Information processing method and apparatus, device, and storage medium

Abstract

Embodiments of the present disclosure relate to an information processing method and apparatus, a device, and a computer-readable storage medium. The method provided herein comprises: in response to receiving a creation request, presenting a configuration page used for receiving configuration information of a knowledge base, wherein the configuration page comprises a first configuration area used for receiving a configuration for a target type of the knowledge base, and a second configuration area used for receiving a configuration for a target data source of the knowledge base; in response to receiving the configurations for the target type and the target data source, importing data of the target type from the target data source into the knowledge base; in response to completing the importing of the data, presenting an index setting page corresponding to the target type; and creating the knowledge base of the target type on the basis of index setting information.

Description

Information processing method, device, equipment and storage medium

[0001] This application claims priority to the Chinese invention patent application entitled “Information processing method, apparatus, equipment and storage medium” and application number 202410371110.2, filed on March 28, 2024, and this application also claims priority to the Chinese invention patent application entitled “Information processing method, apparatus, equipment and storage medium” and application number 202411748663.1, filed on November 29, 2024. The entire contents of the above applications are incorporated into this application by reference. Technical Field

[0002] Example embodiments of the present disclosure relate generally to the field of computers, and more particularly to information processing. Background Art

[0003] In recent years, with the rapid development of artificial intelligence (AI), the creation and use of knowledge bases has become increasingly widespread. Knowledge bases can store specialized knowledge or content in relevant fields, allowing people to quickly access the information they need. However, existing methods for creating and accessing knowledge bases remain unsatisfactory, potentially hindering the efficiency of creating and accessing information. Summary of the Invention

[0004] In a first aspect of the present disclosure, an information processing method is provided. The method includes: in response to receiving a creation request, presenting a configuration page for receiving configuration information of a knowledge base, the configuration page including: a first configuration area for receiving a configuration of a target type of the knowledge base from a plurality of data types, and a second configuration area for receiving a configuration of a target data source of the knowledge base; in response to receiving the configuration of the target type and the target data source, importing data of the target type from the target data source into the knowledge base; in response to completing the data import, presenting an index setting page corresponding to the target type, for receiving index setting information for the imported data; and in response to receiving the index setting information, creating a knowledge base of the target type based on the index setting information.

[0005] In a second aspect of the present disclosure, a device for information processing is provided. The device includes: a presentation module configured to present a configuration page for receiving configuration information of a knowledge base in response to receiving a creation request, the configuration page including: a first configuration area for receiving a configuration of a target type of the knowledge base from a plurality of data types, and a second configuration area for receiving a configuration of a target data source of the knowledge base; an import module configured to import data of the target type from the target data source into the knowledge base in response to receiving the configuration of the target type and the target data source; a setting module configured to present an index setting page corresponding to the target type in response to completion of data import, for receiving index setting information for the imported data; and a creation module configured to create a knowledge base of the target type based on the index setting information in response to receiving the index setting information.

[0006] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform operations to implement the method of the first aspect.

[0007] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0008] In a fifth aspect of the present disclosure, a computer program product is provided, which is tangibly stored in a computer storage medium and includes computer-executable instructions that, when executed by a device, cause the device to perform operations to implement the method of the first aspect.

[0009] It should be understood that the content described in this summary section is not intended to limit the key features or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0011] FIG1 shows a schematic diagram of an example environment in which embodiments according to the present disclosure may be implemented;

[0012] FIG2 shows a schematic diagram of a knowledge base architecture according to some embodiments of the present disclosure;

[0013] FIG3 shows a flowchart of an example process of data processing according to some embodiments of the present disclosure;

[0014] 4A to 4E illustrate examples of pages for creating a knowledge base of a document type according to some embodiments of the present disclosure;

[0015] 5A to 5G illustrate examples of pages for creating a knowledge base of image type according to some embodiments of the present disclosure;

[0016] FIG6 shows an example of a page of a knowledge base viewing list according to some embodiments of the present disclosure;

[0017] 7A to 7F illustrate examples of pages for managing a knowledge base of document types according to some embodiments of the present disclosure;

[0018] 8A to 8C illustrate examples of pages for managing a knowledge base of image types according to some embodiments of the present disclosure;

[0019] FIG9 shows an example of a page for configuring a knowledge base in a third-party application according to some embodiments of the present disclosure;

[0020] FIG10 shows a flowchart of an example process of adding table-type data according to some embodiments of the present disclosure;

[0021] FIG11 is a flowchart illustrating an example process of retrieving knowledge base data based on hybrid search according to some embodiments of the present disclosure;

[0022] FIG12 shows an example of a page for knowledge base application settings according to some embodiments of the present disclosure;

[0023] 13A and 13B are flowcharts illustrating an example process of retrieving image type knowledge base data according to some embodiments of the present disclosure;

[0024] FIG14 shows a flowchart of an example process of information processing according to some embodiments of the present disclosure;

[0025] FIG15 shows a schematic structural block diagram of an example apparatus for information processing according to some embodiments of the present disclosure; and

[0026] FIG16 illustrates a block diagram of an electronic device capable of implementing various embodiments of the present disclosure. DETAILED DESCRIPTION

[0027] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0028] It should be noted that the titles of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and any type of embodiment may be included under any section / subsection. Furthermore, the embodiments described in any section / subsection may be combined in any manner with any other embodiments described in the same section / subsection and / or in different sections / subsections.

[0029] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0030] Herein, unless explicitly stated otherwise, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.

[0031] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0032] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the type, scope of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to relevant users and authorization should be obtained from relevant users in an appropriate manner in accordance with relevant laws and regulations. The relevant users may include any type of right holders, such as individuals, enterprises, and groups.

[0033] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly prompt the relevant user that the operation requested to be performed will require obtaining and using the information of the relevant user, so that the relevant user can independently choose whether to provide information to the software or hardware such as the electronic device, application, server or storage medium that executes the operation of the technical solution of the present disclosure based on the prompt message.

[0034] As an optional but non-limiting implementation, in response to receiving an active request from a relevant user, a prompt message may be sent to the relevant user in the form of a pop-up window, in which the prompt message may be presented in text form. Furthermore, the pop-up window may also include a selection control for the user to select "agree" or "disagree" to provide information to the electronic device.

[0035] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0036] As used herein, the term "model" can learn the association between corresponding inputs and outputs from training data, so that after training is completed, corresponding outputs can be generated for given inputs. The generation of the model can be based on machine learning technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multiple layers of processing units. A neural network model is an example of a model based on deep learning. In this article, "model" may also be referred to as "machine learning model", "learning model", "machine learning network" or "learning network", and these terms are used interchangeably in this article.

[0037] As mentioned above, with the rapid development of artificial intelligence, the creation and use of knowledge bases are becoming increasingly widespread. Knowledge bases can store specialized knowledge or content in relevant fields, allowing people to quickly access the information they need. However, limitations in existing knowledge base creation and access methods significantly impact the efficiency of knowledge base creation and information retrieval.

[0038] Some embodiments of the present disclosure propose solutions for knowledge base creation, management, and application. One solution may include: in response to receiving a creation request, presenting a configuration page for receiving configuration information of the knowledge base, the configuration page including a first configuration area for receiving a configuration of a target type of the knowledge base from a plurality of data types, and a second configuration area for receiving a configuration of a target data source of the knowledge base. In response to receiving the configuration of the target type and the target data source, importing data of the target type from the target data source into the knowledge base. In response to the completion of the data import, presenting an index setting page corresponding to the target type for receiving index setting information for the imported data. In response to receiving the index setting information, processing the imported data based on the index setting information to create a knowledge base of the target type, the created knowledge base including a plurality of data items that can be indexed after processing.

[0039] In this way, users can be supported in creating specific types of knowledge bases as needed, and based on the type of knowledge base, they can be guided in configuring the information required for the knowledge base, thereby improving the efficiency of knowledge base creation and the flexibility of subsequent use of the knowledge base. In addition, some embodiments of the present disclosure can provide a modular, simple, and data-selective knowledge base creation solution, allowing users to easily and quickly create knowledge bases that are easy to index data, while also making it easier for users to obtain the information they need from the knowledge base.

[0040] Various example implementations of this solution are described in detail below in conjunction with the accompanying drawings.

[0041] Figure 1 shows a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. As shown in Figure 1, an application management platform 110 can provide a user 105 with an environment for creating, managing, and publishing knowledge bases, data sets, various applications, and workflows. The application management platform 110 can be any appropriate platform that supports users in developing knowledge bases, various applications, workflows, and the like. In some embodiments, the application management platform 110 can be a low-code platform that provides a collection of tools for knowledge base creation. The application management platform 110 can support visual development of knowledge bases, applications, and workflows, allowing developers to skip the manual coding process and speed up the development cycle. Such a platform can support users in efficient development and implement operations such as application creation and application function adjustment.

[0042] The application management platform 110 can be deployed locally on the terminal device of the user 105, and / or can be supported by a remote server. For example, the terminal device of the user 105 can run a client of the application management platform 110, which can support the interaction between the user and the application management platform 110. In the case where the application management platform 110 runs locally on the user's terminal device, the user 105 can directly use the client to interact with the local application management platform 110. In the case where the application management platform 110 runs on a server-side device, the server-side device can, based on the communication connection with the terminal device, realize the provision of services to the client running in the terminal device. The application management platform 110 can present a corresponding page 122 to the user 105 based on the operation of the user 105 to output information to the user 105 and / or receive information from the user 105.

[0043] In some embodiments, the application management platform 110 can be associated with a corresponding database, which stores the data or information required for the knowledge base creation process supported by the application management platform 110. For example, the database can store the code and description information corresponding to each functional module used to constitute the knowledge base. The application management platform 110 can also perform operations such as calling, adding, deleting, and updating on the functional modules in the database. The database can also store operations that can be performed on different functional blocks. For example, in a scenario where a knowledge base is to be created, the application management platform 110 can call the corresponding functional blocks from the database to build the knowledge base.

[0044] In an embodiment of the present disclosure, the user 105 can create a knowledge base 120 as needed on the application management platform 110 and publish the knowledge base 120. The knowledge base 120 can be published to any appropriate platform as long as the platform can support access to the knowledge base.

[0045] After publication, the knowledge base 120 can be associated with one or more applications 135 or workflows 136. The application 135 or workflow 136 may need to rely on the knowledge in the knowledge base 120 to determine the response to the user's query. In some embodiments, the application 135 may include a digital assistant. The knowledge base 120 can be configured to the digital assistant. The digital assistant can interact with the user 135 based on the content in the knowledge base 120. The interactive messages between the user 135 and the digital assistant may include messages in multimodal forms, such as text messages (e.g., natural language text), voice messages, image messages, video messages, and the like.

[0046] The application management platform 110 can run on appropriate electronic devices. The electronic devices here can be any appropriate type of device with computing capabilities, including terminal devices or server devices. The terminal device can be any type of mobile terminal, fixed terminal or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication systems (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio broadcast receivers, e-book devices, gaming devices or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. The server device can, for example, include a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and so on. In some embodiments, the application management platform 110 can be implemented based on cloud services.

[0047] It should be understood that the structure and functionality of the environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure. For example, although FIG1 illustrates a single user interacting with the application management platform 110, multiple users may access the application management platform 110 to each create a knowledge base, develop applications, workflows, and the like.

[0048] Some example embodiments of the present disclosure will be described in detail below with reference to the examples in the accompanying drawings. It should be understood that the pages shown in the accompanying drawings are merely examples, and a variety of page designs may exist. The various graphical elements in a page may have different arrangements and different visual representations, one or more elements may be omitted or replaced, and one or more other elements may also be present. The embodiments of the present disclosure are not limited in this respect.

[0049] The knowledge base creation process described in the embodiments of the present disclosure can be implemented on a knowledge base creation platform, a terminal device on which the knowledge base creation platform is installed, and / or a server corresponding to the knowledge base creation platform. In the examples below, for the purpose of discussion, the description is from the perspective of the knowledge base creation platform, such as the application management platform 110 shown in Figure 1. The page presented by the application management platform 110 can be presented via the terminal device of the user 105, and user input can be received via the terminal device of the user 105. In this article, the user 105 who creates the knowledge base is sometimes also referred to as a knowledge base creator, a knowledge base developer, etc.

[0050] The user 105 can initiate a creation request to the application management platform 110 as needed. In response to receiving the creation request, the application management platform 110 presents a page for creating a knowledge base. On this page, the user 105 can configure the knowledge base to be created (assuming it is the knowledge base 120 shown in Figure 1). Unlike creating a knowledge base by writing code, in an embodiment of the present disclosure, the page for creating a knowledge base is designed to include at least one configuration area for receiving configuration information of the knowledge base, and each configuration area is defined as receiving a type of configuration information required for building the knowledge base.

[0051] FIG2 shows a schematic diagram of a knowledge base architecture according to some embodiments of the present disclosure. As shown in the schematic diagram 200 of the knowledge base architecture in FIG2 , the knowledge base architecture 202 can be composed of multiple types of data. For example, the types of the knowledge base architecture 202 can include document type 210, table type 212, and image type 214. The user 105 can create at least one knowledge base 120 of the corresponding type based on the knowledge base architecture 202 of the corresponding type. For example, under the knowledge base of document type 210, the user 105 can establish one or more knowledge bases (knowledge base 1, knowledge base 2) of document type 210 as needed. The knowledge base of each document type can include one document or a combination of multiple documents. For table type 212 and image type 214, the user 105 can also similarly create one or more corresponding databases. It will be understood that the knowledge base 120 of document type 210 can include data of document type 210, the knowledge base 120 of table type 212 can include data of table type 212, and the knowledge base 120 of image type 214 can include data of image type 214.

[0052] In some embodiments, continuing with reference to Figure 2, an application or workflow can be associated with at least one knowledge base 120. Furthermore, the application or workflow can call data from at least one knowledge base 120 associated therewith during use. As an example, as shown in Figure 2, the application is associated with a knowledge base 120 of two document types 210 and a knowledge base 120 of an image type 214. The application can then retrieve document data from the knowledge base 120 of the two document types 210 and image data from the knowledge base 120 of an image type 214 during use. A workflow 222 is associated with a knowledge base 120 of a table type 212. The workflow 222 can retrieve table data from the knowledge base of the table type 212. The application mentioned here can be implemented as a digital assistant, any database with a question-and-answer function, or a knowledge retrieval function. The workflow mentioned here can be configured to automatically perform specific tasks.

[0053] FIG3 shows a flow chart of an example process 300 of knowledge base management according to some embodiments of the present disclosure. The data processing process 300 may be executed in the application management platform 110 as described above. The process 300 is described below with reference to FIG1 .

[0054] As shown in Figure 3, the management cycle of the knowledge base can be divided into the creation / import stage and the viewing / editing stage.

[0055] During the creation / import phase, at block 302 , the application management platform 110 may receive a knowledge base creation request.

[0056] In response to receiving the knowledge base creation request, the application management platform 110 may provide the user with selectable knowledge base types for selection. The selectable knowledge base types include document type 210, table type 212, and image type 214. It will be appreciated that, depending on actual application needs, more, fewer, or different types of data may be configured or supported, such as video type, mind map type, and so on.

[0057] After determining that the user selects the document type 210 , in block 310 , the application management platform 110 may present a corresponding page to the user and receive segment settings corresponding to the document type from the user.

[0058] After determining that the user selects the table type 212 , in block 312 , the application management platform 110 may present a corresponding page to the user and receive a table header structure setting corresponding to the table type from the user.

[0059] After determining that the user selects the image type 214 , in block 314 , the application management platform 110 may present a corresponding page to the user and receive annotation settings corresponding to the image type from the user.

[0060] After executing box 310 , box 312 or box 314 , in box 320 , the application management platform 110 may perform data processing to import and process data, thereby completing the creation of the knowledge base.

[0061] After the knowledge base is created, it can also be associated with one or more applications (e.g., digital assistant applications, question-and-answer applications, etc.) or workflows (e.g., workloads that rely on knowledge to perform data queries). If the knowledge base is associated with an application or workflow, then the knowledge base can be called to process query information for the associated application or workflow. The call to the knowledge base is optional, and it can be determined based on the query information whether the associated knowledge base needs to be scheduled to assist in the processing of the current query information. The data stored in the knowledge base can be queried to determine the response to the query information.

[0062] After the knowledge base is created, it can be viewed or edited. During the view / edit phase, the data in the knowledge base 120 can be viewed or edited. For clarity, the view / edit phase will be described with respect to an image type knowledge base. At block 325, the application management platform 110 can view the image set.

[0063] At block 330 , the application management platform 110 may view a single image from the image collection.

[0064] At block 335 , the application management platform 110 may modify the image annotation information.

[0065] The detailed steps in data processing can be found in the following description and will not be repeated here.

[0066] 4A to 4E illustrate examples of pages 400A to 400E for creating a document-type knowledge base according to some embodiments of the present disclosure. Pages 400A to 400E may be provided by the application management platform 110 shown in FIG1 , for example.

[0067] Specifically, the page includes at least a first configuration area for receiving a configuration of a target type for the knowledge base 120 from a plurality of data types. For example, page 400A of FIG. 4A (also referred to as knowledge base creation page 400A) provides a first configuration area 410, which includes three type selection boxes, each corresponding to a document type, a table type, and an image type. Selecting the document type selection box indicates that the target type for receiving the configuration for the knowledge base 120 is the document type.

[0068] The target type configured for knowledge base 120, received as part of the configuration information for knowledge base 120, will limit the data types supported by knowledge base 120 to the target type and exclude data of other types. Knowledge base 120 can only store data of the target type. In other words, the knowledge base 120 established here is a dedicated database that only supports the target type.

[0069] During the creation process, a specific visual configuration area is provided to allow the user to select the target type, so that the user can conveniently set the data types supported by the knowledge base 120.

[0070] In some embodiments, the page may further include a second configuration area for receiving configuration of a target data source for the knowledge base 120. The knowledge base 120 may obtain data from the configured target data source, that is, the user 105 may select a method or source for uploading data.

[0071] In some embodiments, the second configuration area presents at least one supported type. The at least one type of data source may include at least one of a local data source, an online data source, a database, custom data, and the like. For example, page 400A of FIG4A shows a second configuration area 420 associated with the document type selection box in the first configuration area 410, which includes a plurality of document selection boxes, each of which corresponds to a target data source. The target data sources here may include local documents (for example, local documents in formats such as PDF, TXT, DOCX, etc.), online data (for example, obtaining content from an online web page), XX application (document data in any application or database can be obtained), and customization (for example, document content can be customized to be created and edited).

[0072] In some embodiments, the page also includes a third configuration area for receiving a name for the knowledge base 120. The user can name the knowledge base being created based on the third configuration area. For example, page 400A of FIG4A shows a third configuration area 430, which includes a name input box for accepting a name entered by the user in natural language.

[0073] In some embodiments, the page also includes a fourth configuration area for receiving descriptive information about the knowledge base. The user can enter descriptive information about the knowledge base based on the fourth configuration area. The descriptive information can indicate the type, function, and other information of the knowledge base. For example, page 400A of Figure 4A provides a fourth configuration area 432, which includes a description input box for receiving descriptive information about the knowledge base input by the user in natural language. The name and descriptive information of the knowledge base 120 can be collectively referred to as the metadata of the knowledge base. In some embodiments, if the knowledge base is associated with a specific application or workflow, then the corresponding application or workflow can determine whether to call the knowledge base based on the descriptive information or metadata of the knowledge base when processing its respective query information. In some embodiments, if the application or workflow is built based on a machine learning model (e.g., a generative model), if the knowledge base is associated with the above-mentioned application or workflow, then a prompt word (Prompt) can be constructed based on the descriptive information or metadata of the knowledge base and provided to the model on which the above-mentioned application or workflow relies, and the model determines whether to call the knowledge base to determine the response to the query information.

[0074] In some embodiments, the application management platform 110 may import data of the target type from the target data source into the knowledge base in response to receiving the configuration of the target type and the target data source.

[0075] In some embodiments, the application management platform 110 may present a page 400B as shown in FIG. 4B in response to receiving the configuration of the document type and the local document.

[0076] In some embodiments, page 400B of FIG. 4B provides a document upload area 435. The document upload area 435 may provide information indicating the format, size, or number of pages of documents that can be received. In some embodiments, the document upload area 435 includes a document upload control 436. In response to triggering the document upload control 436, the application management platform 110 may receive a document uploaded to the knowledge base 120 by the user 105 through the document upload control 436.

[0077] In some embodiments, the application management platform 110 may also receive documents that the user 105 drags to the document upload area 435 . For example, the user 105 may select a document from a local file and drag it to the document upload area 435 to upload the document to the knowledge base 120 .

[0078] In some embodiments, page 400B of FIG4B further provides a document area 440. Document area 440 may present at least one document that has been uploaded to knowledge base 120. Document area 440 may also present upload information of at least one document, which may include the document name, document upload status, and document size.

[0079] In some embodiments, the document area 440 of Figure 4B further provides a document operation control 441. Furthermore, the application management platform 110 can also delete the document associated with the document operation control 441 in response to triggering the document operation control 441.

[0080] In some embodiments, the application management platform 110 may present a page 400C as shown in FIG. 4C in response to receiving the configuration of the document type and online data.

[0081] In some embodiments, page 400C of FIG. 4C provides a new URL (Uniform Resource Locator, also known as a web link) area 445. In some embodiments, the new URL area 445 includes a new URL control. In response to triggering the new URL control, the application management platform 110 can receive the user's URL link, further obtain the document in the URL link, and upload it to the knowledge base 120. As an example, the method for obtaining the document in the URL link can be online extraction.

[0082] In some embodiments, the application management platform 110 may present a page 400D as shown in FIG. 4D in response to receiving the configuration of the document type and customization.

[0083] In some embodiments, the application management platform 110 may present a data input area in response to the target data source being a custom data type. In the data input area, the user may customize or enter the input they wish to import. However, the application management platform 110 may import the input data received in the data input area into the knowledge base.

[0084] In some embodiments, page 400D of Figure 4D provides a document customization area 450 (corresponding to the "data input area" under the document type). The application management platform 110 can receive the document content edited by the user in the document customization area 450, generate a document based on the document content, and upload the document to the knowledge base 120. As an example, as shown in Figure 4D, the document customization area 450 can include a custom name control 451 and a custom edit control 452. The custom name control 451 can be used to receive the document name entered by the user through natural language. The custom edit control 452 can be used to receive the document content entered by the user through natural language. In some embodiments, the number of natural language characters that the custom name control 451 and / or the custom edit control 452 can receive can also be limited, and any limit on the number of input characters will be included in the scope of this disclosure.

[0085] Although FIG4D illustrates the customization of document-type data, it is understood that for table-type data, a corresponding data input area may also be provided for receiving user-defined table data, such as one or more table entries. Furthermore, for image-type data, a corresponding data input area, such as a drawing board, may also be provided for receiving user-defined images.

[0086] In some embodiments, in response to the completion of the data import, the application management platform 110 may present an index setting page corresponding to the target type for receiving index setting information for the imported data. It should be noted that when accessing data in the knowledge base, the corresponding data in the knowledge base may be matched based on the index information associated with the index setting information.

[0087] In some embodiments, in response to the completion of document type data import, the application management platform 110 may present an index settings page corresponding to the document data type, for receiving segmented index settings for the document, where the segmented index settings indicate at least one of the following: a segmentation rule for the document, a segment length, and a segment pre-processing rule. Here, the document segments correspond to data items for indexing.

[0088] In some embodiments, the application management platform 110 may present an index setting page corresponding to the table data type in response to completion of the table type data import, for receiving a header index setting for the table, where the header index setting indicates a header field in the table used to index data items.

[0089] In some embodiments, the application management platform 110 provides a document index setting area 455 on page 400E of FIG. 4E . The application management platform 110 can receive document index setting information (also referred to as segment index settings) in the document index setting area 455. As an example, as shown in FIG. 4E , the document index setting area 455 provides an automatic segmentation and cleaning control 456 (also referred to as an input entry for default segment index settings) and a custom control 457 (also referred to as an input entry for user-defined segment index settings). It should be noted that the automatic segmentation and cleaning control 456 and the custom control 457 are mutually exclusive controls.

[0090] In some embodiments, the application management platform 110 can respond to triggering the automatic segmentation and cleaning control 456 and use the automatic segmentation and pre-processing rules as index setting information for the document. The automatic segmentation and pre-processing rules can be set by technicians as needed, and this disclosure does not limit this.

[0091] In some embodiments, the application management platform 110 can use the customized segmentation rules, segment length, and pre-processing rules as the index setting information of the document in response to triggering the customized control 457. For example, the user can enter the customized segmentation rules, segment length, and pre-processing rules in the customized control 457 through natural language.

[0092] 5A to 5G illustrate examples of pages 500A to 500G for creating an image-type knowledge base according to some embodiments of the present disclosure. Pages 500A to 500G may be provided by the application management platform 110 shown in FIG1 , for example.

[0093] In some embodiments, with continued reference to FIG. 4A , the application management platform 110 may present a second configuration area 420 as shown in page 500A of FIG. 5A in response to a selection operation on the image type selection box in the first configuration area 410 .

[0094] In some embodiments, as shown in FIG5A , the second configuration area 420 associated with the image type selection box in the first configuration area 410 may include multiple image selection boxes, each of which may correspond to a target data source. The target data sources may include local images (e.g., local image files supporting JPG, JPEG, and PNG), online images (e.g., images obtained from online web pages), XX applications (image files from any application or database may be obtained), and custom images (e.g., image files may be created and edited by the user).

[0095] In some embodiments, the application management platform 110 may present a page 500B as shown in FIG. 5B in response to receiving the configuration of the image type and the local image.

[0096] In some embodiments, page 500B of FIG5B provides an image upload area 510. Image upload area 510 may provide information indicating acceptable image formats, sizes, etc. In some embodiments, image upload area 510 includes an image upload control 511. In response to triggering image upload control 511, application management platform 110 may receive a document uploaded to knowledge base 120 by user 105 through image upload control 511.

[0097] In some embodiments, the application management platform 110 may also receive an image that the user 105 drags to the image upload area 510 . For example, the user 105 may select an image from the local images and drag it to the image upload area 510 to upload the image to the knowledge base 120 .

[0098] In some embodiments, page 500B of Figure 5B further provides an image area 515. Image area 515 may present at least one image that has been uploaded to knowledge base 120. Image area 515 may also present upload information of at least one image, which may include image name, image upload status, and image size.

[0099] In some embodiments, the image area 515 of Figure 5B further provides an image operation control 516. Furthermore, the application management platform 110 can also delete the image associated with the image operation control 516 in response to triggering the image operation control 516.

[0100] In some embodiments, the application management platform 110 may present a page 500C as shown in FIG. 5C in response to receiving the configuration of the image type and the online image.

[0101] In some embodiments, page 500C in FIG5C provides a manual collection area 520. In some embodiments, in response to receiving a trigger for the manual collection area 520, the application management platform 110 may receive a URL link from a user, further retrieve an image from the URL link, and upload it to the knowledge base 120. As an example, the image from the URL link may be retrieved by installing a browser extension in the manual collection area 520 and relying on the browser extension to retrieve the image from the URL link.

[0102] In some embodiments, with continued reference to FIG. 5C , the application management platform 110 may also present a page 500D as shown in FIG. 5D in response to receiving a URL link from the user in the manual collection area 520 .

[0103] In some embodiments, the application management platform 110 may provide an image display area 530 on the page 500D of Figure 5D. The image display area 530 may present at least one image associated with a URL link.

[0104] In some embodiments, the application management platform 110 may also provide an image search control 525 in the page 500D. Furthermore, the application management platform 110 may receive input information from the user 105 in the image search control 525 and update the image display area 530 to present at least one image associated with the input information.

[0105] In some embodiments, the application management platform 110 may also provide an image filter control 535 in the page 500D. Furthermore, the application management platform 110 may receive a conditional selection operation of the user 105 on the image filter control 535 and update the image display area 530 to present at least one image associated with the filter control 535.

[0106] In some embodiments, the application management platform 110 may further provide a radio button 540 in the page 500D. Furthermore, the application management platform 110 may receive an image selected by the user 105 in the image display area 530 in response to triggering the radio button 540 .

[0107] In some embodiments, the application management platform 110 may also provide a multi-selection control 545 in the page 500D. Furthermore, the application management platform 110 may receive multiple images selected by the user 105 in the image display area 530 in response to triggering the multi-selection control 545.

[0108] In some embodiments, the application management platform 110 may also provide a view data control 550 in the page 500D. Furthermore, in response to triggering the view data control 545, the application management platform 110 may present a page 500E as shown in FIG5E.

[0109] In some embodiments, the page 500E of Figure 5E presents a picture pre-selection area 555. The application management platform 110 can present, in the picture pre-selection area 555, thumbnails of at least one image selected by the user 105 based on a single-select or multi-select control.

[0110] In some embodiments, the application management platform 110 may further provide an image deletion control 556 in the thumbnail of at least one image in the image pre-selection area 555. Furthermore, the application management platform 110 may delete the image associated with the image deletion control 556 in the image pre-selection area 555 in response to triggering the image deletion control 556.

[0111] In some embodiments, the application management platform 110 may also provide a completion and collection control 560 in the page 500D. Furthermore, in response to triggering the completion and collection control 560, the application management platform 110 may present a page 500F as shown in FIG5F.

[0112] In some embodiments, in response to the target type being an image type, the application management platform 110 may present an index setting page corresponding to the image type for receiving annotation settings for the image, wherein the flag setting indicates a text annotation for indexing the image.

[0113] In some embodiments, the application management platform 110 provides an image index setting area 565 on page 500F of FIG. The application management platform 110 can receive image index setting information (also referred to as annotation settings) in the image index setting area 565. As an example, as shown in FIG. 5F , the image index setting area 565 provides an automatic annotation control 566 (also referred to as an automatically generated entry for annotation settings) and a manual annotation control 567 (also referred to as an input entry for user-defined annotation settings). It should be noted that the automatic annotation control 566 and the manual annotation control 567 are mutually exclusive controls.

[0114] In some embodiments, the application management platform 110 can respond to the triggering of the automatic annotation control 566, deeply understand the image, automatically generate a content description of the image, and use the content description as image index setting information. Here, the automatic annotation of the image can be implemented as OCR (Optical Character Recognition) text recognition, extracting text information in the image as annotation information. Here, the automatic annotation of the image can also be implemented as an image processing model, and the present disclosure does not limit the specific image processing model.

[0115] In some embodiments, the application management platform 110 can use the customized image description as the index setting information of the image in response to triggering the manual annotation control 567. As an example, the user can enter the image description in the manual annotation control 567 through natural language.

[0116] In some embodiments, the application management platform 110 may, in response to receiving the index setting information, create a target-type knowledge base 120 based on the index setting information. In some embodiments, the received index setting information can be used to build a data index. The application management platform 110 may process the imported target-type data based on the index setting information to create a target-type knowledge base 120, where the created knowledge base 120 includes a plurality of data items that are indexable after processing.

[0117] In some embodiments, the application management platform 110 may present a page 500G as shown in FIG. 5G in response to the received index setting information of the image.

[0118] In some embodiments, the application management platform 110 may present the image processing process in page 500G. The image processing process may include image processing progress.

[0119] In some embodiments, the application management platform 110 may present a knowledge base list page in response to the knowledge base list viewing request. The knowledge base list page may include multiple category viewing entries corresponding to multiple data types.

[0120] In some embodiments, FIG6 shows an example of a page 600 of a knowledge base viewing list according to some embodiments of the present disclosure. The page 600 may be provided by the application management platform 110 shown in FIG1 , for example.

[0121] In some embodiments, as shown in FIG6 , the application management platform 110 may present a page 600 of a knowledge base viewing list in response to a request to view a knowledge base list. As an example, the page 600 may present a knowledge base list area 610. The knowledge base list area 610 may present multiple knowledge bases 120 (e.g., knowledge base A, knowledge base B, etc.), and the multiple knowledge bases 120 may include multiple data types (e.g., knowledge base A is a document type, knowledge base B is a table type, and knowledge base E is an image type). The knowledge base list area 610 may also present knowledge base information corresponding to each knowledge base 120, and the knowledge base information may include the knowledge base type, knowledge base size, knowledge base creation time, etc.

[0122] In some embodiments, the application management platform 110 may provide an enablement control 611 in the knowledge base list area 610. Furthermore, in response to triggering the enablement control 611, the application management platform 110 may switch the enablement state of the knowledge base 120 or the data in the knowledge base associated with the enablement control 611 to on or off. For example, if the enablement state of the knowledge base 120 is on, it means that the data in the knowledge base 120 can be called, and if the enablement state of the knowledge base 120 is off, it means that the data in the knowledge base 120 cannot be called.

[0123] In some embodiments, the application management platform 110 may provide a knowledge base deletion control 612 in the knowledge base list area 610. Furthermore, the application management platform 110 may delete the knowledge base 120 associated with the knowledge base deletion control 612 in the knowledge base list area 610 in response to triggering the knowledge base deletion control 612.

[0124] In some embodiments, the application management platform 110 may provide multiple category viewing entries 620 in page 600. Each category viewing entry is associated with the knowledge base 120 of the corresponding data type. As an example, as shown in FIG6 , the application management platform 110 provides an all-category viewing entry 620-1, a document category viewing entry 620-2, a table category viewing entry 620-3, and an image category viewing entry 620-4 (collectively or individually referred to as category viewing entries 620) on page 600. The first data type corresponding to the all-category viewing entry 620-1 is the database 120 of all data types, the first data type corresponding to the document category viewing entry 620-2 is the document type, the first data type corresponding to the table category viewing entry 620-3 is the table type, and the first data type corresponding to the image category viewing entry 620-4 is the image type.

[0125] In some embodiments, the application management platform 110 may present the created knowledge base 120 of the first data type in the knowledge base list area 610 in response to selection of the category view entry 620 corresponding to the first data type among the multiple data types.

[0126] In some embodiments, the application management platform 110 may also provide a knowledge base search input box 625 in the page 600. Furthermore, the application management platform 110 may receive search information input by the user 105 in the knowledge base search input box 625 and update the knowledge base list area 610 to present the knowledge base 120 associated with the search information.

[0127] In some embodiments, the application management platform 110 may further provide a create knowledge base control 630 in the page 600. Furthermore, in response to the triggering of the create knowledge base control 630, the application management platform 110 may call the application management platform 110 to present the knowledge base creation page 400A of FIG. 4A.

[0128] In some embodiments, the application management platform 110 may present a details page of the knowledge base 120 in response to a request to view details of the knowledge base 120. The details page includes an aggregated presentation of multiple processed data items, and may also include metadata of the knowledge base 120 (the name and description of the knowledge base 120 may be collectively referred to as metadata of the knowledge base), a list of files imported into the knowledge base 120, index setting information corresponding to the knowledge base, and / or the number of data items.

[0129] In some embodiments, the application management platform 110 may also provide a detail view control 613 in the knowledge base list area 610. Furthermore, the application management platform 110 may present a detail page of the knowledge base 120 associated with the detail view control in response to triggering of the detail view control 613.

[0130] In some embodiments, the application management platform 110 may present a detail page 700A of the knowledge base 120 of the document type as shown in FIG. 7A in response to triggering the detail view control 613 of the knowledge base 120 associated with the document type.

[0131] 7A to 7F illustrate examples of pages 700A to 700F of a knowledge base for managing document types according to some embodiments of the present disclosure. Pages 700A to 700F may be provided by the application management platform 110 shown in FIG1 , for example.

[0132] In some embodiments, the application management platform 110 may present a details page 700A for a knowledge base A of a document type, as shown in FIG7A . The application management platform 110 may present a document presentation area 710 on the details page 700A, which may present multiple indexable data items. For example, in the details page 700A shown in FIG7A , the data corresponding to each color block is an indexable data item (here, a document type).

[0133] In some embodiments, in response to selection of a target file in the list of files, the application management platform 110 may present an aggregate presentation of data items obtained after processing the target file in a detail page.

[0134] In some embodiments, the application management platform 110 may provide a document list control 715 on the details page 700A. Furthermore, in response to triggering the document list control 715, the application management platform 110 may present a list of documents (which may be referred to as files) imported into the knowledge base 120. The list of documents may present multiple document selection items, each of which may include a full content selection item and at least one document name selection item associated with a single document. For example, as shown in the details page 700A of FIG. 7A , the list of documents may include a full content selection item, a XXXXX.TXT selection item, a XXXXXX.DOC selection item, and so on.

[0135] In some embodiments, the application management platform 110 can, in response to a triggering of a document selection, update the at least one indexable data item associated with the document selection in the document presentation area 710. For example, as shown in detail page 700A of FIG7A , the application management platform 110 can, in response to a triggering of a full content selection, update the presentation of all data items in the knowledge base 120 in the document presentation area 710. The application management platform 110 can also, in response to a triggering of a XXXXX.TXT selection, update the content of XXXXX.TXT presented in the document presentation area 710.

[0136] In some embodiments, the application management platform 110 may also present metadata corresponding to the knowledge base 120 (ie, the name and description information of the knowledge base 120 ) in the details page 700A. The description information may indicate the type, function, etc. of the knowledge base 120 .

[0137] In some embodiments, the application management platform 110 may also present index setting information corresponding to the knowledge base 120 (ie, the segmentation strategy of the knowledge base 120 ) in the details page 700A.

[0138] In some embodiments, the application management platform 110 may also present the number of data items (ie, the total number of segments of the data items) in the detail page 700A.

[0139] In some embodiments, the application management platform 110 may also present a new data addition entry on the details page 700A. For example, the details page 700A in FIG7A provides an add document control 720. In response to triggering the add document control 720, the application management platform 110 may present the new data page 700B shown in FIG7B. The method for selecting uploaded data on the new data page 700B can be referenced to the method described in the second configuration area 420 of page 400A in FIG4A , and will not be further described here.

[0140] In some embodiments, the application management platform 110 may present an upload data page 700C as shown in FIG7C in response to selecting the local document upload method in the newly added data page 700B. The upload method of the upload data page 700C here can refer to the method involved in the document upload area 435 of the page 400B of FIG4B, and will not be repeated here.

[0141] In some embodiments, the application management platform 110 may also present a re-indexing trigger entry on the details page 700A. For example, the details page 700A in FIG7A provides a re-segmentation control 725. In response to triggering the re-segmentation control 725, the application management platform 110 may present a re-segmentation page 700D as shown in FIG7D. The segmentation method for re-segmenting the re-segmentation page 700D can be referred to the method described in the document index settings area 455 on page 400E in FIG4E , and will not be further described here.

[0142] In some embodiments, the application management platform 110 may present an update content page 700E as shown in FIG7E in response to the segmentation setting completion of the re-segmentation page 700D. As can be seen on the update content page 700E, based on the segmentation setting on the re-segmentation page 700D, the segmentation setting of all data items in the knowledge base 120 may be updated (i.e., the index setting information is updated).

[0143] In some embodiments, the application management platform 110 may also present an entry for setting the update frequency in the details page 700A. As an example, the entry for setting the update frequency only appears in the details page of the knowledge base 120 where the target data source is selected as online data. The application management platform 110 may provide an update frequency control in the details page of the knowledge base 120 where the target data source is selected as online data. Furthermore, the application management platform 110 may present update frequency selection items in response to the triggering of the update frequency control. The update frequency selection items may include no automatic update, daily update, update every 3 days, update every 7 days, etc. The update frequency is the frequency of updating documents from online data, such as daily update means updating documents from online data once a day. The specific update frequency selection items can be set as needed, and the present disclosure does not impose any restrictions on this.

[0144] In some embodiments, the application management platform 110 may also present a processing control associated with the target data item in response to a first preset operation (long press or double click, etc.) on a target data item among multiple data items on the details page 700A. As an example, in the 700F page shown in FIG7F , the application management platform 110 may present a processing box 730 associated with the target data item in response to the first preset operation on the target data item. The processing box 730 may include an edit option 731 and a delete option 732. Further, the application management platform 110 may receive editing information of the user 105 on the data item associated with the edit document control 731 in the edit mode in response to the triggering of the edit document control 731, thereby modifying the data item. The application management platform 110 may also delete the data item associated with the delete row control 732 in response to the triggering of the delete row control 732.

[0145] In some embodiments, the application management platform 110 may receive a modification request for the knowledge base 120 , where the modification request indicates at least one of the following: modification of metadata of the knowledge base, modification of index setting information of the knowledge base, and addition of data to the knowledge base.

[0146] In some embodiments, the application management platform 110 can receive modification information of the knowledge base metadata (including the knowledge base name and description information) input by the user through natural language in response to a second preset operation (long press or double click, etc.) on the knowledge base name on the details page 700A, and then modify the metadata of the knowledge base 120.

[0147] In some embodiments, for a table-type knowledge base, the layout of its detail page and the information presented can be similar to the document-type knowledge base shown in Figures 7A to 7F . The difference is that in a table-type knowledge base, each entry in the table (corresponding to the indexable data items in the table) can be presented to the user one by one.

[0148] In some embodiments, with continued reference to FIG. 6 , the application management platform 110 may present a detail page 800A of the image-type knowledge base 120 as shown in FIG. 8A in response to triggering the detail view control 613 of the image-type knowledge base 120 .

[0149] 8A to 8C illustrate examples of pages 800A to 800C of a knowledge base for managing image types according to some embodiments of the present disclosure. Pages 800A to 800C may be provided by the application management platform 110 shown in FIG1 , for example.

[0150] In some embodiments, the application management platform 110 may present a details page 800A associated with the knowledge base E of the image-type knowledge base 120, as shown in FIG8A . The application management platform 110 may present an image presentation area 810 on the details page 800A, which may present multiple indexable data items. As an example, in the details page 800A shown in FIG8A , each box containing an image and an image annotation is an indexable data item (here, of the image type).

[0151] In some embodiments, the application management platform 110 can present a list of images imported into the knowledge base E (including the image content of each data item (including the image and image name)) and the text annotations corresponding to the images in the details page 800A. The application management platform 110 can present the upload method of the data item in the knowledge base in the details page 800A. The upload method may include local image, online image, XX application, and custom. As an example, the 800A interface in Figure 8A presents an upload method area 815, and the upload method area 815 presents a local representation that the upload method of the data item in the knowledge base E is a local image. Correspondingly, when the upload method of the data item in the knowledge base E is an online image, the online method can be presented in the upload method area 815, when the upload method of the data item in the knowledge base E is XX application, the XX application can be presented in the upload method area 815, and when the upload method of the data item in the knowledge base E is custom, the custom method can be presented in the upload method area 815.

[0152] In some embodiments, the application management platform 110 may also present the annotation method of the data item in the knowledge base on the details page 800A. For example, as shown in FIG8A , the interface 800A presents the annotation method area 820. If the annotation method area 820 displays "Automatic Identification", it indicates that the annotation method of the data item in the knowledge base E is automatic annotation (or intelligent annotation). Correspondingly, if the annotation method of the data item in the knowledge base E is manual annotation, the upload method area 815 may display "Manual Identification".

[0153] In some embodiments, the application management platform 110 may further present a target image on a detail page 800A in response to a request to view the details of a target image among the multiple images in the knowledge base 120. For example, as shown in the detail page 800A of FIG8A , the application management platform 110 may present a target image page 800B as shown in FIG8B in response to a request to view the details of the target image (receiving an operation of clicking on the image or annotating the image).

[0154] In some embodiments, the application management platform 110 can present the target image's image content (image name and image) and image annotations (text annotations of the image) on the target image page 800B in FIG8B . The application management platform 110 can also provide an annotation input box 825 (also known as an annotation display area) on the target image page 800B. Furthermore, the application management platform 110 can receive annotation information input by the user through natural language and update the image annotations of the target image.

[0155] In some embodiments, the application management platform 110 may also provide an automatic identification control 830 on the target image page 800B. Furthermore, when the target image's image annotation content is not empty, the application management platform 110 may, in response to triggering the automatic identification control 830, present an overlay reminder area 835 as shown in FIG8C . For example, as shown in FIG8C , the overlay reminder area may present a reminder message, which may be textual content such as "Confirm to overwrite existing annotation content."

[0156] In some embodiments, further, the overlay reminder area 835 may provide a confirmation option 836 and a cancel option 837. The application management platform 110 may automatically generate annotation content for the target image in response to the triggering of the confirmation option 836. The application management platform 110 may also cancel the automatic generation of annotation content for the target image in response to the triggering of the confirmation option 837.

[0157] In some embodiments, when the image annotation content of the target image is empty, the application management platform 110 can automatically generate annotation content for the target image in response to triggering of the automatic recognition control 830 .

[0158] In some embodiments, the method of automatically generating annotation content for the target image may be to rely on a relevant image model to deeply understand the image to generate annotation content or perform OCR (Optical Character Recognition) text recognition to extract text information in the image as annotation information.

[0159] In some embodiments, the application management platform 110 may also provide an add image control 840 in the target image page 800A. Furthermore, the application management platform 110 may add a new image to the knowledge base in response to triggering the add image control 840. The specific method for adding an image can refer to the image upload method described above in Figures 5A to 5G and will not be further described here.

[0160] As mentioned above, the created knowledge base can be associated with an application or workflow. In some embodiments, the application management platform 110 can present a knowledge base selection area in the creation page of the target application or target workflow, and the knowledge base selection area indicates multiple data types. In response to the selection of a target type from the multiple data types, the application management platform 110 can present at least a knowledge base corresponding to the target data type in the knowledge base selection area. In response to receiving the selection of the presented knowledge base, the application management platform 110 can associate the selected knowledge base with the target application or target workflow.

[0161] Figure 9 shows an example of a creation page 900 for configuring a knowledge base in a third-party application according to some embodiments of the present disclosure. The third-party application can be a target application or a target workflow. In the example of Figure 9, it is assumed that the application for which the knowledge base is to be configured is a digital assistant. For example, when developing a digital assistant application, it is desired to associate the digital assistant with a specific knowledge base to perform information retrieval from the knowledge base, thereby enabling better question-and-answer interaction with the user. The creation page 900 can be provided, for example, by the application management platform 110 shown in Figure 1.

[0162] In some embodiments, the application management platform 110 may present a creation page 900 for a digital assistant as shown in FIG9 . The application management platform 110 may provide a knowledge base selection area 910 in the creation page 900. The knowledge base selection area 910 may provide options corresponding to multiple data types of the knowledge base, document options, table options, and image options. As an example, as shown in the creation page 900 of FIG9 , the knowledge base selection area 910 may include a document option 915-1, a table option 915-2, and an image option 915-3 (individually or collectively referred to as data type options 915). The creator of the digital assistant may determine as needed to associate the digital assistant to one or more knowledge bases, and select the corresponding type for knowledge base association.

[0163] For example, in response to selection of a target type from among multiple data types, the application management platform 110 may present at least one or more knowledge bases 120 that have been created and are associable under the target type in the knowledge base selection area 910. For example, as shown in the creation page 900 of FIG9 , in response to selection of the document option 915-1 from among multiple data type options 915, the application management platform 110 may present a knowledge base 120 of the document type.

[0164] In some embodiments, upon receiving a selection of a knowledge base 120 on the create page 900 , the application management platform 110 may associate the knowledge base 120 with the target application or target workflow. After the association is complete, the target application or target workflow determines whether to call the associated knowledge base as needed (e.g., based on received query information). If a call is determined to be necessary, the query information for the target application or target workflow can be processed by calling data from the associated knowledge base 120.

[0165] In some embodiments, the application management platform 110 may further provide a storage selection area and / or a skill configuration area on the creation page 900 to configure storage or corresponding skills for a target application or a target workflow.

[0166] FIG10 illustrates a flowchart of an example process 1000 for adding table-type data according to some embodiments of the present disclosure. This process 1000 can be performed on the aforementioned application management platform 110 or within the application management platform 110 (hereinafter, execution within the application management platform 110 is used as an example; the execution within the application management platform 110 is similar and is not further described here). The process 1000 is described below with reference to FIG1 .

[0167] As shown, at block 1010 , the application management platform 110 may receive a request 1010 to add a table fragment.

[0168] In block 1015 , the application management platform 110 may receive a selected upload method, which may include local upload 1015 - 1 , API interface upload 1015 - 2 , and custom upload 1015 - 3 .

[0169] After selecting local upload 1015 - 1 , block 1020 - 1 may be executed. In block 1020 - 1 , the application management platform 110 receives a table file in a local file, such as a table file on a user's terminal device.

[0170] After selecting the API interface to upload 1015-2, block 1020-2 may be executed. In block 1020-2, the application management platform 110 may receive a table file associated with the API interface. The API interface here may be any application that can provide a table type file.

[0171] After selecting custom upload 1015 - 3 , block 1020 - 3 may be executed. In block 1020 - 3 , the application management platform 110 may receive the manually written table file.

[0172] After executing block 1020 - 1 or block 1020 - 2 , block 1025 is executed. In block 1025 , the application management platform 110 may verify whether the layout of the tables is aligned, and align the tables if the layout is not aligned.

[0173] After executing block 1025 , block 1030 is executed. In block 1030 , the application management platform 110 previews the table file and sets index setting information (eg, header structure settings, indicating header fields in the table for indexing data items) for the table file.

[0174] After executing block 1030 or block 1020 - 3 , block 1035 is executed. In block 1035 , the application management platform 110 may complete the addition of the form in response to the completion of uploading the form file.

[0175] In some embodiments, one or more types of index libraries can be constructed for the data imported into the target type of knowledge base. The processed multiple data items are respectively stored in multiple types of index libraries and are indexed by multiple types of data indexes. Pre-constructing multiple types of data indexes helps to provide diversified data retrieval methods in subsequent calls to the knowledge base. In some embodiments, for the knowledge base 120 of document type, at least two types of index libraries can be established for the data items imported therein. The first index library can be a full-text search engine based on dependent keywords (such as ES (Elasticsearch)). The second index library can be a vector-based text relevance query engine (such as Viking), in which the feature vectors corresponding to each segment (i.e., data item) of the document are used as the basis for relevance retrieval. The establishment of the index library can be, for example, in the data processing stage of knowledge base creation.

[0176] FIG11 shows an example of a page 1100 provided by a knowledge base application according to some embodiments of the present disclosure. The page 1100 may be provided by the application management platform 110 shown in FIG1 , for example.

[0177] The application management platform 110 may receive an application setting request for the knowledge base 120 and present a knowledge base application setting page 1100 in FIG11 . The application management platform 110 may provide a search strategy area 1101 on page 1100 . The search strategy area 1101 may include a hybrid search option 1105-1, a semantic search option 1105-2, and a full-text search option 1105-3 (individually or collectively referred to as search options 1105 ). In response to selection of search option 1105 , the application management platform 110 may set the search strategy of the knowledge base 120 to the search strategy associated with the search option 1105 .

[0178] If the semantic search option 1105-2 is enabled, then for the data in the knowledge base 120, a semantic search of the document data can be performed based on the feature vectors in the second index library. If the full-text search option 1105-3 is enabled, then for the data in the knowledge base 120, a full-text search can be performed on the document data through keywords based on the first index library. If the hybrid search option 1105-1 is enabled, then semantic search and full-text search of the document data can be performed simultaneously based on the first index library and the second index library. As an example, as shown in page 1100 of Figure 11, the application management platform 110 can set the search strategy of the knowledge base 120 to a hybrid search strategy in response to the selection of the hybrid search option 1105-1.

[0179] In some embodiments, the application management platform 110 may provide a maximum recall number setting area 1110, a minimum match setting area 1115 and / or a recall method setting area 1120 on page 1100. Further, the application management platform 110 may receive the set maximum recall number (for example, the range may be 1-10) in the maximum recall number setting area 1110. The application management platform 110 may receive the set minimum match setting area 1115 (for example, the range may be 0.01-0.99). The application management platform 110 may receive the set recall method (i.e., the method of recalling data, such as automatic recall or recall on demand) in the recall method setting area 1120.

[0180] FIG12 shows a flowchart of an example process 1200 for retrieving knowledge base data based on hybrid search according to some embodiments of the present disclosure. The process 1200 for retrieving knowledge base data based on hybrid search can be executed in the application management platform 120 as described above. The process 1200 is described below with reference to FIG1 .

[0181] In the example of FIG12 , it is assumed that a knowledge base 120 of the document type is associated with a digital assistant 1205. In response to receiving a query for the knowledge base 120, the application management platform 120 can search for multiple groups of data items matching the query from index libraries of multiple types according to search algorithms corresponding to the multiple types, and select at least one data item from the multiple groups of data items as a response to the query based on the sorting results of the multiple groups of data items.

[0182] As shown in FIG12 , the application management platform 120 can respond to the digital assistant 1205's request to obtain data from the knowledge base 120, and index at least one data item 1220-1 (e.g., top-K1 data items) and at least one data item 1220-2 (e.g., top-K2 data items) that match the query from the knowledge base 120 based on the first index library 1215-1 and the second index library 1215-2, respectively, where K1 and K2 are positive integers greater than or equal to 1. The first index library 1215-1 can be a full-text search engine based on dependent keywords (such as ES (Elasticsearch)). The second index library 1215-2 can be a vector-based text relevance query engine (such as Viking), in which the feature vectors corresponding to each segment (i.e., data item) of the document are used as the basis for relevance retrieval. Thereafter, the at least one data item 1220-1 and the at least one data item 1220-2 can be reordered, and at least one filtered data item 1225 can be obtained based on the reordering results. For example, the first K data items out of K1+K2 data items may be selected, where K is a positive integer greater than or equal to 1. In some embodiments, the sets of two data items given by the two index libraries may be reordered based on the RFF algorithm (Reciprocal Rank Fusion, an algorithm that merges multiple ranked lists into a single aggregated list). At least one filtered data item 1225 is returned to the digital assistant 1205 as a retrieval result of the knowledge retrieval.

[0183] It should be understood that although two index libraries are used in the relevant descriptions of Figures 11 and 12, there may actually be more different types of index libraries that rely on different retrieval schemes.

[0184] Figures 13A and 13B illustrate flowcharts of example processes 1300A and 1300B for retrieving image-type knowledge base data, according to some embodiments of the present disclosure. These processes 1300A and 1300B can be executed within the application management platform 110 described above. In this example, it is assumed that the knowledge base created is an image-type knowledge base. Processes 1300A and 1300B are described below with reference to Figure 1.

[0185] As shown in FIG13A , in box 1305 , the application management platform 110 may receive a request from a digital assistant (or other applications such as a workflow) to associate with an image type knowledge base, and associate the digital assistant with the image type knowledge base.

[0186] In block 1310 , the application management platform 110 may receive query information input by a user via a digital assistant.

[0187] At block 1315, the application management platform 110 may calculate the similarity between the query information and the annotation information of the images in the knowledge base 120, and match the images in the knowledge base 120 based on the calculated similarity. Since both the query information and the annotation information are in text form, the application management platform 110 may also use a semantic search, full-text search, or hybrid search strategy within the image annotation information to find annotation information that matches the query information, in accordance with a document-based knowledge base approach.

[0188] In block 1320 , the application management platform 110 may recall a preset number of images whose similarity meets a preset threshold and the annotation information corresponding to the images as recalled content.

[0189] At block 1325, the application management platform 110 may combine the recalled content (including the image and its corresponding annotation information) with the query information as a query result and output it to the digital assistant. For example, the process of generating the query result based on the recalled content and the query information may be implemented using an LLM (Large Language Model).

[0190] FIG14 shows a flow chart of an example process 1400 for information processing according to some embodiments of the present disclosure. The process 1400 may be implemented in the application management platform 110. The process 1400 is described below with reference to FIG1.

[0191] As shown in the figure, in box 1410, the application management platform 110 presents a configuration page for receiving configuration information of the knowledge base in response to receiving the creation request, and the configuration page includes: a first configuration area for receiving the configuration of the target type of the knowledge base from multiple data types, and a second configuration area for receiving the configuration of the target data source of the knowledge base.

[0192] In block 1420 , the application management platform 110 imports data of the target type from the target data source into the knowledge base in response to receiving the configuration of the target type and the target data source.

[0193] In block 1430 , in response to the data import being completed, the application management platform 110 presents an index setting page corresponding to the target type for receiving index setting information for the imported data.

[0194] In block 1440 , in response to receiving the index setting information, the application management platform 110 creates a knowledge base of the target type based on the index setting information.

[0195] In some embodiments, the second configuration area presents at least one type of supported data source, where the at least one type of data source includes at least one of the following: a local data source, an online data source, a database, and custom data.

[0196] In some embodiments, importing the target type of data from the target data source into the knowledge base includes: presenting a data input area in response to the target data source being the type of custom data; and importing input data received in the data input area into the knowledge base.

[0197] In some embodiments, the target type includes a document type, and presenting an index settings page that matches the target type includes presenting an index settings page corresponding to the document type for receiving segment indexing settings for the document, the segment indexing settings indicating at least one of: a segmentation rule, a segment length, and a segment pre-processing rule for the document, the document segments corresponding to data items for indexing. In some embodiments, the target type includes a table type, and presenting an index settings page that matches the target type includes presenting an index settings page corresponding to the table type for receiving header indexing settings for the table, the header indexing settings indicating header fields in the table for indexing data items. In some embodiments, the target type includes an image type, and presenting an index settings page that matches the target type includes presenting an index settings page corresponding to the image type for receiving annotation settings for the image, the flag settings indicating text annotations for indexing the image.

[0198] In some embodiments, the target type includes a document type, and the index settings page corresponding to the document type includes an entry for default segment index settings and a user-defined segment index setting. In some embodiments, the target type includes an image type, and the index settings page corresponding to the image type includes an entry for automatically generating annotation settings and a user-defined annotation setting.

[0199] In some embodiments, process 1400 also includes: in response to a knowledge base list viewing request, presenting a knowledge base list page, the knowledge base list page including multiple category viewing entries corresponding to each of the multiple data types; and in response to selection of a category viewing entry corresponding to a first data type among the multiple data types, presenting a knowledge base of the created first data type.

[0200] In some embodiments, process 1400 also includes: in response to a request to view the details of the knowledge base, presenting a details page of the knowledge base, the details page including an aggregated presentation of multiple processed data items, and also including at least one of the following: metadata of the knowledge base, a list of files imported into the knowledge base; index setting information corresponding to the knowledge base, the number of data items, a new data addition entry, a re-indexing trigger entry, or an update frequency setting entry.

[0201] In some embodiments, process 1400 also includes: in response to a trigger operation on the first data item in the details page, presenting an edit option or a delete option for the first data item; and in response to selection of the edit option, receiving editing input for the first data item in the edit mode of the first data item; and in response to selection of the delete option, deleting the first data item from the knowledge base.

[0202] In some embodiments, process 1400 further includes: in response to selection of a target file in the list of files, presenting an aggregate presentation of data items obtained after processing the target file in the detail page.

[0203] In some embodiments, process 1400 further includes: receiving a modification request for the knowledge base, the modification request indicating at least one of the following: modification of metadata of the knowledge base, modification of index setting information of the knowledge base, and addition of data to the knowledge base.

[0204] In some embodiments, the target type of the knowledge base is an image type, and presenting a detail page of the knowledge base includes presenting a list of images imported into the knowledge base and text annotations corresponding to one or more images on the detail page.

[0205] In some embodiments, process 1400 further includes: in response to a request to view the details of a target image in a knowledge base, presenting the target image. Alternatively or additionally, in some embodiments, process 1400 further includes: in response to receiving a trigger operation for automatic annotation generation, using an automatic annotation generation tool to generate a target text annotation corresponding to the target image. Alternatively or additionally, in some embodiments, process 1400 further includes, in response to the target image not having a corresponding text annotation, presenting the target text annotation in the annotation display area corresponding to the target image. Alternatively or additionally, in some embodiments, process 1400 further includes, in response to the target image having a corresponding previous text annotation, replacing the previous text annotation with the target text annotation in the annotation display area corresponding to the target image upon receiving user confirmation.

[0206] In some embodiments, process 1400 also includes: presenting a knowledge base selection area in a creation page of a target application or a target workflow, the knowledge base selection area indicating a plurality of data types; in response to a selection of a target type from the plurality of data types, presenting at least the knowledge base corresponding to the target type in the knowledge base selection area; and in response to receiving a selection of a knowledge base, associating the knowledge base with the target application or the target workflow.

[0207] In some embodiments, process 1400 further includes: in response to the knowledge base being associated with the target application or target workflow, causing the knowledge base to be called to determine processing of the query information based on query information of the target application or target workflow.

[0208] In some embodiments, creating the knowledge base of the target type includes: processing the imported data of the target type based on the index setting information, and the created knowledge base includes a plurality of data items that are indexable after the processing.

[0209] In some embodiments, for the target type of data, the plurality of data items are stored in multiple types of index repositories and indexed by multiple types of data indexes. Process 1400 further includes: in response to receiving a query against a knowledge base, searching the multiple types of index repositories for multiple groups of data items that match the query according to search algorithms corresponding to the multiple types; and selecting at least one data item from the multiple groups of data items as a response to the query based on a ranking result of the multiple groups of data items.

[0210] Embodiments of the present disclosure also provide corresponding apparatuses for implementing the above-described methods or processes. FIG15 shows a schematic block diagram of an example apparatus 1500 for creating a virtual object according to certain embodiments of the present disclosure. Apparatus 1500 may be implemented as or included in electronic device 110. The various modules / components in apparatus 1500 may be implemented by hardware, software, firmware, or any combination thereof.

[0211] As shown in Figure 15, the device 1500 includes a presentation module 1510, which is configured to present a configuration page for receiving configuration information of a knowledge base in response to receiving a creation request, the configuration page including: a first configuration area for receiving a configuration of a target type of the knowledge base from a plurality of data types, and a second configuration area for receiving a configuration of a target data source of the knowledge base; an import module 1520, which is configured to import data of the target type from the target data source into the knowledge base in response to receiving the configuration of the target type and the target data source; a setting module 1530, which is configured to present an index setting page corresponding to the target type in response to completion of the data import, for receiving index setting information for the imported data; a creation module 1540, which is configured to create a knowledge base of the target type based on the index setting information in response to receiving the index setting information.

[0212] In some embodiments, the second configuration area presents at least one type of supported data source, where the at least one type of data source includes at least one of the following: a local data source, an online data source, a database, and custom data.

[0213] In some embodiments, the import module 1520 is further configured to: present a data input area in response to the target data source being the type of custom data; and import the input data received in the data input area into the knowledge base.

[0214] In some embodiments, the target type includes a document type, and the presentation module 1510 is configured to present an index setting page corresponding to the document type, for receiving segment indexing settings for the document, the segment indexing settings indicating at least one of the following: a segmentation rule, a segment length, and a segment pre-processing rule for the document, the segments of the document corresponding to the data items for indexing. In some embodiments, the target type includes a table type, and the presentation module 1510 is configured to present an index setting page corresponding to the table type, for receiving a header indexing setting for the table, the header indexing setting indicating a header field in the table for indexing the data items. In some embodiments, the target type includes an image type, and the presentation module 1510 is configured to present an index setting page corresponding to the image type, for receiving a tag setting for the image, the flag setting indicating a text tag for indexing the image.

[0215] In some embodiments, the target type includes a document type, and the index settings page corresponding to the document type includes an entry for default segment index settings and a user-defined segment index setting. In some embodiments, the target type includes an image type, and the index settings page corresponding to the image type includes an entry for automatically generating annotation settings and a user-defined annotation setting.

[0216] In some embodiments, the device 1500 also includes: a list presentation module, configured to present a knowledge base list page in response to a knowledge base list viewing request, the knowledge base list page including multiple category viewing entries corresponding to each of the multiple data types; and a knowledge base viewing module, configured to present a created knowledge base of the first data type in response to a selection of a category viewing entry corresponding to a first data type among the multiple data types.

[0217] In some embodiments, the device 1500 also includes: a details presentation module, configured to present a details page of the knowledge base in response to a details viewing request for the knowledge base, the details page including an aggregated presentation of multiple processed data items, and also including at least one of the following: metadata of the knowledge base, a list of files imported into the knowledge base; index setting information corresponding to the knowledge base, the number of data items, a new data addition entry, a re-indexing trigger entry, or an update frequency setting entry.

[0218] In some embodiments, the device 1500 also includes: an option presentation module, configured to present an edit option or a delete option for the first data item in response to a trigger operation on the first data item in the details page; and an edit receiving module, configured to receive edit input for the first data item in the edit mode of the first data item in response to selection of the edit option; and a data item deletion module, configured to delete the first data item from the knowledge base in response to selection of the delete option.

[0219] In some embodiments, the device 1500 further includes an aggregate presentation module configured to present an aggregate presentation of data items obtained after processing the target file in the detail page in response to selection of the target file in the list of files.

[0220] In some embodiments, the device 1500 also includes a modification request receiving module, which is configured to: receive a modification request for the knowledge base, the modification request indicating at least one of the following: modification of the metadata of the knowledge base, modification of the index setting information of the knowledge base, and addition of data to the knowledge base.

[0221] In some embodiments, the target type of the knowledge base is an image type, and the presentation module 1510 is further configured to present a list of images imported into the knowledge base and text annotations corresponding to one or more images on the detail page.

[0222] In some embodiments, the device 1500 also includes: an image presentation module, configured to present the target image in response to a request for viewing the details of the target image in the knowledge base; an annotation generation module, configured to generate a target text annotation corresponding to the target image using an automatic annotation generation tool in response to receiving a trigger operation for automatic annotation generation; an annotation presentation module, configured to present the target text annotation in the annotation display area corresponding to the target image in response to the existence of a corresponding text annotation for the target image; and an annotation replacement module, configured to replace the previous text annotation with the target text annotation in the annotation display area corresponding to the target image upon receiving user confirmation in response to the existence of a corresponding previous text annotation for the target image.

[0223] In some embodiments, the device 1500 also includes: a knowledge base selection module, configured to present a knowledge base selection area in a creation page of a target application or a target workflow, the knowledge base selection area indicating multiple data types; a type selection module, configured to present at least the knowledge base corresponding to the target type in the knowledge base selection area in response to a selection of a target type among multiple data types; and a knowledge base association module, configured to associate the knowledge base with the target application or target workflow in response to receiving a selection of the knowledge base.

[0224] In some embodiments, the apparatus 1500 further includes a calling module configured to: in response to the knowledge base being associated with the target application or target workflow, based on query information of the target application or target workflow, cause the knowledge base to be called to determine processing of the query information.

[0225] In some embodiments, the creation module 1530 is further configured to: process the imported data of the target type based on the index setting information, and the created knowledge base includes a plurality of data items that can be indexed after the processing.

[0226] In some embodiments, for the target type of data, the multiple data items are stored in multiple types of index repositories and indexed by multiple types of data indexes. Apparatus 1500 further includes a search module configured to, in response to receiving a query against a knowledge base, search the multiple types of index repositories for multiple groups of data items that match the query according to search algorithms corresponding to the multiple types; and a data item selection module configured to select at least one data item from the multiple groups of data items as a response to the query based on a ranking result of the multiple groups of data items.

[0227] FIG16 shows a block diagram of an electronic device 1600 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 1600 shown in FIG16 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 1600 shown in FIG16 can be used to implement the application management platform 110 and the application management platform 110 of FIG1 .

[0228] As shown in FIG16 , electronic device 1600 is a general-purpose electronic device. Components of electronic device 1600 may include, but are not limited to, one or more processors or processing units 1610, memory 1620, storage device 1630, one or more communication units 1640, one or more input devices 1650, and one or more output devices 1660. Processing unit 1610 may be a real or virtual processor and is capable of performing various processes according to programs stored in memory 1620. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to enhance the parallel processing capabilities of electronic device 1600.

[0229] The electronic device 1600 typically includes a plurality of computer storage media. Such media can be any accessible media that is accessible to the electronic device 1600, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 1620 can be a volatile memory (e.g., registers, cache, random access memory (RAM)), a non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 630 can be a removable or non-removable medium and can include a machine-readable medium, such as a flash drive, a disk, or any other medium that can be used to store information and / or data and can be accessed within the electronic device 1600.

[0230] The electronic device 1600 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 16 , a disk drive for reading from or writing to a removable, non-volatile disk (e.g., a “floppy disk”) and an optical drive for reading from or writing to a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data media interfaces. The memory 1620 may include a computer program product 1625 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0231] The communication unit 1640 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 1600 can be implemented as a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, the electronic device 1600 can operate in a networked environment using a logical connection to one or more other servers, a network personal computer (PC), or another network node.

[0232] Input device 1650 may be one or more input devices, such as a mouse, keyboard, or trackball. Output device 1660 may be one or more output devices, such as a renderer, speaker, or printer. Electronic device 1600 may also communicate with one or more external devices (not shown) via communication unit 1640 as needed, such as a storage device, a renderer, or the like, with one or more devices that allow a user to interact with electronic device 1600, or with any device that allows electronic device 1600 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0233] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0234] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0235] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0236] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0237] The flow charts and block diagrams in the accompanying drawings have presented the possible architecture, functions and operations of the systems, methods and computer program products according to multiple implementations of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a special hardware-based system that performs the function or action of the specification, or can be implemented by a combination of special hardware and computer instructions.

[0238] While various implementations of the present disclosure have been described above, the foregoing description is intended to be illustrative, not exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is selected to best explain the principles of the implementations, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. An information processing method, comprising: In response to receiving the creation request, presenting a configuration page for receiving configuration information of the knowledge base, the configuration page including: a first configuration area for receiving a configuration of a target type of the knowledge base from a plurality of data types, and A second configuration area is used to receive configuration of a target data source of the knowledge base; In response to receiving the configuration of the target type and the target data source, importing data of the target type from the target data source into the knowledge base; In response to the data import being completed, presenting an index setting page corresponding to the target type for receiving index setting information for the imported data; and In response to receiving the index setting information, the knowledge base of the target type is created based on the index setting information. 2 . The method according to claim 1 , wherein the second configuration area presents at least one type of supported data source, the at least one type of data source comprising at least one of the following: a local data source, an online data source, a database, and custom data.

3. The method according to claim 2, wherein importing the target type of data from the target data source into the knowledge base comprises: In response to the target data source being the type of the custom data, presenting a data input area; as well as Input data received in the data input area is imported into the knowledge base.

4. The method according to claim 1, wherein The target type includes a document type, and presenting an index setting page matching the target type includes: Presenting an index setting page corresponding to the document type, for receiving segment index settings for the document, the segment index settings indicating at least one of the following: a segment rule, a segment length, and a segment pre-processing rule for the document, wherein the segments of the document correspond to data items for indexing; or, The target type includes a table type, and presenting an index setting page matching the target type includes: presenting an index setting page corresponding to the table type, for receiving a header index setting for the table, the header index setting indicating a header field in the table for indexing data items; or The target type includes an image type, and presenting an index setting page matching the target type includes presenting an index setting page corresponding to the image type for receiving an annotation setting for the image, the flag setting indicating a text annotation for indexing the image.

5. The method according to claim 1, wherein The target type includes a document type, and the index setting page corresponding to the document type includes input entries for default segment index settings and user-defined segment index settings; or The target type includes an image type, and the index setting page corresponding to the image type includes an automatic generation entry for annotation settings and an input entry for user-defined annotation settings.

6. The method according to claim 1, further comprising: In response to the knowledge base list viewing request, presenting a knowledge base list page, the knowledge base list page including a plurality of category viewing entries corresponding to each of the plurality of data types; as well as In response to selection of a classification view entry corresponding to a first data type among the plurality of data types, the created knowledge base of the first data type is presented.

7. The method according to claim 1, further comprising: In response to a request for viewing details of the knowledge base, a details page of the knowledge base is presented, wherein the details page includes an aggregate presentation of the processed multiple data items and further includes at least one of the following: metadata of the knowledge base, a list of files imported into the knowledge base; Index setting information corresponding to the knowledge base, the number of data items, New data addition entry, Re-indexing trigger entry, Entrance to set the update frequency.

8. The method according to claim 7, further comprising: In response to a triggering operation on a first data item in the detail page, presenting an edit option or a delete option for the first data item; as well as In response to selection of the edit option, receiving an edit input for the first data item in an edit mode for the first data item; and In response to selection of the delete option, the first data item is deleted from the knowledge base.

9. The method according to claim 7, further comprising: In response to selection of a target file in the file list, an aggregate presentation of data items processed from the target file is presented in the detail page.

10. The method according to claim 1, further comprising: A modification request for the knowledge base is received, the modification request indicating at least one of the following: Modification of metadata of said knowledge base, Modification of index setting information of the knowledge base, Additions to the knowledge base.

11. The method according to claim 7, wherein the target type of the knowledge base is an image type, and wherein presenting a detail page of the knowledge base comprises: A list of images imported into the knowledge base and text annotations corresponding to one or more images are presented on the detail page.

12. The method of claim 11, further comprising performing at least one of the following: In response to a request for viewing details of a target image in the knowledge base, presenting the target image; In response to receiving a trigger operation for automatic annotation generation, generating a target text annotation corresponding to the target image using an automatic annotation generation tool; In response to the target image not having a corresponding text annotation, presenting the target text annotation in an annotation display area corresponding to the target image; In response to the existence of a previous text annotation corresponding to the target image, the previous text annotation is replaced with the target text annotation in the annotation display area corresponding to the target image upon receiving user confirmation.

13. The method according to claim 1, further comprising: In a creation page of a target application or a target workflow, presenting a knowledge base selection area, wherein the knowledge base selection area indicates the plurality of data types; In response to selection of the target type from the plurality of data types, presenting at least the knowledge base corresponding to the target type in the knowledge base selection area; as well as In response to receiving a selection of the knowledge base, the knowledge base is associated with the target application or the target workflow.

14. The method according to claim 13, further comprising: In response to the knowledge base being associated with the target application or the target workflow, the knowledge base is called to determine processing of the query information based on query information of the target application or the target workflow.

15. The method of claim 1 , wherein creating the knowledge base of the target type comprises: The imported data of the target type is processed based on the index setting information, and the created knowledge base includes a plurality of data items that are indexable after the processing.

16. The method according to claim 15, wherein for the data of the target type, the plurality of data items are respectively stored in index repositories of multiple types and indexed by data indexes of multiple types, the method further comprising: In response to receiving a query targeting the knowledge base, searching for a plurality of groups of data items matching the query from the index libraries of the plurality of types respectively according to the search algorithms corresponding to the plurality of types; as well as Based on the ranking results of the plurality of groups of data items, at least one data item is selected from the plurality of groups of data items to be used as a response to the query.

17. An apparatus for information processing, comprising: a presentation module configured to present, in response to receiving a creation request, a configuration page for receiving configuration information of a knowledge base, the configuration page comprising: a first configuration area for receiving configuration of a target type of the knowledge base from a plurality of data types, and a second configuration area for receiving configuration of a target data source of the knowledge base; an import module configured to import data of the target type from the target data source into the knowledge base in response to receiving configuration of the target type and the target data source; a setting module configured to, in response to completion of the data import, present an index setting page corresponding to the target type, for receiving index setting information for the imported data; A creating module is configured to create the knowledge base of the target type based on the index setting information in response to receiving the index setting information.

18. An electronic device comprising: at least one processing unit; as well as At least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 16 when executed by the at least one processing unit.

19. A computer-readable storage medium having a computer program stored thereon, wherein the computer program is executable by a processor to implement the method according to any one of claims 1 to 16.

20. A computer program product tangibly stored in a computer storage medium and comprising computer executable instructions which, when executed by a device, cause the device to perform the method according to any one of claims 1 to 16.

Images