Interaction method and device, server and computer readable storage medium

Abstract

The invention provides an interaction method and device, a server and a computer readable storage medium. The method comprises the steps of obtaining first to-be-processed data information; determining multiple pieces of second to-be-processed data information according to the first to-be-processed data information; determining target retrieval information according to the second to-be-processed data information; and determining target data information corresponding to the first to-be-processed data according to the target retrieval information. According to the interaction method, the problem of the first to-be-processed data information proposed by the user can be obtained, and multiple pieces of associated second to-be-processed data information can be generated according to the first to-be-processed data information. Afterwards, according to the associated second to-be-processed data information, relevant answer retrieval can be carried out on the question proposed by the user, and the finally retrieved answer is fed back to the user. Therefore, compared with retrieval only according to the questions proposed by the user, retrieval of the related questions is carried out, richer answers can be provided for the user, and excessive limitation of the answers is avoided.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an interaction method, device, server and computer-readable storage medium. Background Art

[0002] In daily life, information acquisition and integration are necessary cognitive processes before analysis and decision-making, which usually requires a lot of manpower and time. Although the birth of search engines has significantly reshaped and simplified the process of human information acquisition, it is not possible to accurately obtain information when encountering complex human intentions. Alternatively, large language models such as Chat-GPT can also provide users with corresponding information.

[0003] However, although obtaining and integrating information through search engines or large language models is simple and direct, the information lacks depth and complexity, which leads to suboptimal quality. Summary of the invention

[0004] The present application provides an interactive method that can effectively answer questions raised by users.

[0005] In a first aspect, the present application provides an interaction method, the method comprising:

[0006] Obtaining first data information to be processed;

[0007] Determining a plurality of second data information to be processed according to the first data information to be processed;

[0008] Determining target retrieval information according to each of the second data to be processed;

[0009] According to the target retrieval information, target data information corresponding to the first data to be processed is determined.

[0010] In some embodiments of the present application, determining target retrieval information according to each of the second data to be processed includes:

[0011] Get retrieval mode information;

[0012] Determining initial retrieval information according to the retrieval mode information and each of the second data to be processed information;

[0013] Target retrieval information is determined according to the retrieval mode information and the initial retrieval information.

[0014] In some embodiments of the present application, determining target retrieval information according to the retrieval model information and the initial retrieval information includes:

[0015] If the retrieval mode corresponding to the retrieval mode information is the first mode, determining the initial retrieval information as the target retrieval information;

[0016] If the search mode corresponding to the search mode information is the second mode, screening the initial search information to obtain candidate search information, and determining target search information according to the candidate search information;

[0017] If the retrieval mode corresponding to the retrieval mode information is the third mode, the initial retrieval information is screened to obtain candidate retrieval information, and the candidate retrieval information is determined as target retrieval information.

[0018] In some embodiments of the present application, determining target search information according to the candidate search information includes:

[0019] Segmenting the candidate search information to obtain a plurality of first search fragment information;

[0020] Calculating similarity between each of the first search fragment information and the second data information to be processed to obtain similarity information corresponding to each of the first search fragment information;

[0021] The plurality of first search fragment information are screened according to the similarity information to obtain a plurality of second search fragment information; the plurality of second search fragment information are search fragment information whose similarity values ​​corresponding to the similarity information in the plurality of first search fragment information are greater than a similarity threshold;

[0022] A plurality of the second search fragment information are fused to obtain target search information.

[0023] In some embodiments of the present application, determining the initial retrieval information according to the retrieval mode information and the plurality of the second data to be processed information includes:

[0024] Perform information retrieval processing according to the retrieval mode information and the plurality of the second data information to be processed to obtain retrieval information to be processed;

[0025] De-duplication processing is performed on the search information to be processed to obtain initial search information.

[0026] In some embodiments of the present application, before obtaining the first data information to be processed, the method further includes:

[0027] Obtain target control instructions operated by the user;

[0028] According to the target control instruction, retrieval mode information is determined.

[0029] In some embodiments of the present application, after determining the target data information corresponding to the first to-be-processed data according to the target retrieval information, the method further includes:

[0030] Obtain a target jump instruction from the user to jump to target retrieval information;

[0031] According to the target jump instruction, jump to the target interface corresponding to the target search information.

[0032] In a second aspect, the present application further provides an interactive device, the device comprising:

[0033] An acquisition module, used for acquiring first data information to be processed;

[0034] A determination module, configured to determine a plurality of second data information to be processed according to the first data information to be processed;

[0035] The determination module is further used to determine target retrieval information according to each of the second data to be processed;

[0036] The determination module is further configured to determine target data information corresponding to the first data to be processed according to the target retrieval information.

[0037] In a third aspect, the present application also provides a server, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in any one of the interaction methods.

[0038] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to implement the steps in any one of the interaction methods.

[0039] The present application provides an interactive method, which can obtain the first data information to be processed question raised by the user, and generate multiple related second data information to be processed based on the first data information to be processed. Afterwards, the relevant answers to the questions raised by the user can be retrieved based on the related second data information to be processed, and the final retrieved answers can be fed back to the user. It can be seen that compared with searching only based on the questions raised by the user, the present application searches for related questions, which can provide users with richer answers and avoid overly limited answers. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1is a schematic diagram of a scenario of an interactive system provided in an embodiment of the present application;

[0042] Figure 2 This is a flowchart of an embodiment of the interaction method in the embodiment of the present application;

[0043] Figure 3 is a schematic diagram of a functional module of an interactive device in an embodiment of the present application;

[0044] Figure 4 It is a schematic diagram of the structure of the server in the embodiment of the present application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0046] In the description of the present application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the feature. In the description of the present application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0047] In this application, the word "exemplary" is used to mean "used as an example, illustration or description". Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. At the same time, it is to be understood that in the specific implementation of this application, when user information, user data and other related data are involved, when the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data shall comply with relevant laws, regulations and standards of relevant countries and regions.

[0048] In order to enable any person skilled in the art to implement and use the present application, the following description is provided. In the following description, details are listed for the purpose of explanation. It should be understood that those of ordinary skill in the art will recognize that the present application can be implemented without using these specific details. In other examples, known structures and processes will not be elaborated in detail to avoid unnecessary details that make the description of the present application obscure. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the widest range of principles and features disclosed in the present application.

[0049] See also Figure 1 , Figure 1 A schematic diagram of a scenario of an interactive method provided in an embodiment of the present application, wherein the interactive system may include a server 100 and a terminal device 200, wherein the server 100 and the terminal device 200 are in communication connection, and the server 100 may transmit data to the terminal device 200, and the terminal device 200 may also transmit data to the server 100, such as Figure 1 The server 100 can process the interaction method mentioned in the present application based on the first data information to be processed sent by the terminal device 200.

[0050] In the embodiment of the present application, the server 100 includes but is not limited to an independent server, and may also be a server network or server cluster composed of servers, including but not limited to a computer, a network host, a single network server, a plurality of network server sets or a cloud server composed of multiple servers. The cloud server may be composed of a large number of computers or network servers based on cloud computing.

[0051] In the embodiment of the present application, the terminal device 200 includes but is not limited to a desktop computer, a portable computer, a network server, a PDA (Personal Digital Assistant), a tablet computer, a wireless terminal device, an embedded device, a mobile phone, etc.

[0052] In the embodiments of the present application, communication between the server 100 and the terminal device 200 can be achieved through any communication method, including but not limited to mobile communications based on the 3rd Generation Partnership Project (3GPP), Long Term Evolution (LTE), and Worldwide Interoperability for Microwave Access (WiMAX), or computer network communications based on the TCP / IP Protocol Suite (TCP / IP), User Datagram Protocol (UDP), etc.

[0053] Those skilled in the art will understand that Figure 1 The application environment shown in the figure is only one application scenario of the present application solution and does not constitute a limitation on the application scenario of the present application solution. Other application environments may also include Figure 1 More or fewer servers and backend equipment as shown in Figure 1Only one server or backend device is shown, and the interactive system may also include one or more other servers and servers that can process data, which are not specifically limited here.

[0054] It should be noted that Figure 1 The scenario diagram of the interactive system shown is merely an example. The interactive system and scenario described in the embodiment of the present application are intended to more clearly illustrate the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided in the embodiment of the present application. A person of ordinary skill in the art can appreciate that with the evolution of the interactive system and the emergence of new business scenarios, the technical solution provided in the embodiment of the present application is equally applicable to similar technical problems.

[0055] like Figure 2 As shown, Figure 2 This is a flow chart of an embodiment of an interactive method in an embodiment of the present application. The interactive method may include the following steps 201 to 204:

[0056] 201. Obtain first data information to be processed.

[0057] In the embodiment of the present application, the first data information to be processed may be a question sent by a user through a terminal device, for example, a question in text form or a question in voice form, which is not limited by the specific embodiment of the present application.

[0058] 202. Determine a plurality of second data information to be processed according to the first data information to be processed.

[0059] In the embodiment of the present application, the second data information to be processed may be data information associated with the first data information to be processed. For example, if the first data information to be processed is: What is the temperature today? At this time, the second data information to be processed may be: What is the humidity today? Is it raining today? Etc. It can be seen that the second data information to be processed is highly correlated with the first data information to be processed.

[0060] In addition, in the embodiment of the present application, the associated second data information to be processed may be determined according to the first data information to be processed in the following manner:

[0061] Specifically, feature extraction is first performed on the first data information to be processed proposed by the user. For example, if the first data information to be processed is a text question, feature extraction is performed directly based on the question text; if the first data information to be processed is audio data, the audio data is converted into text data, and then feature extraction is performed.

[0062] After the feature vector of the first data information to be processed is determined, the first data information to be processed can be classified according to the feature vector to obtain the classification result of the first data information to be processed, such as weather classification, path finding classification, etc. After the classification information is determined, some related questions can be selected from the classification as the second data information to be processed.

[0063] It should be noted that in the embodiment of the present application, feature comparison can also be performed in the question library according to the feature vector corresponding to the first data information to be processed, so as to obtain the second data information to be processed in the question library that is associated with the first data information to be processed. Therefore, there are many ways to determine the second data information to be processed that is associated with the first data information to be processed, which are not limited by the specific embodiment of the present application.

[0064] In addition, it should be emphasized that after determining the second data information to be processed related to the first data information to be processed, the first data information to be processed can also be used as one of the second data information to be processed. In this way, when searching for problems based on the second data information to be processed later, the original problem of the user will not be ignored.

[0065] 203. Determine target retrieval information according to each second data information to be processed.

[0066] According to the above steps, the second data information to be processed related to the first data information to be processed can be searched for questions in the target search library, such as by searching in a search engine, so as to find answers matching the questions of each second data information to be processed.

[0067] Specifically, the search may be performed by keyword search or the like, thereby retrieving target search information that matches each second data information to be processed. Alternatively, the search may be performed on the Internet through an LLM (Large Language Model), for example, by crawling public network information through a crawler, and performing feature search on the crawled network information through the LLM large model, thereby obtaining target search information. Therefore, the embodiments of the present application do not limit the specific search method.

[0068] 204. Determine target data information corresponding to the first data to be processed according to the target search information.

[0069] After obtaining the search information matching each of the second data information to be processed, the searched answers to the questions are fed back to the user.

[0070] For example: after searching based on keywords, the text in the keyword paragraph in the searched web page results can be fed back to the user as an answer, and the specific embodiments of the present application are not limited to this.

[0071] The present application provides an interactive method, which can obtain the first data information to be processed question raised by the user, and generate multiple related second data information to be processed based on the first data information to be processed. Afterwards, the relevant answers to the questions raised by the user can be retrieved based on the related second data information to be processed, and the final retrieved answers can be fed back to the user. It can be seen that compared with searching only based on the questions raised by the user, the present application searches for related questions, which can provide users with richer answers and avoid overly limited answers.

[0072] In order to better implement the embodiment of the present application, in one embodiment of the present application, the target retrieval information is determined according to each second data information to be processed, including:

[0073] Acquire retrieval mode information; determine initial retrieval information according to the retrieval mode information and each second data to be processed information; determine target retrieval information according to the retrieval mode information and the initial retrieval information.

[0074] The above embodiment provides a solution for determining target retrieval information based on the second data information to be processed. However, in some application scenarios, users have different requirements for the level of detail of the answer. For example, if the user currently only needs a more general answer, if the level of retrieval is too deep, the deep answer retrieved at this time cannot match the user's needs. Therefore, in order to avoid wasting retrieval resources, the embodiment of the present application also provides a solution for determining the level of retrieval based on retrieval mode information.

[0075] Specifically, when the user is interacting with a question and answer, such as inputting a question to the model, the user can select a search mode, such as a light search, a medium search, a deep search, an expert search, and the like. Once the user determines the search mode, the system can obtain the search mode information and perform a search for answers of the corresponding search level based on the search mode information. For example: when the search mode is a light search, a simple search can be performed, such as taking the top search result as the initial search information; or, when the search mode is a medium search, a medium search is performed, such as taking the top 5 search results as the initial search information; or, when the search mode is a deep search, a deeper search is performed, such as taking the top 10 search results as the initial search information; or, when the search mode is an expert search, all search results are taken as the initial search information.

[0076] In addition, after the initial search information is determined, the search answer needs to be fed back to the user. Therefore, the initial search results need to be sorted out to a certain extent, rather than directly feeding back the information collected from the web page. Therefore, after obtaining the initial search information, the answer can be refined to different degrees according to the search mode information. For example: if it is a simple search, the initial search results are highly summarized at this time, including only retaining the main sentence of the answer and deleting the modifying words; if it is a moderate search, the initial search results are moderately summarized, such as retaining the modifying words on the basis of retaining the main sentence of the answer; if it is a deep search, a small answer summary is performed, such as retaining some relevant background descriptions in the web page information on the basis of retaining the sentence trunk and modifying words; if it is an expert search, the search results can be directly retained and used as answers, making the answer information richer.

[0077] It can be seen from this that grading the degree of retrieval modes and adopting different answers for the graded retrieval modes can better meet the needs of users in different retrieval scenarios.

[0078] In order to better implement the embodiment of the present application, in one embodiment of the present application, the target search information is determined according to the search model information and the initial search information, including:

[0079] If the retrieval mode corresponding to the retrieval mode information is the first mode, the initial retrieval information is determined as the target retrieval information; if the retrieval mode corresponding to the retrieval mode information is the second mode, the initial retrieval information is screened to obtain candidate retrieval information, and the target retrieval information is determined based on the candidate retrieval information; if the retrieval mode corresponding to the retrieval mode information is the third mode, the initial retrieval information is screened to obtain candidate retrieval information, and the candidate retrieval information is determined as the target retrieval information.

[0080] The above embodiment provides a solution for searching for answers according to different search levels. The embodiment of the present application also provides a solution for searching according to different search levels.

[0081] Specifically, the above embodiment provides a scheme for dividing the retrieval degree into at least 4 levels. However, in actual application scenarios, the classification levels of the retrieval mode can be appropriately reduced. For example: the first mode is a concise mode, the second mode is a research mode, and the third mode is an in-depth mode. In the concise mode, the initial retrieval information of the web page fragments obtained by retrieving each second data information to be processed can be used as the final target retrieval information. When the retrieval mode is the second mode, the initial retrieval information can be screened to a certain extent to filter out irrelevant content, such as filtering out some background content or content with low relevance, so as to obtain candidate retrieval information; then, some other web page fragments with higher relevance and candidate retrieval information are selected together as the final target retrieval information. When the retrieval mode is the third mode, filtering can be performed on the basis of the initial retrieval information, and the obtained candidate retrieval information can be used as the target retrieval information.

[0082] When answering based on different search information, the searched search information can also be integrated to a certain extent before answering. For example, in the first mode, the target search information can be integrated to a certain extent to answer the user's question as context. In the third mode, the paragraphs and other webpage fragments with high relevance to the user's question after integration are used as context to answer the user's question. In the second mode, the complete webpage content and other webpage fragments after integration are used as context to answer the user's question.

[0083] In order to better implement the embodiment of the present application, in one embodiment of the present application, determining target search information according to candidate search information includes:

[0084] The candidate search information is segmented to obtain a plurality of first search fragment information; similarity is calculated between each first search fragment information and the second data information to be processed to obtain similarity information corresponding to each first search fragment information; the plurality of first search fragment information is screened according to the similarity information to obtain a plurality of second search fragment information; the plurality of second search fragment information is the search fragment information whose similarity value corresponding to the similarity information in the plurality of first search fragment information is greater than a similarity threshold; the plurality of second search fragment information is fused to obtain target search information.

[0085] The above embodiment provides a solution for determining target retrieval information with respect to candidate retrieval information. In the embodiment of the present application, a specific calculation method is also provided.

[0086] Specifically, when the candidate search information is obtained and the information is screened, each text paragraph can be segmented for the corresponding web page in the candidate search information, so as to obtain each text paragraph, that is, multiple first search fragment information. Afterwards, since there are multiple second data information to be processed, each first search fragment information can be respectively calculated for similarity with each second data information to be processed, for example, after converting the text into a feature vector, the Euclidean distance or cosine similarity between the feature vectors is calculated to calculate the similarity information. For example, if fragment A corresponds to three second data information to be processed, three similarity information can be obtained. If one of the three similarity information has a similarity greater than the similarity threshold, it can be determined that fragment A matches a second data information to be processed. At this time, fragment A is used as a required text paragraph in the target search information, that is, the second search fragment information. Through this method, multiple second search fragment information can be obtained. Finally, multiple second search fragment information are combined with text according to the corresponding grammar to obtain the final target search information. Specifically, any text integration and fusion scheme can be seen, and the embodiment of the present application does not limit it.

[0087] In order to better implement the embodiment of the present application, in one embodiment of the present application, initial search information is determined according to the search mode information and the plurality of second data to be processed information, including:

[0088] Information retrieval processing is performed according to the retrieval mode information and a plurality of second data information to be processed to obtain retrieval information to be processed; and duplicate removal processing is performed on the retrieval information to be processed to obtain initial retrieval information.

[0089] In the above embodiments, a variety of information retrieval schemes are provided. However, based on any of the above embodiments, deduplication processing can also be performed. Specifically, since the second data information to be processed is data information associated with the first data information to be processed. Therefore, during the retrieval process, duplicate answers are inevitable. Therefore, if duplicate answers appear, the retrieved retrieval information to be processed can be deduplicated. For example: if there are answers with the same paragraph, or the same web page domain name appears, the same data can be deduplicated.

[0090] In order to better implement the embodiment of the present application, in one embodiment of the present application, before obtaining the first data information to be processed, the method further includes:

[0091] Obtain the target control instruction of the user operation; and determine the retrieval mode information according to the target control instruction.

[0092] The above embodiment provides a scheme for searching according to the retrieval mode information. Based on this, when obtaining the retrieval mode information, for example, when the user turns on the model for question-and-answer interaction, a pop-up window may pop up, which includes UIs of different retrieval modes, and the user can click on different retrieval mode UIs to determine the retrieval mode information. Alternatively, when the user starts the model, the user may be prompted to input a voice to determine the specific retrieval mode, and the determination may be made based on the user's voice instructions. Whether it is controlled by UI or voice input, it may be understood as a target control instruction. Therefore, the embodiments of the present application do not limit the target control instructions.

[0093] In order to better implement the embodiment of the present application, in one embodiment of the present application, after determining the target data information corresponding to the first to-be-processed data according to the target retrieval information, the method further includes:

[0094] Obtain a target jump instruction from the user to jump to the target search information; and jump to the target interface corresponding to the target search information according to the target jump instruction.

[0095] In some cases, when the model summarizes the corresponding answer for the user, the user has a need to check the source of the answer. Therefore, the embodiment of the present application also provides a solution for jumping to a specific web page.

[0096] Specifically, in the target search information, each paragraph may correspond to a link, which may be a hidden link or a non-hidden link, and may be specifically set according to actual conditions. The user may click on the corresponding link position of the paragraph to jump to specific web page information.

[0097] In order to better implement the interactive method in the embodiment of the present application, in addition to the interactive method, an interactive device is also provided in the embodiment of the present application, such as Figure 3 As shown, the device 300 includes:

[0098] An acquisition module 301 is used to acquire first data information to be processed;

[0099] A determination module 302 is used to determine a plurality of second data information to be processed according to the first data information to be processed;

[0100] The determination module 302 is further used to determine target retrieval information according to each second data information to be processed;

[0101] The determination module 302 is further configured to determine target data information corresponding to the first data to be processed according to the target search information.

[0102] The present application provides an interactive device, in which the acquisition module 301 can obtain the first data information to be processed question raised by the user. At the same time, the determination module 302 can generate multiple related second data information to be processed based on the first data information to be processed. Afterwards, the relevant answers to the questions raised by the user can be retrieved based on the related second data information to be processed, and the final retrieved answers can be fed back to the user. It can be seen that compared with searching only based on the questions raised by the user, the present application searches for related questions, which can provide users with richer answers and avoid overly limited answers.

[0103] In some embodiments of the present application, the determination module 302 is specifically used to:

[0104] Get retrieval mode information;

[0105] Determining initial retrieval information according to the retrieval mode information and each second data to be processed information;

[0106] Target retrieval information is determined according to the retrieval mode information and the initial retrieval information.

[0107] In some embodiments of the present application, the determination module 302 is further configured to:

[0108] If the retrieval mode corresponding to the retrieval mode information is the first mode, determining the initial retrieval information as the target retrieval information;

[0109] If the search mode corresponding to the search mode information is the second mode, the initial search information is screened to obtain candidate search information, and target search information is determined according to the candidate search information;

[0110] If the retrieval mode corresponding to the retrieval mode information is the third mode, the initial retrieval information is screened to obtain candidate retrieval information, and the candidate retrieval information is determined as target retrieval information.

[0111] In some embodiments of the present application, the determination module 302 is further configured to:

[0112] Segmenting the candidate search information to obtain a plurality of first search fragment information;

[0113] Calculate the similarity between each first search fragment information and the second data information to be processed to obtain the similarity information corresponding to each first search fragment information;

[0114] The plurality of first search fragment information are screened and processed according to the similarity information to obtain a plurality of second search fragment information; the plurality of second search fragment information are search fragment information whose similarity values ​​corresponding to the similarity information in the plurality of first search fragment information are greater than a similarity threshold;

[0115] A plurality of second search fragment information is fused to obtain target search information.

[0116] In some embodiments of the present application, the determination module 302 is further configured to:

[0117] Perform information retrieval processing according to the retrieval mode information and the plurality of second data information to be processed to obtain retrieval information to be processed;

[0118] The search information to be processed is deduplicated to obtain initial search information.

[0119] In some embodiments of the present application, the acquisition module 301 is specifically used to:

[0120] Obtain target control instructions operated by the user;

[0121] According to the target control instruction, the retrieval mode information is determined.

[0122] In some embodiments of the present application, the acquisition module 301 is further used to:

[0123] Obtain a target jump instruction from the user to jump to target retrieval information;

[0124] According to the target jump instruction, jump to the target interface corresponding to the target retrieval information.

[0125] The embodiment of the present application also provides a server, which integrates any one of the interaction methods provided in the embodiment of the present application, such as Figure 4 As shown, it shows a schematic diagram of the structure of the server involved in the embodiment of the present application, specifically:

[0126] The server may include one or more processing core processors 401, one or more computer-readable storage media memories 402, a power supply 403, an input unit 404 and other components. Those skilled in the art will appreciate that Figure 4 The server structure shown in the figure does not constitute a limitation on the server, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0127] in:

[0128] The processor 401 is the control center of the server, and uses various interfaces and lines to connect various parts of the entire server. By running or executing software programs and / or modules stored in the memory 402, and calling data stored in the memory 402, the processor 401 executes various functions of the server and processes data, thereby monitoring the server as a whole. Optionally, the processor 401 may include one or more processing cores; the processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. Preferably, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 401.

[0129] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the server, etc. In addition, the memory 402 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0130] The server also includes a power supply 403 for supplying power to each component. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, so that the power management system can manage charging, discharging, power consumption and other functions. The power supply 403 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.

[0131] The server may further include an input unit 404, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0132] Although not shown, the server may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 401 in the server will load the executable files corresponding to the processes of one or more application programs into the memory 402 according to the following instructions, and the processor 401 will run the application programs stored in the memory 402, thereby realizing various functions, such as:

[0133] Obtaining first data information to be processed;

[0134] Determining a plurality of second data information to be processed according to the first data information to be processed;

[0135] Determining target retrieval information according to each second data to be processed;

[0136] According to the target retrieval information, target data information corresponding to the first data to be processed is determined.

[0137] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0138] To this end, an embodiment of the present application provides a computer-readable storage medium, which may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in any of the interactive methods provided in the embodiments of the present application. For example, the computer program may be loaded by a processor to execute the following steps:

[0139] Obtaining first data information to be processed;

[0140] Determining a plurality of second data information to be processed according to the first data information to be processed;

[0141] Determining target retrieval information according to each second data to be processed;

[0142] According to the target retrieval information, target data information corresponding to the first data to be processed is determined.

[0143] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the detailed description of other embodiments above, and will not be repeated here.

[0144] In specific implementation, the above units or structures can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities. The specific implementation of the above units or structures can refer to the previous method embodiments, which will not be repeated here.

[0145] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0146] The above is a detailed introduction to an interactive method and device provided in an embodiment of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An interactive method, characterized in that: The method comprises: Obtaining first data information to be processed; Determining a plurality of second data information to be processed according to the first data information to be processed; Determining target retrieval information according to each of the second data to be processed; According to the target retrieval information, target data information corresponding to the first data to be processed is determined.

2. The interactive method according to claim 1, characterized in that: The step of determining target retrieval information according to each of the second data to be processed includes: Get retrieval mode information; Determining initial retrieval information according to the retrieval mode information and each of the second data to be processed information; Target retrieval information is determined according to the retrieval mode information and the initial retrieval information.

3. The interactive method according to claim 2, characterized in that: The step of determining target retrieval information according to the retrieval model information and the initial retrieval information includes: If the retrieval mode corresponding to the retrieval mode information is the first mode, determining the initial retrieval information as the target retrieval information; If the search mode corresponding to the search mode information is the second mode, screening the initial search information to obtain candidate search information, and determining target search information according to the candidate search information; If the retrieval mode corresponding to the retrieval mode information is the third mode, the initial retrieval information is screened to obtain candidate retrieval information, and the candidate retrieval information is determined as target retrieval information.

4. The interactive method according to claim 3, characterized in that: The step of determining target search information according to the candidate search information includes: Segmenting the candidate search information to obtain a plurality of first search fragment information; Calculating similarity between each of the first search fragment information and the second data information to be processed to obtain similarity information corresponding to each of the first search fragment information; The plurality of first search fragment information are screened according to the similarity information to obtain a plurality of second search fragment information; the plurality of second search fragment information are search fragment information whose similarity values ​​corresponding to the similarity information in the plurality of first search fragment information are greater than a similarity threshold; A plurality of the second search fragment information are fused to obtain target search information.

5. The interactive method according to claim 2, characterized in that: The determining of initial retrieval information according to the retrieval mode information and the plurality of second data to be processed information comprises: Perform information retrieval processing according to the retrieval mode information and the plurality of the second data information to be processed to obtain retrieval information to be processed; De-duplication processing is performed on the search information to be processed to obtain initial search information.

6. The interactive method according to claim 1, characterized in that: Before obtaining the first data information to be processed, the method further includes: Obtain target control instructions operated by the user; According to the target control instruction, retrieval mode information is determined.

7. The interactive method according to any one of claims 1 to 6, characterized in that: After determining the target data information corresponding to the first data to be processed according to the target search information, the method further includes: Obtain a target jump instruction from the user to jump to target retrieval information; According to the target jump instruction, jump to the target interface corresponding to the target search information.

8. An interactive device, characterized in that: The device comprises: An acquisition module, used for acquiring first data information to be processed; A determination module, configured to determine a plurality of second data information to be processed according to the first data information to be processed; The determination module is further used to determine target retrieval information according to each of the second data to be processed; The determination module is further configured to determine target data information corresponding to the first data to be processed according to the target retrieval information.

9. A server, characterized in that: The server includes a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the steps of the interaction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps in the interactive method according to any one of claims 1 to 7.

Images