Search prompting method and device, equipment and storage medium

Abstract

The invention relates to the technical field of information search, and discloses a search prompt method and device, and equipment, and a storage medium, the method comprises the following steps: selecting a search expression suggestion from a preset search expression library, generating search prompt information according to the search expression suggestion, and displaying the search prompt information at a preset position; the search prompt information is generated by directly selecting the search expression suggestions from the preset search expression library, and the search expressions in the preset search expression library are expressions convenient for the search engine to understand, so that search prompt can be performed based on the high-quality search expressions, the search prompt effect can be improved, and the search accuracy can be improved.

Description

Technical Field

[0001] The present invention relates to the field of information search technology, and in particular to a search prompt method, equipment, storage medium and device. Background Art

[0002] Currently, a conventional search prompt method is to sort historical search information on the Internet based on search frequency, and display historical search information with high search frequency as a search prompt.

[0003] However, the above search prompt method has the disadvantages of poor search prompt effect and inaccurate search because the historical search information is the search information input by the user, and the search information input by the user may not be clearly expressed, resulting in failure to obtain high-quality search results.

[0004] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of the present invention is to provide a search prompt method, device, storage medium and apparatus, aiming to solve the technical problem that the existing search prompt method has poor search prompt effect and inaccurate search because the historical search information is the search information input by the user, and the search information input by the user may not be clearly expressed, resulting in the inability to obtain high-quality search results.

[0006] To achieve the above object, the present invention provides a search prompt method, the search prompt method comprising:

[0007] Select search expression suggestions from the preset search expression library;

[0008] Generating search prompt information according to the search expression suggestion;

[0009] The search prompt information is displayed at a preset position.

[0010] Optionally, selecting a search expression suggestion from a preset search expression library includes:

[0011] Responding to current search information, and determining a current search intent based on the current search information;

[0012] Search expression suggestions are selected from a preset search expression library based on the current search intent.

[0013] Optionally, responding to the current search information and determining the current search intention according to the current search information includes:

[0014] Responding to current search information and identifying a current search scenario;

[0015] The user's search intention is determined according to the current search information and the current search scenario.

[0016] Optionally, responding to the current search information and identifying the current search scenario includes:

[0017] Responding to the current search information, and obtaining the current search time, the current search location, and the current search user;

[0018] A current search scenario is identified according to at least one of the current search time, the current search location, and the current search user.

[0019] Optionally, selecting a search expression suggestion from a preset search expression library based on the current search intent includes:

[0020] Determine a current search engine according to the current search information, and search for a search rule corresponding to the current search engine;

[0021] Search expression suggestions are selected from a preset search expression library based on the current search intent and the search rules.

[0022] Optionally, the search prompt method further includes:

[0023] Selecting a target search expression from the search record information, wherein the target search expression is an expression that is easy for the search engine to understand;

[0024] A preset search expression library is constructed based on the target search expression.

[0025] Optionally, selecting a target search expression from the search record information includes:

[0026] Extracting historical search expressions and historical search results corresponding to the historical search expressions from the search record information;

[0027] Analyzing the result quality of the historical search results;

[0028] A target search expression is selected from the historical search expressions based on the result quality.

[0029] Optionally, constructing a preset search expression library based on the target search expression includes:

[0030] Analyze search samples through natural language processing models to obtain standard search keywords and standard search formats;

[0031] Generate a standard search expression according to the standard search keyword and the standard search format;

[0032] A preset search expression library is constructed based on the standard search expression and the target search expression.

[0033] Optionally, generating search prompt information according to the search expression suggestion includes:

[0034] Analyzing the user search habits of the current search user according to the user information of the current search user;

[0035] Generate search prompt information based on the search expression suggestion and the user's search habits.

[0036] Optionally, the search prompt method further includes:

[0037] Responding to current search information, and determining a current search intent based on the current search information;

[0038] The preset position for displaying the search prompt information is determined according to the current search intent.

[0039] Optionally, the search prompt method further includes:

[0040] Detect whether the user has searched multiple times within a preset time;

[0041] If so, execute the step of selecting search expression suggestions from the preset search expression library.

[0042] In addition, to achieve the above-mentioned purpose, the present invention also proposes a search prompt device, which includes a memory, a processor, and a search prompt program stored in the memory and executable on the processor, and the search prompt program is configured to implement the search prompt method as described above.

[0043] In addition, to achieve the above-mentioned purpose, the present invention further proposes a storage medium, on which a search prompt program is stored, and when the search prompt program is executed by a processor, the search prompt method as described above is implemented.

[0044] In addition, to achieve the above-mentioned purpose, the present invention also proposes a search prompt device, which includes: a statement selection module, a prompt generation module and a prompt display module;

[0045] The expression selection module is used to select search expression suggestions from a preset search expression library;

[0046] The prompt generating module is used to generate search prompt information according to the search expression suggestion;

[0047] The prompt display module is used to display the search prompt information at a preset position.

[0048] Optionally, the expression selection module is further used to respond to current search information and determine the current search intention according to the current search information;

[0049] The expression selection module is also used to select search expression suggestions from a preset search expression library based on the current search intention.

[0050] Optionally, the expression selection module is further used to respond to current search information and identify the current search scenario;

[0051] The expression selection module is also used to determine the user's search intention based on the current search information and the current search scenario.

[0052] Optionally, the expression selection module is further used to respond to the current search information and obtain the current search time, the current search location and the current search user;

[0053] The expression selection module is further used to identify the current search scenario according to at least one of the current search time, the current search location and the current search user.

[0054] Optionally, the expression selection module is further used to determine the current search engine according to the current search information, and find the search rule corresponding to the current search engine;

[0055] The expression selection module is also used to select search expression suggestions from a preset search expression library based on the current search intent and the search rules.

[0056] Optionally, the search prompt device further comprises: a statement library construction module;

[0057] The expression library construction module is used to select a target search expression from the search record information, wherein the target search expression is an expression that is easy for the search engine to understand;

[0058] The expression library construction module is also used to construct a preset search expression library based on the target search expression.

[0059] Optionally, the expression library construction module is further used to extract historical search expressions and historical search results corresponding to the historical search expressions from the search record information;

[0060] The expression library construction module is also used to analyze the result quality of the historical search results;

[0061] The expression library construction module is also used to select a target search expression from the historical search expressions based on the result quality.

[0062] The present invention discloses selecting search expression suggestions from a preset search expression library, generating search prompt information based on the search expression suggestions, and displaying the search prompt information at a preset position; since the present invention directly selects search expression suggestions from the preset search expression library to generate search prompt information, and the search expressions in the preset search expression library are expressions that are easy for the search engine to understand, search prompts can be performed based on high-quality search expressions, thereby improving the search prompt effect and the search accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 It is a structural diagram of a search prompt device of a hardware operating environment involved in an embodiment of the present invention;

[0064] Figure 2 This is a flow chart of a first embodiment of a search prompt method of the present invention;

[0065] Figure 3 A schematic diagram of a search prompt according to an embodiment of a search prompt method of the present invention;

[0066] Figure 4 A schematic diagram of a flow chart of a second embodiment of a search prompt method of the present invention;

[0067] Figure 5 A schematic diagram of a flow chart of a third embodiment of a search prompt method of the present invention;

[0068] Figure 6 This is a structural block diagram of the first embodiment of the search prompt device of the present invention.

[0069] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0070] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0071] Reference Figure 1 , Figure 1 The present invention is a schematic diagram of the structure of a search prompt device for a hardware operating environment according to an embodiment of the present invention.

[0072] like Figure 1As shown, the search prompt device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), and the user interface 1003 may also include a standard wired interface and a wireless interface. The wired interface of the user interface 1003 may be a USB interface in the present invention. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable memory (Non-volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0073] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the search prompt device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0074] like Figure 1 As shown, the memory 1005 identified as a computer storage medium may include an operating system, a network communication module, a user interface module, and a search prompt program.

[0075] exist Figure 1 In the search prompt device shown, the network interface 1004 is mainly used to connect to the background server and communicate data with the background server; the user interface 1003 is mainly used to connect to the user device; the search prompt device calls the search prompt program stored in the memory 1005 through the processor 1001, and executes the search prompt method provided by the embodiment of the present invention.

[0076] Based on the above hardware structure, an embodiment of the search prompt method of the present invention is proposed.

[0077] Reference Figure 2 , Figure 2 The figure is a flow chart of the first embodiment of the search prompt method of the present invention, and the first embodiment of the search prompt method of the present invention is proposed.

[0078] In a first embodiment, the search prompt method comprises the following steps:

[0079] Step S10: Select a search expression suggestion from a preset search expression library.

[0080] It should be understood that the executor of the method of this embodiment can be a search prompt device with data processing, network communication and program running functions, such as terminal devices such as mobile phones and computers, or other electronic devices that can achieve the same or similar functions. This embodiment does not impose any restrictions on this.

[0081] In order to improve information processing capabilities, in some embodiments, an intelligent assistant can be installed on the terminal device. The intelligent assistant can be a program built based on natural language processing technology of the Generative Pre-trained Transformer (GPT) model. The intelligent assistant can receive user input text, parse the input text into a computer-understandable data format, and then use a pre-trained neural network model to generate response text.

[0082] In the specific implementation, the intelligent assistant uses the neural network in deep learning technology and is trained through a large amount of corpus data, so that it can learn the structure, grammatical rules and semantic information of the language. After the user enters the text, the intelligent assistant will first segment and parse the text, convert it into a computer-readable vector form, and then send it to the pre-trained neural network model for inference. During the inference process, the intelligent assistant will predict the most likely next response based on the text entered by the user and the previous context. This prediction process is based on the model's learning of a large amount of corpus data, so it can largely restore the way humans express natural language and generate highly coherent and natural response text. Finally, the intelligent assistant returns the generated response text to the user to complete a dialogue interaction. Throughout the process, the intelligent assistant will continue to learn and optimize to provide more accurate and user-friendly answers.

[0083] It can be understood that in this embodiment, a search prompt may be given when the user is searching, for example, when the user is searching through the search box; a search prompt may also be given when the user is not searching, for example, when the user enters the application interface; for example, a search prompt may be given when the user inputs through an input method, and this embodiment does not limit this.

[0084] It should be noted that the preset search expression library can be generated in advance, and the preset search expression library can include multiple search expressions, and the search expressions are expressions that are easy for the search engine to understand.

[0085] It should be understood that selecting search expression suggestions from the preset search expression library may be randomly selecting search expression suggestions from the preset search expression library; or selecting search expression suggestions from the preset search expression library based on user information, for example, predicting the user's search preferences based on the user's account information, browsing history, or personal preferences, and selecting search expression suggestions from the preset search expression library based on the search preferences; and also selecting search expression suggestions from the preset search expression library based on the current search information when the user enters the current search information, which is not limited in this embodiment.

[0086] Step S20: Generate search prompt information according to the search expression suggestion.

[0087] It should be understood that generating search prompt information based on search expression suggestions may be directly using the search expression suggestions as search prompt information; or the search expression suggestions may be written into a preset prompt template to obtain search prompt information; or the search prompt information may be generated in combination with the user search habits of the current search user, which is not limited in this embodiment.

[0088] Step S30: Displaying the search prompt information at a preset location.

[0089] It should be understood that the preset position can be preset, for example, the preset position can be a floating window near the search input box, a floating window near the search input box, or other preset prompt positions. Of course, in order to better meet user needs, the preset position can also be determined according to the current search intent, and this embodiment does not limit this.

[0090] For ease of understanding, refer to Figure 3 This is for illustration only, but not for limitation. Figure 3 This is a diagram of search prompts. In the figure, after the user enters the application interface of the smart assistant, the search prompt information can be displayed above the search bar. The search prompt information consists of two parts, one is the prompt content, such as "I can give you inspiration", and the other is the search expression suggestion, such as "write a science fiction novel". If the user clicks on the search example, the search example can be directly filled into the search bar as search information.

[0091] In the present embodiment, it is disclosed that search expression suggestions are selected from a preset search expression library, search prompt information is generated according to the search expression suggestions, and the search prompt information is displayed at a preset position; since the present embodiment directly selects search expression suggestions from the preset search expression library to generate search prompt information, and the search expressions in the preset search expression library are expressions that are easy for the search engine to understand, search prompts can be performed based on high-quality search expressions, thereby improving the search prompt effect and the search accuracy.

[0092] Reference Figure 4 , Figure 4 This is a flow chart of the second embodiment of the search prompt method of the present invention, based on the above Figure 2 The first embodiment shown provides a second embodiment of the search prompt method of the present invention.

[0093] In the second embodiment, the step S10 includes:

[0094] Step S101: responding to current search information and determining a current search intention according to the current search information.

[0095] It should be understood that in order to generate search prompt information corresponding to the current search information when searching to improve search efficiency and accuracy, in this embodiment, in response to the current search information and according to the current search intent corresponding to the current search information, a search expression suggestion is selected from a preset search expression library.

[0096] It should be noted that the current search information may be various types of information. For example, the current search information may be at least one of text search information, image search information, and voice search information. This embodiment does not limit this.

[0097] It is understandable that determining the current search intent based on the current search information may be to perform content recognition on the current search information to obtain the current search intent. In a specific implementation, for example, when the current search information is text search information, the current search information is subjected to content recognition through a text content recognition model to obtain the current search intent. The text content recognition model may include at least one of a text classification model, an entity recognition model, a sentiment analysis model, and a topic analysis model, and this embodiment does not limit this.

[0098] For ease of understanding, the following examples are used to illustrate each model, but this solution is not limited: In this embodiment, content recognition can be performed from the text category dimension, that is, a text classification model is used as a text content recognition model to automatically classify the input text into predefined categories, such as news, comments, advertisements, etc. The text classification model may include a Naive Bayes Model (NBM) model, a support vector machine (SVM), a deep learning model based on convolutional neural networks (CNN), and a deep learning model based on recurrent neural networks (RNN).

[0099] Content recognition can also be performed from the text entity dimension, that is, an entity recognition model is used as a text content recognition model to mark entities of specified types in the text, such as names of people, places, organizations, etc. The entity recognition model can include a conditional random field (CRF) model and a deep learning model based on named entity recognition (NER).

[0100] Content recognition can also be performed from the text sentiment dimension, that is, using a sentiment analysis model as a text content recognition model to analyze the emotional tendencies expressed in the text, such as positive, negative, or neutral. Sentiment analysis models can include rule-based sentiment analysis models, sentiment analysis models based on sentiment dictionaries, deep learning models based on long short-term memory networks (LSTM), and deep learning models based on CNN.

[0101] Content recognition can also be performed from the text topic dimension, that is, using a topic analysis model as a text content recognition model to discover topics in the text and analyze the connections between topics. The topic analysis model can include a latent semantic analysis (LSA) model and a latent Dirichlet allocation (LDA) model.

[0102] When the current search information is image search information, the current search information is subject to content recognition through an image content recognition model to obtain the current search intent. The image content recognition model may include at least one of an image classification model, a target detection model, and a semantic segmentation model, wherein the image classification model may be used to automatically classify the input image into predefined categories, such as faces, animals, etc., and the image classification model may include a CNN-based deep learning model and a transfer learning model, etc.; the target detection model may mark the location of the target object in the image and perform classification recognition, such as pedestrians, vehicles, etc., and the target detection model may include a region-convolutional neural network (RCNN) model, a YOLO model, and a single shot multi-box detector (SSD) model, etc.; the semantic segmentation model may identify the category to which each pixel in the image belongs and segment the image into different semantic regions, and the semantic segmentation model may include a fully convolutional network (FCN), a U-shaped network (UNet) model, and a deep labeling (DeepLab) model.

[0103] When the current search information is voice search information, the current search information is subject to content recognition through a voice content recognition model to obtain the current search intent. The voice content recognition model may include a hidden Markov model (HMM), a deep neural network model, such as a CNN-based deep learning model and a RNN-based deep learning model.

[0104] Furthermore, considering that the search intentions of users in different search scenarios are different, in order to improve the accuracy of search intention recognition, in this embodiment, the user's search intention is comprehensively determined based on the current search intention and the current search scenario, and the step S101 includes:

[0105] In response to current search information and identifying a current search scenario, a user's search intent is determined based on the current search information and the current search scenario.

[0106] It can be understood that determining the user's search intent based on the current search information and the current search scenario can be to first preliminarily determine the user's search intent based on the current search information, and then adjust the preliminarily determined search intent based on the current search scenario to obtain the user's search intent.

[0107] Furthermore, in order to accurately identify the current search scenario, in this embodiment, the current search scenario can be identified from multiple dimensions. The responding to the current search information and identifying the current search scenario include:

[0108] In response to current search information, a current search time, a current search location, and a current search user are obtained, and a current search scenario is identified according to at least one of the current search time, the current search location, and the current search user.

[0109] It should be noted that the current search time may be the current moment when the search is conducted, the current search location may be the current location when the search is conducted, and the current search user may be the basic information of the user conducting the search, such as account information, browsing history, or personal preferences.

[0110] In a specific implementation, for example, if the current search time is in the early morning or early morning, the user's search intention may be to search for breakfast recipes, fitness training methods and other content related to morning activities; while in the evening, the user's search intention may be to search for dinner recipes, movie recommendations and other content related to leisure and entertainment. If the user's current search location is in a certain city, it can be inferred based on the characteristics and needs of the city that the user's search intention may be the weather conditions, traffic guides, tourist attractions, etc. in the area. If the user has recently searched a lot of content about basketball games, it can be inferred that the user's search intention may be basketball-related news, team schedules, player data, etc.

[0111] Step S102: Select search expression suggestions from a preset search expression library based on the current search intent.

[0112] It should be understood that selecting search expression suggestions from a preset search expression library based on the current search intent may be to calculate the content similarity between the current search intent and the search expressions in the preset search expression library, and selecting search expression suggestions from the preset search expression library based on the content similarity.

[0113] In order to better capture the semantic information in the text and improve the accuracy of content similarity calculation, in this embodiment, the semantic features in the current search intent and the search expressions in the preset search expression library can be extracted through a pre-trained deep learning model, and then the content similarity between the current search intent and the search expressions in the preset search expression library is calculated based on the semantic features. Among them, the pre-trained deep learning model can be a Bidirectional Encoder Representations from Transformers (BERT) model to improve text processing efficiency.

[0114] This embodiment responds to current search information and selects search expression suggestions from a preset search expression library according to the current search intent corresponding to the current search information, so that when searching, search prompt information corresponding to the current search information can be generated, thereby improving search efficiency and accuracy.

[0115] Furthermore, considering that different search engines have different search rules, for example, the search rule of a search engine is: use double quotes to enclose words and only search for results containing the words; while the search rule of another search engine is: use plus signs to connect words and only search for results containing these words at the same time, the two are completely different. Therefore, in order to ensure that the search expression suggestion complies with the search rules of the search engine, the step S102 includes:

[0116] The current search engine is determined based on the current search information, and the search rules corresponding to the current search engine are found. Search expression suggestions are selected from the preset search expression library based on the current search intent and search rules.

[0117] It should be understood that determining the current search engine according to the current search information may be to obtain a search box corresponding to the current search information and then find the current search engine corresponding to the search box.

[0118] It can be understood that selecting search expression suggestions from the preset search expression library based on the current search intent and search rules can be to select search expression suggestions from the preset search expression library using the current search intent and search rules as reference information; or it can be to first select initial search expression suggestions from the preset search expression library based on the current search intent, and then adjust the format of the initial search expression suggestions based on the search rules to obtain search expression suggestions. This embodiment is not limited to this.

[0119] In the second embodiment, the step S20 includes:

[0120] Step S201: analyzing the user search habits of the current search user according to the user information of the current search user.

[0121] It should be understood that in order to better meet user needs and improve user experience, in this embodiment, when generating search prompt information, the user search habits of the current search user are also referred to. The user search habits may be the commonly used search language and commonly used expression methods when the user searches.

[0122] It should be noted that the user information may include the user's account information, search history or personal preferences, etc. Therefore, the user search habits of the current search user may be obtained by analyzing the user information of the current search user.

[0123] Step S202: Generate search prompt information according to the search expression suggestion and the user's search habits.

[0124] It is understandable that generating search prompt information based on search expression suggestions and user search habits can be to adjust the search expression suggestions according to the user search habits to obtain the search prompt information; or the user search habits and search expression suggestions can be directly used as the search prompt information, which is not limited in this embodiment.

[0125] This embodiment also refers to the user search habits of the current search user when generating search prompt information, so as to better meet user needs and improve user experience.

[0126] Reference Figure 5 , Figure 5 The flowchart of the third embodiment of the search prompt method of the present invention is shown in FIG. Based on the above embodiments, the third embodiment of the search prompt method of the present invention is proposed.

[0127] In the third embodiment, before step S10, the method further includes:

[0128] Step S01: Select a target search expression from the search record information, where the target search expression is an expression that is easy for the search engine to understand.

[0129] It should be understood that, in order to facilitate subsequent search prompts, in this embodiment, a target search expression is first selected from the search record information, and then a preset search expression library is constructed based on the target search expression.

[0130] It should be noted that the search record information may be record information when searching on the Internet.

[0131] It is understandable that selecting the target search expression from the search record information may be to score the search record information, and select the target search expression from the search record information based on the expression score. For example, the search record information may be scored based on dimensions such as search keywords and search formats, and the target search expression may be extracted from the search record information with expression scores higher than a preset score, so as to obtain a target search expression with accurate keywords and a standardized format.

[0132] Furthermore, in order to improve the quality of the target search expression, in this embodiment, the target search expression can be selected from the historical search expressions according to the result quality of the historical search results corresponding to the historical search expressions. The step S01 includes:

[0133] Extract historical search expressions and historical search results corresponding to the historical search expressions from the search record information, analyze the result quality of the historical search results, and select target search expressions from the historical search expressions based on the result quality.

[0134] It is understandable that in order to accurately analyze the result quality of historical search results, in this embodiment, historical search results can be analyzed from multiple dimensions, for example, from the source website of the historical search results, access information, and result feedback, etc., and this embodiment does not limit this.

[0135] It should be understood that selecting a target search expression from historical search expressions based on result quality can be by sorting the historical search results from high to low based on result quality, and selecting the historical search expressions corresponding to a preset number of historical search results with the highest sorting as the target search expression; or it can be by selecting the historical search expressions corresponding to historical search results with result quality higher than a preset quality as the target search expression, which is not limited in this embodiment.

[0136] Step S02: constructing a preset search expression library based on the target search expression.

[0137] It can be understood that constructing a preset search expression library based on a target search expression may be storing the target search expression into a preset database to obtain the preset search expression library.

[0138] This embodiment first selects a target search expression from the search record information, and then constructs a preset search expression library based on the target search expression, thereby being able to pre-construct a preset search expression library for subsequent search prompts.

[0139] Furthermore, considering that selecting a target search expression from search record information is essentially selecting an expression that is easy for the search engine to understand from the search information input by the user as the target search expression, there may be a defect that is easily affected by the search information input by the user, and there are certain limitations. Therefore, in order to overcome the above defects, in this embodiment, by analyzing the search samples to summarize the standard search keywords and standard search formats, and generating standard search expressions based on the standard search keywords and standard search formats to construct a preset search expression library, the step S02 includes:

[0140] The search samples are analyzed through the natural language processing model to obtain standard search keywords and standard search formats, standard search expressions are generated according to the standard search keywords and standard search formats, and a preset search expression library is constructed based on the standard search expressions and target search expressions.

[0141] It should be noted that the natural language processing model may include at least one of a word vector model, a word segmentation model, a part-of-speech tagging model, a named entity recognition model, a syntax analysis model, and a sentiment analysis model, and this embodiment does not limit this. The search sample may be a search expression sample that is easy for the search engine to understand, and may be obtained from the Internet or uploaded in advance, and this embodiment does not limit this.

[0142] It can be understood that analyzing the search samples through a natural language processing model to obtain standard search keywords and a standard search format can be to perform a commonality analysis on high-quality search samples through a natural language processing model to obtain common features between high-quality search samples, and extract information from the high-quality search samples based on the common features to obtain standard search keywords and a standard search format.

[0143] Based on the above embodiments, a fourth embodiment of the search prompt method of the present invention is proposed.

[0144] In a fourth embodiment, the search prompt method further includes:

[0145] Responding to current search information, and determining a current search intent based on the current search information;

[0146] The preset position for displaying the search prompt information is determined according to the current search intent.

[0147] It should be understood that in order to facilitate users to view the search prompt information, in this embodiment, the preset position when displaying the search prompt information is determined according to the previous search intention.

[0148] It can be understood that determining the current search intent based on the current search information may be to perform content recognition on the current search information to obtain the current search intent.

[0149] In a fourth embodiment, the search prompt method further includes:

[0150] Detect whether the user has searched multiple times within a preset time;

[0151] If so, execute the step of selecting search expression suggestions from the preset search expression library.

[0152] It should be understood that in order to meet the actual search needs of users and improve user experience, in this embodiment, the search prompt is not immediately given when the user searches, but when the user fails to find accurate search results after multiple searches, that is, when it is detected that the user has searched multiple times within a preset time and continues to search, the search prompt method is executed. The preset time can be preset, for example, the preset time can be five minutes, that is, when the user fails to find accurate search results after multiple searches within five minutes, the search prompt is given.

[0153] In addition, an embodiment of the present invention further proposes a storage medium, on which a search prompt program is stored. When the search prompt program is executed by a processor, the search prompt method as described above is implemented.

[0154] In addition, refer to Figure 6 , the embodiment of the present invention further provides a search prompt device, the search prompt device comprising: a statement selection module 10, a prompt generation module 20 and a prompt display module 30;

[0155] The expression selection module 10 is used to select search expression suggestions from a preset search expression library.

[0156] It can be understood that in this embodiment, a search prompt may be given when the user is searching, for example, when the user is searching through the search box; a search prompt may also be given when the user is not searching, for example, when the user enters the application interface; for example, a search prompt may be given when the user inputs through an input method, and this embodiment does not limit this.

[0157] It should be noted that the preset search expression library can be generated in advance, and the preset search expression library can include multiple search expressions, and the search expressions are expressions that are easy for the search engine to understand.

[0158] It should be understood that selecting search expression suggestions from the preset search expression library may be randomly selecting search expression suggestions from the preset search expression library; or selecting search expression suggestions from the preset search expression library based on user information, for example, predicting the user's search preferences based on the user's account information, browsing history, or personal preferences, and selecting search expression suggestions from the preset search expression library based on the search preferences; and also selecting search expression suggestions from the preset search expression library based on the current search information when the user enters the current search information, which is not limited in this embodiment.

[0159] The prompt generating module 20 is used to generate search prompt information according to the search expression suggestion.

[0160] It should be understood that generating search prompt information based on search expression suggestions may be directly using the search expression suggestions as search prompt information; or the search expression suggestions may be written into a preset prompt template to obtain search prompt information; or the search prompt information may be generated in combination with the user search habits of the current search user, which is not limited in this embodiment.

[0161] The prompt display module 30 is used to display the search prompt information at a preset position.

[0162] It should be understood that the preset position can be preset, for example, the preset position can be a floating window near the search input box, a floating window near the search input box, or other preset prompt positions. Of course, in order to better meet user needs, the preset position can also be determined according to the current search intent, and this embodiment does not limit this.

[0163] For ease of understanding, refer to Figure 3 This is for illustration only, but not for limitation. Figure 3 This is a diagram of search prompts. In the figure, after the user enters the application interface of the smart assistant, the search prompt information can be displayed above the search bar. The search prompt information consists of two parts, one is the prompt content, such as "I can give you inspiration", and the other is the search expression suggestion, such as "write a science fiction novel". If the user clicks on the search example, the search example can be directly filled into the search bar as search information.

[0164] In the present embodiment, it is disclosed that search expression suggestions are selected from a preset search expression library, search prompt information is generated according to the search expression suggestions, and the search prompt information is displayed at a preset position; since the present embodiment directly selects search expression suggestions from the preset search expression library to generate search prompt information, and the search expressions in the preset search expression library are expressions that are easy for the search engine to understand, search prompts can be performed based on high-quality search expressions, thereby improving the search prompt effect and the search accuracy.

[0165] Other embodiments or specific implementations of the search prompt device of the present invention can refer to the above-mentioned method embodiments and will not be described in detail here.

[0166] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0167] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0168] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory image (ROM) / random access memory (RAM), a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0169] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

[0170] The present invention discloses A1, a search prompt method, the search prompt method comprising:

[0171] Select search expression suggestions from the preset search expression library;

[0172] Generating search prompt information according to the search expression suggestion;

[0173] The search prompt information is displayed at a preset position.

[0174] A2. The search prompt method as described in A1, wherein the selecting a search expression suggestion from a preset search expression library comprises:

[0175] Responding to current search information, and determining a current search intent based on the current search information;

[0176] Search expression suggestions are selected from a preset search expression library based on the current search intent.

[0177] A3. The search prompt method as described in A2, wherein responding to the current search information and determining the current search intention according to the current search information comprises:

[0178] Responding to current search information and identifying a current search scenario;

[0179] The user's search intention is determined according to the current search information and the current search scenario.

[0180] A4. The search prompt method as described in A3, wherein responding to the current search information and identifying the current search scenario comprises:

[0181] Responding to the current search information, and obtaining the current search time, the current search location, and the current search user;

[0182] A current search scenario is identified according to at least one of the current search time, the current search location, and the current search user.

[0183] A5. The search prompt method as described in A2, wherein the selecting a search expression suggestion from a preset search expression library based on the current search intent comprises:

[0184] Determine a current search engine according to the current search information, and search for a search rule corresponding to the current search engine;

[0185] Search expression suggestions are selected from a preset search expression library based on the current search intent and the search rules.

[0186] A6. The search prompt method as described in any one of A1 to A5, wherein the search prompt method further comprises:

[0187] Selecting a target search expression from the search record information, wherein the target search expression is an expression that is easy for the search engine to understand;

[0188] A preset search expression library is constructed based on the target search expression.

[0189] A7. The search prompt method as described in A6, wherein the step of selecting a target search expression from the search record information comprises:

[0190] Extracting historical search expressions and historical search results corresponding to the historical search expressions from the search record information;

[0191] Analyzing the result quality of the historical search results;

[0192] A target search expression is selected from the historical search expressions based on the result quality.

[0193] A8. The search prompt method as described in A6, wherein the step of constructing a preset search expression library based on the target search expression comprises:

[0194] Analyze search samples through natural language processing models to obtain standard search keywords and standard search formats;

[0195] Generate a standard search expression according to the standard search keyword and the standard search format;

[0196] A preset search expression library is constructed based on the standard search expression and the target search expression.

[0197] A9. The search prompt method as described in any one of A1 to A5, wherein generating search prompt information according to the search expression suggestion comprises:

[0198] Analyzing the user search habits of the current search user according to the user information of the current search user;

[0199] Generate search prompt information based on the search expression suggestion and the user's search habits.

[0200] A10. The search prompt method as described in any one of A1 to A5, further comprising:

[0201] Responding to current search information, and determining a current search intent based on the current search information;

[0202] The preset position for displaying the search prompt information is determined according to the current search intent.

[0203] A11. The search prompt method as described in any one of A1 to A5, wherein the search prompt method further comprises:

[0204] Detect whether the user has searched multiple times within a preset time;

[0205] If so, execute the step of selecting search expression suggestions from the preset search expression library.

[0206] The present invention also discloses B12, a search prompt device, which includes: a memory, a processor, and a search prompt program stored in the memory and executable on the processor, wherein the search prompt program implements the search prompt method described above when executed by the processor.

[0207] The present invention also discloses C13, a storage medium, on which a search prompt program is stored, and when the search prompt program is executed by a processor, the search prompt method as described above is implemented.

[0208] The present invention also discloses D14, a search prompt device, the search prompt device comprising: a statement selection module, a prompt generation module and a prompt display module;

[0209] The expression selection module is used to select search expression suggestions from a preset search expression library;

[0210] The prompt generating module is used to generate search prompt information according to the search expression suggestion;

[0211] The prompt display module is used to display the search prompt information at a preset position.

[0212] D15. The search prompt device as described in D14, wherein the expression selection module is further used to respond to current search information and determine the current search intention according to the current search information;

[0213] The expression selection module is also used to select search expression suggestions from a preset search expression library based on the current search intention.

[0214] D16. The search prompt device as described in D15, wherein the expression selection module is further used to respond to the current search information and identify the current search scenario;

[0215] The expression selection module is also used to determine the user's search intention based on the current search information and the current search scenario.

[0216] D17. The search prompt device as described in D16, wherein the expression selection module is further used to respond to the current search information and obtain the current search time, the current search location and the current search user;

[0217] The expression selection module is further used to identify the current search scenario according to at least one of the current search time, the current search location and the current search user.

[0218] D18. The search prompt device as described in D15, wherein the expression selection module is further used to determine the current search engine according to the current search information, and to find the search rule corresponding to the current search engine;

[0219] The expression selection module is also used to select search expression suggestions from a preset search expression library based on the current search intent and the search rules.

[0220] D19. The search prompt device as described in any one of D14 to D18, further comprising: a statement library construction module;

[0221] The expression library construction module is used to select a target search expression from the search record information, wherein the target search expression is an expression that is easy for the search engine to understand;

[0222] The expression library construction module is also used to construct a preset search expression library based on the target search expression.

[0223] D20, the search prompt device as described in D19, wherein the expression library construction module is further used to extract historical search expressions and historical search results corresponding to the historical search expressions from the search record information;

[0224] The expression library construction module is also used to analyze the result quality of the historical search results;

[0225] The expression library construction module is also used to select a target search expression from the historical search expressions based on the result quality.

Claims

1. A search prompt method, characterized in that: The search prompt method comprises: Select search expression suggestions from the preset search expression library; Generating search prompt information according to the search expression suggestion; The search prompt information is displayed at a preset position.

2. The search prompt method according to claim 1, characterized in that: The selecting a search expression suggestion from a preset search expression library includes: Responding to current search information, and determining a current search intent based on the current search information; Search expression suggestions are selected from a preset search expression library based on the current search intent.

3. The search prompt method according to claim 2, characterized in that: The responding to the current search information and determining the current search intention according to the current search information includes: Responding to current search information and identifying a current search scenario; The user's search intention is determined according to the current search information and the current search scenario.

4. The search prompt method according to claim 3, characterized in that: The responding to the current search information and identifying the current search scenario includes: Responding to the current search information, and obtaining the current search time, the current search location, and the current search user; A current search scenario is identified according to at least one of the current search time, the current search location, and the current search user.

5. The search prompt method according to claim 2, characterized in that: The selecting a search expression suggestion from a preset search expression library based on the current search intent includes: Determine a current search engine according to the current search information, and search for a search rule corresponding to the current search engine; Search expression suggestions are selected from a preset search expression library based on the current search intent and the search rules.

6. The search prompt method according to any one of claims 1 to 5, characterized in that: The search prompt method further includes: Selecting a target search expression from the search record information, wherein the target search expression is an expression that is easy for the search engine to understand; A preset search expression library is constructed based on the target search expression.

7. The search prompt method according to claim 6, characterized in that: The step of selecting a target search expression from the search record information includes: Extracting historical search expressions and historical search results corresponding to the historical search expressions from the search record information; Analyzing the result quality of the historical search results; A target search expression is selected from the historical search expressions based on the result quality.

8. A search prompt device, characterized in that: The search prompt device includes: a memory, a processor, and a search prompt program stored in the memory and executable on the processor, wherein the search prompt program implements the search prompt method according to any one of claims 1 to 7 when executed by the processor.

9. A storage medium, characterized in that: The storage medium stores a search prompt program, and when the search prompt program is executed by the processor, the search prompt method according to any one of claims 1 to 7 is implemented.

10. A search prompt device, characterized in that: The search prompt device comprises: a statement selection module, a prompt generation module and a prompt display module; The expression selection module is used to select search expression suggestions from a preset search expression library; The prompt generating module is used to generate search prompt information according to the search expression suggestion; The prompt display module is used to display the search prompt information at a preset position.

Images