Data processing method, electronic equipment and computer storage medium

By performing browser search and external knowledge base search in parallel in the intelligent question-and-answer system, prompt information is generated and the generative basic model is used to solve the problem of poor reply data in the traditional intelligent question-and-answer system, achieving more accurate, professional and real-time reply Data output.

CN119089026APending Publication Date: 2024-12-06UC MOBILE CHINA CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410963571.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

When obtaining reply data, the output effect of traditional intelligent question-and-answer system is poor and cannot effectively meet the users' accurate, professional and real-time needs.

Method used

By enhancing the processing of browser search and external knowledge base search in parallel during the information retrieval process, prompt information is generated, and reply data is generated using a generative basic model, combining browser web page data and external knowledge base data to improve the accuracy of reply data. and real-time.

Benefits of technology

It improves the accuracy, professionalism and real-timeness of the reply data of the intelligent question-and-answer system, enhances the output effect of the model, and can better meet users' information acquisition needs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089026A_ABST
    Figure CN119089026A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a data processing method, electronic equipment and a computer storage medium. The data processing method comprises the steps of receiving input data; aiming at the input data, performing browser retrieval through a preset interface to obtain a first retrieval result; furthermore, by taking embedding corresponding to the input data as a benchmark, performing retrieval enhancement generation processing based on an external knowledge base to obtain a second retrieval result; analyzing the input data, the first retrieval result and the second retrieval result to generate prompt information; and taking the prompt information as model input, and generating reply data for replying the input data through the generative basic model. Through the embodiment of the invention, the generative basic model can obtain more accurate, professional, timely and comprehensive reply data, namely, the output effect of the model is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and in particular to a data processing method, an electronic device, and a computer storage medium. Background Art

[0002] With the continuous development of intelligent technology, intelligent question-answering search has become an important way for people to obtain information. As an artificial intelligence application, the intelligent question-answering system can understand the questions asked by users in natural language and provide accurate and relevant answers.

[0003] Intelligent question-answering technology is usually based on a pre-trained model built based on deep learning. It uses semantic understanding to identify the user's input question intent, and then searches the knowledge base to obtain the response data corresponding to the input question.

[0004] However, in actual applications, the response data obtained through the traditional intelligent question-and-answer method has a poor response effect on the input questions, that is, the traditional intelligent question-and-answer method has the problem of poor output effect. Summary of the invention

[0005] In view of this, an embodiment of the present application provides a data processing solution to at least partially solve the above-mentioned problem.

[0006] According to a first aspect of an embodiment of the present application, a data processing method is provided, including:

[0007] Receive input data;

[0008] For the input data, a browser search is performed through a preset interface to obtain a first search result; and based on the embedding corresponding to the input data, a search enhancement generation process based on an external knowledge base is performed to obtain a second search result;

[0009] Parsing the input data, the first search result, and the second search result to generate prompt information;

[0010] The prompt information is used as a model input, and response data for responding to the input data is generated through a generative basic model.

[0011] According to a second aspect of an embodiment of the present application, another data processing method is provided, including:

[0012] Receive input data entered by the user;

[0013] Sending the input data to a preset browser interface and a service interface for providing a generative service respectively;

[0014] Receiving reply data for the input data through the service interface, wherein the reply data is generated based on the input data, a first search result, and a second search result; the first search result is obtained by searching the input data by a browser corresponding to the browser interface, and the second search result is obtained by searching an external knowledge base by a generative service corresponding to the service interface for the input data through a search-enhanced generation method;

[0015] The reply data is displayed.

[0016] According to the third aspect of an embodiment of the present application, there is provided an electronic device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; the memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform an operation corresponding to the method described in the first aspect or the second aspect.

[0017] According to a fourth aspect of an embodiment of the present application, a computer storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method described in the first aspect or the second aspect is implemented.

[0018] According to the data processing solution provided in the embodiment of the present application, after the input data is obtained, when performing information retrieval on the input data, in addition to performing retrieval enhancement generation processing based on an external knowledge base, a browser search is also performed based on a preset interface, so that the retrieval results include both the first retrieval result obtained from the browser web page and the second retrieval result retrieved from the external knowledge base; thereafter, prompt information is generated based on the above-mentioned retrieval results containing two sources, so as to generate reply data corresponding to the input data through the generative basic model according to the prompt information.

[0019] In the above-mentioned embodiments of the present application, since the browser web page data with high real-time performance and large data volume, as well as the external knowledge base data with high accuracy and professionalism are considered in parallel when performing information retrieval, the prompt information input into the generative basic model can take into account multiple requirements such as accuracy, professionalism, and real-time performance, and thus more accurate, professional, timely, and comprehensive response data can be obtained through the generative basic model, that is, the output effect of the model is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0021] Figure 1 A flowchart of a data processing method according to Embodiment 1 of the present application;

[0022] Figure 2 for Figure 1 A schematic diagram of an example scenario in the illustrated embodiment;

[0023] Figure 3 A schematic diagram of an exemplary system applicable to the data processing method of an embodiment of the present application;

[0024] Figure 4 is a flowchart of a data processing method according to Embodiment 2 of the present application;

[0025] Figure 5 is a structural block diagram of a data processing device according to Embodiment 3 of the present application;

[0026] Figure 6 is a structural block diagram of a data processing device according to Embodiment 4 of the present application;

[0027] Figure 7 This is a schematic diagram of the structure of an electronic device according to Embodiment 5 of the present application. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings 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. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the embodiments of the present application should fall within the scope of protection of the embodiments of the present application.

[0029] The specific implementation of the embodiment of the present application is further explained below in conjunction with the accompanying drawings of the embodiment of the present application.

[0030] Embodiment 1

[0031] Refer to the figure, Figure 1 The data processing method provided in the embodiment of the present application may include the following steps:

[0032] Step 102, receiving input data.

[0033] Specifically, the input data received by this step may be question data in the intelligent question-answering process. In the embodiment of the present application, the technical field to which the input data belongs, the amount of data, and the specific content of the input data are not limited, and can be customized according to actual conditions. For example: in the field of educational counseling, the input data may be academic questions raised by students; in the field of tourism planning, the input data may be tourism consulting questions; in the field of e-commerce, the input data may be commodity consulting questions regarding commodity performance, etc.

[0034] Step 104, for the input data, a browser search is performed through a preset interface to obtain a first search result; and, based on the embedding corresponding to the input data, a search enhancement generation process based on an external knowledge base is performed to obtain a second search result.

[0035] Specifically, in the embodiment of the present application, after the input data is obtained through step 102, on the one hand, by calling the preset interface in the browser, data retrieval is performed in the web page data with high real-time performance and large data volume, thereby obtaining a first retrieval result for the input data; on the other hand, through the RAG (Retrieval-Augmented Generation) operation, data retrieval is performed from a pre-built external database with higher matching degree and accuracy, thereby obtaining a second retrieval result for the input data.

[0036] Step 106, parse the input data, the first search result, and the second search result to generate prompt information.

[0037] Specifically, in order to improve the accuracy of response data generated by the model and ensure that the generated response data has a high correlation with the input data and the retrieval results, before using the generative basic model to generate response data, prompt information for guiding the model generation process can usually be generated based on the input data and the retrieval results.

[0038] After obtaining the search results from two different sources in step 104, prompt information having multiple advantages such as accuracy, professionalism, and real-time performance can be generated based on the search results and the input data.

[0039] In the embodiment of the present application, when generating prompt information based on input data, the first search result, and the second search result, the specific generation method adopted is not limited, and can be customized according to actual conditions. For example, in the embodiment of the present application, any of the following methods can be selected to generate prompt information:

[0040] In the first way, the prompt information can be obtained by splicing the input data, the first search result and the second search result. Specifically, the above three types of data can be spliced ​​together in a preset order to form the prompt information.

[0041] The second method is to fuse the input data, the first search result, and the second search result to obtain prompt information. Specifically, for example, keyword extraction can be performed on the input data, the first search result, and the second search result, respectively, so as to generate prompt information based on the extracted keywords; for another example, semantic analysis can be performed on the above three types of data, respectively, so as to combine semantically related or complementary data parts to form prompt information, and so on.

[0042] Among the above two methods of generating prompt information, the first method can obtain the prompt information by simply splicing the data. The operation process is simple and therefore the efficiency is high. The second method deeply integrates the data from the perspectives of keywords, semantics, etc. to obtain the prompt information. That is, the second method semantically condenses the input data, the first search result, and the second search result. Therefore, the semantic information of the above three types of data can be accurately represented through a smaller amount of data, thereby reducing the data processing amount of the model and improving the data processing efficiency while ensuring the semantic accuracy of the reply data.

[0043] Step 108, using the prompt information as a model input, and generating response data for responding to the input data through a generative basic model.

[0044] Specifically, after the prompt information is acquired, the prompt information may be input into the generative basic model, so that the generative basic model generates reply data for replying to the input data based on the prompt information.

[0045] In the embodiment of the present application, there is no limitation on the specific structure and parameters of the generative basic model, and any suitable generative language model can be used to perform the above step 108 to generate reply data.

[0046] According to the data processing solution provided in the embodiment of the present application, after the input data is obtained, when performing information retrieval on the input data, in addition to performing retrieval enhancement generation processing based on an external knowledge base, a browser search is also performed based on a preset interface, so that the retrieval results include both a first retrieval result obtained from the browser web page and a second retrieval result retrieved from the external knowledge base; thereafter, prompt information is generated based on the above-mentioned retrieval results containing two sources, so as to generate response data corresponding to the input data through a generative basic model according to the prompt information.

[0047] In the above-mentioned embodiments of the present application, since the browser web page data with high real-time performance and large data volume, as well as the external knowledge base data with high accuracy and professionalism are considered in parallel when performing information retrieval, the prompt information input into the generative basic model can take into account multiple requirements such as accuracy, professionalism, and real-time performance, and thus more accurate, professional, timely, and comprehensive response data can be obtained through the generative basic model, that is, the output effect of the model is improved.

[0048] The data processing method provided in the embodiment of the present application can be executed by any appropriate device with data processing capabilities, including but not limited to: a PC and a server.

[0049] Furthermore, in some of the embodiments, in the above step 104, the process of performing a browser search through a preset interface for the input data to obtain the first search result may include:

[0050] Extract key information from input data to obtain corresponding key information;

[0051] Expanding the key information to obtain at least one expanded result;

[0052] For key information and extended results, a browser search is performed through a preset interface to obtain the first search result.

[0053] Specifically, when extracting key information from input data, it may be to extract keywords from the input data, or it may be to extract semantic information from the input data, thereby using the extracted keywords or semantic information as key information; thereafter, performing synonym expansion on the key information to obtain expansion results, and performing a browser search on the obtained expansion results and key information to obtain a first search result.

[0054] In the process of obtaining the first search result, the key information of the input data is extracted, so that the non-key information in the input data that has little impact on the data search can be effectively filtered, so that the input information of the browser search is more lightweight and the search efficiency is improved. In addition, after the key information is obtained through the key information extraction, the key information is also expanded, so that the subsequent browser search is performed based on the key information and the expansion result at the same time. The advantage of the above expansion processing is that it can enrich the search expression so that it can more comprehensively cover the intention corresponding to the input data, and through the expansion of synonyms or related words, it can also effectively reduce the search deviation caused by the deviation of the word meaning and increase the number of the first search results retrieved.

[0055] Optionally, in some of the embodiments, taking the embedding corresponding to the input data as a reference, performing search enhancement generation processing based on an external knowledge base to obtain a second search result includes:

[0056] Embed the input data to obtain the corresponding embedding vector;

[0057] Based on the embedded vector, the second search result is obtained by searching from the external knowledge base through the search enhancement generation method.

[0058] Specifically, the process of obtaining the second search result through retrieval enhancement generation processing may include: embedding the input data, thereby encoding the input data into the form of an embedded vector, so as to perform similarity matching with the embedded vector corresponding to the knowledge data in the external knowledge base based on the embedded vector, thereby obtaining a second search result that matches the input data.

[0059] See also Figure 2 , Figure 2 This is a schematic diagram of a scene corresponding to the first embodiment of the present application. Figure 2 The schematic diagram shown in the figure illustrates an embodiment of the present application by taking a specific scenario as an example:

[0060] The data processing flow provided in the embodiment of the present application may include the following three stages:

[0061] The first stage is the recall stage. Figure 2 After obtaining the input data, the input data can be searched according to two different search links. One search link is: key information expansion-browser interface call-first search result. Specifically, the key information of the input data can be extracted first to obtain the key information, and the key information can be expanded to obtain the expanded result; then the browser page can be searched by calling the preset browser interface to obtain the first search result; the other search link is: embedded word processing-search enhancement generation-second search result. Specifically, the input data can be embedded first to obtain an embedded vector; then the second search result can be obtained by retrieving from the external knowledge base based on the embedded vector through search enhancement generation.

[0062] The second stage is the integration stage. Specifically, information integration can be performed based on the acquired input data, the first search result, and the second search result to generate prompt information.

[0063] The third stage is the generation stage. Specifically, the prompt information obtained in the second stage can be input into the generative basic model, so that the generative basic model can output the response data for the input data.

[0064] Optionally, in some of the embodiments, the data processing method provided in the embodiments of the present application may further include:

[0065] An interactive operation for an interactive control is received, wherein information corresponding to reply data is displayed in the interactive control, wherein the interactive control is displayed in a bubble control where the reply data is located, and the bubble control displays text content of the reply data and the interactive control;

[0066] In response to the interactive operation, jump to a page of the online document generated based on the reply data.

[0067] Specifically, after the reply data corresponding to the input data is generated, the reply data may be displayed to the user in the form of a page control so that the user can promptly learn the answer information corresponding to the input data.

[0068] Furthermore, after the reply data is generated and displayed to the user, the embodiment of the present application also provides the user with an interactive experience for the reply data. Specifically, a bubble control can be created in the page, and then the reply data and the interactive control corresponding to the reply data can be displayed through the bubble control. After that, the user can perform preset interactive operations on the interactive control so that the device generates corresponding long text data based on the reply data: an online document. For example, after the reply data is generated, the data and the interactive control can be displayed in the bubble control. When a click operation on the interactive control is detected, the online document is generated by using the reply data as the theme or outline and the generative basic model to create a long text. After that, the page can be jumped to the document page displaying the above-mentioned online document so that the user can read the online document.

[0069] In the above embodiment of the present application, the reply data is displayed by means of a bubble control. Since the bubble control usually has a unique shape and style, and can also be configured with animation effects, the fun and attractiveness of the user experience can be improved. In addition, by setting an interactive control in the bubble control and guiding the user to perform a preset interactive operation, an online document for the reply data can be further generated for the user, so that the user can obtain more detailed and comprehensive relevant information, which can further improve the user experience from the perspective of interactive experience and comprehensive information acquisition.

[0070] See also Figure 3 , Figure 3 This is a schematic diagram of an exemplary system for the data processing method of the embodiment of the present application. For ease of understanding, first combine Figure 3 The application scenarios of the data processing method provided in the embodiments of the present application are explained.

[0071] like Figure 3As shown, the system 300 may include a server 302, a communication network 304 and / or one or more user devices (ie, client devices) 306. Figure 3 The example in FIG. 1 is a plurality of user devices.

[0072] The server 302 may be any suitable device with a generative service deployed thereon, including but not limited to a server cluster, a computing cloud server cluster, etc. In some embodiments, the server 302 may perform any suitable function. For example, in some embodiments, the server 302 may be used to search an external knowledge base through a search enhancement generator according to the input data to obtain a second search result, and to generate reply data of the input data based on the input data and the search result, and send it to the corresponding user device 306 for the user to view.

[0073] In some embodiments, the communication network 304 can be any suitable combination of one or more wired and / or wireless networks. For example, the communication network 304 can include any one or more of the following: the Internet, an intranet, a wide area network (WAN), a local area network (LAN), a wireless network, a digital subscriber line (DSL) network, a frame relay network, an asynchronous transfer mode (ATM) network, a virtual private network (VPN) and / or any other suitable communication network. The user device 306 can be connected to the communication network 304 via one or more communication links (e.g., communication link 312), and the communication network 304 can be linked to the service end 302 via one or more communication links (e.g., communication link 314). The communication link can be any communication link suitable for transmitting data between the user device 306 and the service end 302, such as a network link, a dial-up link, a wireless link, a hard-wired link, any other suitable communication link or any suitable combination of such links.

[0074] User equipment 306 may include any one or more user equipment suitable for data processing. In some embodiments, user equipment 306 may include any suitable type of equipment. For example, in some embodiments, user equipment 306 may include a mobile device, a tablet computer, a laptop computer, a desktop computer, and / or any other suitable type of user equipment.

[0075] Embodiment 2

[0076] Reference Figure 4 , Figure 4is a flowchart of a data processing method according to the second embodiment of the present application. The data processing method provided in the embodiment of the present application can be Figure 3 The user equipment 306 in the system shown in the figure executes. Specifically, the data processing method provided in this embodiment includes the following steps:

[0077] Step 402: receiving input data input by a user.

[0078] Specifically, the input data received by this step may be question data in the intelligent question-answering process. In the embodiment of the present application, the technical field to which the input data belongs, the amount of data, and the specific content of the input data are not limited, and can be customized according to actual conditions.

[0079] In addition, the method for receiving input data in the present application example is not limited, and any suitable method can be used to receive input data input by the user. For example, the data input by the user in the preset input box of the page can be monitored, and the monitored data can be used as input data; the voice information input by the user can also be monitored, and the input data can be obtained by extracting the text of the voice information, and so on.

[0080] Step 404 , sending the input data to a preset browser interface and a service interface for providing generative services respectively.

[0081] Specifically, a browser interface for browser retrieval can be pre-set, and a service interface for providing generative services can be pre-set on the server. After the input data is obtained through step 402, the input data can be sent to the above interfaces respectively, and a browser page retrieval is performed through the browser interface to obtain a first retrieval result; a retrieval enhancement generation process based on an external knowledge base is performed through the service interface provided by the server to obtain a second retrieval result; prompt information is generated based on the input data, the first retrieval result and the second retrieval result, and reply data corresponding to the input data is generated through the generative basic model based on the prompt information.

[0082] Step 406, receiving reply data for the input data through the service interface, wherein the reply data is generated based on the input data, a first search result and a second search result; the first search result is obtained by a browser corresponding to the browser interface searching for the input data, and the second search result is obtained by a generative service corresponding to the service interface searching for the input data through an external knowledge base through a search enhancement generation method.

[0083] Specifically, after the client sends the input data to the service interface of the server, the reply data that the user wants to obtain can be generated through the generative service provided by the server. In the embodiment of the present application, the specific process of generating the first search result and the second search result, and the process of generating the reply data based on the input data, the first search result and the second search result can refer to the content of the above-mentioned embodiment 1, which will not be repeated here.

[0084] Step 408, display the reply data.

[0085] Specifically, after the reply data is obtained, the reply data may be displayed on the current page for the convenience of user reading.

[0086] Optionally, in some of the embodiments, the specific manner of displaying the reply data may include:

[0087] The content of the reply data is displayed through the bubble control, and the interactive controls corresponding to the reply data are displayed;

[0088] An interactive operation on an interactive control is received, and in response to the interactive operation, an online document generated based on the reply data is displayed.

[0089] Specifically, after the reply data corresponding to the input data is obtained, the reply data may be displayed to the user in the form of a page control so that the user can promptly learn the answer information corresponding to the input data.

[0090] Furthermore, after the reply data is generated and displayed to the user, the embodiment of the present application also provides the user with an interactive experience for the reply data. Specifically, a bubble control can be created in the page, and then the reply data and the interactive control corresponding to the reply data can be displayed through the bubble control. After that, the user can perform preset interactive operations on the interactive control so that the device generates corresponding long text data based on the reply data: an online document. For example, after the reply data is generated, the data and the interactive control can be displayed in the bubble control. When a click operation on the interactive control is detected, the online document is generated by using the reply data as the theme or outline and the generative basic model to create a long text. After that, the page can be jumped to the document page displaying the above-mentioned online document so that the user can read the online document.

[0091] In the above embodiment of the present application, the reply data is displayed by means of a bubble control. Since the bubble control usually has a unique shape and style, and can also be configured with animation effects, the fun and attractiveness of the user experience can be improved. In addition, by setting an interactive control in the bubble control and guiding the user to perform a preset interactive operation, an online document for the reply data can be further generated for the user, so that the user can obtain more detailed and comprehensive relevant information, which can further improve the user experience from the perspective of interactive experience and comprehensive information acquisition.

[0092] Optionally, in some of the embodiments, an option for exporting the document is provided in the page displaying the online document;

[0093] The method also includes:

[0094] A trigger operation on an option is received, and in response to the trigger operation, the online document is exported as an offline document in a preset format.

[0095] Specifically, after generating an online document, in order to facilitate user saving, in the embodiment of the present application, a document export option is also set in the page displaying the online document. When the user wants to save the above document, the preset trigger operation can be performed on the document export option. After the user device detects the trigger operation for the option, the online document is exported to an offline document in a preset format. The above embodiment of the present application further provides the user with a document saving function. Through a simple trigger operation, the offline saving of the online document can be realized, thereby further improving the user's experience.

[0096] Embodiment 3

[0097] Figure 5 1 is a structural block diagram of a data processing device according to Embodiment 3 of the present application. The data processing device provided in the embodiment of the present application includes:

[0098] A first receiving module 502, configured to receive input data;

[0099] The search result obtaining module 504 is used to perform a browser search through a preset interface for the input data to obtain a first search result; and to perform a search enhancement generation process based on an external knowledge base based on the embedding corresponding to the input data to obtain a second search result;

[0100] A prompt information generating module 506, used for parsing input data, the first search result, and the second search result, and generating prompt information;

[0101] The reply data generation module 508 is used to use the prompt information as a model input and generate reply data for replying to the input data through a generative basic model.

[0102] Optionally, in some embodiments, the search result obtaining module 504, when executing the step of performing a browser search through a preset interface for input data to obtain a first search result, is specifically used to:

[0103] Extract key information from input data to obtain corresponding key information;

[0104] Expanding the key information to obtain at least one expanded result;

[0105] For key information and extended results, a browser search is performed through a preset interface to obtain the first search result.

[0106] Optionally, in some embodiments, the retrieval result obtaining module 504, when executing the step of performing retrieval enhancement generation processing based on an external knowledge base based on the embedding corresponding to the input data to obtain the second retrieval result, is specifically used to:

[0107] Embed the input data to obtain the corresponding embedding vector;

[0108] Based on the embedded vector, the second search result is obtained by searching from the external knowledge base through the search enhancement generation method.

[0109] Optionally, in some embodiments, the prompt information generating module 506 is specifically configured to:

[0110] The input data, the first search result and the second search result are spliced ​​and / or merged to obtain prompt information.

[0111] Optionally, in some of the embodiments, the data processing device may further include:

[0112] An interactive module, configured to receive an interactive operation on an interactive control, wherein information corresponding to reply data is displayed in the interactive control, wherein the interactive control is displayed in a bubble control where the reply data is located, and the bubble control displays text content of the reply data and the interactive control;

[0113] In response to the interactive operation, jump to a page of the online document generated based on the reply data.

[0114] Optionally, in some of the embodiments, the data processing device may further include:

[0115] The online document generation module is used to generate online documents based on the reply data.

[0116] The data processing device of this embodiment is used to implement the corresponding data processing method in the above-mentioned embodiment 1, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here. In addition, the functional implementation of each module in the data processing device of this embodiment can refer to the description of the corresponding part in the above-mentioned method embodiment 1, which will not be described in detail here.

[0117] Embodiment 4

[0118] Figure 6 1 is a structural block diagram of a data processing device according to Embodiment 4 of the present application. The data processing device provided in the embodiment of the present application includes:

[0119] The second receiving module 602 is used to receive input data input by the user;

[0120] A data sending module 604, used to send input data to a preset browser interface and a service interface for providing a generative service;

[0121] The reply data receiving module 606 is used to receive reply data for the input data through the service interface, wherein the reply data is generated based on the input data, the first search result, and the second search result; the first search result is obtained by the browser corresponding to the browser interface searching for the input data, and the second search result is obtained by the generated service corresponding to the service interface searching for the input data through the external knowledge base through the search enhancement generation method;

[0122] The display module 608 is used to display the reply data.

[0123] Optionally, in some embodiments, the display module 608 is specifically configured to:

[0124] The content of the reply data is displayed through the bubble control, and the interactive controls corresponding to the reply data are displayed;

[0125] An interactive operation on an interactive control is received, and in response to the interactive operation, an online document generated based on the reply data is displayed.

[0126] Optionally, in some of the embodiments, an option for exporting the document is provided in the page displaying the online document;

[0127] The data processing device also includes:

[0128] The document export module is used to receive a trigger operation on an option, and in response to the trigger operation, export the online document into an offline document in a preset format.

[0129] Optionally, in some of the embodiments, information corresponding to the reply data is displayed in the interactive control.

[0130] The data processing device of this embodiment is used to implement the corresponding data processing method in the aforementioned embodiment 2, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here. In addition, the functional implementation of each module in the data processing device of this embodiment can refer to the description of the corresponding part in the aforementioned method embodiment 2, which will not be described in detail here.

[0131] Embodiment 5

[0132] Reference Figure 7 , shows a schematic diagram of the structure of an electronic device according to Embodiment 5 of the present application. The specific embodiments of the present application do not limit the specific implementation of the electronic device.

[0133] like Figure 7 As shown, the electronic device may include: a processor (processor) 702, a communication interface (Communications Interface) 704, a memory (memory) 706, and a communication bus 708.

[0134] in:

[0135] The processor 702 , the communication interface 704 , and the memory 706 communicate with each other via a communication bus 708 .

[0136] The communication interface 704 is used to communicate with other electronic devices or servers.

[0137] The processor 702 is used to execute the program 710, and specifically can execute the relevant steps in the above method embodiment.

[0138] Specifically, the program 710 may include program codes, which include computer operation instructions.

[0139] The processor 702 may be a CPU, or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs; or may be processors of different types, such as one or more CPUs and one or more ASICs.

[0140] The memory 706 is used to store the program 710. The memory 706 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.

[0141] The program 710 may include multiple computer instructions. Specifically, the program 710 may enable the processor 702 to execute operations corresponding to the method described in any of the aforementioned method embodiments through the multiple computer instructions.

[0142] The specific implementation of each step in program 710 can refer to the corresponding description of the corresponding steps and units in the above method embodiment, and has corresponding beneficial effects, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described devices and modules can refer to the corresponding process description in the above method embodiment, which will not be repeated here.

[0143] The present application also provides a computer storage medium on which a computer program is stored, and when the program is executed by a processor, the method described in any of the above-mentioned multiple method embodiments is implemented. The computer storage medium includes but is not limited to: a compact disk (CD-ROM), a random access memory (RAM), a floppy disk, a hard disk or a magneto-optical disk, etc.

[0144] An embodiment of the present application also provides a computer program product, including computer instructions, which instruct a computing device to execute operations corresponding to any one of the above-mentioned multiple method embodiments.

[0145] In addition, it should be noted that the user-related information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to sample data used to train the model, data used for analysis, stored data, displayed data, etc.) involved in the embodiments of the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0146] It should be pointed out that, according to the needs of implementation, the various components / steps described in the embodiments of the present application can be split into more components / steps, or two or more components / steps or partial operations of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of the present application.

[0147] The above-mentioned method according to the embodiment of the present application can be implemented in hardware, firmware, or implemented as software or computer code that can be stored in a recording medium (such as a CD-ROM, RAM, floppy disk, hard disk or magneto-optical disk), or implemented as a computer code originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded through a network and to be stored in a local recording medium, so that the method described herein can be stored in such software processing on a recording medium using a general-purpose computer, a dedicated processor or programmable or dedicated hardware (such as an Application Specific Integrated Circuit (ASIC) or a Field Programmable Gate Array (FPGA)). It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component (for example, a random access memory (RAM), a read-only memory (ROM), a flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by a computer, a processor or hardware, the method described herein is implemented. In addition, when a general purpose computer accesses code for implementing the methods shown herein, the execution of the code transforms the general purpose computer into a special purpose computer for executing the methods shown herein.

[0148] Those of ordinary skill in the art will appreciate that the units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present application.

[0149] The above implementation methods are only used to illustrate the embodiments of the present application, and are not limitations on the embodiments of the present application. Ordinary technicians in the relevant technical field can make various changes and modifications without departing from the spirit and scope of the embodiments of the present application. Therefore, all equivalent technical solutions also belong to the scope of the embodiments of the present application. The scope of patent protection of the embodiments of the present application should be limited by the claims.

Claims

1. A data processing method, comprising: Receive input data; For the input data, a browser search is performed through a preset interface to obtain a first search result; and based on the embedding corresponding to the input data, a search enhancement generation process based on an external knowledge base is performed to obtain a second search result; Parsing the input data, the first search result, and the second search result to generate prompt information; The prompt information is used as a model input, and response data for responding to the input data is generated through a generative basic model.

2. The method according to claim 1, wherein: The step of performing a browser search through a preset interface for the input data to obtain a first search result includes: Extracting key information from the input data to obtain corresponding key information; Expanding the key information to obtain at least one expanded result; A browser search is performed through a preset interface for the key information and the extended result to obtain the first search result.

3. The method according to claim 1 or 2, wherein: The step of performing search enhancement generation processing based on an external knowledge base based on the embedding corresponding to the input data to obtain a second search result includes: Performing embedding processing on the input data to obtain a corresponding embedding vector; The second search result is obtained by searching from the external knowledge base using the embedding vector as a reference through a search enhancement generation method.

4. The method according to claim 1, wherein: The step of parsing the input data, the first search result, and the second search result to generate prompt information includes: The input data, the first search result and the second search result are concatenated and / or merged to obtain the prompt information.

5. The method according to claim 1, wherein: The method further comprises: An interactive operation on an interactive control is received, wherein the interactive control displays information corresponding to the reply data, wherein the interactive control is displayed in a bubble control where the reply data is located, and the bubble control displays text content of the reply data and the interactive control; In response to the interactive operation, jump to a page of an online document generated based on the reply data.

6. The method according to claim 5, wherein: The method further comprises: The online document is generated based on the response data.

7. A data processing method, comprising: Receive input data entered by the user; Sending the input data to a preset browser interface and a service interface for providing a generative service respectively; Receiving reply data for the input data through the service interface, wherein the reply data is generated based on the input data, a first search result, and a second search result; the first search result is obtained by searching the input data by a browser corresponding to the browser interface, and the second search result is obtained by searching an external knowledge base by a generative service corresponding to the service interface for the input data through a search-enhanced generation method; The reply data is displayed.

8. The method according to claim 7, wherein: The displaying of the reply data includes: Displaying the content of the reply data through a bubble control, and displaying an interactive control corresponding to the reply data; An interactive operation on the interactive control is received, and in response to the interactive operation, an online document generated based on the reply data is displayed.

9. The method according to claim 8, wherein: An option for exporting the document is provided in the page displaying the online document; The method further comprises: A trigger operation for the option is received, and in response to the trigger operation, the online document is exported as an offline document in a preset format.

10. The method according to claim 8, wherein: The interactive control displays information corresponding to the reply data.

11. An electronic device, comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform an operation corresponding to the method according to any one of claims 1 to 10.

12. A computer storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.

13. A computer program product, comprising computer instructions, wherein the computer instructions instruct a computing device to execute operations corresponding to the method according to any one of claims 1 to 10.