Searching method and device, equipment, medium, program product and intelligent agent

Abstract

The invention provides a search method and device, equipment, a medium, a program product and an intelligent agent, and relates to the field of artificial intelligence, in particular to the fields of large models, man-machine interaction and intelligent search. The search method comprises the following steps: for each search intention in at least one search intention determined according to search input information, determining a target operation interface for the search intention from an operation area for the search intention; wherein the operation area comprises a plurality of operation interfaces aiming at the search intention; based on the search input information and the target operation interface, generating at least one of a jump parameter and a search parameter for the target operation interface, and obtaining search information for the search intention; wherein the jump parameter is used for jumping to the target operation interface, and the search parameter represents a search operation needing to be executed in the target operation interface; and executing at least one of page jump operation and content search operation based on the search information to obtain a search result.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to technical fields such as large models, human-computer interaction, and intelligent search, and specifically to a search method, device, equipment, medium, program product, and intelligent agent. Background Art

[0002] With the development of computer technology and network technology, computer systems can interact with users. For example, a business platform can interact with users through a graphical user interface (GUI), providing a variety of business functions to meet the diverse needs of users. Summary of the invention

[0003] The present disclosure provides a search method, device, electronic device, storage medium, program product and intelligent agent.

[0004] According to one aspect of the present disclosure, a search method is provided, comprising: for each search intent among at least one search intent determined according to search input information, determining a target operation interface for the search intent from an operation area for the search intent; wherein the operation area includes multiple operation interfaces for the search intent; based on the search input information and the target operation interface, generating at least one of a jump parameter and a search parameter for the target operation interface to obtain search information for the search intent; wherein the jump parameter is used to jump to the target operation interface, and the search parameter represents a search operation that needs to be performed in the target operation interface; and performing at least one of a page jump operation and a content search operation based on the search information to obtain search results.

[0005] According to another aspect of the present disclosure, a search device is provided, including: a target operation interface determination module, used to determine, for each search intent of at least one search intent determined according to search input information, a target operation interface for the search intent from an operation area for the search intent; wherein the operation area includes multiple operation interfaces for the search intent; a search information determination module, used to generate at least one of a jump parameter and a search parameter for the target operation interface based on the search input information and the target operation interface, to obtain search information for the search intent; wherein the jump parameter is used to jump to the target operation interface, and the search parameter represents the search operation that needs to be performed in the target operation interface; and a search result determination module, used to perform at least one of a page jump operation and a content search operation based on the search information, to obtain search results.

[0006] According to another aspect of the present disclosure, an artificial intelligence agent is provided, which is configured to execute the method provided by the embodiment of the present disclosure.

[0007] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method of the present disclosure.

[0008] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method of the present disclosure.

[0009] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program is stored on at least one of a readable storage medium and an electronic device, and the computer program implements the method of the present disclosure when executed by a processor.

[0010] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0012] Figure 1 An exemplary system architecture to which the search method and device according to an embodiment of the present disclosure can be applied is schematically shown;

[0013] Figure 2 A flowchart of a search method according to an embodiment of the present disclosure is schematically shown;

[0014] Figure 3 The search process according to one embodiment of the present disclosure is schematically shown;

[0015] Figure 4 Schematically illustrates a search process according to another embodiment of the present disclosure;

[0016] Figure 5 A schematic diagram of a search method according to an embodiment of the present disclosure is shown;

[0017] Figure 6 A schematic diagram of a search method according to an embodiment of the present disclosure is exemplarily shown;

[0018] Figure 7 A block diagram schematically shows a content processing device according to an embodiment of the present disclosure;

[0019] Figure 8A block diagram schematically shows a structure of an artificial intelligence agent according to an embodiment of the present disclosure; and

[0020] Fig. 9 A block diagram of an electronic device suitable for implementing a content processing method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0021] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0022] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision, disclosure and application of user personal information involved comply with the provisions of relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good morals.

[0023] In the technical solution of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0024] With the development of computer technology and network technology, users can perform a series of operations on the current interface to achieve various business functions based on the target operation interface. However, the inventors found that when business functions are rich, diverse and increasingly complex, it is difficult for users to know how to enter the target operation interface through a series of related operations on the current interface.

[0025] The disclosed embodiments provide a search method, device, electronic device, storage medium, program product and intelligent agent. The search method includes: for each search intent among at least one search intent determined according to search input information, determining a target operation interface for the search intent from an operation area for the search intent; wherein the operation area includes multiple operation interfaces for the search intent; based on the search input information and the target operation interface, generating at least one of a jump parameter and a search parameter for the target operation interface, and obtaining search information for the search intent; wherein the jump parameter is used to jump to the target operation interface, and the search parameter represents the search operation that needs to be performed on the target operation interface; and performing at least one of a page jump operation and a content search operation based on the search information, and obtaining search results.

[0026] According to an embodiment of the present disclosure, by determining the search intent based on the search input information, and determining the target operation interface from the operation interface set based on the search intent, and generating jump parameters and / or search parameters for the target operation interface, operations such as page jump and / or content search can be performed according to the jump parameters and / or search parameters, thereby achieving the purpose of directly jumping to the specified operation interface or obtaining specified information based on the search input information. The interaction method based on the search intent can effectively streamline the user's operation process and improve search efficiency and user experience.

[0027] Figure 1 An exemplary system architecture to which the search method and apparatus according to an embodiment of the present disclosure can be applied is schematically shown.

[0028] It should be noted that Figure 1 The examples shown are only examples of system architectures to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios. For example, in another embodiment, the exemplary system architecture to which the search method and apparatus can be applied may include a terminal device, but the terminal device may implement the search method and apparatus provided by the embodiments of the present disclosure without interacting with the server.

[0029] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0030] The user may use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as knowledge reading applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software, etc. (only as examples).

[0031] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0032] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for the content browsed by the user using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0033] The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server can also be a server of a distributed system, or a server combined with blockchain.

[0034] It should be noted that the search method provided in the embodiment of the present disclosure can generally be executed by the first terminal device 101, the second terminal device 102 or the third terminal device 103. Accordingly, the search device provided in the embodiment of the present disclosure can also be set in the first terminal device 101, the second terminal device 102 or the third terminal device 103.

[0035] Alternatively, the search method provided in the embodiment of the present disclosure may also be generally performed by the server 105. Accordingly, the search device provided in the embodiment of the present disclosure may generally be arranged in the server 105. The search method provided in the embodiment of the present disclosure may also be performed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the search device provided in the embodiment of the present disclosure may also be arranged in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0036] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0037] Figure 2 The flowchart of the search method according to the embodiment of the present disclosure is schematically shown.

[0038] like Figure 2 As shown, the search method 200 includes operations S210 to S230.

[0039] In operation S210, for each search intent among at least one search intent determined according to the search input information, a target operation interface for the search intent is determined from an operation area for the search intent; wherein the operation area includes multiple operation interfaces for the search intent.

[0040] In operation S220, based on the search input information and the target operation interface, at least one of a jump parameter and a search parameter for the target operation interface is generated to obtain search information for the search intent; wherein the jump parameter is used to jump to the target operation interface, and the search parameter represents the search operation that needs to be performed on the target operation interface.

[0041] In operation S230, at least one of a page jump operation and a content search operation is performed based on the search information to obtain search results.

[0042] According to an embodiment of the present disclosure, the search input information may represent the user's search intention. The form of the search input information may include text, voice, gesture, etc.

[0043] Exemplarily, the search input information may include text information in a natural language format input by the user. For example, the search input information may be "show my schedule", "create a marketing plan for maternal and infant products", "query the sales of product A last month", etc. As an example, the search input information may be processed based on a large model to determine the search intent.

[0044] According to an embodiment of the present disclosure, the search intent may represent the target operation that the user wants to perform. For example, the target operation that the user wants to perform may include querying information, executing tasks, managing data, and the like.

[0045] According to an embodiment of the present disclosure, a target operation interface may be used to perform a target operation. For example, for an information query operation, the target operation interface may include a graphical user interface that displays specified information. For example, for an execution task operation, the target operation interface may include a graphical user interface that enables the execution of a specified task. For example, for a data management operation, the target operation interface may include a graphical user interface that enables the addition, modification, and deletion of data. Exemplarily, the target operation interface may be the same as the current operation page, or the target operation interface may be different from the current operation page.

[0046] According to an embodiment of the present disclosure, the operation area may include the entire or partial area in the graphical user interface. Exemplarily, the operation area may be defined according to position, function, etc. For example, the operation area may include a top area, a bottom area, a left area, a right area, a central area, etc. For example, the operation area may include an information input area, a navigation bar area, a function menu area, an information display area, etc.

[0047] According to an embodiment of the present disclosure, the operation area may include multiple operation interfaces for the search intention. Exemplarily, the operation interface may correspond to a specific operation.

[0048] For example, the search intent may include query information, the operation area for the query information may include an information display area, and the information display area may include multiple operation interfaces for the query information. For example, the multiple operation interfaces for the query information may include a report display interface, a chart display interface, a generated information display interface, a media information display interface, etc.

[0049] According to an embodiment of the present disclosure, an operation area may be preset for a search intent. For example, a target operation for each search intent may be preset, and an operation area for the search intent may be determined based on at least one operation interface corresponding to the target operation. Optionally, the operation area may be determined by artificial definition or by clustering at least one operation interface corresponding to the target operation.

[0050] According to one embodiment of the present disclosure, an operation area may be associated with multiple search intents, and the operation area may include at least one operation interface for each search intent. For example, an information display area may be associated with search intents such as query information and data management, and the information display area may include at least one operation interface for each search intent such as query information and data management. At least one operation interface for query information may be determined from the information display area based on the search intent of the query information.

[0051] According to an embodiment of the present disclosure, the search information may be used to perform a target operation, and the search information may include at least one of a jump parameter and a search parameter. For example, the computer system may jump to a target operation interface based on the jump parameter. For example, the computer system may perform a search operation on the target operation interface based on the search parameter.

[0052] According to an embodiment of the present disclosure, the search results may include, for example, a target operation interface, text information, chart data, reports, media information, etc., targeted at the search intent.

[0053] As an example, based on the search input information and the target operation interface, a jump parameter for the target operation interface can be generated to obtain the search information. A page jump operation can be performed based on the search information to obtain search results. For example, based on "show my schedule" and the schedule view interface, a jump parameter can be generated to directly jump to the schedule view interface.

[0054] As another example, based on the search input information and the target operation interface, a search parameter for the target operation interface can be generated to obtain search information. A content search operation can be performed based on the search information to obtain search results. For example, based on "query the sales of product A last month" and the current operation page, a search parameter can be generated to directly obtain the relevant data of the sales of product A last month.

[0055] As another example, based on the search input information and the target operation interface, a jump parameter and a search parameter for the target operation interface can be generated to obtain the search information. Based on the search information, a page jump and a content search operation can be performed to obtain search results. For example, based on "create a marketing plan for maternal and infant products" and a marketing plan creation interface, a jump parameter and a search parameter can be generated to directly jump to the marketing plan creation interface and select the product category filter item in the interface as maternal and infant products.

[0056] According to an embodiment of the present disclosure, by determining the search intent based on the search input information, and determining the target operation interface from the operation interface set based on the search intent, a jump parameter and at least one of the search parameters for the target operation interface are generated, and at least one of the page jump and content search operations can be executed according to at least one of the jump parameter and the search parameter, thereby achieving the purpose of directly jumping to the specified operation interface or obtaining specified information based on the search input information. The interaction method based on the search intent can effectively streamline the user's operation process and improve search efficiency and user experience.

[0057] According to an embodiment of the present disclosure, the operation area includes multiple functions for the search intent; determining the target operation interface for the operation intent includes: determining an operation sub-area corresponding to the intent type of the search intent from the operation area; determining a target function from the operation sub-area based on the search input information, wherein the target function represents a function used to realize the search intent; determining an interface that supports executing the target function based on the target function to obtain the target operation interface.

[0058] According to an embodiment of the present disclosure, the target function may represent a function related to realizing the search intention, and the target function may include, for example, a picture display function. An interface supporting execution of the target function may be determined based on the target function to obtain a target operation interface.

[0059] According to one embodiment of the present disclosure, the operation area for the search intent may include, for example, a media area. The media area may include, for example, a picture sub-area and a video sub-area. The intent type may be used to characterize the operation sub-area corresponding to the target operation, and may include, for example, a picture type and a video type. Exemplarily, a picture sub-area corresponding to a picture type may be determined from the media area.

[0060] According to an embodiment of the present disclosure, the media area may include, for example, a picture display function and a video display function for the search intent. For example, the picture display function for realizing the search intent may be determined from the picture sub-area according to the search input information. For example, an interface that can support the execution of the picture display function may be determined based on the picture display function, a target operation interface may be obtained, and a specified picture may be displayed.

[0061] According to an embodiment of the present disclosure, by presetting an operation area for search intent, the target function and the interface supporting the execution of the target function can be determined respectively from the operation area for the search intent according to the intent type search and input information to obtain the target operation interface. This can quickly and accurately achieve determination of the target operation interface based on the search intent, which is beneficial to improving search efficiency and the accuracy of search results, and helps to improve user experience.

[0062] According to an embodiment of the present disclosure, each function is configured with a function description vector, and the function description vector represents a vector generated according to the function description of the function; according to the search input information, determining the target function from the operation sub-area includes: vectorizing the search input information to obtain the input information vector; determining the function description vector in the operation sub-area that matches the input information vector to obtain the target function.

[0063] According to an embodiment of the present disclosure, a function description vector may be used to characterize a vector generated according to a function description for a function, and a function description vector may be configured for each function. For example, a function description vector may be used to describe the intent corresponding to the function, the operation required to implement the function, etc. Exemplarily, an operation sub-area may correspond to at least one function's respective function description vector.

[0064] According to an embodiment of the present disclosure, the search input information may be vectorized to obtain an input information vector. The input information vector may be matched with at least one function description vector corresponding to the operation sub-region to determine a function description vector matching the input information vector and obtain a target function.

[0065] According to an embodiment of the present disclosure, the vectorization processing of the search input information can be implemented by using any type of machine learning algorithm such as word embedding or bag-of-words model, and no specific limitation is made here.

[0066] According to an embodiment of the present disclosure, a function description vector matching the input information vector may be determined by calculating the similarity between the input information vector and at least one function description vector.

[0067] According to the embodiments of the present disclosure, the function description vector can convert the function description into a vector form for easy processing by the computer system. By determining the function description vector corresponding to the input information vector through vector matching, the target function can be determined quickly and accurately, which is beneficial to improving the search efficiency and the accuracy of the search results, and helps to improve the user experience.

[0068] According to an embodiment of the present disclosure, generating at least one of a jump parameter and a search parameter for a target function interface includes: matching prompt words for a target operation interface from a preset prompt word configuration file; optimizing prompt words with search input information to obtain target prompt words; inputting the target prompt words into a large model, and outputting at least one of a jump parameter and a search parameter.

[0069] According to the embodiments of the present disclosure, the large model may be a model with a large-scale parameter structure, and the parameter magnitude is generally in the tens of millions or hundreds of millions, and may reach the billions or tens of billions. In terms of the network structure of the large model, for example, a network structure such as UFO (Unified Feature Optimization) may be adopted. By processing the target prompt word through the large model, the relatively powerful feature understanding and expression capabilities of the large model can be brought into play, and the target prompt word can be efficiently processed, thereby improving the accuracy of the jump parameters and / or search parameters.

[0070] According to an embodiment of the present disclosure, a prompt word can be understood as text input to the big model in the big model, and the prompt word can guide the model to generate a specific output or perform a specific task. As an example, in natural language processing (NLP), a prompt word can be a question, the beginning of a sentence, an instruction, or any text that can stimulate the model to produce an expected response.

[0071] According to an embodiment of the present disclosure, a prompt word may be configured for each operation interface, and a preset prompt word configuration file may include a prompt word for each operation interface. Prompt words for a target operation interface may be matched from the preset prompt word configuration file. For example, a prompt word for a picture display interface may include "display a specified picture".

[0072] According to the disclosed embodiment, the prompt word can be optimized with the search input information to obtain the target prompt word. For example, the prompt word "show specified picture" can be optimized with the search input information "what is product A like" to obtain the target prompt word "show product A picture".

[0073] According to an embodiment of the present disclosure, the target prompt word can be input into the large model, and at least one of the jump parameter and the search parameter can be output. As an example, the target prompt word can be input into the large model, and the jump parameter can be output. As another example, the target prompt word can be input into the large model, and the search parameter can be output. As another example, the target prompt word can be input into the large model, and the jump parameter and the search parameter can be output.

[0074] According to an embodiment of the present disclosure, the jump parameter can be used to jump to the target operation interface, and the page jump operation can be performed based on the jump parameter. The search parameter can be used to characterize the search operation that needs to be performed in the target operation interface, and the content search operation can be performed based on the search parameter.

[0075] As just one example, the jump parameter and the search parameter may be passed via a URL (Uniform Resource Locator) or managed in other ways.

[0076] For example, for http: / / example.com / page?param1=value1¶m2=value2, param1 and param2 are the jump parameters.

[0077] For example, in http: / / example.com / page?search=books&sort=recent, search and sort are search parameters.

[0078] Figure 3 The search process according to one embodiment of the present disclosure is schematically illustrated.

[0079] According to one embodiment of the present disclosure, a search intent determined according to search input information may include one.

[0080] like Figure 3 As shown, the search intent 302 can be determined based on the search input information 301 .

[0081] Exemplarily, a target operation interface 304 for the search intent 302 can be determined from the operation area 303 for the search intent 302. At least one of a jump parameter 305 and a search parameter 306 for the target operation interface 304 can be generated based on the search input information 301 and the target operation interface 304, and search information 307 for the search intent 302 can be obtained. At least one of a page jump operation and a content search can be performed based on the search information 307 to obtain search results 308.

[0082] Figure 4The search process according to another embodiment of the present disclosure is schematically illustrated.

[0083] According to one embodiment of the present disclosure, the search intention determined according to the search input information may include multiple ones.

[0084] like Figure 4 As shown, the first search intent 402A and the second search intent 402B can be determined based on the search input information 401.

[0085] For example, a first target operation interface 404A for the first search intent 402A can be determined from a first operation area 403A for the first search intent 402A. Based on the search input information 401 and the first target operation interface 404A, at least one of a first jump parameter 405A and a first search parameter 406A for the first target operation interface 404A can be generated to obtain first search information 407A for the first search intent 402A.

[0086] For example, a second target operation interface 404B for the second search intent 402B can be determined from the second operation area 403B for the second search intent 402B. Based on the search input information 401 and the second target operation interface 404B, at least one of a second jump parameter 405B and a second search parameter 406B for the second target operation interface 404B can be generated to obtain second search information 407B for the second search intent 402B.

[0087] Exemplarily, comprehensive search information 408 may be determined based on first search information 407A and second search information 407B. Comprehensive search information 408 and execution order query information 409 may be sent to the current operation page to facilitate determining operation execution order 410. Based on operation execution order 410, at least one of page jump operation and content search may be performed based on comprehensive search information 408 to obtain first search result 411A for first search intent 402A and second search result 411B for second search intent 402B, respectively.

[0088] According to an embodiment of the present disclosure, when the search intention includes multiple items, by sending comprehensive search information and execution order inquiry information to the current operation page, it is convenient for users to confirm whether the operation is correct and the execution order of the operations, thereby improving the accuracy, security and user experience of executing the operation.

[0089] According to an embodiment of the present disclosure, the search method also includes: in response to receiving a search request, vectorizing the search input information in the search request to obtain an input information vector; inputting the input information vector into a pre-trained intent recognition model, and outputting at least one search intent.

[0090] According to an embodiment of the present disclosure, the search input information may include text information, and the vectorization processing of the search input information may be implemented by using any type of machine learning algorithm such as word embedding or bag-of-words model, which is not specifically limited here.

[0091] According to one embodiment of the present disclosure, the intent recognition model may include template matching based on preset rules, support vector machine algorithm, deep learning algorithm, large model, etc., which are not specifically limited here.

[0092] According to an embodiment of the present disclosure, by obtaining an input information vector based on search input information, the intent recognition model can more accurately determine the user intent, thereby improving the accuracy of the search intent.

[0093] According to an embodiment of the present disclosure, the intent recognition model includes at least one of the following: a structured model, a long short-term memory model, and a large model.

[0094] According to one embodiment of the present disclosure, the structured model may include, for example, a preset rule template, and at least one search intent may be determined based on the matching result between the input information vector and the rule template. The long short-term memory model may be trained based on historical data associated with the user, and the input information vector may be input into the long short-term memory model to obtain at least one search intent. The large model may include large-scale parameters and complex computing structures, and the input information vector may be input into the large model to obtain at least one search intent.

[0095] According to one embodiment of the present disclosure, the intent recognition model may include a structured model, a long short-term memory model, and a large model.

[0096] Exemplarily, the input information vector may be first input into the structured model for intent recognition. If the structured model does not output the search intent, the input information vector may be input into the long short-term memory model for intent recognition. If the long short-term memory model does not output the search intent, the input information vector may be input into the long short-term memory model for intent recognition.

[0097] According to the embodiments of the present disclosure, by performing intent recognition on the input information vector through a structured model, a long short-term memory model and a large model, it can be ensured that at least one search intent is obtained, thereby improving the robustness and accuracy of the intent recognition model.

[0098] Figure 5 The schematic diagram shows a principle diagram of a search method according to an embodiment of the present disclosure.

[0099] like Figure 5 As shown, the search method of the embodiment of the present disclosure can be implemented based on the intention recognition module and the operation execution module.

[0100] like Figure 5 As shown, in the intention recognition module, the search input information 501 can be vectorized to obtain an input information vector 502. The input information vector 502 can be input into an intention recognition model 503 to obtain at least one search intention 504. The intention recognition model 503 can include at least one of a structured model, a long short-term memory model, and a large model.

[0101] like Figure 5 As shown, in the operation execution module, for each search intent 504, an operation area 505 for the search intent 504 can be determined. From the operation area 505 for the search intent 504, a target operation interface 506 for the operation intent 504 can be determined. Based on the search input information and the prompt word for the target operation interface 506, a target prompt word 507 can be obtained. The target prompt word 507 can be input into the large model 508, and at least one of the jump parameter and the search parameter can be output to obtain search information 509. At least one of the page jump operation and the content search operation can be performed based on the search information 509 to obtain search results 510.

[0102] According to an embodiment of the present disclosure, the search request also includes page information of the current operation page, and the search method also includes: based on the page information, when it is determined that the current operation page does not belong to the operation area, generating jump confirmation information; before performing a page jump operation and a content search operation based on the search information, sending the jump confirmation information to the current operation page, so as to display the jump confirmation information on the current operation page.

[0103] According to an embodiment of the present disclosure, the page information may indicate whether the current operation page belongs to the operation area for the operation intention. For example, if it is determined that the current operation page does not belong to the operation area, a page jump operation needs to be performed to jump to the target operation interface.

[0104] As an example, when it is determined that the current operation page does not belong to the operation area, the jump confirmation information may be generated. The jump confirmation information may be sent to the current operation page so that the jump confirmation information is displayed on the current operation page.

[0105] Exemplarily, the jump confirmation information can be displayed to the user through a pop-up window, etc., for the user to confirm whether to perform the page jump operation. The user can choose "OK" to perform the page jump operation, or choose "Cancel" to stay on the current operation page.

[0106] According to an embodiment of the present disclosure, when it is determined that the current operation page does not belong to the operation area, by sending jump confirmation information to the current operation page, the user can confirm whether the jump operation is correct and whether to perform the jump operation, thereby improving the accuracy, security and user experience of the execution of the operation.

[0107] Figure 6 A schematic diagram of a search method according to an embodiment of the present disclosure is exemplarily shown.

[0108] like Figure 6 As shown, the search input information 601 may include "What is product A like?" The search intent and intent type 611 may be determined by performing intent recognition on the search input information 601. The search intent may include, for example, "query information" and the intent type may include, for example, picture type.

[0109] Exemplarily, the operation area for "query information" may include a media area 602. The media area may include, for example, a picture sub-area 603 and a video sub-area 604. For example, a picture sub-area 603 corresponding to the picture type may be determined from the media area 602 as an operation sub-area for the intent type according to the intent type. For example, a picture display function for realizing the search intent may be determined from the picture sub-area 603 according to the search intent. For example, an interface that can support the execution of the picture display function may be determined based on the picture display function, and the target operation interface 612 may include, for example, a picture display interface 605. Afterwards, a target prompt word 613 is generated according to the target operation interface 612 and the search input information 601.

[0110] Exemplarily, the target prompt word 613 may include, for example, "display specified pictures". For example, the prompt word "display specified pictures" may be optimized using the search input information "what is product A like" to obtain the target prompt word "display pictures of product A".

[0111] For example, the target prompt word "display product A pictures" can be input into the macro model to determine the jump parameter and the search parameter 614. The jump parameter can be used to jump from the current operation page to the picture display interface 605, and the search parameter can be used to query the pictures of product A. For example, the page jump operation and the content search operation can be performed to obtain the search results, that is, the picture of product A 606 is displayed based on the picture display interface 605. The picture display interface 605 can be different from the current operation page.

[0112] Figure 7 A block diagram of a search device according to an embodiment of the present disclosure is schematically shown.

[0113] like Figure 7As shown, the search device 700 may include a target operation interface determination module 710 , a search information determination module 720 and a search result determination module 730 .

[0114] The target operation interface determination module 710 is used to determine the target operation interface for each search intent among at least one search intent determined based on the search input information from the operation area for the search intent; wherein the operation area includes multiple operation interfaces for the search intent.

[0115] The search information determination module 720 is used to generate at least one of a jump parameter and a search parameter for a target operation interface based on the search input information and the target operation interface, and obtain search information for the search intent; wherein the jump parameter is used to jump to the target operation interface, and the search parameter represents the search operation that needs to be performed on the target operation interface.

[0116] The search result determination module 730 is used to perform at least one of a page jump operation and a content search operation based on the search information to obtain search results.

[0117] According to an embodiment of the present disclosure, the target operation interface determination module may include an operation sub-area determination sub-module, a target function determination sub-module and a target operation interface determination sub-module.

[0118] The operation sub-area determination submodule is used to determine the operation sub-area corresponding to the intention type of the search intention from the operation area.

[0119] The target function determination submodule is used to determine the target function from the operation sub-area according to the search input information, wherein the target function represents the function used to realize the search intention.

[0120] The target operation interface determination submodule is used to determine the interface supporting the execution of the target function based on the target function to obtain the target operation interface.

[0121] According to an embodiment of the present disclosure, the target function determination submodule may include an input information vector determination unit and a target function determination unit.

[0122] The input information vector determination unit is used to perform vectorization processing on the search input information to obtain the input information vector.

[0123] The target function determination unit is used to determine the function description vector in the operation sub-region that matches the input information vector to obtain the target function.

[0124] According to an embodiment of the present disclosure, the search result determination module may include a prompt word determination submodule, a target prompt word determination submodule and a search result determination submodule.

[0125] The prompt word determination submodule is used to match the prompt words for the target operation interface from the preset prompt word configuration file.

[0126] The target prompt word determination submodule is used to optimize the prompt word by using the search input information to obtain the target prompt word.

[0127] The search result determination submodule is used to input the target prompt word into the large model and output at least one of the jump parameter and the search parameter.

[0128] According to an embodiment of the present disclosure, the search device 700 may include a vectorization processing module and a search intent determination module.

[0129] The vectorization processing module is used to, in response to receiving a search request, perform vectorization processing on the search input information in the search request to obtain an input information vector.

[0130] The search intent determination module is used to input the input information vector into a pre-trained intent recognition model and output at least one search intent.

[0131] According to an embodiment of the present disclosure, the search device 700 may include a jump confirmation information generating module and a jump confirmation information sending module.

[0132] The jump confirmation information generating module is used to generate jump confirmation information based on the page information when it is determined that the current operation page does not belong to the operation area.

[0133] The jump confirmation information sending module is used to send jump confirmation information to the current operation page before executing the page jump operation and content search operation based on the search information, so as to display the jump confirmation information on the current operation page.

[0134] It should be noted that the search device part in the embodiment of the present disclosure corresponds to the search method part in the embodiment of the present disclosure. The description of the search device part specifically refers to the search method part and will not be repeated here.

[0135] An embodiment of the present disclosure also provides an AI (Artificial Intelligence) agent configured to execute the large model-based text processing method as described above.

[0136] Figure 8 The structural block diagram of an artificial intelligence agent according to an embodiment of the present disclosure is schematically shown.

[0137] In the embodiments of the present disclosure, inspired by the von Neumann structure in modern computer theory, such as Figure 8As shown, the AI ​​agent 800 may include five core modules: an input module 810 , a control module 820 , a storage module 830 , a calculation module 840 and an output module 850 .

[0138] The input module 810 is responsible for receiving or sensing information such as queries, requests, instructions, signals or data from the outside world (such as users or external environment), and converting them into a format that can be understood and processed by the AI ​​agent 800. The input module 810 is the primary link for the AI ​​agent 800 to interact with the outside world. It enables the AI ​​agent 800 to efficiently and accurately obtain the necessary "sensory" information from the outside world and respond to this information.

[0139] In an example, the input module 810 may input the search request described above.

[0140] In the example, the control module 820 is the core support for the AI ​​agent 800 to handle complex tasks. The control module 820 can execute the search method described above.

[0141] In the example, the control module 820 will continuously interact with the storage module 830, the computing module 840 and / or the output module 850 during operation. However, it should be noted that in the embodiment of the present disclosure, the control module 820 acts as a single initiator to initiate communication with the storage module 830, the computing module 840 and / or the output module 850, and there is no communication coupling between the storage module 830, the computing module 840 and the output module 850.

[0142] In the example, the performance of the control module 820 may be closely related to the large model on which the AI ​​agent 800 is based. In order to give full play to the capabilities of the large language model, the internal structure of the control module 820 may be designed to be highly configurable and scalable to cope with various types of tasks and requirements in real scenarios.

[0143] The storage module 830 may be responsible for memorizing information such as historical conversations, event streams, etc. The aforementioned operation area and preset prompt word configuration files may be included in the storage module 830 .

[0144] In the example, after the AI ​​agent 800 obtains the search request, the AI ​​agent 800 can determine the search intent for the search input information in the search request. The operation area can be stored in the storage module 830. The AI ​​agent 800 can determine the operation area for the search intent from the storage module 830 and feed it back to the control module 820. Then, the control module 820 can use the fed-back operation area to determine the target operation interface, can obtain search information based on the search input information and the target operation interface, can perform corresponding operations based on the search information to obtain search results, and pass the search results to the output module 850.

[0145] The operation module 840 can be regarded as a predefined tool library. An operator for determining the jump parameter and / or search parameter as described above can be included in the operation module 840 .

[0146] In the example, when the AI ​​agent 800 needs to determine the jump parameters and / or search parameters for the target operation interface, the relevant operator can be called from the operation module 840 and fed back to the control module 820. Then, the control module 820 can use the fed-back operator to generate the jump parameters and / or search parameters for the target operation interface, obtain the search information, perform corresponding operations according to the search information to obtain the search results, and pass the search results to the output module 850. It can be understood that although the large language model has excellent language understanding and generation capabilities, it is the same as a human being, without the help of any tools, the tasks that can be solved are very limited. When the AI ​​agent 800 is given the ability to call tools, it can achieve tasks such as completing mathematical operations with the help of a calculator, completing data analysis with the help of python, and completing weather forecasts with the help of a search engine.

[0147] In an example, the output module 850 may output the search results described above.

[0148] The AI ​​agent 800 according to the embodiment of the present disclosure can simply and effectively improve the level of intelligence, and improve flexibility and versatility.

[0149] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0150] According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method of the present disclosure.

[0151] According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute the method of the present disclosure.

[0152] According to an embodiment of the present disclosure, a computer program product includes a computer program, wherein the computer program is stored in at least one of a readable storage medium and an electronic device, and the computer program implements the method of the present disclosure when executed by a processor.

[0153] Fig. 9 A schematic block diagram of an example electronic device 900 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0154] like Fig. 9 As shown, the device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0155] A number of components in the device 900 are connected to an input / output (I / O) interface 905, including: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0156] The computing unit 901 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 901 performs the various methods and processes described above, such as the search method. For example, in some embodiments, the search method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the search method described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the search method in any other appropriate manner (e.g., by means of firmware).

[0157] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0158] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0159] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0160] To provide interaction with a user, the systems and techniques described herein 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 the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0161] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0162] A computer system may include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises through computer programs running on respective computers and having a client-server relationship to each other. The server may be a cloud server, a server in a distributed system, or a server combined with a blockchain.

[0163] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0164] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A search method, comprising: For each search intent among at least one search intent determined according to the search input information, determine a target operation interface for the search intent from an operation area for the search intent; wherein the operation area includes a plurality of operation interfaces for the search intent; Based on the search input information and the target operation interface, at least one of a jump parameter and a search parameter for the target operation interface is generated to obtain search information for the search intention; wherein the jump parameter is used to jump to the target operation interface, and the search parameter represents the search operation that needs to be performed on the target operation interface; and At least one of a page jump operation and a content search operation is performed based on the search information to obtain search results.

2. The method according to claim 1, wherein: The operation area includes a plurality of functions for the search intention; Determining a target operation interface for the operation intention includes: Determining, from the operation area, an operation sub-area corresponding to the intention type of the search intention; Determine a target function from the operation sub-area according to the search input information, wherein the target function represents a function used to realize the search intention; Based on the target function, an interface that supports execution of the target function is determined to obtain the target operation interface.

3. The method according to claim 2, wherein: Each of the functions is configured with a function description vector, wherein the function description vector represents a vector generated according to a function description for the function; Determining a target function from the operation sub-area according to the search input information includes: Performing vectorization processing on the search input information to obtain an input information vector; A function description vector in the operation sub-region that matches the input information vector is determined to obtain the target function.

4. The method according to any one of claims 1 to 3, wherein: The generating at least one of the jump parameter and the search parameter for the target function interface comprises: Matching prompt words for the target operation interface from a preset prompt word configuration file; Optimizing the prompt word by using the search input information to obtain a target prompt word; The target prompt word is input into the large model, and at least one of the jump parameter and the search parameter is output.

5. The method according to claim 1, further comprising: In response to receiving a search request, vectorizing the search input information in the search request to obtain an input information vector; The input information vector is input into a pre-trained intent recognition model, and at least one of the search intents is output.

6. The method according to claim 5, wherein: The search request also includes page information of the current operation page, and the method further includes: Based on the page information, if it is determined that the current operation page does not belong to the operation area, generating jump confirmation information; Before executing the page jump operation and the content search operation based on the search information, the jump confirmation information is sent to the current operation page, so as to display the jump confirmation information on the current operation page.

7. The method according to claim 6, wherein: The intention recognition model includes at least one of the following: a structured model, a long short-term memory model, and a large model.

8. A search device, comprising: A target operation interface determination module, for determining, for each search intent among at least one search intent determined according to the search input information, a target operation interface for the search intent from an operation area for the search intent; wherein the operation area includes a plurality of operation interfaces for the search intent; A search information determination module, configured to generate at least one of a jump parameter and a search parameter for the target operation interface based on the search input information and the target operation interface, and obtain search information for the search intention; wherein the jump parameter is used to jump to the target operation interface, and the search parameter represents a search operation that needs to be performed on the target operation interface; and The search result determination module is used to perform at least one of a page jump operation and a content search operation based on the search information to obtain search results.

9. The device according to claim 8, wherein: The operation area includes a plurality of functions for the search intention; The target operation interface determination module includes: An operation sub-region determining submodule, used to determine an operation sub-region corresponding to the intention type of the search intention from the operation region; A target function determination submodule, used to determine a target function from the operation subregion according to the search input information, wherein the target function represents a function used to realize the search intention; The target operation interface determination submodule is used to determine an interface that supports executing the target function based on the target function to obtain the target operation interface.

10. The device according to claim 9, wherein: Each of the functions is configured with a function description vector, wherein the function description vector represents a vector generated according to a function description for the function; The target function determination submodule includes: An input information vector determining unit, used for performing vectorization processing on the search input information to obtain an input information vector; The target function determination unit is used to determine a function description vector in the operation sub-area that matches the input information vector to obtain the target function.

11. The device according to any one of claims 8 to 10, wherein: The search result determination module comprises: A prompt word determination submodule, used to match prompt words for the target operation interface from a preset prompt word configuration file; A target prompt word determination submodule is used to optimize the prompt word by using the search input information to obtain a target prompt word; The search result determination submodule is used to input the target prompt word into the large model and output at least one of the jump parameter and the search parameter.

12. The apparatus according to claim 8, further comprising: A vectorization processing module, configured to, in response to receiving a search request, perform vectorization processing on search input information in the search request to obtain an input information vector; The search intention determination module is used to input the input information vector into a pre-trained intention recognition model and output at least one of the search intentions.

13. The device according to claim 12, wherein: The search request also includes page information of the current operation page, and the device also includes: A jump confirmation information generating module, configured to generate jump confirmation information based on the page information when it is determined that the current operation page does not belong to the operation area; The jump confirmation information sending module is used to send the jump confirmation information to the current operation page before executing the page jump operation and the content search operation based on the search information, so as to display the jump confirmation information on the current operation page.

14. An artificial intelligence agent, configured to execute the method according to any one of claims 1 to 7.

15. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

16. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.

17. A computer program product, comprising a computer program, wherein the computer program is stored on at least one of a readable storage medium and an electronic device, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images