Information extraction method and device, equipment and storage medium
Automatically determine and extract structured data items in emails and other contents through the component operation platform, solving the problem of inefficiency in the existing technology, and achieving efficient information sorting and automated structured extraction. It is suitable for a variety of scenarios and improving Work efficiency.
Patent Information
- Application Number
- CN202410382444.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-29
- Publication Date
- 2024-11-22
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
It is difficult for the prior art to efficiently convert content such as emails from unstructured forms to structured data, resulting in users being inefficient and prone to errors in scenarios such as procurement applications and bill applications.
Through the component operation platform, the target content and structured data objects are determined based on user input, structured information is obtained, and data items are determined based on the content and information, and they are automatically added to the corresponding fields to realize structured extraction of information.
It improves efficient organization and automated structured extraction of information, reduces manual work, is suitable for different scenarios, improves work efficiency, and meets users' personalized needs through information extraction rules, simplifies the usage process.
Smart Images

Figure CN119003582A_ABST
Abstract
Description
Technical Field
[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, devices, apparatuses, and computer-readable storage media for information extraction. Background Art
[0002] With the rapid development of computer technology, users have always had the need to extract various contents into structured carriers. For example, with the widespread use of emails, users have long had the need to extract email contents into different data tables in a structured manner. For example, in scenarios such as purchase applications and bill applications, users need to convert text information in emails into structured data for further processing. Summary of the invention
[0003] In a first aspect of the present disclosure, a method for information extraction is provided. The method includes: determining target content and a target structured data object based on user input indicating information extraction; obtaining structured information of the target structured data object, the structured information indicating at least one field contained in the target structured data object; determining at least one data item from the target content based on the target content and the structured information, the data item corresponding to one or more fields in at least one field; and in the target structured data object, adding the at least one data item to the corresponding one or more fields respectively.
[0004] In a second aspect of the present disclosure, a device for information extraction is provided. The device includes: a determination module configured to determine target content and a target structured data object based on a user input indicating information extraction; an information acquisition module configured to acquire structured information of the target structured data object, the structured information indicating at least one field contained in the target structured data object; a data item determination module configured to determine at least one data item from the target content based on the target content and the structured information, the data item corresponding to one or more fields in at least one field; and a data item adding module configured to add at least one data item to the corresponding one or more fields in the target structured data object.
[0005] 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, 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 device executes the method of the first aspect.
[0006] 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.
[0007] It should be understood that the contents described in this content section are not intended to limit the key features or important features of the embodiments of the present disclosure, nor are they 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
[0008] 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:
[0009] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;
[0010] Figure 2 A schematic diagram showing an example architecture for information extraction according to some embodiments of the present disclosure;
[0011] FIG. 3A to FIG. 3D A schematic diagram showing an example interface for specifying target content and target structured data objects according to some embodiments of the present disclosure is shown;
[0012] Figure 4A A schematic diagram of an example interface for specifying information extraction rules according to some embodiments of the present disclosure is shown;
[0013] Figure 4B A schematic diagram showing an example architecture for information extraction according to other embodiments of the present disclosure;
[0014] Figure 4C A schematic diagram showing an example interface for displaying prompt information according to some embodiments of the present disclosure is shown;
[0015] Figure 5 A flowchart showing a process for information extraction according to some embodiments of the present disclosure is shown;
[0016] Figure 6 A schematic structural block diagram of an apparatus for information extraction according to some embodiments of the present disclosure is shown; and
[0017] Figure 7 A block diagram of a device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION
[0018] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.
[0019] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.
[0020] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.
[0021] 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 the relevant laws and regulations may also be applied to the implementation of the present disclosure.
[0022] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.
[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] It should be noted that the titles of any sections / subsections provided herein are not restrictive. Various embodiments are described throughout this article, and any type of embodiment may be included under any section / subsection. In addition, 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 different sections / subsections.
[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] 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.
[0027] 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 multiple layers of processing units. In this article, "model" may also be referred to as "machine learning model", "machine learning network" or "network", which are used interchangeably in this article. A model may also include different types of processing units or networks.
[0028] Figure 1 1 is a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. In the example environment 100 , a component execution platform 110 can support the execution of a business component 125 . A user 140 can interact with the business component 125 via a client of the component execution platform 110 .
[0029] In some embodiments, the service component 125 can be downloaded and installed on the terminal device of the user 140. In some embodiments, the service component 125 can also be accessed through other means, such as through a web page. Figure 1 In the environment 100 , in response to the business component 125 being started, the client of the component execution platform 110 may present the interface 150 of the business component 125 .
[0030] The business component 125 includes but is not limited to one or more of the following: a chat business component (also known as an instant messaging business IM component), a document business component, an audio and video conference business component, an email business component, a task business component, a calendar business component, an objective and key result (OKR) business component, etc. It can be understood that although Figure 1A single business component is shown in FIG. 1 , but in fact, multiple business components can be installed on the component operation platform 110. Multiple business components can be integrated on the component operation platform 110, and such a component operation platform 110 can be regarded as a multifunctional collaboration platform. In the case where multiple business components are installed in the component operation platform 110, these multiple business components can be integrated on one or more component operation platforms 110. In the component operation platform 110, people can start different business components as needed to complete corresponding information processing, sharing, communication, etc. The business component 125 can provide a content entity 126. The content entity 126 can be a content instance created by the user 140 or other users on the business component 125. For example, depending on the type of the business component 125, the content entity 126 can be unstructured content. For example, documents (for example, word documents, pdf documents, presentations, spreadsheet documents, etc.), emails, messages (for example, conversation messages on instant messaging business components), calendars, schedules, tasks, audio, video, images, etc. The content entity 126 can be structured content. For example, data tables, forms, etc.
[0031] In some embodiments, the component operation platform 110 may provide a digital assistant 120. The digital assistant 120 may be provided by a separate business component, or may be integrated into a business component 120 that can provide a content entity. The business component for providing a client interface for a digital assistant may correspond to a single-function business component or a multi-function collaboration platform, such as an office suite or other collaboration platform that can integrate multiple components. It is understood that similar to the business component, although Figure 1 A single digital assistant is shown in the figure, but there may actually be multiple digital assistants.
[0032] The component operation platform 110 may be deployed locally on the terminal device of each user 140, and / or may be supported by a server-side device. For example, the terminal device of the user 140 may run a client of the component operation platform 110, which may support the interaction between the user 140 and the component operation platform 110 provided by the server. In the case where the component operation platform 110 runs locally on the user's terminal device, the user 145 may directly interact with the local component operation platform 110 using the terminal device. In the case where the component operation platform 110 runs on the server-side device, the server-side device may provide services to the client running in the terminal device based on the communication connection with the terminal device. The component operation platform 110 may present a corresponding interface 150 to the user 140 based on the operation of the user 140, so as to output to the user 140 and / or receive from the user 140 information related to the use of the component.
[0033] In some embodiments, at least some of the functions of business component 125 and / or at least some of the functions of digital assistant 120 may be implemented based on target model 155. During the operation of business component 125, one or more target models 155 may be called. Target model 155 may be used to understand user input, and to provide services based on the output of target model 155, such as providing a response to the user.
[0034] Although shown as being independent of the component runtime platform 110, one or more target models 155 may be run on the component runtime platform 110, or other remote servers. In some embodiments, the target 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 target model 155 may also be based on other appropriate models.
[0035] The component operation platform 110 can be run on appropriate electronic devices. The electronic device 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 component operation platform 110 can be implemented based on cloud services.
[0036] It should be understood that the structure and functionality of environment 100 are described for exemplary purposes only and does not imply any limitation on the scope of the present disclosure.
[0037] As briefly described above, users have a need to extract various contents into structured carriers. Taking email as an example, users have long had a need to extract email contents into different carriers in a structured manner. Conventionally, users usually organize the data in emails into different carriers by manually copying and pasting. This method is inefficient and prone to errors.
[0038] In view of this, an embodiment of the present disclosure proposes an improved scheme for information extraction. According to various embodiments of the present disclosure, the component operation platform determines the target content and the target structured data object based on the user input indicating the information extraction. The structured information of the target structured data object is obtained, and the structured information indicates at least one field contained in the target structured data object. Then, the component operation platform determines at least one data item from the target content based on the target content and the structured information, and each data item corresponds to one or more fields in the target structured data object. In the target structured data object, these data items are respectively added to the corresponding one or more fields. Thereby, it can help users to organize the information in the target content into various structured carriers more efficiently. For example, organize the information in the email into tables, to-do items, structured documents, and so on.
[0039] Some example embodiments of the present disclosure will continue to be described with reference to the accompanying drawings. It should be understood that the interfaces shown in the accompanying drawings are merely examples, and various interface designs may actually exist. The various graphical elements in the interface may have different arrangements and different visual representations, one or more of which 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. In addition, hereinafter, the example embodiments will be described mainly with respect to the component runtime platform 110. It should be understood that the actions described with respect to the component runtime platform 110 may be implemented by the client and / or server of the component runtime platform 110. For example, it may be performed by an application, component, or suite (e.g., business component 125) running on a terminal device, or it may be performed by an application, component, or suite in collaboration with its server.
[0040] The following will refer to Figure 2 The scheme for information extraction according to the embodiment of the present disclosure is described. Figure 2 A schematic diagram of an example architecture 200 for information extraction according to some embodiments of the present disclosure is shown. Figure 1 Give a description.
[0041] like Figure 2 As shown, the component execution platform 110 determines the target content 212 and the target structured data object 211 according to the user input indicating the information extraction (e.g., from the user 140). The target content 212 is the content from which the information is to be extracted. The target content 212 can be any suitable type of content, which can be unstructured content (e.g., email, text document) or structured content (e.g., data table, form, etc.). In some examples, the target content 212 can include at least a part of the email, the latest email under the same subject, a text document, a certain chapter of the text, etc.
[0042] The target structured data object 211 is a carrier into which the extracted information is to be written. The target structured data object can be any suitable type of object capable of storing data in a structured manner, such as a data table, a key-value database, etc. In some examples, the target structured data object 211 can be an online data table, such as a multidimensional table managed by the component operation platform. In other examples, the target structured data object 211 can be a data table stored locally on the terminal device of the user 140 or a data table stored in other suitable devices. The following will describe in detail the component operation platform 110 determining the target content and the target structured data object in conjunction with two examples.
[0043] In some embodiments, the component operation platform 110 obtains structured information of the target structured data object. The structured information obtained by the component operation platform 110 is used to indicate at least one field included in the target structured data object. For example, the target structured data object includes three fields: "product name", "quantity", "price", etc.
[0044] exist Figure 2 In the example of , the component running platform 110 may provide the target structured data object 211 to the server 213 to obtain the structured information 214. Exemplarily, the server 213 may be a server of the component running platform 110. The component running platform 110 obtains the structured field type of the target structured data object 211, for example, the header information in a multidimensional table, through an application programming interface (API).
[0045] In some embodiments, the component operation platform 110 determines at least one data item, also referred to as a target data item, from the target content based on the target content and the structured information. Each data item corresponds to one or more fields in at least one field, that is, corresponds to one or more fields in the target structured data object 211. Continuing with the above example, the Bluetooth headset corresponds to the field "product name", 123 corresponds to the field "quantity", and 12,123 yuan corresponds to the field "price", and the Bluetooth speaker corresponds to the field "product name", 44 corresponds to the field "quantity", and 12,843 yuan corresponds to the field "price". That is, the component operation platform 110 determines information that conforms to the structure of the target structured data object 211 from the target content 212 based on the target content 212 and the structured information 214.
[0046] In some embodiments, if the target content 212 itself is structured, such as another data table, the component execution platform 110 can determine data items that conform to the structure of the target structured data object 212 based on the structured information of the target content 202 (eg, the included fields).
[0047] In some embodiments, the component operation platform 110 can determine the target data item with the aid of the target model. For example, if the target content 212 includes unstructured text content, the target model can be used to understand the text content to extract the target data item. For example, the component operation platform 110 can generate prompt information for the target model based on the target content and structured information, such as prompt words. Then, the component operation platform 110 provides the prompt information to the target model to obtain the output of the target model, and determines at least one data item based on the output of the target model.
[0048] In some examples, such as Figure 2 As shown, the component execution platform 110 generates prompt information based on the target content 212 and the structured information 214. The component execution platform 110 inputs the prompt information into the target model 155. The target model 155 may output at least one data item 215 or may output an intermediate result, and the component execution platform 110 further determines at least one data item 215 according to the output of the model. For example, the target model 155 generates key information that can match these fields by learning and understanding the structure of the fields of the target structured data object 211 and analyzing the semantics of the target content 212 (e.g., email content).
[0049] In some embodiments, the component execution platform 110 adds at least one data item to the corresponding one or more fields in the target structured data object. In some examples, the component execution platform 110 inputs at least one data item 215 to the server 213, and the server 213 writes at least one data item 215 to the corresponding one or more fields in the target structured data object 211.
[0050] For example, the component execution platform 110 writes the information obtained through the target model 155 and the prompt information into the target structured data object 211 through the API interface. In this way, it can be ensured that the structured information 214 accurately matches one or more fields included in the target structured data object 211.
[0051] The following will take an example and refer to FIG. 3A to FIG. 3D The description component operation platform 110 determines the target content and the target structured data object. The target content can be an email, a text, a data table, etc. For example, document information is extracted into a table, and table information is extracted into another table. For the convenience of discussion, the following description will be made by taking the target content type of email as an example, but this is only exemplary and the present disclosure does not limit this.
[0052] FIG. 3A to FIG. 3DA schematic diagram for specifying target content and target structured data objects according to some embodiments of the present disclosure is shown. The component execution platform 110 receives an information extraction configuration from a user. The information extraction configuration received by the component execution platform 110 is for a content collection and is used to indicate an extraction destination and a source content range in the content collection.
[0053] In some embodiments, the component execution platform 110 displays a configuration entry for information extraction in a content display interface associated with a content collection. Figure 3A As shown, the component execution platform 110 displays a configuration entry for information extraction (eg, an extract information control 310 ) on a content display interface 300A that is presented and is associated with a content collection (eg, a collection of emails) (eg, a certain email).
[0054] In some embodiments, the component execution platform 110 displays an extraction configuration interface for the content set in response to the configuration portal being triggered. Then, the component execution platform 110 receives user designation of an extraction destination and user designation of a source content range through the extraction configuration interface.
[0055] like Figure 3B As shown, the component operation platform 110 presents an extraction configuration interface 320 in response to the user 140 clicking the extraction information control 310. The component operation platform 110 receives the specified source content range and the specified extraction destination input by the user 140. In some examples, the specified source content range input by the user 140 may be one or more chapters or pages of the latest email, document or text under the same topic. For example, the user 140 selects "latest email under this topic" for selecting the content of the email to be extracted.
[0056] In some examples, the extraction destination specified by the user 140 may be a target structured data object or a document directory. If the extraction destination input by the user 140 is a document directory, the target structured data object may be a data table under the directory. Figure 2 In the example of FIG. 1 , the user 140 selects to extract to the “XXX table” for the extraction destination. The user 140 clicks the “OK” control 321 , and the operating platform 110 receives the configuration information input by the user 140 .
[0057] In some embodiments, the component execution platform 110 determines the target structured data object according to the extraction destination. For example, based on the user 140 selecting to extract "XXX table", the "XXX table" is determined as the target structured data object. For another example, if the user 140 selects a certain document directory, the target structured data object may be each data table under the document directory.
[0058] In some embodiments, the component execution platform 110 determines the target content from the content set according to the source content range. For example, based on the user 140 selecting "latest email under this topic", the content of the latest email received under this topic each time is determined as the target content.
[0059] In some embodiments, the component execution platform 110 displays at least one data item and one or more fields corresponding to each data item. If the component execution platform 110 receives a positive indication of at least one data item, the at least one data item is added to the corresponding one or more fields.
[0060] like Figure 3C As shown, the component operation platform 110 displays the extracted information in the interface 300C. For example, the data items corresponding to the fields "Product Name", "Quantity", and "Price" are extracted: "Product Name is Product A, the quantity is 123, and the price is XX yuan", "Product Name is Product B, the quantity is 456, and the price is XXX yuan". If the user 140 clicks the "OK" control 331, the component operation platform 110 adds the extracted data items to the corresponding fields respectively.
[0061] After adding the data items to the corresponding fields, the component execution platform 110 presents an "extracted to XXX table" control 340 on the interface 300D. The user 140 can click the "extracted to XXX table" control to view the target structured data object (e.g., XXX table) updated by the component execution platform 110.
[0062] In the above example, the target content and the target structured data object are specified by the user. In some embodiments, the target content and / or the target structured data object may not be specified by the user. For example, the user 140 may pre-specify or set information extraction rules for determining the target content and / or the target structured data object.
[0063] The following will take another example and refer to FIG. 4A to FIG. 4C The description component operation platform 110 determines the target content and the target structured data object. For the convenience of discussion, the target content will be described as an email as an example, but this is only exemplary and the present disclosure does not limit this.
[0064] In some embodiments, the component execution platform 110 receives information extraction rules for predetermined types of content (eg, emails) from a user. For example, the component execution platform 110 receives a custom rule for email content from a user 140, and the custom rule is used to automatically trigger the information extraction process.
[0065] In some embodiments, the information extraction rule indicates the information extraction condition and extraction destination for the predetermined type of content. The component execution platform 110 determines the candidate content that meets the information extraction condition as the target content. Accordingly, the component execution platform 110 determines the extraction destination as the target structured data object.
[0066] The following is for easy understanding. Figure 4A Describes the rules for extracting information received by the component runtime platform. Figure 4A A schematic diagram of an example interface for specifying or setting information extraction rules according to some embodiments of the present disclosure is shown.
[0067] like Figure 4A As shown, the component operation platform 110 can present an information extraction rule setting interface 400A on the terminal device of the user 140, so that the user 140 can set the information extraction rule. The information extraction rule includes an extraction condition 410 and an extraction destination 412.
[0068] In some embodiments, the information extraction conditions may include conditions for entities related to the predetermined type of content. For example, "the email contains a certain sender", "the email contains the creator of a certain document", etc. The information extraction conditions may also include conditions for semantics related to the predetermined type of content. For example, "the email contains the subject of a certain document", "the type of the email is a certain type", etc.
[0069] In some examples, user 140 sets extraction condition 410 and extraction destination 412 in interface 400A. For example, user 140 sets extraction condition as "emails containing a certain sender and the content is of type X". User 140 sets extraction destination 412 in interface 400A. At this time, if user 140 clicks "save rule" control 413, component operation platform 110 saves the information extraction rule set by user 140 and automatically triggers the information extraction process based on the rule. It should be understood that this is only exemplary, and user 140 can also set or specify target content.
[0070] In some examples, if the component execution platform 110 determines that the candidate content (e.g., the content of the latest email) meets the extraction conditions 410 set by the user 140, the candidate content can be determined as the target content for extracting information from it to the extraction destination 412 (e.g., "XXX table").
[0071] Figure 4B FIG. 4 is a schematic diagram of an example architecture 400B for information extraction according to other embodiments of the present disclosure. Figure 4BAs shown, the component execution platform 110 determines the content that meets the information extraction rule 421 as the target content from the candidate content 420 based on the information extraction rule 421 (for example, a custom rule) set by the user 140 .
[0072] In some examples, if the information extraction rule 421 involves a user-defined fixed rule (eg, the email content contains a certain sender) 422 , the component execution platform 110 determines whether the content is the target content based on the information extraction rule 421 .
[0073] In some examples, if the information extraction rule 421 involves a user-defined broad condition 423 (e.g., a rule requiring understanding of the content), the component execution platform 110 can use the target model 155 to perform semantic recognition on the candidate content, and then determine whether the candidate content is the target content. For example, if the information extraction rule 421 includes "the content of the email is about the type of customer complaint", the email content needs to be understood.
[0074] If the component execution platform 110 determines that the candidate content 420 satisfies the information extraction rule 421, the information extraction process may be automatically triggered, for example, referring to Figure 2 The process described. That is, the component operation platform 110 obtains the structured information of the target structured data object. Based on the target content and the structured information, the component operation platform 110 determines at least one data item from the target content, each data item corresponding to one or more fields in the at least one field. Then, the component operation platform 110 adds the at least one data item to the corresponding one or more fields in the target structured data object.
[0075] In some embodiments, the component execution platform 110 displays prompt information for extracting information from the target content to the target structured data object in the interaction interface between the user and the digital assistant. Figure 4C A schematic diagram 400C is shown for displaying prompt information for extracting target content into a target structured data object according to some embodiments of the present disclosure.
[0076] like Figure 4C As shown, the component operation platform 110 displays a prompt message 432 for extracting information from the target content to the target structured data object in the interactive interface 431 between the user 140 and the digital assistant 120. For example, the component operation platform 110 displays a prompt message from the digital assistant 120: "Hello, you just received an "XXX" email, and I have helped you extract the "XXX" information into the "XXX" data table."
[0077] In summary, through the embodiments of the present disclosure, content (e.g., email content) can be efficiently and automatically extracted into different data tables, reducing manual work. Furthermore, automated structured extraction suitable for different scenarios improves work efficiency. Through information extraction rules, a conditional trigger mechanism is implemented to meet the user's personalized needs for automatic extraction and simplify the user's use process.
[0078] Example procedures, devices and equipment
[0079] Figure 5 A flowchart of a process 500 for information extraction according to some embodiments of the present disclosure is shown. The process 500 may be implemented at the component execution platform 110, for example, by a server of the business component 125, or by a terminal device of the business component 125, or by a server and a terminal device in coordination. Figure 1 Process 500 is described.
[0080] At block 510 , the component execution platform 110 determines target content and target structured data objects based on user input indicating information extraction.
[0081] In block 520 , the component execution platform 110 obtains structured information of the target structured data object, where the structured information indicates at least one field included in the target structured data object.
[0082] In block 530 , the component execution platform 110 determines at least one data item from the target content based on the target content and the structured information. Each data item corresponds to one or more fields of the at least one field.
[0083] In block 540 , the component execution platform 110 adds at least one data item to the corresponding one or more fields in the target structured data object.
[0084] In some embodiments, determining the target content and the target structured data object includes: receiving an information extraction configuration for a content collection from a user, the information extraction configuration indicating an extraction destination and a range of source content in the content collection; determining the target structured data object based on the extraction destination; and determining the target content from the content collection based on the source content range.
[0085] In some embodiments, receiving an extraction information configuration for a content collection includes: displaying a configuration entry for information extraction in a content display interface associated with the content collection; in response to the configuration entry being triggered, displaying an extraction configuration interface for the content collection; and receiving user specification of multiple extraction destinations and user specification of a source content range via the extraction configuration interface.
[0086] In some embodiments, adding at least one data item to the corresponding one or more fields includes: displaying at least one data item and one or more fields corresponding to each data item; and in response to receiving a positive indication of at least one data item, adding at least one data item to the corresponding one or more fields.
[0087] In some embodiments, determining the target content and the target structured data object includes: receiving an information extraction rule for a predetermined type of content from a user, the information extraction rule indicating information extraction conditions and an extraction destination for the predetermined type of content; determining candidate content that meets the information extraction conditions as the target content; and determining the target structured data object based on the extraction destination.
[0088] In some embodiments, the information extraction condition includes at least one of the following: a condition on an entity related to a predetermined type of content, or a condition on the semantics of the predetermined type of content.
[0089] In some embodiments, process 500 further includes: displaying prompt information for extracting information from the target content to the target structured data object in the interaction interface between the user and the digital assistant.
[0090] In some embodiments, determining at least one data item from the target content includes: generating prompt information for a target model based on the target content and structured information; providing the prompt information to the target model to obtain an output of the target model; and determining at least one data item based on the output of the target model.
[0091] In some embodiments, the target content includes at least a portion of an email.
[0092] Figure 6 A schematic structural block diagram of an apparatus 600 for information extraction according to some embodiments of the present disclosure is shown. The apparatus 600 may be implemented as or included in the component execution platform 110. Each module / component in the apparatus 600 may be implemented by hardware, software, firmware or any combination thereof.
[0093] As shown in the figure, the device 600 includes a determination module 610, which is configured to determine the target content and the target structured data object based on the user input indicating the information extraction. The device 600 also includes an information acquisition module 620, which is configured to obtain the structured information of the target structured data object, and the structured information indicates at least one field contained in the target structured data object. The device 600 also includes a data item determination module 630, which is configured to determine at least one data item from the target content based on the target content and the structured information, and the data item corresponds to one or more fields in at least one field. The device 600 also includes a data item addition module 640, which is configured to add at least one data item to the corresponding one or more fields in the target structured data object.
[0094] In some embodiments, the determination module 610 is also configured to receive an information extraction configuration for a content collection from a user, the information extraction configuration indicating an extraction destination and a range of source content in the content collection; determine a target structured data object based on the extraction destination; and determine the target content from the content collection based on the source content range.
[0095] In some embodiments, the determination module 610 also includes an information receiving module, which is configured to display a configuration entry for information extraction in a content display interface associated with a content collection; in response to the configuration entry being triggered, display an extraction configuration interface for the content collection; and receive user specification of multiple extraction destinations and user specification of source content range via the extraction configuration interface.
[0096] In some embodiments, the data item adding module 640 is further configured to display at least one data item and one or more fields corresponding to each data item; and in response to receiving a positive indication of at least one data item, add at least one data item to the corresponding one or more fields.
[0097] In some embodiments, the determination module 610 is also configured to receive information extraction rules for a predetermined type of content from a user, the information extraction rules indicating information extraction conditions and extraction destinations for the predetermined type of content; determine candidate content that meets the information extraction conditions as target content; and determine a target structured data object based on the extraction destination.
[0098] In some embodiments, the information extraction condition includes at least one of the following: a condition on an entity related to a predetermined type of content, or a condition on the semantics of the predetermined type of content.
[0099] In some embodiments, the device 600 also includes a prompt information display module, which is configured to display prompt information for extracting information from the target content to the target structured data object in the interaction interface between the user and the digital assistant.
[0100] In some embodiments, the data item determination module 630 is further configured to generate prompt information for a target model based on the target content and structured information; provide the prompt information to the target model to obtain an output of the target model; and determine at least one data item based on the output of the target model.
[0101] In some embodiments, the target content includes at least a portion of an email.
[0102] Figure 7 A block diagram of an electronic device 700 is shown in which one or more embodiments of the present disclosure may be implemented. It should be understood that Figure 7 The electronic device 700 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Figure 7 The electronic device 700 shown can be used to implement Figure 1 An electronic device 110.
[0103] like Figure 7 As shown, the electronic device 700 is in the form of a general electronic device. The components of the electronic device 700 may include, but are not limited to, one or more processors or processing units 710, a memory 720, a storage device 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. The processing unit 710 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 720. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 700.
[0104] The electronic device 700 typically includes a plurality of computer storage media. Such media may be any accessible media that is accessible to the electronic device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 720 may be a volatile memory (e.g., registers, caches, 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 730 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 700.
[0105] The electronic device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 7As 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. The memory 720 may include a computer program product 725 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.
[0106] The communication unit 740 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 700 can be implemented with a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 700 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.
[0107] The input device 750 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 760 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 700 may also communicate with one or more external devices (not shown) through the communication unit 740 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 700, or communicate with any device that allows the electronic device 700 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).
[0108] 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.
[0109] 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.
[0110] 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.
[0111] 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.
[0112] 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.
[0113] 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. An information extraction method, include: determining target content and target structured data objects based on user input indicating information extraction; Acquire structured information of the target structured data object, where the structured information indicates at least one field included in the target structured data object; Based on the target content and the structured information, determining at least one data item from the target content, the data item corresponding to one or more fields of the at least one field; as well as In the target structured data object, the at least one data item is added to the corresponding one or more fields respectively.
2. The method according to claim 1, wherein determining the target content and the target structured data object include: receiving an information extraction configuration for a content set from a user, the information extraction configuration indicating an extraction destination and a range of source contents in the content set; Based on the extraction destination, determining the target structured data object; as well as The target content is determined from the content collection based on the source content range.
3. The method according to claim 2, wherein receiving an extraction information configuration for a content set include: Displaying a configuration entry for information extraction in a content display interface associated with the content set; In response to the configuration entry being triggered, displaying an extraction configuration interface for the content set; as well as A user specification of a plurality of extraction destinations and a user specification of a range of the source content are received via the extraction configuration interface.
4. The method according to claim 2, wherein the at least one data item is added to the corresponding one or more fields. include: displaying the at least one data item and one or more fields corresponding to each data item; as well as In response to receiving a positive indication of the at least one data item, the at least one data item is added to the corresponding one or more fields respectively.
5. The method according to claim 1, wherein determining the target content and the target structured data object include: receiving an information extraction rule for a predetermined type of content from a user, the information extraction rule indicating an information extraction condition and an extraction destination for the predetermined type of content; determining the candidate content satisfying the information extraction condition as the target content; as well as Based on the extraction destination, the target structured data object is determined.
6. The method according to claim 5, wherein the information extraction condition comprises at least one of the following: a condition on an entity related to said predetermined type of content, or A condition on the semantics of the predetermined type of content.
7. The method according to claim 1, further comprising: include: In the interaction interface between the user and the digital assistant, prompt information for extracting information from the target content to the target structured data object is displayed.
8. The method of claim 1, wherein at least one data item is determined from the target content. include: generating prompt information for a target model based on the target content and the structured information; Providing the prompt information to the target model to obtain an output of the target model; as well as Based on an output of the target model, the at least one data item is determined.
9. The method of claim 1, wherein the target content comprises at least a portion of an email.
10. A device for information extraction, include: a determination module configured to determine target content and target structured data object based on user input indicating information extraction; An information acquisition module, configured to acquire structured information of the target structured data object, wherein the structured information indicates at least one field included in the target structured data object; a data item determination module, configured to determine at least one data item from the target content based on the target content and the structured information, the data item corresponding to one or more fields of the at least one field; as well as The data item adding module is configured to add the at least one data item to the corresponding one or more fields in the target structured data object.
11. An electronic device, include: 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 9 when executed by the at least one processing unit.
12. 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 9.
Citation Information
Patent Citations
System and method for automatically filling data table
CN111191429A
Data extraction method and related equipment
CN111475700A
Data processing method and device, electronic equipment and storage medium
CN117763209A
