Target knowledge data generation method and device, electronic equipment and storage medium

Abstract

The invention provides a target knowledge data generation method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the technical field of image processing. The specific implementation scheme is as follows: performing content identification and clustering processing on to-be-processed pictures to obtain text data corresponding to each group of to-be-processed pictures; extracting keywords from the text data of each group of to-be-processed pictures, and generating knowledge texts corresponding to each group of to-be-processed pictures according to the keywords; aggregating the knowledge text corresponding to each group of pictures to be processed with other knowledge texts to obtain a knowledge document; and obtaining target knowledge data according to the to-be-processed picture and the knowledge document. According to the method and the device, the automation level and the accuracy of information extraction are improved, and the organizability and the searchability of knowledge are enhanced, so that a user can more efficiently manage and utilize the knowledge information extracted from the picture, and the convenience of knowledge arrangement and sharing is greatly improved.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, specifically to the field of image processing technology, and in particular to a method, device, electronic device and storage medium for generating target knowledge data. Background Art

[0002] In public classes or courseware shared by others, people usually record information by taking photos. However, these photo records are difficult to organize and usually need to be manually selected and added to albums (such as online disk albums), and then viewed one by one to extract effective information and form notes. Currently, there is no product on the market that can automatically integrate these photos for knowledge management. In addition, due to the lack of an automatic organization mechanism, the photographed materials are often forgotten and cannot be organized in a timely manner. Summary of the invention

[0003] The present invention provides a method, device, electronic device and storage medium for generating target knowledge data.

[0004] According to one aspect of the present disclosure, a method for generating target knowledge data is provided, the method comprising:

[0005] Perform content recognition and clustering processing on the images to be processed to obtain text data corresponding to each group of images to be processed;

[0006] Extracting keywords from the text data of each group of images to be processed, and generating knowledge text corresponding to each group of images to be processed according to the keywords;

[0007] Aggregate the knowledge text corresponding to each group of images to be processed with other knowledge texts to obtain a knowledge document;

[0008] Target knowledge data is obtained according to the image to be processed and the knowledge document.

[0009] According to another aspect of the present disclosure, there is provided a target knowledge data generating device, comprising:

[0010] A processing module, used to perform content recognition and clustering processing on the images to be processed, and obtain text data corresponding to each group of images to be processed;

[0011] An extraction module, used to extract keywords from the text data of each group of images to be processed, and generate knowledge text corresponding to each group of images to be processed according to the keywords;

[0012] An aggregation module, used for aggregating the knowledge text corresponding to each group of images to be processed with other knowledge texts to obtain a knowledge document;

[0013] A generation module is used to obtain target knowledge data based on the image to be processed and the knowledge document.

[0014] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any method in any of the above technical solutions.

[0018] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any one of the methods described in the above technical solutions.

[0019] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program implements any one of the methods described in the above technical solutions when executed by a processor.

[0020] The present disclosure provides a method, device, equipment and storage medium for generating target knowledge data. The present disclosure extracts text data corresponding to each group of pictures by performing content recognition and clustering processing on the processed pictures, and then extracts keywords from these text data, and generates knowledge texts corresponding to each group of pictures based on these keywords. By aggregating these knowledge texts, a structured knowledge document is formed, and finally the target knowledge data is generated by combining the original pictures and knowledge documents. This process not only improves the automation level and accuracy of information extraction, but also enhances the organization and searchability of knowledge, allowing users to more efficiently manage and use the knowledge information extracted from the pictures, but also provides users with an intuitive and highly interactive learning and review platform, which greatly improves the convenience of knowledge organization and sharing.

[0021] It should be understood that the content described in this section is not intended to identify the key 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

[0022] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0023] Figure 1 is a schematic diagram of the steps of the method for generating target knowledge data in an embodiment of the present disclosure;

[0024] Figure 2is a flowchart of a method for generating target knowledge data in an embodiment of the present disclosure;

[0025] Figure 3 A principle block diagram of a target knowledge data generating device in an embodiment of the present disclosure;

[0026] Figure 4 It is a block diagram of an electronic device used to implement the target knowledge data generating method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0028] Traditional text scanning technology relies on users to actively take photos or select pictures from albums to extract text and generate learning notes. This method has obvious limitations: first, it requires users to personally participate in taking photos or selecting pictures, which increases the complexity of the operation. Secondly, due to the lack of automated classification and preservation mechanisms, it is difficult for users to effectively manage a large amount of original picture materials, making it difficult to organize and retrieve information. In addition, manually processing a large number of pictures is not only time-consuming and labor-intensive, but also prone to errors, making the organization and review of learning materials inefficient. Therefore, this traditional text scanning method has shortcomings in convenience, efficiency, and data management. There is an urgent need for a technology that can automatically process and organize picture materials to improve user experience.

[0029] In order to solve the above problems, the present disclosure provides a method for generating target knowledge data. Figure 1 As shown, Figure 1 : is a schematic diagram of the steps of the target knowledge data generation method in an embodiment of the present disclosure. The method can be applied to the server side. The method includes:

[0030] Step S101 , performing content recognition and clustering processing on the images to be processed to obtain text data corresponding to each group of images to be processed.

[0031] Specifically, in this solution, "pictures to be processed" refers to a collection of pictures uploaded by users to the server that need to be extracted and organized, such as slide pictures taken by users. "Content recognition" refers to the process of detecting and extracting visible text, objects, scenes and other information from pictures to be processed using image recognition technology and optical character recognition (OCR) technology. And "clustering processing" refers to the use of algorithms to group related pictures with similar features or content so that they can be processed and analyzed in a unified manner. Through these two steps, the server can "obtain text data corresponding to each group of pictures to be processed", that is, generate text information describing the content of each group of pictures, providing basic data for subsequent knowledge generation and organization. This process is a key link in realizing automated knowledge management and documentation, which enables the knowledge extracted from pictures to be structured and used to create smart album notes.

[0032] In this way, by performing content recognition and clustering on the images to be processed, the server can effectively extract the text data corresponding to each group of images. This process not only improves the accuracy and efficiency of information extraction, but also enables the relevant content to be systematically organized and classified. This processing method helps users quickly obtain and understand the key information in the image, reduces the time and effort of manual sorting, and lays a solid foundation for subsequent knowledge generation and documentation, thereby improving the overall knowledge management and learning experience.

[0033] Step S102, extracting keywords from the text data of each group of images to be processed, and generating knowledge text corresponding to each group of images to be processed according to the keywords.

[0034] Specifically, after obtaining the text data corresponding to each group of pictures to be processed, it is necessary to extract keywords from these text data. "Keyword extraction" refers to the use of natural language processing (NLP) technology to identify the core vocabulary that best represents the content and theme of the picture from the text data. Subsequently, "generating knowledge text based on keywords" means that the server uses these keywords as a basis, combined with the understanding and reasoning capabilities of the AI ​​(artificial intelligence) large model, to generate detailed and coherent text content to form knowledge text corresponding to each group of pictures to be processed. This process realizes the intelligent conversion from pictures to text, providing a rich information foundation for the subsequent knowledge organization and creation of learning notes.

[0035] In this way, by accurately extracting keywords from the text data of each group of images to be processed, and generating knowledge text corresponding to each group of photos based on these keywords, this solution can automatically convert the information contained in the images into structured, searchable knowledge content, greatly improving the efficiency and accuracy of information processing, while providing convenience for users to organize and review knowledge, and enhancing the usability and practicality of knowledge. This process not only saves time for manually organizing notes, but also improves the quality and depth of knowledge management through intelligent means, allowing users to understand and apply the knowledge extracted from images more quickly and deeply.

[0036] Step S103, aggregating the knowledge text corresponding to each group of images to be processed with other knowledge texts to obtain a knowledge document.

[0037] Specifically, "knowledge text" refers to the text information obtained from these images through text recognition and content analysis, which contains the key knowledge points in the images. "Aggregation" refers to the process of integrating and organizing the knowledge text corresponding to each group of images to be processed with other related knowledge texts. Through this process, the server brings together scattered knowledge points into a coherent and structured whole, namely the "knowledge document". This document not only contains information extracted from a single group of images, but may also include supplementary content from other related images or external data sources, thereby providing users with a comprehensive and systematic knowledge resource for easy learning and sharing. Implementing this process usually involves natural language processing technology, content management systems, and artificial intelligence algorithms to ensure the logical relationship and semantic coherence between knowledge points.

[0038] In this way, by aggregating the knowledge text corresponding to each group of images to be processed with other related knowledge texts, this solution can integrate scattered information points into structured knowledge documents. This process not only enhances the coherence and completeness of the content, but also improves the efficiency and convenience of knowledge retrieval, enabling users to manage and utilize the information extracted from images more systematically, thereby greatly improving learning and work efficiency.

[0039] Step S104, obtaining target knowledge data according to the image to be processed and the knowledge document.

[0040] Specifically, "knowledge documents" refer to the text information obtained from these images through content recognition and text extraction technology, which is a detailed document formed after further organization and supplementation. "Target knowledge data" is generated based on these images to be processed and the corresponding knowledge documents. It is a more user-friendly and interactive information summary, usually containing pictures, key knowledge points and personal notes. In order to achieve this process, the server usually matches and associates the pictures with the content in the knowledge documents, creating an intuitive note interface that allows users to view, edit and share, thereby transforming static pictures and documents into dynamic and easy-to-manage knowledge resources. This conversion not only improves the accessibility and practicality of information, but also provides users with a convenient learning and review platform.

[0041] The present disclosure provides a method, device, equipment and storage medium for generating target knowledge data. The present disclosure extracts text data corresponding to each group of pictures by performing content recognition and clustering processing on the processed pictures, and then extracts keywords from these text data, and generates knowledge texts corresponding to each group of pictures based on these keywords. By aggregating these knowledge texts, a structured knowledge document is formed, and finally the target knowledge data is generated by combining the original pictures and knowledge documents. This process not only improves the automation level and accuracy of information extraction, but also enhances the organization and searchability of knowledge, allowing users to more efficiently manage and use the knowledge information extracted from the pictures, but also provides users with an intuitive and interactive learning and review platform, which greatly improves the convenience of knowledge organization and sharing.

[0042] In some optional embodiments, content recognition and clustering processing are performed on the images to be processed to obtain text data corresponding to each group of images to be processed, including:

[0043] Identify the text content in the image to be processed and obtain text data corresponding to the image to be processed;

[0044] The images to be processed are clustered according to their shooting time and text content to obtain text data corresponding to each group of images to be processed.

[0045] Specifically, after obtaining the pictures to be processed, the visible text information is extracted from these pictures using image recognition technology and optical character recognition (OCR) technology, and converted into machine-readable text data to obtain text data corresponding to the pictures to be processed.

[0046] After obtaining the text data corresponding to the image to be processed, a clustering algorithm is used to group images with similar or related contents according to the shooting time of the image and the extracted text content to form different image groups. The clustering algorithm is a method in unsupervised learning, which is used to divide the samples in the data set into several clusters or groups, so that the similarity of samples in the same group is high, while the similarity of samples between different groups is low. The clustering algorithm can adopt, for example, a K-means clustering algorithm, a hierarchical clustering algorithm, and a density-based clustering algorithm, which are not limited here.

[0047] Through this process, the server can effectively organize the text data corresponding to each group of images to be processed, providing a structured data foundation for subsequent knowledge generation and documentation, thereby realizing the intelligent conversion from images to knowledge texts.

[0048] In this way, by identifying the text content in the image to be processed and clustering the images based on the shooting time and text content, the corresponding text data can be accurately extracted from the image, and related images and their text data can be effectively grouped. This not only improves the automation and accuracy of information extraction, but also enhances the organization and retrieval efficiency of data, allowing users to access and understand key information in the image more quickly, thereby greatly improving the efficiency of knowledge management and information utilization.

[0049] In some optional embodiments, keywords are extracted from the text data of each group of images to be processed, and knowledge text corresponding to each group of images to be processed is generated according to the keywords, including:

[0050] Extract keywords from the text data of each group of images to be processed to obtain keywords and non-keywords;

[0051] Keywords and non-keywords are input into the large language model, and the knowledge text corresponding to each group of images to be processed is generated by the large language model.

[0052] Specifically, after obtaining the text data of each group of images to be processed, the next step is to extract keywords. Among them, "keyword extraction" refers to the use of natural language processing (NLP) technology to identify important words from text data, which can represent the core content of the text, and distinguish non-keywords, that is, words that do not carry core information. Then, these "keywords" and "non-keywords" are input into a "big language model", which is an advanced artificial intelligence model that can understand and process large amounts of language data. Through this big language model, the server can generate detailed "knowledge texts" corresponding to each group of images to be processed based on the input keywords and non-keywords. These texts not only contain information directly extracted from the images, but may also include additional knowledge inferred by the model based on the context, thereby providing users with richer and deeper content understanding. This process realizes the intelligent conversion from images to text, providing a rich information foundation for subsequent knowledge organization and the creation of learning notes.

[0053] In this way, by extracting keywords and non-keywords from the text data of each group of images to be processed and inputting these words into the large language model, it is possible to use advanced artificial intelligence technology to generate knowledge texts closely related to each group of images. This method not only improves the accuracy and efficiency of information extraction, but also can deeply explore and understand the content of the image, generate rich and coherent knowledge texts, greatly enhance the availability and practicality of information, and provide users with a powerful tool to more effectively manage and use the knowledge extracted from the image.

[0054] In some optional embodiments, extracting keywords from the text data of each group of images to be processed to obtain keywords and non-keywords includes:

[0055] Natural language processing technology is used to extract keywords from the text data of each group of images to be processed to obtain keywords and non-keywords.

[0056] Specifically, "natural language processing technology" is a technology in the field of computer science and artificial intelligence that aims to enable computers to understand, analyze and generate natural language, such as word segmentation, syntactic analysis, etc. By adopting this technology, the server can identify the "keywords" that best represent the core content of each set of text data of the images to be processed, and distinguish those "non-keywords" that do not carry important information. This process realizes the intelligent analysis of text information, provides a basis for subsequent knowledge generation and organization, and ensures that users can quickly obtain and use key information in the images.

[0057] In this way, by using natural language processing technology to extract keywords from the text data of each group of images to be processed, the server can effectively identify core information and topics, and distinguish between keywords and non-keywords. This process not only improves the accuracy and efficiency of information extraction, but also enables users to quickly obtain key knowledge related to the image content, thereby strengthening the foundation for subsequent knowledge generation and organization, and providing users with a more convenient and efficient knowledge management experience.

[0058] In some optional embodiments, the knowledge text corresponding to each group of images to be processed is aggregated with other knowledge texts to obtain a knowledge document, including:

[0059] Aggregate the knowledge text corresponding to each group of images to be processed and the text information associated with other knowledge texts to obtain aggregated knowledge texts;

[0060] Sort the knowledge points in the aggregated knowledge text according to logical order and chronological order to obtain an unstructured knowledge text;

[0061] Convert unstructured text into a structured format to obtain knowledge documents.

[0062] Specifically, the knowledge text corresponding to each group of images to be processed refers to the text information obtained from these images through image recognition technology and natural language processing technology, which contains the key knowledge points in the images, while other knowledge texts refer to other knowledge texts except the current knowledge texts. After obtaining the knowledge texts corresponding to all the images to be processed, all the knowledge texts are aggregated. "Aggregation" refers to the process of integrating and organizing the knowledge text corresponding to each group of images to be processed with other related knowledge texts, with the aim of obtaining a more comprehensive and coherent "aggregated knowledge text".

[0063] After obtaining the aggregated knowledge text, it is then structured. "Unstructured knowledge text" refers to text information that has not been organized in a specific format, while "structured format" refers to sorting and organizing this information in a certain logical order or chronological order, and finally transforming it into an easy-to-read and understand "knowledge document". This process involves sorting and formatting knowledge points, so that the originally scattered information is systematically integrated, improving the availability and retrievability of information, and finally forming a structured knowledge base for users to learn and share.

[0064] In this way, by aggregating the knowledge texts and other related text information corresponding to each group of images to be processed, sorting the knowledge points in logical or chronological order, and then converting these unstructured texts into structured formats, it is possible to achieve an efficient transformation from scattered information to ordered knowledge documents. This process not only enhances the organization and readability of information, but also improves the retrieval efficiency and practicality of knowledge, ultimately providing users with a clear and systematic knowledge management platform, greatly improving the convenience and depth of information processing.

[0065] In some optional embodiments, the target knowledge data is obtained according to the image to be processed and the knowledge document, including:

[0066] Establish a mapping relationship between the image to be processed and the knowledge document;

[0067] The image to be processed is associated with the relevant knowledge points in the knowledge document, and the association results are displayed on the user interface to obtain the target knowledge data.

[0068] Specifically, "mapping relationship" refers to a connection created by the server to match each image to be processed with its corresponding knowledge document content. Through this mapping, the server is able to "associate the image to be processed with the associated knowledge points in the knowledge document", which means that each image will be linked to its related knowledge points. Finally, "target knowledge data" is the result of this association, which is displayed in the user interface, intuitively presenting the image and its corresponding knowledge points to the user, allowing the user to see the image and the knowledge content behind it at a glance, thereby realizing visual management and rapid review of knowledge.

[0069] In this way, by establishing a mapping relationship between the image to be processed and the knowledge document, and intuitively associating the image to be processed with the related knowledge points in the knowledge document in the user interface, this solution realizes the visualization and structured display of knowledge, which not only improves the efficiency of information retrieval, but also enhances the user's understanding and memory of knowledge, allowing users to manage and review knowledge content more conveniently, greatly improving learning and work efficiency.

[0070] In order to understand the technical solution of this application as a whole, see Figure 2 , Figure 2It is a flowchart of the target knowledge data generation method in the embodiment of the present disclosure. Specifically, the flowchart shows the workflow of an intelligent album note generation system based on an AI big model. After the user starts the APP, he selects the picture to be processed. The server uses the big model to perform content recognition, clustering and keyword extraction on the picture to be processed, and generates knowledge texts corresponding to each group of pictures to be processed based on the keywords; aggregates the knowledge texts corresponding to each group of pictures to be processed with other knowledge texts to obtain knowledge documents; obtains the target knowledge data based on the pictures to be processed and the knowledge documents. This process realizes the automated conversion from pictures to knowledge documents, improving the efficiency and convenience of knowledge organization.

[0071] The following describes an apparatus embodiment of the present application, which can be used to execute the target knowledge data generation method in the above embodiment of the present application. For details not disclosed in the apparatus embodiment of the present application, please refer to the above embodiment of the target knowledge data generation method of the present application.

[0072] The present disclosure also provides a target knowledge data generating device 300, such as Figure 3 As shown, including:

[0073] Processing module 301, used to perform content recognition and clustering processing on the images to be processed, and obtain text data corresponding to each group of images to be processed;

[0074] An extraction module 302 is used to extract keywords from the text data of each group of images to be processed, and generate knowledge text corresponding to each group of images to be processed according to the keywords;

[0075] Aggregation module 303, used to aggregate the knowledge text corresponding to each group of images to be processed with other knowledge texts to obtain a knowledge document;

[0076] The generation module 304 is used to obtain target knowledge data according to the image to be processed and the knowledge document.

[0077] In some optional embodiments, the processing module 301 performs content recognition and clustering processing on the images to be processed to obtain text data corresponding to each group of images to be processed, including:

[0078] Identify the text content in the image to be processed and obtain text data corresponding to the image to be processed;

[0079] The images to be processed are clustered according to the shooting time and text content of the images to be processed to obtain text data corresponding to each group of images to be processed.

[0080] In some optional embodiments, the extraction module 302 extracts keywords from the text data of each group of images to be processed, and generates knowledge text corresponding to each group of images to be processed according to the keywords, including:

[0081] Extract keywords from the text data of each group of images to be processed to obtain keywords and non-keywords;

[0082] Keywords and non-keywords are input into the large language model, and the knowledge text corresponding to each group of images to be processed is generated by the large language model.

[0083] In some optional embodiments, the extraction module 302 extracts keywords from the text data of each group of images to be processed to obtain keywords and non-keywords, including:

[0084] Natural language processing technology is used to extract keywords from the text data of each group of images to be processed to obtain keywords and non-keywords.

[0085] In some optional embodiments, the aggregation module 303 aggregates the knowledge text corresponding to each group of images to be processed with other knowledge texts to obtain a knowledge document, including:

[0086] Aggregate the knowledge text corresponding to each group of images to be processed and the text information associated with other knowledge texts to obtain aggregated knowledge texts;

[0087] Sort the knowledge points in the aggregated knowledge text according to logical order and chronological order to obtain an unstructured knowledge text;

[0088] Convert unstructured text into a structured format to obtain knowledge documents.

[0089] In some optional embodiments, the generating module 304 obtains target knowledge data according to the image to be processed and the knowledge document, including:

[0090] Establish a mapping relationship between the image to be processed and the knowledge document;

[0091] The image to be processed is associated with the relevant knowledge points in the knowledge document, and the association results are displayed on the user interface to obtain the target knowledge data.

[0092] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0093] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0094] Figure 4A schematic block diagram of an example electronic device 400 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0095] like Figure 4 As shown, the electronic device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0096] A number of components in the device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0097] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above, such as the target knowledge data generation method. For example, in some embodiments, the target knowledge data generation method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the applet distribution described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the target knowledge data generation method in any other appropriate manner (e.g., by means of firmware).

[0098] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0099] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0100] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0101] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0102] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0103] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0104] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0105] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for generating target knowledge data, the method comprising: Perform content recognition and clustering processing on the images to be processed to obtain text data corresponding to each group of images to be processed; Extracting keywords from the text data of each group of images to be processed, and generating knowledge text corresponding to each group of images to be processed according to the keywords; Aggregate the knowledge text corresponding to each group of images to be processed with other knowledge texts to obtain a knowledge document; Target knowledge data is obtained according to the image to be processed and the knowledge document.

2. The method according to claim 1, wherein: The content recognition and clustering processing are performed on the images to be processed to obtain text data corresponding to each group of images to be processed, including: Identify the text content in the image to be processed to obtain text data corresponding to the image to be processed; The pictures to be processed are clustered according to the shooting time and text content of the pictures to be processed to obtain text data corresponding to each group of pictures to be processed.

3. The method according to claim 1, wherein: The step of extracting keywords from the text data of each group of images to be processed, and generating knowledge text corresponding to each group of images to be processed according to the keywords, includes: Extract keywords from the text data of each group of images to be processed to obtain keywords and non-keywords; The keywords and the non-keywords are input into a large language model, and a knowledge text corresponding to each group of images to be processed is generated through the large language model.

4. The method according to claim 3, wherein: The step of extracting keywords from the text data of each group of images to be processed to obtain keywords and non-keywords includes: Natural language processing technology is used to extract keywords from the text data of each group of images to be processed to obtain keywords and non-keywords.

5. The method according to claim 1, wherein: The knowledge text corresponding to each group of images to be processed is aggregated with other knowledge texts to obtain a knowledge document, including: Aggregating the knowledge text corresponding to each group of images to be processed and text information associated with other knowledge texts to obtain aggregated knowledge texts; Sorting the knowledge points in the aggregated knowledge text according to a logical order and a chronological order to obtain an unstructured knowledge text; The unstructured text is converted into a structured format to obtain a knowledge document.

6. The method according to any one of claims 1 to 5, wherein: The step of obtaining target knowledge data according to the image to be processed and the knowledge document includes: Establishing a mapping relationship between the image to be processed and the knowledge document; The image to be processed is associated with the relevant knowledge points in the knowledge document, and the association result is displayed on the user interface to obtain the target knowledge data.

7. A target knowledge data generating device, comprising: A processing module, used to perform content recognition and clustering processing on the images to be processed, and obtain text data corresponding to each group of images to be processed; An extraction module, used to extract keywords from the text data of each group of images to be processed, and generate knowledge text corresponding to each group of images to be processed according to the keywords; An aggregation module, used for aggregating the knowledge text corresponding to each group of images to be processed with other knowledge texts to obtain a knowledge document; A generation module is used to obtain target knowledge data based on the image to be processed and the knowledge document.

8. The device according to claim 7, wherein: The processing module performs content recognition and clustering processing on the images to be processed to obtain text data corresponding to each group of images to be processed, including: Identify the text content in the image to be processed to obtain text data corresponding to the image to be processed; The pictures to be processed are clustered according to the shooting time and text content of the pictures to be processed to obtain text data corresponding to each group of pictures to be processed.

9. The device according to claim 7, wherein: The extraction module extracts keywords from the text data of each group of images to be processed, and generates knowledge text corresponding to each group of images to be processed according to the keywords, including: Extract keywords from the text data of each group of images to be processed to obtain keywords and non-keywords; The keywords and the non-keywords are input into a large language model, and a knowledge text corresponding to each group of images to be processed is generated through the large language model.

10. The device according to claim 9, wherein: The extraction module extracts keywords from the text data of each group of images to be processed to obtain keywords and non-keywords, including: Natural language processing technology is used to extract keywords from the text data of each group of images to be processed to obtain keywords and non-keywords.

11. The device according to claim 7, wherein: The aggregation module aggregates the knowledge text corresponding to each group of images to be processed with other knowledge texts to obtain a knowledge document, including: Aggregating the knowledge text corresponding to each group of images to be processed and text information associated with other knowledge texts to obtain aggregated knowledge texts; Sorting the knowledge points in the aggregated knowledge text according to a logical order and a chronological order to obtain an unstructured knowledge text; The unstructured text is converted into a structured format to obtain a knowledge document.

12. The device according to any one of claims 7 to 11, wherein: The generation module obtains target knowledge data according to the image to be processed and the knowledge document, including: Establishing a mapping relationship between the image to be processed and the knowledge document; The image to be processed is associated with the relevant knowledge points in the knowledge document, and the association result is displayed on the user interface to obtain the target knowledge data.

13. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-6.

15. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images