Searching method and device, storage medium and program product

Abstract

The invention relates to a search method and device, a storage medium and a program product, and relates to the technical field of computers. The searching method comprises the steps of receiving first input of a user; the intention responding to the first input is a search book, the first book is recalled from the one or more books according to the first input and the first feature of the one or more books, and the first feature is generated according to the content of the one or more books; generating first description information of the first book according to the content of the first book and the first input; and displaying the first description information.

Description

Search method, device, storage medium and program product TECHNICAL FIELD

[0001] The present disclosure relates to the field of computer technology, and in particular, to a search method, device, storage medium and program product. BACKGROUND

[0002] In book search technology, a fixed attribute of a book is usually taken as a basis for search, such as the name, classification, author, and the like of the book. A user can input a book name, category, author, and the like information that the user wants to search in a search engine, and the result returned by the search engine is displayed on an interface. The displayed search result includes fixed information of the book, such as the book name, author, and book abstract original text, and the like.

[0003] SUMMARY

[0004] This summary is provided to introduce a selection of concepts, which are further described below in the detailed description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used in limiting the scope of the claimed subject matter.

[0005] According to some embodiments of the present disclosure, a search method is provided, including: receiving a first input of a user; in response to an intention of the first input being to search for a book, recalling a first book from one or more books according to the first input and a first feature of the one or more books, the first feature being generated according to content of the one or more books; generating first description information of the first book according to the content of the first book and the first input; and displaying the first description information.

[0006] According to some embodiments of the present disclosure, a search device is provided, including: a memory; and a processor coupled to the memory, the processor being configured to execute a search method of any embodiment described in the present disclosure based on instructions stored in the memory.

[0007] According to some embodiments of the present disclosure, a computer-readable storage medium is provided, having a computer program stored thereon, the program being executed by a processor to perform a search method of any embodiment described in the present disclosure.

[0008] According to some embodiments of the present disclosure, a computer program is provided, including: instructions that, when executed by a processor, cause the processor to perform a search method of any embodiment described in the present disclosure.

[0009] Other features, aspects, and advantages of the present disclosure will become apparent from the following detailed description of the exemplary embodiments of the present disclosure with reference made to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0010] Preferred embodiments of the present disclosure are explained hereinafter with reference to the accompanying drawings. The drawings used herein are intended to provide a further understanding about the present disclosure, and together with the specific description below, contain part of the present specification and are incorporated herein to form part of the present specification. It should be understood that the drawings described below only relate to some embodiments of the present disclosure, and do not constitute a limitation on the present disclosure. In the drawings:

[0011] FIG. 1 shows a flowchart of a search method according to some embodiments of the present disclosure.

[0012] FIG. 2 shows a flowchart of a method for generating a first feature according to some embodiments of the present disclosure.

[0013] FIG. 3 shows a flowchart of a method for recalling a first book according to some embodiments of the present disclosure.

[0014] FIG. 4 shows a flowchart of a method for generating a first description information according to some embodiments of the present disclosure.

[0015] FIG. 5 shows a flowchart of a method for searching a book content according to some embodiments of the present disclosure.

[0016] FIG. 6 shows a schematic diagram of a search interface according to some embodiments of the present disclosure.

[0017] FIG. 7 shows a schematic diagram of a dialogue interface according to some embodiments of the present disclosure.

[0018] FIG. 8 shows a flowchart of a search method according to some other embodiments of the present disclosure.

[0019] FIG. 9 shows a schematic diagram of a technical architecture according to some embodiments of the present disclosure.

[0020] FIG. 10 shows a schematic diagram of a structure of a search device according to some embodiments of the present disclosure.

[0021] FIG. 11 shows a schematic diagram of a structure of an electronic device according to some embodiments of the present disclosure.

[0022] FIG. 12 shows a schematic diagram of a structure of a computer system according to some embodiments of the present disclosure.

[0023] It should be understood that, for the purpose of convenience, the sizes of the various parts shown in the drawings are not necessarily drawn according to the actual proportions. The same or similar reference signs are used in the drawings to represent the same or similar parts. Therefore, once a part is defined in one drawing, it can not be further discussed in the subsequent drawings. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present disclosure will be described clearly and completely in the embodiments of the present disclosure in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only some of the embodiments of the present disclosure, but not all the embodiments. The description of the embodiments below is actually only illustrative, but not as any limitation on the present disclosure and its application or use. It should be understood that the present disclosure can be implemented in various forms, and should not be interpreted as being limited to the embodiments set forth herein.

[0025] It should be understood that each of the steps recited in the method embodiments of the present disclosure can be performed in different orders and / or in parallel. In addition, the method embodiments can include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect. Unless otherwise specified, the relative arrangement of the components and steps set forth in the embodiments, numerical expressions, and numerical values should be interpreted as merely illustrative, not limiting the scope of the present disclosure.

[0026] The term "comprise" and variations of the term, such as "comprising," "comprises," and "comprised of" as used in the present disclosure are open-ended, meaning that additional elements / features can be included. The term "consisting of" means "including and limited to." The term "consisting essentially of" means "including at least the elements listed after the term, and any additional elements are optional, but do not materially alter the basic and novel characteristics of the claim.

[0027] Reference throughout this specification to "an embodiment," "some embodiments," or "embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrases "in one embodiment," "in some embodiments," or "in embodiments" in various places in the specification are not necessarily all referring to the same embodiment, although they can. Furthermore, the terms "a" or "an," as used in this specification do not denote a limitation of quantity or an intent that more than one of the referenced item is present.

[0028] It should be noted that the terms "first", "second", and the like in the present disclosure are used only to distinguish different devices, modules or units, and do not imply the order or the mutual dependency of the functions performed by these devices, modules or units. Unless otherwise specified, the terms "first", "second", and the like are not intended to imply a given order or any other way of given order.

[0029] It should be noted that the modification of "one", "multiple" mentioned in the present disclosure is illustrative but not restrictive, and those skilled in the art should understand that unless otherwise explicitly indicated in the context, it should be understood as "one or more".

[0030] The names of the messages or information exchanged between the plurality of devices in the embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of the messages or information.

[0031] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings, but the present disclosure is not limited to these specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes can not be described in some embodiments. In addition, in one or more embodiments, specific features, structures or characteristics can be combined by any suitable means from the present disclosure that is clear to those skilled in the art.

[0032] As the user's search needs become more and more rich, it is difficult to provide accurate search results to the user by searching only by title, author, classification and other attributes. For example, the user wants to search for content with a specific plot, but the plot is not reflected in the attributes of the book, so the search result may not be accurate.

[0033] To solve the above problem, the embodiments of the present disclosure generate features of books by using the content of the books, so as to search by using these features and improve the accuracy of the search. Thus, for the case that the user wants to search for a plot or specific details, the user's needs can be met.

[0034] FIG. 1 shows a flowchart of a search method according to some embodiments of the present disclosure. As shown in FIG. 1, the search method of this embodiment includes steps S102 to S108.

[0035] In step S102, a first input of a user is received.

[0036] The user can input in various ways such as voice, text, etc. If the user inputs by voice, it can be converted into text. The user can input through the interface in the application with search function, such as search interface or other types of interface.

[0037] If the user inputs through the search interface, it can be confirmed that the input has a search intention. However, in some scenarios, the user's input can be for searching or for other functions. For example, in the conversation interface between the user and the intelligent agent, the user can send a message to the intelligent agent. The message can be a message in which the user chats with the intelligent agent, or a message that includes content that needs to be answered by the intelligent agent. Since some intelligent agents have strong natural language processing capabilities and information search capabilities, the user can request the intelligent agent to complete a search task, such as a book search task, by sending a message to the intelligent agent.

[0038] The intention of the first input can be determined according to an intention recognition model or a classification model, or can be recognized by keywords, length, etc. The first input can include description information of any type of content of a book.

[0039] In step S104, in response to the intention of the first input being to search for a book, a first book is recalled from one or more books according to the first input and first features of the one or more books, the first features being generated according to the content of the one or more books. One recall process can recall one or more books, and the books fed back to the user can also include one or more books, and the first book can be one of the one or more books.

[0040] The content of the book includes at least one of the content in the chapter, the summary of the chapter, the content of the key plot, the description content of the character, etc. These contents can come from the main text of the book. Thus, the first features can be associated with the content of the book. Since the content information of the main text of the book and the like is large, the content needs to be screened, refined, or other information is determined using the content, and then the first features are generated according to the determined information. In this way, the data amount can be reduced and the storage efficiency can be improved while representing the main text of the book.

[0041] In recalling the first book, a recall model or a recall algorithm can be used. For example, the first input can also be converted into input features, and the similarity between the input features and the first features of each book is calculated, and one or more books including the first book are recalled according to the similarity.

[0042] The recall model can be trained in advance. For example, a double-tower embedding model can be trained, which can map the features of the user's input and the features of the target book that the user wants to search to vectors that are close to each other. Thus, using the model to recall the book can more accurately match the search result based on the user's input.

[0043] In step S106, first description information of the first book is generated according to the content of the first book and the first input.

[0044] The first description information is, for example, content from the first book and matching the first input. Matching the first input can refer to including keywords in the first input, being semantically similar to the first input, and the like.

[0045] In some embodiments, the first description information can be generated using a text generation model. For example, the content of the first book and the first input, or information determined according to the content of the first book and the first input, are input into a generative model. Then, the first description information output by the generative model is obtained. Thus, the first description information can match the content of the searched book and the input of the user. The text generation model is, for example, a foundation model or a large language model (LLM).

[0046] When generating the first description information using the generative model, a processing instruction can be sent to the generative model. The processing instruction can be a natural language, such as "generate text close to the first input using the language in the body of the first book".

[0047] In step S108, the first description information is displayed.

[0048] However, as known from the foregoing steps, the technical solution of the present disclosure uses the content of the book to recall the search results. If fixed content is still displayed in the search results, the user can have difficulty capturing the relevance between the search results and the user input through the content displayed by the search results. By displaying the first description information, the first input and the content of the book can be associated, which helps the user to determine whether the search results are available.

[0049] For example, the first input of user A is "a book with a martial arts plot", and the first input of user B is "a book with a dancing plot". Book M includes both plots, so book M can be included in the above two search results, but the information displayed for the users can be different. For example, in the search results displayed for user A, the relevant description of the martial arts plot in book M can be included; in the search results displayed for user B, the relevant description of the dancing plot in book M can be included.

[0050] Through the embodiments of the present disclosure, on the one hand, search results matching the first input of the user can be searched according to the content of the book, and on the other hand, the relevance between the first input and the search results can be represented by the first description information when the search results are displayed. Thus, the search accuracy of the user and the efficiency of information acquisition can be improved.

[0051] Embodiments of the present disclosure can use various ways to determine the first feature of a book. For example, the search terms that can be used for each book can be determined in advance based on the content of each book, and the books can be represented by these terms. In some embodiments, the first feature of one or more books is determined according to the simulated search terms of each book, which are search terms that imitate the search terms used by a user to recall the book. For example, a simulated search term can be generated for the entire book, or the book can be divided into multiple parts (e.g., by chapters or other ways), and then a simulated search term is generated for each part. Embodiments of the generation method of the first feature are described below with reference to FIG. 2.

[0052] FIG. 2 shows a flowchart of a method for generating a first feature according to some embodiments of the present disclosure. As shown in FIG. 2, the generation method of this embodiment includes steps S202 to S204.

[0053] In step S202, the content of one or more books is processed using a text processing model to generate one or more simulated search terms for each book in the one or more books. It should be noted that the "search term" in the present application can be a word, phrase, or sentence, representing the text used in the search.

[0054] The text processing model is, for example, a generative model. For example, for each book, or each part of each book, the content of the book and a processing instruction can be input into the text processing model, where the processing instruction is used to indicate that the search terms that can be generated according to the content of the book are to be generated. For example, the processing instruction is "generate sentences that can be used by a user to search for the content according to the content of the book". In addition, the processing instruction can also specify or constrain the number of generated search terms.

[0055] In step S204, the features of the simulated search terms of each book are determined as the first feature of the book.

[0056] The features of the simulated search terms can be determined according to the features of the text units (e.g., words, characters, symbols) contained in the simulated search terms, and the features of the text can be determined according to a feature dictionary of the text. For example, the features of the simulated search terms can be concatenated, or averaged, etc. Since the simulated search terms are determined according to the content of the book, the first feature determined according to the features of the simulated search terms is also associated with the content of the book.

[0057] In determining the features of the simulated search terms, a feature extraction network in a mapping model can be used to determine the features of the book according to the features of the simulated search terms. The mapping model is used to map the simulated search terms and the content of the book, so as to map the simulated search terms and the content of the corresponding book into similar vectors. The mapping model can be a dual tower mapping model.

[0058] In some embodiments, the mapping model is used for mapping each item of content of one or more books and a simulated search term corresponding to each item of content, including a first feature extraction network for extracting features of the simulated search term, and a second feature extraction network for extracting features of the content. The simulated search term of each book is processed by the first feature extraction network in the mapping model to determine the first features of the book. Thus, the features of the search term can correspond to the features of the content of the book, so that the features of the search term can accurately represent the content of the book, i.e., the features of the search term can represent the book.

[0059] The generated first features can be used as document vectors (doc embeddings) of the books. Each book can correspond to one or more first features, and further, each part of the book can also correspond to one or more first features. The generated features and the correspondence between the features and the books can be stored in a database and read from the database when searching.

[0060] In some embodiments, the first features of the book corresponding to multiple categories can be generated according to different categories of content in the book. For example, some first features are generated according to the main text of the book, and some first features are generated according to the description of the characters, etc. When extracting the features, the feature extraction network corresponding to the category can also be used for processing.

[0061] The search term determined by the above embodiments can represent the content of the book on the one hand, and also has the attribute of searching on the other hand. Therefore, by using the first features, the book matching the first input can be more accurately searched.

[0062] When recalling the book, the book can be further filtered according to the relevance of the recalled book to the first features. FIG. 3 shows a flowchart of a method for recalling a first book according to some embodiments of the present disclosure. As shown in FIG. 3, the method for recalling includes steps S302 to S304.

[0063] In step S302, a set of books is recalled from one or more books according to the first input and the first features of the one or more books. The set of books includes one or more books, and in the case of including multiple books, the subsequent step S304 can be used for further filtering.

[0064] In step S304, a first book is determined from the set of books according to the relevance of the book in the set of books to the first input.

[0065] In determining the relevance, the attribute information of the books can be reused, or the content of the books is matched with the first input to determine the relevance of the books to the first input. For example, the information of each book in the book set is converted into a vector, and the similarity of the vector to the first input is calculated.

[0066] In some embodiments, a plurality of recall models or recall strategies can be used to recall books to form the book set. For example, different types of content of the books can be used for recall, i.e., some are based on the content in the chapters of the books, some are based on the description of the roles, etc., so that the books in the book set can be determined based on one or more strategies.

[0067] By using the relevance of the books in the book set to the first book to further screen, the first book can be more accurately determined, and the accuracy of the user book search is improved.

[0068] After the first book is determined, the first description information displayed to the user when the first book is fed back can be further determined. In order to make the first description information respond to the content of the first input, the content corresponding to the first input can be extracted from the content of the book to generate the first description information. The embodiments of the generation method of the first description information of the present disclosure are described below with reference to FIG. 4.

[0069] FIG. 4 shows a flowchart of a generation method of the first description information according to some embodiments of the present disclosure. As shown in FIG. 4, the generation method of this embodiment includes steps S402 to S404.

[0070] In step S402, according to the first input, the content of the first book that matches the first input is determined.

[0071] The content that matches the first input can be content that has a keyword in the first input, or content that is close in semantics to the first input. For example, the first input of the user is "a book that eats to tears in a restaurant", and for the searched book N, the relevant paragraph "C ate a bowl of home-style noodles in a Chinese restaurant and cried" in the book N is extracted when the information of the search result is displayed. Thus, the user can quickly understand the matching of the search result to his search intent.

[0072] In step S404, the first description information of the first book is generated according to the content that matches the first input and the first book.

[0073] The content that matches the first input can be directly used as the first description information, or it can be processed to generate the first description information. For example, in the case where the content is long, it can be summarized or summarized to generate more concise language and improve the efficiency of delivering information to the user.

[0074] Embodiments of the present disclosure also support a user searching for content in a book, such as a classic plot, a classic quote, and the like. Embodiments of a book content search method of the present disclosure are described below with reference to FIG. 5.

[0075] FIG. 5 shows a flowchart of a book content search method according to some embodiments of the present disclosure. As shown in FIG. 5, the book content search method of this embodiment includes steps S502-S504.

[0076] In step S502, in response to the intent of the first input being to search for content in a book, target content in one or more books is recalled according to the first input.

[0077] The manner of recalling the target content of the book can refer to the manner of recalling the book. However, there are differences in the recall model used and the features used when searching.

[0078] In some embodiments, the features of the first input are matched with second features of one or more contents of one or more books to recall the target content from the one or more contents of the one or more books, and the second features are determined according to the simulated search terms of each content. For example, the matching result can be determined by calculating the similarity between the features of the first input and the second features of each content. One or more contents with high similarity can be used as the recalled target content. The second features can be generated according to the content of the book, such as a vector corresponding to the content or a vector of other content corresponding to the content.

[0079] For example, one or more simulated search terms can be generated for each of one or more contents of one or more books in advance by using a text processing model to process the one or more contents; and the features of the simulated search terms of each content are used as the features of the content. That is, the simulated search terms can also be used when characterizing the features of the content of the book. The manner of generating simulated search terms for the content of the book can refer to the manner of generating simulated search terms for the book, which is not described here.

[0080] In step S504, second description information of the target content is generated according to the target content and the first input.

[0081] In the case where the user wants to search for the second description information, description information can also be generated for the search result. Thus, the explainability of the search result can be improved, and the accuracy of user search and the efficiency of information transmission can be improved.

[0082] The search method of the present disclosure can also be applied to a search interface and a dialogue interface. That is, the first input of the user can be received through the search interface or the dialogue interface. The two scenarios are further described below by way of example.

[0083] FIG. 6 shows a schematic diagram of a search interface according to some embodiments of the present disclosure. As shown in FIG. 6, in the search interface 6, the user inputs “a book that makes you cry after eating in a restaurant” in the search box 61, and the search interface returns multiple search results 62 to 64. In this example, the search result 62 is obtained using the search method of embodiments of the present disclosure, and the search results 63 and 64 are obtained using a traditional search method. It can be seen that, compared with the search results 63 and 64, the search result 62 adds a first description information 621 to reflect the relevance between the book in the search result and the input of the user.

[0084] In some embodiments, in response to a triggering operation on the search result 62, a dialogue interface between the user and the intelligent agent can be displayed, in which further information related to the search result 62 can be displayed.

[0085] FIG. 7 shows a schematic diagram of a dialogue interface according to some embodiments of the present disclosure. As shown in FIG. 7, in the dialogue interface 7, the message “a book that makes you cry after eating in a restaurant” 71 input and sent by the user is displayed, and the message 72 corresponding to the search result obtained according to embodiments of the present disclosure is also displayed. Of course, the dialogue interface 7 can also be displayed in response to the user triggering the search result 62 in the search interface 6, in which case the messages 71 and 72 can also be automatically generated after jumping from the interface 6 to the interface 7.

[0086] In the dialogue scenario, in response to the first input not being for searching, dialogue content is generated according to the first input; and the dialogue content is displayed. That is, after the user inputs information, it can be determined whether the intention of the first input is to search for a book, search for content in the book, or is unrelated to searching. In this way, in the dialogue scenario, the user’s input is not considered as a search request at all times, so that the dialogue function of the intelligent agent can be taken into account while searching for a book or content in the book.

[0087] The intelligent agent can generate and display the dialogue content according to the generative model. For example, the intelligent agent can process the first input using the generative model to obtain a response content to the first input.

[0088] The user can search again in the case of being not satisfied with the first search. Embodiments of the present disclosure consider the relevance between multiple consecutive searches to improve the accuracy of the search. Embodiments of the search method of the present disclosure are described below with reference to FIG. 8.

[0089] FIG. 8 shows a schematic flow diagram of a search method according to some embodiments of the present disclosure. As shown in FIG. 8, the search method of this embodiment includes steps S802 to S808.

[0090] In step S802, a second input of a user is received.

[0091] The second input is an input from the user after the first input. The interval time between the first input and the second input is not less than a specified time length, i.e., the occurrence time of the two is close, thus having relevance. For example, it can be that the user is not satisfied with the search result of the first input, and the additional input condition is added.

[0092] In step S804, in response to the intention of the first input and the second input both being to search for books, a second book is recalled according to the second input, and the second book is different from the first book.

[0093] The recalling process of the second book can refer to the recalling process of the first book. However, different from recalling the first book, when recalling the second book, a deduplication operation needs to be performed to avoid repeatedly providing the search result to the user.

[0094] In some embodiments, the second book can be recalled according to the first input and the second input together. For example, the first input and the second input are integrated into a third input, and the method of recalling the book with the first input in the foregoing embodiments is referred to, and the book is recalled using the third input, so that the recalled book can meet the search intention of the user twice.

[0095] In step S806, third description information of the second book is generated according to the content of the second book, the first input, and the second input.

[0096] The method of generating the third description information can refer to the method of generating the first description information in the foregoing embodiments. Only in the process of generating the third description information, in addition to considering the second input used in this search, the content of the first input is also considered, so that the third description information can match the first input and the second input at the same time. In this way, the search result fed back to the user can better match the user's search demand again.

[0097] In step S808, the third description information is displayed.

[0098] The above embodiments can consider the input and search result of the previous search when the user performs secondary search. Therefore, the user can not have to re-input the input information used in the previous search, thereby improving the search efficiency and search experience of the user.

[0099] FIG. 9 shows a technical architecture diagram according to some embodiments of the present disclosure. As shown in FIG. 9, the technical architecture of the present disclosure is divided into three levels of front-end module 91, text processing module 92, and recall module 93. The front-end module 91 is used to interact with the user, such as receiving the input 911 of the user, displaying the output result 912. The text processing module 92 is used to use large language models and the like to perform intent recognition 921, generation of recall parameters 922, relevance judgment of recall results 923, generation of description information 924 (such as generating a description of search results, generating an answer of an agent), and the like. The intent recognition 921 refers to determining the type of user input, such as whether it has the intention to search for books, whether it has the intention to search for the content of books, whether it is a non-search intention, and the like. In the case where the user's input has a search intention, the generation of recall parameters 922 is performed to generate recall parameters for the recall model to process, which includes information required for recall, such as the user's input, and the like. The recall module 93 can call one or more models to perform recall 931 as needed, and perform data processing 932 such as field splicing and data reduction on the recall results as needed, and then return the processing results to the text processing module 92. The relevance judgment 923 is performed on the results returned by the recall module 93 as needed to further filter and sort the recall results. Then, the generation of description information 924 is performed, and the results are returned to the front-end module 91 to display the output results 912.

[0100] The method and technical architecture of the embodiments of the present disclosure are described above. The related devices for implementing the embodiments of the present disclosure are further introduced below.

[0101] FIG. 10 shows a structural diagram of a search device according to some embodiments of the present disclosure. As shown in FIG. 10, the search device 10 of this embodiment includes a receiving module 101 configured to receive a first input of a user; a recall module 102 configured to, in response to the intention of the first input being to search for books, recall a first book from one or more books according to the first input and a first feature of the one or more books, the first feature being generated according to the content of the one or more books; a generation module 103 configured to generate first description information of the first book according to the content of the first book and the first input; and a display module 104 configured to display the first description information.

[0102] In some embodiments, the first feature of the one or more books is determined according to a simulated search term of each book, and the simulated search term is a search term used to recall the content of the book.

[0103] In some embodiments, the search apparatus 10 further comprises a first feature determination module 105 configured to process the content of one or more books by using a text processing model to generate one or more simulated search terms for each of the one or more books; and determine the features of the simulated search terms of each of the one or more books as the first features of the one or more books.

[0104] In some embodiments, the feature determination module 105 is further configured to process the simulated search terms of each of the one or more books by using a first feature extraction network in the mapping model to determine the first features of the one or more books, wherein the mapping model is used for mapping each of the content of the one or more books and the simulated search terms corresponding to the content, and the mapping model comprises the first feature extraction network used for extracting the features of the simulated search terms and a second feature extraction network used for extracting the features of the content.

[0105] In some embodiments, the recall module 102 is further configured to recall a set of books from the one or more books according to the first input and the first features of the one or more books; and determine the first book from the set of books according to the relevance of the books in the set of books to the first input.

[0106] In some embodiments, the generation module 103 is further configured to determine the content of the first book that matches the first input according to the first input; and generate the first description information of the first book according to the content that matches the first input and the first book.

[0107] In some embodiments, the generation module 103 is further configured to, in response to the intent of the first input being to search for the content in the book, recall target content in the one or more books according to the first input; and generate the second description information of the target content according to the target content and the first input.

[0108] In some embodiments, the recall module 102 is further configured to match the features of the first input with the second features of one or more of the content of the one or more books to recall the target content from the one or more of the content of the one or more books, and the second features are determined according to the simulated search terms of each of the content.

[0109] In some embodiments, the search apparatus 10 further comprises a second feature determination module 106 configured to process one or more of the content of the one or more books by using a text processing model to generate one or more simulated search terms for each of the one or more of the content; and determine the features of the simulated search terms of each of the one or more of the content as the features of the one or more of the content.

[0110] In some embodiments, the display module 104 is further configured to, in response to the intent of the first input not being to search, generate conversation content according to the first input; and display the conversation content.

[0111] In some embodiments, the receiving module 101 is further configured to receive a second input of the user; the recalling module 102 is further configured to, in response to the intention of the first input and the second input both being searching for books, recall a second book according to the second input, the second book being different from the first book; the generating module 103 is further configured to generate third description information of the second book according to the content of the second book, the first input and the second input; and the displaying module 104 is further configured to display the third description information.

[0112] In some embodiments, the content of the book comprises at least one of content in a chapter, an abstract of a chapter, content of a key plot, and description content of a character.

[0113] In some embodiments, the receiving module 101 is further configured to receive the first input of the user through a search interface or a dialogue interface.

[0114] It should be noted that the above-mentioned various units are only logical modules according to the specific functions they implement, and are not intended to limit the specific implementation manner, for example, they can be implemented in software, hardware or a combination of software and hardware. In actual implementation, the above-mentioned various units can be implemented as independent physical entities, or can also be implemented by a single entity (for example, a processor (CPU or DSP, etc.), an integrated circuit, etc.). In addition, the above-mentioned various units are indicated by dashed lines in the drawings, indicating that these units can not actually exist, and the operations / functions they implement can be implemented by the processing circuit itself.

[0115] In addition, although not shown, the device can also include a memory, which can store various information generated by the device, the units included in the device in operation, programs and data for operation, data to be sent by the communication unit, etc. The memory can be a volatile memory and / or a non-volatile memory. For example, the memory can include but is not limited to random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), flash memory. Of course, the memory can also be located outside the device. Alternatively, although not shown, the device can also include a communication unit, which can be used for communication with other devices. In one example, the communication unit can be implemented in a suitable manner known in the art, for example, including communication components such as antenna array and / or radio frequency link, various types of interfaces, communication units, etc. Here will not be described in detail. In addition, the device can also include other components not shown, such as radio frequency link, baseband processing unit, network interface, processor, controller, etc. Here will not be described in detail.

[0116] Some embodiments of the present disclosure also provide an electronic device. FIG. 11 shows a structural schematic diagram of an electronic device according to some embodiments of the present disclosure. For example, in some embodiments, the electronic device 11 can be various types of devices, for example, can include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle terminals (for example, car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. For example, the electronic device 11 can include a display panel for displaying data and / or execution results utilized in the schemes according to the present disclosure. For example, the display panel can be various shapes, for example, a rectangular panel, an oval panel, or a polygonal panel, and the like. In addition, the display panel can not only be a flat panel, but also a curved panel, or even a spherical panel.

[0117] As shown in FIG. 11, the electronic device 11 of this embodiment includes a memory 111 and a processor 112 coupled to the memory 111. It should be noted that the components of the electronic device 11 shown in FIG. 11 are only exemplary and are not limiting, and the electronic device 11 can also have other components according to actual application needs. The processor 112 can control other components in the electronic device 11 to perform desired functions.

[0118] In some embodiments, the memory 111 is configured to store one or more computer readable instructions. When the processor 112 executes the computer readable instructions, the computer readable instructions are executed by the processor 112 to implement the method according to any of the above embodiments. For specific implementation of each step of the method and related explanations, please refer to the above embodiments, and repeated parts will not be described here.

[0119] For example, the processor 112 and the memory 111 can directly or indirectly communicate with each other. For example, the processor 112 and the memory 111 can communicate through a network. The network can include a wireless network, a wired network, and / or any combination of a wireless network and a wired network. The processor 112 and the memory 111 can also communicate with each other through a system bus, and the present disclosure does not limit this.

[0120] For example, the processor 112 can be embodied as various appropriate processors, processing devices, and the like, such as a central processing unit (CPU), a graphics processing unit (GPU), a network processing unit (NP), and the like; also can be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The central processing unit (CPU) can be an X86 or ARM architecture, etc. For example, the memory 111 can include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The memory 111 may, for example, include a system memory, which stores, for example, an operating system, application programs, a boot loader, a database, and other programs, etc. Various application programs and various data, etc. can also be stored in the storage medium.

[0121] In addition, according to some embodiments of the present disclosure, various operations / processes according to the present disclosure, in the case of being implemented by software and / or firmware, can install programs constituting the software from a storage medium or a network to a computer system having a dedicated hardware structure, such as the computer system 120 shown in FIG. 12, which, when various programs are installed, can perform various functions, including functions such as those described above, etc. FIG. 12 shows a structural schematic diagram of a computer system according to some embodiments of the present disclosure.

[0122] In FIG. 12, the central processing unit (CPU) 1201 performs various processes according to programs stored in the read-only memory (ROM) 1202 or programs loaded from the storage portion 1208 to the random access memory (RAM) 1203. In the RAM 1203, data required when the CPU 1201 performs various processes, etc. is also stored as needed. The central processing unit is merely exemplary, and can also be other types of processors, such as various processors described above. The ROM 1202, the RAM 1203, and the storage portion 1208 can be various forms of computer-readable storage media, as described below. It should be noted that although the ROM 1202, the RAM 1203, and the storage device 1208 are shown in FIG. 12, respectively, one or more of them can be combined or located in the same or different memory or storage module.

[0123] The CPU 1201, the ROM 1202, and the RAM 1203 are connected to each other via a bus 1204. An input / output interface 1205 is also connected to the bus 1204.

[0124] The following components are connected to the input / output interface 1205: an input portion 1206 such as a touch panel, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, and the like; an output portion 1207 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), a speaker, a vibrator, and the like; a storage portion 1208 including a hard disk, a magnetic tape, and the like; and a communication portion 1209 including a network interface card such as a LAN card, a modem, and the like. The communication portion 1209 allows communication processing to be performed via a network such as the Internet. It is easily understood that, although the respective devices or modules in the computer system 120 are shown in FIG. 12 as communicating through the bus 1204, they can also communicate through a network or other means, where the network can include a wireless network, a wired network, and / or any combination of a wireless network and a wired network.

[0125] A drive 1210 is also connected to the input / output interface 1205 as necessary. A removable recording medium 1211 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like is attached to the drive 1210 as necessary, so that a computer program read therefrom is installed into the storage portion 1208 as necessary.

[0126] In the case where the above series of processes are implemented by software, the program constituting the software can be installed from a network such as the Internet or a storage medium such as the removable recording medium 1211.

[0127] According to an embodiment of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product including a computer program carried on a computer-readable medium, the computer program containing program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from the network by the communication device 1209, or installed from the storage device 1208, or installed from the ROM 1202. When the computer program is executed by the CPU 1201, the above-described functions defined in the methods of the embodiments of the present disclosure are executed.

[0128] Note that in the context of the present disclosure, a computer-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer-readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer-readable storage medium can be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium can include a computer-readable program code transmitted in baseband or as part of a carrier wave over a transmission medium, in which the computer-readable program code can be embodied. Such a transmitted computer-readable signal medium can take a variety of forms, including but not limited to electro-magnetic, optical, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium that can be used to carry or transport a computer-readable program code for use by or in connection with an instruction execution system, apparatus, or device. The program code contained in the computer-readable medium can be transmitted using any suitable medium, including but not limited to wire, cable, RF (radio frequency), etc., or any suitable combination of the foregoing.

[0129] The computer-readable medium described above can be included in the electronic device described above; or can exist separately from the electronic device and be not assembled in the electronic device.

[0130] In some embodiments, a computer program is also provided, including instructions which, when executed by a processor, cause the processor to perform the method of any one of the above embodiments. For example, the instructions can be embodied as computer program code.

[0131] Computer program code for carrying out operations of the present disclosure can be written in any one or more of a variety of programming languages or combinations of languages including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0132] The flow diagrams and the block diagrams in the drawings are meant as possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flow diagrams and the block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flow diagrams, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0133] The modules, components or units described in the embodiments of the present disclosure can be implemented by software or by hardware. In some cases, the name of the module, component or unit does not constitute a limitation on the module, component or unit itself.

[0134] The functions described above in the detailed description of embodiments of the present disclosure can be implemented in one or more hardware logic components or by computer instructions that are executed in a hardware logic component. For example, and without limitation, illustrative hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Application-specific Integrated Circuits (ASICs), Application-specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0135] The above description merely provides an overview of some embodiments of the present disclosure and the inventive concept thereof. The disclosure should not be limited by the specific illustrated embodiments, which can vary in many ways. For example, the above described embodiments and terminology are used in a non-limiting sense to provide a general description of the principles of the present disclosure. The scope of the disclosure is not limited to the specific embodiments described herein, but only to what the claims shall ultimately claim. It should be appreciated that those skilled in the art can devise other embodiments and modifications that fall within the scope and spirit of the disclosure. For example, features shown in the above described embodiments can be used in combination with each other or in other embodiments, or replaced by other features having the same or similar function. Any such modifications that do not depart from the scope and spirit of the present disclosure are intended to be included.

[0136] In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application can be practiced without these specific details. In other instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

[0137] In addition, while operations are depicted in a particular, chronological sequence, this should not be understood as requiring such order unless otherwise specifically indicated, and include can be advantageous to perform multiple operations loading or in parallel. Likewise, while several specific implementations are discussed herein, these should not be taken as limiting. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented or provided in multiple embodiments separately or in any suitable sub-combination. It will be appreciated that numerous specific details are set forth herein, in order to provide a thorough understanding of the application. However, it is recognized that the application might be practiced without these specific details. In other instances, well-known methods, procedures and components have not been described in detail so as not to unnecessarily obscure aspects of the application.

[0138] While certain embodiments of the disclosure have been described herein, other embodiments will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure. Therefore, the disclosure is not limited to these embodiments, but instead has a scope as defined by the appended claims. Various modifications and changes can be made thereto by those skilled in the art which fall within the scope and spirit of the disclosure as described.

Claims

1. A search method comprising: receiving a first input of a user; in response to an intention of the first input being to search for a book, recalling a first book from one or more books according to the first input and first features of the one or more books, the first features being generated according to content of the one or more books; generating first description information of the first book according to the content of the first book and the first input; displaying the first description information.

2. The search method of claim 1, wherein, The first features of the one or more books are determined according to simulated search terms of each book, the simulated search terms being search terms used to recall the content of the book.

3. The search method of claim 2, further comprising: processing the content of the one or more books using a text processing model to generate one or more simulated search terms for each book of the one or more books; determining the features of the simulated search terms of each book as the first features of the book.

4. The search method of claim 3, wherein, The determining the features of the simulated search terms of each book as the first features of the book comprises: processing the simulated search terms of each book using a first feature extraction network in a mapping model to determine the first features of the book, wherein the mapping model is used for mapping each item of content of the one or more books and a simulated search term corresponding to the item of content, and comprises the first feature extraction network used to extract features of the simulated search term and a second feature extraction network used to extract features of the content.

5. The search method of claim 1, wherein, The recalling the first book from the one or more books according to the first input and the first features of the one or more books comprises: recalling a set of books from the one or more books according to the first input and the first features of the one or more books; determining the first book from the set of books according to relevance of books in the set of books to the first input.

6. The search method of claim 1, wherein, The generating the first description information of the first book according to the content of the first book and the first input comprises: determining content of the first book that matches the first input according to the first input; generating the first description information of the first book according to the content that matches the first input and the first book.

7. The search method of claim 1, further comprising: in response to the intention of the first input being to search for content in a book, recalling target content in one or more books according to the first input; generating second description information of the target content according to the target content and the first input.

8. The search method of claim 7, wherein, The recalling the target content in the one or more books according to the first input comprises: matching features of the first input with second features of one or more items of content of the one or more books to recall the target content from the one or more items of content of the one or more books, the second features being determined according to simulated search terms of each item of content.

9. The search method of claim 8, further comprising: processing one or more contents of the one or more books by using a text processing model to generate one or more simulated search terms for each of the one or more contents; using a feature of the simulated search terms of each of the contents as a feature of the content. 10.The search method of claim 1, further comprising: in response to the first input not being intended for searching, generating a dialogue content according to the first input; displaying the dialogue content. 11.The search method of claim 1, further comprising: receiving a second input of the user; in response to the first input and the second input both being intended for searching books, recalling a second book according to the second input, the second book being different from the first book; generating third description information of the second book according to a content of the second book, the first input, and the second input; displaying the third description information.

12. The search method of any one of claims 1 to 11, wherein, The content of the book comprises at least one of a content in a chapter, a summary of a chapter, a content of a key plot, and a description content of a character.

13. The search method of any one of claims 1 to 11, wherein, The receiving the first input of the user comprises: receiving the first input of the user through a search interface or a dialogue interface. 14.A search apparatus, comprising: a memory; and a processor coupled to the memory, the processor being configured to perform the search method of any one of claims 1 to 13 based on instructions stored in the memory. 15.A computer readable storage medium having stored thereon a computer program, which, when executed by a processor, implements the search method of any one of claims 1 to 13. 16.A computer program product, which, when executed on a computer, causes the computer to implement the search method of any one of claims 1 to 13. 17.A computer program, comprising: instructions which, when executed by a processor, cause the processor to perform the search method of any one of claims 1 to 13.

Images