Content searching method and device and computer readable storage medium

Abstract

The embodiment of the invention discloses a content searching method and device and a computer readable storage medium. A dialogue type search page is displayed, and the dialogue type search page provides a dialogue type search function; obtaining search information in response to a search information input operation for the dialogue type search page; a dialogue type search result page is displayed, the dialogue type search result page comprises reply information corresponding to the search information, the reply information comprises identification information of search content searched based on the search information and dialogue reply information for the search information, and the dialogue reply information is generated based on summary information extracted from the search content. Therefore, the identification information of the search content corresponding to the search information and the reply information generated based on the abstract of the search content are displayed in a dialogue mode, the search content matched with the input search information can be visually displayed, a user can visually and conveniently obtain the search result of the search information, and the user experience is improved. And the content search efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to a content search method, device and computer-readable storage medium. Background Art

[0002] With the rapid development of computer technology, a large amount of content has been generated on the Internet. Users can search for required content in the large amount of content through search engines. In existing content search methods, users can obtain search content associated with the search keyword by inputting a search keyword, and find required information in the searched content.

[0003] In the process of research and practice of existing technologies, it is found that the existing content search method is relatively cumbersome, and users cannot intuitively obtain content that matches the input search keywords, and thus cannot quickly obtain the required content, which makes the content search efficiency low. Summary of the invention

[0004] The embodiments of the present application provide a content search method, device and computer-readable storage medium, which can intuitively display search content matching the input search information, so that users can intuitively and conveniently obtain the search results of the search information, thereby improving the content search efficiency.

[0005] The present application embodiment provides a content search method, which is applied to a terminal, including:

[0006] Displaying a conversational search page, wherein the conversational search page provides a conversational search function;

[0007] In response to a search information input operation on the conversational search page, obtaining search information;

[0008] A conversational search results page is displayed, wherein the conversational search results page includes reply information corresponding to the search information, wherein the reply information includes identification information of search content searched based on the search information, and conversational reply information for the search information, wherein the conversational reply information is generated based on summary information extracted from the search content.

[0009] Accordingly, the embodiment of the present application further provides a content search method, which is applied to a server and includes:

[0010] receiving search information sent by a terminal;

[0011] Searching for search content matching the search information based on the search information;

[0012] generating identification information corresponding to the search content based on the search content;

[0013] Extracting a summary of the search content to generate summary information corresponding to the search content;

[0014] The dialog reply information corresponding to the search information is generated according to the summary information, and the identification information and the dialog reply information are sent to the terminal so as to be displayed on the dialog search result page of the terminal.

[0015] Accordingly, an embodiment of the present application provides a content search device, applied to a terminal, including:

[0016] A first display unit, configured to display a conversational search page, wherein the conversational search page provides a conversational search function;

[0017] an information acquisition unit, configured to acquire search information in response to a search information input operation on the conversational search page;

[0018] A second display unit is used to display a conversational search results page, wherein the conversational search results page includes reply information corresponding to the search information, the reply information includes identification information of the search content searched based on the search information, and conversational reply information for the search information, wherein the conversational reply information is generated based on summary information extracted from the search content.

[0019] In one embodiment, the conversational search result page further includes user conversation text, and the user conversation text is obtained based on the search information.

[0020] In one embodiment, the content search device further includes:

[0021] The detail viewing unit is used to display a content detail page of the target search content corresponding to the target identification information in the identification information in response to a detail viewing operation on the target identification information, wherein the content detail page includes the detailed content of the target search content.

[0022] Accordingly, the embodiment of the present application further provides a content search device, which is applied to a server and includes:

[0023] A receiving unit, used for receiving search information sent by a terminal;

[0024] A search unit, configured to search for search content matching the search information based on the search information;

[0025] an identification generating unit, configured to generate identification information corresponding to the search content based on the search content;

[0026] A generating unit, configured to extract a summary of the search content and generate summary information corresponding to the search content;

[0027] A sending unit is used to generate dialogue reply information corresponding to the search information according to the summary information, and send the identification information and the dialogue reply information to the terminal so as to display the identification information and the dialogue reply information in the dialogue search result page of the terminal.

[0028] In one embodiment, the generating unit comprises:

[0029] A key text extraction subunit, configured to extract key text from the search content using the trained first summary model to obtain key text corresponding to the search content;

[0030] The summary information generating subunit is used to generate a summary of the key text by using the trained second summary model to obtain summary information corresponding to the search content.

[0031] In one embodiment, the content search device further includes:

[0032] a sample acquisition unit, configured to acquire a first sample pair of a first language type, and translate the sample pair of the first language type to obtain a second sample pair of a second language type, wherein the second language type is the same as the language type corresponding to the search information;

[0033] A first training unit is configured to perform model training processing on a preset first summary model and a preset second summary model based on the first sample to obtain a trained first summary model and a second summary model in a first language type;

[0034] The second training unit is used to perform language transfer training on the trained first summary model and the second summary model in the first language type according to the second sample to obtain the trained first summary model and the trained second summary model in the second language type.

[0035] In one embodiment, the first sample pair includes a search information sample, and a content sample and target summary information matched by the search information sample, and the first training unit is used to:

[0036] Using a preset first summary model to extract features from the sentence text in the content sample to obtain text features corresponding to the sentence text;

[0037] Filtering out sample key texts from the sentence texts based on the text features;

[0038] Generate a summary of the sample key text using a preset second summary model to obtain sample summary information matching the search information sample;

[0039] Determine loss information corresponding to the preset first summary model and the preset second summary model according to the sample summary information, the search information sample and the target summary information;

[0040] The preset first summary model and the preset second summary model are converged based on the loss information to obtain a trained first summary model and a trained second summary model in the first language type.

[0041] In one embodiment, the content search device further includes:

[0042] a reply generating unit, configured to generate reply information matching the search information by using a dialogue generating model if no search content matching the search information is found based on the search information;

[0043] The reply sending unit is used to send the reply information to the terminal so that the reply information corresponding to the search information is displayed in the conversational search result page of the terminal.

[0044] In addition, an embodiment of the present application further provides a computer-readable storage medium, which stores a plurality of instructions, and the instructions are suitable for a processor to load to execute the steps in any one of the content search methods provided in the embodiment of the present application.

[0045] In addition, an embodiment of the present application further provides a computer device, including a processor and a memory, wherein the memory stores an application program, and the processor is used to run the application program in the memory to implement the content search method provided in the embodiment of the present application.

[0046] In addition, an embodiment of the present application also provides a content search system, the system comprising: a server and a terminal;

[0047] The server includes the above-mentioned content search device;

[0048] The terminal comprises the above-mentioned content searching device.

[0049] The embodiment of the present application also provides a computer program product or a computer program, wherein the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the content search method provided in the embodiment of the present application.

[0050] The embodiment of the present application displays a conversational search page, which provides a conversational search function; obtains search information in response to a search information input operation on the conversational search page; and displays a conversational search result page, which includes reply information corresponding to the search information, the reply information including identification information of the search content searched based on the search information, and conversation reply information for the search information, the conversation reply information being generated based on summary information extracted from the search content. In this way, by determining the conversation reply information in the form of a conversation based on the identification information of the search content corresponding to the search information and the reply information generated based on the summary of the search content for the search information input on the conversational search page, and displaying the conversation reply information on the conversational search result page, the search content matching the input search information can be displayed in an intuitive conversational manner, so that the user can intuitively and conveniently obtain the search results matching the input search information, thereby improving the efficiency of content search. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0052] Figure 1 This is a schematic diagram of an implementation scenario of a content search method provided in an embodiment of the present application;

[0053] Figure 2 It is a flowchart of a content search method provided in an embodiment of the present application;

[0054] Figure 3 This is a schematic diagram of a conversational search result page of a content search method provided in an embodiment of the present application;

[0055] Figure 4 is another flowchart of a content search method provided by an embodiment of the present application;

[0056] Figure 5a It is a schematic diagram of the overall process of a content search method provided by an embodiment of the present application;

[0057] Figure 5b It is a specific flow chart of a content search method provided by an embodiment of the present application;

[0058] Figure 5c It is a training flow diagram of a content search method provided in an embodiment of the present application;

[0059] Figure 6is a schematic diagram of the structure of a content search device provided in an embodiment of the present application;

[0060] Figure 7 is another structural schematic diagram of the content search device provided in an embodiment of the present application;

[0061] Figure 8 is a flowchart of a content search system provided by an embodiment of the present application;

[0062] Fig. 9 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0064] The embodiments of the present application provide a content search method, device and computer-readable storage medium. The content search device can be integrated in a computer device, which can be a server or a terminal.

[0065] Among them, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, network acceleration services (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms. Terminals may include but are not limited to mobile phones, computers, intelligent voice interaction devices, smart home appliances, vehicle-mounted terminals, aircraft, etc. Terminals and servers can be directly or indirectly connected via wired or wireless communications, and this application does not limit this.

[0066] See also Figure 1 , taking the case where the content search device is integrated into a computer device, Figure 1A schematic diagram of an implementation scenario of the content search method provided in an embodiment of the present application, wherein the computer device may be a terminal, and the computer device may display a conversational search page, the conversational search page providing a conversational search function; in response to a search information input operation for the conversational search page, the search information is obtained; and a conversational search results page is displayed, the conversational search results page including reply information corresponding to the search information, the reply information including identification information of the search content searched based on the search information, and conversational reply information for the search information, the conversational reply information being generated based on summary information extracted from the search content.

[0067] It should be noted that Figure 1 The implementation environment scenario diagram of the content search method shown is only an example. The implementation environment scenario of the content search method described in the embodiment of the present application is to more clearly illustrate the technical solution of the embodiment of the present application, and does not constitute a limitation on the technical solution provided by the embodiment of the present application. It is known to those skilled in the art that with the evolution of data processing and the emergence of new business scenarios, the technical solution provided by the present application is also applicable to similar technical problems.

[0068] The solutions provided by the embodiments of the present application are specifically described by the following embodiments. It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments.

[0069] This embodiment will be described from the perspective of a content search device, which may be integrated in a terminal.

[0070] See also Figure 2 , Figure 2 : is a flow chart of a content search method provided in an embodiment of the present application. The content search method includes:

[0071] In step 101, a conversational search page is displayed.

[0072] The conversational search page may be a page for implementing conversational search, and conversational search may refer to a scenario in which search triggering and search result feedback are implemented in the form of a conversation. The conversational search page may provide a conversational search function, and the conversational search function may refer to a function in which search triggering and search result feedback are implemented in the form of a conversation.

[0073] In step 102, in response to a search information input operation on a conversational search page, search information is acquired.

[0074] The search information input operation may be an operation of inputting search information, for example, an operation triggered by a user inputting search information in an input box provided on a conversational search page. The search information may be information to be searched, may be text-type information input by a user, may be voice-type information input by a user, etc. For example, when a user needs to search for a nearby coffee shop with good coffee, the user may enter search information such as "recommendations for coffee shops in XX area" in the conversational search page.

[0075] In step 103, a conversational search result page is displayed.

[0076] Among them, the conversational search result page can be a page that displays the search results corresponding to the search information in a conversational manner. The conversational search result page may include reply information corresponding to the search information. The reply information may be a reply to the search information generated based on the searched search results. The reply information may include identification information of the search content searched based on the search information, and conversational reply information for the search information. The conversational reply information is generated based on summary information extracted from the search content.

[0077] The search content may be content searched by the search engine according to the search information, and the content may be articles, notes, pictures, videos and other types of content. The identification information may be information identifying a search content, may indicate a search content, and may also enable viewing of the search content by triggering the identification information. For example, the identification information may be a mark of a link corresponding to the search content, and identification information carrying a link corresponding to the search content may be generated in the form of a hyperlink. The identification information may use the title or summary of the search content as a carrier of the link to the search content, and the user may click on the identification information in the form of a link corresponding to the search content to jump to the details of the search content for viewing. The dialogue reply information may be information that replies to the search information in the form of a dialogue based on the summary information extracted from the search content, and the summary information may be a content summary extracted from the search content corresponding to the search information. For example, when the search information is "recommendations for coffee shops in XX area", the dialogue reply information may be "There are many delicious coffee shops in XX area. For example, there is a XX coffee shop on XX Road, which is closest to you. This shop has many repeat customers. Their coffee beans are all produced from XX coffee shops in XX area and are rich in flavor. In addition, there is a XX coffee shop on XX Road. This shop has many people queuing up every day and uses the latest XX method to make coffee..." etc. Specific dialogue reply information may be generated based on actual needs and actual search conditions. In this way, users can intuitively and conveniently obtain search results that match the input search information based on the concise and clear search results indicated in the dialogue reply information, so that they can quickly obtain the required information in the search results, avoiding the need to check each search content to find information that meets the user's needs in the prior art, improving content search efficiency, and thus improving the user's search experience.

[0078] In one embodiment, the conversational search result page also includes a user conversation text, which is obtained based on the search information. For example, the user conversation text may be the search information input by the user, and may be displayed in the conversational search result page in the form of a conversation. For example, please refer to Figure 3 , Figure 31 is a schematic diagram of a conversational search result page of a content search method provided in an embodiment of the present application. Assuming that the search information is "the best coffee in Shanghai", the user conversation text can be displayed in the conversational search result page, and then the search result corresponding to the search information can be displayed in the conversational search result page in the form of reply information. The information display area where the reply information is located may include an area for displaying the conversation reply information and an area for displaying the identification information of the search content. The conversation reply information may be "The best coffee shop in Shanghai is recommended: XX Coffee Shop 1: A warm corner in a corner of the city...; XX Coffee Shop 2...", etc. The area for displaying the identification information of the search content may include identification information of at least one search content corresponding to the search information. The text included in the identification information may be the title of the search content. For example, please continue to refer to Figure 3 The identification information of the search content can carry a link to the search content, and include a text carrier of the search content, such as "A review of the top 10 coffee shops in Shanghai (in my mind)", "Ceiling-level coffee shops in Shanghai that you can visit repeatedly", etc. In this way, users can search clearly and intuitively through the user conversation text displayed on the conversational search result page, thereby improving the search experience.

[0079] Optionally, after the conversational search result page is displayed, in response to a detail viewing operation for the target identification information in the identification information, a content detail page of the target search content corresponding to the target identification information may be displayed.

[0080] Among them, the target identification information can be the identification information selected for detail viewing in the identification information, the detail viewing operation can be an operation of viewing the details of the search content, the target search content can be the search content corresponding to the target identification in detail, and the content details page can include the details of the target search content.

[0081] For example, please refer to Figure 3 In the area displaying the identification information of the search content, the user can determine the target identification information in the identification information of the search content according to the information of interest, and can perform trigger operations such as clicking on the target identification information, thereby triggering a detail viewing operation for the target identification information, and displaying the content details page of the target search content corresponding to the target identification information. Optionally, the content details page of the target search content can be directly opened, or a new conversation message can be generated in the form of a conversation in the conversational search results page, and the conversation information may include the content details of the target search content, etc.

[0082] Optionally, you can also ask questions about the search information entered by the user in the conversational search results page to further refine, correct or expand the user's original question. For example, please continue to refer to Figure 3 When the search information is "the best coffee in Shanghai", the search information can be followed up to obtain at least one follow-up information, for example, it can include "What famous coffee shops in Shanghai are there?", "What special coffees in Shanghai are worth tasting?" and "What coffee shops in Shanghai are suitable for taking photos?", etc., so that the user's original question "the best coffee in Shanghai" can be further refined, corrected or expanded, so as to guide the user to determine more appropriate and necessary search information, thereby improving the user's retention rate, search accuracy and search experience.

[0083] As can be seen from the above, the embodiment of the present application displays a conversational search page, which provides a conversational search function; obtains search information in response to a search information input operation on the conversational search page; and displays a conversational search result page, which includes reply information corresponding to the search information, the reply information including identification information of the search content searched based on the search information, and conversational reply information for the search information, the conversational reply information being generated based on summary information extracted from the search content. In this way, by determining the conversational reply information in the form of a conversation based on the identification information of the search content corresponding to the search information and the reply information generated based on the summary of the search content for the search information input on the conversational search page, and displaying the conversational reply information on the conversational search result page, the search content matching the input search information can be displayed in an intuitive conversational manner, so that the user can intuitively and conveniently obtain the search results matching the input search information, thereby improving the efficiency of content search.

[0084] This embodiment will be described from the perspective of a content search device, which may be specifically integrated in a server.

[0085] For a better description of the embodiments of this application, please refer to Figure 4 , Figure 4 This is another flowchart of the content search method provided in the embodiment of the present application. The specific process is as follows:

[0086] In step 201, search information sent by a terminal is received.

[0087] The search information may be text input by the user for search, or may be voice-type search information input by the user, thereby converting the voice-type search information into text-type search information.

[0088] In step 202, search content matching the search information is searched based on the search information.

[0089] The search content may be content that matches the search information found through a search engine.

[0090] For example, see Figure 5a , Figure 5a This is a schematic diagram of the overall process of a content search method provided by an embodiment of the present application. After obtaining the search information input by the user, the search information can be rewritten with search keywords, so that the search keywords can be extracted from the search information, and the search keywords can be keywords extracted from the search information and provided to the search engine for content search. Therefore, the search engine can search for search content matching the search information based on the search keywords of the search information.

[0091] In step 203, identification information corresponding to the search content is generated based on the search content.

[0092] The identification information may be information identifying a search content, may indicate a search content, and may also enable viewing of the search content by triggering the identification information. For example, the identification information may be a mark of a link corresponding to the search content, and identification information carrying a link corresponding to the search content may be generated in a hyperlink manner. The identification information may use the title or summary of the search content as a carrier of the link to the search content, and the user may click on the identification information in the form of a link corresponding to the search content to jump to the details of the search content for viewing.

[0093] In step 204, a summary is extracted from the search content to generate summary information corresponding to the search content.

[0094] The summary information may be a content summary extracted from the search content, and may be used to summarize the content included in the search content.

[0095] There are many ways to extract the summary of the search content and generate the summary information corresponding to the search content. For example, the trained first summary model can be used to extract the key text of the search content to obtain the key text corresponding to the search content, and the trained second summary model can be used to generate the summary of the key text to obtain the summary information corresponding to the search content. For example, please refer to Figure 5b , Figure 5b This is a specific flow chart of a content search method provided in an embodiment of the present application. Assuming that the search content is a note, after the search information is obtained and Note 1, Note 2, ... Note n matching the search information are obtained through a search engine, a trained first summary model can be used to extract key text from the search content to obtain key text corresponding to the search content, and a trained second summary model can be used to generate a summary of the key text, thereby obtaining summary information corresponding to the search content.

[0096] Among them, the trained first summary model can be a summary model trained to extract key text from the search content, and can be an extractive summary model. For example, the bidirectional encoder representation from the transformer (Bidirectional Encoder Representations from Transformers, referred to as BERT) can be used as the basic model of the first summary model. The key text can be the key text in the search content, or it can be a more important sentence in the search content. The trained second summary model can be a summary model trained to generate a summary of the key text, and can be a generative summary model. For example, the generative pre-trained Transformer model (Generative Pre-Trained Transformer, referred to as GPT) can be used as the basic model of the second summary model.

[0097] Optionally, there are many ways to train the first summary model and the second summary model. For example, please refer to Figure 5c , Figure 5c It is a training flow diagram of a content search method provided by an embodiment of the present application, which can obtain a first sample pair of a first language type, translate the sample pair of the first language type to obtain a second sample pair of a second language type, perform model training processing on a preset first summary model and a preset second summary model based on the first sample pair, and obtain a trained first summary model and a second summary model in the first language type, and perform language transfer training on the trained first summary model and second summary model in the first language type according to the second sample pair to obtain a trained first summary model and a trained second summary model in the second language type.

[0098] The first language type may be the language type of the acquired data set, for example, it may be the English type, the data set may be a sample set for training the first summary model and the second summary model, the first sample pair may be a sample pair in the data set of the first language type, that is, a sample pair of the first language type corresponding to the first summary model and the second summary model. The second language type may be the same as the language type corresponding to the search information, for example, it may be the Chinese type. The second sample pair may be a sample pair of the second language type. The trained first summary model and second summary model in the first language type may be the first summary model and second summary model obtained by training with the sample pair of the first language type, and the first summary model and second summary model at this time may extract and generate a summary of the search content corresponding to the search information of the first language type.

[0099] There are many ways to translate the sample pairs of the first language type to obtain the second sample pairs of the second language type. For example, some sample pairs of the sample pairs of the first language type can be translated to obtain the second sample pairs of the second language type. For example, assuming that the number of first sample pairs of the first language type is 1.8 million, 170,000 sample pairs can be selected from the first sample pairs of the first language type and translated into the second language type to obtain the second sample pairs of the second language type.

[0100] There are multiple ways to perform model training on the preset first summary model and the preset second summary model based on the first sample to obtain the trained first summary model and the second summary model under the first language type. For example, the first sample pair may include a search information sample of the first language type, a content sample and a target summary information matched by the search information sample. The search information sample may be a query, a keyword, or a text. The content sample may be the content matched by the search information sample that can be searched by a search engine. In this way, the preset first summary model may be used to extract features from the sentence text in the content sample to obtain text features corresponding to the sentence text. Based on the text features, sample key texts are screened out from the sentence texts. The preset second summary model is used to generate a summary of the sample key text to obtain sample summary information matching the search information sample. According to the sample summary information, the search information sample, and the target summary information, the loss information corresponding to the preset first summary model and the preset second summary model is determined. Based on the loss information, the preset first summary model and the preset second summary model are converged to obtain the trained first summary model and the second summary model under the first language type.

[0101] Among them, the target summary information can be the summary information expected to be extracted from the content sample, that is, it can be used as a label in the model training process. The preset first summary model can be a preset untrained first summary model, the sentence text can be a sentence in the content sample, the text feature can be a feature that characterizes the sentence text, the sample key text can be a sentence text with a high degree of importance screened out from the sentence text, the preset second summary model can be a preset untrained second summary model, and the sample summary information can be the summary information generated in the content sample. The loss information can be information that measures the gap between the summary generation capabilities of the preset first summary model and the preset second summary model and the expected summary generation capabilities, that is, it can be information that measures the gap between the sample summary information extracted from the content sample by the preset first summary model and the preset second summary model and the expected target summary information of the content sample.

[0102] There are multiple ways to determine the loss information corresponding to the preset first summary model and the preset second summary model based on the sample summary information, the search information sample, and the target summary information. For example, the similarity between the sample summary information and the search information sample and the target summary information can be calculated, and the loss information corresponding to the preset first summary model and the preset second summary model can be calculated based on the similarity. For example, a cross entropy loss function (Softmax function) can be used to calculate the loss information corresponding to the preset first summary model and the preset second summary model based on the similarity between the sample summary information and the search information sample and the target summary information.

[0103] After the preset first summary model and the preset second summary model are trained based on the first sample, the first summary model and the second summary model trained in the first language type can be trained for language transfer according to the second sample pair to obtain the trained first summary model and the trained second summary model in the second language type. There are many ways to perform language transfer training on the first summary model and the second summary model trained in the first language type according to the second sample pair. For example, the second sample pair may include a search information sample in the second language type, and the search information sample matches a content sample and target summary information in the second language type. For this, please continue to refer to Figure 5c In the second stage training of domain transfer, the first summary model trained in the first language type can be used to extract features of sentence texts in the content sample of the second sample pair to obtain text features corresponding to the sentence texts in the second language type, and sample key texts of the second language type are screened out from the sentence texts based on the text features of the second language type. The second summary model trained in the first language type is used to generate summaries of the sample key texts of the second language type to obtain sample summary information of the second language type that matches the search information sample, and loss information of the second language type corresponding to the first summary model trained in the first language type and the preset second summary model is determined according to the sample summary information of the second language type, the search information sample and the target summary information, and the first summary model and the second summary model trained in the first language type are converged based on the loss information in the second language type to obtain the trained first summary model and the trained second summary model in the second language type.

[0104] Since most of the existing datasets are English datasets, in order to obtain the trained first summary model and second summary model that match the currently required language type (such as Chinese type), a two-stage model training method can be used to train the first summary model and the second summary model. For details, please continue to refer to Figure 5cIn the first stage of training, a large number of sample pairs of the first language type (English type) can be used to train the preset first summary model and the second summary model, so as to obtain a trained summary model with good summary generation capability for the search content of the first language type. In the second stage of training, sample pairs of the second language type with a small amount of data can be used to train the trained first summary model and the second summary model of the first language type, so as to obtain a trained summary model with good summary generation capability for the search content of the second language type. In this way, when the number of sample pairs of the second language type is small or missing, the first summary model and the second summary model can be trained in two stages by using sample pairs of the first language type and sample pairs of the second language type obtained by translating the sample pairs of the first language type, so as to obtain the first summary model and the second summary model with good summary generation capability suitable for the second language type, thereby improving the model training efficiency and thus improving the summary generation efficiency.

[0105] In step 205, dialog reply information corresponding to the search information is generated based on the summary information, and the identification information and the dialog reply information are sent to the terminal so as to be displayed on the dialog search result page of the terminal.

[0106] There are many ways to generate dialogue reply information corresponding to the search information based on the summary information. For example, please continue to refer to Figure 5a And 5b, a trained dialogue generation model can be used to generate dialogue response information to answer the search information based on the summary information, and the dialogue generation model can use a generative pre-trained model such as GPT as a basic model. For example, assuming that the summary information is "XX Coffee Shop 1 is a warm corner in a corner of the city, one bean and three drinks, and the beans are fragrant; XX Coffee Shop 2 is a quirky special coffee shop, which is not ordinary, and the beans have a unique flavor", the trained dialogue generation model can be used to generate dialogue response information to answer the search information based on the summary information. For example, the dialogue response content can be obtained as "There are many delicious coffee shops in Shanghai. For example, the nearest delicious coffee shop to you is XX Coffee Shop 1. This shop is a warm corner in a corner of the city, one bean and three drinks, and the beans are fragrant. At the same time, there is XX Coffee Shop 2. This shop is a quirky special coffee shop, which is not ordinary, and the beans have a unique flavor. I recommend you to try them all."

[0107] Optional, please continue to refer to Figure 5aIf no search content matching the search information is found based on the search information, a dialogue generation model can be used to generate reply information matching the search information, and the reply information can be sent to the terminal so that the reply information corresponding to the search information can be displayed on the dialogue search result page of the terminal. In this way, the situation where the user enters the search information but fails to obtain the search results can be avoided, the content search efficiency can be improved, and the content search experience can be improved.

[0108] Optionally, after receiving the search information sent by the terminal, a trained keyword rewriting model can be used to predict the search keywords corresponding to the search information and the search response type corresponding to the search keywords, so as to directly determine whether to search through a search engine or directly use a dialogue generation model to generate reply information according to the search keywords and search response type corresponding to the search information, which can avoid the situation where the user inputs the search information but fails to search for the matching search content, and the unnecessary resource and time consumption caused when the search content cannot be searched, thereby improving the content search efficiency and further improving the content search experience. Specifically, a trained keyword rewriting model can be used to perform keyword processing on the search information to obtain the search keywords corresponding to the search information and the search response type corresponding to the search keywords. When the search response type is a search engine response type, the search content matching the search information can be searched based on the search information. Based on the search keywords, the search content is abstracted and abstract information corresponding to the search content is generated. According to the abstract information, the dialogue reply information corresponding to the search information is generated, and the search content and the dialogue reply information are sent to the terminal as the search results matching the search information, so as to display the search content and the dialogue reply information corresponding to the search information on the dialogue search results page of the terminal. When the search response type is a dialogue model response type, reply information matching the search information can be generated as search results based on the search keywords through a dialogue generation model, and the search results are sent to a sender corresponding to the search information.

[0109] In one embodiment, there may be multiple ways to train the keyword rewriting model. For example, a training sample corresponding to a preset keyword rewriting model may be obtained, the training sample including sample search information, expected search keywords corresponding to the sample search information, and expected search response types; the preset keyword rewriting model is used to extract keywords and predict search response types for the sample search information to obtain predicted search keywords and predicted search response types corresponding to the sample search information; keyword rewriting loss information corresponding to the preset keyword rewriting model is calculated based on the expected search keywords and predicted search keywords, as well as the expected search response types and predicted search response types; the preset keyword rewriting model is converged based on the keyword rewriting loss information to obtain a trained keyword rewriting model.

[0110] Among them, the preset keyword rewriting model can be an untrained model for keyword rewriting. Optionally, the preset keyword rewriting model can use a text processing model such as a generative pre-trained Transformer model (GPT) as a basic model structure. The training sample can be a sample for training the preset keyword rewriting model, the sample search information can be the search information used as a sample, the expected search keyword and the expected search response type can be the training target of the preset keyword rewriting model, the expected search keyword can be the search keyword that the preset keyword rewriting model is expected to rewrite in the sample search information, the expected search response type can be the search response type corresponding to the sample search information predicted by the preset keyword rewriting model, the predicted search keyword can be the search keyword obtained by the preset keyword rewriting model performing keyword processing on the sample search information, and the predicted search response type can be the search response type obtained by the preset keyword rewriting model predicting the sample search information. The keyword rewriting loss information can be used to measure the gap between expected search keywords and predicted search keywords, as well as the gap between expected search response types and predicted search response types, and can be used to evaluate the gap between the keyword rewriting ability of a preset keyword rewriting model and the expected keyword rewriting ability.

[0111] Among them, there can be multiple ways to obtain training samples corresponding to the preset keyword rewriting model. For example, you can obtain a training sample data set corresponding to the preset keyword rewriting model, divide the training sample data set into a simple training sample set and a difficult training sample set; obtain a first weight parameter corresponding to the simple training sample set in each training round of the preset keyword rewriting model, and a second weight parameter corresponding to the difficult training sample set in each training round of the preset keyword rewriting model; according to the first weight parameter and the second weight parameter, filter out the training samples of the preset keyword rewriting model in each training round in the simple training sample set and the difficult training sample set.

[0112] The training sample data set may be a sample data set used to train the preset keyword rewriting model, the simple training sample set may be the whole of simple samples in the training sample data set, and the difficult training sample set may be the whole of difficult samples in the training sample data set. Optionally, the simple training sample set may be divided into simple samples of at least one degree of simplicity, and the difficult training sample set may be divided into difficult samples of at least one degree of difficulty. The training round (epoch) may refer to a process of inputting a training sample data set completely into the preset keyword rewriting model once, and the model parameters of the preset keyword rewriting model are iterated once during this epoch. The first weight parameter may be a weight parameter corresponding to the simple training sample set in each training round of the preset keyword rewriting model, and the first weight parameter is used to determine the number of simple samples in the training samples used in one training round. The second weight parameter may be a weight parameter corresponding to the difficult training sample set in each training round of the preset keyword rewriting model, and the second weight parameter is used to determine the number of difficult samples in the training samples used in one training round.

[0113] Optionally, the first weight parameter may decrease with the number of training iterations of the preset keyword rewriting model, and the second weight parameter may increase with the number of training iterations of the preset keyword rewriting model. For example, assuming that during the training of the preset keyword rewriting model, the number of training rounds epoch is set to 10 times, the first weight parameter may be set to 90% and the second weight parameter may be set to 10% in the first epoch. Then, 90% of the training samples used in the first training round are simple samples and 10% of the training samples are difficult samples. In the second epoch, the first weight parameter may be 80% and the second weight parameter may be 20%. Then, 80% of the training samples used in the second training round are simple samples and 20% of the training samples are difficult samples. In the third epoch, the first weight parameter may be 80% and the second weight parameter may be 20%. Then, 80% of the training samples used in the second training round are simple samples and 20% of the training samples are difficult samples. In poch, the first weight parameter can be 70% and the second weight parameter can be 30%. In the third training round, 70% of the training samples are simple samples and 30% of the training samples are difficult samples. In the fourth epoch, the first weight parameter can be 60% and the second weight parameter can be 40%. In the fourth training round, 60% of the training samples are simple samples and 40% of the training samples are difficult samples. In the fifth epoch, the first weight parameter can be 50% and the second weight parameter can be 50%. In the fifth training round, 60% of the training samples are simple samples and 40% of the training samples are difficult samples. In this case, 50% of the training samples are simple samples and 50% of the training samples are difficult samples. In the sixth epoch, the first weight parameter can be 40% and the second weight parameter can be 40%. Then, 40% of the training samples used in the sixth training round are simple samples and 60% of the training samples are difficult samples. In the seventh epoch, the first weight parameter can be 30% and the second weight parameter can be 70%. Then, 30% of the training samples used in the seventh training round are simple samples and 70% of the training samples are difficult samples. In the eighth epoch, the first weight parameter can be 40% and the second weight parameter can be 40%. The first weight parameter can be 20%, and the second weight parameter can be 80%. Then, 20% of the training samples used in the eighth training round are simple samples, and 80% of the training samples are difficult samples. In the ninth epoch, the first weight parameter can be 10%, and the second weight parameter can be 90%. Then, 10% of the training samples used in the ninth training round are simple samples, and 90% of the training samples are difficult samples. By the tenth epoch, the first weight parameter can be 0, and the second weight parameter can be 100%, that is, all the training samples used in the tenth training round are difficult samples, and so on.In this way, as the number of training iterations of the preset keyword rewriting model increases, the first weight parameter is decreased and the second weight parameter is increased, so that in the training rounds of the preset keyword rewriting model, the proportion of simple samples is gradually reduced and the proportion of difficult samples is gradually increased. In this way, the preset keyword rewriting model can be trained from simple to difficult, which makes it easy for the preset keyword rewriting model to find better local optimal parameters, and at the same time can speed up the training speed and improve the model training efficiency.

[0114] Optional, please continue to refer to Figure 5a In the content search method provided in the embodiment of the present application, a post-processing stage is also provided: Since the content search method provided in the embodiment of the present application is a user-oriented system, it is necessary to ensure the quality and legality of the output content. To this end, a trained security review model and a content quality model can be used to screen the output content. In addition, a follow-up stage can also be provided to bring daily active user (Daily Active User, referred to as DAU) benefits. To this end, after generating the reply information, a trained follow-up model can be used to correct, expand and refine the search information input by the user, so that new search information can be provided to the user, so that the user can be guided to determine more appropriate and required search information, thereby improving the user's retention rate, search accuracy and search experience.

[0115] As can be seen from the above, the embodiment of the present application receives the search information sent by the terminal; searches for the search content matching the search information based on the search information; generates identification information corresponding to the search content based on the search content; extracts the summary of the search content to generate the summary information corresponding to the search content; generates the dialogue reply information corresponding to the search information according to the summary information, and sends the identification information and the dialogue reply information to the terminal to display the identification information and the dialogue reply information in the dialogue search result page of the terminal. In this way, by extracting the summary information and identification information corresponding to the search content from the search content searched based on the search information, and generating the dialogue reply corresponding to the search information according to the summary information, the identification information and the dialogue reply information are sent to the terminal to display the identification information and the dialogue reply information corresponding to the search information in the dialogue search result page of the terminal, the search content matching the input search information can be displayed in the corresponding terminal in an intuitive dialogue manner, so that the user can intuitively and conveniently obtain the search results matching the input search information, thereby improving the content search efficiency.

[0116] In order to better implement the above method, an embodiment of the present invention further provides a content search device, which can be integrated in a computer device, and the computer device can be a terminal.

[0117] For example, Figure 6As shown, it is a schematic diagram of the structure of the content search device provided in an embodiment of the present application. The content search device may include a first display unit 301, an information acquisition unit 302, and a second display unit 303, as follows:

[0118] A first display unit 301 is used to display a conversational search page, which provides a conversational search function;

[0119] An information acquisition unit 302, configured to acquire search information in response to a search information input operation on a conversational search page;

[0120] The second display unit 303 is used to display a conversational search results page, which includes reply information corresponding to the search information, the reply information includes identification information of the search content searched based on the search information, and conversational reply information for the search information, and the conversational reply information is generated based on summary information extracted from the search content.

[0121] In one embodiment, the conversational search result page also includes user conversation text, and the user conversation text is obtained based on the search information.

[0122] In one embodiment, the content search device further includes:

[0123] The detail viewing unit is used to display a content detail page of the target search content corresponding to the target identification information in response to a detail viewing operation on the target identification information in the identification information, wherein the content detail page includes the detailed content of the target search content.

[0124] In specific implementation, the above units can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities. The specific implementation of the above units can refer to the previous method embodiments, which will not be repeated here.

[0125] As can be seen from the above, the embodiment of the present application displays a conversational search page through the first display unit 301, and the conversational search page provides a conversational search function; the information acquisition unit 302 obtains search information in response to the search information input operation for the conversational search page; the second display unit 303 displays the conversational search result page, and the conversational search result page includes reply information corresponding to the search information, and the reply information includes identification information of the search content searched based on the search information, and conversation reply information for the search information, and the conversation reply information is generated based on the summary information extracted from the search content. In this way, by inputting the search information for the conversational search page, the conversation reply information is determined in the form of a conversation according to the identification information of the search content corresponding to the search information and the reply information generated based on the summary of the search content, and the conversation reply information is displayed in the conversational search result page, so that the search content matching the input search information can be displayed in an intuitive conversational manner, so that the user can intuitively and conveniently obtain the search results matching the input search information, thereby improving the content search efficiency.

[0126] In order to better implement the above method, an embodiment of the present invention further provides a content search device, which can be integrated in a computer device, and the computer device can be a server.

[0127] For example, Figure 7 As shown, it is another structural schematic diagram of the content search device provided in an embodiment of the present application. The content search device may include a receiving unit 401, a searching unit 402, a generating unit 403 and a sending unit 404, as follows:

[0128] The receiving unit 401 is used to receive the search information sent by the terminal;

[0129] A search unit 402, configured to search for search content matching the search information based on the search information;

[0130] An identification generating unit 403 is used to generate identification information corresponding to the search content based on the search content;

[0131] A generating unit 404 is used to extract a summary of the search content and generate summary information corresponding to the search content;

[0132] The sending unit 405 is used to generate dialogue reply information corresponding to the search information according to the summary information, and send the identification information and the dialogue reply information to the terminal so as to display the identification information and the dialogue reply information in the dialogue search result page of the terminal.

[0133] In one embodiment, the generating unit 404 includes:

[0134] A key text extraction subunit is used to extract key text from the search content using the trained first summary model to obtain key text corresponding to the search content;

[0135] The summary information generation subunit is used to generate a summary of the key text using the trained second summary model to obtain summary information corresponding to the search content.

[0136] In one embodiment, the content search device further includes:

[0137] A sample acquisition unit, configured to acquire a first sample pair of a first language type, translate the sample pair of the first language type, and obtain a second sample pair of a second language type, wherein the second language type is the same as the language type corresponding to the search information;

[0138] A first training unit is used to perform model training processing on a preset first summary model and a preset second summary model based on the first sample to obtain a trained first summary model and a second summary model in a first language type;

[0139] The second training unit is used to perform language transfer training on the trained first summary model and the second summary model in the first language type according to the second sample to obtain the trained first summary model and the trained second summary model in the second language type.

[0140] In one embodiment, the first sample pair includes a search information sample, and a content sample and target summary information matched by the search information sample, and the first training unit is used to:

[0141] Using a preset first summary model to extract features from sentence texts in the content sample, and obtaining text features corresponding to the sentence texts;

[0142] Filter out sample key texts from sentence texts based on text features;

[0143] A preset second summary model is used to generate a summary of the sample key text to obtain sample summary information matching the search information sample;

[0144] Determine loss information corresponding to a preset first summary model and a preset second summary model according to the sample summary information, the search information sample, and the target summary information;

[0145] The preset first summary model and the preset second summary model are converged based on the loss information to obtain the trained first summary model and second summary model under the first language type.

[0146] In one embodiment, the content search device further includes:

[0147] A reply generating unit, configured to generate reply information matching the search information by using a dialogue generating model if no search content matching the search information is found based on the search information;

[0148] The reply sending unit is used to send the reply information to the terminal so that the reply information corresponding to the search information is displayed in the conversational search result page of the terminal.

[0149] In specific implementation, the above units can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities. The specific implementation of the above units can refer to the previous method embodiments, which will not be repeated here.

[0150] As can be seen from the above, the embodiment of the present application receives the search information sent by the terminal through the receiving unit 401; the search unit 402 searches for the search content matching the search information based on the search information; the identification generation unit 403 generates identification information corresponding to the search content based on the search content; the generation unit 404 extracts the summary of the search content and generates the summary information corresponding to the search content; the sending unit 405 generates the dialogue reply information corresponding to the search information according to the summary information, and sends the identification information and the dialogue reply information to the terminal, so as to display the identification information and the dialogue reply information in the dialogue search result page of the terminal. In this way, by extracting the summary information and identification information corresponding to the search content from the search content searched based on the search information, and generating the dialogue reply corresponding to the search information according to the summary information, the identification information and the dialogue reply information are sent to the terminal, so as to display the identification information and the dialogue reply information of the search content corresponding to the search information in the dialogue search result page of the terminal, the search content matching the input search information can be displayed in the corresponding terminal in an intuitive dialogue manner, so that the user can intuitively and conveniently obtain the search results matching the input search information, thereby improving the content search efficiency.

[0151] Correspondingly, the embodiment of the present invention further provides a content search system, including a server and a terminal. The content search device can be integrated in the server and the terminal included in the content search system. The content search device is any content device provided in the embodiment of the present application. For details, please refer to the description of the embodiment of the above device. Figure 8 , Figure 8 : is a flow chart of a content search system provided by an embodiment of the present application. The method flow of the content search system may include:

[0152] In step S1, the terminal displays a conversational search page, which provides a conversational search function;

[0153] In step S2, the terminal obtains search information in response to a search information input operation on the conversational search page;

[0154] In step S3, the server receives the search information sent by the terminal;

[0155] In step S4, the server searches for search content matching the search information based on the search information;

[0156] In step S5, the server generates identification information corresponding to the search content based on the search content;

[0157] In step S6, the server extracts a summary of the search content and generates summary information corresponding to the search content;

[0158] In step S7, the server generates dialogue reply information corresponding to the search information according to the summary information, and sends the identification information and the dialogue reply information to the terminal so that the identification information and the dialogue reply information are displayed on the dialogue search result page of the terminal;

[0159] In step S8, the terminal displays a conversational search results page, which includes reply information corresponding to the search information, the reply information including identification information of the search content searched based on the search information, and conversational reply information for the search information, and the conversational reply information is generated based on summary information extracted from the search content.

[0160] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0161] Since the data processing system can include any content search device provided in the embodiments of the present invention, the beneficial effects that can be achieved by any content search device provided in the embodiments of the present invention can be achieved. Please refer to the previous embodiments for details, which will not be repeated here.

[0162] The present application also provides a computer device, such as Fig. 9 As shown, it shows a schematic diagram of the structure of a computer device involved in an embodiment of the present application, and the computer device may be a terminal. Specifically:

[0163] The computer device may include one or more processing core processors 501, one or more computer-readable storage media memories 502, a power supply 503, an input unit 504 and other components. Those skilled in the art will appreciate that Fig. 9 The computer device structure shown in the figure does not constitute a limitation on the computer device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Among them:

[0164] The processor 501 is the control center of the computer device, and uses various interfaces and lines to connect various parts of the entire computer device. By running or executing software programs and / or modules stored in the memory 502, and calling data stored in the memory 502, the processor 501 performs various functions of the computer device and processes data. Optionally, the processor 501 may include one or more processing cores; preferably, the processor 501 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 501.

[0165] The memory 502 can be used to store software programs and modules. The processor 501 executes various functional applications and data processing by running the software programs and modules stored in the memory 502. The memory 502 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 502 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 502 may also include a memory controller to provide the processor 501 with access to the memory 502.

[0166] The computer device also includes a power supply 503 for supplying power to various components. Preferably, the power supply 503 can be logically connected to the processor 501 through a power management system, so as to manage charging, discharging, power consumption and other functions through the power management system. The power supply 503 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.

[0167] The computer device may further include an input unit 504, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0168] Although not shown, the computer device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 501 in the computer device will load the executable files corresponding to the processes of one or more application programs into the memory 502 according to the following instructions, and the processor 501 will run the application programs stored in the memory 502, thereby realizing various functions, as follows:

[0169] A conversational search page is displayed, which provides a conversational search function; in response to a search information input operation on the conversational search page, search information is obtained; a conversational search results page is displayed, which includes reply information corresponding to the search information, the reply information includes identification information of search content searched based on the search information, and conversational reply information for the search information, wherein the conversational reply information is generated based on summary information extracted from the search content.

[0170] The specific implementation of each of the above operations can be found in the previous embodiments, which will not be described in detail here. It should be noted that the computer device provided in the embodiment of this application and the content search method in the above embodiment belong to the same concept, and its specific implementation process is detailed in the above method embodiment, which will not be described in detail here.

[0171] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0172] To this end, an embodiment of the present application provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in any of the content search methods provided in the embodiments of the present application. For example, the instructions can execute the following steps:

[0173] A conversational search page is displayed, which provides a conversational search function; in response to a search information input operation on the conversational search page, search information is obtained; a conversational search results page is displayed, which includes reply information corresponding to the search information, the reply information includes identification information of search content searched based on the search information, and conversational reply information for the search information, wherein the conversational reply information is generated based on summary information extracted from the search content.

[0174] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0175] Since the instructions stored in the computer-readable storage medium can execute the steps in any content search method provided in the embodiments of the present application, the beneficial effects that can be achieved by any content search method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0176] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the various optional implementations provided in the above embodiments.

[0177] The above is a detailed introduction to a content search method, device and computer-readable storage medium provided in an embodiment of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A content search method, characterized in that: Applied to a terminal, the method comprises: Displaying a conversational search page, wherein the conversational search page provides a conversational search function; In response to a search information input operation on the conversational search page, obtaining search information; A conversational search results page is displayed, wherein the conversational search results page includes reply information corresponding to the search information, wherein the reply information includes identification information of search content searched based on the search information, and conversational reply information for the search information, wherein the conversational reply information is generated based on summary information extracted from the search content.

2. The content search method according to claim 1, characterized in that: The conversational search result page also includes a user conversation text, and the user conversation text is obtained based on the search information.

3. The content search method according to claim 1 or 2, characterized in that: After displaying the conversational search result page, the method further includes: In response to a detail viewing operation on the target identification information in the identification information, a content detail page of the target search content corresponding to the target identification information is displayed, and the content detail page includes detailed content of the target search content.

4. A content search method, characterized in that: Applied to a server, the method comprises: receiving search information sent by a terminal; Searching for search content matching the search information based on the search information; generating identification information corresponding to the search content based on the search content; Extracting a summary of the search content to generate summary information corresponding to the search content; The dialog reply information corresponding to the search information is generated according to the summary information, and the identification information and the dialog reply information are sent to the terminal so as to be displayed on the dialog search result page of the terminal.

5. The content search method according to claim 4, characterized in that: The extracting summary of the search content to generate summary information corresponding to the search content includes: Using the trained first summary model to extract key text from the search content to obtain key text corresponding to the search content; The trained second summary model is used to generate a summary of the key text to obtain summary information corresponding to the search content.

6. The content search method according to claim 5, characterized in that: Before extracting key text from the search content using the trained first summary model, the method further includes: Acquire a first sample pair of a first language type, translate the sample pair of the first language type to obtain a second sample pair of a second language type, where the second language type is the same as the language type corresponding to the search information; Performing model training processing on a preset first summary model and a preset second summary model based on the first sample to obtain a trained first summary model and a second summary model in a first language type; Language transfer training is performed on the trained first summary model and the second summary model in the first language type according to the second sample to obtain the trained first summary model and the trained second summary model in the second language type.

7. The content search method according to claim 6, characterized in that: The first sample pair includes a search information sample, and a content sample and target summary information matched by the search information sample. The model training process is performed on a preset first summary model and a preset second summary model based on the first sample pair to obtain a trained first summary model and a second summary model in a first language type, including: Using a preset first summary model to extract features from the sentence text in the content sample to obtain text features corresponding to the sentence text; Filtering out sample key texts from the sentence texts based on the text features; Generate a summary of the sample key text using a preset second summary model to obtain sample summary information matching the search information sample; Determine loss information corresponding to the preset first summary model and the preset second summary model according to the sample summary information, the search information sample and the target summary information; The preset first summary model and the preset second summary model are converged based on the loss information to obtain a trained first summary model and a trained second summary model in the first language type.

8. The content search method according to any one of claims 4 to 7, characterized in that: After searching for search content matching the search information based on the search information, the method further includes: If no search content matching the search information is found based on the search information, using a dialogue generation model to generate reply information matching the search information; The reply information is sent to the terminal so that the reply information corresponding to the search information is displayed on the conversational search result page of the terminal.

9. A content search device, characterized in that: include: A first display unit, configured to display a conversational search page, wherein the conversational search page provides a conversational search function; an information acquisition unit, configured to acquire search information in response to a search information input operation on the conversational search page; A second display unit is used to display a conversational search results page, wherein the conversational search results page includes reply information corresponding to the search information, the reply information includes identification information of the search content searched based on the search information, and conversational reply information for the search information, wherein the conversational reply information is generated based on summary information extracted from the search content.

10. A content search system, characterized in that: The content search system includes a terminal and a server, including: The terminal displays a conversational search page, where the conversational search page provides a conversational search function; The terminal obtains search information in response to a search information input operation on the conversational search page; The server receives the search information sent by the terminal; The server searches for search content matching the search information based on the search information; The server generates identification information corresponding to the search content based on the search content; The server extracts a summary of the search content and generates summary information corresponding to the search content; The server generates dialog reply information corresponding to the search information according to the summary information, and sends the identification information and the dialog reply information to the terminal so as to display the identification information and the dialog reply information on a dialog search result page of the terminal; The terminal displays a conversational search results page, which includes reply information corresponding to the search information, the reply information including identification information of the search content searched based on the search information, and conversational reply information for the search information, wherein the conversational reply information is generated based on summary information extracted from the search content.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the steps in the content search method according to any one of claims 1 to 8.

12. A computer device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the content search method according to any one of claims 1 to 8 when executing the computer program.

Images