CN116501960A - Content retrieval method, device, equipment and medium - Google Patents

Abstract

The disclosure provides a content retrieval method, a device, equipment and a medium, which relate to the field of artificial intelligence, in particular to the fields of deep learning, intelligent searching and natural language processing. The implementation scheme is as follows: acquiring first retrieval information input by a user through a search engine; searching to obtain at least one first search result based on the first search information; and obtaining first search contents corresponding to the first search information generated by the first language model through the first language model based on the first search information and at least one first search result, so as to display the first search contents on a search result page.

Description

Content retrieval method, device, equipment and medium

Technical Field

The present disclosure relates to the field of artificial intelligence, and in particular, to the fields of deep learning, intelligent searching, natural language processing, and the like, and more particularly, to a method, an apparatus, an electronic device, a computer readable storage medium, and a computer program product for content retrieval.

Background

Artificial intelligence is the discipline of studying the process of making a computer mimic certain mental processes and intelligent behaviors (e.g., learning, reasoning, thinking, planning, etc.) of a person, both hardware-level and software-level techniques. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, a machine learning/deep learning technology, a big data processing technology, a knowledge graph technology and the like.

Generally, a user expresses his search intention mainly by a term input by the user at the time of searching, and a search engine acquires a corresponding plurality of search results based on the term. The user obtains information matching his search intent by browsing the content in the plurality of search results. With the continued development of artificial intelligence technology, users desire to be able to more quickly obtain opinion or suggestion fed back by a search engine.

The approaches described in this section are not necessarily approaches that have been previously conceived or pursued. Unless otherwise indicated, it should not be assumed that any of the approaches described in this section qualify as prior art merely by virtue of their inclusion in this section. Similarly, the problems mentioned in this section should not be considered as having been recognized in any prior art unless otherwise indicated.

Disclosure of Invention

The present disclosure provides a content retrieval method, apparatus, electronic device, computer-readable storage medium, and computer program product.

According to an aspect of the present disclosure, there is provided a content retrieval method including: acquiring first retrieval information input by a user through a search engine; searching to obtain at least one first search result based on the first search information; and obtaining first search contents corresponding to the first search information generated by the first language model through the first language model based on the first search information and the at least one first search result, so as to display the first search contents on a search result page.

According to another aspect of the present disclosure, there is provided a content retrieval apparatus including: the acquisition unit is configured to acquire first retrieval information input by a user through a search engine; a search unit configured to search for at least one first search result based on the first search information; and a content generation unit configured to obtain, based on the first search information and the at least one first search result, first search content corresponding to the first search information generated by the first language model through a first language model, so as to display the first search content on a search result page.

According to one or more embodiments of the present disclosure, after first search information input by a user is obtained, data search is performed on the first search information, and first search content is quickly generated through a first language model based on search results and the search information, so that opinion or suggestion fed back by a search engine can be obtained without clicking the corresponding search results one by a user, efficiency of information search by the user through the search engine is improved, and user experience is enhanced.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

The accompanying drawings illustrate exemplary embodiments and, together with the description, serve to explain exemplary implementations of the embodiments. The illustrated embodiments are for exemplary purposes only and do not limit the scope of the claims. Throughout the drawings, identical reference numerals designate similar, but not necessarily identical, elements.

FIG. 1 illustrates a schematic diagram of an exemplary system in which various methods described herein may be implemented, in accordance with an embodiment of the present disclosure;

FIG. 2 illustrates a flow chart of a content retrieval method according to an embodiment of the present disclosure;

FIG. 3 shows a search results page schematic in accordance with an embodiment of the present disclosure;

FIG. 4 shows a search results page schematic in accordance with an embodiment of the present disclosure;

FIG. 5 illustrates a first search content schematic according to an embodiment of the present disclosure;

FIG. 6 illustrates a first search content schematic according to an embodiment of the present disclosure;

FIG. 7 illustrates a first search content schematic according to an embodiment of the present disclosure;

FIG. 8 shows a search results page schematic in accordance with an embodiment of the present disclosure;

FIG. 9 shows a schematic diagram of a search results page and detail page according to an embodiment of the present disclosure;

Fig. 10 shows a block diagram of a content retrieval device according to an embodiment of the present disclosure; and

fig. 11 illustrates a block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the present disclosure, the use of the terms "first," "second," and the like to describe various elements is not intended to limit the positional relationship, timing relationship, or importance relationship of the elements, unless otherwise indicated, and such terms are merely used to distinguish one element from another element. In some examples, a first element and a second element may refer to the same instance of the element, and in some cases, they may also refer to different instances based on the description of the context.

The terminology used in the description of the various illustrated examples in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context clearly indicates otherwise, the elements may be one or more if the number of the elements is not specifically limited. Furthermore, the term "and/or" as used in this disclosure encompasses any and all possible combinations of the listed items.

Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

Fig. 1 illustrates a schematic diagram of an exemplary system 100 in which various methods and apparatus described herein may be implemented, in accordance with an embodiment of the present disclosure. Referring to fig. 1, the system 100 includes one or more client devices 101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. Client devices 101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

In embodiments of the present disclosure, the server 120 may run one or more services or software applications that enable methods of content retrieval to be performed.

In some embodiments, server 120 may also provide other services or software applications, which may include non-virtual environments and virtual environments. In some embodiments, these services may be provided as web-based services or cloud services, for example, provided to users of client devices 101, 102, 103, 104, 105, and/or 106 under a software as a service (SaaS) model.

In the configuration shown in fig. 1, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or a combination thereof that are executable by one or more processors. A user operating client devices 101, 102, 103, 104, 105, and/or 106 may in turn utilize one or more client applications to interact with server 120 to utilize the services provided by these components. It should be appreciated that a variety of different system configurations are possible, which may differ from system 100. Accordingly, FIG. 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

The user may use client devices 101, 102, 103, 104, 105, and/or 106 to input retrieval information and receive returned retrieval content. The client device may provide an interface that enables a user of the client device to interact with the client device. The client device may also output information to the user via the interface. Although fig. 1 depicts only six client devices, those skilled in the art will appreciate that the present disclosure may support any number of client devices.

Client devices 101, 102, 103, 104, 105, and/or 106 may include various types of computer devices, such as portable handheld devices, general purpose computers (such as personal computers and laptop computers), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, gaming systems, thin clients, various messaging devices, sensors or other sensing devices, and the like. These computer devices may run various types and versions of software applications and operating systems, such as MICROSOFT Windows, APPLE iOS, UNIX-like operating systems, linux, or Linux-like operating systems (e.g., GOOGLE Chrome OS); or include various mobile operating systems such as MICROSOFT Windows Mobile OS, iOS, windows Phone, android. Portable handheld devices may include cellular telephones, smart phones, tablet computers, personal Digital Assistants (PDAs), and the like. Wearable devices may include head mounted displays (such as smart glasses) and other devices. The gaming system may include various handheld gaming devices, internet-enabled gaming devices, and the like. The client device is capable of executing a variety of different applications, such as various Internet-related applications, communication applications (e.g., email applications), short Message Service (SMS) applications, and may use a variety of communication protocols.

Network 110 may be any type of network known to those skilled in the art that may support data communications using any of a number of available protocols, including but not limited to TCP/IP, SNA, IPX, etc. For example only, the one or more networks 110 may be a Local Area Network (LAN), an ethernet-based network, a token ring, a Wide Area Network (WAN), the internet, a virtual network, a Virtual Private Network (VPN), an intranet, an extranet, a blockchain network, a Public Switched Telephone Network (PSTN), an infrared network, a wireless network (e.g., bluetooth, WIFI), and/or any combination of these and/or other networks.

The server 120 may include one or more general purpose computers, special purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-end servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and/or combination. The server 120 may include one or more virtual machines running a virtual operating system, or other computing architecture that involves virtualization (e.g., one or more flexible pools of logical storage devices that may be virtualized to maintain virtual storage devices of the server). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

The computing units in server 120 may run one or more operating systems including any of the operating systems described above as well as any commercially available server operating systems. Server 120 may also run any of a variety of additional server applications and/or middle tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

In some implementations, server 120 may include one or more applications to analyze and consolidate data feeds and/or event updates received from users of client devices 101, 102, 103, 104, 105, and/or 106. Server 120 may also include one or more applications to display data feeds and/or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and/or 106.

In some implementations, the server 120 may be a server of a distributed system or a server that incorporates a blockchain. The server 120 may also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. The cloud server is a host product in a cloud computing service system, so as to solve the defects of large management difficulty and weak service expansibility in the traditional physical host and virtual private server (VPS, virtual Private Server) service.

The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of databases 130 may be used to store information such as search results. Database 130 may reside in various locations. For example, the database used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. Database 130 may be of different types. In some embodiments, the database used by server 120 may be, for example, a relational database. One or more of these databases may store, update, and retrieve the databases and data from the databases in response to the commands.

In some embodiments, one or more of databases 130 may also be used by applications to store application data. The databases used by the application may be different types of databases, such as key value stores, object stores, or conventional stores supported by the file system.

The system 100 of fig. 1 may be configured and operated in various ways to enable application of the various methods and apparatus described in accordance with the present disclosure.

Embodiments according to the present disclosure provide a content retrieval method. Fig. 2 shows a flowchart of a content retrieval method according to an embodiment of the present disclosure, as shown in fig. 2, a method 200 includes: acquiring first search information input by a user through a search engine (step 210); searching for at least one first search result based on the first search information (step 220); and obtaining, based on the first search information and the at least one first search result, first search content corresponding to the first search information generated by the first language model through a first language model, so as to display the first search content on a search result page (step 230).

According to the embodiment of the disclosure, after the first search information input by the user is obtained, the data search is performed on the first search information, and the first search content is quickly generated through the first language model based on the search result and the search information, so that the opinion or suggestion fed back by the search engine can be obtained without clicking the corresponding search result one by the user, the information search efficiency of the user through the search engine is improved, and the user experience is enhanced.

In some embodiments, the first search information (i.e., search query) includes, but is not limited to, text, voice, picture, etc. The first search content is feedback information that the search engine makes based on an understanding of the first search information. For example, when the first search information input by the user is "how today's weather is," the corresponding first search content may be weather conditions including the current date and region. In some examples, when entered in the form of speech, the speech may be converted to text by speech recognition techniques to obtain the first retrieved information.

In this disclosure, the search engine may understand and obtain at least one first search result from the first search information in any suitable manner. The search engine may perform a data search through one or more search systems and obtain at least one first search result. Wherein the at least one first search result may be, for example, a top-ranked one or more of the search results searched for by each of the one or more search systems.

In some embodiments, the first search information and at least one first search result may be input into the first language model together, so as to obtain first search content corresponding to the first search information, which is generated by the first language model.

FIG. 3 shows a search results page schematic diagram according to an exemplary embodiment of the present disclosure.

As shown in fig. 3, when a user inputs first search information 301 in a search engine, the search engine may generate first search content 302 corresponding to the first search information based on the above-described method for generating search content and display it in a search result page. The search result page refers to a result page that the search engine feeds back to a certain search request. A typical search results page typically contains a list of search results, most web sites have their own search functionality, and using this search functionality a search results page appears to present results that meet the search criteria. As shown in fig. 3, the first search content 302 may include content of the first search information, so as to facilitate a user to know that the search content is obtained based on the search information.

In some embodiments, the first search content may include summary information of the first search information generated by overwriting the first search information, and reply information (e.g., including knowledge information for solving the first search information) to the first search information generated by fusing the content in the at least one first search result.

According to some embodiments, the first language model is obtained based at least on knowledge resources and dialogue data training of a preset scale.

In some embodiments, the first language model may be a knowledge-enhanced large language model for conversations (e.g., ERNIE bot, etc.), the first language model being obtained through training of massive knowledge resources and conversational data (e.g., including more than trillion levels of web page data, billions of search data, billions of levels of picture data, billions of voice request data per day, more than 500 billions of text request data, and more than 5500 billions of factual knowledge).

Therefore, the model is applied as the first language model, not only can the chatting dialogue information be directly processed, but also the logic reasoning dialogue information, the common sense dialogue information and the image generation dialogue information can be directly generated, and the generation efficiency can be further improved while higher-quality reply information is generated.

According to some embodiments, obtaining, by a first language model, first search content generated by the first language model and corresponding to the first search information includes: obtaining a score for each of the at least one first search result, the score being used to evaluate at least one of content quality, timeliness and authority of the respective first search result, relevance to the respective query text; and in response to obtaining at least one second search result meeting a first preset condition from the at least one first search result, inputting the first search information and the at least one second search result into the first language model to obtain the first search content generated by the first language model, wherein the first preset condition indicates that the score is greater than a preset threshold.

In some embodiments, upon recall of each first search result, a score for each first search result may be simultaneously obtained by the search system, which may be used to evaluate at least one dimension of content quality, timeliness, authority, and relevance to the corresponding query text for that first search result. For example, the score of the search system for each first search result may be determined based on one or more of a number of clicks, a score, a content richness of the first search result by the user, feedback information after other users conduct data searches based on similar search information (query), and so on.

And filtering the first search results through the score of each first search result, so as to filter out the first search results with low scores. In response to search results still meeting the first preset condition after filtering, the search results (namely, second search results) and the first retrieval information are input into the first language model to obtain first retrieval content.

Therefore, the quality of the search results can be improved by further screening the search results, and the quality of the generated first search content can be further improved.

According to some embodiments, inputting the first search information and the at least one second search result into the first language model to obtain the first search content generated by the first language model comprises: acquiring first page content corresponding to each second search result in the at least one second search result; inputting the first page content into the second language model to obtain second page content generated by the second language model, wherein the second page content comprises summary information of the first page content; and inputting the first retrieval information and the second page content into the first language model to obtain the first retrieval content generated by the first language model.

In particular, the content in each search result may be very much, and if the entire content in the corresponding search result is input into the first language model, the time for the model to generate the first search content may be relatively long, thereby affecting the user search efficiency.

Thus, in some examples, a respective first page content for each of the at least one second search result is first obtained. For example, where the second search result includes an article, the first page content may be, for example, a summary portion and/or a body portion. The first page content is input into a second language model to obtain second page content. The second language model is a trained model for extracting important content from the first page content, and summarizing information of the first page content. Therefore, after the summarized second page content and the first search information are input into the first language model, the corresponding first search content can be obtained quickly, and the search efficiency of the user based on the search engine is improved.

It is to be appreciated that the second language model can be any suitable model including, but not limited to, ERNIE bot, bert, etc., without limitation.

According to some embodiments, the search result page includes a first content area and a second content area, and wherein the first retrieved content is displayed in the first content area and at least one third search result obtained in the at least one first search result is displayed in the second content area.

FIG. 4 shows a search results page schematic diagram according to an exemplary embodiment of the present disclosure. As shown in fig. 4, the search result page includes a first content area 401 and a second content area 402, which are displayed one above the other. Wherein the first content area 401 displays search content generated according to the content search method, and the second content area 402 displays at least one third search result recalled by the search request based on the first search information 301.

In the present disclosure, the at least one third search result is a search result that the search engine obtains to meet the user's search criteria based on any suitable search function already present. For example, the at least one third search result may be obtained from the at least one first search result.

According to some embodiments, obtaining, by a first language model, first search content generated by the first language model and corresponding to the first search information includes: inputting the first search information, the at least one second search result and at least one preset instruction into the first language model to obtain the first search content generated by the first language model, wherein the at least one preset instruction is used for guiding the generation process of the first search content.

In some embodiments, one or more preset instructions may be simultaneously input into the first language model when the first language model is applied to generate the first search content, so as to guide the first language model to conduct the arrangement of the search results and the reply of the first search information through the preset instructions.

In some embodiments, the preset instructions may be, for example, instructions for directing the first search content generation process to cause the first search content to be generated in a particular form (e.g., generated as a list, in a tabular form).

Therefore, when the second search result meeting the preset condition is obtained, at least one preset instruction (prompt) can be further introduced in the generation process of the reply content (namely the first search content) so as to guide the model to generate the reply content more meeting the user expectation based on the search information and the search result, thereby improving the generation quality of the reply content and improving the user experience.

For example, the preset instruction may be "please answer questions using chinese, and do not generate answers that contradict each other or are semantically repeated, so as to control answer contents to be within 250 words as much as possible", "please organize answers using formats or symbols such as line feed," - ", etc. so as to make the answers easy to read and understand.

According to some embodiments, each of the at least one second search result includes a search result identification, and the at least one preset instruction includes a first preset instruction for directing a generation process of the first search content such that each of at least one reference information in the first search content, each of which is derived from a respective second search result in the at least one second search result, is tagged with a respective search result identification.

In some embodiments, the at least one preset instruction includes a first preset instruction, which may be used to enable the first language model to mark the reference information referenced to the search result when generating the reply message, and display the reference source (search result identifier) in the generated reply message. For example, each first search result corresponds to a search result identifier (e.g., a search result sequence number), and the first preset instruction may be "please use a reference label to label the search results referenced in the answer, e.g., [1] (single reference source), [1] [2] [3] (multiple reference sources), where the number in brackets is the search result sequence number. "

Fig. 5 shows a first search content schematic diagram according to an exemplary embodiment of the present disclosure.

As shown in fig. 5, the first language model marks the reference information 501 in the first search content by the search result identifier 502 while generating the first search content generated for the first search information through understanding the first preset instruction.

Therefore, the first preset instruction, the first search information and at least one second search result are input into the first language model, so that the search content replied by the search engine can be more in line with the user expectation, the generation quality of the search content is improved, and the user experience is improved.

In some embodiments, each search result identifier may also be linked to a web page link or a book text of the corresponding second search result, so that when the user clicks the identifier, the user can trace the reference information, and the user can obtain richer information through simple interactive operation, thereby further improving user experience.

Thus, according to some embodiments, a method according to the present disclosure further comprises: and in response to acquiring a preset operation at any one of the at least one piece of reference information in the first search content, displaying the reference information source data of the reference information in a floating layer or popup form.

Fig. 6 shows a first search content schematic diagram according to an exemplary embodiment of the present disclosure. As shown in fig. 6, when the user clicks on the reference information identification or clicks on the reference information, the reference information source data 601 of the reference information may be displayed in a floating layer or popup window form. Where "AAA" may represent the source platform information of the reference information.

According to some embodiments, the at least one preset instruction further comprises a second preset instruction for guiding a generation process of the first search content, so that the first search content is displayed in a structured form.

In some examples, the at least one preset instruction may include a second preset instruction that may be used to cause the retrieved content generated by the first language model to be presented in a more structured form (e.g., list, tabular form, etc.). For example, the second preset instructions may be "please organize the answers using a linefeed, list, etc. format to make the answers easy to read and understand. "

According to some embodiments, the at least one preset instruction further comprises a third preset instruction, the third preset instruction is used for guiding the generation process of the first search content, so that the first search content is displayed in the form of one or more content tags.

In some examples, the at least one preset instruction includes a third preset instruction that may be used to cause the retrieved content class generated by the first language model to reply to the retrieved information. The first language model can automatically extract corresponding content tags (tags) according to the third preset instruction and generate search contents corresponding to the content tags, so that the search contents are more convenient to understand and read, and user experience is improved.

Fig. 7 shows a first search content schematic diagram according to an exemplary embodiment of the present disclosure. As shown in fig. 7, the first search contents 302 include TAG1, TAG2, and TAG3 content TAGs, and search contents to which the TAG1, TAG2, and TAG3 content TAGs respectively correspond. Although the plurality of content tags and their corresponding search content are shown in a horizontal arrangement in fig. 7, it will be appreciated that the plurality of content tags and their corresponding search content may be shown in other arrangements (e.g., a vertical arrangement), which is not limited thereto.

According to some embodiments, the at least one preset instruction is at least one preset instruction in a preset instruction pool, and before obtaining, by a first language model, first search content generated by the first language model and corresponding to the first search information, the method further includes: the first search information is input into a second language model to obtain the at least one preset instruction corresponding to the first search information.

In some examples, the preset instructions may be instructions in a preset instruction pool. The developer may continually maintain the instruction pool to update, add, or delete instructions in the instruction pool. At least one preset instruction corresponding to the first search information is obtained by inputting the first search information into the second language model.

In some embodiments, the second language model is a trained neural network model. For example, a developer may preset some search information and one or more sets of preset instructions corresponding to the search information (and one or more preset instructions may be included in each set), and the developer may label each search information to determine which set of preset instructions corresponds to the best effect (e.g., shown in a scoring form) on the search information. Each search information, one or more groups of preset instructions corresponding to the search information and information marked by a user can be input into a second language model to train the second language model, so that a trained second language model is obtained.

According to some embodiments, the at least one preset instruction is a preset instruction in a preset instruction template, and before obtaining, by a first language model, first search content generated by the first language model and corresponding to the first search information, the method further includes: and inputting the first retrieval information into a third language model to obtain a preset instruction template corresponding to the first retrieval information.

In some examples, the preset instructions may be instructions in a preset instruction pool, and the instructions in the preset instruction pool are stored in the form of an instruction template. The developer can maintain the instruction pool continuously to update, add or delete the instructions in the existing instruction templates; alternatively or additionally, new instruction templates are added or existing instruction templates are deleted, and so on. And obtaining a preset instruction template corresponding to the first retrieval information by inputting the first retrieval information into the second language model.

In this embodiment, the third language model is similar to the second language model described above, and the training process is adapted to be modified, which is not described herein.

According to some embodiments, the at least one second search result is a plurality of, and obtaining, by a first language model, first search content generated by the first language model and corresponding to the first search information includes: aggregating the at least one second search result to obtain at least one set of search results, wherein the search results in each of the at least one set of search results comprise the same topic; and inputting the first dialogue information and each search result in the search result set into the first language model for each search result set in the at least one search result set, and obtaining second search content corresponding to the search result set generated by the first language model so as to obtain the first search content based on at least one second search content corresponding to the at least one search result set.

In some embodiments, when the number of second search results is a plurality, the plurality of third search results may be first aggregated.

In some embodiments, the subject matter (e.g., title information) in each second search result may be extracted and clustered according to semantic similarity between the subject matter, thereby obtaining at least one set of search results.

Therefore, before the generation of the search content, the search results of the same subject are aggregated together, and corresponding second search content is generated for each subject respectively, so that the first search content is obtained based on each second search content, the generation efficiency can be improved, the generation quality of the search content can be improved, and the user experience can be improved.

In some embodiments, it may be determined that the search information is search information that requires outputting multiple perspectives (e.g., "which places the a country has play") when the demand analysis is performed on the first search information.

In some embodiments, when the above model for demand analysis marks the search information as a search information type that needs to output multiple views, more than a certain number of search results may be obtained through data searching, the search results are aggregated to obtain at least one search result set, and the number of search results in each set is counted.

When the first search content is generated, a specific preset instruction can be matched based on the search information type so as to guide the first language model to carry out information summary of search results of the same subject on the input multiple search results, generate second search content corresponding to each subject, and mark the provenance information and the number of the search results for each second search content. The user can click the provenance information, and information tracing can be performed, so that the user can acquire richer information through simple interactive operation, and user experience is further improved.

According to some embodiments, the method according to the present disclosure further comprises: and predicting first information in the first search content based on the first search information and the first search content so as to highlight the first information when the first search content is displayed.

With continued reference to fig. 5, before presenting the first search content, the first search information and the generated first search content may first be simultaneously input into a trained reading understanding model, and first information (e.g., key information) in the first search content is marked by the reading understanding model, and when presenting the first search content 302, first information 503, in which "first search information" is located near below, is highlighted (e.g., enlarged, bolded, or highlighted). Thus, by analyzing and understanding the first search information and the first search content, the first information (such as key information) in the first search content is obtained by prediction (for example, a trained reading and understanding model can be applied), and the key in the search content is highlighted. Therefore, the search content can be more in line with the user expectation, the generation quality of the search content is improved, the search content is more convenient to understand and read, and the user experience is improved.

According to some embodiments, the method according to the present disclosure further comprises: and predicting at least one piece of first recommended search information based on the first search information and the first search content so as to guide the user to conduct a top-up.

In some embodiments, after the reply message is generated, the session information and the reply message may be further input into a trained generation model, and one or more recommended questions for guiding the user to make a challenge may be generated through analysis.

FIG. 8 shows a search results page schematic diagram according to an exemplary embodiment of the present disclosure. As shown in fig. 8, while the first search content 302 is displayed, one or more recommended questions 801 may also be displayed in a preset area below the first search content 302 (e.g., in or above the top of the first content area 401 in fig. 8).

Therefore, after the search content is generated, the search information and the search content can be further predicted based on the round of search information to obtain at least one recommendation problem, so that a user can be guided to conduct the inquiry, and the user experience is improved.

According to some embodiments, predicting at least one first recommended search information based on the first search information and the first search content includes: inputting the first retrieval information, the first retrieval content and a fourth preset instruction into a fourth language model to obtain the fourth language model to generate at least one first recommendation retrieval information, wherein the fourth preset instruction is used for guiding the generation process of the at least one first recommendation retrieval information.

In some examples, the at least one first recommendation retrieval information may be obtained through a trained fourth language model. Specifically, the first search information and the first search content may be input as a pair of question-answers to the fourth language model to obtain the corresponding recommended search information. Further, the first search information, the first search content and the fourth preset instruction may be input into the fourth language model to obtain at least one first recommended search information. The fourth preset instruction is used for guiding the generation process of the at least one first recommended retrieval information, for example, the fourth preset instruction is "generate 10 extracted sentences related to the question-answer".

According to some embodiments, predicting at least one first recommended search information based on the first search information and the first search content comprises: inputting the first retrieval information, the first retrieval content and a fourth preset instruction into a fourth language model to obtain a plurality of second recommendation retrieval information generated by the fourth language model, wherein the fourth preset instruction is used for guiding the generation process of the plurality of second recommendation retrieval information; inputting the plurality of second recommendation search information into a fifth language model to obtain a score corresponding to each of the plurality of second recommendation search information, wherein the score represents a degree of recommendation of the recommendation search information; and ranking the plurality of second recommended retrieval information based on the first score to determine the at least one first recommended retrieval information among the plurality of second recommended retrieval information.

In some examples, when multiple recommended search information is obtained from the input question, the pair of recommended search information may be further filtered (e.g., filtered, deduplicated) to obtain one or more preferred recommended search information for display to the user. For example, a score corresponding to each of the plurality of second recommendation search information may be obtained by a trained fifth language model. The fifth language model may be any suitable model, such as ERNIE, without limitation.

In some examples, the ranking of the plurality of second recommendation retrieval information based on the first score may be ranking from high to low or from low to high in score to obtain at least one first recommendation retrieval information having a score greater than a preset threshold. Additionally or alternatively, the plurality of recommended search information may also be subjected to a relevance and diversity analysis, for example by an MMR algorithm (Maximal Marginal Relevance, maximum boundary correlation algorithm), to rank the plurality of recommended search information to obtain at least one first recommended search information satisfying a preset condition.

According to some embodiments, predicting at least one first recommended search information based on the first search information and the first search content may include: and predicting at least one first recommended search information based on the user portrait of the user, the historical search behavior of the user, the first search information and the first search content to guide the user to make a query.

In any of the embodiments described above with respect to obtaining at least one first recommendation search information in the present disclosure, the at least one first recommendation search information may be further obtained based on a user representation of the user, historical search behavior of the user. By way of example, the user's historical retrieval behavior may be user historical browsing data, historical click data, and the like.

According to some embodiments, at least a portion of the information of the first retrieved content is displayed in the first content area, and the method comprises: in response to acquiring a preset second operation for the first search content in the first content area, jumping from the search result page to a detail page to display all information of the first search content in the detail page.

In some examples, when the retrieved content information is greater, at least a portion of the content of the first retrieved content is displayed in a first content area of the search results page, and when the user clicks on the retrieved content or clicks "view all content" below the retrieved content, the page jumps to a detail page to fully reveal the retrieved content.

FIG. 9 shows a schematic diagram of a search results page and detail page according to an exemplary embodiment of the present disclosure. In the example shown in fig. 9, the reference information source data in the detail page may be displayed entirely below the first retrieval information.

According to some embodiments, the detail page includes a third content area and a fourth content area, and the method further includes: in response to jumping to the detail page, at least one fourth search result is obtained to display all information of the first search content in the third content area and the at least one fourth search result is displayed in the detail page, wherein the at least one fourth search result is associated with at least one of the first search information and the first search content.

With continued reference to fig. 9, the details page includes a third content area 901 and a fourth content area 902, the third content area 901 may be used to display complete information of the retrieved content, and the fourth content area 902 may be used to display at least one fourth search result. Thus, the detail page further displays at least one fourth search result as a recommended content link related to the aforementioned search information and the search content while displaying the complete information of the search content. Therefore, the user is prevented from jumping back to the page, and the user experience is improved.

In some examples, at least one fourth search result in the details page may be the same as or different from the search result in the second content area in the search result page, without limitation.

According to some embodiments, obtaining at least one fourth search result in response to jumping to the details page comprises: responding to jumping to the detail page, and acquiring at least one keyword in the first retrieval information; acquiring at least one second search information matched with the first search information based on the at least one keyword; and obtaining the at least one fourth search result corresponding to the second search information based on the second search information.

In some examples, the matching at least one second search information and the search result corresponding to the at least one second search information are determined by keyword extraction of the search information in a semantic matching manner.

According to some embodiments, obtaining at least one fourth search result in response to jumping to the details page comprises: inputting the first retrieval information into a sixth language model to obtain a first semantic vector corresponding to the first retrieval information; and performing similarity calculation on the first semantic vector and a second semantic vector corresponding to at least one fifth search result in a preset information base so as to acquire at least one fourth search result from the at least one fifth search result.

In some examples, the semantic vector corresponding to the first search content is obtained through a trained sixth language model, and other relevant search results are obtained through a semantic vector matching mode.

It is to be appreciated that the sixth language model can be any suitable model for obtaining semantic vectors, and is not limited herein.

As shown in fig. 10, there is also provided a content retrieval device 1000 according to an embodiment of the present disclosure, including: an acquisition unit 1010 configured to acquire first search information input by a user through a search engine; a search unit 1020 configured to search for at least one first search result based on the first search information; and a content generating unit 1030 configured to obtain, based on the first search information and the at least one first search result, first search content corresponding to the first search information generated by the first language model through a first language model, so as to display the first search content on a search result page.

Here, the operations of the above units 1010 to 1030 of the content retrieval device 1000 are similar to those of the steps 210 to 230 described above, respectively, and are not described again here.

In the technical scheme of the disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user accord with the regulations of related laws and regulations, and the public order colloquial is not violated.

According to embodiments of the present disclosure, there is also provided an electronic device, a readable storage medium and a computer program product.

Referring to fig. 11, a block diagram of an electronic device 1100 that may be a server or a client of the present disclosure, which is an example of a hardware device that may be applied to aspects of the present disclosure, will now be described. Electronic devices are intended to represent various forms of digital electronic computer devices, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 11, the electronic device 1100 includes a computing unit 1101 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 1102 or a computer program loaded from a storage unit 1108 into a Random Access Memory (RAM) 1103. In the RAM 1103, various programs and data required for the operation of the electronic device 1100 can also be stored. The computing unit 1101, ROM 1102, and RAM 1103 are connected to each other by a bus 1104. An input/output (I/O) interface 1105 is also connected to bus 1104.

A number of components in the electronic device 1100 are connected to the I/O interface 1105, including: an input unit 1106, an output unit 1107, a storage unit 1108, and a communication unit 1109. The input unit 1106 may be any type of device capable of inputting information to the electronic device 1100, the input unit 1106 may receive input numeric or character information and generate key signal inputs related to user settings and/or function control of the electronic device, and may include, but is not limited to, a mouse, a keyboard, a touch screen, a trackpad, a trackball, a joystick, a microphone, and/or a remote control. The output unit 1107 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, video/audio output terminals, vibrators, and/or printers. Storage unit 1108 may include, but is not limited to, magnetic disks, optical disks. The communication unit 1109 allows the electronic device 1100 to exchange information/data with other devices through computer networks such as the internet and/or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers and/or chipsets, such as bluetooth devices, 802.11 devices, wiFi devices, wiMax devices, cellular communication devices, and/or the like.

The computing unit 1101 may be a variety of general purpose and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 1101 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1101 performs the various methods and processes described above, such as method 200. For example, in some embodiments, the method 200 may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 1108. In some embodiments, some or all of the computer programs may be loaded and/or installed onto electronic device 1100 via ROM 1102 and/or communication unit 1109. One or more of the steps of the method 200 described above may be performed when a computer program is loaded into the RAM 1103 and executed by the computing unit 1101. Alternatively, in other embodiments, the computing unit 1101 may be configured to perform the method 200 by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may 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 machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is 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 a machine-readable storage medium would include an electrical connection based on 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.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.

Although embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it is to be understood that the foregoing methods, systems, and apparatus are merely exemplary embodiments or examples, and that the scope of the present invention is not limited by these embodiments or examples but only by the claims following the grant and their equivalents. Various elements of the embodiments or examples may be omitted or replaced with equivalent elements thereof. Furthermore, the steps may be performed in a different order than described in the present disclosure. Further, various elements of the embodiments or examples may be combined in various ways. It is important that as technology evolves, many of the elements described herein may be replaced by equivalent elements that appear after the disclosure.

Claims (26)

1. A content retrieval method, comprising:

acquiring first retrieval information input by a user through a search engine;

Searching to obtain at least one first search result based on the first search information; and

and based on the first search information and the at least one first search result, obtaining first search content corresponding to the first search information generated by the first language model through a first language model, so as to display the first search content on a search result page.

2. The method of claim 1, wherein obtaining, by a first language model, first search content generated by the first language model corresponding to the first search information comprises:

obtaining a score for each of the at least one first search result, the score being used to evaluate at least one of content quality, timeliness and authority of the respective first search result, relevance to the respective query text; and

and in response to acquiring at least one second search result meeting a first preset condition from the at least one first search result, inputting the first search information and the at least one second search result into the first language model to obtain the first search content generated by the first language model, wherein the first preset condition indicates that the score is greater than a preset threshold.

3. The method of claim 2, wherein inputting the first search information and the at least one second search result into the first language model to obtain the first search content generated by the first language model comprises:

acquiring first page content corresponding to each second search result in the at least one second search result;

inputting the first page content into the second language model to obtain second page content generated by the second language model, wherein the second page content comprises summary information of the first page content; and

inputting the first retrieval information and the second page content into the first language model to obtain the first retrieval content generated by the first language model.

4. A method according to claim 2 or 3, wherein obtaining, by a first language model, first search content generated by the first language model corresponding to the first search information comprises:

inputting the first search information, the at least one second search result and at least one preset instruction into the first language model to obtain the first search content generated by the first language model, wherein the at least one preset instruction is used for guiding the generation process of the first search content.

5. The method of claim 4, wherein each of the at least one second search result includes a search result identification, the at least one preset instruction including a first preset instruction for directing a generation process of the first search content such that each of at least one piece of reference information in the first search content is tagged with a respective search result identification, each of the at least one piece of reference information being derived from a respective second search result in the at least one second search result.

6. The method of claim 3 or 4, wherein the at least one preset instruction further comprises a second preset instruction for guiding a generation process of the first search content to cause the first search content to be presented in a structured form.

7. The method of any of claims 4-6, wherein the at least one preset instruction further comprises a third preset instruction for directing a generation process of the first retrieved content to cause the first retrieved content to be presented in the form of one or more content tags.

8. The method of any of claims 4-7, wherein the at least one preset instruction is at least one preset instruction in a preset instruction pool, and wherein, before obtaining, by a first language model, first search content generated by the first language model and corresponding to the first search information, further comprises: the first search information is input into a second language model to obtain the at least one preset instruction corresponding to the first search information.

9. The method of any of claims 4-7, wherein the at least one preset instruction is a preset instruction in a preset instruction template, and wherein prior to obtaining, by a first language model, first search content generated by the first language model that corresponds to the first search information, further comprising: and inputting the first retrieval information into a third language model to obtain a preset instruction template corresponding to the first retrieval information.

10. The method of any of claims 2 to 5, wherein the number of the at least one second search result is a plurality, and obtaining, by a first language model, first search content generated by the first language model and corresponding to the first search information comprises:

Aggregating the at least one second search result to obtain at least one set of search results, wherein the search results in each of the at least one set of search results comprise the same topic; and

inputting the first dialogue information and each search result in the search result set into the first language model for each search result set in the at least one search result set, and obtaining second search content corresponding to the search result set generated by the first language model, so as to obtain the first search content based on at least one second search content corresponding to the at least one search result set.

11. The method of any one of claims 1 to 10, further comprising:

and predicting first information in the first search content based on the first search information and the first search content so as to highlight the first information when the first search content is displayed.

12. The method of any one of claims 1 to 10, further comprising:

and predicting at least one piece of first recommended search information based on the first search information and the first search content so as to guide the user to conduct a top-up.

13. The method of claim 12, wherein predicting at least one first recommended search information based on the first search information and the first search content comprises:

inputting the first retrieval information, the first retrieval content and a fourth preset instruction into a fourth language model to obtain the fourth language model to generate the at least one first recommended retrieval information, wherein the fourth preset instruction is used for guiding the generation process of the at least one first recommended retrieval information.

14. The method of claim 12, wherein predicting at least one first recommended search information based on the first search information and the first search content comprises:

inputting the first retrieval information, the first retrieval content and a fourth preset instruction into a fourth language model to obtain a plurality of second recommendation retrieval information generated by the fourth language model, wherein the fourth preset instruction is used for guiding the generation process of the plurality of second recommendation retrieval information;

inputting the plurality of second recommendation search information into a fifth language model to obtain a score corresponding to each of the plurality of second recommendation search information, wherein the score represents a degree of recommendation of the recommendation search information; and

The plurality of second recommendation retrieval information is ranked based on the first score to determine the at least one first recommendation retrieval information among the plurality of second recommendation retrieval information.

15. The method of claims 12-14, wherein predicting at least one first recommended search information based on the first search information and the first search content comprises:

and predicting at least one first recommended search information based on the user portrait of the user, the historical search behavior of the user, the first search information and the first search content to guide the user to make a query.

16. The method of claim 5, further comprising: and in response to acquiring a preset operation at any one of the at least one piece of reference information in the first search content, displaying the reference information source data of the reference information in a floating layer or popup form.

17. The method of any of claims 1-16, wherein the search results page includes a first content area and a second content area, and wherein the first retrieved content is displayed in the first content area and at least one third search result obtained in the at least one first search result is displayed in the second content area.

18. The method of claim 17, wherein at least a portion of the information of the first retrieved content is displayed in the first content area, and the method comprises: in response to acquiring a preset second operation for the first search content in the first content area, jumping from the search result page to a detail page to display all information of the first search content in the detail page.

19. The method of claim 18, wherein the detail page includes a third content area and a fourth content area, and the method further comprises:

in response to jumping to the detail page, at least one fourth search result is obtained to display all information of the first search content in the third content area and the at least one fourth search result is displayed in the detail page, wherein the at least one fourth search result is associated with at least one of the first search information and the first search content.

20. The method of claim 19, wherein obtaining at least one fourth search result in response to jumping to the details page comprises:

responding to jumping to the detail page, and acquiring at least one keyword in the first retrieval information;

Acquiring at least one second search information matched with the first search information based on the at least one keyword; and

the at least one fourth search result corresponding to the second search information is acquired based on the second search information.

21. The method of claim 19, wherein obtaining at least one fourth search result in response to jumping to the details page comprises:

inputting the first retrieval information into a sixth language model to obtain a first semantic vector corresponding to the first retrieval information; and

and performing similarity calculation on the first semantic vector and a second semantic vector corresponding to at least one fifth search result in a preset information base so as to acquire at least one fourth search result from the at least one fifth search result.

22. The method of any of claims 1 to 21, wherein the first language model is obtained based at least on knowledge resources and dialogue data training of a preset scale.

23. A content retrieval device, comprising:

the acquisition unit is configured to acquire first retrieval information input by a user through a search engine;

a search unit configured to search for at least one first search result based on the first search information; and

And a content generation unit configured to obtain, based on the first search information and the at least one first search result, first search content corresponding to the first search information generated by the first language model through a first language model, so as to display the first search content on a search result page.

24. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the method comprises the steps of

The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-22.

25. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-22.

26. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the method of any of claims 1-22.