Information processing method and device, equipment and storage medium

Abstract

The embodiment of the invention provides an information processing method and device, equipment and a storage medium. The method comprises the following steps: determining a target keyword from streaming content generated by a target application based on a target request; when the streaming content is displayed, determining a group of search results corresponding to the target keyword; and in response to the obtained group of search results, associating a target keyword in the displayed streaming content to a search interface, so that the target keyword can trigger access to the search interface, and the search interface is used for presenting the obtained group of search results. Based on the mode, according to the embodiment of the invention, the target keyword can be associated to the search interface, so that the target keyword can trigger to access the related search result, and the information transmission efficiency is effectively improved. Besides, the search result corresponding to the target keyword can be determined while the streaming content is displayed, so that the information search efficiency is effectively improved.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and particularly to information processing methods, devices, equipment, and computer-readable storage media. Background Art

[0002] With the development of computer technology, various forms of electronic devices can greatly enrich people's daily lives. For example, people can use electronic devices to conduct various interactions. For instance, users can input requests to electronic devices and then obtain response content generated by the electronic devices for the input requests, and so on. Summary of the Invention

[0003] In a first aspect of the present disclosure, an information processing method is provided. The method includes: determining a target keyword from the streaming content generated by a target application based on a target request; determining a set of search results corresponding to the target keyword while the streaming content is being displayed; and in response to obtaining a set of search results, associating the target keyword in the displayed streaming content with a search interface such that the target keyword can trigger access to the search interface, and the search interface is used to present the obtained set of search results.

[0004] In a second aspect of the present disclosure, an apparatus for information processing is provided. The apparatus includes: a first determination module configured to determine a target keyword from the streaming content generated by a target application based on a target request; a second determination module configured to determine a set of search results corresponding to the target keyword while the streaming content is being displayed; and an association module configured to, in response to obtaining a set of search results, associate the target keyword in the displayed streaming content with a search interface such that the target keyword can trigger access to the search interface, and the search interface is used to present the obtained set of search results.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. The instructions, when executed by the at least one processing unit, cause the device to execute the method of the first aspect.

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided. A computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0007] In a fifth aspect of the present disclosure, a computer program product is provided. The computer program product includes computer-executable instructions that, when executed by a processor, implement the method according to the first aspect of the present disclosure.

[0008] It should be understood that the content described in this content section is not intended to define the key features or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In conjunction with the accompanying drawings and with reference to the following detailed description, the above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent. In the drawings, the same or similar reference numerals denote the same or similar elements, where:

[0010] Figure 1 FIG. shows a schematic diagram of an exemplary environment in which embodiments of the present disclosure can be implemented;

[0011] Figure 2 FIG. shows a flowchart of a process of information processing according to some embodiments of the present disclosure;

[0012] Figures 3A - 3D FIG. shows a schematic diagram of an interface according to some embodiments of the present disclosure;

[0013] Figure 4 FIG. shows an exemplary flowchart of information processing according to some embodiments of the present disclosure;

[0014] Figure 5 FIG. shows a schematic structural block diagram of a device for information processing according to certain embodiments of the present disclosure;

[0015] Figure 6 FIG. shows a block diagram of an electronic device capable of implementing multiple embodiments of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not used to limit the scope of protection of the present disclosure.

[0017] It should be noted that the titles of any sections / subsections provided herein are not restrictive. Various embodiments are described throughout this document, and any type of embodiment can be included under any section / subsection. Additionally, the embodiments described in any section / subsection can be combined with any other embodiments described in the same section / subsection and / or different sections / subsections in any manner.

[0018] In the description of the embodiments of the present disclosure, the term "including" and its similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". There may also be other explicit and implicit definitions hereinafter. The terms "first", "second", etc. may refer to different or the same objects. There may also be other explicit and implicit definitions hereinafter.

[0019] In the embodiments of the present disclosure, it may involve the user's data, data acquisition and / or use, etc. These aspects all comply with the corresponding laws, regulations and related provisions. In the embodiments of the present disclosure, all data collection, acquisition, processing, processing, forwarding, use, etc. are carried out on the premise that the user is aware of and confirms. Accordingly, when implementing the embodiments of the present disclosure, the types, usage scopes, usage scenarios, etc. of the data or information that may be involved should be informed to the user and the user's authorization should be obtained through appropriate means according to relevant laws and regulations. The specific notification and / or authorization methods may vary according to the actual situation and application scenarios, and the scope of the present disclosure is not limited in this regard.

[0020] In the solutions of this specification and embodiments, if personal information processing is involved, it will be processed on the premise of having a legal basis (such as obtaining the consent of the personal information subject, or being necessary for performing a contract, etc.), and will only be processed within the specified or agreed scope. If the user refuses to process personal information other than the necessary information required for the basic functions, it will not affect the user's use of the basic functions.

[0021] The embodiments of the present disclosure propose a solution for information processing. According to this solution, determine a target keyword from the streaming content generated by a target application based on a target request; while the streaming content is being displayed, determine a set of search results corresponding to the target keyword; and in response to obtaining a set of search results, associate the target keyword in the displayed streaming content with a search interface, so that the target keyword can trigger an access to the search interface, and the search interface is used to present the obtained set of search results.

[0022] Based on such a method, the embodiments of the present disclosure can associate the target keyword with the search interface, so that the target keyword can trigger an access to relevant search results, effectively improving the information transmission efficiency. In addition, the present disclosure can determine the search results corresponding to the target keyword while the streaming content is being displayed, effectively improving the information search efficiency.

[0023] Example environment

[0024] Figure 1A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. As Figure 1 shown, the example environment 100 may include an electronic device 110.

[0025] In this example environment 100, the electronic device 110 may obtain streaming content generated by the target application 120 based on a target request. The target application 120 is an application that can support interface interaction. The target application 120 may be any suitable type of application for interface interaction, examples of which may include, but are not limited to: video applications, social applications, or other suitable applications.

[0026] In Figure 1 the environment 100, if the target application 120 is active, the target application 120 may provide a presentation interface 150 for the user 140. The user 140 may input a target request based on the interface 150.

[0027] In some embodiments, the target application 120 may be installed on any suitable device, such as on the electronic device 110 (not shown in the figure), or may also be installed on an electronic device 130 other than the electronic device 110, which will not be elaborated here.

[0028] The electronic device 110 and / or the electronic device 130 may be any type of mobile terminal, fixed terminal, or portable terminal, etc., devices with a display device, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, handheld computers, portable game terminals, VR / AR devices, Personal Communication System (PCS) devices, personal navigation devices, Personal Digital Assistant (PDA), audio / video players, digital cameras / cameras, positioning devices, television receivers, radio broadcast receivers, e-book devices, game devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. In some embodiments, the electronic device 110 and / or the electronic device 130 can also support any type of interface for the target user (such as a "wearable" circuit, etc.).

[0029] The electronic device 110 may also be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It may also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. The electronic device 110 may, for example, include a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and so on.

[0030] A communication connection may be established between the electronic device 130 and the electronic device 110. The communication connection may be established by wired or wireless means. The communication connection may include, but is not limited to, a Bluetooth connection, a mobile network connection, a Universal Serial Bus (USB) connection, a Wireless Fidelity (WiFi) connection, etc. Embodiments of the present disclosure are not limited in this regard. In embodiments of the present disclosure, other devices and the electronic device 110 may achieve signaling interaction through the communication connection therebetween.

[0031] It should be understood that the structures and functions of the various elements in the environment 100 are described only for exemplary purposes, without implying any limitation on the scope of the present disclosure.

[0032] Some exemplary embodiments of the present disclosure will be described below with continued reference to the drawings.

[0033] Example process

[0034] Figure 2 A flowchart of a process 200 for information processing according to some embodiments of the present disclosure is shown. The process 200 may be implemented at the electronic device 110. The following refers to Figure 1 Describe the process 200.

[0035] At block 210, the electronic device 110 determines a target keyword from the streaming content generated by the target application 120 based on the target request.

[0036] In some embodiments, the target application 120 may be any suitable type of application for interface interaction, examples of which may include, but are not limited to: a video application, a social application, or other suitable applications.

[0037] In some embodiments, the target request may be input by the user 140 based on the interface 150. At this time, the electronic device 130 may obtain the target request input by the user 140. The interface 150 may be any suitable application interface, such as an interaction interface between the user 140 and a virtual object.

[0038] For Figure 3AAs an example, the electronic device 130 may present an interaction interface 300A with a virtual object. The virtual object may refer to Figure 3A the "Virtual Object 1" shown. The electronic device 130 may provide an input control 301 in the interaction interface 300A. The user may input a target request through the input control 301, and thus interact with the virtual object 1.

[0039] In some embodiments, the target request may be any suitable type of request, such as at least one of text, image, and video, which will not be elaborated here.

[0040] Exemplarily, the input control 301 may include a text input component, a voice input component, and input components corresponding to images and / or videos. As an example, the user may input an image or a video by triggering the input control corresponding to the image and / or video in the interaction interface 300A. At this time, the electronic device 130 may obtain a target request of the image or video type. As another example, the user may input text by triggering the text input control in the interaction interface 300A. At this time, the electronic device 130 may obtain a target request of the text type. As another example, the user may input voice by triggering the voice input control in the interaction interface 300A. At this time, the electronic device may obtain a target request of the voice type.

[0041] Further, the electronic device 130 may identify the request type corresponding to the target request in response to obtaining the target request. The request type may be any suitable request, such as a request of the information retrieval type, a request of the business type, a request of the e-commerce type, a request of the life service type, etc., which will not be elaborated here. Specifically, the electronic device may use an agent to identify the request type corresponding to the target request.

[0042] In some embodiments, for efficient request processing, the target application may correspond to at least one agent. An agent is a system or software program that can perceive the environment and make decisions to achieve a specific goal. In some embodiments, taking the at least one agent as multiple agents as an example, each agent may process requests of at least one request type. For example, agent A may be used to process requests of the business type, and agent B may be used to process requests of the information retrieval type.

[0043] Further, the electronic device 130 may determine a target agent that matches the request type of the target request from the at least one agent based on the request type of the target request. Further, the electronic device 130 may use the target agent to obtain a reply content corresponding to the target request based on the target request. The reply content may be any suitable type of reply, such as at least one of text, image, and video, which will not be elaborated here.

[0044] To improve the interaction efficiency and reduce the waiting time of the user, in some embodiments, the electronic device 130 may utilize a target intelligent agent to generate response content in a streaming manner, that is, the electronic device 130 may utilize the target intelligent agent corresponding to the target application to generate streaming content. The streaming content represents that the response content is generated in a continuous and real-time manner, and it is part of the final response content generated for the target request. Taking the response content as text content as an example, the electronic device 130 can generate and output one character at a time by using the target intelligent agent corresponding to the target application.

[0045] In some embodiments, the electronic device 130 may display the generated streaming content on the application interface corresponding to the target application 120 in real time. For example, the electronic device 130 can present the streaming content one character at a time on the interaction interface between the user 140 and the virtual object.

[0046] In some embodiments, the electronic device 110 may obtain the streaming content sent by the electronic device 130. Further, the electronic device may determine a target keyword in the streaming content based on the streaming content. The target keyword may be a word or phrase in the streaming content that can express the core meaning, theme or concept. As an example, the target keyword may be a named entity corresponding to a preset type in the streaming content. A named entity is an entity with specific meanings and attributes, and this entity may be an object, concept or event in the real world, etc. The preset type may be any appropriate type, such as an e-commerce type, a life service type, etc. For example, the target named entity may be a product associated with e-commerce such as a mobile phone, a computer, a dish, etc. For another example, the target named entity may be a point of interest associated with life services such as a restaurant, a park, etc.

[0047] Specifically, the electronic device 110 may identify the target named entity included in the streaming content. The target named entity includes a named entity that matches the preset type. Further, the electronic device 110 may determine the target named entity as the target keyword.

[0048] When the request corresponds to some scenarios, it is impossible to find the corresponding search results based on the keywords included in the request under that scenario. For example, for the target request of "Please help me draw a picture", no search results can be found. To improve the efficiency of information processing and avoid performing the search process when no search results can be obtained, the electronic device 110 can determine whether the target request corresponds to a predetermined scenario to further determine whether subsequent operations of searching based on keywords are required. The predetermined scenario is a scenario where search results can be obtained, such as scenarios related to e-commerce, scenarios related to life services, and so on. For example, for the target request of "Please help me recommend a mobile phone worth about 3000 yuan", the electronic device 110 can search for which mobile phone models under which brands are mobile phones worth about 3000 yuan for the user 140, and so on.

[0049] To improve the efficiency of information processing, in some embodiments, when the electronic device 130 receives the target request input by the user, it can immediately send the target request to the electronic device 110, so that the electronic device 110 can, in response to obtaining the target request, determine whether the target request corresponds to a predetermined scenario by processing the target request.

[0050] In other embodiments, the electronic device 110 can, in response to the target request being processed by the target application, determine whether the target request corresponds to a predetermined scenario based on the reference information associated with the target application. The reference information can be any appropriate information that can assist the electronic device 110 in determining the scenario corresponding to the target request.

[0051] In some embodiments, the reference information can indicate the tool called by the agent in the target application to process the target request. The tool called by the agent to process the target request can be any appropriate type of tool, such as a database query tool, an interface call tool, a data analysis tool, and so on. It should be noted that for different tools, they may be associated with different scenarios. For example, for the e-commerce scenario, the data analysis tool can be associated with the e-commerce scenario, and it can be used to analyze the transaction situation corresponding to the product and the interaction information for the product, and so on. That is, the electronic device 110 can determine whether the target request corresponds to a predetermined scenario based on the relevance between the tool called by the agent in the target application to process the target request and each scenario.

[0052] In some embodiments, the reference information may further indicate the type of agent in the target application that processes the target request. The type of agent is associated with the type of request corresponding to the target request. For example, if the target request corresponds to a request type for information retrieval, the type of agent in the target application that processes the target request may also be an information retrieval type agent. As another example, if the type of agent that processes the target request is a drawing type agent, the target request does not correspond to a predetermined scenario. As another example, if the type of agent that processes the target request is a product recommendation type agent, the target request corresponds to a predetermined scenario.

[0053] In some other embodiments, the electronic device 110 may determine whether the target request corresponds to a predetermined scenario both by processing the target request and based on the reference information associated with the target application, that is, the electronic device 110 may comprehensively determine whether the target request corresponds to a predetermined scenario based on two methods.

[0054] Further, the electronic device 110 may, in response to the target request corresponding to a predetermined scenario, determine a target keyword from the streaming content generated by the target application. The electronic device 110 may, in response to the target request not corresponding to a predetermined scenario, not perform the steps after determining the target keyword from the streaming content generated by the target application, which may effectively reduce the workload corresponding to the electronic device 110.

[0055] To improve the efficiency of information processing, when the target application generates streaming content based on the target request and presents the streaming content on the application interface of the target application 120, the electronic device 110 may, in response to the target request corresponding to a predetermined scenario, copy the streaming content to construct an asynchronous content stream. Further, the electronic device may process the asynchronous content stream to determine the target keyword.

[0056] Based on such a method, the present disclosure can, while streaming and outputting the streaming content at the front end, construct an asynchronous content stream and simultaneously process the constructed asynchronous content stream, which can effectively improve the efficiency of information processing.

[0057] In block 220, the electronic device 110 determines a set of search results corresponding to the target keyword while the streaming content is being displayed.

[0058] In some embodiments, to improve the efficiency of interaction and reduce the user's waiting time for feedback, the streaming content can be streamed and displayed on the application interface as soon as it is generated. Specifically, the target keyword in the streaming content can be presented on the application interface in a first presentation style.

[0059] The process of determining a set of search results corresponding to the target keyword will be described below.

[0060] In some embodiments, the electronic device 110 may determine at least one search service corresponding to the type of the target keyword. The type of the target keyword may be any suitable type, such as an e-commerce type or a lifestyle service type, etc. The search service may also be any suitable type of search service, such as a search service corresponding to e-commerce or a search service corresponding to lifestyle services. For example, if the target keyword is "mobile phone", the type corresponding to the target keyword is the e-commerce type, and the corresponding search service is the search service corresponding to e-commerce.

[0061] Further, the electronic device 110 may use at least one search service to determine a set of search results corresponding to the target keyword. As an example, if the search service corresponding to the e-commerce for the type of the target keyword, the electronic device 110 may use the interface of the search service corresponding to e-commerce to determine a set of search results corresponding to the target keyword. As another example, if the search service corresponding to the lifestyle service for the type of the target keyword, the electronic device 110 may use the interface of the search service corresponding to the lifestyle service to determine a set of search results corresponding to the target keyword.

[0062] Since keywords are polysemous, the search results determined based on the keyword may include search results corresponding to at least two different types of objects. To improve the accuracy of determining the search results corresponding to the keyword, the electronic device 110 may further screen out the search results associated with the target request from the search results obtained based on the keyword itself based on some context information.

[0063] Specifically, the electronic device 110 may determine multiple candidate search results corresponding to the target keyword. As an example, these multiple candidate search results may be determined by using at least one search service.

[0064] Further, the electronic device 110 may determine the first context information associated with the target keyword and / or the second context information associated with the target request. In some embodiments, the first context information may be determined based on the target request, that is, the other information in the target request except the target keyword may be determined as the first context information. In some embodiments, the second context information is determined based on the historical interaction information associated with the target application. In some embodiments, the historical interaction information may be the historical requests input by the user 140 into the target application. In other embodiments, the historical interaction information may also be determined based on the historical interaction information during the interaction between the user 140 and the virtual object. The historical interaction information may include the historical information associated with the user 140 and may also include the historical information associated with the virtual object, etc.

[0065] Further, the electronic device 110 may determine a set of search results corresponding to the target keyword from multiple candidate search results based on the first context information and / or the second context information. For example, if the multiple candidate search results determined based on the target keyword include search results corresponding to objects of type 1 and also include search results corresponding to objects of type 2, and it is determined that the user 140 is involved in objects of type 1 during the historical interaction with the virtual object, the electronic device 110 may determine the search results corresponding to objects of type 1 among the multiple candidate search results as the set of search results corresponding to the final target keyword.

[0066] In block 230, in response to obtaining a set of search results, the electronic device 110 associates the target keyword in the displayed streaming content with the search interface, such that the target keyword can trigger access to the search interface, and the search interface is used to present the obtained set of search results.

[0067] In some embodiments, the electronic device 110 may send the link corresponding to the search interface to the electronic device 130, so that the electronic device 130 can associate the link with the target keyword in the streaming content, so as to implement the association of the target keyword in the streaming content with the search interface.

[0068] To improve the visibility of the target keyword and enhance the interaction reminder. In some embodiments, the electronic device 130 may also adjust the presentation style of the target keyword in the application interface in response to associating the target keyword in the streaming content with the search interface. For example, if the presentation style of the target keyword in the application interface is the first presentation style before associating the target keyword in the streaming content with the search interface, the electronic device may adjust the presentation style of the target keyword on the application interface to the second style in response to associating the target keyword in the streaming content with the search interface.

[0069] Take Figure 3A As an example, when the keyword 310 "Specialty 2" is not associated with the search interface, the electronic device 130 presents the keyword "Specialty 2" in the interaction interface in the first style. Take Figure 3B As an example, when the keyword 310 "Specialty 2" is associated with the search interface, the electronic device 130 presents the keyword "Specialty 2" in the interaction interface in the second style, and the second style may indicate that the user can jump to the search interface associated with "Specialty 2" by clicking on the keyword "Specialty 2".

[0070] In some embodiments, this set of search results corresponding to the target keyword can be associated with a set of objects, and the electronic device 130 can present a set of content items corresponding to this set of objects on the search interface. This set of objects are objects associated with the target keyword, and the corresponding object types can be the same or different. The object can be any appropriate object, such as mobile phone A, mobile phone B, mobile phone C, etc.

[0071] Take Figure 3C as an example. The user can click on the keyword 310 "Specialty 2" on the interface 300B. At this time, the electronic device 130 can respond to the selection of the keyword 310 "Specialty 2" and present an interface 300C as shown in Figure 3C Figure. Among them, a set of fruits (including pitayas, apples, and lychees) associated with "Specialty 2" can be presented on the interface 300C, and the electronic device can present the content item 320 corresponding to the pitaya, the content item 321 corresponding to the apple, and the content item 322 corresponding to the lychee, etc. on the interface 300C.

[0072] In some embodiments, the set of content items corresponding to the set of obtained objects presented in the search interface can correspond to a predetermined presentation order, where the presentation order can be determined based on the interaction information and / or description information corresponding to each object. The interaction information can be the evaluation information of the user on each object, the trading volume of each object, etc. The description information can be the attribute information corresponding to each object, such as the group purchase information that the store can provide, the location information of the store, etc. As an example, the content item corresponding to the object with a higher trading volume can be presented earlier in the search interface.

[0073] Furthermore, the electronic device 130 can respond to the selection of any one of the set of content items presented on the search interface (for example, the user can click on the image in a certain content item) and present an associated interface of the object corresponding to the content item. The associated interface can be any appropriate interface, such as an object details interface, an object purchase interface, etc., which will not be elaborated here.

[0074] In some embodiments, in addition to the interface provided by the target application 120, the associated interface can also be the interface provided by other applications other than the target application 120. To ensure the security of the user and improve the user experience, the electronic device 130 can respond to the selection of a certain content item in this set of content items and present a target prompt window in the search interface to prompt that it is about to jump or open other applications. In some embodiments, an authorization control and a non-authorization control can be presented in the target prompt window to support the user to choose whether to authorize to open other applications to present the associated interface of other applications.

[0075] Take Figure 3DAs an example, the electronic device 130 may present a target prompt window 330 in the interface 300D to prompt the user to confirm whether to allow jumping to another application for a commodity purchase operation. Further, the electronic device 130 may present a purchase interface corresponding to another application in response to the authorization control 311 being selected. Further, the electronic device 130 may present the interface 300C as shown in Figure 3C when the non-authorization control 312 is selected.

[0076] Figure 4 FIG. shows an example flowchart of information processing according to some embodiments of the present disclosure. Now, an explanation will be given with respect to Figure 4 wherein the marking system is the electronic device 110.

[0077] In block 401, the electronic device 130 obtains a target request based on an agent.

[0078] As an example, the user may input a target request based on an interaction interface presented by the target application 120 with a virtual object. At this time, the electronic device 130 uses the agent to obtain and process the target request. The interaction interface, as a bridge between the user and the agent, can transmit the target request input by the user and display the output of the agent.

[0079] As an example, the target request may be any appropriate type of request, such as at least one of text, image, and video, which will not be elaborated here.

[0080] In block 402, the marking system performs a preprocessing operation based on the target request to obtain first reference information.

[0081] To improve the efficiency of information processing, in some embodiments, after obtaining the target request, the electronic device 130 may send the target request to the marking system to perform a preprocessing operation on the target request through an asynchronous link. Further, the marking system may perform a preprocessing operation on the target request to obtain first reference information. In some embodiments, the first reference information may indicate whether the target request corresponds to an e-commerce scenario or a life service scenario. The first reference information may also indicate the search scope, search object, etc. corresponding to a subsequent search operation based on the target named entity in the target request.

[0082] As an example, if the target request is "Please find me a restaurant in City A", after the marking system performs a preprocessing operation on the target request, it may determine that the target request corresponds to a life service scenario, and when performing a subsequent search, it is necessary to search for restaurants in "City A".

[0083] To improve the efficiency of information processing, the operation of the marking system in block 402 may be synchronized with blocks 403 and 404 to generate streaming content corresponding to the target request.

[0084] In some embodiments, the result information indicating whether the target request in the first reference information corresponds to an e-commerce scenario or a life service scenario can be used as a reference for the subsequent marking system to determine whether to execute the processes of block 405 - block 408. Specifically, if the target request corresponds to an e-commerce scenario or a life service scenario, the marking system can determine to subsequently execute the processes of block 405 - block 408. If the target request does not correspond to an e-commerce scenario or a life service scenario, the marking system can determine not to execute the processes of block 405 - block 408 subsequently.

[0085] In block 403, the electronic device 130 identifies the processing type corresponding to the target request.

[0086] As an example, the processing type corresponding to the target request can be a business processing type, an information retrieval type, etc. The processing type corresponding to the target request may correspond to an e-commerce scenario or a life service scenario, or may not correspond to an e-commerce scenario or a life service scenario. The processing type corresponding to the target request can also be used as a reference for the subsequent marking system to determine whether to execute the processes of block 405 - block 408. Specifically, if the processing type corresponding to the target request corresponds to an e-commerce scenario or a life service scenario, the marking system can determine to subsequently execute the processes of block 405 - block 408. If the processing type corresponding to the target request does not correspond to an e-commerce scenario or a life service scenario, the marking system can determine not to execute the processes of block 405 - block 408 subsequently.

[0087] In block 404, the electronic device 130 generates streaming content corresponding to the target request based on the agent corresponding to the processing type.

[0088] To improve the efficiency of information processing, the target application 120 can correspond to multiple agents, and these multiple agents correspond to different types and can respectively process requests of different processing types.

[0089] As an example, if the processing type corresponding to the target request is a business processing type, the electronic device 130 can use a business agent to process the target request. As another example, if the processing type corresponding to the target request is an information retrieval type, the electronic device 130 can use an information retrieval agent to process the target request.

[0090] In some embodiments, the type of the agent is similar to the processing type corresponding to the target request, and it can also be used as a reference for the subsequent marking system to determine whether to execute the processes of block 405 - block 408.

[0091] Specifically, if the type of the agent processing the target request supports processing requests in the e-commerce scenario or the life service scenario, the tagging system may determine to execute the processes of block 405 - block 408 subsequently. If the type of the agent processing the target request does not support processing requests in the e-commerce scenario or the life service scenario, the tagging system may determine not to execute the processes of block 405 - block 408 subsequently.

[0092] In some embodiments, the agent may also call a predetermined tool to process the target request, and the tool can also correspond to multiple types, such as a database query tool, an interface call tool, a data analysis tool, etc. For different tools, they may be associated with different scenarios. For example, for the e-commerce scenario, the data analysis tool can be associated with the e-commerce scenario, and it can be used to analyze the transaction situation corresponding to the product and the interaction information for the product, etc.

[0093] As an example, the tool called by the agent to process the target request can also be used as reference information for the tagging system to subsequently determine whether to execute the processes of block 405 - block 408.

[0094] Specifically, if the tool called to process the target request is associated with the e-commerce scenario or the life service scenario, the tagging system may determine to execute the processes of block 405 - block 408 subsequently. If the tool called to process the target request is not associated with the e-commerce scenario or the life service scenario, the tagging system may determine not to execute the processes of block 405 - block 408 subsequently.

[0095] It should be noted that, in order to improve the efficiency of information processing, the tool called to process the target request and the type of the agent can be passed into the tagging system together with the generated streaming content.

[0096] In addition, after the streaming content is generated, it can be presented in real time in the interaction interface with the virtual object.

[0097] In block 405, the tagging system extracts named entities based on the named entity extraction model.

[0098] As an example, the tagging system can perform the named entity extraction operation shown in block 405 based on the reference information determined in block 402 and the reference information passed in by the agent.

[0099] As an example, the named entity extraction model can be any suitable machine learning model that can extract named entities. It can be deployed in the tagging system or in other devices.

[0100] As an example, the target named entities extracted are named entities corresponding to e-commerce or life services, such as commodities like mobile phones, computers, and dishes. For another example, the target named entities can be points of interest such as restaurants and parks.

[0101] In block 406, the tagging system performs entity search based on a scene-customized search strategy to obtain multiple candidate search results.

[0102] In some embodiments, the tagging system can determine whether to perform information search based on an e-commerce search interface or a life service search interface based on the type corresponding to the named entity. Specifically, the tagging system can respond to the e-commerce type corresponding to the named entity and perform information search based on the e-commerce search interface to obtain multiple candidate search results. Specifically, the tagging system can also respond to the life service type corresponding to the named entity and perform information search based on the life service search interface to obtain multiple candidate search results.

[0103] It should be noted that when obtaining these multiple candidate search results, the tagging system can perform the search based on reference information such as the search object and / or search scope determined in block 402.

[0104] In block 407, the tagging system performs accuracy matching to filter out some candidate search results whose accuracy meets a predetermined condition from the multiple candidate search results determined in block 406.

[0105] As an example, the tagging system can determine some candidate search results whose accuracy meets a predetermined condition among the multiple candidate search results based on the context information corresponding to the named entity (such as other information in the target request except the identified named entity) and / or the context information associated with the target request, such as the historical interaction information presented in the interaction interface between the user and the virtual object.

[0106] For example, if the multiple candidate search results determined based on the target named entity include search results corresponding to objects of type 1 and also include search results corresponding to objects of type 2, and the electronic device can determine that user 140 is involved in objects of type 1 during the historical interaction with the virtual object, the electronic device can determine the search results corresponding to objects of type 1 among the multiple candidate search results as the filtered-out part of the candidate search results.

[0107] In block 408, the tagging system performs personalized recommendation to determine a set of search results that meet the personalized requirements from the part of the candidate search results determined in block 407.

[0108] As an example, the tagging system can determine the target intent corresponding to user 140 based on historical interaction information associated with the target application. For example, if user 140 enters information associated with outdoor activities in the historical interaction information, and the currently identified target named entity based on the target request is a down jacket, the tagging system can determine the search results corresponding to the down jackets with good warmth retention in this part of the candidate search results as the search results meeting the personalized requirements.

[0109] As another example, the tagging system can use the portrait information corresponding to user 140 to determine the target intent corresponding to user 140. For example, if the portrait information corresponding to user 140 is pursuing fashion, and the currently identified target named entity based on the target request is a down jacket, the tagging system can determine the search results corresponding to the fashionable down jackets in this part of the candidate search results as the search results meeting the personalized requirements.

[0110] In some embodiments, the tagging system can send the entity link information of the search interface corresponding to a set of search results meeting the personalized requirements determined by frame 408 to electronic device 130. Further, electronic device 130 can key the entity link information to the named entities in the streaming content presented on the interaction interface with the virtual object, so that the user can jump to the search interface by clicking on the target named entity, etc. The search interface can present a set of content items, each content item corresponding to an object such as a commodity or a point of interest that meets the e-commerce or life service scenario, and each object is associated with this set of search results meeting the personalized requirements.

[0111] Based on such a method, the embodiments of the present disclosure can associate the target keyword with the search interface, so that the target keyword can trigger the access to relevant search results, effectively improving the information transmission efficiency. In addition, the present disclosure can determine the search results corresponding to the target keyword while displaying the streaming content, effectively improving the information search efficiency.

[0112] Example device and equipment

[0113] The embodiments of the present disclosure also provide corresponding devices for implementing the above methods or processes. Figure 5 The schematic structural block diagram of device 500 for information processing according to some embodiments of the present disclosure is shown. Device 500 can be implemented as or included in electronic device 110 as discussed above. Each module / component in device 500 can be implemented by hardware, software, firmware, or any combination thereof.

[0114] As Figure 5As shown, the apparatus 500 includes a first determination module 510 configured to determine a target keyword from the streaming content generated by a target application based on a target request; a second determination module 520 configured to determine a set of search results corresponding to the target keyword while the streaming content is being displayed; and an association module 530 configured to, in response to obtaining a set of search results, associate the target keyword in the displayed streaming content with a search interface such that the target keyword can trigger access to the search interface, which is used to present the obtained set of search results.

[0115] In some embodiments, the first determination module 510 is further configured to: determine whether the target request corresponds to a predetermined scenario; and in response to the target request corresponding to the predetermined scenario, determine a target keyword from the streaming content generated by the target application.

[0116] In some embodiments, the first determination module 510 is further configured to: in response to the target request corresponding to the predetermined scenario, construct an asynchronous content stream by copying the streaming content; and process the asynchronous content stream to determine the target keyword.

[0117] In some embodiments, the first determination module 510 is further configured to: in response to obtaining the target request, determine whether the target request corresponds to a predetermined scenario by processing the target request; and / or in response to the target request being processed by the target application, determine whether the target request corresponds to a predetermined scenario based on reference information associated with the target application.

[0118] In some embodiments, the target application corresponds to at least one agent, and the reference information indicates at least one of the following: the tool called by the agent in the target application to process the target request; the type of the agent in the target application that processes the target request.

[0119] In some embodiments, the first determination module 510 is further configured to: identify a target named entity included in the streaming content to determine it as the target keyword, where the target named entity includes a named entity that matches a preset type.

[0120] In some embodiments, the second determination module 520 is further configured to: determine a plurality of candidate search results corresponding to the target keyword; determine first context information associated with the target keyword and / or second context information associated with the target request; and based on the first context information and / or the second context information, determine a set of search results corresponding to the target keyword from the plurality of candidate search results.

[0121] In some embodiments, wherein: the first context information is determined based on the target request; and / or the second context information is determined based on historical interaction information associated with the target application.

[0122] In some embodiments, the second determination module 520 is further configured to: determine at least one search service corresponding to the type of the target keyword; and utilize the at least one search service to determine a set of search results corresponding to the target keyword.

[0123] In some embodiments, the streaming content is configured to be presented in an application interface associated with the target application, and the application interface is further configured to: in response to associating the target keyword in the streaming content with a search interface, adjust the presentation style of the target keyword in the application interface.

[0124] In some embodiments, a set of search results is associated with a set of objects, and the search interface is configured to present a set of content items corresponding to the set of objects, and each content item is configured to jump to an associated interface of the corresponding object.

[0125] The units included in the apparatus 500 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units can be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to the machine-executable instructions, some or all of the units in the apparatus 500 can be implemented at least in part by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that can be used include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0126] Figure 6 The block diagram of an electronic device 600 in which one or more embodiments of the present disclosure can be implemented is shown. It should be understood that Figure 6 The electronic device 600 shown is merely exemplary and should not constitute any limitation to the functions and scopes of the embodiments described herein. Figure 6 The electronic device 600 shown can be used to implement Figure 1 The electronic device 110 shown.

[0127] As Figure 6 shown, the electronic device 600 is in the form of a general-purpose electronic device. The components of the electronic device 600 can include but are not limited to one or more processors or processing units 610, a memory 620, a storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. The processing unit 610 can be an actual or virtual processor and can execute various processes according to the programs stored in the memory 620. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing ability of the electronic device 600.

[0128] The electronic device 600 generally includes multiple computer storage media. Such media can be any accessible media that the electronic device 600 can access, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 620 can be a volatile memory (such as registers, caches, random access memory (RAM)), a non-volatile memory (such as read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 630 can be a removable or non-removable medium and can include machine-readable media, such as a flash drive, a magnetic disk, or any other medium that can be capable of storing information and / or data (such as training data for training) and can be accessed within the electronic device 600.

[0129] The electronic device 600 can further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in Figure 6 it, a disk drive for reading from or writing to a removable, non-volatile magnetic disk (such as a "floppy disk") and an optical disk drive for reading from or writing to a removable, non-volatile optical disk can be provided. In these cases, each drive can be connected to a bus (not shown) by one or more data media interfaces. The memory 620 can include a computer program product 625 having one or more program modules that are configured to perform the various methods or actions of the various embodiments of the present disclosure.

[0130] The communication unit 640 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 600 can be implemented by a single computing cluster or multiple computer machines that can communicate via a communication connection. Thus, the electronic device 600 can operate in a networked environment using a logical connection with one or more other servers, network personal computers (PCs), or another network node.

[0131] The input device 650 can be one or more input devices, such as a mouse, a keyboard, a trackball, etc. The output device 660 can be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 600 can also communicate with one or more external devices (not shown) as needed via the communication unit 640, such as a storage device, a display device, etc., communicate with one or more devices that enable a user to interact with the electronic device 600, or communicate with any device that enables the electronic device 600 to communicate with one or more other electronic devices (such as a network card, a modem, etc.). Such communication can be performed via an input / output (I / O) interface (not shown).

[0132] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, and the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, the computer program product being tangibly stored on a non-transitory computer-readable medium and including computer-executable instructions, and the computer-executable instructions being executed by a processor to implement the method described above.

[0133] Aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0134] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is produced that implements the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause a computer, a programmable data processing device, and / or other devices to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured article that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0135] The computer-readable program instructions can be loaded onto a computer, other programmable data processing device, or other device, so that a series of operation steps are executed on the computer, other programmable data processing device, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing device, or other device implement the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0136] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various implementations of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or by a combination of dedicated hardware and computer instructions.

[0137] The various implementations of the present disclosure have been described above. The above description is exemplary, not exhaustive, and is not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The choice of terms used herein is intended to best explain the principles of the implementations, the practical application, or the improvement of technologies in the market, or to enable other ordinary skill in the art to understand the various implementation manners disclosed herein.

Claims

1. An information processing method, comprising: determining a target keyword from streaming content generated by a target application based on a target request; While the streaming content is being displayed, determining a set of search results corresponding to the target keyword; as well as In response to obtaining the set of search results, the target keyword in the displayed streaming content is associated with a search interface so that the target keyword can trigger access to the search interface, which is used to present the obtained set of search results.

2. The method according to claim 1, wherein determining the target keyword from the streaming content generated by the target application based on the target request comprises: determining whether the target request corresponds to a predetermined scenario; as well as In response to the target request corresponding to the predetermined scenario, the target keyword is determined from the streaming content generated by the target application.

3. The method according to claim 2, wherein in response to the target request corresponding to the predetermined scenario, determining the target keyword from the streaming content generated by the target application comprises: In response to the target request corresponding to the predetermined scenario, the streaming content is copied to construct an asynchronous content stream; as well as The asynchronous content stream is processed to determine the target keyword.

4. The method according to claim 2, wherein determining whether the target request corresponds to a predetermined scenario comprises: In response to acquiring the target request, determining whether the target request corresponds to the predetermined scenario by processing the target request; and / or In response to the target request being processed by the target application, it is determined whether the target request corresponds to the predetermined scenario based on reference information associated with the target application.

5. The method according to claim 4, wherein the target application corresponds to at least one agent, and the reference information indicates at least one of the following: The agent in the target application processes the tool invoked by the target request; The type of agent in the target application that processes the target request.

6. The method according to claim 1, wherein determining the target keyword from the streaming content generated by the target application based on the target request comprises: A target named entity included in the streaming content is identified to be the target keyword, wherein the target named entity includes a named entity matching a preset type.

7. The method of claim 1, wherein determining a set of search results corresponding to the target keyword comprises: Determine a plurality of candidate search results corresponding to the target keyword; Determining first context information associated with the target keyword and / or second context information associated with the target request; as well as Based on the first context information and / or the second context information, the group of search results corresponding to the target keyword is determined from the multiple candidate search results.

8. The method according to claim 7, wherein: The first context information is determined based on the target request; and / or The second context information is determined based on historical interaction information associated with the target application.

9. The method of claim 1, wherein determining a set of search results corresponding to the target keyword comprises: determining at least one search service corresponding to the type of the target keyword; as well as The group of search results corresponding to the target keyword is determined by using the at least one search service.

10. The method according to claim 1, wherein the streaming content is configured to be displayed in an application interface associated with the target application, and the application interface is further configured to: In response to associating the target keyword in the streaming content with the search interface, adjusting a presentation style of the target keyword in the application interface.

11. The method according to claim 1, wherein the set of search results is associated with a set of objects, and the search interface is configured to present a set of content items corresponding to the set of objects, and each content item is configured to jump to an associated interface of the corresponding object.

12. An apparatus for information processing, comprising: A first determination module is configured to determine a target keyword from streaming content generated by a target application based on a target request; a second determination module, configured to determine a set of search results corresponding to the target keyword while the streaming content is being displayed; as well as The association module is configured to, in response to obtaining the set of search results, associate the target keyword in the displayed streaming content with a search interface so that the target keyword can trigger access to the search interface, which is used to present the obtained set of search results.

13. An electronic device, comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 11 when executed by the at least one processing unit.

14. A computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the method according to any one of claims 1 to 11 when executed by a processor.

15. A computer program product comprising computer executable instructions, wherein the computer executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 11.

Images