information in the search candidate area corresponding to the search area; wherein, the search candidate area is used to display information generated based on the input search information.

[0015] In this embodiment, the information input module is further configured to: respond to the input operation triggered by the input control for the search area; obtain the search candidate information corresponding to the input information; determine a second specified number of candidate strings selected from the search candidate information as strings to be judged; obtain the search intent value corresponding to the string to be judged, wherein the search intent value represents the degree of search intent reflected by the string to be judged; and when the search intent value is greater than a specified search intent value, display the input information, the search candidate information, and the recommended search information.

[0016] In this embodiment of the application, the information input module is further configured to cancel the acquisition of recommended search information when the search intent value is less than or equal to the specified search intent value.

[0017] In this embodiment of the application, the information input module is further configured to obtain the search frequency corresponding to each candidate string in the string to be judged, and obtain the search frequency to be judged corresponding to the string to be judged, wherein the search frequency to be judged is the cumulative value of at least one search frequency; obtain the total search frequency corresponding to the search candidate information; and determine the search intent value corresponding to the string to be judged based on the comparison result between the search frequency to be judged and the total search frequency.

[0018] In this embodiment of the application, the information input module is further configured to, when the search intent value is greater than the specified search intent value, insert the recommended search information between the string to be judged and the remaining string in the search candidate information to obtain a string sequence to be displayed, wherein the remaining string refers to the string in the recommended search information other than the string to be judged; and display the input information and the string sequence to be displayed.

[0019] In this embodiment of the application, the information search module is further configured to, in response to the selection operation for the recommended search information, display the recommended search information in the search area; and, in response to the search operation for the search area displaying the recommended search information, display the information search results obtained based on the recommended search information.

[0020] In this embodiment of the application, the information search module is further configured to, in response to the selection operation for the recommended search information, replace the input search information displayed in the search area with the recommended search information.

[0021] In this embodiment, the information input module is further configured to: obtain the input information in response to the input operation for the search area; acquire, from each piece of data in the specified search candidate library, at least one candidate string including the input information and the search frequency corresponding to each of the at least one candidate string, wherein each piece of data in the specified search candidate library includes the candidate string, the string key information and the search frequency; determine the candidate string with a search frequency greater than a specified search frequency as the search candidate information among the at least one candidate string; and display the input information, the search candidate information, and the recommended search information.

[0022] In this embodiment of the application, the combination construction module is further configured to obtain the string key information and the search frequency corresponding to each of the plurality of candidate strings; combine the string key information and the search frequency corresponding to each candidate string to obtain the specified search candidate library corresponding to the plurality of candidate strings.

[0023] This application provides an information search device, including: Memory, used to store executable instructions; The processor, when executing executable instructions stored in the memory, implements the information search method provided in the embodiments of this application.

[0024] This application provides a computer-readable storage medium storing executable instructions, which, when executed by a processor, implement the information search method provided in this application.

[0025] This application provides a computer program product, including a computer program or instructions, which, when executed by a processor, implement the information search method provided in this application.

[0026] The embodiments of this application have at least the following beneficial effects: when an input operation is received for the search area, not only will the input information corresponding to the input operation and the candidate information semantically related to the input information (referred to as search candidate information) be displayed, but also the recommended information determined based on the input information and semantically independent of the input information (referred to as recommended search information) will be displayed; thus, the diversity of the displayed information corresponding to the input information is improved; thereby, when information search is performed based on the recommended search information, the information search scope can be expanded, thereby improving the information search effect. Attached Figure Description

[0027] Figure 1This is an exemplary schematic diagram of pre-entered search information provided in an embodiment of this application; Figure 2 This is a schematic diagram illustrating an exemplary search information to be input, provided in an embodiment of this application. Figure 3 This is a schematic diagram illustrating an exemplary search candidate information provided in an embodiment of this application; Figure 4 This is an exemplary diagram illustrating the search for candidate information; Figure 5 This is a schematic diagram of the architecture of the information search system provided in the embodiments of this application; Figure 6 This is provided by the embodiments of this application. Figure 5 A schematic diagram of the terminal's composition structure; Figure 7 This is a flowchart illustrating the information search method provided in the embodiments of this application. Figure 1 ; Figure 8 This is a schematic diagram of information display provided in an embodiment of this application; Figure 9 This is a flowchart illustrating the information search method provided in the embodiments of this application. Figure 2 ; Figure 10 This is a schematic diagram of an exemplary information search process provided in an embodiment of this application; Figure 11 This is an exemplary display illustration of information search provided in the embodiments of this application. Figure 1 ; Figure 12 This is an exemplary display illustration of information search provided in the embodiments of this application. Figure 2 ; Figure 13 This is an exemplary display illustration of information search provided in the embodiments of this application. Figure 3 ; Figure 14 This is an exemplary display illustration of information search provided in the embodiments of this application. Figure 4 ; Figure 15 This is an exemplary display illustration of information search provided in the embodiments of this application. Figure 5 ; Figure 16 This is an exemplary display illustration of information search provided in the embodiments of this application. Figure 6 . Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0029] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0030] In the following description, the terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first" and "second" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0031] Unless otherwise defined, all technical and scientific terms used in the embodiments of this application have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the embodiments of this application is for the purpose of describing the embodiments of this application only and is not intended to limit this application.

[0032] Before providing a further detailed description of the embodiments of this application, the nouns and terms involved in the embodiments of this application will be explained, and the nouns and terms involved in the embodiments of this application shall be interpreted as follows.

[0033] 1) Search input information, representing search intention information, including at least one of already entered search information and search information to be entered; wherein, the already entered search information is, for example, information that has been displayed on the screen to the search area, which is the already entered search information in this application embodiment; the search information to be entered is the most frequent information corresponding to the key operation received through the keyboard, which is the search information to be entered in this application embodiment.

[0034] For example, see Figure 1 , Figure 1 This is an exemplary schematic diagram of pre-entered search information provided in an embodiment of this application; such as... Figure 1 As shown, the search box 1-11 on the search page 1-1 has already displayed "Xiao Gang", thus "Xiao Gang" is the search information that has been entered, and also the search input information.

[0035] See Figure 2 , Figure 2 This is an exemplary schematic diagram of search information to be input, provided in an embodiment of this application; such as... Figure 2As shown, in search page 2-1, a user's key operations are received via the virtual keyboard 2-11 (the user successively triggers virtual buttons respectively corresponding to "X", "I", "A", "O", "G", "A", "N", "G" ... on the virtual keyboard 2-11), the keyboard input information (xiao'gang) is displayed in the candidate display area 2-12 corresponding to the keyboard input information, and "Xiao Gang", "Xiao Gang", "Xiao Gang" ... are displayed in the candidate display area 2-12 (referred to as the input candidate area); here, "Xiao Gang" is both the to-be-input search information and the search input information.

[0036] 2) Search candidate information, which is candidate information generated based on search input information, including at least one of candidate information corresponding to a search area and candidate information corresponding to keyboard input information. Wherein, the candidate information corresponding to the search area is candidate information generated by a search application based on input to-be-searched information, which is the input candidate information in the embodiments of the present application, and is displayed in a search candidate area corresponding to the search area; the candidate information corresponding to keyboard input information may be candidate information generated by a keyboard application based on input search information, may also be candidate information generated by the keyboard application based on input information in the virtual keyboard, or may be a combination of both, which is the to-be-input candidate information in the embodiments of the present application, and all is displayed in a keyboard candidate area. In addition, a search application refers to an application with a search function, which is the target application in the embodiments of the present application; a keyboard application refers to an application that acquires input information via a keyboard, for example, an input method application; herein, the keyboard application may generate candidate information based on keyboard information, may also generate candidate information based on to-be-input search information corresponding to the keyboard information, and may also interact with the search application to acquire input search information in the search area of the search application and generate candidate information including the input search information based on the input search information, etc., which is not limited in the embodiments of the present application.

[0037] For example, see Figure 3 , Figure 3 is a schematic diagram of exemplary search candidate information provided by the embodiments of the present application; as Figure 3 shown, the search input information "Xiao Gang" has been committed to the search box 3-11 in the search page 3-1, the information in the search candidate area 3-12 and the information in the keyboard candidate area 3-13 (referred to as the input candidate area) are both search candidate information; wherein, the information in the search candidate area 3-12 is candidate information generated by a video application (referred to as the search application) based on the input search information, and the information in the keyboard candidate area 3-13 is candidate information generated by the keyboard application based on the input search information.

[0038] 3) Content creation object, a content producer who uploads or publishes content on an Internet platform; for example, video providers on short video platforms, anchors on live streaming platforms, etc.

[0039] 4) Similar creative objects refer to at least two content creation objects that belong to the same category based on the content being created; for example, if the content creation object A corresponds to the food category and the content creation object B corresponds to the food category, then content creation object A and content creation object B are similar creative objects.

[0040] 5) Shared creative objects refer to the correlation between content creation objects established based on big data. For example, based on big data of viewing information, it is determined that users who watch the content created by content creation object C are more likely (greater than a threshold) to also watch the content created by content creation object D. Then content creation object C and content creation object D are shared creative objects, which is the shared relationship in the embodiment of this application. As another example, based on big data of search information, it is determined that users who search for content creation object E are more likely (greater than a threshold) to also search for content creation object F. Then content creation object E and content creation object F are shared creative objects.

[0041] Generally, when a user inputs an action into the search box of a target application, search candidate information will be displayed in both the search candidate area of ​​the search box and the keyboard candidate area. This search candidate information is the completion information of the input information corresponding to the input action.

[0042] For example, see Figure 4 , Figure 4 This is an exemplary diagram illustrating search candidate information; such as Figure 4 As shown, the search input information "Xiao Li Tong" has been displayed in the search box 4-11 of the search page 4-1. The information in the search candidate area 4-12 and the information in the keyboard candidate area 4-13 are all search candidate information. Among them, "Xiao Li Tongxue", "Xiao Li Tongzhuo", "Xiao Li Tongyi Qichi", "Xiao Li Tongxue Riji", and "Xiao Li Tongxue Jiayou" in the search candidate area 4-12 are search candidate information obtained by the video application by completing the input information "Xiao Li Tong". The "Xiao Li Tongxue" and "Xiao Li Tongxue Jiayou" in the keyboard candidate area 4-13 are search candidate information obtained by the keyboard application by completing the search input information "Xiao Li Tong".

[0043] However, when search candidate information is obtained by completing the search input information, the search candidate information is limited; therefore, when searching for information based on this search candidate information, only search results including the search input information can be found, the search scope is small, resulting in poor search performance.

[0044] Based on this, embodiments of this application provide an information search method, apparatus, device, computer-readable storage medium, and computer program product, which can improve the information search effect. The following describes exemplary applications of the information search device provided in this application. The information search device provided in this application can be implemented as various types of terminals such as smartphones, smartwatches, laptops, tablets, desktop computers, smart home appliances, set-top boxes, smart in-vehicle devices, portable music players, personal digital assistants, dedicated messaging devices, intelligent voice interaction devices, portable gaming devices, and smart speakers, or it can be implemented as a server. The following will describe exemplary applications when the information search device is implemented as a terminal.

[0045] See Figure 5 , Figure 5 This is a schematic diagram of the architecture of the information search system provided in the embodiments of this application; as shown below. Figure 5 As shown, to support an information search application, in the information search system 100, terminals 400 (terminals 400-1 and 400-2 are shown as examples, referred to as information search devices) are connected to server 200 via network 300. Network 300 can be a wide area network (WAN), a local area network (LAN), or a combination of both. Additionally, the information search system 100 also includes a database 500 for providing data support to server 200; and... Figure 5 The example shown illustrates a scenario where the database 500 is independent of the server 200. However, the database 500 can also be integrated into the server 200, and this embodiment does not limit this to any particular case.

[0046] Terminal 400 is used to display a search area in an information input state, where the information input state refers to the state of receiving information input; in response to an input operation on the search area, it displays the input information and sends a candidate acquisition request to server 200 via network 300; it receives search candidate information corresponding to the input information and recommended search information corresponding to the search candidate information sent by server 200 via network 300, and displays the search candidate information and recommended search information (graphical interfaces 410-1 and 410-2 are shown exemplarily), wherein the search candidate information is candidate information semantically related to the input information, and the recommended search information is information to be recommended determined based on the search candidate information and semantically independent of the search candidate information; in response to a selection operation on the recommended search information, it sends a search request to server 200 via network 300; it receives information search results obtained based on the recommended search information sent by server 200 via network 300, and displays the information search results.

[0047] Server 200 is configured to receive candidate retrieval requests sent by terminal 400 via network 300, and in response to the candidate retrieval requests, retrieve search candidate information corresponding to the input information and recommended search information corresponding to the search candidate information; send the search candidate information and recommended search information to terminal 400 via network 300; receive search requests sent by terminal 400 via network 300, and in response to the search requests, perform information search based on the recommended search information to obtain information search results; and send the information search results to terminal 400 via network 300.

[0048] In some embodiments, server 200 may be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. Terminal 400 may be a smartphone, smartwatch, laptop, tablet, desktop computer, smart TV, set-top box, smart in-vehicle device, portable music player, personal digital assistant, dedicated messaging device, portable gaming device, and smart speaker, but is not limited to these. Terminals and servers can be directly or indirectly connected via wired or wireless communication, which is not limited in this embodiment.

[0049] See Figure 6 , Figure 6 This is provided by the embodiments of this application. Figure 5 A schematic diagram of the terminal's composition structure. Figure 6 The terminal 400 shown includes at least one processor 411, a memory 450, at least one network interface 420, and a user interface 430. The various components in the terminal 400 are coupled together via a bus system 440. It is understood that the bus system 440 is used to implement communication between these components. In addition to a data bus, the bus system 440 also includes a power bus, a control bus, and a status signal bus. However, for clarity, ... Figure 6 The general labeled all buses as Bus System 440.

[0050] Processor 411 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0051] User interface 430 includes one or more output devices 431 that enable the presentation of media content, including one or more speakers and / or one or more visual displays. User interface 430 also includes one or more input devices 432, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

[0052] The memory 450 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state storage, hard disk drives, optical disk drives, etc. The memory 450 may optionally include one or more storage devices physically located away from the processor 411.

[0053] The memory 450 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), and the volatile memory may be random access memory (RAM). The memory 450 described in this application embodiment is intended to include any suitable type of memory.

[0054] In some embodiments, memory 450 is capable of storing data to support various operations, examples of which include programs, modules, and data structures or subsets or supersets thereof, as illustrated below.

[0055] Operating system 451 includes system programs for handling various basic system services and performing hardware-related tasks, such as the framework layer, core library layer, driver layer, etc., for implementing various basic business functions and handling hardware-based tasks; The network communication module 452 is used to reach other computer devices via one or more (wired or wireless) network interfaces 420, exemplary network interfaces 420 including: Bluetooth, Wi-Fi, and Universal Serial Bus (USB), etc. Presentation module 453 is configured to enable the presentation of information (e.g., a user interface for operating peripheral devices and displaying content and information) via one or more output devices 431 associated with user interface 430 (e.g., a display screen, a speaker, etc.). The input processing module 454 is used to detect and translate one or more user inputs or interactions from one or more input devices 432.

[0056] In some embodiments, the information search device provided in this application can be implemented in software. Figure 6An information search device 455 stored in memory 450 is shown. This device can be software in the form of programs and plug-ins, and includes the following software modules: a region display module 4551, an information input module 4552, an information search module 4553, and a combination construction module 4554. These modules are logically connected and can therefore be arbitrarily combined or further separated according to their implemented functions. The functions of each module will be described below.

[0057] In some embodiments, the information search device provided in this application can be implemented in hardware. As an example, the information search device provided in this application can be a processor in the form of a hardware decoding processor, which is programmed to execute the information search method provided in this application. For example, the processor in the form of a hardware decoding processor can be one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0058] In some embodiments, the terminal or server can implement the information search method provided in this application by running a computer program. For example, the computer program can be a native program or software module in an operating system; it can be a native application (APP), that is, a program that needs to be installed in the operating system to run, such as a live streaming APP or an instant messaging APP; it can also be a mini-program, that is, a program that only needs to be downloaded into a browser environment to run; or it can be a mini-program that can be embedded in any APP. In short, the above-mentioned computer program can be any form of application, module or plugin.

[0059] The information search method provided in this application will be described below with reference to exemplary applications and implementations of the information search device provided in the embodiments of this application. Furthermore, the information search method provided in the embodiments of this application is applicable to various information search scenarios such as cloud technology, artificial intelligence, smart transportation, and in-vehicle systems.

[0060] See Figure 7 , Figure 7 This is a flowchart illustrating the information search method provided in the embodiments of this application. Figure 1 , will combine Figure 7 The steps shown are explained.

[0061] Step 701: displaying a search area in an information input state.

[0062] In the embodiment of the present application, when a user performs information search in a target application, when the information search device displays information including the information search function in response to the user's operation, the search area is displayed, and the displayed search area is in an information input state; wherein the information input state refers to a state of receiving information input, for example, the input cursor is focused on the search area; It should be noted that the search area is configured to acquire information to be searched, such as a search box, a delimited area, etc. In addition, when the search area in the information input state is displayed, an input control (for example, a virtual keyboard) may also be displayed, or input prompt information of the input control (for example, Wubi, English, Chinese, etc.) may also be displayed, or information related to the input control may not be displayed (which may be a default input mode at this time), etc., which is not limited in the embodiment of the present application.

[0063] Step 702: responding to an input operation on the search area, displaying input information, and displaying search candidate information corresponding to the input information, and recommended search information corresponding to the search candidate information.

[0064] In the embodiment of the present application, when the user inputs information in the search area, the information search device receives the input operation on the search area; at this time, the information search device responds to the input operation, displays the input information, and displays the search candidate information corresponding to the input information, and the recommended search information corresponding to the search candidate information.

[0065] It should be noted that the input information is information corresponding to the input operation; the search candidate information is candidate information semantically related to the input information; the recommended search information is to-be-recommended information determined based on the search candidate information and semantically independent of the search candidate information; wherein, the recommended search information being semantically independent of the search candidate information means that there is no semantic correlation between the recommended search information and the search candidate information, for example, the search candidate information is "Dubao Meijiang You", and the recommended search information is "Golden Retriever Yolk".

[0066] It should also be noted that the input information includes at least one of key press information, to-be-input search information and already-input search information. Among them, the key press information refers to information corresponding to the key triggered by the input operation, for example, "xiao". The to-be-input search information refers to information corresponding to the key press information determined based on the input information type (for example, Chinese, English, capital letters, etc.), for example, "小", "XIAO", etc.; when the input information type indicates the immediate key input type, the to-be-input search information is the key press information. The already-input search information refers to information in the search area, for example, a character string that has been entered into the search box. The search candidate information includes at least one of already-input candidate information and to-be-input candidate information. Among them, the already-input candidate information refers to search candidate information generated based on the already-input search information in the search area, which can be obtained by acquiring a character string including the already-input candidate information. The to-be-input candidate information is search candidate information semantically related to candidate basis information, and the candidate basis information includes at least one of to-be-input search information, key press information and already-input search information, which can be obtained by acquiring information including at least one of to-be-input search information, key press information and already-input search information. For example, "Xiaogang", "Senior Brother Xiaogang" and "Xiaoyang" obtained based on "小" or "xiao". In addition, both the search candidate information and the recommended search information may be character strings.

[0067] In the embodiment of the present application, the search candidate information is candidate information generated based on input information, and that the search candidate information is semantically related to the input information includes at least two cases; one case is that the search candidate information refers to candidate information including information determined based on the input information.

[0068] For example, when the input information is key press information, that the search candidate information is semantically related to the input information may mean that the search candidate information includes candidate information of to-be-input search information determined based on the input information; for example, when the input information is "xiaogang" and the determined corresponding to-be-input search information are "小刚" and "小港", the search candidate information is "Xiaogang", "Junior Brother Xiaogang", "Xiaogang Bay" and the like.

[0069] For example, when the input information is already-input search information, that the search candidate information is semantically related to the input information may mean that the search candidate information includes candidate information of other input type information determined based on the input information; for example, when the already-input search information is "xiaogang" and the determined other input type information are "小刚" and "小港", the search candidate information is "Xiaogang", "Junior Brother Xiaogang", "Xiaogang Bay" and the like.

[0070] Another case is that the search candidate information refers to candidate information including the input information.

[0071] For example, when the input information is key press information and to-be-input search information, that the search candidate information is semantically related to the input information may mean that the search candidate information includes candidate information of the to-be-input search information in the input information; for example, when the key press information is "xiaogang", and the to-be-input search information are "Xiaogang" and "Xiaogang", the search candidate information are "Xiaogang", "Xiaogang Junior" and "Xiaogang Bay", etc.

[0072] For example, when the input information is to-be-input search information or inputted search information, that the search candidate information is semantically related to the input information means that the search candidate information includes candidate information of the input information; for example, when the to-be-input search information is "little", the search candidate information may be "little" and "little egg", etc.; for another example, when the inputted search information is "Xiaogang", the search candidate information are "Xiaogang Junior" and "Xiaogang Bay", etc.

[0073] Step 703: In response to a selection operation for the recommended search information, display information search results searched based on the recommended search information.

[0074] In the embodiment of the present application, when a user selects the displayed recommended search information to perform information search, the information search device also receives the selection operation for the recommended search information; at this time, the information search device, in response to the selection operation, performs information search based on the recommended search information, and displays the obtained information search results.

[0075] It can be understood that when an input operation for a search area is received, not only the input information corresponding to the input operation and candidate information semantically related to the input information will be displayed, but also to-be-recommended information that is determined based on the input information and semantically independent of the input information will be displayed; therefore, the diversity of display information corresponding to the input information is improved; thus, when information search is performed based on the recommended search information, the information search range can be expanded, and the information search effect can be further improved.

[0076] In the embodiment of the present application, after step 702, the information search method further comprises: the information search device, in response to a first search operation for the input information, displays results searched based on the input information; or, the information search device, in response to a second search operation for the search candidate information, displays results searched based on the search candidate information.

[0077] In the embodiments of this application, the relationship between recommended search information and search candidate information includes at least one of the following: the recommended search information and search candidate information belong to the same category, for example, the recommended search information and search candidate information are content creation objects of the same type (same field of creative content), the recommended search information and search candidate information are video names of the same type (same field of video content), etc.; the recommended search information and search candidate information have a shared interest relationship, for example, the recommended search information and search candidate information are creation objects of the same interest, etc.

[0078] It's important to note that a "shared interest" relationship indicates that different pieces of information have a higher probability of conversion on the same object (e.g., an account) than a specified probability. Conversion includes searching, watching, purchasing, following, etc. When recommended search information and search candidate information have a shared interest relationship, it means that the object converting the search candidate information has a higher probability of converting the recommended search information than a specified probability; that is, the object converting the search candidate information has a relatively high probability (a higher probability of conversion than the specified probability) of converting the recommended search information. Here, recommended search information and search candidate information can be information of the same category, information with a shared interest relationship, or information that is both of the same category and has a shared interest relationship.

[0079] In this embodiment of the application, when the recommended search information and the search candidate information belong to the same category, steps 704 and 705 (not shown in the figure) are included before step 702; that is, before the information search device responds to the input operation for the search area, displays the input information, and displays the search candidate information corresponding to the input information and the recommended search information corresponding to the search candidate information, the information search method further includes steps 704 and 705, and each step will be described below.

[0080] Step 704: Classify the multiple strings to be processed to obtain the set of strings to be processed corresponding to each category.

[0081] In this embodiment of the application, the information search device obtains multiple strings to be processed by collecting strings from various platforms; here, the information search device classifies the multiple strings to be processed; thus, each category will correspond to a set of strings to be processed, and the set of strings to be processed includes at least two strings to be processed, and at least two strings to be processed in the set of strings to be processed belong to the same category.

[0082] Step 705: Select the first specified number of strings to be processed from the set of strings to be processed, determine them as strings of the same type, and obtain each string of the same type corresponding to each category.

[0083] In this embodiment, the information search device selects a first specified number of strings to be processed from the set of strings to be processed, and determines the first specified number of strings to be processed as a combination of strings of the same type; thereby, corresponding to each category, each combination of strings of the same type can be obtained, so as to determine the recommended search information corresponding to the search candidate information based on each combination of strings of the same type; and, each category corresponds one-to-one with each combination of strings of the same type; and, each string to be processed in a combination of strings of the same type belongs to the same category.

[0084] It should be noted that the first specified quantity is a positive integer greater than 1, and this first specified quantity is less than or equal to the number of strings to be processed in the set of strings to be processed; for example, 2, 3, etc. It is easy to see that the input information and the recommended search information can belong to the same type of string combination.

[0085] Accordingly, in the embodiments of this application, step 702 can be implemented through steps 7021 and 7022 (not shown in the figure); that is, the information search device responds to the input operation for the search area, displays the input information, and displays the search candidate information corresponding to the input information and the recommended search information corresponding to the search candidate information, including steps 7021 and 7022. Each step will be described below.

[0086] Step 7021: In response to the input operation for the search area, perform string matching in each combination of similar strings based on the search candidate information corresponding to the input information.

[0087] In this embodiment of the application, after the information search device obtains the input information, it acquires the search candidate information corresponding to the input information, and performs string matching in various similar string combinations based on the search candidate information.

[0088] Step 7022: Among the matched strings of the same type, identify the strings other than the search candidate information as recommended search information, and display the input information, search candidate information, and recommended search information.

[0089] In this embodiment, the information search device performs string matching on the search candidate information and each similar string combination. If it is determined that the string matching result includes a matching similar string combination, it indicates that each similar string combination includes a string to be processed that is consistent with the string in the search candidate information, meaning that the search candidate information has corresponding recommended search information. At this time, the information search device combines the strings to be processed in each similar string combination except for the search candidate information into a first initial recommended search information, and determines the first initial recommended search information as the recommended search information; thereby, the input information, the search candidate information, and the recommended search information are displayed.

[0090] It should be noted that when the number of strings to be processed included in the first initial recommended search information is greater than a specified value (e.g., 1, 2, etc.), the information search device selects a specified number of strings to be processed from the first initial recommended search information as recommended search information; the selection criteria can be the number of searches, the number of times the recommended information is selected, etc.

[0091] Understandably, when users perform an input operation to search for information in the search area, not only are the search candidate information corresponding to the input information displayed, but also the recommended search information belonging to the same category as the search candidate information. Thus, it is possible to achieve searches based on input information, searches based on search candidate information, and searches based on recommended search information, thereby improving the scope and flexibility of information search.

[0092] In this embodiment of the application, step 7021 is followed by step 7023 (not shown in the figure); that is, after the information search device responds to the input operation for the search area and performs string matching in each combination of similar strings based on the search candidate information corresponding to the input information, the information search method further includes step 7023, which will be described below.

[0093] Step 7023: When the string matching result indicates that the search candidate information does not match any of the combinations of similar strings, display the input information and the search candidate information.

[0094] It should be noted that when the information search device compares the search candidate information with various similar string combinations, if it determines that the matching results do not include matching similar string combinations, it means that none of the similar string combinations contain a string that matches the string in the search candidate information. In other words, the search candidate information has no corresponding search candidate information. In this case, the information search device displays the input information and search candidate information, but does not display recommended search information.

[0095] In this embodiment of the application, when the recommended search information and the search candidate information are related, steps 706 to 709 (not shown in the figure) are included before step 702; that is, before the information search device responds to the input operation for the search area, displays the input information, and displays the search candidate information corresponding to the input information and the recommended search information corresponding to the search candidate information, the information search method further includes steps 706 to 709, and each step is described below.

[0096] Step 706: Obtain multiple conversion records.

[0097] It should be noted that among the multiple conversion records obtained by the information search device, each conversion record includes at least two conversion strings corresponding to the target object; that is, at least two conversion strings in a conversion record have both resulted in a conversion on the target object of that conversion record. Multiple conversion records may include, for example, search data records, viewing data records, and purchase data records.

[0098] Step 707: From multiple conversion records, obtain a first specified number of different information combinations on the same target object to obtain the conversion string combinations, and obtain the number of target objects corresponding to the conversion string combinations.

[0099] In this embodiment, the information search device obtains a first specified number of conversion string combinations from multiple conversion records, representing the conversions of different information onto the same target object. These conversion string combinations include the first specified number of conversion strings, and all of the first specified number of conversion strings in the combination have been converted onto the same target object. Here, the information search device will obtain multiple conversion string combinations. Furthermore, the information search device also obtains the number of target objects corresponding to each conversion string combination, indicating that the conversion string combination has been converted onto all target objects within that number of target objects.

[0100] Step 708: Based on the comparison results of the number of target objects and the number of records of multiple conversion records, determine the probability of similarity corresponding to the combination of conversion strings.

[0101] In this embodiment, the information search device obtains the number of conversion records corresponding to multiple conversion records, compares the number of target objects with the number of records, and determines the ratio of the number of target objects to the number of records as the same probability for the conversion string combination. Here, the ratio of the number of target objects to the number of records is the comparison result. Alternatively, the information search device can use other comparison methods, such as subtraction, which is not limited in this embodiment. It is easy to understand that the same probability represents the likelihood that a first specified number of conversion strings in the conversion string combination will be converted on the same target object; or, the same probability refers to the probability that different information will be converted on the same object.

[0102] Step 709: Combine the conversion strings with a probability greater than a specified probability to obtain various string combinations for the same hobby.

[0103] In this embodiment, the information search device compares the obtained probability of similar interests with a specified probability. If the probability of similar interests is greater than the specified probability, it indicates that the first specified number of conversion strings in the conversion string combination are more likely to be converted on the same target object. If the probability of similar interests is less than or equal to the specified probability, it indicates that the first specified number of conversion strings in the conversion string combination are less likely to be converted on the same target object. Here, the information search device acquires each combination of similar interests with a probability greater than the specified probability, and determines the recommended search information corresponding to the search candidate information based on each combination of similar interests. It is easy to see that the search candidate information and the recommended search information can belong to the same combination of similar interests.

[0104] Accordingly, in the embodiments of this application, step 702 can be implemented through steps 7024 and 7025 (not shown in the figure); that is, the information search device responds to the input operation for the search area, displays the input information, and displays the search candidate information corresponding to the input information and the recommended search information corresponding to the search candidate information, including steps 7024 and 7025. Each step will be described below.

[0105] Step 7024: In response to the input operation for the search area, perform string matching in each combination of like strings based on the search candidate information corresponding to the input information.

[0106] In this embodiment of the application, after the information search device obtains the input information, it acquires the search candidate information corresponding to the input information, and performs string matching in each combination of similar strings based on the search candidate information.

[0107] Step 7025: Among the matched strings of like-minded people, the transformed strings other than the search candidate information are identified as recommended search information, and the input information, search candidate information, and recommended search information are displayed.

[0108] In this embodiment, the information search device, based on the string matching results of search candidate information and various similar string combinations, determines that the string matching results include matching similar string combinations. This indicates that each similar string combination of the matching similar string combinations includes a string to be processed that is consistent with the string in the search candidate information, meaning that the search candidate information has corresponding recommended search information. At this time, the information search device combines the strings to be processed in each similar string combination of the matching similar string combinations (excluding the search candidate information) into second initial recommended search information, and determines the second initial recommended search information as the recommended search information; thereby, it displays the input information, search candidate information, and recommended search information.

[0109] It should be noted that the process by which the information search device selects recommended search information from the second initial recommended search information is similar to the process in step 7022, and will not be described again here.

[0110] Understandably, when users input information in the search area, the system not only displays the search candidate information corresponding to the input information, but also recommends search information that shares similar interests with the search candidate information. Thus, it enables searches based on input information, search candidate information, and recommended search information, thereby improving the scope and flexibility of information searches.

[0111] In this embodiment of the application, after obtaining various similar string combinations and various like-minded string combinations, the information search device can also integrate the various similar string combinations and various like-minded string combinations to obtain a recommended search library, so as to determine the recommended search information corresponding to the search candidate information based on the recommended search library.

[0112] In this embodiment of the application, step 702 can be implemented by step 7026 (not shown in the figure); that is, the information search device responds to the input operation for the search area, displays the input information, and displays the search candidate information corresponding to the input information and the recommended search information corresponding to the search candidate information, including step 7026, which will be described below.

[0113] Step 7026: In response to an input operation triggered on the input control for the search area, display the input information, and display the search candidate information corresponding to the input information and the recommended search information corresponding to the search candidate information in the input candidate area of ​​the input control.

[0114] It should be noted that when the information search device displays the search area, it also displays input controls and an input candidate area. Therefore, the information search device can display search candidate information and recommended search information in the input candidate area; at this time, the search candidate information is the input candidate information. The input controls are used to obtain the information to be searched for in the search area, and the input candidate area is used to display information generated by the input application corresponding to the input controls based on the key information corresponding to the input controls. Furthermore, the input information can be displayed in the search area or in the input candidate area of ​​the input controls; this embodiment does not limit this.

[0115] In this embodiment of the application, when the input information is already entered search information and is displayed in the search area, the search candidate information and recommended search information can be displayed in the input candidate area; when the input information is at least one of key information and search information to be entered, the search candidate information and recommended search information are displayed in the input candidate area.

[0116] Understandably, the input control first determines the search candidate information corresponding to the input information based on the input information displayed in the search area or its own input candidate area, and then simultaneously displays recommended search information in the input candidate area, thereby improving the input flexibility of the input control; thus, when information is searched based on the input control, the flexibility, scope and efficiency of the information search can be improved.

[0117] In this embodiment of the application, when the input information includes the input search information, step 702 can be implemented by step 7027 (not shown in the figure); that is, the information search device responds to the input operation for the search area, displays the input information, and displays the search candidate information corresponding to the input information and the recommended search information corresponding to the search candidate information, including step 7027, which will be described below.

[0118] Step 7027: In response to an input operation on the search area, display the input information in the search area, and display the search candidate information corresponding to the input information and the recommended search information corresponding to the search candidate information in the search candidate area corresponding to the search area.

[0119] In this embodiment, when the input information is already entered search information, the input information is displayed in the search area. At this time, search candidate information and recommended search information can be displayed in the search candidate area; of course, it is also possible to display search candidate information in the search candidate area and recommended search information in the input candidate area, etc., and this embodiment does not limit this. The search candidate area is used to display information generated by the target application corresponding to the search area based on the already entered search information.

[0120] See Figure 8 , Figure 8 This is a schematic diagram of information display provided in an embodiment of this application; as shown Figure 8 As shown, the display of input information, search candidate information, and recommended search information can be as follows: Input information 8-11 is displayed in search area 8-12, and search candidate information 8-13 and recommended search information 8-14 are both displayed in search candidate area 8-15. Alternatively, as shown on page 8-2, input information 8-21 is displayed in search area 8-22, search candidate information 8-23 is displayed in search candidate area 8-24, and recommended search information 8-25 is displayed in input candidate area 8-26. Another possible display is as shown on page 8-3, where input information 8-31 is displayed in search area 8-32, and search candidate information 8-33 and recommended search information 8-34 are both displayed in input candidate area 8-35. Finally, as shown on page 8-4, input information 8-41, search candidate information 8-42, and recommended search information 8-43 are all displayed in input candidate area 8-44.

[0121] See Figure 9 , Figure 9 This is a flowchart illustrating the information search method provided in the embodiments of this application. Figure 2 ;like Figure 9 As shown, step 702 can be implemented through steps 7028 to 70210; that is, the information search device responds to the input operation for the search area, displays the input information, and displays the search candidate information corresponding to the input information and the recommended search information corresponding to the search candidate information, including steps 7028 to 70210. Each step is explained below.

[0122] Step 7028: In response to an input operation triggered on the input control for the search area, obtain search candidate information corresponding to the input information.

[0123] In this embodiment, the information search device responds to the input operation of the input control triggered for the search area, thereby obtaining the input information corresponding to the input operation; then, it obtains search candidate information based on the input information.

[0124] Step 7029: Select a second specified number of candidate strings from the search candidate information, determine them as strings to be judged, and obtain the search intent value corresponding to the strings to be judged.

[0125] It should be noted that the second specified number is a positive integer, such as 1, 2, etc. When the search candidate information is arranged in reverse order based on the candidate probability, the information search device can start from the first candidate string of the search candidate information, sequentially select the second specified number of candidate strings, and determine the selected second specified number of candidate strings as the strings to be judged; then, it obtains the search intent value corresponding to the string to be judged; whereby the search intent value represents the degree of search intent reflected by the string to be judged, which can be determined by search frequency, etc.

[0126] Step 70210: When the search intent value is greater than the specified search intent value, display the input information, search candidate information, and recommended search information.

[0127] In this embodiment of the application, the information search device compares the obtained search intent value with the specified search intent value. If it is determined that the search intent value is greater than the specified search intent value, it indicates that the search intent has converged to the string to be judged and the search intent has been clarified. Only then is the recommended search information of the search candidate information obtained, and the input information, search candidate information, and recommended search information are displayed.

[0128] See also Figure 9 Step 7029 is followed by step 70211; that is, after the information search device obtains the search intent value corresponding to the string to be judged, the information search method further includes step 70211. The steps are explained below.

[0129] Step 70211: When the search intent value is less than or equal to the specified search intent value, cancel the acquisition of recommended search information.

[0130] In this embodiment of the application, the information search device compares the obtained search intent value with the specified search intent value. If it is determined that the search intent value is less than or equal to the specified search intent value, it indicates that the search intent does not converge to the judgment string and the search intent is still unclear. Therefore, at this time, the recommended search information corresponding to the search candidate information is not obtained, but the input information and search candidate information are displayed.

[0131] Understandably, by determining the degree to which the search intent is reflected in the top two specified number of candidate strings among the search candidates, and obtaining recommended search information corresponding to the search candidates when the search intent is clear, the accuracy of recommended search information can be improved, and the number of times inferred search information is found can be reduced, thereby improving the efficiency of information retrieval. Conversely, by not obtaining recommended search information corresponding to the search candidates when the search intent is unclear, the resource consumption of information retrieval can be reduced.

[0132] In this embodiment of the application, in step 7029, the information search device obtains the search intent value corresponding to the string to be judged, including steps 70291 to 70293 (not shown in the figure). Each step is described below.

[0133] Step 70291: Obtain the search frequency corresponding to each candidate string in the string to be judged, and get the search frequency corresponding to the string to be judged.

[0134] In this embodiment, each candidate string corresponds to a search frequency, which represents the number of times the candidate string is searched. Thus, the information search device can obtain the corresponding search frequency for each candidate string in the string to be judged. Therefore, it obtains at least one search frequency corresponding to the string to be judged. Here, the information search device accumulates the at least one search frequency corresponding to the string to be judged, and thus obtains the search frequency to be judged. That is to say, the search frequency to be judged is the accumulated value of at least one search frequency.

[0135] Step 70292: Obtain the total search frequency corresponding to the search candidate information.

[0136] It should be noted that the information search device obtains the total search frequency of the search candidate information by accumulating the search frequency of each candidate string in the search candidate information.

[0137] Step 70293: Based on the comparison result between the search frequency to be judged and the total search frequency, determine the search intent value corresponding to the string to be judged.

[0138] In this embodiment, the information search device can obtain a comparison result between the search frequency to be judged and the total search frequency by obtaining the ratio of the search frequency to be judged to the total search frequency; it can also obtain a comparison result between the search frequency to be judged and the total search frequency by obtaining the difference between the search frequency to be judged and the total search frequency; etc., this embodiment does not limit this; here, the search intent value corresponding to the string to be judged is the comparison result between the search frequency to be judged and the total search frequency.

[0139] In this embodiment of the application, when the search intent value is greater than a specified search intent value, the information search device displays input information, search candidate information, and recommended search information, including: when the search intent value is greater than the specified search intent value, the information search device inserts the recommended search information between the string to be judged and the remaining string in the search candidate information to obtain a string sequence to be displayed, wherein the remaining string refers to the string in the recommended search information other than the string to be judged; and displays the input information and the string sequence to be displayed.

[0140] It should be noted that recommended search information can be displayed independently of search candidate information, and when the search candidate information includes multiple candidate strings, recommended search information can also be inserted into the search candidate information for display. This application embodiment does not limit this. When the information search device inserts recommended search information into the search candidate information for display, the insertion position can be between the string to be judged and the next candidate string of the string to be judged, that is, the position between the string to be judged and the remaining strings in the search candidate information. Here, the search candidate information and recommended search information are displayed by displaying the sequence of strings to be displayed.

[0141] In this embodiment of the application, in step 703, the information search device responds to the selection operation for the recommended search information and displays the information search results based on the recommended search information, including: the information search device responds to the selection operation for the recommended search information, displays the recommended search information in the search area; and responds to the search operation for the search area displaying the recommended search information, displays the information search results based on the recommended search information.

[0142] It should be noted that when a user selects recommended search information, the information search device can directly perform an information search based on the recommended search information; alternatively, it can display the recommended search information in the search area and then perform an information search based on the recommended search information when a search operation is received for the search area where the recommended search information is displayed; this application embodiment does not limit this.

[0143] In this embodiment, when the input information includes previously entered search information, the information search device, in response to a selection operation for recommended search information, displays recommended search information in the search area. This includes: the information search device, in response to a selection operation for recommended search information, replacing the previously entered search information with the recommended search information in the search area. Of course, the information search device may also display both previously entered search information and recommended search information in the search area; etc., this embodiment does not limit this to these possibilities.

[0144] In this embodiment, step 702, in response to an input operation on the search area, the information search device displays input information and corresponding search candidate information and recommended search information. This includes: the information search device receiving input information in response to an input operation on the search area; obtaining at least one candidate string (including the input information) and the search frequency corresponding to each candidate string in at least one search character from each piece of data in a specified search candidate library; wherein each piece of data in the specified search candidate library includes a candidate string, string key information, and search frequency; identifying candidate strings with a search frequency greater than a specified search frequency as search candidate information among the at least one candidate string; and displaying the input information, search candidate information, and recommended search information. Here, the candidate string can be the same as the string key information, or it can be a string corresponding to the string key information determined based on the input information type.

[0145] It should be noted that when the input information is key press information, the information search device matches the key press information to obtain at least one candidate string that includes the input information; when the input information is search information to be entered or search information has been entered, the information search device matches the candidate strings to obtain at least one candidate string that includes the input information.

[0146] In this embodiment of the application, before the information search device obtains candidate strings or string key information, including at least one candidate string of input information and the search frequency corresponding to each candidate string in at least one search character, from each piece of data in the specified search candidate library, the information search method further includes: the information search device obtaining string key information and search frequency corresponding to each candidate string of multiple candidate strings; combining the string key information and search frequency corresponding to each candidate string to obtain the specified search candidate library corresponding to the multiple candidate strings.

[0147] The following describes an exemplary application of the embodiments of this application in a real-world application scenario. This example application describes the process of searching by entering information in the search box of a target application through an input method application, and displaying recommended candidate information (referred search information) that is similar to or similar to the completed input information (referred to as search candidate information) in the input candidate area corresponding to the input method application, so as to achieve information search through the recommended candidate information.

[0148] See Figure 10 , Figure 10 This is a schematic diagram of an exemplary information search process provided in an embodiment of this application; such as Figure 10As shown, the exemplary information search process includes steps 1001 to 1007, and each step will be described separately below.

[0149] Step 1001: the client reports the text input by the user (referred to as input search information) or key information to the server.

[0150] Step 1002: the server generates search candidate information based on the reported information: search term 1, search term 2, search term 3, ....

[0151] It should be noted that the search candidate information includes a plurality of search terms arranged in descending order based on the number of search input times, which are sequentially search term 1, search term 2, search term 3, ....

[0152] In the embodiment of the present application, the server includes a search term list generated based on big data (referred to as a specified search candidate library); wherein each record in the search term list includes: a search term (referred to as a candidate string), a key corresponding to the search term (referred to as string key information), and the number of search input times of the search term (referred to as search frequency); for example: Xiaogang Senior - xiaogangxuezhang - 10000.

[0153] Here, when the server performs matching in the search term list based on the reported text input by the user, it matches each search term in the search term list with the text input by the user; when the server performs matching in the search term list based on the reported key information, it matches the key corresponding to each search term in the search term list with the key information. During matching, search terms that include the reported information may be obtained, or search terms starting with the reported information may be obtained; finally, the obtained matched search terms are arranged in descending order based on the number of search input times, thereby generating the search candidate information: search term 1, search term 2, search term 3, .... For example, when the user inputs the Chinese character "小", the reported information is "小", and all search terms starting with "小" are matched from the search term list; when the user inputs "xiao", the reported information is "xiao", and all search terms whose corresponding keys start with "xiao" are matched from the search term list.

[0154] Step 1003: the server determines whether the search intention converges to search term 1 in the search candidate information (referred to as a to-be-determined string). If yes, go to step 1004; if no, go to step 1005.

[0155] It should be noted that when the concentration degree of search term 1 (referred to as a search intention value) is higher than a threshold (referred to as a specified search intention value), it indicates that the search intention converges to search term 1; when the concentration degree of search term 1 is lower than or equal to the threshold, it indicates that the search intention does not converge to search term 1. Wherein, the concentration degree of search term 1 can be described by formula (1), which is shown as follows.

[0156] (1); wherein, J is the concentration of the first search term, is the number of search input times of the first search term (referred to as the to-be-judged search frequency), is the sum of the search input times respectively corresponding to the n search terms in the search candidate information (referred to as the total search frequency).

[0157] For example, when the reported information is "xiao", the obtained search candidate information includes 3 search words in sequence: Xiaogang, Xiaoyang and Xiaohui, with corresponding search input times of 5000, 4000 and 3000 respectively, then the concentration of "Xiaogang" is , which is lower than the threshold 0.8, thereby determining that the search intention does not converge to the first search term in the search candidate information.

[0158] When the reported information is "xiaogangxue", the obtained search candidate information includes 3 search words in sequence: Senior Xiaogang, Senior Xiaogang's Daily Life and Senior Xiaogang's Marriage, with corresponding search input times of 5000, 100 and 10 respectively, then the concentration of "Senior Xiaogang" is , which is higher than the threshold 0.8, thereby determining that the search intention converges to the first search term in the search candidate information.

[0159] Step 1004: the server determines whether there is a corresponding recommendation word for the first search term (referred to as recommended search information). If yes, perform step 1006; if no, perform step 1005.

[0160] It should be noted that the server determines whether the first search term has a corresponding recommendation word by matching the first search term in a recommendation table (which refers to various homogeneous string combinations and various like-minded string combinations). When it is determined that the recommendation table includes a mapping record corresponding to the first search term, it is determined that the first search term has a corresponding recommendation word, and the word corresponding to the first search term in the mapping record is used as the recommendation word; when it is determined that the recommendation table does not include a mapping record corresponding to the first search term, it is determined that the first search term does not have a corresponding recommendation word.

[0161] In the embodiments of the present application, each mapping record in the recommendation table is a recommendation mapping of two search terms, for example, "Senior Xiaogang - Influencer Talking about Cars"; wherein the establishment of the recommendation mapping for two search terms includes two aspects. On one hand, for the collected open data of each application platform, the recommendation mapping of two search terms is established based on the same category; for example, the content creation objects "Senior Xiaogang" and "Influencer Talking about Cars" on the short-video platform both belong to the category of "automobile review", thus, a same-category recommendation mapping of "Senior Xiaogang - Influencer Talking about Cars" is established in the recommendation table. On the other hand, for input big data, based on that the probability that different information is input by the same object is greater than a specified probability, a recommendation mapping representing a like-minded relationship is established; for example, in search input data, among users who input "Li Si Drumming" in the search box of the short-video platform, a relatively high proportion (the input probability is greater than the specified probability) also input "Zhang San Storytelling", thus, a like-minded recommendation mapping of "Li Si Drumming - Zhang San Storytelling" is established in the recommendation table.

[0162] Step 1005: The server returns search candidate information, so that the client displays: search term 1, search term 2, search term 3, ....

[0163] Step 1006: The server inserts a recommended term between search term 1 and search term 2 in the search candidate information.

[0164] Step 1007: The server returns the inserted search candidate information (referred to as the to-be-displayed string sequence), so that the client displays: search term 1, the recommended term, search term 2, search term 3, ....

[0165] In the following, Figures 11 to 16 illustrates an exemplary description of information searching performed based on the steps in Figure 10 .

[0166] Referring to Figure 11 , Figure 11 is an exemplary schematic display diagram of information searching provided by an embodiment of the present application Figure 1 ; as shown in Figure 11As shown, when the user inputs the text "Xiaogang Xue" via page 11-1, the search candidate area 11-11 displays the search candidate information generated by the short video application A based on "Xiaogang Xue". When the search intent does not converge to "Xiaogang Xuezhang" among the search candidate information "Xiaogang Xuezhang" and "Xiaogang Xuedi" generated by the input method, or when the search intent converges to "Xiaogang Xuezhang" but "Xiaogang Xuezhang" does not have a corresponding recommended word, the search candidate information "Xiaogang Xuezhang" and "Xiaogang Xuedi" generated by the input method are displayed in the input candidate area 11-12 of the input method. When the search intent converges to "Xiaogang Xuezhang" and "Xiaogang Xuezhang" has a corresponding recommended word "Daren Shuo Che", the search candidate information "Xiaogang Xuezhang", "Daren Shuo Che", and "Xiaogang Xuedi" generated by the input method are displayed in the input candidate area 11-12 of the input method. In this way, it is possible to search for content related to "Xiaogang Xuezhang" such as "Xiaogang Xue", as well as "Daren Shuo Che". The "Expert Car Review" section includes the prompt "Recommended:". Additionally, when the input candidate area is limited and cannot be fully displayed, partial information and an omission indicator are shown. The omission indicator triggers the display of all information; alternatively, a sliding box can be used to display the information. Here, both "Expert Car Review" and "Xiao Gang Xuechang" are content creation objects in the car review category of short video application A, therefore they are of the same category.

[0167] For example, see Figure 12 , Figure 12 This is an exemplary display illustration of information search provided in the embodiments of this application. Figure 2 ;like Figure 12As shown, when the user inputs the text "Li Shiliu" via page 12-1, the search candidate area 12-11 displays the search candidate information generated by the short video application based on "Li Shiliu". When the search candidate information generated by the input method, such as "Li Shiliu Xuezhang", "Who is Li Shiliu", or "Li Shiliu Live", does not converge to "Li Shiliu Xuezhang", or the search intent converges to "Li Shiliu Xuezhang" but there is no corresponding recommended word for "Li Shiliu Xuezhang", the search results generated by the input method are displayed in the input candidate area 12-12 of the input method. The search results initially include "Li Shiliu Xuezhang" (senior student Li Shiliu), "Who is Li Shiliu?", and "Li Shiliu live stream". When the search intent converges to "Li Shiliu Xuezhang" and there are corresponding recommended terms "Xiao Chengzi" and "Wang Shiqi", the input method's generated search candidate information "Li Shiliu Xuezhang", "Xiao Chengzi", "Wang Shiqi", "Who is Li Shiliu", and "Li Shiliu live stream" are displayed in the input candidate area 12-12. This allows users to search for content related to "Li Shiliu", including "Li Shiliu Xuezhang", as well as "Xiao Chengzi" and "Wang Shiqi". "Xiao Chengzi" and "Wang Shiqi" are accompanied by the prompt "Recommended:". Additionally, when the input candidate area is limited and cannot display all the information, partial information and an omission indicator are displayed. The omission indicator triggers the display of all information; alternatively, a sliding box can be used to display the information. Here, "Xiao Chengzi", "Wang Shiqi" and "Li Shiliu Xuechang" are all content creation objects of the short video application A, and the three are like-minded. That is, a relatively high proportion of users who search for "Li Shiliu Xuechang" (referred to as the object or target object) also search for "Xiao Chengzi" and "Wang Shiqi" (referred to as the probability of like-mindedness being greater than the specified probability).

[0168] See Figure 13 , Figure 13 This is an exemplary display illustration of information search provided in the embodiments of this application. Figure 3 ;like Figure 13As shown, when the user inputs the text "Zhang Sanmeng" via page 13-1, the search candidate area 13-11 displays the search candidate information generated by short video application B based on "Zhang Sanmeng". When the search candidate information "Zhang Sanmeng Pet" and "Zhang Sanmeng Pet Live" generated by the input method does not converge to "Zhang Sanmeng Pet", or when the search intent converges to "Zhang Sanmeng Pet" but there is no corresponding recommended word for "Zhang Sanmeng Pet", the search candidate information "Zhang Sanmeng Pet" and "Zhang Sanmeng Pet Live" generated by the input method are displayed in the input candidate area 13-12 of the input method. When the search intent converges to "Zhang Sanmeng Pet" and "Zhang Sanmeng Pet" has a corresponding recommended word "Jinmao Wangwu", the search candidate information "Zhang Sanmeng Pet", "Jinmao Wangwu", and "Zhang Sanmeng Pet Live" generated by the input method are displayed in the input candidate area 13-12 of the input method. In this way, it is possible to search for content related to "Zhang Sanmeng Pet" and also to search for content related to "Jinmao Wangwu". Among them, "Golden Retriever Wang Wu" corresponds to the prompt message "Recommended:". In addition, when the input candidate area is limited and cannot be fully displayed, partial information and an omission mark are displayed. The omission mark can trigger the display of all information; of course, it can also be displayed through a sliding box. Here, "Zhang San's Cute Pet" and "Golden Retriever Wang Wu" are both content creation objects in the pet category of short video application B, so they are of the same type.

[0169] See Figure 14 , Figure 14 This is an exemplary display illustration of information search provided in the embodiments of this application. Figure 4 ;like Figure 14As shown, when the user inputs the text "Liu Liu said" via page 14-1, the search candidate area 14-11 displays the search candidate information generated by the short video application D based on "Liu Liu said". When the search intent in the search candidate information "Liu Liu said cars" and "Liu Liu said cars live" does not converge to "Liu Liu said cars", or when the search intent converges to "Liu Liu said cars" but there is no corresponding recommended word for "Liu Liu said cars", the search candidate information "Liu Liu said cars" and "Liu Liu said cars live" generated by the input method are displayed in the input candidate area 14-12 of the input method. When the search intent converges to "Liu Liu said cars" and "Liu Liu said cars" has a corresponding recommended word "Teacher Xiaoming", the search candidate information "Liu Liu said cars", "Teacher Xiaoming", and "Liu Liu said cars live" generated by the input method are displayed in the input candidate area 14-12 of the input method. In this way, it is possible to search for content related to "Liu Liu said cars" and also to search for content related to "Teacher Xiaoming". Among them, "Teacher Xiaoming" corresponds to the prompt message "Recommended:". In addition, when the input candidate area is limited and cannot be fully displayed, partial information and an omission mark are displayed. The omission mark can trigger the display of all information; of course, it can also be displayed through a sliding box. Here, "Liu Liu Talks Cars" and "Teacher Xiaoming" are both content creation objects in the car review category of the short video application D, so they are of the same type.

[0170] See Figure 15 , Figure 15 This is an exemplary display illustration of information search provided in the embodiments of this application. Figure 5 ;like Figure 15 As shown, when the user inputs the text "Li Si" via page 15-1, the search candidate area 15-11 displays the search candidate information generated by the short video application E based on "Li Si". When the search candidate information "Li Si", "Li Si skincare", and "Li Si video" generated by the input method does not converge to "Li Si", or the search intent converges to "Li Si" but there is no corresponding recommended word for "Li Si", the search candidate information "Li Si", "Li Si skincare", and "Li Si video" generated by the input method are displayed in the input candidate area 15-12. When the search intent converges to "Li Si" and "Li Si" has a corresponding recommended word "Xiao Bai", the search candidate information "Li Si", "Xiao Bai", "Li Si skincare", and "Li Si video" generated by the input method are displayed in the input candidate area 15-12. In this way, it is possible to search for content related to "Li Si" and also to search for content related to "Xiao Bai". Among them, "Xiaobai" corresponds to the prompt message "Recommended:". In addition, when the input candidate area is limited and cannot be fully displayed, partial information and an omission mark are displayed. The omission mark can trigger the display of all information; of course, it can also be displayed through a sliding box. Here, "Li Si" and "Xiaobai" are both content creation objects in the short video application E, so they are of the same type.

[0171] See Figure 16 , Figure 16 This is an exemplary display illustration of information search provided in the embodiments of this application. Figure 6 ;like Figure 16 As shown, when the user inputs the text "Li Si" via page 16-1, the search candidate area 16-11 displays the search candidate information generated by the live streaming application F based on "Li Li Si". When the search candidate information "Li Li Si Elite" generated by the input method does not converge to "Li Li Si Elite", or when the search intent converges to "Li Li Si Elite" but there is no corresponding recommended word for "Li Li Si Elite", the search candidate information "Li Li Si Elite" generated by the input method is displayed in the input candidate area 16-12. When the search intent converges to "Li Li Si Elite" and "Li Li Si Elite" has a corresponding recommended word "Xiao Bai Liu Liu", the search candidate information "Li Li Si Elite" and "Xiao Bai Liu Liu" generated by the input method are displayed in the input candidate area 16-12. In this way, it is possible to search for content related to "Li Li Si Elite" and also to search for content related to "Xiao Bai Liu Liu". Among them, "Xiaobai Liuliu" corresponds to the prompt message "Recommended:". In addition, when the input candidate area is limited and cannot be fully displayed, partial information and an omission mark are displayed. The omission mark can trigger the display of all information; of course, it can also be displayed through a sliding box. Here, "Li Li Si Elite" and "Xiaobai Liuliu" are both content creation objects in the live streaming application F, and the two are related, that is, a high proportion of users who search for "Li Li Si Elite" also search for "Xiaobai Liuliu".

[0172] It is understood that the information search method provided in this application embodiment can not only search for search candidate information corresponding to the text or key information entered by the user, but also search for related content of recommended words that belong to the same category or have the same interest relationship as the search candidate information; thus, it can improve the information search scope of the content consumer and improve the flexibility of information search; it can also achieve accurate recommendation of recommended words, reduce the number of information searches for recommended words, thereby reducing the resource consumption in information search; and it can also improve the efficiency of content distribution in the information search process.

[0173] The following description continues to illustrate the exemplary structure of the information search device 455 provided in the embodiments of this application as a software module. In some embodiments, such as Figure 6 As shown, the software module stored in the information search device 455 of the memory 450 may include: The area display module 4551 is used to display the search area in the information input state, wherein the information input state refers to the state of receiving information input; Information input module 4552 is used to respond to an input operation for the search area, display input information, and display search candidate information corresponding to the input information and recommended search information corresponding to the search candidate information, wherein the search candidate information is candidate information semantically related to the input information, and the recommended search information is information to be recommended determined based on the search candidate information and semantically independent of the search candidate information; The information search module 4553 is used to display the information search results based on the recommended search information in response to the selection operation of the recommended search information.

[0174] In this embodiment of the application, the relationship between the recommended search information and the search candidate information includes at least one of the following: the recommended search information and the search candidate information belong to the same category; the recommended search information and the search candidate information have a similar relationship, wherein the similar relationship means that the probability of different information being converted on the same object is greater than a specified probability.

[0175] In this embodiment of the application, when the recommended search information and the search candidate information belong to the same category, the information search device 455 further includes a combination construction module 4554, which is used to classify multiple strings to be processed to obtain a set of strings to be processed corresponding to each category; to determine a first specified number of strings to be processed selected from the set of strings to be processed as a combination of strings of the same type, and to obtain each combination of strings of the same type corresponding to each category.

[0176] In this embodiment of the application, the information input module 4552 is further configured to respond to the input operation for the search area, perform string matching in each of the same type of string combinations based on the search candidate information corresponding to the input information; in the matched same type of string combinations, determine the unprocessed string other than the search candidate information as the recommended search information, and display the input information, the search candidate information, and the recommended search information.

[0177] In this embodiment of the application, the information input module 4552 is further configured to display the input information and the search candidate information when the string matching result indicates that the search candidate information does not match any of the combinations of the same type of strings.

[0178] In this embodiment, when the recommended search information and the search candidate information have a similar relationship, the information search device 455 further includes a combination construction module 4554, used to obtain multiple conversion records, wherein each conversion record includes at least two conversion strings corresponding to the target object; from the multiple conversion records, obtain a first specified number of different information on the same target object to obtain conversion string combinations, and obtain the number of target objects corresponding to the conversion string combinations; based on the comparison result between the number of target objects and the number of records of the multiple conversion records, determine the similarity probability corresponding to the conversion string combination; combine the conversion string combinations whose similarity probability is greater than the specified probability to obtain various similarity string combinations.

[0179] In this embodiment of the application, the information input module 4552 is further configured to respond to the input operation for the search area, perform string matching in each of the same-interest string combinations based on the search candidate information corresponding to the input information; in the matched same-interest string combinations, determine the converted string other than the search candidate information as the recommended search information, and display the input information, the search candidate information, and the recommended search information.

[0180] In this embodiment, the input information includes at least one of key information, search information to be input, and search information already input. The key information is the information corresponding to the key triggered by the input operation; the search information to be input is the information corresponding to the key information determined based on the input information type; and the search information already input is the information in the search area. The search candidate information includes at least one of input candidate information and search information to be input. The input candidate information is candidate information generated based on the input search information, and the search information to be input refers to candidate information generated based on candidate criteria information, which includes at least one of the key information, the search information to be input, and the search information already input.

[0181] In this embodiment, the information input module 4552 is further configured to respond to the input operation triggered by the input control for the search area, display the input information, and display the search candidate information corresponding to the input information and the recommended search information corresponding to the search candidate information in the input candidate area of ​​the input control; wherein, the input control is used to obtain the information to be searched for the search area, and the input candidate area is used to display the information generated based on the key information corresponding to the input control.

[0182] In this embodiment of the application, when the input information includes input search information, the information input module 4552 is further configured to, in response to the input operation for the search area, display the input information in the search area, and display the search candidate information corresponding to the input information and the recommended search information corresponding to the search candidate information in the search candidate area corresponding to the search area; wherein, the search candidate area is used to display information generated based on the input search information.

[0183] In this embodiment, the information input module 4552 is further configured to: respond to the input operation triggered by the input control for the search area; obtain the search candidate information corresponding to the input information; determine a second specified number of candidate strings selected from the search candidate information as strings to be judged; obtain the search intent value corresponding to the string to be judged, wherein the search intent value represents the degree of search intent reflected by the string to be judged; and when the search intent value is greater than a specified search intent value, display the input information, the search candidate information, and the recommended search information.

[0184] In this embodiment of the application, the information input module 4552 is further configured to cancel the acquisition of the recommended search information when the search intent value is less than or equal to the specified search intent value.

[0185] In this embodiment of the application, the information input module 4552 is further configured to obtain the search frequency corresponding to each candidate string in the string to be judged, and obtain the search frequency to be judged corresponding to the string to be judged, wherein the search frequency to be judged is the cumulative value of at least one search frequency; obtain the total search frequency corresponding to the search candidate information; and determine the search intent value corresponding to the string to be judged based on the comparison result between the search frequency to be judged and the total search frequency.

[0186] In this embodiment of the application, the information input module 4552 is further configured to, when the search intent value is greater than the specified search intent value, insert the recommended search information between the string to be judged and the remaining string in the search candidate information to obtain a string sequence to be displayed, wherein the remaining string refers to the string in the recommended search information other than the string to be judged; and display the input information and the string sequence to be displayed.

[0187] In this embodiment of the application, the information search module 4553 is further configured to, in response to the selection operation for the recommended search information, display the recommended search information in the search area; and, in response to the search operation for the search area displaying the recommended search information, display the information search results obtained based on the recommended search information.

[0188] In this embodiment of the application, the information search module 4553 is further configured to, in response to the selection operation for the recommended search information, replace the input search information displayed in the search area with the recommended search information.

[0189] In this embodiment, the information input module 4552 is further configured to: obtain the input information in response to the input operation for the search area; acquire, from each piece of data in the specified search candidate library, at least one candidate string including the input information and the search frequency corresponding to each of the at least one candidate string, wherein each piece of data in the specified search candidate library includes the candidate string, the string key information and the search frequency; determine the candidate string with a search frequency greater than the specified search frequency as the search candidate information in the at least one candidate string; and display the input information, the search candidate information and the recommended search information.

[0190] In this embodiment of the application, the combination construction module 4554 is further configured to obtain the string key information and the search frequency corresponding to each of the plurality of candidate strings; combine the string key information and the search frequency corresponding to each candidate string to obtain the specified search candidate library corresponding to the plurality of candidate strings.

[0191] This application provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device (referred to as an information search device) reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the information search method described in this application.

[0192] This application provides a computer-readable storage medium storing executable instructions. When these executable instructions are executed by a processor, they cause the processor to execute the information search method provided in this application. For example, ... Figure 7 The information search method is shown.

[0193] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a variety of devices including one or any combination of the above-mentioned memories.

[0194] In some embodiments, executable instructions may take the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0195] As an example, executable instructions may, but do not necessarily, correspond to files in a file system. They may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a Hyper Text Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple collaborating files (e.g., a file that stores one or more modules, subroutines, or code sections).

[0196] As an example, executable instructions can be deployed to execute on a single computer device (in which case, this single computer device is an information search device), or to execute on multiple computer devices located in one location (in which case, multiple computer devices located in one location are information search devices), or to execute on multiple computer devices distributed across multiple locations and interconnected via a communication network (in which case, multiple computer devices distributed across multiple locations and interconnected via a communication network are information search devices).

[0197] It is understood that the embodiments of this application involve multiple strings to be processed, multiple conversion strings, and search frequency and other related data. When the embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0198] In summary, in this embodiment of the application, when an input operation is received for the search area, not only will the input information corresponding to the input operation and the candidate information semantically related to the input information be displayed, but also the recommended information determined based on the input information and whose semantics are independent of the input information will be displayed. Therefore, the diversity of the displayed information corresponding to the input information is improved. Thus, when information is searched based on the recommended search information, the scope of information search can be expanded, thereby improving the information search effect.

[0199] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, and improvements made within the spirit and scope of this application are included within the scope of protection of this application.

Claims

1. An information search method, characterized in that, The method includes: The search area is displayed in the information input state, where the information input state refers to the state of receiving information input; In response to an input operation triggered on the input control for the search area, search candidate information corresponding to the input information is obtained; A second specified number of candidate strings selected from the search candidate information are determined as the strings to be judged; Obtain the search frequency corresponding to each candidate string in the string to be judged, and obtain the search frequency to be judged corresponding to the string to be judged, wherein the search frequency to be judged is the cumulative value of at least one search frequency; Obtain the total search frequency corresponding to the search candidate information; Based on the comparison result between the search frequency to be judged and the total search frequency, the search intent value corresponding to the string to be judged is determined, wherein the search intent value represents the degree of search intent reflected by the string to be judged; When the search intent value is greater than the specified search intent value, the input information, the search candidate information, and the recommended search information are displayed. Wherein, the search candidate information is candidate information that is semantically related to the input information, and the recommended search information is information to be recommended that is determined based on the search candidate information and is semantically independent of the search candidate information; In response to a selection operation based on the recommended search information, the search results are displayed.

2. The method according to claim 1, characterized in that, The relationship between the recommended search information and the search candidate information includes at least one of the following: The recommended search information and the search candidate information belong to the same category; The recommended search information and the search candidate information are related in a similar way, where the similarity means that the probability of different information being converted on the same object is greater than a specified probability.

3. The method according to claim 1 or 2, characterized in that, When the recommended search information and the search candidate information belong to the same category, before displaying the input information, the search candidate information, and the recommended search information, the method further includes: The multiple strings to be processed are classified to obtain a set of strings to be processed for each category; A first specified number of strings to be processed are selected from the set of strings to be processed, determined to be combinations of strings of the same type, and each combination of strings of the same type corresponding to each category is obtained; The display of the input information, the search candidate information, and the recommended search information includes: Based on the search candidate information corresponding to the input information, string matching is performed in each of the same type of string combinations; Among the matched string combinations of the same type, the strings to be processed other than the search candidate information are identified as the recommended search information, and the input information, the search candidate information, and the recommended search information are displayed.

4. The method according to claim 3, characterized in that, After performing string matching among the various combinations of strings of the same type based on the search candidate information corresponding to the input information, the method further includes: When the string matching result indicates that the search candidate information does not match any of the combinations of the same type of string, the input information and the search candidate information are displayed.

5. The method according to claim 1 or 2, characterized in that, When the recommended search information and the search candidate information are related, before displaying the input information, the search candidate information, and the recommended search information, the method further includes: Retrieve multiple conversion records, wherein each conversion record includes at least two conversion strings corresponding to the target object; From multiple conversion records, obtain a first specified number of different information on the same target object to obtain a combination of conversion strings, and obtain the number of target objects corresponding to the combination of conversion strings; Based on the comparison results between the number of target objects and the number of records of multiple conversion records, the probability of the same interest corresponding to the combination of conversion strings is determined; By combining the transformed strings whose probability of sharing the same interest is greater than a specified probability, we obtain various combinations of strings sharing the same interest. The step of displaying the input information, the search candidate information, and the recommended search information when the search intent value is greater than a specified search intent value includes: Based on the search candidate information corresponding to the input information, string matching is performed in each of the like-minded string combinations; Among the matched combinations of like-minded strings, the transformed strings other than the search candidate information are identified as the recommended search information, and the input information, the search candidate information, and the recommended search information are displayed.

6. The method according to claim 1 or 2, characterized in that, The input information includes at least one of key information, search information to be entered, and search information already entered, wherein the key information is the information corresponding to the key triggered by the input operation, the search information to be entered is the information corresponding to the key information determined based on the input information type, and the search information already entered is the information in the search area; The search candidate information includes at least one of input candidate information and candidate information to be input; the input candidate information is candidate information generated based on the input search information, and the candidate information to be input refers to candidate information generated based on candidate basis information, which includes at least one of the key information, the search information to be input, and the input search information.

7. The method according to claim 1 or 2, characterized in that, The display of the input information, the search candidate information, and the recommended search information includes: In response to the input operation triggered on the input control for the search area, the input information is displayed, and the search candidate information corresponding to the input information and the recommended search information are displayed in the input candidate area of ​​the input control; The input control is used to obtain information to be searched for in the search area, and the input candidate area is used to display information generated based on the key information corresponding to the input control.

8. The method according to claim 1 or 2, characterized in that, When the input information includes already entered search information, displaying the input information, the search candidate information, and the recommended search information includes: In response to the input operation for the search area, the input information is displayed in the search area, and the search candidate information corresponding to the input information and the recommended search information corresponding to the search candidate information are displayed in the search candidate area corresponding to the search area; The search candidate area is used to display information generated based on the input search information.

9. The method according to claim 1, characterized in that, After obtaining the search intent value corresponding to the string to be judged, the method further includes: When the search intent value is less than or equal to the specified search intent value, the acquisition of the recommended search information is canceled.

10. The method according to claim 1, characterized in that, The step of displaying the input information, the search candidate information, and the recommended search information when the search intent value is greater than a specified search intent value includes: When the search intent value is greater than the specified search intent value, the recommended search information is inserted between the string to be judged and the remaining string in the search candidate information to obtain a string sequence to be displayed, wherein the remaining string refers to the string in the search candidate information other than the string to be judged; The input information and the string sequence to be displayed are displayed.

11. The method according to claim 1 or 2, characterized in that, The response to the selection operation for the recommended search information, displaying the search results based on the recommended search information, includes: In response to the selection operation for the recommended search information, the recommended search information is displayed in the search area; In response to a search operation targeting the search area displaying the recommended search information, the search results based on the recommended search information are displayed.

12. The method according to claim 11, characterized in that, When the input information includes already entered search information, the step of displaying the recommended search information in the search area in response to the selection operation for the recommended search information includes: In response to the selection operation for the recommended search information, the entered search information is replaced by the recommended search information in the search area.

13. The method according to claim 1 or 2, characterized in that, The step of responding to an input operation triggered by the input control for the search area, and obtaining search candidate information corresponding to the input information, includes: The input information is obtained in response to an input operation on the trigger input control for the search area; From each piece of data in the specified search candidate library, obtain at least one candidate string or string key information including the input information, and the search frequency corresponding to each of the candidate strings, wherein each piece of data in the specified search candidate library includes the candidate string, the string key information and the search frequency; Among at least one of the candidate strings, the candidate string whose search frequency is greater than a specified search frequency is determined as the search candidate information; The input information, the search candidate information, and the recommended search information are displayed.

14. The method according to claim 13, characterized in that, Before obtaining candidate strings or string key information from each piece of data in the specified search candidate library, including at least one candidate string of the input information and the search frequency corresponding to each of the candidate strings, the method further includes: Obtain the string key information and search frequency corresponding to each of the multiple candidate strings; By combining the string key information corresponding to each candidate string and the search frequency, a specified search candidate library corresponding to multiple candidate strings is obtained.

15. An information search device, characterized in that, The information search device includes: The area display module is used to display the search area in the information input state, wherein the information input state refers to the state of receiving information input; An information input module is configured to respond to an input operation triggered by an input control for the search area, obtain search candidate information corresponding to the input information; determine a second specified number of candidate strings selected from the search candidate information as strings to be judged; obtain the search frequency corresponding to each candidate string in the strings to be judged, and obtain the search frequency to be judged corresponding to the strings to be judged, wherein the search frequency to be judged is the cumulative value of at least one search frequency; obtain the total search frequency corresponding to the search candidate information; determine the search intent value corresponding to the strings to be judged based on the comparison result between the search frequency to be judged and the total search frequency, wherein the search intent value represents the degree of search intent reflected by the strings to be judged; when the search intent value is greater than a specified search intent value, display the input information, the search candidate information, and recommended search information; wherein the search candidate information is candidate information semantically related to the input information, and the recommended search information is recommended information determined based on the search candidate information and semantically independent of the search candidate information; The information search module is used to display the information search results based on the recommended search information in response to the selection operation of the recommended search information.

16. The information search device according to claim 15, characterized in that, The relationship between the recommended search information and the search candidate information includes at least one of the following: The recommended search information and the search candidate information belong to the same category; The recommended search information and the search candidate information are related in a similar way, where the similarity means that the probability of different information being converted on the same object is greater than a specified probability.

17. The information search device according to claim 15 or 16, characterized in that, The information search device further includes a combination construction module, used when the recommended search information and the search candidate information belong to the same category: The multiple strings to be processed are classified to obtain a set of strings to be processed for each category; A first specified number of strings to be processed are selected from the set of strings to be processed, determined to be combinations of strings of the same type, and each combination of strings of the same type corresponding to each category is obtained; The information input module is also used for: Based on the search candidate information corresponding to the input information, string matching is performed in each of the same type of string combinations; Among the matched string combinations of the same type, the strings to be processed other than the search candidate information are identified as the recommended search information, and the input information, the search candidate information, and the recommended search information are displayed.

18. The information search device according to claim 17, characterized in that, The information input module is further configured to display the input information and the search candidate information when the string matching result indicates that the search candidate information does not match any of the combinations of the same type of strings.

19. The information search device according to claim 15 or 16, characterized in that, The information search device further includes a combination construction module, used when the recommended search information and the search candidate information have a similar relationship: Retrieve multiple conversion records, wherein each conversion record includes at least two conversion strings corresponding to the target object; From multiple conversion records, obtain a first specified number of different information on the same target object to obtain a combination of conversion strings, and obtain the number of target objects corresponding to the combination of conversion strings; Based on the comparison results between the number of target objects and the number of records of multiple conversion records, the probability of the same interest corresponding to the combination of conversion strings is determined; By combining the transformed strings whose probability of sharing the same interest is greater than a specified probability, we obtain various combinations of strings sharing the same interest. The information input module is also used for: Based on the search candidate information corresponding to the input information, string matching is performed in each of the like-minded string combinations; Among the matched combinations of like-minded strings, the transformed strings other than the search candidate information are identified as the recommended search information, and the input information, the search candidate information, and the recommended search information are displayed.

20. The information search device according to claim 15 or 16, characterized in that, The input information includes at least one of key information, search information to be entered, and search information already entered, wherein the key information is the information corresponding to the key triggered by the input operation, the search information to be entered is the information corresponding to the key information determined based on the input information type, and the search information already entered is the information in the search area; The search candidate information includes at least one of input candidate information and candidate information to be input; the input candidate information is candidate information generated based on the input search information, and the candidate information to be input refers to candidate information generated based on candidate basis information, which includes at least one of the key information, the search information to be input, and the input search information.

21. The information search device according to claim 15 or 16, characterized in that, The information input module is also used to display the input information, and to display the search candidate information and the recommended search information in the input candidate area of ​​the input control; The input control is used to obtain information to be searched for in the search area, and the input candidate area is used to display information generated based on the key information corresponding to the input control.

22. The information search device according to claim 15 or 16, characterized in that, The information input module is further configured to display the input information in the search area when the input information includes input search information, and to display the search candidate information and the recommended search information in the search candidate area corresponding to the search area; The search candidate area is used to display information generated based on the input search information.

23. The information search device according to claim 15, characterized in that, The information input module is also used to cancel the acquisition of recommended search information when the search intent value is less than or equal to the specified search intent value.

24. The information search device according to claim 15, characterized in that, The information input module is further configured to insert the recommended search information between the string to be judged and the remaining string in the search candidate information when the search intent value is greater than the specified search intent value, so as to obtain a string sequence to be displayed, wherein the remaining string refers to the string in the search candidate information other than the string to be judged; The information input module is also used to display the input information and the string sequence to be displayed.

25. The information search device according to claim 15 or 16, characterized in that, The information search module is also used for: In response to the selection operation for the recommended search information, the recommended search information is displayed in the search area; In response to a search operation targeting the search area displaying the recommended search information, the search results based on the recommended search information are displayed.

26. The information search device according to claim 25, characterized in that, The information search module is further configured to, when the input information includes already entered search information, respond to the selection operation for the recommended search information and replace the already entered search information with the recommended search information in the search area.

27. The information search device according to claim 15 or 16, characterized in that, The information input module is also used for: The input information is obtained in response to the input operation of the trigger input control for the search area; From each piece of data in the specified search candidate library, obtain at least one candidate string or string key information including the input information, and the search frequency corresponding to each of the candidate strings, wherein each piece of data in the specified search candidate library includes the candidate string, the string key information and the search frequency; Among at least one of the candidate strings, the candidate string whose search frequency is greater than a specified search frequency is determined as the search candidate information; The input information, the search candidate information, and the recommended search information are displayed.

28. The information search device according to claim 27, characterized in that, The information search device further includes a combination construction module for: Obtain the string key information and search frequency corresponding to each of the multiple candidate strings; By combining the string key information corresponding to each candidate string and the search frequency, a specified search candidate library corresponding to multiple candidate strings is obtained.

29. An information search device, characterized in that, The information search device includes: Memory, used to store executable instructions; A processor, when executing executable instructions stored in the memory, implements the information search method according to any one of claims 1 to 14.

30. A computer-readable storage medium storing executable instructions, characterized in that, The executable instructions, when executed by a processor, implement the information search method according to any one of claims 1 to 14.

31. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by the processor, they implement the information search method according to any one of claims 1 to 14.

Images