Searching method and device, electronic equipment and computer readable storage medium

Abstract

The invention discloses a search method and device, electronic equipment and a computer readable storage medium, and belongs to the technical field of artificial intelligence. Wherein the search information comprises a search text and directional search information, and the directional search information comprises at least one of the following items: a directional search symbol and a directional search identifier; and searching the search text according to the directional search information to obtain a search result.

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence technology, and specifically relates to a search method, device, electronic device and computer-readable storage medium. Background Art

[0002] With the rapid development of artificial intelligence technology, the search method using AI big models as search engines has brought many conveniences to users. At the same time, with the continuous advancement of information technology, users' demand for information has become increasingly diversified and precise. In this context, how to further improve the accuracy of big model network search has become a technical problem that needs to be solved in the current field of artificial intelligence. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a search method, device, electronic device and computer-readable storage medium, which can improve search accuracy.

[0004] In a first aspect, an embodiment of the present application provides a search method, the method comprising:

[0005] Receive search information; wherein the search information includes search text and directional search information, and the directional search information includes at least one of the following: a directional search symbol and a directional search identifier;

[0006] The search text is searched according to the directional search information to obtain search results.

[0007] In a second aspect, an embodiment of the present application provides a search device, the device comprising:

[0008] A receiving module, configured to receive search information; wherein the search information includes search text and directional search information, and the directional search information includes at least one of the following: a directional search symbol and a directional search identifier;

[0009] The search module is used to search the search text according to the directional search information to obtain search results.

[0010] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the search method described in the first aspect are implemented.

[0011] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the search method described in the first aspect are implemented.

[0012] In a fifth aspect, an embodiment of the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the search method as described in the first aspect.

[0013] In a sixth aspect, an embodiment of the present application provides a computer program product, which is stored in a storage medium and is executed by at least one processor to implement the search method as described in the first aspect.

[0014] In an embodiment of the present application, search information is received; wherein the search information includes a search text and directional search information, and the directional search information includes at least one of the following: a directional search symbol and a directional search identifier; and according to the directional search information, the search text is searched to obtain search results. Since the user can specify the directional search information in the search information during the above search process, the search engine can search the search text according to the directional search information specified by the user, thereby improving the search accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a flow chart of a search method provided by some embodiments of the present application;

[0016] Figure 2 It is one of the example diagrams of the AI ​​interaction interface provided by some embodiments of the present application;

[0017] Figure 3 This is the second example diagram of the AI ​​interaction interface provided by some embodiments of the present application;

[0018] Figure 4 This is a third example diagram of an AI interaction interface provided by some embodiments of the present application;

[0019] Figure 5 is a structural block diagram of a search device provided by some embodiments of the present application;

[0020] Figure 6 is a schematic diagram of the structure of an electronic device provided by some embodiments of the present application;

[0021] Figure 7 It is a schematic diagram of the hardware structure of an electronic device implementing various embodiments of the present application. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0023] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0024] To facilitate understanding, some relevant concepts and application scenarios involved in the embodiments of the present application are first introduced below.

[0025] 1. Related concepts

[0026] Big model network search refers to a search method that uses an AI (Artificial Intelligence) big model as a search engine, connects to the Internet, obtains relevant content links from a wide range of network resources, and extracts core ideas based on the understanding of the big model to generate results and respond to users.

[0027] Multi-platform targeted search refers to a search mode in which users use a specific search input text format to allow the large model search engine to obtain relevant content links from multiple different search platforms in a targeted manner, analyze and refine them, and then return the refined results to the user.

[0028] 2. Application Scenarios

[0029] In today's era of artificial intelligence, AI big model network search has brought many conveniences to users. It can connect to the search platform on the Internet, obtain information from the extensive resources of the search platform, and extract core ideas based on the understanding of the big model, and generate results to reply to users. At the same time, with the continuous advancement of information technology, users' demand for information is becoming increasingly diversified and precise. In this context, how to further improve the accuracy of search and meet the personalized needs of users has become an important topic in the current field of artificial intelligence.

[0030] However, the current large-scale online search has the following defects: 1) The accuracy of its search results is not high, and it often cannot accurately meet the specific needs of users; 2) There is a lack of targeted search on different search platforms, which makes it difficult for users to quickly find the source of the information they need; 3) The existing interaction design cannot meet the user's needs for targeted search on a specific search platform, and users cannot instruct the large-scale search engine to obtain information from a specific search platform in a concise and clear manner; 4) There is a lack of targeted search on different search topics, which makes it difficult for users to quickly find information on topics of interest to them; 5) The existing search method cannot achieve multi-platform targeted search, and users cannot obtain and compare search results from multiple different search platforms at the same time, which reduces the user's search experience and information acquisition efficiency.

[0031] In order to solve the above technical problems, the embodiments of the present application provide a search method, device, electronic device and computer-readable storage medium.

[0032] A search method provided in an embodiment of the present application is described in detail below with reference to the accompanying drawings.

[0033] It should be noted that the search method provided in the embodiment of the present application is suitable for electronic devices running a large model search engine. In actual applications, the electronic devices include but are not limited to: mobile terminals such as smart phones and tablets, and computer devices such as desktop computers and servers. The embodiment of the present application does not limit this.

[0034] Figure 1 is a flowchart of a search method provided by some embodiments of the present application, such as Figure 1 As shown, the method may include the following steps: step 101 and step 102;

[0035] In step 101, search information is received; wherein the search information includes search text and directional search information, and the directional search information includes at least one of the following: a directional search symbol and a directional search identifier.

[0036] In an embodiment of the present application, the electronic device receives search information.

[0037] In the embodiment of the present application, the big model search engine is an engine technology that uses a big model as a search engine. When a user has a search need, he or she can input search information into the big model search engine. Accordingly, the big model search engine receives the search information and performs a directed search operation based on the search information.

[0038] In the embodiment of the present application, the search text refers to one or more keywords entered by the user in the search engine, which directly reflects the user's search intention. For example, the search text may be "Which exhibition can I visit in Shanghai this weekend?", or the search text may be "Recommendations for niche attractions in Yunnan during the National Day holiday".

[0039] In the embodiment of the present application, the directional search information is used to instruct the large model engine to search the search text in a directional manner.

[0040] In an embodiment of the present application, the directional search symbol is a symbol, for example, “@”, “#”, etc.

[0041] In the embodiment of the present application, the directional search identifier is an identifier, such as a name, ID, etc.

[0042] In the embodiment of the present application, in the search information, the directional search information may be located before the search text, in which case the format of the search information is: "directional search information search text"; or the directional search information may be located after the search text, in which case the format of the search information is: "search text directional search information". Considering the general usage habits of users, the format of the search information is usually: "directional search information search text".

[0043] In the embodiment of the present application, in addition to supporting users to add search text in the search information, the large model search engine also supports users to add directional search information in the search information, so as to control the large model search engine to search the search text in a directional manner.

[0044] In some embodiments, in order to facilitate user searches, the large model search engine may provide an AI interaction interface, which is a human-computer interaction dialogue interface. Accordingly, the above step 101 may include the following steps: step 1011 and step 1012.

[0045] In step 1011, a first input to the AI ​​interaction interface is received.

[0046] In an embodiment of the present application, the first input is used to input search information on the AI ​​interaction interface.

[0047] In the embodiment of the present application, the AI ​​interaction interface may include a text input box, and the user enters the search information in the text input box through the first input. Alternatively, the AI ​​interaction interface may include multiple candidate information, and the user selects the candidate information through the first input. The selected candidate information is the information entered on the AI ​​interaction interface by the first input, and the selected candidate information is determined as the search information.

[0048] In step 1012, in response to the first input, search information is determined.

[0049] In the embodiment of the present application, the information input by the first input on the AI ​​interaction interface is determined as the search information.

[0050] Exemplarily, the AI ​​interactive interface includes a text input box, and the user enters search information that matches his or her search needs in the text input box of the AI ​​interactive interface according to his or her search needs.

[0051] It can be seen that in the embodiment of the present application, the large model search engine can provide a special AI interactive interface, so that users can quickly and intuitively input search information on the AI ​​interactive interface, and users can instruct the large model search engine to search in a targeted manner in a concise and clear manner. The interactive design can meet the user's needs for targeted search of specific information.

[0052] In some embodiments, on the one hand, considering that by default the large model search engine can obtain information resources from any search platform on the Internet; on the other hand, considering that the amount of information obtained from the entire network is too large, it is not targeted and accurate, and it is difficult for users to accurately find the information they want from a large amount of information. In this case, the user hopes to obtain information resources from a specific search platform such as a certain search platform or several search platforms.

[0053] In order to meet the user's targeted search on different search platforms and enable the user to quickly find the information he needs, the targeted search information is the first targeted search information, wherein the first targeted search information is used to indicate the search platform, and the first targeted search information includes a first targeted search symbol and a first targeted search identifier, and the number of the first targeted search identifier is at least one.

[0054] In the embodiments of the present application, the search platform refers to a platform that can provide information resources, such as various websites, applications, servers, etc.

[0055] In the embodiment of the present application, the first directional search symbol is used to indicate that the user has specified a search platform. The first directional search symbol is a symbol, for example, the first directional search symbol is “@”.

[0056] In the embodiment of the present application, considering that the symbol "@" is often used in the human-computer interaction process of the application, and is usually used to mention or reference a certain object, for example, in a social application, when @ is used in a group chat plus a person's name, the person will receive a special reminder and clearly know that someone is mentioning him or her. Therefore, in order to facilitate the user to write the first directional search information, the first directional search symbol can be "@". In addition, the first directional search symbol can also be other types of symbols, which are not limited in the embodiment of the present application.

[0057] In the embodiment of the present application, the first directional search identifier is used to indicate the identifier of the search platform specified by the user, which identifier is usually a name, that is, the first directional search identifier is the name of the search platform, such as some content sharing platforms.

[0058] In the embodiment of the present application, in the first directional search information, the first directional search symbol may be located in front of the first directional search identifier, in which case the format of the first directional search information is: "first directional search symbol first directional search identifier"; or the first directional search symbol may be located after the first directional search identifier, in which case the format of the first directional search information is: "first directional search identifier first directional search symbol". Considering the general usage habits of users, the format of the first directional search information is usually: "first directional search symbol first directional search identifier".

[0059] Exemplarily, when the user wants to control the large model search engine to search for information from content sharing platform A, he can write the following first directional search information: "@A content sharing platform", where "@" is the first directional search symbol, and "A content sharing platform" is the first directional search identifier. The format of the first directional search information is: "first directional search symbol first directional search identifier".

[0060] For example, when a user wants to use a large model search engine to search for information related to "which exhibitions in Shanghai can be visited this weekend" on content sharing platform A, Figure 2 As shown, the user can enter the following search information in the text input box 22 of the AI ​​interactive interface 21 of the electronic device 20: "@A content sharing platform Which exhibition can I visit in Shanghai this weekend", and then click the search control 23 to trigger the large model engine in the electronic device 20 to search for relevant information on the A content sharing platform "Which exhibition can I visit in Shanghai this weekend"; among which, "@" is the first directional search symbol, "A content sharing platform" is the first directional search identifier, and "Which exhibition can I visit in Shanghai this weekend" is the search text, and the format of the search information is: "first directional search symbol first directional search identifier search text".

[0061] In the embodiment of the present application, the purpose of specifying a specific search platform of a large model search engine is achieved by inputting "@search platform name search text". On the one hand, it is easier to understand from the user's visual perspective, and on the other hand, it is easier to write from the user's operation perspective.

[0062] In the embodiment of the present application, the interactive design of "first directional search symbol, first directional search identifier, search text" is used as one of the specific design methods for the user to interact with the large model search engine. The user issues a search task to the large model search engine by inputting "first directional search symbol, first directional search identifier, search text", thereby achieving the purpose of targeted search for information on a specific search platform.

[0063] In an embodiment of the present application, in order to control the large model search engine to obtain information resources from the search platform specified by the user, the large model search engine can support the user to specify the search platform in the search information. Specifically, the user can write the search information according to a specific content format, for example, "first directional search symbol first directional search identifier search text". In addition to the search text, the search information also includes first directional search information. The written search information is input into the large model search engine, and the large model search engine can obtain information resources from the search platform specified by the user. On the one hand, the search results are more accurate, and on the other hand, it can meet the user's personalized search needs.

[0064] Exemplarily, there are a large number of search platforms 1, 2, ..., N on the Internet, for example, N is 10000. By default, the large model search engine can obtain information resources from the above search platforms 1 to N. If the user is only interested in the information resources of search platform 1, the search platform 1 can be specified in the content format of the search information. The large model search engine only obtains search results matching the search text from search platform 1 according to the above search information.

[0065] It can be seen that in the embodiment of the present application, when the user uses the big model search engine to search for information, in addition to entering the basic search text, he only needs to enter the first directional search symbol and the first directional search identifier (such as the name of the search platform he wants) to control the big model search engine to obtain relevant information resources from one or more search platforms specified by the user. Since the content and format of the above search information are relatively simple, the user is more convenient to operate.

[0066] In some embodiments, on the one hand, considering that by default the big model search engine can obtain information resources on any topic from the Internet; on the other hand, considering that the amount of information resources obtained from the entire network is too large, it is not targeted and accurate, and it is difficult for users to accurately find information on the topic they want from a large amount of information. In this case, the user hopes that the big model engine can only search for information resources on a certain topic or several topics.

[0067] In order to satisfy users' targeted searches for different topics and enable users to quickly find information on topics of interest to them, the directional search information is the second directional search information, wherein the second directional search information is used to indicate search resources, and the second directional search information includes a second directional search symbol and a second directional search identifier, and the number of the second directional search identifiers is at least one.

[0068] In the embodiment of the present application, the search resource refers to the topic to which the information belongs, for example, food sharing, travel guides, science and technology information, medical consultation, transportation, mobile payment, etc.

[0069] In the embodiment of the present application, the second directional search symbol is used to indicate that the user has specified the search resource, and the second directional search symbol is a symbol. In order to avoid user confusion and content recognition of the large model engine, the first directional search symbol and the second directional search symbol are usually two different symbols. For example, the second directional search symbol is "#".

[0070] In the embodiments of the present application, it is considered that the symbol "#" is also often used in the human-computer interaction process of the application, and is usually used by users to organize and retrieve information on the search platform. For example, users classify and label the content by adding "#+topic" when publishing content, such as "#food sharing", "#travel guide", etc. Therefore, when using a large model search engine to search for information, specific keywords, such as "#technology frontier", can also be used to quickly locate information on related topics, so that users can more efficiently find specific topic information of interest in a large amount of information, thereby improving the discoverability and organization of information. Therefore, in order to facilitate users to write search input text, the second directional search symbol can be "#". In addition, the second directional search symbol can also be other types of symbols, which are not limited in the embodiments of the present application.

[0071] In an embodiment of the present application, the second directional search identifier is used to indicate the identifier of the search resource specified by the user, which identifier is usually a name, that is, the second directional search identifier is the name of the search resource (topic), such as food sharing, travel guides, science and technology information, medical consultation, transportation, mobile payment, etc.

[0072] In the embodiment of the present application, in the second directional search information, the second directional search symbol may be located in front of the second directional search identifier, in which case the format of the second directional search information is: "second directional search symbol second directional search identifier"; or the second directional search symbol may be located after the second directional search identifier, in which case the format of the second directional search information is: "second directional search identifier second directional search symbol". Considering the general usage habits of users, the format of the second directional search information is usually: "second directional search symbol second directional search identifier".

[0073] Exemplarily, when the user wants to control the large model search engine to only search for relevant information of "travel guide", the user can write the following second directional search information: "#travel guide", where "#" is the second directional search symbol and "travel guide" is the second directional search identifier. The format of the second directional search information is: "second directional search symbol second directional search identifier".

[0074] For example, when a user wants to use a large model search engine to search for travel guide information related to "Which exhibitions can I visit in Shanghai this weekend?", Figure 3 As shown, the user can enter the following search information in the text input box 32 of the AI ​​interactive interface 31 of the electronic device 30: "#Travel guide Which exhibition can I visit in Shanghai on weekends", and then click the search control 33 to trigger the large model engine in the electronic device 30 to search the Internet for travel guide information related to "Which exhibition can I visit in Shanghai on weekends"; among which, "#" is the second directional search symbol, "travel guide" is the second directional search identifier, and "Which exhibition can I visit in Shanghai on weekends" is the search text, and the format of the search information is: "Second directional search symbol second directional search identifier search text".

[0075] In the embodiment of the present application, the purpose of specifying the search topic of the large model search engine is achieved by inputting "#search resource name search text". On the one hand, it is easier to understand from the user's visual perspective, and on the other hand, it is easier to write from the user's operation perspective.

[0076] In the embodiment of the present application, the interactive method of "second directional search symbol second directional search identifier search text" is used as one of the specific design methods for the user to interact with the large model search engine. The user issues a search task to the large model search engine by inputting "second directional search symbol second directional search identifier search text", thereby achieving the purpose of targeted search for information on specific topics.

[0077] In an embodiment of the present application, in order to control the large model search engine to search for information resources on a topic specified by a user, the large model search engine can support users to specify search resources (i.e., topics) in search information. Specifically, users can write search information in accordance with a specific content format, for example, "second directional search symbol second directional search identifier search text". In addition to the search text, the search information also includes second directional search information. The written search information is input into the large model search engine, and the large model search engine can search for information resources on the topic specified by the user. On the one hand, the search results are more accurate, and on the other hand, it can meet the user's personalized search needs.

[0078] Exemplarily, there are a large number of search platforms 1, 2, …, N on the network. For example, N is 10,000. By default, the large model search engine can obtain information resources from the above-mentioned search platforms 1 to search platform N. If the user is only interested in information resources related to technology, the user can specify the search resource "#Technology Frontier" in the content format of the search information. The large model search engine will only search for technology-related information resources that match the search text according to the above search information.

[0079] It can be seen that in the embodiments of the present application, when the user uses the large model search engine to search for information, in addition to entering the basic search text, the user only needs to enter the second directional search symbol and the second directional search identifier (such as the name of the search resource the user wants), and then the user can control the large model search engine to search for information resources related to one or more topics specified by the user. Since the content and format of the above search information are relatively simple, the convenience of the user operation is relatively high.

[0080] In some embodiments, in order to further improve the search accuracy, the large model search engine not only supports the user to specify the search platform in the search information, but also supports the user to specify the search topic in the search information. Correspondingly, the directional search information includes the first directional search information and the second directional search information; wherein, the first directional search information is used to indicate the search platform, the first directional search information includes the first directional search symbol and the first directional search identifier, and the number of the first directional search identifiers is at least one; the second directional search information is used to indicate the search resource, the second directional search information includes the second directional search symbol and the second directional search identifier, and the number of the second directional search identifiers is at least one.

[0081] In the embodiments of the present application, the format of the search information can be: "Second directional search information First directional search information Search text", more specifically, the format of the search information can be: "Second directional search symbol Second directional search identifier First directional search symbol First directional search identifier Search text".

[0082] Exemplarily, when the user wants to use the large model search engine to search for travel guide information related to "which exhibitions can be visited in Shanghai on weekends" from the A content sharing platform, such as Figure 4As shown, the user can enter the following search information in the text input box 42 of the AI ​​interactive interface 41 of the electronic device 40: "#Travel guide @A content sharing platform Which exhibition can I visit in Shanghai this weekend", and then click the search control 43 to trigger the large model engine in the electronic device 40 to search for travel guide information related to "Which exhibition can I visit in Shanghai this weekend" from the A content sharing platform; wherein, "@" is the first directional search symbol, "A content sharing platform" is the first directional search identifier, "#" is the second directional search symbol, "travel guide" is the second directional search identifier, and "Which exhibition can I visit in Shanghai this weekend" is the search text, and the format of the search information is: "second directional search symbol second directional search identifier first directional search symbol first directional search identifier search text".

[0083] In the embodiment of the present application, the purpose of specifying a specific search platform and topic of a large model search engine is achieved by inputting "#name of search resource@name of search platform search text". On the one hand, it is easier to understand from the user's visual perspective, and on the other hand, it is easier to write from the user's operation perspective.

[0084] In an embodiment of the present application, the interactive design of "second directional search symbol, second directional search identifier, first directional search symbol, first directional search identifier, search text" is used as one of the specific design methods for users to interact with the large model search engine. The user issues a search task to the large model search engine by inputting "second directional search symbol, second directional search identifier, first directional search symbol, first directional search identifier, search text", thereby achieving the purpose of targeted search for relevant information on a specific topic on a specific search platform.

[0085] In an embodiment of the present application, in order to control the large model search engine to obtain information resources on the topic specified by the user from the search platform specified by the user, the large model search engine can support the user to specify the search platform and search resources in the search information. Specifically, the user can write the search information according to a specific content format, for example, "second directional search symbol second directional search identifier first directional search symbol first directional search identifier search text". In addition to the search text, the search information also includes first directional search information and second directional search information. The written search information is input into the large model search engine, and the large model search engine can obtain information resources on the topic specified by the user from the search platform specified by the user. On the one hand, the search results are more accurate, and on the other hand, it can meet the user's personalized search needs.

[0086] Exemplarily, there are a large number of search platforms 1, 2, …, N on the network. For example, when N is 10,000, by default, the large model search engine can obtain information resources from the above-mentioned search platforms 1 to N. If the user is only interested in the technology-related information resources in search platform 1, the user can specify search platform 1 and the search resource "#Technology Frontier" in the content format of the search information. The large model search engine obtains the technology-related information resources that match the search text from search platform 1 according to the above search information.

[0087] It can be seen that in the embodiments of the present application, when the user uses the large model search engine to search for information, in addition to inputting the basic search text, the user only needs to input the first and second directional search symbols and the first and second directional search identifiers to control the large model search engine to obtain the relevant information resources of the topic specified by the user from one or more search platforms specified by the user. Since the content and format of the above search information are relatively simple, the convenience of user operation is relatively high.

[0088] It can be understood that for the case where the search information includes the first directional search information, the user needs to clearly determine the type of information required and the search platform that is most likely to provide such information in order to obtain accurate information more efficiently. For the case where the first directional search information includes multiple first directional search identifiers, the user needs to have a certain understanding of the characteristics and advantages of different search platforms in order to select the most suitable combination of search platforms for searching.

[0089] In step 102, according to the directional search information, the search text is searched to obtain search results.

[0090] In the embodiments of the present application, the electronic device searches the search text according to the directional search information to obtain search results.

[0091] In the embodiments of the present application, the electronic device can use the AI large model search engine to search the search text according to the directional search information to obtain search results.

[0092] In the embodiments of the present application, the search results include but are not limited to: resources in various forms such as texts (such as articles, posts), images, audios, videos, etc.

[0093] In the embodiments of the present application, the number of search results can be 1 or multiple, and the embodiments of the present application do not make any limitations in this regard.

[0094] In the embodiment of the present application, after receiving the search information for the large model search engine, the large model search engine can parse the directional search information and the search text from the search information. For example, if the user specifies the search platform in the directional search information, the large model search engine can further parse the name of the search platform from the directional search information, and access the corresponding search platform in a targeted manner through a specific interface or protocol. For example, if the search platform is content sharing platform A, the large model search engine will use the API open to content sharing platform A or legal and compliant web crawler technology to connect to the server of content sharing platform A and obtain information that matches the search text in the search information.

[0095] In the embodiment of the present application, after successfully accessing the search platform specified by the user, the large model search engine can use the search algorithm and keyword matching technology to search for some information matching the search text on the search platform. If the user specifies the search resource in the search information, the information matching the search text will be further screened based on the search resource to obtain the final search results, such as some relevant content links, which can be resources in various forms such as articles, posts, videos, etc. In addition, the large model search engine can also screen and sort the search results, giving priority to content links with high relevance and strong authority to improve the quality of the search results.

[0096] In an embodiment of the present application, the search results can be displayed on the AI ​​interactive interface of the large model engine to intuitively present the search results to the user.

[0097] In some embodiments, when the first directed search information is included in the directed search information, that is, the user only specifies the search platform but does not indicate the search topic in the search information, the large model engine obtains search results matching the search text from the search platform specified by the user.

[0098] It can be seen that in the embodiment of the present application, the big model search engine obtains information from the search platform specified by the user, which can achieve the following effects: 1) Improve the accuracy of search results: Through the user-specified search platform, the big model search engine can focus on a specific information source for search, reduce the interference of irrelevant information, and thus improve the accuracy of search results; 2) Meet the personalized needs of users: Different users have different needs for information. Some users may prefer to obtain information from a specific search platform, which meets the personalized needs of users and allows users to choose the search platform according to their preferences and needs; 3) Improve user search experience: The concise and clear "first directional search information search text" interaction method enables users to quickly and conveniently issue search tasks to the big model search engine without complicated operations and settings; at the same time, high-quality search results can also improve the user's search experience, making users more satisfied and trusting of the big model search engine's services.

[0099] In some embodiments, when the targeted search information includes second targeted search information, that is, the user only specifies the search topic in the search information but does not indicate the search platform, the big model engine obtains search results from the network that match both the search text and the search topic specified by the user.

[0100] It can be seen that in the embodiment of the present application, the large model search engine obtains information from the search platform specified by the user, which can achieve the following effects: 1) Further improve the search accuracy: By introducing specific search topics, the information required by the user can be more accurately located, and the interference of irrelevant results can be reduced; 2) Better meet the needs of specific topics: For searches in specific fields, such as travel guides, scientific and technological information, etc., users can use topic tags to quickly find more professional and in-depth content; 3) Enhance the comprehensibility of search results: The result replies generated by combining topic tags are more targeted and coherent, and users can more easily understand and apply the searched information.

[0101] In some embodiments, when the targeted search information includes first targeted search information and second targeted search information, that is, the user specifies both the search topic and the search platform in the search information, the big model engine obtains search results that match both the search text and the search topic specified by the user from the search platform specified by the user.

[0102] It can be seen that in the embodiment of the present application, when the large model search engine obtains information from the search platform specified by the user, the user can also further clarify the scope and direction of the search through the search topic, thereby improving the accuracy of the search.

[0103] As can be seen from the above embodiment, in this embodiment, search information is received; wherein the search information includes search text and directional search information, and the directional search information includes at least one of the following: a directional search symbol and a directional search identifier; and according to the directional search information, the search text is searched to obtain search results. Since the user can specify the directional search information in the search information during the above search process, the large model search engine can accurately search the search text according to the directional search information specified by the user, thereby improving the accuracy of the search and meeting the personalized needs of the user.

[0104] In some other embodiments provided in the present application, the search method provided is: Figure 1 After step 102 in the method embodiment shown, the following steps may also be included: step 103 and step 104;

[0105] In step 103, the search results are subjected to text extraction processing by using the AI ​​function.

[0106] In an embodiment of the present application, in order to improve the readability of the output results of the large model engine, the large model engine can perform text extraction processing on the search results through the AI ​​function.

[0107] For example, the search results are some content links. For each content link obtained, the big model search engine will conduct in-depth analysis, extract key information and core ideas through natural language processing technology, such as text classification, entity recognition, sentiment analysis, etc., and perform text extraction processing such as understanding and summarizing the content. Since the big model search engine has powerful text analysis capabilities, it can accurately extract the core points of the content and provide users with concise and clear target search results.

[0108] In step 104, the text extraction processing result is output.

[0109] In the embodiment of the present application, in addition to collating and organizing the core viewpoints obtained from the analysis to generate the final search results, the large model search engine can also output the final search results to the user in a clear and easy-to-understand manner, wherein the output can be in the form of text, charts, links, etc., so that the user can better understand and view the search results. Furthermore, the large model search engine can also select the most appropriate output method according to the user's needs and preferences, thereby improving user satisfaction.

[0110] In an embodiment of the present application, the text extraction processing results can be displayed on the AI ​​interactive interface of the large model engine to intuitively present the final search results to the user.

[0111] It can be seen that in the embodiment of the present application, for the search results obtained from the search platform, the big model engine can also perform text extraction on the search results, and provide the text extraction results as the final search results to the user. On the one hand, some invalid information can be filtered out, making it easier for users to find key information; on the other hand, the readability of the search results can be improved, thereby improving the user's reading efficiency of the search results.

[0112] In some other embodiments provided by the present application, when the number of directional search information is at least two and the at least two directional search information are used to indicate different search platforms, the provided search method includes: Figure 1 After step 102 in the method embodiment shown, the following steps may also be included: step 105 and step 106;

[0113] In step 105, the search results of each search platform are summarized and processed through the AI ​​function.

[0114] In an embodiment of the present application, when the number of search platforms indicated by the directional search information is greater than 1, for different search platforms, the large model search engine can obtain search results from different search platforms.

[0115] In an embodiment of the present application, in order to improve the readability of the output results of the big model engine, the big model search engine can use the AI ​​function to summarize and compare the search results of different specific search platforms.

[0116] Exemplarily, the user instructs the big model search engine to search from search platform 1, search platform 2, and search platform 3. The big model search engine responds to the user's instruction and obtains original search result 1 from search platform 1, original search result 2 from search platform 2, and original search result 3 from search platform 3. Afterwards, the big model search engine summarizes the opinions of search result 1 to obtain opinion information 1, summarizes the opinions of search result 2 to obtain opinion information 2, summarizes the opinions of search result 3 to obtain opinion information 3, and compares opinion information 1, opinion information 2, and opinion information 3 to obtain comparison information. Finally, opinion information 1, opinion information 2, opinion information 3, and comparison information are returned to the user together.

[0117] In step 106, the summary processing result is output.

[0118] In an embodiment of the present application, the summary processing results can be displayed on the AI ​​interactive interface of the large model engine to intuitively present the final search results to the user.

[0119] It can be seen that in the embodiment of the present application, when the number of search platforms specified by the user is greater than 1, on the one hand, the big model search engine can search from multiple search platforms at the same time, and can obtain broader and richer information resources, providing users with multi-perspective, comprehensive answers and solutions; on the other hand, the big model search engine can summarize the search results of different search platforms, so that users can intuitively understand the different views of different search platforms on the same search text, which helps users make more informed decisions; on the other hand, the big model search engine can meet the user's needs for different types of search platforms in different scenarios, improve the applicability and flexibility of the big model search engine, and better serve the user's diverse information search needs.

[0120] In summary, in order to solve the problem of inaccurate search results of existing large-model network, in the embodiment of the present application, by introducing the interactive mode of "directional search information search text", users can accurately specify the search platform and / or search topic to be searched, thereby improving the accuracy of search results. In addition, the above interactive design is relatively simple, and users can easily issue instructions to the large-model search engine for directional search of specific search platforms and / or search topics, making full use of the advantageous resources of different platforms.

[0121] In response to the problem that existing interactive devices are unable to implement multi-platform targeted search, in the embodiments of the present application, the multi-platform targeted search function allows users to obtain search results from multiple different search platforms at the same time. Users can view them one by one or in comparison, providing users with more comprehensive and richer information, meeting users' diverse information needs, and improving users' search experience and information acquisition efficiency.

[0122] The search method provided in the embodiment of the present application can be executed by a search device. In the embodiment of the present application, the search device provided in the embodiment of the present application is described by taking the search method executed by the search device as an example.

[0123] Figure 5 is a structural block diagram of a search device provided by some embodiments of the present application, such as Figure 5 As shown, the search device 500 may include: a receiving module 501 and a search module 502;

[0124] The receiving module 501 is used to receive search information; wherein the search information includes search text and directional search information, and the directional search information includes at least one of the following: a directional search symbol and a directional search mark;

[0125] The search module 502 is used to search the search text according to the directional search information to obtain search results.

[0126] As can be seen from the above embodiment, in this embodiment, search information is received; wherein the search information includes search text and directional search information, and the directional search information includes at least one of the following: a directional search symbol and a directional search identifier; and according to the directional search information, the search text is searched to obtain search results. Since the user can specify the directional search information in the search information during the above search process, the large model search engine can accurately search the search text according to the directional search information specified by the user, thereby improving the accuracy of the search and meeting the personalized needs of the user.

[0127] Optionally, as an embodiment, the receiving module 501 may include:

[0128] A receiving submodule, configured to receive a first input to the AI ​​interaction interface;

[0129] a determination submodule, configured to determine the search information in response to the first input;

[0130] The search device 500 may further include:

[0131] A display module is used to display the search results on the AI ​​interaction interface.

[0132] Optionally, as an embodiment, the directional search information is first directional search information or second directional search information;

[0133] The first directional search information is used to indicate a search platform, the first directional search information includes a first directional search symbol and a first directional search identifier, and the number of the first directional search identifier is at least one;

[0134] The second directional search information is used to indicate a search resource. The second directional search information includes a second directional search symbol and a second directional search identifier. The number of the second directional search identifier is at least one.

[0135] Optionally, as an embodiment, the directional search information includes first directional search information and second directional search information;

[0136] The first directional search information is used to indicate a search platform, the first directional search information includes a first directional search symbol and a first directional search identifier, and the number of the first directional search identifier is at least one;

[0137] The second directional search information is used to indicate a search resource. The second directional search information includes a second directional search symbol and a second directional search identifier. The number of the second directional search identifier is at least one.

[0138] Optionally, as an embodiment, the search device 500 may further include:

[0139] A first processing module, configured to perform text extraction processing on the search results through an AI function;

[0140] The first output module is used to output the text extraction processing results.

[0141] Optionally, as an embodiment, the number of the directional search information is at least two, and the at least two directional search information are used to indicate different search platforms;

[0142] The search device 500 may further include:

[0143] The second processing module is used to summarize the search results of each search platform through the AI ​​function;

[0144] The second output module is used to output the summary processing results.

[0145] The search device in the embodiment of the present application can be an electronic device, or a component in the electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or other devices other than a terminal. Exemplarily, the electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted electronic device, a mobile Internet device (Mobile Internet Device, MID), an augmented reality (Augmented Reality, AR) / virtual reality (Virtual Reality, VR) device, a robot, a wearable device, an ultra-mobile personal computer (Ultra-Mobile Personal Computer, UMPC), a netbook or a personal digital assistant (Personal Digital Assistant, PDA), etc., and can also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (Personal Computer, PC), a television (Television, TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0146] The search device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0147] The search device provided in the embodiment of the present application can achieve the above Figure 1 To avoid repetition, the various processes implemented in the illustrated method embodiment will not be described again here.

[0148] Alternatively, if Figure 6 As shown, an embodiment of the present application also provides an electronic device 600, including a processor 601 and a memory 602, wherein the memory 602 stores programs or instructions that can be executed on the processor 601, and when the program or instructions are executed by the processor 601, the various steps of the above-mentioned search method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, they are not repeated here.

[0149] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0150] Figure 7 It is a schematic diagram of the hardware structure of an electronic device implementing various embodiments of the present application.

[0151] The electronic device 700 includes but is not limited to: a radio frequency unit 701, a network module 702, an audio output unit 703, an input unit 704, a sensor 705, a display unit 706, a user input unit 707, an interface unit 708, a memory 709, and a processor 710.

[0152] Those skilled in the art will appreciate that the electronic device 700 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 710 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Figure 7 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.

[0153] In some embodiments, the user input unit 707 is used to receive search information; wherein the search information includes search text and directional search information, and the directional search information includes at least one of the following: a directional search symbol, a directional search mark;

[0154] Processor 710, configured to search the search text according to the directional search information to obtain search results

[0155] It can be seen that in the embodiment of the present application, since in the above search process, the user can specify the directional search information in the search information, the large model search engine can accurately search the search text according to the directional search information specified by the user, thereby improving the accuracy of the search and meeting the personalized needs of the user.

[0156] Optionally, as an embodiment, the user input unit 707 is specifically configured to receive a first input to the AI ​​interaction interface;

[0157] The processor 710 is specifically configured to determine the search information in response to the first input;

[0158] The display unit 706 is used to display the search results on the AI ​​interaction interface.

[0159] Optionally, as an embodiment, the directional search information is first directional search information or second directional search information;

[0160] The first directional search information is used to indicate a search platform, the first directional search information includes a first directional search symbol and a first directional search identifier, and the number of the first directional search identifier is at least one;

[0161] The second directional search information is used to indicate a search resource. The second directional search information includes a second directional search symbol and a second directional search identifier. The number of the second directional search identifier is at least one.

[0162] Optionally, as an embodiment, the directional search information includes first directional search information and second directional search information;

[0163] The first directional search information is used to indicate a search platform, the first directional search information includes a first directional search symbol and a first directional search identifier, and the number of the first directional search identifier is at least one;

[0164] The second directional search information is used to indicate a search resource. The second directional search information includes a second directional search symbol and a second directional search identifier. The number of the second directional search identifier is at least one.

[0165] Optionally, as an embodiment, the processor 710 is further configured to perform text extraction processing on the search results through an AI function; and output the text extraction processing results.

[0166] Optionally, as an embodiment, the number of the directional search information is at least two, and the at least two directional search information are used to indicate different search platforms;

[0167] Processor 710 is also used to summarize the search results of various search platforms through AI functions and output the summary processing results.

[0168] It should be understood that in the embodiment of the present application, the input unit 704 may include a graphics processor (Graphics Processing Unit, GPU) 7041 and a microphone 7042, and the graphics processor 7041 processes the image data of the static picture or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode. The display unit 706 may include a display panel 7061, and the display panel 7061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 707 includes a touch panel 7071 and at least one of other input devices 7072. The touch panel 7071 is also called a touch screen. The touch panel 7071 may include two parts: a touch detection device and a touch controller. Other input devices 7072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

[0169] The memory 709 can be used to store software programs and various data. The memory 709 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 709 may include a volatile memory or a non-volatile memory, or the memory 709 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 709 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0170] The processor 710 may include one or more processing units; optionally, the processor 710 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 710.

[0171] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned search method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0172] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0173] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned search method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0174] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0175] An embodiment of the present application provides a computer program product, which is stored in a storage medium. The program product is executed by at least one processor to implement the various processes of the above-mentioned search method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0176] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0177] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0178] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A search method, characterized in that: The method comprises: Receive search information; wherein the search information includes search text and directional search information, and the directional search information includes at least one of the following: a directional search symbol and a directional search identifier; The search text is searched according to the directional search information to obtain search results.

2. The method according to claim 1, characterized in that The receiving of search information includes: Receiving a first input to the AI ​​interaction interface; In response to the first input, determining the search information; The method further comprises: The search results are displayed on the AI ​​interaction interface.

3. The method according to claim 1, characterized in that: The directional search information is first directional search information or second directional search information; The first directional search information is used to indicate a search platform, the first directional search information includes a first directional search symbol and a first directional search identifier, and the number of the first directional search identifier is at least one; The second directional search information is used to indicate a search resource. The second directional search information includes a second directional search symbol and a second directional search identifier. The number of the second directional search identifier is at least one.

4. The method according to claim 1, characterized in that: The directional search information includes first directional search information and second directional search information; The first directional search information is used to indicate a search platform, the first directional search information includes a first directional search symbol and a first directional search identifier, and the number of the first directional search identifier is at least one; The second directional search information is used to indicate a search resource. The second directional search information includes a second directional search symbol and a second directional search identifier. The number of the second directional search identifier is at least one.

5. The method according to claim 1, characterized in that The method further comprises: Perform text extraction processing on the search results through AI function; Output text extraction processing results.

6. The method according to claim 1, characterized in that The number of the directional search information is at least two, and the at least two directional search information are used to indicate different search platforms; The method further comprises: Summarize and process the search results of each search platform through AI functions; Output summarizes the processing results.

7. A search device, characterized in that: The device comprises: A receiving module, configured to receive search information; wherein the search information includes search text and directional search information, and the directional search information includes at least one of the following: a directional search symbol and a directional search identifier; The search module is used to search the search text according to the directional search information to obtain search results.

8. The device according to claim 7, characterized in that The receiving module comprises: A receiving submodule, configured to receive a first input to the AI ​​interaction interface; a determination submodule, configured to determine the search information in response to the first input; The device also includes: A display module is used to display the search results on the AI ​​interaction interface.

9. An electronic device, characterized in that: The electronic device comprises a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the search method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the search method according to any one of claims 1 to 6 are implemented.

Images