WO2025161306A1 - 互动信息展示方法、装置、设备及存储介质 - Google Patents

互动信息展示方法、装置、设备及存储介质

Info

Publication number
WO2025161306A1
WO2025161306A1 PCT/CN2024/108478 CN2024108478W WO2025161306A1 WO 2025161306 A1 WO2025161306 A1 WO 2025161306A1 CN 2024108478 W CN2024108478 W CN 2024108478W WO 2025161306 A1 WO2025161306 A1 WO 2025161306A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
interactive
search result
result information
text
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2024/108478
Other languages
English (en)
French (fr)
Inventor
惠浩
赵振宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Douyin Vision Co Ltd
Original Assignee
Douyin Vision Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Douyin Vision Co Ltd filed Critical Douyin Vision Co Ltd
Publication of WO2025161306A1 publication Critical patent/WO2025161306A1/zh
Anticipated expiration legal-status Critical
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/332—Query formulation
    • G06F16/3329—Natural language query formulation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/3332—Query translation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/338—Presentation of query results
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • G06N5/041—Abduction
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Definitions

  • the embodiments of the present disclosure relate to an interactive information display method, apparatus, device, and storage medium.
  • users can enter question text in the interactive interface of the artificial intelligence software.
  • the artificial intelligence software uses the model to obtain interactive response information corresponding to the question text and display the interactive response information in the interactive interface.
  • the inventors have discovered that the above situation has at least the following technical problems: when the question text entered by the user is unclear or less targeted, the interactive response information obtained through the question text often cannot answer the user's questions, resulting in a poor user experience.
  • Embodiments of the present disclosure provide an interactive information display method, apparatus, device, and storage medium.
  • the present disclosure provides an interactive information display method, including:
  • the search result information According to the second search result information that matches the first search result information and each second interactive information
  • the search result information generates interactive reply information, and the interactive reply information is displayed on the interactive interface.
  • the present disclosure also provides an interactive information display device, including:
  • a selection module configured to select, in response to first interaction information input by a user, a tool group corresponding to the first interaction information from a target plug-in;
  • a modification module configured to modify the first interaction information into at least one second interaction information based on a preset database associated with files uploaded by the user, using the tool group;
  • a determination module configured to determine first search result information matching the first interaction information and second search result information matching each second interaction information
  • a display module is used to generate interactive reply information based on the first search result information and the second search result information that matches each second interactive information, and to display the interactive reply information on an interactive interface.
  • the present disclosure also provides an electronic device, including:
  • processor and a memory communicatively connected to the processor
  • the memory stores computer-executable instructions
  • the processor executes the computer-executable instructions stored in the memory to implement the interactive information display method as described above.
  • An embodiment of the present disclosure further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions.
  • the interactive information display method described above is implemented.
  • An embodiment of the present disclosure further provides a computer program product, including a computer program, which implements the interactive information display method described above when executed by a processor.
  • FIG1 is a schematic diagram of an application scenario of an interactive information display method provided by some embodiments of the present disclosure.
  • FIG2 is a flow chart of an interactive information display method provided by some embodiments of the present disclosure.
  • FIG3 is a schematic diagram of an interactive information display method provided by some embodiments of the present disclosure.
  • FIG4 is a schematic diagram of an interactive information display method provided by some embodiments of the present disclosure.
  • FIG5 is a flow chart of an interactive information display method provided by some embodiments of the present disclosure.
  • FIG6 is a structural block diagram of an interactive information display device provided in some embodiments of the present disclosure.
  • FIG7 is a schematic diagram of the hardware structure of an electronic device provided in some embodiments of the present disclosure.
  • user information including but not limited to user device information, user personal information, etc.
  • data including but not limited to data used for analysis, stored data, displayed data, etc.
  • user information including but not limited to user device information, user personal information, etc.
  • data including but not limited to data used for analysis, stored data, displayed data, etc.
  • artificial intelligence software uses the model to obtain interactive response information corresponding to the question text and display the interactive response information in the interactive interface.
  • the inventors have discovered that the above situation has at least the following technical problems: when the question text entered by the user is unclear or less targeted, the interactive response information obtained through the question text often cannot answer the user's questions, resulting in a poor user experience.
  • this embodiment proposes the following technical concept: a target plug-in can be pre-installed.
  • the input question is rewritten by calling the target plug-in to improve the effectiveness of the question and then search for the content the user wants to see.
  • the specific steps may include: first, in response to the first interactive information input by the user, selecting a tool group corresponding to the first interactive information from the target plug-in. Then, based on the interaction information with the user, the tool group is used to select the tool group corresponding to the first interactive information.
  • the system searches a preset database associated with the uploaded file, modifies the first interactive information into at least one second interactive information, determines first search result information that matches the first interactive information, and second search result information that matches each second interactive information. Finally, it generates interactive response information based on the first search result information and each second search result information that matches the second interactive information, and displays the interactive response information on the interactive interface.
  • the user question can be rewritten according to the file uploaded by the user, which improves the effectiveness of the user question and searches for the content the user wants to see, thereby improving the user experience.
  • the interactive information display method provided by the embodiments of the present disclosure can be applied to application scenarios in which interactive information is displayed in various ways.
  • interactive information can be displayed through artificial intelligence software on a mobile terminal, or through an artificial intelligence web page on a computer terminal.
  • the artificial intelligence software can be AI smart assistant software.
  • Figure 1 is a schematic diagram of the application scenario of the interactive information display method provided by some embodiments of the present disclosure.
  • the user can input a question into the interactive interface of the artificial intelligence software or the artificial intelligence web page: How did XX's daughter die?
  • the question can be rewritten as: How did YY die?
  • the question input by the user and the search results of the rewritten question are used to improve the effectiveness of the user's question, so that the content that the user wants to see can be searched, thereby improving the user experience.
  • FIG2 is a flow chart of an interactive information display method provided by some embodiments of the present disclosure.
  • the interactive information display method is described as an example in which the execution subject is an electronic device. Referring to FIG2 , the method includes:
  • S201 In response to first interaction information input by a user, select a tool group corresponding to the first interaction information from a target plug-in.
  • the first interactive information may be any type of information such as text information, image information, video information, etc.
  • the tool group corresponding to the first interaction information may include one or more tools.
  • the tool group includes a first target tool, a second target tool, and a third target tool. Accordingly, this step may include: in response to the first interaction information input by the user, selecting a target plug-in from the target plug-in. The first target tool, the second target tool, and the third target tool are taken and determined as a tool group corresponding to the first interaction information.
  • the first target tool is used to generate at least one search text information related to the first interactive information; the second target tool is used to obtain search result information matching the search text information from a preset database; and the third target tool is used to modify the first interactive information into the second interactive information based on the search result information.
  • the first target tool is: a tool for asking questions based on interactive information.
  • the first target tool can be expressed as: ask_question_for_query.
  • the second target tool is: a question answering tool.
  • the second target tool can be expressed as: ask_document.
  • the third target tool is: a question rewriting tool.
  • the third target tool can be expressed as: rewrite_query.
  • S202 Using a tool group, based on a preset database associated with the file uploaded by the user, modify the first interaction information into at least one second interaction information.
  • search text information is first generated based on the first interactive information, and search result information matching the search text information is obtained from a preset database based on the search text information. Then, the first interactive information is adjusted based on the search result information. Accordingly, this step can include the following steps (1) to (3):
  • a new question may be generated through a question generation model.
  • this step may include: invoking the question generation model through the first target tool, obtaining multiple preset search texts through the question generation model; for each preset search text, selecting a target keyword from the multiple keywords included in the first interactive information; and adding the target keyword to a preset position of the preset search text to generate search text information including the target keyword.
  • the first interactive message is: "How did XX's daughter die?”
  • a target keyword, "XX's daughter,” is selected from the multiple keywords included in the first interactive message.
  • the preset search text is: "Who is XX's daughter?"
  • the target keyword is added to a preset position in the preset search text (e.g., the position corresponding to XX's daughter), generating the search text information including the target keyword: "Who is XX's daughter?"
  • the second target tool obtains search result information matching the search text information from a preset database to obtain search result information corresponding to at least one search text information.
  • search result information can be obtained through vector similarity.
  • this step may include: performing vectorization processing on the search text information using a second target tool to obtain a first text vector; obtaining, from a preset database, at least one second text vector having a similarity with the first text vector greater than a first preset threshold value based on the first text vector; and determining the text information corresponding to the at least one second text vector as the search result information.
  • the preset database may be a knowledge base.
  • the preset database stores text vectors corresponding to a plurality of text information. Accordingly, obtaining, from the preset database using the first text vector, at least one second text vector having a similarity with the first text vector greater than a first preset threshold, includes: determining a file identifier corresponding to the first interactive information, and obtaining, from the plurality of text vectors corresponding to the file identifier, at least one second text vector having a similarity with the first text vector greater than the first preset threshold.
  • the first interactive message is: "How did XX's daughter die?”
  • the file identifier corresponding to the first interactive message is: "Novel XX.”
  • the search text is: "Who is XX's daughter?"
  • a second text vector is obtained from multiple text vectors corresponding to the novel XX.
  • the text information corresponding to the second text vector, "XX's daughter is YY,” is determined as the search result.
  • the first interactive information is modified into second interactive information according to the search result information by a third target tool to obtain at least one second interactive information.
  • the first interaction information can be modified into the second interaction information using a question modification model. Accordingly, this step is as follows: for each search result information, the question modification model is called by a third target tool, and the first interaction information is modified into the second interaction information using the question modification model, thereby obtaining at least one second interaction information.
  • the second interactive message combines the search results from the preset database with the first interactive message.
  • the first interactive message is: "How did XX's daughter die?"
  • the search results are: "XX's daughter is YY.”
  • the question modification model modifies the first interactive message to: "How did YY die?"
  • search text information is first generated based on the first interactive information, and search result information matching the search text information is obtained from a preset database based on the search text information, and then the first interactive information is adjusted based on the search result information; that is, the second interactive information integrates the search result information in the preset database and the first interactive information, thereby increasing the effectiveness of the second interactive information.
  • S203 Determine the first search result information that matches the first interactive information and each second interactive information. The information matches the second search result information.
  • the first search result information that matches the first interaction information and the second search result information that matches each second interaction information may be determined by a generative model such as a preset model.
  • the preset model can be a deep learning model trained on massive text data. It can not only generate natural language text, but also deeply understand the meaning of the text and handle various natural language tasks such as text summarization, question answering, and translation.
  • the first interactive information is: How did XX's daughter die?
  • the second interactive information is: How did YY die?
  • the first search result information that matches the first interactive information, as determined by the preset model, is: No relevant information was found.
  • the second search result information that matches the second interactive information, as determined by the preset model, is: YY died of complications during childbirth.
  • S204 Generate interactive reply information based on the first search result information and the second interactive information that matches each second interactive information, and display the interactive reply information on the interactive interface.
  • interactive reply information is generated based on the first search result information and the second search result information that matches each second interactive information, including: selecting search result information of the searched result from the second search result information that matches the first search result information and each second interactive information, and determining the search result information as interactive reply information.
  • the first search result is: No relevant information was found.
  • the second search result is: YY died of complications during childbirth.
  • the second search result, which has been found, is determined as the interactive reply, and the interactive reply is displayed on the interactive interface: YY died of complications during childbirth.
  • the number of second search result information is relatively large.
  • several search result information with similarity can be screened out from the multiple search result information, and then interactive reply information can be obtained based on the several search result information with similarity.
  • the interactive reply information is generated based on the second search result information that matches the first search result information and each second interactive information, including: selecting a preset number of target search result information from the second search result information that matches the first search result information and each second interactive information, wherein the similarity between the preset number of target search result information is greater than a second preset threshold; and generating interactive reply information based on the preset number of target search result information using a preset model.
  • the values of the preset number and the second preset threshold there is no specific limitation on the values of the preset number and the second preset threshold, and they can be set and modified as needed.
  • search result information with close similarity is convenient for improving the accuracy of the interactive reply information generated by the preset model, thereby further improving the user experience.
  • the disclosed embodiment provides a method for displaying interactive information: in response to first interactive information input by a user, selecting a tool group corresponding to the first interactive information from a target plug-in; modifying the first interactive information into at least one second interactive information through the tool group; determining first search result information that matches the first interactive information and second search result information that matches each second interactive information; generating interactive reply information based on the first search result information and the second search result information that matches each second interactive information, and displaying the interactive reply information on an interactive interface.
  • the user's question can be rewritten based on the file uploaded by the user, thereby improving the effectiveness of the user's question, thereby searching for the content the user wants to see, and thus improving the user experience.
  • the method in response to the first interactive information input by the user, before selecting the tool group corresponding to the first interactive information from the target plug-in, the method further includes:
  • S501 In response to receiving a request to upload a file, obtaining a file identifier of the file, and segmenting the file to obtain multiple sub-texts.
  • the file may be a text file, an image file, a video file, or other file related to the user's question.
  • the user's question i.e., the first interactive information
  • the file information may be the text information of the novel "XX.”
  • XX is a character in the novel "XX.”
  • the upload request may include a file and a file identifier.
  • the file may include multiple subtexts. Accordingly, the file information may be segmented into subtext units to obtain multiple subtexts.
  • the subtexts may include character text, word text, sentence text, paragraph text, etc.
  • the upload request includes a file and a file identifier "XX".
  • the file eg, the file of the novel "XX”
  • the file is segmented into sub-text units to obtain multiple sub-texts corresponding to the file of the novel "XX”.
  • S502 Perform vectorization processing on each subtext to obtain a subtext vector corresponding to each subtext.
  • AI Artificial Intelligence
  • the quantization interface performs vectorization on each subtext to obtain the subtext vector corresponding to each subtext.
  • the first character count of the subtext can also be limited.
  • the first character count of the subtext can be set to be less than a first preset value.
  • the value of the first preset value can be set and modified as needed. For example, the first preset value is 500.
  • the second character count of identical characters in the subtext can be limited.
  • the second character count of identical characters in the subtext can be set to be less than a second preset value.
  • the value of the second preset value can be set and modified as needed. For example, the second preset value is 50.
  • concurrent vectorization can be performed, i.e., multiple subtexts can be vectorized simultaneously.
  • the number of subtexts to be processed concurrently can be set and modified as needed. For example, the concurrency level is 10.
  • S503 Establish an association relationship between the file identifier, the subtext, and the subtext vector, and store the association relationship in a preset database.
  • the novel "XX” contains 3,000 subtexts. Each subtext in the novel "XX” is vectorized to obtain 3,000 subtext vectors. For each subtext, an association is established between the subtext, the subtext vector, and the file identifier "XX", and the association is stored in a preset database.
  • the files related to the first interactive information are uploaded to the preset database in advance, when the first interactive information is rewritten, the information in the related files can be called from the preset database, thereby improving the effectiveness of the rewritten second interactive information.
  • FIG6 is a structural block diagram of an interactive information display device provided by an embodiment of the present disclosure.
  • the device includes: a selection module 601 , a modification module 602 , a determination module 603 and a display module 604 .
  • a selection module 601 is configured to select a tool group corresponding to the first interaction information from a target plug-in in response to the first interaction information input by the user;
  • a modification module 602 for modifying the first interaction information into at least one second interaction information based on a preset database associated with the file uploaded by the user through a tool group;
  • a determination module 603 is configured to determine first search result information that matches the first interaction information and second search result information that matches each second interaction information;
  • the display module 604 is configured to generate interactive reply information based on the first search result information and the second interactive information that matches each second interactive information, and display the interactive reply information on the interactive interface.
  • the modification module 602 through the tool group, based on the preset database associated with the file uploaded by the user, modifies the first interactive information into at least one second interactive information, specifically including: generating at least one search text information related to the first interactive information through the first target tool; for each search text information, obtaining search result information matching the search text information from the preset database through the second target tool, and obtaining search result information corresponding to each of the at least one search text information; for each search result information, modifying the first interactive information into second interactive information according to the search result information through the third target tool, and obtaining at least one second interactive information.
  • the modification module 602 generates at least one search text information related to the first interactive information through a first target tool, specifically including: calling a question generation model through the first target tool, and obtaining multiple preset search texts through the question generation model; for each preset search text, selecting a target keyword from multiple keywords included in the first interactive information; adding the target keyword to a preset position of the preset search text, and generating search text information including the target keyword.
  • the modification module 602 obtains search result information matching the search text information from a preset database through the second target tool, specifically including: performing vectorization processing on the search text information through the second target tool to obtain a first text vector; obtaining, through the first text vector, at least one second text vector from a preset database whose similarity with the first text vector is greater than a first preset threshold; and determining the text information corresponding to the at least one second text vector as the search result information.
  • the modification module 602 modifies the first interaction information into second interaction information according to the search result information through the third target tool, and obtains at least one second interaction information, specifically including: for each search result information, calling the question modification model through the third target tool, and modifying the first interaction information into second interaction information according to the search result information through the question modification model, and obtaining at least one second interaction information.
  • the display module 604 generates an interactive search result based on the second search result information that matches the first search result information and each second interactive information.
  • the reply information specifically includes: selecting a preset number of target search result information from the second search result information that matches the first search result information and each second interactive information, wherein the similarity between the preset number of target search result information is greater than a second preset threshold; generating the interactive reply information according to the preset number of target search result information through a preset model.
  • the device also includes: an upload module, which is used to obtain a file identifier corresponding to the file in response to receiving an upload request for the file, and to segment the file to obtain multiple sub-texts; vectorize each sub-text to obtain a sub-text vector corresponding to each sub-text; establish an association relationship between the file identifier, sub-text and sub-text vector, and store the association relationship in a preset database.
  • an upload module which is used to obtain a file identifier corresponding to the file in response to receiving an upload request for the file, and to segment the file to obtain multiple sub-texts
  • vectorize each sub-text to obtain a sub-text vector corresponding to each sub-text
  • establish an association relationship between the file identifier, sub-text and sub-text vector and store the association relationship in a preset database.
  • the electronic device 700 may be a terminal device or a server.
  • the terminal device may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (Portable Android Devices, PADs), portable multimedia players (PMPs), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs and desktop computers.
  • PDAs personal digital assistants
  • PADs Portable Android Devices, PADs
  • PMPs portable multimedia players
  • vehicle-mounted terminals such as vehicle-mounted navigation terminals
  • fixed terminals such as digital TVs and desktop computers.
  • the electronic device shown in FIG7 is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.
  • electronic device 700 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 701, which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 702 or programs loaded from a storage device 708 into a random access memory (RAM) 703. Various programs and data required for the operation of electronic device 700 are also stored in RAM 703. Processing device 701, ROM 702, and RAM 703 are connected to each other via a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
  • a processing device e.g., a central processing unit, a graphics processing unit, etc.
  • I/O input/output
  • the following devices may be connected to the I/O interface 705: an input device 706 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 707 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 708 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 709.
  • the communication device 709 may allow the electronic device 700 to communicate with other devices wirelessly or by wire to exchange data.
  • FIG. 7 shows an electronic device 700 having various devices, it should be understood that not all devices are connected. It is required to implement or possess all the devices shown. More or fewer devices may alternatively be implemented or possessed.
  • an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart.
  • the computer program can be downloaded and installed from the network through the communication device 709, or installed from the storage device 708, or installed from the ROM 702.
  • the processing device 701 the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.
  • the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two.
  • a computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above.
  • Computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, 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 above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • the program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.
  • the computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.
  • the computer-readable medium carries one or more programs.
  • the electronic device executes the method shown in the above embodiment.
  • Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages.
  • the program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server.
  • the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).
  • LAN local area network
  • WAN wide area network
  • Internet service provider e.g., AT&T, MCI, Sprint, EarthLink, MSN, GTE, etc.
  • each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function.
  • the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved.
  • each box in the block diagram and/or flowchart, and the combination of the boxes in the block diagram and/or flowchart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments described in this disclosure may be implemented in software or hardware.
  • the name of a unit does not limit the unit itself.
  • the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses.”
  • exemplary types of hardware logic components include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.
  • FPGAs field programmable gate arrays
  • ASICs application specific integrated circuits
  • ASSPs application specific standard products
  • SOCs systems on chip
  • CPLDs complex programmable logic devices
  • a machine-readable medium may be a tangible medium that can contain or store information for use by or in conjunction with an instruction execution system, apparatus, or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • the machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing.
  • machine-readable storage media may include an electrical connection based on one or more wires, 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.
  • RAM random access memory
  • ROM read-only memory
  • EPROM or flash memory erasable programmable read-only memory
  • CD-ROM portable compact disk read-only memory
  • magnetic storage device or any suitable combination of the foregoing.
  • a method for displaying interactive information comprising:
  • the tool group modifies the first interactive information into at least one second interactive information based on a preset database associated with the file uploaded by the user, including: generating at least one search text information related to the first interactive information through the first target tool; for each search text information, obtaining search result information matching the search text information from the preset database through the second target tool, and obtaining search result information corresponding to each of the at least one search text information; for each search result information, modifying the first interactive information into second interactive information according to the search result information through the third target tool, and obtaining at least one second interactive information.
  • generating at least one search text information related to the first interactive information through the first target tool includes: calling a question generation model through the first target tool, and obtaining multiple preset search texts through the question generation model; for each preset search text, selecting a target keyword from multiple keywords included in the first interactive information; adding the target keyword to a preset position of the preset search text, and generating search text information including the target keyword.
  • obtaining search result information that matches the search text information from a preset database through the second target tool includes: vectorizing the search text information through the second target tool to obtain a first text vector; obtaining, through the first text vector, at least one second text vector from a preset database whose similarity with the first text vector is greater than a first preset threshold; and determining the text information corresponding to the at least one second text vector as the search result information.
  • the first interaction information is modified into second interaction information according to the search result information by the third target tool to obtain at least one second interaction information, including: for each search result information, the question modification model is called by the third target tool, and the first interaction information is modified into second interaction information according to the search result information by the question modification model to obtain at least one second interaction information.
  • the generating of interactive reply information based on the second search result information that matches the first search result information and each second interactive information includes: selecting a preset number of target search result information from the second search result information that matches the first search result information and each second interactive information, wherein the similarity between the preset number of target search result information is greater than a second preset threshold; and generating the interactive reply information based on the preset number of target search result information through a preset model.
  • the method before selecting a tool group corresponding to the first interactive information input by the user from the target plug-in in response to the first interactive information, the method also includes: in response to receiving a request to upload a file, obtaining a file identifier corresponding to the file, and segmenting the file to obtain multiple sub-texts; vectorizing each sub-text to obtain a sub-text vector corresponding to each sub-text; establishing an association relationship between the file identifier, the sub-text and the sub-text vector, and storing the association relationship in a preset database.
  • an interactive information display device comprising:
  • a selection module configured to select, in response to first interaction information input by a user, a tool group corresponding to the first interaction information from a target plug-in;
  • a modification module configured to modify the first interaction information into at least one second interaction information based on a preset database associated with files uploaded by the user, using the tool group;
  • a determination module configured to determine first search result information matching the first interaction information and second search result information matching each second interaction information
  • a display module is used to generate interactive reply information based on the first search result information and the second search result information that matches each second interactive information, and to display the interactive reply information on an interactive interface.
  • the modification module modifies the first interactive information into at least one second interactive information based on a preset database associated with the file uploaded by the user, specifically including: generating at least one search text information related to the first interactive information through the first target tool; for each search text information, obtaining search result information matching the search text information from the preset database through the second target tool, and obtaining search result information corresponding to each of the at least one search text information; for each search result information, modifying the first interactive information into second interactive information according to the search result information through the third target tool, and obtaining at least one second interactive information.
  • the modification module generates at least one search text information related to the first interactive information through a first target tool, specifically including: calling a question generation model through the first target tool, and obtaining multiple preset search texts through the question generation model; for each preset search text, selecting a target keyword from multiple keywords included in the first interactive information; adding the target keyword to a preset position of the preset search text, and generating search text information including the target keyword.
  • the modification module obtains search result information matching the search text information from a preset database through the second target tool, specifically including: performing vectorization processing on the search text information through the second target tool to obtain a first text vector; obtaining, through the first text vector, at least one second text vector from a preset database whose similarity with the first text vector is greater than a first preset threshold; and determining the text information corresponding to the at least one second text vector as the search result information.
  • the modification module modifies the first interactive information into second interactive information according to the search result information through the third target tool to obtain at least one second interactive information, specifically including: for each search result information, calling the question modification model through the third target tool, modifying the first interactive information into second interactive information according to the search result information through the question modification model, and obtaining at least one second interactive information.
  • One less second interactive message For each search result information, calling the question modification model through the third target tool, modifying the first interactive information into second interactive information according to the search result information through the question modification model, and obtaining at least one second interactive information.
  • the display module generates interactive reply information based on the first search result information and the second search result information that matches each second interactive information, specifically including: selecting a preset number of target search result information from the second search result information that matches the first search result information and each second interactive information, wherein the similarity between the preset number of target search result information is greater than a second preset threshold; and generating the interactive reply information based on the preset number of target search result information through a preset model.
  • the device also includes: an upload module, which is used to obtain a file identifier corresponding to the file in response to receiving an upload request for the file, and to segment the file to obtain multiple sub-texts; vectorize each sub-text to obtain a sub-text vector corresponding to each sub-text; establish an association relationship between the file identifier, sub-text and sub-text vector, and store the association relationship in a preset database.
  • an upload module which is used to obtain a file identifier corresponding to the file in response to receiving an upload request for the file, and to segment the file to obtain multiple sub-texts
  • vectorize each sub-text to obtain a sub-text vector corresponding to each sub-text
  • establish an association relationship between the file identifier, sub-text and sub-text vector and store the association relationship in a preset database.
  • An embodiment of the present disclosure further provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;
  • the memory stores computer-executable instructions
  • the processor executes the computer-executable instructions stored in the memory to implement the interactive information display method as described above.
  • An embodiment of the present disclosure further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions.
  • the interactive information display method described above is implemented.
  • An embodiment of the present disclosure further provides a computer program product, including a computer program, which implements the interactive information display method described above when executed by a processor.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Human Computer Interaction (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

本公开实施例提供一种互动信息展示方法、装置、设备及存储介质，该方法包括：响应于用户输入的第一互动信息，从目标插件中选取与第一互动信息对应的工具组；通过工具组，基于与用户上传的文件相关联的预设数据库，将第一互动信息修改为至少一个第二互动信息；确定第一互动信息相匹配的第一搜索结果信息以及每个第二互动信息相匹配的第二搜索结果信息；根据第一搜索结果信息和每个第二互动信息相匹配的第二搜索结果信息生成互动回复信息，在互动界面展示互动回复信息。

Description

互动信息展示方法、装置、设备及存储介质
本申请要求于2024年1月31日递交的中国专利申请第202410141110.3号的优先权，在此全文引用上述中国专利申请公开的内容以作为本申请的一部分。
技术领域
本公开实施例涉及一种互动信息展示方法、装置、设备及存储介质。
背景技术
随着人工智能技术的发展，越来越多的用户通过人工智能平台获取知识或解答问题。
在一些情形下，用户可以在人工智能软件的互动界面输入问题文本，人工智能软件利用模型，获取该问题文本对应的互动回复信息，并在互动界面中展示互动回复信息。
然而，发明人发现上述情形至少存在如下技术问题：当用户输入的问题文本不清楚或针对性较弱时，通过该问题文本获取的互动回复信息往往不能够解答用户的疑问，因此用户体验较差。
发明内容
本公开实施例提供一种互动信息展示方法、装置、设备及存储介质。
本公开实施例提供一种互动信息展示方法，包括：
响应于用户输入的第一互动信息，从目标插件中选取与所述第一互动信息对应的工具组；
通过所述工具组，基于与用户上传的文件相关联的预设数据库，将所述第一互动信息修改为至少一个第二互动信息；
确定所述第一互动信息相匹配的第一搜索结果信息以及每个第二互动信息相匹配的第二搜索结果信息；
根据所述第一搜索结果信息和所述每个第二互动信息相匹配的第二搜 索结果信息生成互动回复信息，在互动界面展示所述互动回复信息。
本公开实施例还提供一种互动信息展示装置，包括：
选取模块，用于响应于用户输入的第一互动信息，从目标插件中选取与所述第一互动信息对应的工具组；
修改模块，用于通过所述工具组，基于与用户上传的文件相关联的预设数据库，将所述第一互动信息修改为至少一个第二互动信息；
确定模块，用于确定所述第一互动信息相匹配的第一搜索结果信息以及每个第二互动信息相匹配的第二搜索结果信息；
展示模块，用于根据所述第一搜索结果信息和所述每个第二互动信息相匹配的第二搜索结果信息生成互动回复信息，在互动界面展示所述互动回复信息。
本公开实施例还提供一种电子设备，包括：
处理器，以及与所述处理器通信连接的存储器；
所述存储器存储计算机执行指令；
所述处理器执行所述存储器存储的计算机执行指令，以实现如上所述的互动信息展示方法。
本公开实施例还提供一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机执行指令，当处理器执行所述计算机执行指令时，实现如上所述的互动信息展示方法。
本公开实施例还提供一种计算机程序产品，包括计算机程序，该计算机程序被处理器执行时实现如上所述的互动信息展示方法。
附图说明
为了更清楚地说明本公开实施例的技术方案，下面将对实施例描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本公开的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本公开一些实施例提供的互动信息展示方法的应用场景示意图；
图2为本公开一些实施例提供的互动信息展示方法的流程图；
图3为本公开一些实施例提供的互动信息展示方法的示意图；
图4为本公开一些实施例提供的互动信息展示方法的示意图；
图5为本公开一些实施例提供的互动信息展示方法的流程图；
图6为本公开一些实施例提供的互动信息展示装置的结构框图；以及
图7为本公开一些实施例提供的电子设备的硬件结构示意图。
具体实施方式
为使本公开实施例的目的、技术方案和优点更加清楚，下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本公开一部分实施例，而不是全部的实施例。基于本公开中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本公开保护的范围。
需要说明的是，本公开所涉及的用户信息(包括但不限于用户设备信息、用户个人信息等)和数据(包括但不限于用于分析的数据、存储的数据、展示的数据等)，均为经用户授权或者经过各方充分授权的信息和数据，并且相关数据的收集、使用和处理需要遵守相关法律法规和标准，并提供有相应的操作入口，供用户选择授权或者拒绝。
随着人工智能技术的发展，越来越多的用户通过人工智能平台获取知识或解答问题。在一些情形下，用户可以在人工智能软件的互动界面输入问题文本，人工智能软件利用模型，获取该问题文本对应的互动回复信息，并在互动界面中展示互动回复信息。
然而，发明人发现上述情形至少存在如下技术问题：当用户输入的问题文本不清楚或针对性较弱时，通过该问题文本获取的互动回复信息往往不能够解答用户的疑问，因此用户体验较差。
由此可见，如何在用户输入的问题文本不清楚或针对性较弱时，搜索到用户想看内容是目前亟待解决的一个技术问题。
为了解决上述问题，本实施例提出了以下技术构思：可以预先安装目标插件，当用户输入问题时，通过调用目标插件对输入的问题进行改写，以提高问题的有效性，进而搜索到用户想看内容。
具体步骤可以包括：首先，响应于用户输入的第一互动信息，从目标插件中选取与第一互动信息对应的工具组。然后，通过工具组，基于与用户上 传的文件相关联的预设数据库，将第一互动信息修改为至少一个第二互动信息；确定第一互动信息相匹配的第一搜索结果信息以及每个第二互动信息相匹配的第二搜索结果信息。最后，根据第一搜索结果信息和每个第二互动信息相匹配的第二搜索结果信息生成互动回复信息，在互动界面展示互动回复信息。
在此情况下，由于通过调用目标插件中的工具组，可以根据用户上传的文件对用户问题进行改写，提高了用户问题的有效性，从而搜索到用户想看的内容，因此提高了用户体验。
下面对本公开实施例的应用场景进行解释：
本公开实施例提供的互动信息展示方法，可以应用于通过各种方式对互动信息展示的应用场景中。例如，可以通过移动端的人工智能软件对互动信息展示，也可以通过电脑端的人工智能网页对互动信息展示。示例性的，人工智能软件可以是AI智能助手软件。图1为本公开一些实施例提供的互动信息展示方法的应用场景示意图。如图1所示，用户可以人工智能软件或人工智能网页的互动界面输入问题：XX的女儿是怎么去世的。此时，可以将问题改写为：YY是怎么去世的。之后，通过用户输入的问题以及改写后的问题搜索结果，这样就提高了用户问题的有效性，从而搜索到用户想看的内容，因此可以提高用户体验。
下面采用详细的实施例对本公开实施例提供的互动信息展示方法进行详细说明。
图2为本公开一些实施例提供的互动信息展示方法的流程图。在本实施例，以互动信息展示方法的执行主体是电子设备为例进行说明。参考图2，该方法包括：
S201、响应于用户输入的第一互动信息，从目标插件中选取与第一互动信息对应的工具组。
在本公开实施例中，第一互动信息可以文本信息、图像信息、视频信息等任一类型的信息。
在一些实施例中，与第一互动信息对应的工具组可以包括一个或多个工具。可选地，工具组包括第一目标工具、第二目标工具和第三目标工具。相应地，本步骤可以包括：响应于用户输入的第一互动信息，从目标插件中选 取第一目标工具、第二目标工具和第三目标工具，将第一目标工具、第二目标工具和第三目标工具确定为与第一互动信息对应的工具组。
其中，第一目标工具用于生成与第一互动信息相关的至少一个搜索文本信息；第二目标工具，用于从预设数据库中获取与搜索文本信息相匹配的搜索结果信息；第三目标工具，用于根据搜索结果信息，将第一互动信息修改为第二互动信息。可选地，第一目标工具为：根据互动信息提出问题工具。示例性的，第一目标工具可以表示为：ask_question_for_query。可选地，第二目标工具为：问题答复工具。示例性的，第二目标工具可以表示为：ask_document。可选地，第三目标工具为：问题重写工具。示例性的，第三目标工具可以表示为：rewrite_query。
S202、通过工具组，基于与用户上传的文件相关联的预设数据库，将第一互动信息修改为至少一个第二互动信息。
在本公开实施例中，先根据第一互动信息，生成搜索文本信息，并根据搜索文本信息，从预设数据库中获取与搜索文本信息相匹配的搜索结果信息，然后，根据搜索结果信息，对第一互动信息进行调整。相应地，本步骤可以通过包括以下步骤(1)至(3)：
(1)通过第一目标工具生成与第一互动信息相关的至少一个搜索文本信息。
可选地，如图3所示，可以通过问题生成模型，生成新的问题。相应地，本步骤可以包括：通过第一目标工具调用问题生成模型，通过问题生成模型获取多个预设搜索文本；对于每个预设搜索文本，从第一互动信息包括的多个关键词中选取目标关键词；将目标关键词添加到预设搜索文本的预设位置，生成包括目标关键词的搜索文本信息。
示例性的，第一互动信息为：XX的女儿是怎么去世的。从第一互动信息包括的多个关键词中选取目标关键词：XX的女儿。预设搜索文本为：XX的女儿是谁。将目标关键词添加到预设搜索文本的预设位置(例如，XX的女儿对应的位置)，生成包括目标关键词的搜索文本信息为：XX的女儿是谁。
(2)对于每个搜索文本信息，通过第二目标工具从预设数据库中获取与搜索文本信息相匹配的搜索结果信息，得到至少一个搜索文本信息各自分别对应的搜索结果信息。
可选地，如图3所示，可以通过向量相似度获取搜索结果信息。相应地，本步骤可以包括：通过第二目标工具对搜索文本信息进行向量化处理，得到第一文本向量；通过第一文本向量，从预设数据库中获取与第一文本向量的相似度大于第一预设阈值的至少一个第二文本向量；将至少一个第二文本向量对应的文本信息确定为搜索结果信息。
可选地，预设数据库可以是知识库。该预设数据库内存储有多个文本信息对应的文本向量。相应地，通过第一文本向量，从预设数据库中获取与第一文本向量的相似度大于第一预设阈值的至少一个第二文本向量，包括：确定第一互动信息对应的文件标识，从该文件标识对应的多个文本向量中，获取与第一文本向量的相似度大于第一预设阈值的至少一个第二文本向量。
示例性的，第一互动信息为：XX的女儿是怎么去世的。第一互动信息对应的文件标识为：小说《XX》。搜索文本信息为：XX的女儿是谁。通过向量相似度从小说《XX》对应的多个文本向量中，获取第二文本向量；将第二文本向量对应的文本信息“XX的女儿是YY”，确定为搜索结果信息。
(3)对于每个搜索结果信息，通过第三目标工具根据搜索结果信息将第一互动信息修改为第二互动信息，得到至少一个第二互动信息。
可选地，如图3所示，可以通过问题修改模型，将第一互动信息修改为第二互动信息。相应地，本步骤为：对于每个搜索结果信息，通过第三目标工具调用问题修改模型，通过问题修改模型将第一互动信息修改为第二互动信息，得到至少一个第二互动信息。
其中，第二互动信息综合了预设数据库中的搜索结果信息和第一互动信息。示例性的，第一互动信息为：XX的女儿是怎么去世的。搜索结果信息为：XX的女儿是YY。通过问题修改模型将第一互动信息修改为第二互动信息为：YY是怎么去世的。
在本公开实施例中，由于先根据第一互动信息，生成搜索文本信息，并根据搜索文本信息，从预设数据库中获取与搜索文本信息相匹配的搜索结果信息，然后根据搜索结果信息，对第一互动信息进行调整；也即是，第二互动信息综合了预设数据库中的搜索结果信息和第一互动信息，因此，增加了第二互动信息的有效性。
S203、确定第一互动信息相匹配的第一搜索结果信息以及每个第二互动 信息相匹配的第二搜索结果信息。
在本公开实施例中，可以通过预设模型等生成式模型，确定第一互动信息相匹配的第一搜索结果信息以及每个第二互动信息相匹配的第二搜索结果信息。
其中，预设模型可以是基于海量文本数据训练的深度学习模型。它不仅能够生成自然语言文本，还能够深入理解文本含义，处理各种自然语言任务，如文本摘要、问答、翻译等。
示例性的，第一互动信息为：XX的女儿是怎么去世的。第二互动信息为：YY是怎么去世的。通过预设模型确定第一互动信息相匹配的第一搜索结果信息为：未搜索出相关信息。通过预设模型第二互动信息相匹配的第二搜索结果信息为：YY是难产去世的。
S204、根据第一搜索结果信息和每个第二互动信息相匹配的第二搜索结果信息生成互动回复信息，在互动界面展示互动回复信息。
在一些实施例中，根据第一搜索结果信息和每个第二互动信息相匹配的第二搜索结果信息生成互动回复信息，包括：从第一搜索结果信息和每个第二互动信息相匹配的第二搜索结果信息中，选取已搜索出结果的搜索结果信息，将该搜索结果信息确定为互动回复信息。
示例性的，第一搜索结果信息为：未搜索出相关信息。第二搜索结果信息为：YY是难产去世的。则将已搜索出结果的第二搜索结果信息确定为互动回复信息，在互动界面展示互动回复信息：YY是难产去世的。
在另一些实施例中，第二搜索结果信息的数量较多，此时可以从多个搜索结果信息中筛选出相似度接近的几个搜索结果信息，然后通过相似度接近的几个搜索结果信息，得到互动回复信息。相应地，根据第一搜索结果信息和每个第二互动信息相匹配的第二搜索结果信息生成互动回复信息，包括：从第一搜索结果信息和每个第二互动信息相匹配的第二搜索结果信息中选取预设数量的目标搜索结果信息，其中预设数量的目标搜索结果信息之间的相似度大于第二预设阈值；通过预设模型根据预设数量的目标搜索结果信息，生成互动回复信息。
在本公开实施例中对预设数量和第二预设阈值的数值不作具体限定，可以根据需要进行设定并修改。
由于先从多个搜索结果信息中筛选出相似度接近的几个搜索结果信息，而相似度接近的搜索结果信息，便于提高预设模型生成的互动回复信息的准确性，因此进一步提高了用户体验。
本公开实施例提供了一种互动信息展示方法：响应于用户输入的第一互动信息，从目标插件中选取与第一互动信息对应的工具组；通过工具组，将第一互动信息修改为至少一个第二互动信息；确定第一互动信息相匹配的第一搜索结果信息以及每个第二互动信息相匹配的第二搜索结果信息；根据第一搜索结果信息和每个第二互动信息相匹配的第二搜索结果信息生成互动回复信息，在互动界面展示互动回复信息。在本公开实施例中，由于通过调用目标插件中的工具组，可以根据用户上传的文件对用户问题进行改写，提高了用户问题的有效性，从而搜索到用户想看的内容，因此提高了用户体验。
需要说明的是，如图4所示，为了提高改写后第二互动信息的有效性，用户可以预先将问题相关的文件上传到预设数据库。相应地，如图5所示，响应于用户输入的第一互动信息，从目标插件中选取与第一互动信息对应的工具组之前，该方法还包括：
S501、响应于接收到文件上传的请求，获取文件的文件标识，以及，对文件进行分割，得到多个子文本。
在本公开实施例中，文件可以是文本文件、图像文件、视频文件等与用户问题相关的文件。例如，用户问题(也即第一互动信息)为XX的女儿是怎么去世的。文件信息可以的是小说《XX》的文本信息。其中，XX是小说《XX》中的人物角色。
可选地，上传请求中可以包括文件和文件标识。文件中包括多个子文本。相应地，可以按子文本为单位，对文件信息进行分割，得到多个子文本。其中，子文本可以是字符文本、词语文本、句子文本、段落文本等。
例如，上传请求中包括文件和文件标识“《XX》”。按子文本为单位，对文件(例如，小说《XX》的文件)进行分割，得到小说《XX》的文件对应的多个子文本。
S502、对每个子文本进行向量化处理，得到每个子文本对应的子文本向量。
在本公开实施例中，可以通过AI(Artificial Intelligence，人工智能)向 量化接口，对每个子文本进行向量化处理，得到每个子文本对应的子文本向量。
在一些实施例中，为了控制子文本向量的数据量，还可以对子文本的第一字符数进行限定。可选地，设定子文本的第一字符数小于第一预设值。其中，第一预设值的数值可以根据需要进行设定并修改。示例性的，第一预设值为500。
在另一些实施例中，为了提高子文本向量的有效性，还可以对子文本中相同字符的第二字符数进行限定。可选地，设定子文本中相同字符的第二字符数小于第二预设值。其中，第二预设值的数值可以根据需要进行设定并修改。示例性的，第二预设值为50。
需要说明的是，为了提高对子文本进行向量化处理的效率，可以并发向量化，也即同时对多个子文本进行向量化处理。其中，并发处理的子文本的数值可以根据需要进行设定并修改。示例性的，并发度为10。
S503、建立文件标识、子文本和子文本向量之间的关联关系，并将关联关系存储到预设数据库内。
示例性的，小说《XX》中包括3000个子文本；对小说《XX》中的每个子文本进行向量化处理，得到3000个子文本向量。针对每个子文本，建立子文本、子文本向量和文件标识《XX》之间的关联关系，并存储到预设数据库内。
在本公开实施例中，由于预先将第一互动信息相关的文件上传到预设数据库内，这样，对第一互动信息进行改写时，可以从预设数据库内调用相关文件中的信息，因此提高了改写后的第二互动信息的有效性。
图6为本公开实施例提供的一种互动信息展示装置的结构框图。参见图6，该装置包括：选取模块601、修改模块602、确定模块603和展示模块604。
选取模块601，用于响应于用户输入的第一互动信息，从目标插件中选取与第一互动信息对应的工具组；
修改模块602，用于通过工具组，基于与用户上传的文件相关联的预设数据库，将第一互动信息修改为至少一个第二互动信息；
确定模块603，用于确定第一互动信息相匹配的第一搜索结果信息以及每个第二互动信息相匹配的第二搜索结果信息；
展示模块604，用于根据第一搜索结果信息和每个第二互动信息相匹配的第二搜索结果信息生成互动回复信息，在互动界面展示互动回复信息。
根据本公开的一个或多个实施例，所述修改模块602，通过所述工具组，基于与用户上传的文件相关联的预设数据库，将所述第一互动信息修改为至少一个第二互动信息，具体包括：通过第一目标工具生成与所述第一互动信息相关的至少一个搜索文本信息；对于每个搜索文本信息，通过所述第二目标工具从预设数据库中获取与所述搜索文本信息相匹配的搜索结果信息，得到所述至少一个搜索文本信息各自分别对应的搜索结果信息；对于每个搜索结果信息，通过所述第三目标工具根据所述搜索结果信息将所述第一互动信息修改为第二互动信息，得到至少一个第二互动信息。
根据本公开的一个或多个实施例，所述修改模块602，通过第一目标工具生成与所述第一互动信息相关的至少一个搜索文本信息，具体包括：通过所述第一目标工具调用问题生成模型，通过所述问题生成模型获取多个预设搜索文本；对于每个预设搜索文本，从所述第一互动信息包括的多个关键词中选取目标关键词；将所述目标关键词添加到预设搜索文本的预设位置，生成包括所述目标关键词的搜索文本信息。
根据本公开的一个或多个实施例，所述修改模块602，通过所述第二目标工具从预设数据库中获取与所述搜索文本信息相匹配的搜索结果信息，具体包括：通过所述第二目标工具对所述搜索文本信息进行向量化处理，得到第一文本向量；通过所述第一文本向量，从预设数据库中获取与所述第一文本向量的相似度大于第一预设阈值的至少一个第二文本向量；将所述至少一个第二文本向量对应的文本信息确定为所述搜索结果信息。
根据本公开的一个或多个实施例，所述修改模块602，对于每个搜索结果信息，通过所述第三目标工具根据所述搜索结果信息将所述第一互动信息修改为第二互动信息，得到至少一个第二互动信息，具体包括：对于每个搜索结果信息，通过所述第三目标工具调用问题修改模型，通过所述问题修改模型根据所述搜索结果信息，将所述第一互动信息修改为第二互动信息，得到至少一个第二互动信息。
根据本公开的一个或多个实施例，所述展示模块604，根据所述第一搜索结果信息和所述每个第二互动信息相匹配的第二搜索结果信息生成互动 回复信息，具体包括：从所述第一搜索结果信息和所述每个第二互动信息相匹配的第二搜索结果信息中选取预设数量的目标搜索结果信息，其中所述预设数量的目标搜索结果信息之间的相似度大于第二预设阈值；通过预设模型根据所述预设数量的目标搜索结果信息，生成所述互动回复信息。
根据本公开的一个或多个实施例，所述装置还包括：上传模块，所述上传模块，用于响应于接收到文件的上传请求，获取所述文件对应的文件标识，以及，对所述文件进行分割，得到多个子文本；对每个子文本进行向量化处理，得到每个子文本对应的子文本向量；建立文件标识、子文本和子文本向量之间的关联关系，并将所述关联关系存储到预设数据库内。
参考图7，其示出了适于用来实现本公开实施例的电子设备700的结构示意图，该电子设备700可以为终端设备或服务器。其中，终端设备可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、个人数字助理(Personal Digital Assistant，简称PDA)、平板电脑(Portable Android Device，简称PAD)、便携式多媒体播放器(Portable Media Player，简称PMP)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图7示出的电子设备仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图7所示，电子设备700可以包括处理装置(例如中央处理器、图形处理器等)701，其可以根据存储在只读存储器(Read Only Memory，简称ROM)702中的程序或者从存储装置708加载到随机访问存储器(Random Access Memory，简称RAM)703中的程序而执行各种适当的动作和处理。在RAM 703中，还存储有电子设备700操作所需的各种程序和数据。处理装置701、ROM 702以及RAM 703通过总线704彼此相连。输入/输出(I/O)接口705也连接至总线704。
通常，以下装置可以连接至I/O接口705：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置706；包括例如液晶显示器(Liquid Crystal Display，简称LCD)、扬声器、振动器等的输出装置707；包括例如磁带、硬盘等的存储装置708；以及通信装置709。通信装置709可以允许电子设备700与其他设备进行无线或有线通信以交换数据。虽然图7示出了具有各种装置的电子设备700，但是应理解的是，并不 要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置709从网络上被下载和安装，或者从存储装置708被安装，或者从ROM 702被安装。在该计算机程序被处理装置701执行时，执行本公开实施例的方法中限定的上述功能。
需要说明的是，本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备执行上述实施例所示的方法。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(Local Area Network，简称LAN)或广域网(Wide Area Network，简称WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，单元的名称在某种情况下并不构成对该单元本身的限定，例如，第一获取单元还可以被描述为“获取至少两个网际协议地址的单元”。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结 合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
根据本公开的一个或多个实施例，提供了一种互动信息展示方法，包括：
响应于用户输入的第一互动信息，从目标插件中选取与所述第一互动信息对应的工具组；
通过所述工具组，基于与用户上传的文件相关联的预设数据库，将所述第一互动信息修改为至少一个第二互动信息；
确定所述第一互动信息相匹配的第一搜索结果信息以及每个第二互动信息相匹配的第二搜索结果信息；
根据所述第一搜索结果信息和所述每个第二互动信息相匹配的第二搜索结果信息生成互动回复信息，在互动界面展示所述互动回复信息。
根据本公开的一个或多个实施例，所述通过所述工具组，基于与用户上传的文件相关联的预设数据库，将所述第一互动信息修改为至少一个第二互动信息，包括：通过第一目标工具生成与所述第一互动信息相关的至少一个搜索文本信息；对于每个搜索文本信息，通过所述第二目标工具从预设数据库中获取与所述搜索文本信息相匹配的搜索结果信息，得到所述至少一个搜索文本信息各自分别对应的搜索结果信息；对于每个搜索结果信息，通过所述第三目标工具根据所述搜索结果信息将所述第一互动信息修改为第二互动信息，得到至少一个第二互动信息。
根据本公开的一个或多个实施例，所述通过第一目标工具生成与所述第一互动信息相关的至少一个搜索文本信息，包括：通过所述第一目标工具调用问题生成模型，通过所述问题生成模型获取多个预设搜索文本；对于每个预设搜索文本，从所述第一互动信息包括的多个关键词中选取目标关键词；将所述目标关键词添加到预设搜索文本的预设位置，生成包括所述目标关键词的搜索文本信息。
根据本公开的一个或多个实施例，所述通过所述第二目标工具从预设数据库中获取与所述搜索文本信息相匹配的搜索结果信息，包括：通过所述第二目标工具对所述搜索文本信息进行向量化处理，得到第一文本向量；通过所述第一文本向量，从预设数据库中获取与所述第一文本向量的相似度大于第一预设阈值的至少一个第二文本向量；将所述至少一个第二文本向量对应的文本信息确定为所述搜索结果信息。
根据本公开的一个或多个实施例，所述对于每个搜索结果信息，通过所述第三目标工具根据所述搜索结果信息将所述第一互动信息修改为第二互动信息，得到至少一个第二互动信息，包括：对于每个搜索结果信息，通过所述第三目标工具调用问题修改模型，通过所述问题修改模型根据所述搜索结果信息，将所述第一互动信息修改为第二互动信息，得到至少一个第二互动信息。
根据本公开的一个或多个实施例，所述根据所述第一搜索结果信息和所述每个第二互动信息相匹配的第二搜索结果信息生成互动回复信息，包括：从所述第一搜索结果信息和所述每个第二互动信息相匹配的第二搜索结果信息中选取预设数量的目标搜索结果信息，其中所述预设数量的目标搜索结果信息之间的相似度大于第二预设阈值；通过预设模型根据所述预设数量的目标搜索结果信息，生成所述互动回复信息。
根据本公开的一个或多个实施例，所述响应于用户输入的第一互动信息，从目标插件中选取与所述第一互动信息对应的工具组之前，所述方法还包括：响应于接收到文件的上传请求，获取所述文件对应的文件标识，以及，对所述文件进行分割，得到多个子文本；对每个子文本进行向量化处理，得到每个子文本对应的子文本向量；建立文件标识、子文本和子文本向量之间的关联关系，并将所述关联关系存储到预设数据库内。
根据本公开的一个或多个实施例，还提供了一种互动信息展示装置，包括：
选取模块，用于响应于用户输入的第一互动信息，从目标插件中选取与所述第一互动信息对应的工具组；
修改模块，用于通过所述工具组，基于与用户上传的文件相关联的预设数据库，将所述第一互动信息修改为至少一个第二互动信息；
确定模块，用于确定所述第一互动信息相匹配的第一搜索结果信息以及每个第二互动信息相匹配的第二搜索结果信息；
展示模块，用于根据所述第一搜索结果信息和所述每个第二互动信息相匹配的第二搜索结果信息生成互动回复信息，在互动界面展示所述互动回复信息。
根据本公开的一个或多个实施例，所述修改模块，通过所述工具组，基于与用户上传的文件相关联的预设数据库，将所述第一互动信息修改为至少一个第二互动信息，具体包括：通过第一目标工具生成与所述第一互动信息相关的至少一个搜索文本信息；对于每个搜索文本信息，通过所述第二目标工具从预设数据库中获取与所述搜索文本信息相匹配的搜索结果信息，得到所述至少一个搜索文本信息各自分别对应的搜索结果信息；对于每个搜索结果信息，通过所述第三目标工具根据所述搜索结果信息将所述第一互动信息修改为第二互动信息，得到至少一个第二互动信息。
根据本公开的一个或多个实施例，所述修改模块，通过第一目标工具生成与所述第一互动信息相关的至少一个搜索文本信息，具体包括：通过所述第一目标工具调用问题生成模型，通过所述问题生成模型获取多个预设搜索文本；对于每个预设搜索文本，从所述第一互动信息包括的多个关键词中选取目标关键词；将所述目标关键词添加到预设搜索文本的预设位置，生成包括所述目标关键词的搜索文本信息。
根据本公开的一个或多个实施例，所述修改模块，通过所述第二目标工具从预设数据库中获取与所述搜索文本信息相匹配的搜索结果信息，具体包括：通过所述第二目标工具对所述搜索文本信息进行向量化处理，得到第一文本向量；通过所述第一文本向量，从预设数据库中获取与所述第一文本向量的相似度大于第一预设阈值的至少一个第二文本向量；将所述至少一个第二文本向量对应的文本信息确定为所述搜索结果信息。
根据本公开的一个或多个实施例，所述修改模块，对于每个搜索结果信息，通过所述第三目标工具根据所述搜索结果信息将所述第一互动信息修改为第二互动信息，得到至少一个第二互动信息，具体包括：对于每个搜索结果信息，通过所述第三目标工具调用问题修改模型，通过所述问题修改模型根据所述搜索结果信息，将所述第一互动信息修改为第二互动信息，得到至 少一个第二互动信息。
根据本公开的一个或多个实施例，所述展示模块，根据所述第一搜索结果信息和所述每个第二互动信息相匹配的第二搜索结果信息生成互动回复信息，具体包括：从所述第一搜索结果信息和所述每个第二互动信息相匹配的第二搜索结果信息中选取预设数量的目标搜索结果信息，其中所述预设数量的目标搜索结果信息之间的相似度大于第二预设阈值；通过预设模型根据所述预设数量的目标搜索结果信息，生成所述互动回复信息。
根据本公开的一个或多个实施例，所述装置还包括：上传模块，所述上传模块，用于响应于接收到文件的上传请求，获取所述文件对应的文件标识，以及，对所述文件进行分割，得到多个子文本；对每个子文本进行向量化处理，得到每个子文本对应的子文本向量；建立文件标识、子文本和子文本向量之间的关联关系，并将所述关联关系存储到预设数据库内。
本公开的实施例还提供了一种电子设备，包括：处理器，以及与所述处理器通信连接的存储器；
所述存储器存储计算机执行指令；
所述处理器执行所述存储器存储的计算机执行指令，以实现如上所述的互动信息展示方法。
本公开的实施例还提供了一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机执行指令，当处理器执行所述计算机执行指令时，实现如上所述的互动信息展示方法。
本公开的实施例还提供一种计算机程序产品，包括计算机程序，该计算机程序被处理器执行时实现如上所述的互动信息展示方法。
以上描述仅为本公开的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开中所涉及的公开范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述公开构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。
此外，虽然采用特定次序描绘了各操作，但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下，多任务 和并行处理可能是有利的。同样地，虽然在上面论述中包含了若干具体实现细节，但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地，在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。
尽管已经采用特定于结构特征和/或方法逻辑动作的语言描述了本主题，但是应当理解所附权利要求书中所限定的主题未必局限于上面描述的特定特征或动作。相反，上面所描述的特定特征和动作仅仅是实现权利要求书的示例形式。

Claims (11)

  1. 一种互动信息展示方法，包括：
    响应于用户输入的第一互动信息，从目标插件中选取与所述第一互动信息对应的工具组；
    通过所述工具组，基于与所述用户上传的文件相关联的预设数据库，将所述第一互动信息修改为至少一个第二互动信息；
    确定所述第一互动信息相匹配的第一搜索结果信息以及每个所述第二互动信息相匹配的第二搜索结果信息；以及
    根据所述第一搜索结果信息和每个所述第二互动信息相匹配的第二搜索结果信息生成互动回复信息，在互动界面展示所述互动回复信息。
  2. 根据权利要求1所述的方法，其中，所述通过所述工具组，基于与所述用户上传的文件相关联的预设数据库，将所述第一互动信息修改为至少一个第二互动信息，包括：
    通过第一目标工具生成与所述第一互动信息相关的至少一个搜索文本信息；
    对于每个所述搜索文本信息，通过第二目标工具从所述预设数据库中获取与所述搜索文本信息相匹配的搜索结果信息，得到所述至少一个搜索文本信息各自分别对应的搜索结果信息；以及
    对于每个所述搜索结果信息，通过第三目标工具根据所述搜索结果信息将所述第一互动信息修改为所述第二互动信息，得到所述至少一个第二互动信息。
  3. 根据权利要求2所述的方法，其中，所述通过第一目标工具生成与所述第一互动信息相关的至少一个搜索文本信息，包括：
    通过所述第一目标工具调用问题生成模型，通过所述问题生成模型获取多个预设搜索文本；
    对于每个所述预设搜索文本，从所述第一互动信息包括的多个关键词中选取目标关键词；以及
    将所述目标关键词添加到所述预设搜索文本的预设位置，生成包括所述目标关键词的搜索文本信息。
  4. 根据权利要求2或3所述的方法，其中，所述通过第二目标工具从所述预设数据库中获取与所述搜索文本信息相匹配的搜索结果信息，包括：
    通过所述第二目标工具对所述搜索文本信息进行向量化处理，得到第一文本向量；
    通过所述第一文本向量，从所述预设数据库中获取与所述第一文本向量的相似度大于第一预设阈值的至少一个第二文本向量；以及
    将所述至少一个第二文本向量对应的文本信息确定为所述搜索结果信息。
  5. 根据权利要求2-4中任一项所述的方法，其中，所述对于每个所述搜索结果信息，通过第三目标工具根据所述搜索结果信息将所述第一互动信息修改为所述第二互动信息，得到所述至少一个第二互动信息，包括：
    对于每个搜索结果信息，通过所述第三目标工具调用问题修改模型，通过所述问题修改模型根据所述搜索结果信息，将所述第一互动信息修改为第二互动信息，得到至少一个第二互动信息。
  6. 根据权利要求1所述的方法，其中，所述根据所述第一搜索结果信息和每个所述第二互动信息相匹配的第二搜索结果信息生成互动回复信息，包括：
    从所述第一搜索结果信息和每个所述第二互动信息相匹配的第二搜索结果信息中选取预设数量的目标搜索结果信息，其中，所述预设数量的目标搜索结果信息之间的相似度大于第二预设阈值；以及
    通过预设模型根据所述预设数量的目标搜索结果信息，生成所述互动回复信息。
  7. 根据权利要求1-6任一项所述的方法，其中，在所述响应于用户输入的第一互动信息，从目标插件中选取与所述第一互动信息对应的工具组之前， 所述方法还包括：
    响应于接收到文件上传的请求，获取所述文件的文件标识，以及，对所述文件进行分割，得到多个子文本；
    对每个所述子文本进行向量化处理，得到每个所述子文本对应的子文本向量；以及
    建立所述文件标识、所述子文本和所述子文本向量之间的关联关系，并将所述关联关系存储到所述预设数据库内。
  8. 一种互动信息展示装置，包括：
    选取模块，配置为响应于用户输入的第一互动信息，从目标插件中选取与所述第一互动信息对应的工具组；
    修改模块，配置为通过所述工具组，基于与所述用户上传的文件相关联的预设数据库，将所述第一互动信息修改为至少一个第二互动信息；
    确定模块，配置为确定所述第一互动信息相匹配的第一搜索结果信息以及每个所述第二互动信息相匹配的第二搜索结果信息；以及
    展示模块，配置为根据所述第一搜索结果信息和每个所述第二互动信息相匹配的第二搜索结果信息生成互动回复信息，在互动界面展示所述互动回复信息。
  9. 一种电子设备，包括：处理器，以及与所述处理器通信连接的存储器；
    其中，所述存储器存储计算机执行指令；
    所述处理器执行所述存储器存储的计算机执行指令，以实现如权利要求1-7中任一项所述的互动信息展示方法。
  10. 一种计算机可读存储介质，其中，所述计算机可读存储介质中存储有计算机执行指令，当处理器执行所述计算机执行指令时，实现如权利要求1-7中任一项所述的互动信息展示方法。
  11. 一种计算机程序产品，包括：计算机程序，其中，所述计算机程序被处理器执行时实现如权利要求1-7中任一项所述的互动信息展示方法。
PCT/CN2024/108478 2024-01-31 2024-07-30 互动信息展示方法、装置、设备及存储介质 Pending WO2025161306A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202410141110.3A CN118013005A (zh) 2024-01-31 2024-01-31 互动信息展示方法、装置、设备及存储介质
CN202410141110.3 2024-01-31

Publications (1)

Publication Number Publication Date
WO2025161306A1 true WO2025161306A1 (zh) 2025-08-07

Family

ID=90953280

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2024/108478 Pending WO2025161306A1 (zh) 2024-01-31 2024-07-30 互动信息展示方法、装置、设备及存储介质

Country Status (2)

Country Link
CN (1) CN118013005A (zh)
WO (1) WO2025161306A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118013005A (zh) * 2024-01-31 2024-05-10 抖音视界有限公司 互动信息展示方法、装置、设备及存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200250237A1 (en) * 2019-02-01 2020-08-06 EMC IP Holding Company LLC Contextual image-assisted search
CN114372122A (zh) * 2021-12-08 2022-04-19 阿里云计算有限公司 信息的获取方法、计算设备及存储介质
US20220391849A1 (en) * 2021-06-02 2022-12-08 International Business Machines Corporation Generating interview questions based on semantic relationships
CN116127085A (zh) * 2022-10-31 2023-05-16 北京智谱华章科技有限公司 一种面向对话式知识图谱问答的问题重写方法及设备
CN116244418A (zh) * 2023-05-11 2023-06-09 腾讯科技（深圳）有限公司 问题解答方法、装置、电子设备及计算机可读存储介质
CN116521841A (zh) * 2023-04-18 2023-08-01 百度在线网络技术（北京）有限公司 用于生成回复信息的方法、装置、设备及介质
CN118013005A (zh) * 2024-01-31 2024-05-10 抖音视界有限公司 互动信息展示方法、装置、设备及存储介质

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200250237A1 (en) * 2019-02-01 2020-08-06 EMC IP Holding Company LLC Contextual image-assisted search
US20220391849A1 (en) * 2021-06-02 2022-12-08 International Business Machines Corporation Generating interview questions based on semantic relationships
CN114372122A (zh) * 2021-12-08 2022-04-19 阿里云计算有限公司 信息的获取方法、计算设备及存储介质
CN116127085A (zh) * 2022-10-31 2023-05-16 北京智谱华章科技有限公司 一种面向对话式知识图谱问答的问题重写方法及设备
CN116521841A (zh) * 2023-04-18 2023-08-01 百度在线网络技术（北京）有限公司 用于生成回复信息的方法、装置、设备及介质
CN116244418A (zh) * 2023-05-11 2023-06-09 腾讯科技（深圳）有限公司 问题解答方法、装置、电子设备及计算机可读存储介质
CN118013005A (zh) * 2024-01-31 2024-05-10 抖音视界有限公司 互动信息展示方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN118013005A (zh) 2024-05-10

Similar Documents

Publication Publication Date Title
CN110263142B (zh) 用于输出信息的方法和装置
CN112258622B (zh) 图像处理方法、装置、可读介质及电子设备
CN120578749B (zh) 基于知识图谱召回的智能体问答方法、装置、设备及产品
CN112182255A (zh) 用于存储媒体文件和用于检索媒体文件的方法和装置
CN118964694A (zh) 知识问答方法、装置、可读介质、电子设备及程序产品
CN112148751A (zh) 用于查询数据的方法和装置
WO2025051277A1 (zh) 交互方法、装置及电子设备
WO2025161306A1 (zh) 互动信息展示方法、装置、设备及存储介质
US20260064735A1 (en) Data processing method, apparatus, medium, device and computer program product
CN115688808A (zh) 翻译方法、装置、可读介质及电子设备
CN110765357A (zh) 在线文档的搜索方法、装置、设备及存储介质
CN109857838B (zh) 用于生成信息的方法和装置
WO2025087031A1 (zh) 一种媒体数据的搜索方法、装置、存储介质及电子设备
WO2025108303A1 (zh) 视频生成方法、装置、电子设备和存储介质
CN118964693A (zh) 知识问答方法、装置、可读介质、电子设备及程序产品
WO2025082445A1 (zh) 视频生成方法、设备及存储介质
CN118897879A (zh) 问答方法、装置、设备以及存储介质
WO2025055658A1 (zh) 图像生成方法、装置、系统、电子设备、计算机可读介质
WO2024179373A1 (zh) 资源检索方法、标签生成方法、装置、设备及存储介质
CN117290466A (zh) 基于ChatGPT的智能问答方法、装置、设备及存储介质
CN120470100B (zh) 基于多知识混合召回的智能体知识检索方法、装置及介质
CN121524314B (zh) 基于大模型的知识问答方法、装置、介质、设备及产品
US11636391B2 (en) Automatic combinatoric feature generation for enhanced machine learning
US20230385252A1 (en) Data quality analyze execution in data governance
CN121255965A (zh) 问答搜索方法、装置、设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24921338

Country of ref document: EP

Kind code of ref document: A1