Question and answer method and device, storage medium and equipment

Abstract

The invention discloses a question and answer method and device, a storage medium and equipment, and the method comprises the steps: pre-determining user features of a target user according to historical retrieval behaviors of the target user and user information of the target user on a target platform, and when the target user carries out question retrieval, carrying out question retrieval on the target user; the method comprises the steps of obtaining user characteristics of a target user, a retrieval statement and a pre-established personal knowledge base, generating reply content for the retrieval statement according to the user characteristics, the retrieval statement and the personal knowledge base, and displaying the reply content to the target user. According to the method, the historical behaviors of the users and the user information can be used as references, and personalized reply content for each user can be given according to question retrieval of the users.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a question-answering method, device, storage medium, and equipment. Background Art

[0002] With the rapid development of big data and artificial intelligence technology, information retrieval systems are undergoing unprecedented changes and upgrades. From early linear models to complex large language models (LLMs), and now to the highly anticipated retrieval-augmented generation (RAG) technology, the boundaries of information retrieval have been continuously broadened. RAG technology improves the accuracy and comprehensiveness of information retrieval by organically combining the two mechanisms of retrieval and generation, and gives the model a certain "thinking" ability, so that the model can generate answers or recommendations that are more in line with user expectations based on understanding user queries.

[0003] However, even the emerging RAG technology can only output the same answer content when users ask the same questions and use the same database. It is difficult to give personalized answers based on each user's individual knowledge level and field preferences according to the user's personal characteristics.

[0004] Therefore, the present invention provides a question-answering method, device, storage medium, and equipment. Summary of the invention

[0005] This specification provides a question-answering method and device to partially solve the above-mentioned problems existing in the prior art.

[0006] This manual adopts the following technical solutions: This manual provides a question-and-answer method, including: Predetermining user characteristics of the target user based on historical search behavior of the target user and user information of the target user on the target platform; When the target user performs a question search, the user characteristics, search statements and a pre-established personal knowledge base of the target user are obtained; generating a response content for the search statement according to the user characteristics, the search statement and the personal knowledge base; The reply content is displayed to the target user.

[0007] Optionally, generating a reply content for the search statement according to the user characteristics, search statement and personal knowledge base of the target user specifically includes: Matching the search statement with each knowledge fragment in the personal knowledge base, and determining a target fragment in each knowledge fragment according to the similarity between each knowledge fragment and the search statement; A response content to the search sentence is generated based on the user characteristics, the search sentence and the personal knowledge base.

[0008] Optionally, a personal knowledge base of the target user is pre-established, specifically including: According to the user characteristics of the target user, a number of knowledge documents are determined in the public knowledge base to form a personal knowledge base of the target user.

[0009] Optionally, after forming the personal knowledge base of the target user, the following is further included: In response to a modification operation of the target user, the personal knowledge base of the target user is updated, wherein the modification operation includes at least one of adding a knowledge document and deleting a knowledge document.

[0010] Optionally, before obtaining the search statement of the target user, the method further includes: Determining recommended search content for the target user according to the user characteristics of the target user; The recommended search content is displayed to the target user.

[0011] Optionally, the user characteristics of the target user are pre-determined according to the historical search behavior of the target user and the user information of the target user on the target platform, specifically including: Determining the historical search behavior of the target user according to the historical search statements input by the target user and / or the historical modification operations of the target user on the historical recommended search content; The user characteristics of the target user are predetermined based on the historical search behavior of the target user and the user information of the target user on the target platform.

[0012] Optionally, the user information of the target user on the target platform specifically includes: user registration information and user behavior data of the target user on the target platform.

[0013] This specification provides a question-answering device, including: A feature module, which predetermines user features of the target user based on the historical search behavior of the target user and the user information of the target user on the target platform; An acquisition module, when the target user performs a question search, acquires the user characteristics, search statements and a pre-established personal knowledge base of the target user; A generating module, generating a reply content for the search statement according to the user characteristics, the search statement and the personal knowledge base; A display module displays the reply content to the target user.

[0014] This specification provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned question-and-answer method is implemented.

[0015] This specification provides a device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned question-and-answer method when executing the program.

[0016] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects: In the question-and-answer method provided in this specification, the user characteristics of the target user are determined in advance based on the target user's historical search behavior and the user information of the target user on the target platform. When the target user performs a question search, the user characteristics, search statements and a pre-established personal knowledge base of the target user are obtained. Based on the user characteristics, the search statement and the personal knowledge base, a reply content for the search statement is generated and the reply content is displayed to the target user.

[0017] It can be seen from the above method that this method can use the user's historical behavior and user information as a reference, search for the user's questions, and provide personalized answer content for each user. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation on this specification. In the drawings: Figure 1 A flowchart of a question-and-answer method in this manual; Figure 2 A flowchart for determining user characteristics of a target user in this specification; Figure 3 A schematic diagram of a question-and-answer device provided in this manual; Figure 4 The corresponding Figure 1 Schematic diagram of electronic equipment. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0020] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0021] Figure 1 The following is a flowchart of a question-and-answer method in this specification, which specifically includes the following steps: S100: Predetermine user characteristics of the target user based on the historical search behavior of the target user and the user information of the target user on the target platform.

[0022] At present, when responding to users' search questions, each user platform usually adopts the following three methods: searching the public content in the public website to determine the relevant information of the user's question and generate a reply to the user's question, searching the internal content of its own user platform to determine the relevant information of the user's question and generate a reply to the user's question, and using RAG technology to retrieve the relevant information of the user's question from a pre-established knowledge base and generate a reply to the user's question. However, the above-mentioned retrieval and generation process lacks adaptive adjustment for the personalized characteristics of each user, making it difficult for the generated content to accurately adapt to the personal needs of each user. Therefore, this specification provides a question-and-answer method, which can be applied to a user platform with a search function. The execution subject of this specification can be the server of the user platform or other electronic devices with computing functions connected to the user platform, and this specification does not limit it here. For the sake of convenience, the following only takes the server as the execution subject to illustrate a question-and-answer method provided in this specification.

[0023] It should be noted that the target user in the method provided in this specification may be a registered user of the target platform, so the server may record the user information of the target user. On the other hand, when each target user is not logging into the server for the first time to search for a question, the server may also record the historical search behavior of the target user. Thus, at the preset feature determination moment, the server may determine the user features of the target user or update the determined user features of the target user based on the recorded user information and historical search behavior of the target user.

[0024] Specifically, the process of determining the user characteristics of the target user can be as follows: Figure 2As shown: first, execute step S200 to obtain user information; then execute step S202 to pre-process the obtained user information. The pre-processing operation may include data cleaning and data filtering - removing duplicate, missing or erroneous data (such as data generated by misoperation or system errors, information not filled in the user registration information, incorrect or data values ​​that do not comply with business rules, etc.), and converting the data into a unified format; then execute step S204 to analyze the user information and extract key features. The aforementioned key features may include interests, industry preferences, age / group, education level, etc.; based on the extracted key features, the user features of the target user can be obtained. Among them, the user information can be analyzed by common analysis algorithms such as clustering algorithms (such as K-means, hierarchical clustering, etc.), association rule mining algorithms (such as Apriori, FP-Growth, etc.); the user features of the target user can be stored in text form.

[0025] Among them, the above-mentioned feature determination moment can be one or more of the moments such as the moment when the user information of the target user changes, the moment when the historical search behavior of the target user is updated, the moment when the preset update cycle arrives, or the moment when the search statement of the target user is received, and this specification does not limit this.

[0026] Furthermore, in one or more embodiments of the present specification, a number of knowledge documents are determined in a public knowledge base according to user characteristics of a target user to form a personal knowledge base of the target user.

[0027] The above-mentioned public knowledge base may be a public knowledge base composed of all public resources in the public network, or may be a selected public knowledge base, and this specification does not impose any limitation on this.

[0028] In one or more embodiments of the present specification, the user information of the target user on the target platform specifically includes: user registration information and user behavior data of the target user on the target platform.

[0029] Among them, user registration information may include but is not limited to common personal information such as user group / occupation, interests and hobbies, geographical location, etc.; user behavior data may include user content browsing records, browsing time corresponding to each content category browsed by the user, user feedback records, etc.

[0030] By collecting statistics on user behavior data and personal information, the user's personal preferences and personal knowledge level can be reflected more truly and objectively.

[0031] S102: When the target user performs a question search, the user characteristics, search statements, and a pre-established personal knowledge base of the target user are obtained.

[0032] When, at any time, the target user enters a search statement in the search section of the target platform and confirms it, it can be determined that the target user is performing a question search. The server can obtain the search statement entered by the target user, and obtain the user characteristics of the target user pre-stored in the database based on the user ID of the target user, and at the same time determine the personal knowledge base corresponding to the target user.

[0033] S104: Generate a reply content for the search statement according to the user characteristics, the search statement and the personal knowledge base.

[0034] After obtaining the user characteristics, search statements and personal knowledge base of the target user, the search statement of the target user can be used to match the knowledge fragments in the personal knowledge base to determine the knowledge fragment matching the search statement as the target fragment, and the matched knowledge fragment, the user characteristics and the search statement are input into a pre-trained large language model so that the large language model generates a response content for the search statement.

[0035] Among them, the search statement, target fragment and user features can be input into the large language model in text form as hard prompts, so that the large language model generates a response content for the search statement; or a pre-trained encoding model can be used to encode the target fragment and user features and use them as soft prompts to replace the specified parameters of the model layer in the large language model, and the search statement can be input into the large language model after the parameters are replaced. This manual does not impose any restrictions on this.

[0036] S106: Display the reply content to the target user.

[0037] After generating the reply content for the search statement, the reply content can be displayed to the target user on the front page of the target platform.

[0038] like Figure 1 The question-answering method shown can use the user's historical behavior and user information as a reference, retrieve the user's questions, and provide personalized answer content for each user.

[0039] In addition, in Figure 1 In step S104 shown, the search statement is matched with each knowledge fragment in the personal knowledge base, and a target fragment is determined in each knowledge fragment based on the similarity between each knowledge fragment and the search statement, and a reply content for the search statement is generated based on the user characteristics, the search statement and the personal knowledge base.

[0040] After establishing any user's personal knowledge base, the user's personal knowledge base can be segmented, word-segmented, and vectorized to convert the file content in the personal knowledge base into a machine-understandable data format and extract relevant basic information (such as title, author, knowledge type, research direction, etc.). The term frequency-inverse document frequency (TF-IDF) method can be used to vectorize the document fragments obtained after segmentation and word-segmentation in the personal knowledge base to obtain the knowledge fragments corresponding to each personal knowledge base.

[0041] Specifically, the formula - TF-IDF = TF × IDF can be used to determine the TF-IDF value of each document fragment, and the document fragments with TF-IDF values ​​exceeding the threshold, or several document fragments with the highest TF-IDF values, can be used as knowledge fragments.

[0042] Among them, for any document fragment, TF = , IDF =

[0043] n represents the total number of knowledge documents in the user's personal knowledge base, represents the number of occurrences of the document fragment in the i-th knowledge document, represents the total number of document fragments in the i-th knowledge document, and k represents the total number of knowledge documents in which the document fragment appears in the user's personal knowledge base.

[0044] Furthermore, when generating the reply content for the search statement, the search statement and each knowledge fragment in the personal knowledge base can be encoded using the same vectorization method, and the encoded search statement can be matched with each knowledge fragment to determine the target fragment.

[0045] Specifically, various common difference determination methods may be used to measure the similarity between the search statement and each knowledge fragment, such as Euclidean distance, Jaccard similarity, cosine similarity, etc., which are not limited in this specification.

[0046] In one or more embodiments of the present specification, after establishing a personal knowledge base of any user, the knowledge documents in the personal knowledge base can also be classified to determine the knowledge field corresponding to each knowledge document. Thus, after obtaining the search statement of the target user, the knowledge field corresponding to the search statement is determined, and the knowledge documents of the corresponding knowledge field in the personal knowledge base are determined based on the knowledge field of the search statement, and then the knowledge fragments of the knowledge documents of the corresponding knowledge field are matched with the search statement to determine the target fragments in the knowledge fragments of the knowledge documents of each corresponding knowledge field.

[0047] In one or more embodiments of the present specification, the knowledge documents in the personal knowledge base are classified, which can be edited and determined by the user, or each knowledge document can be input into a large language model for determination.

[0048] In one or more embodiments of the present specification, after forming the personal knowledge base of the target user, the personal knowledge base of the target user is updated in response to a modification operation of the target user, wherein the modification operation includes at least one of adding a knowledge document and deleting a knowledge document.

[0049] Therefore, users can adjust their personal knowledge base according to their personal needs so that the response content generated in subsequent steps is more suitable for the user's search needs.

[0050] In addition, in Figure 1 Before step S102 shown, the recommended search content for the target user is determined according to the user characteristics of the target user, and the recommended search content is displayed to the target user.

[0051] The method provided in this specification can also display the recommended search content to the target user after the target user logs in to the target platform and triggers the recommended search. Specifically, the recommended search can be triggered by common user operations such as the user clicking on a preset section in the front-end page or the target user jumping to the target page, and this specification does not limit this.

[0052] This can further assist users in determining the content they need to retrieve.

[0053] Moreover, in Figure 1 In step S100 shown, the historical search behavior of the target user is determined based on the historical search statements input by the target user and / or the historical modification operations of the target user on the historical recommended search content, and the user characteristics of the target user are pre-determined based on the historical search behavior of the target user and the user information of the target user on the target platform.

[0054] Specifically, the historical search behavior may include the historical search statements input by the target user and at least one of the historical modification operations of the target user on the historical recommended search content. Therefore, each time the target user performs a question search, the user characteristics of the target user can be updated according to the target user's search behavior. During the user's use, the user characteristics of the target user are continuously adjusted. The method provided in this specification can adapt to the changes of the target user himself and can sustainably optimize the reply content for the target user without additional settings or operations, so that each reply content is more suitable for the personal characteristics of the target user.

[0055] In one or more embodiments of the present specification, a feedback statement of the target user to the reply content may also be obtained, and the user characteristics of the target user may be updated according to the feedback statement.

[0056] The above is a question-and-answer method provided by one or more embodiments of this specification. Based on the same idea, this specification also provides a corresponding question-and-answer device, such as Figure 3 shown.

[0057] Figure 3 A schematic diagram of a question-and-answer device provided in this manual specifically includes: The feature module 300 predetermines the user feature of the target user according to the historical search behavior of the target user and the user information of the target user on the target platform; The acquisition module 302 acquires the user characteristics, search statements and the pre-established personal knowledge base of the target user when the target user performs a question search; A generating module 304 generates a reply content for the search statement according to the user characteristics, the search statement and the personal knowledge base; The display module 306 displays the reply content to the target user.

[0058] Optionally, generation module 304 is specifically used to: match the search statement with each knowledge fragment in the personal knowledge base, determine the target fragment in each knowledge fragment according to the similarity between each knowledge fragment and the search statement, and generate a reply content for the search statement according to the user characteristics, the search statement and the personal knowledge base.

[0059] Optionally, the feature module 300 is further used to: determine a number of knowledge documents in the public knowledge base according to the user characteristics of the target user to form a personal knowledge base of the target user.

[0060] Optionally, the feature module 300 is further used to update the personal knowledge base of the target user in response to a modification operation of the target user, wherein the modification operation includes at least one of adding a knowledge document and deleting a knowledge document.

[0061] Optionally, the acquisition module 302 is further configured to: determine the recommended search content for the target user according to the user characteristics of the target user, and display the recommended search content to the target user.

[0062] Optionally, the feature module 300 is specifically used to: determine the historical search behavior of the target user based on the historical search statements input by the target user and / or the historical modification operations of the target user on the historical recommended search content, and pre-determine the user characteristics of the target user based on the historical search behavior of the target user and the user information of the target user on the target platform.

[0063] Optionally, the user information of the target user on the target platform specifically includes: user registration information and user behavior data of the target user on the target platform.

[0064] This specification also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 Question and answer method provided.

[0065] This manual also provides Figure 4 The schematic structure diagram of the electronic device shown in FIG. Figure 4 As mentioned above, at the hardware level, the question-answering device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 Of course, in addition to the software implementation, this specification does not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0066] In the 1990s, it was very clear whether the improvement of a technology was a hardware improvement (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or a software improvement (improvement of the method flow). However, with the development of technology, many improvements in the method flow today can be regarded as direct improvements in the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented with a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming themselves, without having to ask chip manufacturers to design and make dedicated integrated circuit chips. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0067] The controller may be implemented in any suitable manner, for example, the controller may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (e.g., software or firmware) executable by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, and the memory controller may also be implemented as part of the control logic of the memory. It is also known to those skilled in the art that, in addition to implementing the controller in a purely computer-readable program code manner, the controller may be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, such a controller may be considered as a hardware component, and the devices for implementing various functions included therein may also be considered as structures within the hardware component. Or even, the devices for implementing various functions may be considered as both software modules for implementing the method and structures within the hardware component.

[0068] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0069] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0070] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0071] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0072] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0073] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0074] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0075] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0076] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0077] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0078] It should be understood by those skilled in the art that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0079] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media including storage devices.

[0080] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0081] The above description is only an embodiment of this specification and is not intended to limit this specification. For those skilled in the art, this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this specification should be included in the scope of the claims of this application.

Claims

1. A question-answering method, characterized in that: The method comprises: Predetermining user characteristics of the target user based on historical search behavior of the target user and user information of the target user on the target platform; When the target user performs a question search, the user characteristics, search statements and a pre-established personal knowledge base of the target user are obtained; generating a response content for the search statement according to the user characteristics, the search statement and the personal knowledge base; The reply content is displayed to the target user.

2. The method according to claim 1, characterized in that Generate a response to the search statement based on the user characteristics, search statement and personal knowledge base of the target user, including: Matching the search statement with each knowledge fragment in the personal knowledge base, and determining a target fragment in each knowledge fragment according to the similarity between each knowledge fragment and the search statement; A response content to the search sentence is generated based on the user characteristics, the search sentence and the personal knowledge base.

3. The method according to claim 1, characterized in that Pre-establish the target user's personal knowledge base, specifically including: According to the user characteristics of the target user, a number of knowledge documents are determined in the public knowledge base to form a personal knowledge base of the target user.

4. The method according to claim 3, characterized in that After forming the personal knowledge base of the target user, it also includes: In response to the target user's modification operation, the target user's personal knowledge base is updated, and the modification operation includes at least one of adding a knowledge document and deleting a knowledge document.

5. The method according to claim 1, characterized in that Before obtaining the search statement of the target user, the method further includes: Determining recommended search content for the target user according to the user characteristics of the target user; The recommended search content is displayed to the target user.

6. The method according to claim 5, characterized in that According to the historical search behavior of the target user and the user information of the target user on the target platform, the user characteristics of the target user are pre-determined, specifically including: Determining the historical search behavior of the target user according to the historical search statements input by the target user and / or the historical modification operations of the target user on the historical recommended search content; The user characteristics of the target user are predetermined based on the historical search behavior of the target user and the user information of the target user on the target platform.

7. The method according to claim 1, characterized in that The user information of the target user on the target platform specifically includes: user registration information and user behavior data of the target user on the target platform.

8. A question-answering device, characterized in that: include: A feature module, which predetermines user features of the target user based on the historical search behavior of the target user and the user information of the target user on the target platform; An acquisition module, when the target user performs a question search, acquires the user characteristics, search statements and a pre-established personal knowledge base of the target user; A generating module, generating a reply content for the search statement according to the user characteristics, the search statement and the personal knowledge base; A display module displays the reply content to the target user.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of claims 1 to 7 is implemented.

10. A device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method described in any one of claims 1 to 7 is implemented.

Images