Knowledge convergence method, device, equipment, medium and program product

Abstract

The invention discloses a knowledge convergence method, device and equipment, a medium and a program product, relates to the technical field of information and the technical field of agents, and can be applied to the field of financial science and technology. Obtaining original text data; performing data processing on the original text data to obtain first-stage data; performing deep analysis on the first-stage data to obtain second-stage data; and verifying the second-stage data to obtain target technical data. By adopting the technical scheme, the prospective knowledge is collected, processed and summarized through the intelligent agent, the problems of low technical efficiency and insufficient information processing capability are effectively avoided, and comprehensive, timely and accurate convergence and utilization of the prospective technical information are realized.

Description

Technical Field

[0001] The present invention relates to the fields of information technology and intelligent body technology, can be applied to the field of financial technology, and in particular to a knowledge aggregation method, device, equipment, medium and program product. Background Art

[0002] In the current scientific and technological environment, the amount of information on forward-looking technologies is large, updated quickly, and distributed in multiple channels, such as academic journals, patent databases, technical blogs, etc. It is a daunting task to obtain and process this data in real time.

[0003] At present, forward-looking technology knowledge aggregation technology often relies on researchers to manually collect relevant information through search engines, databases, academic journals or other channels, or use web crawlers to obtain the latest information, and then perform data processing and aggregation through structured data processing or manual processing.

[0004] Although manual collection is highly accurate and can accurately obtain the required information, it is inefficient and has difficulty coping with massive amounts of information; automated tools have relatively simple functions and cannot perform in-depth analysis and processing of structured data. Summary of the invention

[0005] The present invention provides a knowledge aggregation method, device, equipment, medium and program product, which collects, processes and aggregates forward-looking knowledge through an intelligent agent, effectively avoiding the problems of low technical efficiency and insufficient information processing capability, and realizing the comprehensive, timely and accurate aggregation and utilization of forward-looking technical information.

[0006] According to one aspect of the present invention, a knowledge aggregation method is provided, which is applied to an intelligent agent, comprising:

[0007] Get the original data;

[0008] Performing data processing on the original data to obtain first-stage data;

[0009] Conducting in-depth analysis on the first-stage data to obtain the second-stage data;

[0010] The second phase data is verified to obtain target technical data.

[0011] According to another aspect of the present invention, there is provided a knowledge aggregation device, which is configured in an intelligent agent and includes:

[0012] An original data acquisition module, used to acquire original data;

[0013] A first-stage data acquisition module, used for processing the original data to obtain first-stage data;

[0014] The second stage data acquisition module is used to perform in-depth analysis on the first stage data to obtain the second stage data;

[0015] The target technical data acquisition module is used to verify the second-stage data to obtain the target technical data.

[0016] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the knowledge aggregation method described in any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the knowledge aggregation method described in any embodiment of the present invention when executed.

[0021] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the knowledge aggregation method according to any embodiment of the present invention is implemented.

[0022] The technical solution of the embodiment of the present invention collects, processes and summarizes forward-looking knowledge through an intelligent agent, effectively avoiding the problems of low technical efficiency and insufficient information processing capabilities, and realizing comprehensive, timely and accurate aggregation and utilization of forward-looking technical information.

[0023] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 is a flow chart of a knowledge aggregation method provided according to an embodiment of the present invention;

[0026] Figure 2 is a depth analysis flow chart adopted by an embodiment of the present invention;

[0027] Figure 3 is a data verification flow chart adopted by an embodiment of the present invention;

[0028] Figure 4 is a schematic diagram of the structure of a knowledge aggregation device provided according to an embodiment of the present invention;

[0029] Figure 5 It is a schematic diagram of the structure of an electronic device for implementing the knowledge aggregation method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] In addition, it should be noted that the collection, storage, use, processing, transmission, provision and disclosure of data involved in the technical solution of the present invention are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0032] Figure 1 is a flow chart of a knowledge aggregation method provided according to an embodiment of the present invention. The present invention is applicable to the case of prospective knowledge aggregation and can be performed by the knowledge aggregation device provided by the embodiment of the present invention. The knowledge aggregation device can be implemented in the form of hardware and / or software and can be integrated into an electronic device carrying a data processing function, such as a server. Figure 1 As shown, the method is applied to an intelligent agent, comprising:

[0033] S110, obtaining original text data.

[0034] Among them, the original data is the information related to the forward-looking technology automatically obtained from the information source. The forward-looking technology refers to the future and current technology trends and innovation fields, such as intelligent research and development, cloud computing, artificial intelligence, etc.; the intelligent agent refers to a computing system that can perform tasks autonomously in a certain environment, and has memory, knowledge and tool calling capabilities; in the embodiment of the present invention, the intelligent agent collects, processes, analyzes and evaluates information by calling a large model; it should be noted that relevant technical personnel can use a single intelligent agent or multiple intelligent agents with different functions to achieve this according to specific scenarios and needs, and the embodiment of the present invention does not specifically limit this.

[0035] Specifically, the agent can automatically obtain information related to forward-looking technologies directly from information sources such as the Internet, patent databases, and academic journals. Exemplarily, the original data in the embodiment of the present invention can be technical data information related to financial scenarios. Preferably, the agent in the embodiment of the present invention can automatically obtain the latest news regularly by calling crawler tools or various source APIs, and summarize them as original data.

[0036] It can be understood that in the embodiment of the present invention, a single intelligent agent is used to implement the entire process of acquiring forward-looking knowledge data and aggregating knowledge; by using a single intelligent agent to collect and process data, the simplicity and integration of the system are guaranteed; it is easy to implement and maintain, and it is also easier to achieve global optimization and consistency processing of data; and by effectively utilizing the tool calling capabilities of the intelligent agent, it is able to autonomously and efficiently acquire data from multiple information sources, ensuring the accuracy and real-time nature of the subsequent forward-looking knowledge summary results.

[0037] In an optional manner of the embodiment of the present invention, the intelligent agent may also be an information collection intelligent agent so as to automatically obtain original text data related to the forward-looking technology from the information source.

[0038] S120, processing the original data to obtain first-stage data.

[0039] Among them, data processing includes preprocessing such as data deduplication, classification, cleaning and storage of original data; the first stage data is the forward-looking knowledge data after preprocessing.

[0040] After obtaining the original data, the intelligent agent independently carries out data cleaning, processing and storage, and pre-processes the stored data to obtain the first-stage data.

[0041] In an optional manner of the embodiment of the present invention, the agent may also be an information processing agent so as to perform data preprocessing on the original data.

[0042] Optionally, the original data is processed to obtain the first-stage data, including:

[0043] De-duplicate the original data to obtain de-duplicated data;

[0044] Classify the deduplicated data to obtain classified data;

[0045] The classified data is cleaned and the format of the cleaned data is processed to obtain the first stage data.

[0046] The obtained original text data is initially deduplicated using a hash algorithm, and duplicate data is further cleaned up through text similarity calculation; the deduplicated data is initially classified based on keyword extraction, and then the data is further semantically understood through the agent's own capabilities to achieve dynamic classification optimization; the classified data is cleaned again, and the agent automatically generates missing data and a unified format as the first-stage data.

[0047] It is understandable that by deduplicating the data, the uniqueness and accuracy of the data are ensured, and the classified data is cleaned again to eliminate irrelevant data to ensure the integrity of the data.

[0048] In an optional manner of an embodiment of the present invention, the formatted data is further stored, including: using a relational database or a graph database for data storage, and designing a table structure according to the attributes of the data to classify the data, and using the classified data as the first-stage data, which can be displayed in a structured or knowledge graph manner; and creating a corresponding index table. Exemplarily, in an embodiment of the present invention, the data can be classified according to fields such as subject, source, and time.

[0049] It can be understood that by storing the classified data in a structured manner and creating an index table based on the categories, the query efficiency of subsequent data is improved.

[0050] S130, performing in-depth analysis on the first-stage data to obtain second-stage data.

[0051] Among them, in-depth analysis can be to extract key trends and technology hotspots from the first-stage data, including technology trend analysis, technology keyword mining and aggregation, and data association analysis; the second-stage data is knowledge data with association relationships.

[0052] Specifically, the intelligent agent performs technology trend analysis, technology keyword mining and aggregation, and data association analysis on the stored structured or knowledge graph data to extract information such as key trends and technology hotspots.

[0053] In an optional manner of the embodiment of the present invention, the intelligent agent may also be an information analysis intelligent agent so as to perform in-depth analysis on the analyzed first-stage data to extract key trends.

[0054] Optional, such as Figure 2 A deep analysis flow chart shown in FIG. 1 performs deep analysis on the first stage data to obtain the second stage data, including:

[0055] S131. Extract time series data from the first phase data, and generate a technical report based on the time series data.

[0056] Among them, time series data is data with timestamp or time series characteristics; technical reports can reflect the laws and trends of time series data.

[0057] Specifically, the intelligent agent identifies data columns with timestamp or time series features from the structured first-stage data, and uses automatic feature extraction tools to extract features from the time series data columns. Based on the feature analysis results, it derives the laws and trends of the time series data and generates a technical report. Exemplarily, the changing trends of the time series data may be seasonal fluctuations and cyclical changes.

[0058] It can be understood that the intelligent agent extracts relevant data in the technology field from structured data, and uses the changing patterns of time series data to predict the direction of technological development and identify the future growth trend of related technologies.

[0059] S132. Extract technical keywords from the first phase data, rearrange and aggregate the technical keywords, and identify technical trend keywords.

[0060] Among them, technical keywords are words that appear frequently in the data. In the embodiment of the present invention, they are preferably high-frequency words related to the current forward-looking technology field.

[0061] Specifically, the frequency of each word appearing in the first phase of data is counted, and high-frequency words are selected as technical keywords. The technical keywords are then rearranged and aggregated based on time series and semantic analysis to identify the current hot technical trend keywords.

[0062] In one embodiment of the present invention, after counting the frequency of each word appearing in the first stage data, it also includes screening high-frequency words, including: filtering out high-frequency words that are not related to the technical field according to the language model, and retaining high-frequency words that are related to the technical field as technical keywords; it can be understood that by filtering high-frequency words through the language model, the accuracy of technical keywords is ensured and the data processing efficiency is improved.

[0063] In one implementation of an embodiment of the present invention, the re-arrangement and aggregation of technical keywords based on time series and semantic analysis can be specifically as follows: the semantic similarity between technical keywords is calculated to re-arrange the technical keywords, and the technical keywords with high semantic similarity are aggregated into one category; the time variation trend of the aggregated keyword category is analyzed, and the technical trend keywords are identified in combination with the frequency variation. It should be noted that the semantic similarity can be calculated using technical means such as word embedding or graph embedding, and the embodiment of the present invention does not specifically limit this, and any method that can realize the calculation of semantic similarity can be used.

[0064] It can be understood that by mining the technical trend keywords related to the first-stage data and conducting in-depth analysis of the processed data through intelligent agents, key trends and technical hotspots can be extracted, which helps to understand the development dynamics in the field of technology and facilitate subsequent correlation analysis.

[0065] S133. Perform correlation analysis on the keywords of technical reports and technical trends to obtain the second stage data.

[0066] Based on technology trend keywords and technology reports, data correlation analysis is performed according to the model's own capabilities to discover the inherent connections between different technology fields; for example, the AI ​​field and the cloud computing field may overlap, and AI can be used to empower Ops operations.

[0067] It is understandable that the intelligent agent autonomously updates these technical associations to ensure that the dynamic changes in associations between related technical fields can be fed back in a timely manner, helping researchers understand the overall picture of current forward-looking technological progress and the potential linkages between different technologies.

[0068] S140, verify the second-stage data to obtain target technical data.

[0069] Among them, the target technology data is the data processed from the forward-looking technology data obtained from multiple data sources, which can provide relevant users with accurate and valuable insights on the forward-looking technology field; data verification is the evaluation of data, which may include data reliability assessment, data cross-validation and feedback optimization, etc.; the second-stage data is verified by the intelligent agent to obtain the target technology data.

[0070] In an optional embodiment of the present invention, the intelligent agent may also include an information evaluation intelligent agent to perform verification evaluation on the analyzed second-stage data.

[0071] Optional, such as Figure 3 A data verification flow chart shown in FIG. 1 ; verifying the second-stage data to obtain target technical data, including:

[0072] S141. Determine the comprehensive weight of the second-stage data.

[0073] Among them, the comprehensive weight of the second-stage data may include the trust weight and timeliness weight of the data; the trust weight refers to the reliability, accuracy and authority of the data or information; the timeliness weight refers to the update frequency of the data or information.

[0074] Specifically, the agent determines the indicators that need to be evaluated based on the second-stage data, and obtains the comprehensive score of the second-stage data according to the trust weight and timeliness weight.

[0075] Optionally, determine the comprehensive weight of the second-stage data, specifically:

[0076] Determine the trust weight of the data source of the original data;

[0077] Determine the timeliness weight of the second-stage data based on its life cycle;

[0078] Determine the comprehensive weight based on the trust weight and timeliness weight.

[0079] Among them, data sources may include academic publications, government agencies, professional organizations, well-known media, industry reports, market research, etc.; the data life cycle may include data capture, data maintenance, data synthesis, data use, data analysis, data release, data archiving and other stages.

[0080] The intelligent agent assigns different trust weights to different data sources by comparing the authority of each data source in the second data. For example, it determines whether the data source is data released by authoritative platforms such as well-known academic journals and technical forums; the intelligent agent evaluates the timeliness weight of the data based on the life cycle of the second-stage data and the frequency of data updates; the comprehensive weight of the second-stage data is determined based on the trust weight and the timeliness weight; it should be noted that the calculation method of the comprehensive weight can be adjusted and optimized according to changes in application fields and objectives to adapt to the needs of different scenarios, and the embodiments of the present invention do not specifically limit this.

[0081] It can be understood that by determining the trust weight and timeliness weight of the data, it is convenient to verify and update the data after in-depth analysis.

[0082] S142. Cross-validate the second-stage data to obtain data cross-scoring.

[0083] The second-stage data can be divided into different subsets based on the data source, and the intelligent agent can be used to verify the data difference to obtain the data cross-scoring. By comparing the data from different platforms and sources, the potential differences and conflicts between the second-stage data can be found to ensure the accuracy of the data.

[0084] S143. Regenerate the second-stage data based on the comprehensive weight and data cross-scoring to obtain the target technical data.

[0085] The total information score is calculated based on the comprehensive weight of the second-stage data and the data cross-scoring, and is used as the target technical data. The score is judged by relevant researchers and feedback is given on the final result. The intelligent agent can self-learn and adjust the evaluation strategy according to the feedback. If the researcher feedback shows that the final report is not good, the intelligent agent will adjust the trust weight of the corresponding data source and regenerate the report for feedback.

[0086] It can be understood that the data after in-depth analysis is verified by the intelligent agent, making the obtained target technical data more reliable and accurate.

[0087] Optionally, after acquiring the target technical data, the method further includes: visualizing the target technical data and providing an original text link of the target technical data.

[0088] After obtaining the target technical data, the analysis results and evaluation scores can be displayed to the user in a visual way, and the original link related to the target technical data can be provided.

[0089] It is understandable that by visualizing the relevant technical data of the forward-looking technology that has been finally analyzed, it can be intuitively displayed to the relevant technical personnel, and the original link related to the original data can be provided, so that the relevant technical personnel can directly read the original text in detail.

[0090] The embodiment of the present invention is applied to an intelligent agent, by acquiring original data; processing the original data to obtain first-stage data; performing in-depth analysis on the first-stage data to obtain second-stage data; verifying the second-stage data to obtain target technical data; the above-mentioned technical scheme collects, processes and summarizes forward-looking knowledge through the intelligent agent, effectively avoiding the problems of low technical efficiency and insufficient information processing capabilities, and realizing the comprehensive, timely and accurate aggregation and utilization of forward-looking technical information, which not only improves the degree of automation of information processing, but also ensures the accuracy and real-time nature of the analysis results.

[0091] Figure 4 is a schematic diagram of the structure of a knowledge aggregation device provided according to an embodiment of the present invention. The present invention is applicable to the case of prospective knowledge aggregation. The knowledge aggregation device can be implemented in the form of hardware and / or software and can be integrated into an electronic device carrying a data processing function, such as a server. Figure 4 As shown, the knowledge aggregation device 200 is configured on the intelligent agent, including:

[0092] The original data acquisition module 210 is used to acquire the original data;

[0093] The first stage data acquisition module 220 is used to process the original data to obtain the first stage data;

[0094] The second stage data acquisition module 230 is used to perform in-depth analysis on the first stage data to obtain the second stage data;

[0095] The target technical data acquisition module 240 is used to verify the second-stage data to obtain the target technical data.

[0096] The embodiment of the present invention is applied to an intelligent agent, by acquiring original data; processing the original data to obtain first-stage data; performing in-depth analysis on the first-stage data to obtain second-stage data; verifying the second-stage data to obtain target technical data; the above-mentioned technical scheme collects, processes and summarizes forward-looking knowledge through the intelligent agent, effectively avoiding the problems of low technical efficiency and insufficient information processing capabilities, and realizing the comprehensive, timely and accurate aggregation and utilization of forward-looking technical information, which not only improves the degree of automation of information processing, but also ensures the accuracy and real-time nature of the analysis results.

[0097] Optionally, the first stage data acquisition module 220 is specifically used to deduplicate the original data to obtain deduplicated data; classify the deduplicated data to obtain classified data; clean the classified data and format the cleaned data to obtain first stage data.

[0098] Optionally, the second-stage data acquisition module 230 is specifically used to extract time series data from the first-stage data and generate a technical report based on the time series data; extract technical keywords from the first-stage data, rearrange and aggregate the technical keywords, and identify technical trend keywords; perform correlation analysis on the technical report and the technical trend keywords to obtain the second-stage data.

[0099] Optionally, the target technology data acquisition module 240 includes a weight determination unit, a data cross-score determination unit, and a target technology data determination unit;

[0100] A weight determination unit, used to determine the comprehensive weight of the second stage data;

[0101] A data cross-score determination unit, used to cross-validate the second-stage data to obtain a data cross-score;

[0102] The target technical data determination unit is used to regenerate the second-stage data according to the comprehensive weight and data cross-scoring to obtain the target technical data.

[0103] Optionally, a weight determination unit is specifically used to determine the trust weight of the data source of the original data; determine the timeliness weight of the second-stage data according to the life cycle of the second-stage data; and determine the comprehensive weight according to the trust weight and the timeliness weight.

[0104] Optionally, the knowledge aggregation device 200 further includes a visualization processing module, which is used to perform visualization processing on the target technical data and provide an original text link of the target technical data.

[0105] The knowledge aggregation device provided in the embodiment of the present invention can execute the knowledge aggregation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0106] According to an embodiment of the present invention, the present invention also provides an electronic device, a readable storage medium and a computer program product.

[0107] Figure 5 1 is a schematic diagram of the structure of an electronic device 10 that implements the knowledge aggregation method of an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) 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 invention described and / or required herein.

[0108] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0109] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0110] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the knowledge aggregation method.

[0111] In some embodiments, the knowledge aggregation method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the knowledge aggregation method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the knowledge aggregation method in any other appropriate manner (e.g., by means of firmware).

[0112] 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.

[0113] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program 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.

[0114] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. 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.

[0115] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device 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 a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0116] The systems and techniques described herein may be implemented in a computing system that includes backend 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 frontend 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 backend components, middleware components, or frontend 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), a blockchain network, and the Internet.

[0117] A computing 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 client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0118] 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 described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0119] The above specific implementations do not constitute a limitation on the protection scope of the present invention. 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 invention should be included in the protection scope of the present invention.

Claims

1. A knowledge aggregation method, characterized in that: Applied to intelligent agents, including: Get the original data; Performing data processing on the original data to obtain first-stage data; Conducting in-depth analysis on the first-stage data to obtain the second-stage data; The second-stage data is verified to obtain the target technical data.

2. The method according to claim 1, characterized in that The original data is processed to obtain the first-stage data, including: Deduplication is performed on the original data to obtain deduplication data; Classifying the deduplicated data to obtain classified data; The classified data is cleaned, and the cleaned data is formatted to obtain first-stage data.

3. The method according to claim 1, characterized in that The first phase data is deeply analyzed to obtain the second phase data, including: Extracting time series data from the first phase data, and generating a technical report based on the time series data; Extracting technical keywords from the data of the first phase, rearranging and aggregating the technical keywords, and identifying technical trend keywords; The technical report and the technical trend keywords are subjected to correlation analysis to obtain the second-stage data.

4. The method according to claim 1, characterized in that: Verify the second phase data to obtain target technical data, including: Determine the comprehensive weight of the second stage data; Cross-validate the second-stage data to obtain data cross-scoring; According to the comprehensive weight and the data cross-scoring, the second-stage data is regenerated to obtain the target technical data.

5. The method according to claim 4, characterized in that Determine the comprehensive weight of the second phase data, including: Determining the trust weight of the data source of the original data; Determine the timeliness weight of the second-stage data according to the life cycle of the second-stage data; A comprehensive weight is determined according to the trust weight and the timeliness weight.

6. The method according to any one of claims 1 to 5, characterized in that Also includes: The target technical data is visualized and a text link of the target technical data is provided.

7. A knowledge aggregation device, characterized in that: Configured in the agent, including: An original data acquisition module, used to acquire original data; A first-stage data acquisition module, used for processing the original data to obtain first-stage data; The second-stage data acquisition module is used to perform in-depth analysis on the first-stage data to obtain the second-stage data; The target technical data acquisition module is used to verify the second-stage data to obtain the target technical data.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the knowledge aggregation method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the knowledge aggregation method according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program implements the knowledge aggregation method according to any one of claims 1 to 6.

Images