Data processing method, device, equipment and storage medium

Abstract

Embodiments of the present disclosure provide a method, apparatus, device, and storage medium for data processing. The method includes: receiving a selection of a target portion in a data object, the target portion having reference content; generating a target vectorized representation corresponding to the target portion based on the target portion in the data object and at least a portion of the reference content; and storing the target vectorized representation in a knowledge base for use in a query against the data object as at least one of the following as a result of the query: at least a portion of the target portion, at least a portion of the reference content. In this way, the application creation user can store the vectorized representation of the reference content of the data object in batches in the knowledge base to expand the knowledge reserve in the knowledge base, which advantageously improves the quality of the query results provided to the end user.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to a method, apparatus, device, and computer-readable storage medium for data processing. Background Art

[0002] With the development of information technology, various terminal devices can provide various services to people in work and life. Applications that provide services can be deployed in terminal devices. Terminal devices present corresponding content and interact with users through the user interface of the application to meet various needs of users. In some cases, users may initiate queries within the application. Therefore, how to provide structured data as knowledge to users to improve the quality of query results provided to users is a problem of concern. Summary of the invention

[0003] In a first aspect of the present disclosure, a method for data processing is provided. The method includes: receiving a selection of a target portion in a data object, the target portion having reference content; generating a target vectorized representation corresponding to the target portion based on the target portion in the data object and at least a portion of the reference content; and storing the target vectorized representation in a knowledge base, for using at least one of the following as a query result in a query for the data object: at least a portion of the target portion, at least a portion of the reference content.

[0004] In a second aspect of the present disclosure, a method for data processing is provided. The method includes: receiving a query for a data object; determining a target vectorized representation matching the query from a knowledge base, the target vectorized representation being generated based on a target portion in the data object and at least a portion of a referenced content of the target portion; and determining a result of the query based on the target vectorized representation, the result of the query indicating at least one of the following: at least a portion of the target portion, at least a portion of the referenced content.

[0005] In a third aspect of the present disclosure, a data processing device is provided. The device includes: a selection receiving module configured to receive a selection of a target part in a data object, the target part having reference content; a target vectorized representation generating module configured to generate a target vectorized representation corresponding to the target part based on the target part in the data object and at least a part of the reference content; and a target vectorized representation storing module configured to store the target vectorized representation in a knowledge base, for taking at least one of the following as a query result in a query for the data object: at least a part of the target part, at least a part of the reference content.

[0006] In a fourth aspect of the present disclosure, a data processing device is provided. The device includes: a query receiving module configured to receive a query for a data object; a target vectorized representation determining module configured to determine a target vectorized representation matching the query from a knowledge base, the target vectorized representation being generated based on a target portion in the data object and at least a portion of the referenced content of the target portion; and a query result determining module configured to determine a result of the query based on the target vectorized representation, the result of the query indicating at least one of the following: at least a portion of the target portion, at least a portion of the referenced content.

[0007] In a fifth aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit. When the instructions are executed by the at least one processing unit, the electronic device executes the methods of the first aspect and the second aspect.

[0008] In a sixth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the medium, and when the computer program is executed by a processor, the method of the first aspect and the method of the second aspect are implemented.

[0009] It should be understood that the content described in this 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] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;

[0012] Figure 2 A schematic diagram showing data transfer to a knowledge base according to some embodiments of the present disclosure is shown;

[0013] Figure 3 An example of a page for selecting fields in a data table according to some embodiments of the present disclosure is shown;

[0014] Figure 4 An example of a page showing a reference content type selection for a text type field according to some embodiments of the present disclosure is shown;

[0015] Figure 5An example of a page for selecting a reference content type for a numeric type field according to some embodiments of the present disclosure is shown;

[0016] Figure 6 An example of a page showing results of a query according to some embodiments of the present disclosure is shown;

[0017] Figure 7 An example of a page showing the learning status of reference contents of various fields in a data table by a knowledge base according to some embodiments of the present disclosure is shown;

[0018] Fig. 8A A flowchart showing a process of data processing according to some embodiments of the present disclosure;

[0019] Figure 8B A flowchart showing another process of data processing according to some embodiments of the present disclosure;

[0020] Fig. 9A A schematic structural block diagram of a data processing device according to some embodiments of the present disclosure is shown;

[0021] Fig. 9B A schematic structural block diagram showing another apparatus for data processing according to some embodiments of the present disclosure; and

[0022] Fig.10 A block diagram of an electronic device in which one or more embodiments of the present disclosure may be implemented is shown. DETAILED DESCRIPTION

[0023] Embodiments of the present disclosure will be described in more detail below 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 being limited to the embodiments set forth herein. On the contrary, 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 only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0024] 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 also be included below.

[0025] Herein, unless explicitly stated, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.

[0026] 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.

[0027] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the types, scopes of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to relevant users and their authorization should be obtained 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.

[0028] 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 software or hardware such as an electronic device, application, server or storage medium that executes the operation of the technical solution of the present disclosure based on the prompt message.

[0029] As an optional but non-limiting implementation, in response to receiving an active request from a relevant user, a prompt message is sent to the relevant user, for example, in the form of a pop-up window, in which the prompt message may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to select "agree" or "disagree" to provide information to the electronic device.

[0030] 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 meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0031] As used herein, the term "model" can learn the association between the corresponding input and output from the training data, so that after the training is completed, the corresponding output can be generated for a given input. 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 multi-layer 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.

[0032] Figure 1A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. Environment 100 involves an application management platform 110, which can support the creation of applications and / or the running of applications. In some embodiments, the portion of the application management platform 110 that supports the creation of applications can also be referred to as an application creation portion. In some embodiments, the portion of the application management platform 110 that supports the running of applications can also be referred to as an application running portion.

[0033] like Figure 1 As shown, the application creation part can provide the user 105 with an environment for creating and publishing applications. User 105 can be referred to as an application creation user or creator. In some embodiments, the application creation part can be a low-code platform that provides a collection of tools for application creation. The application creation part can support visual development of various types of applications, so that developers can skip the manual coding process and speed up the application development cycle and cost. The application creation part can support any appropriate platform for users to develop one or more types of applications, for example, it can include a platform based on Application Platform as a Service (aPaaS). Such a platform can support users to efficiently develop applications and implement operations such as application creation and application function adjustment.

[0034] The application creation part can be deployed locally on the terminal device of user 105, and / or can be supported by a server-side device. For example, the terminal device of user 105 can run a client of the application creation part, which can support the interaction between the user and the application creation part provided by the server. In the case where the application creation part runs locally on the user's terminal device, the user 105 can directly interact with the local application creation part using the terminal device. In the case where the application creation part runs on the server-side device, the server-side device can, based on the communication connection with the terminal device, implement service provision for the client running in the terminal device. The application creation part can present a corresponding page 130 to the user 105 based on the operation of the user 105, so as to output to the user 105 and / or receive from the user 105 information related to application creation.

[0035] In some embodiments, the application creation part can be associated with a corresponding database, which stores data or information required for the application creation process supported by the application creation part. For example, the database can store the code and description information corresponding to each functional module that constitutes the application. The application creation part can also perform operations such as calling, adding, deleting, and updating the functional modules in the database. The database can also store operations that can be performed on different functional blocks. Exemplarily, in a scenario where an application is to be created, the application creation part can call the corresponding functional blocks from the database to build the application.

[0036] In an embodiment of the present disclosure, a user 105 can create a target application 120 as needed on the application creation part and publish the target application 120. The target application 120 can be published to any appropriate application running part, as long as the application running part can support the operation of the target application 120. After publishing, the target application 120 can be used to be operated by one or more users 145. The user 145 can be referred to as the end user of the target application 120. In some embodiments, the target application 120 may include or be implemented as a digital assistant 122.

[0037] The digital assistant 122 may be configured to have an intelligent conversation. Figure 1 In the example shown, the digital assistant 122 can be integrated into the target application 120 as a part of the target application 120 to assist in the task processing within the target application 120. In other examples, the digital assistant 122 can be configured as an independently running application, such as a web application or other types of applications. In such an example, the digital assistant 122 and the target application 120 can be regarded as the same application. The digital assistant 122 is provided to assist users with various task processing requirements in different applications and scenarios. During the interaction with the digital assistant 122, the user inputs an interactive message, and the digital assistant 122 provides a reply message in response to the user input. Generally, the digital assistant 122 can support users to input questions in natural language, and perform tasks and provide replies based on the understanding of natural language input and logical reasoning ability.

[0038] In some embodiments, digital assistant 122 can interact with user 145 as a contact. For example, digital assistant 122 can be implemented in an instant messaging (IM) application. Digital assistant 122 can interact with user 145 in a single chat session with user 145. In some embodiments, digital assistant 122 can interact with multiple users in a group chat session including multiple users.

[0039] For each user 145, the client of the application running part can present an interactive window 142 of the target application 120 or the digital assistant 122 in the client interface, such as a conversation window with the digital assistant 122. The user 145 can enter a conversation message in the conversation window, and the target application 120 can determine the reply message of the digital assistant 122 based on the created configuration information and present it to the user in the interactive window 142. In some embodiments, depending on the configuration of the target application 120, the interactive message with the target application 120 may include a message in a multimodal form, such as a text message (e.g., a natural language text), a voice message, an image message, a video message, and the like.

[0040] Similar to the application creation part, the application running part can be deployed locally on the terminal device of each user 145, and / or can be supported by a server-side device. For example, the terminal device of user 145 can run a client with an application running part, which can support the interaction between the user and the application running part provided by the server. In the case where the application running part runs locally on the user's terminal device, the user 145 can directly interact with the local application running part using the terminal device. In the case where the application running part runs on the server-side device, the server-side device can realize the service supply to the client running in the terminal device based on the communication connection with the terminal device. The application running part can present the corresponding application page to the user 145 based on the operation of the user 145, so as to output and / or receive information related to the use of the application to the user 145.

[0041] In some embodiments, the implementation of at least part of the functions of the target application 120 and / or the implementation of at least part of the functions of the digital assistant 122 in the target application 120 can be implemented based on the model. During the creation or operation of the target application 120, one or more models 155, such as the capabilities of the model 155, can be called. In the target application 120, the digital assistant 122 can use the model 155 to understand the user input and provide a reply to the user based on the output of the model 155.

[0042] During the creation process, the application management platform 110 needs to use the model 155 to determine whether the operation result of the target application 120 meets expectations when testing the target application 120. During the operation process, in response to different operation requests of the user of the target application 120, the application operation part may need to use the model 155 to determine the response result to the user.

[0043] Although shown as being independent of the application management platform 110, one or more models 155 may run on the application management platform 110, or other remote servers. In some embodiments, the model 155 may be a machine learning model, a deep learning model, a learning model, a neural network, etc. In some embodiments, the model may be based on a language model (LM). The language model can have question-answering capabilities by learning from a large amount of corpus. The model 155 may also be based on other appropriate models.

[0044] The application management platform 110 can run on appropriate electronic devices. The electronic devices here can be any 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 include, for example, a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like. In some embodiments, the management platform 110 can be implemented based on cloud services.

[0045] It should be understood that the structure and functionality of environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure. Figure 1 A single user interacting with the application creation portion and a single user interacting with the application running portion are shown, but in reality multiple users can access the application management platform 110 to each create a digital assistant, and each digital assistant can be used to interact with multiple users.

[0046] When a user initiates a query within an application, the application can provide answering services based on a knowledge base. The knowledge base stores data related to the query. In some cases, it may be necessary to use structured data (e.g., data tables, data objects) as knowledge to provide question-and-answer services. In some cases, it may be necessary to use unstructured data (e.g., documents, web pages, etc.) as knowledge to provide question-and-answer services. Therefore, these structured data and / or unstructured data can be stored in a knowledge base. These data may include links that reference other content (e.g., documents). The content in these links is usually valuable. If the content in these links is stored in the knowledge base, it is beneficial to improve the instructions for question-and-answer services.

[0047] To this end, a data processing scheme is provided according to an embodiment of the present disclosure. According to various embodiments of the present disclosure, a selection of a target portion in a data object is received, and the target portion has reference content. Based on the target portion in the data object and at least a portion of the reference content, a target vectorized representation corresponding to the target portion is generated. The target vectorized representation is stored in a knowledge base, and is used to use at least one of the following as a result of the query in a query for the data object: at least a portion of the target portion, at least a portion of the reference content.

[0048] In various embodiments of the present disclosure, when the application creation user generates a vectorized representation of the target part in the data object, the vectorized representation of the reference content of this part can be generated at the same time and stored in the knowledge base. In this way, the application creation user can store the vectorized representation of the reference content in the knowledge base in batches, and efficiently expand the knowledge reserve in the knowledge base. As a result, the quality of the query results provided to the end user can be advantageously improved.

[0049] Some example embodiments of the present disclosure will be described in detail below with reference to the examples of the accompanying drawings. It should be understood that the pages shown in the accompanying drawings are only examples, and various page designs may actually exist. The various graphical elements in the 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 exist. The embodiments of the present disclosure are not limited in this respect.

[0050] The following further describes an exemplary embodiment of the present disclosure with reference to the accompanying drawings. In the following examples, for the sake of discussion, the description is made from the perspective of an application management platform, for example Figure 1 The application management platform 110 is shown. The page presented by the application management platform 110 can be presented via the terminal device of the user 105, and the user input can be received via the terminal device of the user 105.

[0051] Figure 2 FIG. 2 shows a schematic diagram of transferring data to a knowledge base according to some embodiments of the present disclosure. Figure 2 As shown, a question-and-answer function 210 may be deployed on the application management platform 110, and the question-and-answer function 210 recalls the query results that match the query of the terminal user based on the vectorized representation of the data. The data management platform 220 may be a part of the application management platform 110, or may be independent of the application management platform 110. In the data management platform 220, a data table 222 and a structured data object 224 (which is structured data) and unstructured data 228 (for example, documents, web pages, etc.) are maintained. Therefore, it is necessary to vectorize the data table 222, the structured data object 224, and the unstructured data 228. Afterwards, the vectorized representations corresponding to the data table 222, the data object 224, and the unstructured data 228 are stored in the knowledge base 226. The question-and-answer function 210 returns the query results to the terminal user by calling the knowledge base 226 storing the vectorized representation. The data objects described in the present disclosure may include the data table 222, the data object 224, and the unstructured data 228.

[0052] The application management platform 110 receives a selection of a target portion in a data object, the target portion having reference content. The data object here may be Figure 2The data table 222 shown in FIG. 222 may be Figure 2 The structured data object 224 shown in the figure may also be unstructured data 228 (such as various documents). The following mainly describes the data table as an example. However, it should be understood that the embodiment described with reference to the data table can be applied to other types of data, such as unstructured data.

[0053] In some embodiments, the target portion includes the entirety of the data object, or partial data in the data object. For example, when the data object is a data table, the target portion may be all fields in the data table, or partial fields. When the data object is another type of file, the target portion may be the entirety of the file, or partial chapters, paragraphs, etc. of the file.

[0054] The application management platform 110 may generate a target vectorized representation corresponding to the target portion based on the target portion in the data object and at least a portion of the referenced content.

[0055] In some embodiments, the data object includes a data table, and the application management platform 110 presents fields in the data table and receives a selection of at least one field in the data table in response to the data table being selected for vector generation. Figure 3 1 shows an example of a page 300 for selecting fields in a data table according to some embodiments of the present disclosure. The page 300 may be presented on the device of the user 105. Figure 3 As shown, the page 300 includes at least a data table selection area 310, a field selection area 320, and a selected field area 330. For example, after the user 105 selects the product information table for vector generation in the data table selection area 310, various fields in the product information table may be presented in the field selection area 310. The user 105 may trigger selection controls 322, 324, and 326 to add the fields corresponding to these selection controls to the selected field area 330.

[0056] In some embodiments, the application management platform 110 can determine the target data entry in the data table based on the selected fields. For example, the selected fields in the commodity information data table are the commodity name and the commodity evaluation, and the field value of the commodity evaluation field has reference content, then the target data entry includes the field value of the commodity name field, the field value of the commodity evaluation field, and the field value of the commodity evaluation field indicates the reference content. The reference content here can include documents of a preset type, knowledge records in other knowledge bases, etc.

[0057] In some embodiments, if a selection of a target portion in the data object is received, the application management platform 110 may present an extended prompt for the target portion to indicate that the target portion has referenced content. If an extended confirmation of at least a portion of the referenced content is subsequently received, the application management platform 110 may generate a target vectorized representation corresponding to the target portion based on the target portion and at least a portion of the referenced content. The target portion of the data object may have multiple referenced contents (e.g., multiple reference links), and the user 105 may select some of the referenced contents to generate a target vectorized representation corresponding to the target portion.

[0058] In some embodiments, in response to at least one field in the data table being selected, the application management platform 110 presents an extended prompt for one or more fields in the at least one field to prompt that the field values ​​of the one or more fields indicate reference content. Figure 3 In the selected field area 330, an extended prompt for one or more of the selected fields is also presented. For example, the product description field corresponds to an extended prompt control 340, and the product-specific knowledge space ID field corresponds to an extended prompt control 342, which prompts that the field value of the product description field and the field value of the product-specific knowledge space ID field indicate the reference content.

[0059] After determining the target data entry, the application management platform 110 may generate a target vectorized representation of the target data entry based on a field value of at least one field in the target data entry and at least a portion of the referenced content.

[0060] In some embodiments, if confirmation of the extension prompt for a first field in the one or more fields is received, the application management platform 110 generates the target vectorized representation based on the field value of at least one field and the reference content indicated by the field value of the first field. Figure 3 If the user 105 triggers the confirmation control 350 , the application management platform 110 may generate a target vectorized representation.

[0061] In some embodiments, if a second field in the at least one field is selected, the application management platform 110 provides options for one or more reference content types based on the field type of the second field. If a selection of one or more reference content types is received, the application management platform 110 determines the reference content indicated by the field value of the second field in the target data entry according to the selected reference content type.

[0062] For example, refer to Figure 3 , the user 105 triggers the extended prompt control 340 to pop up a page for selecting the reference content type of the product description field, such as Figure 4 shown. Figure 4 An example of a page 400 for selecting a reference content type for a text field according to some embodiments of the present disclosure is shown. In page 400, the reference content type of the product description field is a document type, and the user 105 can trigger a selection control 410 to select a cloud document as the reference content indicated by the field value of the product description field. For another example, Figure 3 , the user 105 triggers the extended prompt control 342 to pop up a page for selecting the reference content type of the commodity-specific knowledge space ID field, such as Figure 5 shown. Figure 5 An example of page 500 for selecting the reference content type for a numerical field according to some embodiments of the present disclosure is shown. In page 500, the reference content type of the commodity-specific knowledge space ID field is knowledge base A or knowledge base B, and the user 105 can trigger the selection control 510 or 512 to select the reference content indicated by the field value of the commodity-specific knowledge space ID field of knowledge base A or knowledge base B. The user 105 can also trigger the selection control 514 to choose not to reference other content. In this way, the application creation user can flexibly select the reference content indicated by the field value, so that the knowledge base learns different types of reference content based on the user's selection.

[0063] In some embodiments, the application management platform 110 provides options for one or more document types in response to the field type of the second field being a text type. For example, the field value of the product description field is text, so the type of the field is a text type. Figure 4 For text type fields, the application management platform 110 provides a document type option.

[0064] In some embodiments, the application management platform 110 provides options for one or more knowledge types in response to the field type of the second field being a numeric type. For example, the field value of the commodity-specific knowledge space ID is a numeric value, so the type of the field is a numeric type. Figure 5 For fields of numeric type, the application management platform 110 applies options of knowledge base A type and options of knowledge base B type.

[0065] After generating the target vectorized representation, the application management platform 110 can store the target vectorized representation in a knowledge base (e.g., knowledge base 226) for use in queries against the knowledge base as the result of the query: at least a portion of the target data entry, at least a portion of the referenced content. Vectorizing the referenced content in the field value and storing it in the knowledge base can be considered extended learning. When a query initiated by user 145 is received, information representing the referenced content is also provided to the machine learning model so that the machine learning model can better understand the user's intent and provide a more accurate answer.

[0066] When receiving a query initiated by user 145 for the knowledge base, application management platform 110 may return at least a portion of the target data entry as a query result to user 145. Since user 145 may not have access rights to the referenced content, application management platform 110 may return at least a portion of the referenced content (e.g., referenced content to which user 145 has access rights) to user 145 as a query result. Figure 6 An example of a page 600 showing the results of a query according to some embodiments of the present disclosure is shown. The page 600 includes at least a query area 610 and an answer area 620. The answer area 620 includes a text area 621 and a reference area 622, the text area 621 presents at least a portion of the target data entry and at least a portion of the reference content, and the reference area 622 presents the source of the reference content.

[0067] In some embodiments, the data table includes multiple data entries under at least one field. If at least one field is selected, the vectorized representations corresponding to the multiple data entries are stored in the knowledge base. The fields in the data table can be understood as columns in the data table, and the data entries in the data table can be understood as rows in the data table. For example, the commodity information data table can include information about commodity A, commodity B, and commodity C, then the commodity information data table includes 3 data entries under at least one field (i.e., data entries for commodity A, data entries for commodity B, and data entries for commodity C). For example, if the commodity name field and the commodity description field are selected, the vectorized representation corresponding to the data entry of commodity A (i.e., the field value of the commodity name field of commodity A, the field value of the commodity description field of commodity A, and the reference content) is stored in the knowledge base. Similarly, the vectorized representations corresponding to the data entries of commodity B and the data entries of commodity C are also stored in the knowledge base.

[0068] In some embodiments, the application management platform 110 may present the learning status of the reference content of each field in the data table. Figure 7 An example of page 700 showing the learning status of the reference content of each field in the data table by the knowledge base according to some embodiments of the present disclosure is shown. In page 700, some fields have completed learning, some fields are being learned, and some fields have failed to learn. Based on this, the application creation user can grasp the overall learning status of the knowledge base.

[0069] After storing the target vectorized representation in the knowledge base, the application management platform 110 can receive a query from the user 145 for the data object, and determine a target vectorized representation matching the query from the knowledge base, the target vectorized representation being generated based on the target portion in the data object and at least a portion of the referenced content of the target portion. Then, the application management platform 110 can determine the result of the query based on the target vectorized representation. The result of the query indicates at least one of the following: at least a portion of the target portion, at least a portion of the referenced content.

[0070] In some embodiments, a machine learning model (e.g., model 155) may be used to determine a target vectorized representation from a knowledge base. For example, the application management platform 110 may provide first information indicating at least a portion of a data object to the machine learning model based on a query for the data object, and obtain second information indicating the target vectorized representation from the machine learning model. The machine learning model may determine a vectorized representation associated with the query from the knowledge base.

[0071] In some embodiments, the result of the query indicates at least a portion of the referenced content, and the application management platform 110 may also present a message corresponding to the result of the query, the message including access information corresponding to the at least a portion of the referenced content. In the case where the result of the query indicates at least a portion of the referenced content, the information corresponding to the result of the query presented by the application management platform 110 may include access information (e.g., a link) corresponding to at least a portion of the referenced content.

[0072] In some embodiments, the target portion includes the entirety of the data object, or partial data in the data object. For example, when the data object is a file of another type, the target portion may be the entirety of the file, or may be a partial chapter of the file.

[0073] In some embodiments, the data object includes a data table, and the target portion includes at least one selected field in the data table. For example, when the data object is a data table, the target portion may be all fields in the data table, or may be at least one selected field.

[0074] In some embodiments, the data table includes multiple data entries under at least one field, and if at least one field is selected, the vectorized representations corresponding to the multiple data entries are stored in the knowledge base. The fields in the data table can be understood as the columns in the data table, and the data entries in the data table can be understood as the rows in the data table. For example, the commodity information data table can include information about commodity A, commodity B, and commodity C, then the commodity information data table includes 3 data entries under at least one field (i.e., the data entry of commodity A, the data entry of commodity B, and the data entry of commodity C). For example, if the commodity name field and the commodity description field are selected, the vectorized representation corresponding to the data entry of commodity A (i.e., the field value of the commodity name field of commodity A, the field value of the commodity description field of commodity A, and the reference content) is stored in the knowledge base. Similarly, the vectorized representations corresponding to the data entry of commodity B and the data entry of commodity C are also stored in the knowledge base.

[0075] Fig. 8A FIG. 8 is a flowchart of a process 800 of data processing according to some embodiments of the present disclosure. The process 800 may be implemented at the application management platform 110. Fig. 8A Process 800 is described.

[0076] At block 810 , the application management platform 110 receives a selection of a target portion in a data object, the target portion having reference content.

[0077] In block 820 , the application management platform 110 generates a target vectorized representation corresponding to the target portion based on the target portion in the data object and at least a portion of the referenced content.

[0078] In block 830 , the application management platform 110 stores the target vectorized representation in the knowledge base for use in a query on the data object as a result of the query by using at least one of the following: at least a portion of the target portion, at least a portion of the referenced content.

[0079] In some embodiments, the target portion includes the entirety of the data object, or a portion of the data in the data object.

[0080] In some embodiments, generating a target vectorized representation includes: in response to receiving a selection of a target portion in a data object, presenting an extended prompt for the target portion to indicate that the target portion has referenced content; and in response to receiving an extended confirmation of at least a portion of the referenced content, generating a target vectorized representation corresponding to the target portion based on the target portion and at least a portion of the referenced content.

[0081] In some embodiments, the data object includes a data table, and receiving a selection of a target portion in the data object includes: in response to the data table being selected for vector generation, presenting fields in the data table; and receiving a selection of at least one field in the data table.

[0082] In some embodiments, process 800 further includes: in response to at least one field in the data table being selected, presenting an extended prompt for one or more fields in the at least one field to prompt that field values ​​of the one or more fields indicate reference content.

[0083] In some embodiments, generating a target vectorized representation includes: in response to receiving confirmation of an extension hint for a first field among one or more fields, generating a target vectorized representation based on a field value of at least one field and reference content indicated by the field value of the first field.

[0084] In some embodiments, process 800 also includes: in response to a second field in at least one field being selected, providing options for one or more reference content types based on the field type of the second field; receiving a selection of one or more reference content types; and determining the reference content indicated by the field value of the second field in the target data entry based on the selected reference content type.

[0085] In some embodiments, providing options for one or more reference content types includes at least one of the following: in response to the field type of the second field being a text type, providing options for one or more document types; and in response to the field type of the second field being a numeric type, providing options for one or more knowledge types.

[0086] In some embodiments, the data table includes a plurality of data entries under at least one field, and in response to at least one field being selected, vectorized representations corresponding to the plurality of data entries are stored in the knowledge base.

[0087] Figure 8B FIG. 8 is a flowchart showing another process 850 of data processing according to some embodiments of the present disclosure. The process 850 may be implemented at the application management platform 110. Figure 8B Process 850 is described.

[0088] At block 860 , the application management platform 110 receives a query for a data object.

[0089] In block 870 , the application management platform 110 determines a target vectorized representation matching the query from the knowledge base, wherein the target vectorized representation is generated based on a target portion in the data object and at least a portion of a reference content of the target portion.

[0090] In block 880 , the application management platform 110 determines a result of the query based on the target vectorized representation, the result of the query indicating at least one of the following: at least a portion of the target portion, at least a portion of the referenced content.

[0091] In some embodiments, the result of the query indicates at least a portion of the reference content, and process 850 further includes: presenting a message corresponding to the result of the query, the message including access information corresponding to at least a portion of the reference content.

[0092] In some embodiments, the target portion includes the entirety of the data object, or a portion of the data in the data object.

[0093] In some embodiments, the data object includes a data table, and the target portion includes at least one selected field in the data table.

[0094] In some embodiments, the data table includes a plurality of data entries under at least one field, and in response to at least one field being selected, vectorized representations corresponding to the plurality of data entries are stored in the knowledge base.

[0095] In some embodiments, determining a target vectorized representation that matches the query from a knowledge base includes: providing first information indicating at least a portion of a data object to a machine learning model based on the query; and obtaining second information indicating the target vectorized representation from the machine learning model.

[0096] Fig. 9A A schematic structural block diagram of a data processing apparatus 900 according to some embodiments of the present disclosure is shown. The apparatus 900 may be implemented in or included in the application management platform 110, for example. Each module / component in the apparatus 900 may be implemented by hardware, software, firmware, or any combination thereof.

[0097] As shown in the figure, the apparatus 900 includes a selection receiving module 910 configured to receive a selection of a target portion in a data object, where the target portion has reference content.

[0098] The apparatus 900 further includes a target vectorized representation generating module 920 configured to generate a target vectorized representation corresponding to the target portion based on the target portion in the data object and at least a portion of the referenced content.

[0099] The device 900 also includes a target vectorized representation storage module 930, which is configured to store the target vectorized representation in a knowledge base, for using at least one of the following as a query result in a query against a data object: at least a portion of the target part, at least a portion of the referenced content.

[0100] In some embodiments, the target portion includes the entirety of the data object, or a portion of the data in the data object.

[0101] In some embodiments, the target vectorized representation generation module 920 includes an extended confirmation receiving module, which is configured to, in response to receiving a selection of a target portion in a data object, present an extended prompt for the target portion to indicate that the target portion has referenced content; and in response to receiving an extended confirmation of at least a portion of the referenced content, generate a target vectorized representation corresponding to the target portion based on the target portion and at least a portion of the referenced content.

[0102] In some embodiments, the data object includes a data table, and the selection receiving module 910 includes a field presenting module configured to present fields in the data table in response to the data table being selected for vector generation; and receive a selection of at least one field in the data table.

[0103] In some embodiments, the device 900 also includes an extended prompt presentation module, which is configured to present an extended prompt for one or more fields in at least one field in response to at least one field in the data table being selected, so as to prompt that the field values ​​of one or more fields indicate reference content.

[0104] In some embodiments, the target vectorized representation generation module 920 is further configured to generate a target vectorized representation based on a field value of at least one field and a reference content indicated by the field value of the first field in response to receiving confirmation of an extension hint for a first field among the one or more fields.

[0105] In some embodiments, the device 900 also includes a reference content determination module, which is configured to provide options for one or more reference content types based on the field type of the second field in response to a second field in at least one field being selected; receive a selection of one or more reference content types; and determine the reference content indicated by the field value of the second field in the target data entry based on the selected reference content type.

[0106] In some embodiments, the reference content determination module is further configured to perform at least one of the following: in response to the field type of the second field being a text type, providing options for one or more document types; and in response to the field type of the second field being a numerical type, providing options for one or more knowledge types.

[0107] In some embodiments, the data table includes a plurality of data entries under at least one field, and in response to at least one field being selected, vectorized representations corresponding to the plurality of data entries are stored in the knowledge base.

[0108] Fig. 9BThe schematic structural block diagram of the data processing device 950 according to some embodiments of the present disclosure is shown. The device 950 may be implemented in or included in the application management platform 110. Each module / component in the device 950 may be implemented by hardware, software, firmware or any combination thereof.

[0109] As shown in the figure, the apparatus 950 includes a query receiving module 960 configured to receive a query for a data object.

[0110] The device 950 also includes a target vectorized representation determination module 970, which is configured to determine a target vectorized representation matching the query from the knowledge base, wherein the target vectorized representation is generated based on a target portion in the data object and at least a portion of the reference content of the target portion.

[0111] The device 950 also includes a query result determination module 980, which is configured to determine a query result based on the target vectorized representation, and the query result indicates at least one of the following: at least a part of the target part, at least a part of the referenced content.

[0112] In some embodiments, the query result indicates at least a portion of the referenced content, and device 950 further includes a query result presentation module configured to present a message corresponding to the query result, the message including access information corresponding to at least a portion of the referenced content.

[0113] In some embodiments, the target portion includes the entirety of the data object, or a portion of the data in the data object.

[0114] In some embodiments, the data object includes a data table, and the target portion includes at least one selected field in the data table.

[0115] In some embodiments, the data table includes a plurality of data entries under at least one field, and in response to at least one field being selected, vectorized representations corresponding to the plurality of data entries are stored in the knowledge base.

[0116] In some embodiments, the target vectorized representation determination module 970 is also configured to provide first information indicating at least a portion of the data object to the machine learning model based on the query; and obtain second information indicating the target vectorized representation from the machine learning model.

[0117] Fig.10 1 shows a block diagram of an electronic device 1000 in which one or more embodiments of the present disclosure may be implemented. It should be understood that Fig.10 The electronic device 1000 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Fig.10 The electronic device 1000 shown may include or be implemented as Figure 1 Application management platform 110, Fig. 9A Device 900 or Fig. 9B Device 950.

[0118] like Fig.10 As shown, the electronic device 1000 is in the form of a general electronic device. The components of the electronic device 1000 may include, but are not limited to, one or more processors or processing units 1010, a memory 1020, a storage device 1030, one or more communication units 1040, one or more input devices 1050, and one or more output devices 1060. The processing unit 1010 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 1020. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 1000.

[0119] The electronic device 1000 typically includes a plurality of computer storage media. Such media may be any accessible media that is accessible to the electronic device 1000, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 1020 may be a volatile memory (e.g., a register, a cache, a random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 1030 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data and may be accessed within the electronic device 1000.

[0120] The electronic device 1000 may further include additional removable / non-removable, volatile / non-volatile storage media. Fig.10 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. Memory 1020 may include a computer program product 1025 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0121] The communication unit 1040 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 1000 can be implemented in a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 1000 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0122] The input device 1050 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 1060 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 1000 may also communicate with one or more external devices (not shown) through the communication unit 1040 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 1000, or communicate with any device that allows the electronic device 1000 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).

[0123] 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.

[0124] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0125] 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, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0126] 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, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0127] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square 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 includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0128] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A method for data processing, comprising: receiving a selection of a target portion in a data object, the target portion having reference content; Based on the target portion in the data object and at least a portion of the referenced content, generate a target vectorized representation corresponding to the target portion; as well as The target vectorized representation is stored in a knowledge base, and is used to use at least one of the following as a result of the query in a query for the data object: at least a part of the target part, at least a part of the reference content. 2 . The method according to claim 1 , wherein the target portion includes the entirety of the data object, or a portion of data in the data object.

3. The method according to claim 1, wherein generating the target vectorized representation comprises: In response to receiving a selection of a target portion in the data object, presenting an expanded prompt for the target portion to prompt that the target portion has the reference content; as well as In response to receiving an extended confirmation of at least a portion of the reference content, a target vectorized representation corresponding to the target portion is generated based on the target portion and the at least a portion of the reference content.

4. The method of claim 1 , wherein the data object comprises a data table, and wherein receiving a selection of a target portion in the data object comprises: In response to the data table being selected for vector generation, presenting fields in the data table; as well as A selection of at least one field in the data table is received.

5. The method according to claim 4, further comprising: In response to the at least one field in the data table being selected, an extended prompt for the one or more fields in the at least one field is presented to prompt that field values ​​of the one or more fields indicate reference content.

6. The method of claim 5, wherein generating the target vectorized representation comprises: In response to receiving confirmation of the extension hint for a first field among the one or more fields, the target vectorized representation is generated based on a field value of the at least one field and reference content indicated by the field value of the first field.

7. The method according to claim 4, further comprising: In response to a second field of the at least one field being selected, providing options for one or more reference content types based on a field type of the second field; receiving a selection of the one or more reference content types; as well as According to the selected reference content type, the reference content indicated by the field value of the second field in the target data entry is determined.

8. The method of claim 7, wherein providing options for one or more reference content types comprises at least one of the following: In response to the field type of the second field being a text type, providing options for one or more document types; and In response to the field type of the second field being a numerical type, options for one or more knowledge types are provided.

9. The method according to claim 4, wherein the data table includes multiple data entries under the at least one field, and in response to the at least one field being selected, vectorized representations corresponding to the multiple data entries are stored in the knowledge base.

10. A method for data processing, comprising: receiving queries for data objects; Determining a target vectorized representation matching the query from a knowledge base, wherein the target vectorized representation is generated based on a target portion in the data object and at least a portion of a reference content of the target portion; as well as A result of the query is determined based on the target vectorized representation, the result of the query indicating at least one of the following: at least a portion of the target portion, at least a portion of the referenced content.

11. The method of claim 10, wherein the result of the query indicates at least a portion of the reference content, the method further comprising: A message corresponding to the result of the query is presented, wherein the message includes access information corresponding to the at least a portion of the referenced content.

12. The method according to claim 10, wherein the target portion includes the entirety of the data object, or a portion of data in the data object.

13. The method of claim 10, wherein the data object comprises a data table, and the target portion comprises at least one selected field in the data table.

14. The method according to claim 13, wherein the data table includes a plurality of data entries under the at least one field, and in response to the at least one field being selected, vectorized representations corresponding to the plurality of data entries are stored in the knowledge base.

15. The method according to claim 10, wherein determining a target vectorized representation matching the query from a knowledge base comprises: providing first information indicative of at least a portion of the data object to a machine learning model based on the query; as well as Second information indicating the target vectorized representation is obtained from the machine learning model.

16. A data processing device, comprising: A selection receiving module configured to receive a selection of a target portion in a data object, the target portion having reference content; A target vectorized representation generation module, configured to generate a target vectorized representation corresponding to the target portion based on the target portion in the data object and at least a portion of the referenced content; as well as A target vectorized representation storage module is configured to store the target vectorized representation in a knowledge base for use in a query against the data object with at least one of the following as a query result: at least a portion of the target portion, at least a portion of the referenced content.

17. A data processing device, comprising: A query receiving module, configured to receive a query for a data object; a target vectorized representation determination module, configured to determine a target vectorized representation matching the query from a knowledge base, wherein the target vectorized representation is generated based on a target portion in the data object and at least a portion of a reference content of the target portion; and A query result determination module is configured to determine a result of the query based on the target vectorized representation, wherein the result of the query indicates at least one of the following: at least a portion of the target portion, and at least a portion of the referenced content.

18. An electronic device, comprising: at least one processing unit; as well as At least one memory, the at least one memory being 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 15 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 can be executed by a processor to implement the method according to any one of claims 1 to 15.

Images