Data processing method, electronic equipment and computer storage medium

Through thinking chain technology, the intelligent text creation process is decomposed and the final content is generated by intermediate data regenerating, solving the shortcomings of richness and comprehensiveness of content generation in the existing technology, and achieving more accurate and reasonable content creation.

CN119089027APending Publication Date: 2024-12-06UC MOBILE CHINA CO LTD

Patent Information

Application Number
CN202410963768.2
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

The text content generated by existing intelligent text creation technology is poor in richness and comprehensiveness and cannot effectively cover user needs.

Method used

Using thinking chain technology, the content creation process is broken down into two logical reasoning steps: first generate intermediate data based on the input data, and then generate final content data based on the intermediate data, and improve the richness and accuracy of the content through two retrievals.

Benefits of technology

By decomposing the creative process, more rich and comprehensive content data are obtained, which improves the accuracy and rationality of content data and meets users' diverse needs for content.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089027A_ABST
    Figure CN119089027A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a data processing method, electronic equipment and a computer storage medium, and the data processing method comprises the following steps: receiving input data, and initiating first retrieval for the input data to obtain a first retrieval result; analyzing the received input data and the generated first retrieval result, generating first prompt information, and performing generation processing on the first prompt information through a generative basic model to obtain intermediate data; initiating second retrieval for the intermediate data to obtain a second retrieval result; and analyzing the intermediate data and the second retrieval result to generate second prompt information, and performing generation processing on the second prompt information through the generative basic model to obtain content data. According to the embodiment of the invention, the generated content data can be richer and more comprehensive, and meanwhile, the accuracy and rationality of the content data can be 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] Intelligent text creation is the process of using artificial intelligence technology, especially natural language processing technology, to generate or assist in the generation of text content. Through intelligent text creation technology, news reports, articles, stories, poems and other text content can be created according to user requirements.

[0003] At present, the main process of intelligent text creation is: based on the pre-training model built on deep learning, it recognizes the input information such as the creation requirements entered by the user through semantic understanding, and then searches the knowledge base for the input information, so as to generate and output the text content as a whole at one time according to the search results.

[0004] The text content generated by the above method is less rich and comprehensive. 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] receiving input data, initiating a first search on the input data, and obtaining a first search result;

[0008] Parsing the received input data and the generated first search result to generate first prompt information, and performing generation processing on the first prompt information through a generative basic model to obtain intermediate data;

[0009] Initiate a second search for the intermediate data to obtain a second search result;

[0010] The intermediate data and the second search result are parsed to generate second prompt information, and the second prompt information is generated and processed by the generative basic model to obtain content data.

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

[0012] Receive input data;

[0013] Sending the input data to a browser interface for providing browser retrieval and a service interface for providing generation services, so as to respectively perform a first retrieval on the input data through a browser corresponding to the browser interface and through a retrieval enhancement service corresponding to the service interface;

[0014] receiving intermediate data generated based on the input data and fed back by the service interface, wherein the intermediate data is generated based on the input data and a first search result of the first search;

[0015] Sending the intermediate data to the browser interface and the service interface, so as to perform a second search on the intermediate data through a browser corresponding to the browser interface and through a search enhancement service corresponding to the service interface, respectively;

[0016] Receive content data generated based on the intermediate data fed back by the service interface, and display the content data, where the content data is generated based on the intermediate data and a second search result of the second search.

[0017] 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.

[0018] 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.

[0019] According to the data processing solution provided in the embodiment of the present application, a search is first performed on the input data to obtain a first search result, and intermediate data is generated based on the content of the first search result; then, a second search is performed on the intermediate data to obtain a second search result, and then the final content data corresponding to the input data is generated based on the content of the second search result.

[0020] In the embodiment of the present application, based on the thought chain technology, the content creation process is decomposed into two logical reasoning steps: the first step is to generate intermediate data based on the search results for the input data, and the second step is to generate content data based on the search results for the intermediate data. On the one hand, the intermediate data generated based on the first search result usually involves content that the first search result does not cover. Therefore, a second search for the intermediate data can obtain a second search result with richer and more comprehensive content, which can make the content data generated based on the second search result with richer and more comprehensive content richer and more comprehensive; on the other hand, decomposing the creation process into different steps through the thought chain technology can help the generative basic model to more clearly display its thinking process, thereby generating more accurate and reasonable content data, that is, it helps to improve the accuracy and rationality of the content data. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] 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.

[0022] Figure 1 A flowchart of a data processing method according to Embodiment 1 of the present application;

[0023] Figure 2 for Figure 1 A schematic diagram of an example scenario in the illustrated embodiment;

[0024] Figure 3 A schematic diagram of an exemplary system applicable to the data processing method of an embodiment of the present application;

[0025] Figure 4 is a flowchart of a data processing method according to Embodiment 2 of the present application;

[0026] Figure 5 is a structural block diagram of a data processing device according to Embodiment 3 of the present application;

[0027] Figure 6 is a structural block diagram of a data processing device according to Embodiment 4 of the present application;

[0028] Figure 7 This is a schematic diagram of the structure of an electronic device according to Embodiment 5 of the present application. DETAILED DESCRIPTION

[0029] 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.

[0030] 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.

[0031] Embodiment 1

[0032] Refer to the figure, Figure 1 The data processing method provided in the embodiment of the present application may include the following steps:

[0033] Step 102: receiving input data, initiating a first search on the input data, and obtaining a first search result.

[0034] Specifically, the input data may be data used for intelligent creation. For example, the input data may include one or more of the following: creation theme, creation requirements (such as word count requirements, creation style requirements), etc. In the embodiment of the present application, there is no limitation on the amount and specific content of the input data, and the setting may be customized according to the actual situation.

[0035] After the input data is obtained, data retrieval can be performed in a preset database based on the input data to recall a first retrieval result associated with the input data. In the embodiment of the present application, there is no limitation on the retrieval method used to obtain the first retrieval result, the specific content of the preset database, and the construction method, and any appropriate retrieval method can be used according to the actual situation.

[0036] Step 104 , parse the received input data and the generated first search result, generate first prompt information, and perform generation processing on the first prompt information through the generative basic model to obtain intermediate data.

[0037] Specifically, in order to improve the accuracy of model-generated data and ensure that the generated data has a high correlation with the input data and the search results, before using the generative basic model to generate data, it is usually possible to first generate prompt information for guiding the model generation process based on the input data and the search results. Therefore, in an embodiment of the present application, after obtaining the first search result, a first prompt information for guiding the generative basic model to generate intermediate data is generated based on the input data and the first search result. The first prompt information may be information including material information, generation requirements and other information required for data generation by the generative basic model. For example: in terms of text creation, the first prompt information may be information including: creation theme, creation requirements (word count requirements, style requirements) and other content. Exemplarily, the first prompt information may be "Please generate a text creation outline based on the following materials."

[0038] In the embodiments of the present application, there is no limitation on the specific content of the generated intermediate data. For example, in terms of text creation, the intermediate data may be text outline data, which may be subsequently used for secondary creation based on the text outline data to obtain the text content data that the user ultimately wants to obtain. For another example, in terms of video creation or image creation, the intermediate data may be video draft data or image draft data, which may be subsequently used for secondary creation based on the above draft data to obtain the ultimately desired video or image data, and so on.

[0039] In terms of the text creation scenario, the generated text outline data can be understood as guiding data in the text creation process, which summarizes the main parts of the final generated text content and the key points of each part. For example, when the user inputs data as: "Please write an article on the theme of XX brand car", the text outline data obtained through the above step 104 may include the following content: "1. The above overview of XX car; 2. Product positioning and design; 3. Technical characteristics and configuration; ......".

[0040] Step 106: initiate a second search for the intermediate data to obtain a second search result.

[0041] Specifically, after the intermediate data is generated, in the embodiment of the present application, a secondary search is performed based on the intermediate data again, thereby obtaining creative materials with a higher degree of relevance to the intermediate data: the second search result. Compared with the input data, the content of the intermediate data is usually more extensive and comprehensive. Therefore, compared with the first search result obtained by searching based on the input data, the content of the second search result obtained by searching based on the intermediate data will be richer and more comprehensive.

[0042] In the embodiment of the present application, there is no limitation on the search method used to obtain the second search result, the specific content and construction method of the preset database, and any appropriate search method can be used according to actual conditions.

[0043] Step 108 , parsing the intermediate data and the second search result to generate second prompt information, and performing generation processing on the second prompt information through the generative basic model to obtain content data.

[0044] Specifically, similar to step 104, after obtaining the second search result associated with the intermediate data, the second prompt information can be generated based on the intermediate data and the second search result to guide the generative basic model to generate the final content data. Since the second search result contains more comprehensive and richer information, the content data finally generated by the second prompt information generated based on the intermediate data and the second search result will also be richer and more comprehensive.

[0045] 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:

[0046] The data processing flow provided in the embodiment of the present application may include the following two stages:

[0047] The first stage is the intermediate data generation stage. Specifically, after obtaining the input data, you can search based on the input data ( Figure 2 ), thereby obtaining a first search result; then, integrating the input data and the first search result to generate first prompt information; inputting the first prompt information into the generative basic model to output intermediate data through the generative basic model.

[0048] The second stage is the content data generation stage. After the intermediate data is generated in the first stage, the intermediate data can be used as new input data to perform subsequent retrieval and generation processes. Specifically: Retrieval is performed again based on the intermediate data ( Figure 2 ), thereby obtaining a second search result; then, integrating the intermediate data and the second search result to generate second prompt information; inputting the second prompt information into the generative basic model to obtain the final content data created through the generative basic model.

[0049] In the data processing method provided in the embodiment of the present application, based on the thought chain technology, the creative process is decomposed into two logical reasoning steps: the first step is to generate intermediate data based on the search results for the input data, and the second step is to generate content data based on the search results for the intermediate data. On the one hand, the intermediate data generated based on the first search result usually involves content that the first search result does not cover. Therefore, a second search for the intermediate data can obtain a second search result with richer and more comprehensive content, which can make the content data generated based on the second search result with richer and more comprehensive content richer and more comprehensive; on the other hand, decomposing the creative process into different steps through the thought chain technology can help the generative basic model to more clearly display its thinking process, thereby generating more accurate and reasonable content data, that is, it helps to improve the accuracy and rationality of the content data.

[0050] 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.

[0051] Optionally, in some of the embodiments, the process of initiating a second search for the intermediate data and obtaining a second search result may include:

[0052] Receiving modified intermediate data generated by performing a modification operation on the intermediate data;

[0053] Based on the modified intermediate data, a second search is initiated to obtain a second search result.

[0054] Specifically, in the embodiment of the present application, considering that the intermediate data is generated by the generative basic model, there may be a certain gap between the intermediate data and the user's expectations. In order to make the final generated content data more in line with user needs, after the intermediate data is generated through the above step 104, the intermediate data can be displayed to the user first, so that the user can modify the intermediate data generated by the model according to his own needs, thereby obtaining intermediate data that meets the creation needs.

[0055] Optionally, in some of the embodiments, the process of initiating a second search for the intermediate data and obtaining a second search result may include:

[0056] For the intermediate data, a browser search is performed through a preset interface to obtain a first sub-intermediate search result; and based on the embedding corresponding to the intermediate data, a search enhancement generation process based on an external knowledge base is performed to obtain a second sub-intermediate search result;

[0057] The first sub-intermediate search result and the second sub-intermediate search result are merged to obtain the second search result.

[0058] Specifically, in the above-mentioned embodiments of the present application, after generating the intermediate data, 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 sub-intermediate retrieval result for the intermediate 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 sub-intermediate retrieval result for the intermediate data; thereafter, based on the first sub-intermediate retrieval result with high real-time performance and the second sub-intermediate retrieval result with high matching degree and accuracy, a second retrieval result that takes into account real-time performance, matching degree and accuracy can be obtained.

[0059] Optionally, in some of the embodiments, the process of performing a browser search on the intermediate data through a preset interface to obtain the first sub-intermediate search result may include:

[0060] Extract key information from intermediate data to obtain corresponding intermediate key information;

[0061] Expanding the intermediate key information to obtain at least one intermediate data expansion result;

[0062] Based on the intermediate key information and the intermediate data extension results, a browser search is performed through a preset interface to obtain a first sub-intermediate search result.

[0063] Specifically, when extracting key information from intermediate data, keyword extraction can be performed on the intermediate data, or semantic information extraction can be performed on the intermediate data, so that the extracted keywords or semantic information are used as intermediate key information; then, synonym expansion is performed on the above intermediate key information to obtain intermediate data expansion results, and a browser search is performed on the obtained intermediate data expansion results and intermediate key information to obtain a first sub-intermediate search result.

[0064] In the process of obtaining the first sub-intermediate search result, key information is extracted from the intermediate data. Therefore, non-key information in the intermediate data that has little impact on data retrieval can be effectively filtered, thereby making the input information of the browser search more lightweight and improving the search efficiency. In addition, after the intermediate key information is obtained through key information extraction, the intermediate key information is also expanded, so that subsequent browser searches are performed based on the intermediate key information and the intermediate data expansion results at the same time. The advantages of the above expansion processing are: it can enrich the search expression so that it covers the intention corresponding to the intermediate data more comprehensively, and through the expansion of synonyms or related words, it can also effectively reduce the search deviation caused by word meaning deviation and increase the number of retrieved first sub-intermediate search results.

[0065] Optionally, in some of the embodiments, the process of initiating a first search on the input data and obtaining a first search result may also include:

[0066] For the input data, a browser search is performed through a preset interface to obtain a first sub-input data 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 sub-input data search result;

[0067] The first sub-input data retrieval result and the second sub-input data retrieval result are integrated to obtain a first retrieval result.

[0068] Specifically, in the above-mentioned embodiment of the present application, similar to obtaining the second search result, after obtaining the input data, 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 the first sub-input data retrieval result for the input data; on the other hand, through the RAG operation, data retrieval is performed from a pre-built external database with higher matching degree and accuracy, thereby obtaining the second sub-input data retrieval result for the input data; thereafter, based on the first sub-input data retrieval result with high real-time performance and the second sub-input data retrieval result with high matching degree and accuracy, the first retrieval result that takes into account real-time performance, matching degree and accuracy can be obtained.

[0069] Optionally, in some of the embodiments, the process of performing a browser search on the input data through a preset interface to obtain a first sub-input data search result may include:

[0070] Extract key information from input data to obtain corresponding key information of input data;

[0071] Expanding key information of input data to obtain at least one input data expansion result;

[0072] Based on the input data key information and the input data expansion result, a browser search is performed through a preset interface to obtain a first sub-input data search result.

[0073] Specifically, similar to the above-mentioned process of extracting key information from intermediate data, when extracting key information from input data, keyword extraction may be performed on the input data, or semantic information extraction may be performed on the input data, thereby using the extracted keywords or semantic information as key information; thereafter, synonym expansion is performed on the above-mentioned key information to obtain input data expansion results, and a browser search is performed on the obtained input data expansion results and key information, thereby obtaining a first sub-input data retrieval result.

[0074] In the process of obtaining the first sub-input data retrieval result, the input data is subjected to key information extraction, so that non-key information in the input data that has little impact on data retrieval can be effectively filtered, thereby making the input information retrieved by the browser more lightweight and improving the retrieval efficiency. In addition, after the key information is obtained through key information extraction, the key information is also expanded, so that subsequent browser retrieval is performed based on the key information and the input data expansion results at the same time. The advantages of the above expansion processing are: it can enrich the retrieval expression to make it more comprehensive. The intention corresponding to the input data, and through the expansion of synonyms or related words, it can also effectively reduce the retrieval deviation caused by the deviation of word meaning, and increase the number of retrieved first sub-input data retrieval results.

[0075] Optionally, in some of the embodiments, parsing the received input data and the generated first search result to generate the first prompt information includes: concatenating and / or fusing the received input data and the generated first search result to obtain the first prompt information;

[0076] Parsing the intermediate data and the second search result to generate the second prompt information includes: concatenating and / or fusing the intermediate data and the second search result to obtain the second prompt information.

[0077] Specifically, when the first prompt information or the second prompt information is generated, it can be obtained by splicing various data or by fusing various data.

[0078] Among the above two methods, the method of obtaining prompt information by simply splicing the data has a simple operation process and is therefore more efficient; the second method is to deeply integrate the data from the perspectives of keywords, semantics, etc. to obtain prompt information. That is, the second method condenses the semantics of each data. Therefore, the semantic information of each data can be accurately represented through a smaller amount of data, thereby reducing the data processing volume of the model and improving data processing efficiency while ensuring the semantic accuracy of the generated data.

[0079] Optionally, in some of the embodiments, the method further comprises:

[0080] An interactive operation for an interactive control is received, wherein information corresponding to the content data is displayed in the interactive control, the interactive control is displayed in a bubble control where the content data is located, and the bubble control displays the content data and the interactive control;

[0081] In response to the interactive operation, jump to a page of the online document generated based on the content data.

[0082] Specifically, after the content data is obtained, the content data may be displayed through the control so that the user can learn about the content data corresponding to the input data in a timely manner.

[0083] Furthermore, after generating and displaying the content data to the user, the embodiment of the present application also provides the user with an interactive experience for the content data, specifically: a bubble control can be created in the page, and then the content data and the interactive control corresponding to the content data can be displayed through the bubble control. After that, the user can perform a preset interactive operation on the interactive control so that the device generates corresponding page data based on the content data: an online document. For example: after generating the content data, the data and the interactive control can be displayed in the bubble control. When a click operation on the interactive control is detected, an online document is generated according to the content data. After that, the page can be jumped to a document page displaying the above-mentioned online document so that the user can read the online document.

[0084] In the above embodiments of the present application, the content 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 enhanced. 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 content data can be further generated for the user, so that the user can obtain more detailed and comprehensive relevant information, which can further enhance the user experience from the perspective of both interactive experience and comprehensive information acquisition.

[0085] 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.

[0086] like Figure 3 As 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.

[0087] The server 302 may be any suitable device on which a generative service is deployed, 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 initiate a first search for input data, obtain a first search result, and generate intermediate data based on the input data and the first search result; and initiate a second search based on the intermediate data, obtain a second search result, generate content data based on the intermediate data and the second search result, and send it to the corresponding user device 306 for the user to view.

[0088] 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.

[0089] 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.

[0090] Embodiment 2

[0091] Reference Figure 4 , Figure 4 is 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:

[0092] Step 402, receiving input data.

[0093] Specifically, the input data may be data used for intelligent creation. For example, the input data may include one or more of the following: creation theme, creation requirements (such as word count requirements, creation style requirements), etc. In the embodiment of the present application, there is no limitation on the amount and specific content of the input data, and the setting may be customized according to the actual situation.

[0094] 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.

[0095] Step 404, sending the input data to a browser interface for providing browser retrieval and a service interface for providing generation services, so as to perform a first retrieval on the input data through a browser corresponding to the browser interface and a retrieval enhancement service corresponding to the service interface, respectively.

[0096] 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 the browser page retrieval is performed through the browser interface, and the retrieval enhancement generation processing based on the external knowledge base is performed through the service interface provided by the server.

[0097] Step 406: Receive intermediate data generated based on the input data and fed back by the service interface, where the intermediate data is generated based on the input data and a first search result of the first search.

[0098] Specifically, after the client sends the input data to the service interface of the server, the intermediate data can be generated through the generative service provided by the server. In the embodiment of the present application, the process of generating intermediate data based on the input data and the first search result can refer to the content of the above embodiment 1, which will not be repeated here.

[0099] Step 408: Send the intermediate data to the browser interface and the service interface, so as to perform a second search on the intermediate data through the browser corresponding to the browser interface and through the search enhancement service corresponding to the service interface.

[0100] Specifically, after the intermediate data is received in step 406, the intermediate data can be sent as new input data to the browser interface and service interface mentioned in step 404 to perform a secondary search (second search) based on the intermediate data, thereby obtaining a second search result.

[0101] Step 410: receiving content data generated based on the intermediate data fed back by the service interface, and displaying the content data, wherein the content data is generated based on the intermediate data and the second search result of the second search.

[0102] Specifically, after the client sends the intermediate data to the service interface of the server, the content 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 process of generating the intermediate data based on the intermediate data and the second search result of the second search can refer to the content of the above embodiment 1, which will not be repeated here.

[0103] In the data processing method provided in the embodiment of the present application, based on the thought chain technology, the creative process is decomposed into two logical reasoning steps: the first step is to generate intermediate data based on the search results for the input data, and the second step is to generate content data based on the search results for the intermediate data. On the one hand, the intermediate data generated based on the first search result usually involves content that the first search result does not cover. Therefore, a second search for the intermediate data can obtain a second search result with richer and more comprehensive content, which can make the content data generated based on the second search result with richer and more comprehensive content richer and more comprehensive; on the other hand, decomposing the creative process into different steps through the thought chain technology can help the generative basic model to more clearly display its thinking process, thereby generating more accurate and reasonable content data, that is, it helps to improve the accuracy and rationality of the content data.

[0104] Optionally, in some of the embodiments, the process of displaying the content data may include:

[0105] The content of the text content data is displayed through the bubble control, and the interactive control corresponding to the content data is displayed;

[0106] An interactive operation on an interactive control is received, and an online document generated based on the content data is displayed in response to the interactive operation.

[0107] Specifically, after the content data is obtained, the content data may be displayed through the control so that the user can learn about the content data corresponding to the input data in a timely manner.

[0108] Furthermore, after generating and displaying the content data to the user, the embodiment of the present application also provides the user with an interactive experience for the content data, specifically: a bubble control can be created in the page, and then the content data and the interactive control corresponding to the content data can be displayed through the bubble control. After that, the user can perform a preset interactive operation on the interactive control so that the device generates corresponding page data based on the content data: an online document. For example: after generating the content data, the data and the interactive control can be displayed in the bubble control. When a click operation on the interactive control is detected, an online document is generated according to the content data. After that, the page can be jumped to a document page displaying the above-mentioned online document so that the user can read the online document.

[0109] In the above embodiment of the present application, the text content 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 content 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.

[0110] Optionally, in some of the embodiments, an option for exporting the document is provided in the page displaying the online document;

[0111] The method also includes:

[0112] 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.

[0113] Specifically, after an online document is generated based on content data, it can be convenient for users to understand content details. However, the online document is usually online data presented in the form of a page, which can only be viewed when the user device is connected to the Internet. Therefore, there is a problem of inconvenience in viewing.

[0114] In the embodiment of the present application, an export option for exporting documents is set in the page displaying online documents. When the user triggers this option, the online document is exported as an offline document and stored locally in the user's device. Afterwards, whether the user's device is in a network environment or in an offline environment, the user can access the document at any time according to his or her own needs, thereby further improving the user's experience.

[0115] Optionally, in some of the embodiments, information corresponding to the content data is displayed in the interactive control.

[0116] Optionally, in some of the embodiments, the interactive control is further used to receive intermediate data editing information, and the method further includes:

[0117] Receive intermediate data editing information through interactive controls;

[0118] The initial intermediate data, the intermediate data editing information and the intermediate data are displayed in the bubble control. The intermediate data is obtained by adjusting the initial intermediate data according to the intermediate data editing information. The initial intermediate data is generated based on the first search result.

[0119] Specifically, considering that the intermediate data is generated by the generative basic model, there may be a certain gap between the intermediate data and user expectations. In order to make the final generated content data more in line with user needs, after the user device receives the intermediate data fed back by the service interface, the intermediate data can be displayed as initial intermediate data in the bubble control for the user to view. Later, when the user wants to modify the initial intermediate data, the intermediate data editing information for the initial intermediate data can be sent through the preset interactive operation of the interactive control, so that the user device can modify the initial intermediate data according to the intermediate data editing information, thereby obtaining new intermediate data and displaying it to the user. The interactive method provided by the above-mentioned embodiment of the present application enables the user to implement the modification and editing operation of the initial intermediate data generated by the model through simple interactive operations, thereby obtaining intermediate data that is more in line with their own needs, and therefore, the user experience can be further improved.

[0120] Embodiment 3

[0121] 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:

[0122] A first search result obtaining module 502 is used to receive input data, initiate a first search on the input data, and obtain a first search result;

[0123] The intermediate data obtaining module 504 is used to parse the received input data and the generated first search result, generate first prompt information, and perform generation processing on the first prompt information through the generative basic model to obtain intermediate data;

[0124] A second search result obtaining module 506, used to initiate a second search for the intermediate data and obtain a second search result;

[0125] The content data obtaining module 508 is used to generate second prompt information based on the intermediate data and the second search result, so as to obtain content data by performing generation processing on the second prompt information through the generative basic model.

[0126] Optionally, in some embodiments, the second search result obtaining module 506 is specifically configured to:

[0127] Receiving modified intermediate data generated by performing a modification operation on the intermediate data;

[0128] Based on the modified intermediate data, a second search is initiated to obtain a second search result.

[0129] Optionally, in some embodiments, the second search result obtaining module 506 is specifically configured to:

[0130] For the intermediate data, a browser search is performed through a preset interface to obtain a first sub-intermediate search result; and based on the embedding corresponding to the intermediate data, a search enhancement generation process based on an external knowledge base is performed to obtain a second sub-intermediate search result;

[0131] The first sub-intermediate search result and the second sub-intermediate search result are merged to obtain the second search result.

[0132] Optionally, in some embodiments, the second search result obtaining module 506, when performing the step of performing a browser search on the intermediate data through a preset interface to obtain the first sub-intermediate search result, is specifically used to:

[0133] Extract key information from intermediate data to obtain corresponding intermediate key information;

[0134] Expanding the intermediate key information to obtain at least one intermediate data expansion result;

[0135] Based on the intermediate key information and the intermediate data extension results, a browser search is performed through a preset interface to obtain a first sub-intermediate search result.

[0136] Optionally, in some embodiments, the first search result obtaining module 502 is specifically configured to:

[0137] For the input data, a browser search is performed through a preset interface to obtain a first sub-input data 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 sub-input data search result;

[0138] The first sub-input data retrieval result and the second sub-input data retrieval result are integrated to obtain a first retrieval result.

[0139] Optionally, in some embodiments, the first search result obtaining module 502, when executing the step of performing a browser search on the input data through a preset interface to obtain the first sub-input data search result, is specifically used to:

[0140] Extract key information from input data to obtain corresponding key information of input data;

[0141] Expanding key information of input data to obtain at least one input data expansion result;

[0142] Based on the input data key information and the input data expansion result, a browser search is performed through a preset interface to obtain a first sub-input data search result.

[0143] Optionally, in some of the embodiments, the intermediate data obtaining module 504, when executing the step of parsing the received input data and the generated first search result to generate the first prompt information, is specifically used to: splice and / or merge the received input data and the generated first search result to obtain the first prompt information;

[0144] The content data obtaining module 508, when executing the step of parsing the intermediate data and the second search result to generate the second prompt information, is specifically used to: splice and / or merge the intermediate data and the second search result to obtain the second prompt information.

[0145] Optionally, in some of the embodiments, the data processing device further comprises:

[0146] An interactive operation receiving module, used for receiving an interactive operation for an interactive control, wherein the interactive control displays information corresponding to the content data, the interactive control is displayed in a bubble control where the content data is located, and the bubble control displays the content data and the interactive control;

[0147] The jump module is used to jump to a page of an online document generated based on the content data in response to an interactive operation.

[0148] 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.

[0149] Embodiment 4

[0150] 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:

[0151] An input data receiving module 602, used to receive input data;

[0152] An input data sending module 604, used to send the input data to a browser interface for providing browser search and a service interface for providing generation service, so as to perform a first search on the input data through a browser corresponding to the browser interface and through a search enhancement service corresponding to the service interface respectively;

[0153] An intermediate data receiving module 606 is used to receive intermediate data generated based on the input data and fed back by the service interface, where the intermediate data is generated based on the input data and a first search result of the first search;

[0154] An intermediate data sending module 608, used to send the intermediate data to the browser interface and the service interface, so as to perform a second search on the intermediate data through the browser corresponding to the browser interface and through the search enhancement service corresponding to the service interface respectively;

[0155] The content receiving module 610 is used to receive content data generated based on the intermediate data fed back by the service interface and display the content data, where the content data is generated based on the intermediate data and the second search result of the second search.

[0156] Optionally, in some embodiments, the content receiving module 610, when executing the step of displaying content data, is specifically configured to:

[0157] The content of the content data is displayed through the bubble control, and the interactive controls corresponding to the content data are displayed;

[0158] An interactive operation on an interactive control is received, and an online document generated based on the content data is displayed in response to the interactive operation.

[0159] Optionally, in some embodiments, an option for exporting a document is provided in the page displaying the online document, and the content receiving module 610 is further used to:

[0160] 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.

[0161] Optionally, in some of the embodiments, information corresponding to the content data is displayed in the interactive control.

[0162] Optionally, in some embodiments, the interactive control is further used to receive intermediate data editing information, and the content receiving module 610 is further used to:

[0163] Receive intermediate data editing information through interactive controls;

[0164] The initial intermediate data, the intermediate data editing information and the intermediate data are displayed in the bubble control. The intermediate data is obtained by adjusting the initial intermediate data according to the intermediate data editing information. The initial intermediate data is generated based on the first search result.

[0165] 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.

[0166] Embodiment 5

[0167] 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.

[0168] 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.

[0169] in:

[0170] The processor 702 , the communication interface 704 , and the memory 706 communicate with each other via a communication bus 708 .

[0171] The communication interface 704 is used to communicate with other electronic devices or servers.

[0172] The processor 702 is used to execute the program 710, and specifically can execute the relevant steps in the above method embodiment.

[0173] Specifically, the program 710 may include program codes, which include computer operation instructions.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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, include: receiving input data, initiating a first search on the input data, and obtaining a first search result; Parsing the received input data and the generated first search result to generate first prompt information, and performing generation processing on the first prompt information through a generative basic model to obtain intermediate data; Initiate a second search for the intermediate data to obtain a second search result; The intermediate data and the second search result are parsed to generate second prompt information, and the second prompt information is generated and processed by the generative basic model to obtain content data.

2. The method according to claim 1, in, The initiating a second search for the intermediate data to obtain a second search result includes: receiving modified intermediate data generated by performing a modification operation on the intermediate data; A second search is initiated for the modified intermediate data to obtain a second search result.

3. The method according to claim 1, in, The initiating a second search for the intermediate data to obtain a second search result includes: For the intermediate data, a browser search is performed through a preset interface to obtain a first sub-intermediate search result; and based on the embedding corresponding to the intermediate data, a search enhancement generation process based on an external knowledge base is performed to obtain a second sub-intermediate search result; The first sub-intermediate search result and the second sub-intermediate search result are merged to obtain a second search result.

4. The method according to claim 3, in, The step of performing a browser search on the intermediate data through a preset interface to obtain a first sub-intermediate search result includes: Extracting key information from the intermediate data to obtain corresponding intermediate key information; Expanding the intermediate key information to obtain at least one intermediate data expansion result; Based on the intermediate key information and the intermediate data extension result, a browser search is performed through a preset interface to obtain the first sub-intermediate search result.

5. The method according to claim 1 or 2, in, The initiating a first search on the input data to obtain a first search result includes: For the input data, a browser search is performed through a preset interface to obtain a first sub-input data 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 sub-input data search result; The first sub-input data retrieval result and the second sub-input data retrieval result are integrated to obtain a first retrieval result.

6. The method according to claim 5, in, The step of performing a browser search on the input data through a preset interface to obtain a first sub-input data search result includes: Extracting key information from the input data to obtain corresponding key information of the input data; Expanding the key information of the input data to obtain at least one input data expansion result; Based on the input data key information and the input data expansion result, a browser search is performed through a preset interface to obtain the first sub-input data search result.

7. The method according to claim 1 or 2, in, The parsing the received input data and the generated first search result to generate first prompt information includes: splicing and / or fusing the received input data and the generated first search result to obtain the first prompt information; The parsing of the intermediate data and the second search result to generate the second prompt information includes: concatenating and / or fusing the intermediate data and the second search result to obtain the second prompt information.

8. The method according to claim 1 or 2, in, The method further comprises: An interactive operation on an interactive control is received, wherein the interactive control displays information corresponding to the content data, the interactive control is displayed in a bubble control where the content data is located, and the bubble control displays the content data and the interactive control; In response to the interactive operation, jumping to a page of an online document generated based on the content data.

9. A data processing method, include: Receive input data; Sending the input data to a browser interface for providing browser retrieval and a service interface for providing generation services, so as to respectively perform a first retrieval on the input data through a browser corresponding to the browser interface and through a retrieval enhancement service corresponding to the service interface; receiving intermediate data generated based on the input data and fed back by the service interface, wherein the intermediate data is generated based on the input data and a first search result of the first search; Sending the intermediate data to the browser interface and the service interface, so as to perform a second search on the intermediate data through a browser corresponding to the browser interface and through a search enhancement service corresponding to the service interface, respectively; Receive content data generated based on the intermediate data fed back by the service interface, and display the content data, where the content data is generated based on the intermediate data and a second search result of the second search.

10. The method according to claim 9, wherein the presenting of the content data comprises: include: Displaying the content of the content data through a bubble control, and displaying an interactive control corresponding to the content data; An interactive operation on the interactive control is received, and in response to the interactive operation, an online document generated based on the content data is displayed.

11. The method according to claim 10, in, 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.

12. The method according to claim 10 or 11, in, The interactive control displays information corresponding to the content data.

13. The method according to claim 10, wherein the interactive control is further used to receive the intermediate data editing information, and the method further include: Receiving the intermediate data editing information through the interactive control; The initial intermediate data, the intermediate data editing information and the intermediate data are displayed in the bubble control, wherein the intermediate data is obtained by adjusting the initial intermediate data based on the intermediate data editing information, and the initial intermediate data is generated based on the first search result.

14. An electronic device, include: 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 1-13.

15. 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 13 is implemented.

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

Citation Information

Patent Citations

  • Intelligent writing method, device, equipment and medium

    CN115630640A

  • Content retrieval method and device, equipment and medium

    CN116501960A

  • Method and device for acquiring information, electronic equipment and storage medium

    CN117453722A

  • Retrieval enhancement generation system and method based on knowledge graph

    CN117973540A

  • Report generation method and device based on large language model

    CN118133973A

Cited By

  • Text information processing method and electronic equipment

    CN121166941A