Information source screening method and system, terminal and medium

Abstract

The invention provides an information source screening method and system, a terminal and a medium, and the method comprises the steps: obtaining a domain keyword corresponding to a target domain, and searching a potential information source based on the domain keyword; integrating and classifying the potential information sources to obtain candidate information sources; and performing quality evaluation on the candidate information source to obtain a quality evaluation result, and determining a target information source based on the quality evaluation result. According to the method, the potential information sources are searched out, then the potential information sources are analyzed, the candidate information sources are determined, then the candidate information sources are evaluated, and the target information source is screened out, so that screening of the information sources can be realized based on a double screening mechanism, and the information sources with higher quality can be obtained.

Description

Technical Field

[0001] The present application relates to the field of information source screening technology, and in particular to an information source screening method, system, terminal and medium. Background Art

[0002] Currently, the source data published online suffers from issues such as insufficient authority and duplication of information. When source screening is required, it is typically done manually, which is unable to quickly, effectively, and accurately identify valid sources.

[0003] Therefore, the prior art still has defects. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method, system, terminal and medium for selecting a signal source in view of the above-mentioned defects of the prior art. The technical solution adopted by the present invention is as follows:

[0005] In a first aspect, the present invention provides a method for selecting a source of information, wherein the method comprises:

[0006] Obtain domain keywords corresponding to the target domain, and search for potential information sources based on the domain keywords;

[0007] Integrating and classifying the potential information sources to obtain candidate information sources;

[0008] Performing quality assessment on the candidate information sources to obtain a quality assessment result, and determining a target information source based on the quality assessment result.

[0009] In one implementation, obtaining domain keywords corresponding to the target domain includes:

[0010] Obtain the network search records corresponding to the target field;

[0011] determining a search frequency of each search term based on the network search records;

[0012] The field keyword is determined based on the search frequency.

[0013] In one implementation, the integrating and classifying the potential information sources to obtain candidate information sources includes:

[0014] Determining attribute information of the potential information source, wherein the attribute information is used to reflect key information in the potential information source;

[0015] Based on the attribute information, the potential information sources are integrated and classified to obtain the candidate information sources.

[0016] In one implementation, the integrating and classifying the potential information sources based on the attribute information to obtain the candidate information sources includes:

[0017] Based on the attribute information, using a pre-trained language model to determine the similarity between the potential information sources;

[0018] Based on the similarity, the potential information sources are integrated and classified to obtain the candidate information sources.

[0019] In one implementation, performing quality assessment on the candidate information source to obtain a quality assessment result includes:

[0020] Scoring the candidate information sources to obtain scoring information of the candidate information sources;

[0021] Based on the scoring information, a quality evaluation result of the candidate information source is obtained.

[0022] In one implementation, scoring the candidate information source to obtain scoring information of the candidate information source includes:

[0023] Obtaining publisher information of the candidate information source and / or browsing information of the candidate information source;

[0024] The weight information corresponding to the publisher information and / or the weight information corresponding to the browsing information are respectively obtained, and the score information of the candidate information source is determined based on the weight information corresponding to the publisher information and / or the weight information corresponding to the browsing information.

[0025] In one implementation, the method further includes:

[0026] After selecting the target information source, determining the information source keywords based on the target information source;

[0027] The domain keywords are updated based on the information source keywords.

[0028] In a second aspect, an embodiment of the present invention further provides a system for filtering information sources, wherein the system is used to implement the steps of the information source filtering method described in any one of the above solutions, and the system includes:

[0029] A potential information source search module is used to obtain domain keywords corresponding to the target domain and search for potential information sources based on the domain keywords;

[0030] a candidate information source determination module, configured to integrate and classify the potential information sources to obtain candidate information sources;

[0031] The candidate information source evaluation module is used to perform quality evaluation on the candidate information sources, obtain a quality evaluation result, and determine a target information source based on the quality evaluation result.

[0032] In a third aspect, an embodiment of the present invention further provides a terminal, wherein the terminal includes a memory, a processor, and a source screening program stored in the memory and runnable on the processor. When the processor executes the source screening program, the steps of the source screening method of any one of the above schemes are implemented.

[0033] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein a source screening program is stored on the computer-readable storage medium, and when the source screening program is executed by a processor, the steps of the source screening method described in any one of the above schemes are implemented.

[0034] Beneficial effect: Compared with the prior art, the present invention provides a method for screening information sources. The present invention first obtains the domain keywords corresponding to the target domain, and searches for potential information sources based on the domain keywords. Then, the potential information sources are integrated and classified to obtain candidate information sources. Finally, the quality of the candidate information sources is evaluated to obtain a quality evaluation result, and the target information source is determined based on the quality evaluation result. The present invention first searches for potential information sources, then analyzes the potential information sources to determine candidate information sources, and then evaluates the candidate information sources to screen out the target information sources. It can be seen that the present application can realize information source screening based on the dual screening mechanism, so as to obtain higher quality information sources. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0036] Figure 1 A diagram illustrating an application environment of the information source screening method provided by an embodiment of the present invention.

[0037] Figure 2 The present invention provides a flowchart of a preferred embodiment of the method for selecting a source of information.

[0038] Figure 3 The present invention provides a flowchart of the actual application of the information source screening method provided in the embodiment of the present invention.

[0039] Figure 4 A schematic diagram of the architecture of a signal source screening system provided by an embodiment of the present invention.

[0040] Figure 5 This is a functional block diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0042] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents, operations, or steps, nor must they be executed in the order described. For example, some operations or steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0043] It should be understood that the terms used in this specification are only for the purpose of describing particular embodiments and are not intended to limit the present invention. As used in the specification and appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0044] It should be understood that, to facilitate a clear description of the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, terms such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. For example, the first control information and the second control information are merely used to distinguish different control information and do not limit their order.

[0045] Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit them to be different.

[0046] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0047] The information source screening method provided by the embodiment of the present invention can be applied to Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store data that server 104 needs to process. The data storage system can be integrated with server 104, or placed on a cloud or other network server. The source screening method can be executed by terminal 102 or server 104, or by terminal 102 and server 104 working together.

[0048] The terminal 102 may be a smartphone, tablet computer, laptop computer, desktop computer, smart speaker, smart watch, IoT device, or portable wearable device. IoT device may be a smart speaker, smart TV, smart air conditioner, or smart car device. Portable wearable device may be a smart watch, smart bracelet, or head-mounted device.

[0049] The server 104 may be an independent physical server or a service node in a blockchain system, where each service node in the blockchain system forms a peer-to-peer network.

[0050] In addition, server 104 can also be a server cluster composed of multiple physical servers, and can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0051] The terminal 102 and the server 104 may be connected via Bluetooth, USB (Universal Serial Bus), a network or other communication connection methods, which are not limited in the present invention.

[0052] In some embodiments, as Figure 2 As shown, a method for filtering information sources is provided. Figure 1 The server or terminal in the Figure 1 The server and terminal in the method are executed in collaboration. Figure 1 The following steps are used as an example to illustrate the terminal execution in .

[0053] Step S100: Obtain domain keywords corresponding to the target domain, and search for potential information sources based on the domain keywords.

[0054] Combine Figure 3As shown in , this embodiment first obtains the domain keywords of the target field. The target field is used to determine the scope of the information source search. For example, if the target field is the semiconductor integrated circuit field, the information source for subsequent search and analysis is the information source in the semiconductor integrated circuit field. The domain keywords are information closely related to the target field in this embodiment. They can be technical terms well-known to the public in the target field, or they can be descriptive words that often appear in the target field, such as slogans. After determining the domain keywords, this embodiment can search for potential information sources based on the domain keywords. In actual application, this embodiment can use web crawler technology to crawl potential information sources based on domain keywords. In addition, the domain keywords of this embodiment can be one or more. When there are multiple domain keywords, this embodiment can search the domain keywords in combination, or use the domain keywords in sequence for search. When searching using domain keywords in sequence, this embodiment can set priority information for each domain keyword and search in sequence based on the priority information.

[0055] In one implementation, this embodiment includes the following steps when obtaining domain keywords:

[0056] Step S101: Obtain network search records corresponding to the target domain;

[0057] Step S102: determining the search frequency of each search term based on the network search records;

[0058] Step S103: Determine the domain keyword based on the search frequency.

[0059] Specifically, this embodiment may first obtain the network search records corresponding to the target domain, and the network search records may be traces of search terms under the target domain. This embodiment may obtain the search records within a preset time period, and then determine the search frequency of each search term within the preset time period. The higher the search frequency, the more times the search term is used, and the more it can reflect the characteristics of the target domain. Therefore, this embodiment may use the search term with the highest search frequency or a search frequency higher than a preset value as a domain keyword. In another implementation method, this embodiment may also determine the number of searches for each search term within a preset time period. The more searches a certain search term has, the more it can reflect the characteristics of the target domain. Therefore, this embodiment may use the search term with the highest search frequency or a search frequency higher than a preset value as a domain keyword. After determining the domain keyword, this embodiment may search for potential information sources based on the domain keyword.

[0060] Step S200: Integrate and classify the potential information sources to obtain candidate information sources.

[0061] After searching for potential information sources, since there are some non-authoritative and duplicate information sources among the potential information sources, in order to quickly screen out high-quality information sources, this embodiment can integrate and classify the potential information sources, with the goal of integrating similar potential information sources and finally obtaining candidate information sources.

[0062] In one implementation, this embodiment includes the following steps when integrating and classifying potential information sources:

[0063] Step S201: Determine attribute information of the potential information source, wherein the attribute information is used to reflect key information of the potential information source;

[0064] Step S202: Based on the attribute information, the potential information sources are integrated and classified to obtain the candidate information sources.

[0065] Specifically, this embodiment first obtains the attribute information of the potential source, and the attribute information is used to reflect the key information in the potential source. The key information can be the source information of the potential source, such as the source is news website A or forum B. The key information can also be the content in the potential source, such as the development prospects of the semiconductor industry or the release of a list of well-known companies in the semiconductor industry. After determining the attribute information, this embodiment can integrate and classify the potential sources based on the attribute information to obtain the candidate sources. In this embodiment, the process of integrating and classifying potential sources is essentially a deduplication process, and the determined attribute information can reflect the characteristics of the potential source to a certain extent. Therefore, this embodiment can analyze the attribute information of the potential source based on the large language model, so as to quickly determine the candidate source.

[0066] Specifically, based on the attribute information, a large language model is used to determine the similarity between the potential sources; then, based on the similarity, the potential sources are integrated and classified to obtain the candidate sources. For example, when the attribute information is the source information of the potential source, it can be combined with the release time of the potential source to determine that the potential sources released on the same news website or the same forum at the same time (or the same time period) are similar. At this time, the similar ones can be integrated together to obtain the candidate sources. In another implementation method, this embodiment can also use a large language model to determine the similarity between the potential sources based on the content in the potential sources reflected by the attribute information. For example, the title or subject of each potential source is obtained to compare whether the title or subject is similar, and then similar potential sources are integrated together to obtain candidate sources.

[0067] In addition, this embodiment can also establish a knowledge graph of potential sources in the target field based on the attribute information. The knowledge graph can be used to reflect the correlation between potential sources, and based on the correlation, the potential sources can be integrated and classified. In specific applications, this embodiment can perform feature extraction based on the content of the potential sources reflected in the attribute information, extract the feature information involved in each attribute information, such as a person's name, company information or key technical terms, etc. Based on the extracted characteristic information, a large language model is used to determine the correlation between the feature information, and then the correlation between the attribute information is obtained, thereby obtaining the correlation between potential sources, and then establishing a knowledge graph. By establishing a knowledge graph, this embodiment can more accurately analyze the relationship between potential sources, which is conducive to integrating and classifying similar or similar potential sources, thereby obtaining candidate sources.

[0068] Step S300: Perform quality assessment on the candidate information sources to obtain a quality assessment result, and determine a target information source based on the quality assessment result.

[0069] After obtaining the candidate signal sources, this embodiment may perform a quality assessment on the candidate signal sources to obtain a quality assessment result. The purpose of the quality assessment is to screen out high-quality signal sources from the candidate signal sources. To this end, this embodiment may perform a quality assessment on the candidate signal sources from multiple dimensions to obtain a high-quality target signal source.

[0070] In one implementation, the quality assessment of candidate information sources in this embodiment includes the following steps:

[0071] Step S301: Score the candidate information source to obtain score information of the candidate information source;

[0072] Step S302: Obtain a quality evaluation result of the candidate information source based on the scoring information.

[0073] Specifically, this embodiment can score candidate sources, and the scoring dimension can be the publisher information and / or browsing information of the candidate source. The credibility and authority of candidate sources published by different publishers are also different. Therefore, this embodiment can pre-set weight information for each type of publisher information. After determining the publisher information of the candidate source, it can be scored based on the weight information corresponding to the publisher information to obtain the scoring information of the candidate source. There are many contents that can be reflected in the browsing information. The browsing information can include the comment information, visit volume, etc. of the candidate source. The more comment information or visit volume, the more credible or popular the candidate source is. Therefore, this embodiment can also set weight information corresponding to different amounts of comment information or visit volume, and then obtain the scoring information of the candidate source based on the weight information. After obtaining the scoring information, this embodiment can obtain the quality assessment result of the candidate source, and the quality assessment result is the specific score of the candidate source.

[0074] In another implementation, this embodiment can also profile the users of a candidate source based on the comments from that source and determine their user information. This user information can reflect information such as their occupation and educational background. Specifically, this embodiment can collect the content described in the user's comments and their profile on websites or forums to create a user profile and obtain the user information. After determining the user's user information, this embodiment can match the user's user information with a database of talent in the target field to determine whether the user is a skilled person in the target field. This embodiment can analyze all comments under each candidate source to identify all skilled people who have posted comments under each candidate source, and then score the candidate source based on the number of skilled people who have posted comments. For example, the more skilled people who have posted comments under a candidate source, the higher the score for that source. Similarly, this embodiment can also utilize the aforementioned user profiling technology to analyze the type of publisher information in a candidate source, thereby quickly identifying the publisher. It can be seen that this embodiment evaluates candidate sources by determining their scoring information, and the evaluation dimensions include publisher information and / or browsing information of the candidate sources. Evaluation is performed from multiple dimensions, which is more objective and accurate, and also facilitates screening out high-quality target sources.

[0075] After obtaining the quality assessment results of each candidate source, the candidate source with the highest score can be directly used as the target source, or the candidate source with a score higher than a preset threshold or a high ranking can be used as the target source to generate a source list, thus completing the screening of high-quality sources. Furthermore, after screening out the target source, this embodiment determines the source keyword based on the target source; based on the source keyword, the domain keyword is updated, so that the potential source can be re-searched based on the updated domain keyword, and the source screening can be re-performed to improve the accuracy of the source screening. This embodiment constructs a closed-loop system in which domain keywords and source quality drive each other. Specifically, potential sources are captured through domain keywords, the quality of potential sources is evaluated, and domain keywords are iterated to form a spiral optimization path, which solves the limitations of traditional single searches. In addition, in this embodiment, the domain keywords are iteratively updated. Whenever the target source is screened out, the source keywords can be re-summarized based on the target source, and then the domain keywords can be updated using the source keywords. During an update, this embodiment can match source keywords with domain keywords. If there are multiple source keywords and multiple domain keywords, the source keywords and domain keywords are retrieved, and the words that differ from the domain keywords in the source keywords are directly added to the domain keywords to update the domain keywords. Furthermore, this embodiment can also construct a keyword library based on the domain keywords. In addition to the domain keywords of the target domain, this keyword library also includes domain keywords for other domains. All domain keywords are divided and stored by domain for easy access.

[0076] In summary, this embodiment first obtains the domain keywords corresponding to the target domain, and searches for potential information sources based on the domain keywords. Then, the potential information sources are integrated and classified to obtain candidate information sources. Finally, the quality of the candidate information sources is evaluated to obtain a quality evaluation result, and the target information source is determined based on the quality evaluation result. This embodiment first searches for potential information sources, then analyzes the potential information sources to determine candidate information sources, and then evaluates the candidate information sources to screen out the target information sources. It can be seen that this application can achieve information source screening based on the dual screening mechanism to obtain higher quality information sources.

[0077] Based on the above embodiment, the present invention further provides a source screening system, which is used to implement the steps of the source screening method described in the above method embodiment, such as Figure 4As shown in , the system of this embodiment includes: a potential information source search module 10, a candidate information source determination module 20, and a candidate information source evaluation module 30. Specifically, the potential information source search module 10 is used to obtain domain keywords corresponding to the target domain and search for potential information sources based on the domain keywords. The candidate information source determination module 20 is used to integrate and classify the potential information sources to obtain candidate information sources. The candidate information source evaluation module 30 is used to perform quality assessment on the candidate information sources, obtain quality assessment results, and determine the target information source based on the quality assessment results.

[0078] In one implementation, the potential information source search module 10 includes:

[0079] A search record acquisition unit, used to acquire network search records corresponding to the target field;

[0080] A search frequency determination unit, configured to determine the search frequency of each search term based on the network search record;

[0081] A domain keyword determining unit is configured to determine the domain keyword based on the search frequency.

[0082] In one implementation, the candidate information source determination module 20 includes:

[0083] an attribute information determining unit, configured to determine attribute information of the potential information source, wherein the attribute information is used to reflect key information in the potential information source;

[0084] The information source integration and classification unit is used to integrate and classify the potential information sources based on the attribute information to obtain the candidate information sources.

[0085] In one implementation, the information source integration and classification unit includes:

[0086] a similarity analysis subunit, configured to determine similarities between the potential information sources based on the attribute information and using a large language model;

[0087] The candidate information source determination subunit is configured to integrate and classify the potential information sources based on the similarity to obtain the candidate information sources.

[0088] In one implementation, the candidate information source evaluation module 30 includes:

[0089] A source scoring unit, configured to score the candidate source to obtain scoring information of the candidate source;

[0090] A quality evaluation unit is configured to obtain a quality evaluation result of the candidate information source based on the scoring information.

[0091] In one implementation, the information source scoring unit includes:

[0092] An information acquisition subunit, configured to acquire publisher information and / or browsing information of the candidate information source;

[0093] The scoring execution subunit is configured to respectively obtain weight information corresponding to the publisher information and / or browsing information, and determine the scoring information of the candidate information source based on the weight information.

[0094] In one implementation, the system further includes:

[0095] an information source keyword determining unit, configured to determine an information source keyword based on the target information source after the target information source is screened out;

[0096] A domain keyword updating unit is configured to update the domain keyword based on the information source keyword.

[0097] The working principles of each module in the information source screening system of this embodiment are the same as the principles of each step in the above method embodiment, and will not be repeated here.

[0098] Each module in the above-mentioned source screening system can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of the processor in the terminal in hardware form, or can be stored in the terminal's memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0099] Each module in the above-mentioned source screening system can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of the processor in the terminal in hardware form, or can be stored in the terminal's memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0100] In some embodiments, a terminal is provided, whose internal structure diagram can be as follows: Figure 5As shown. The terminal includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the terminal is used to provide computing and control capabilities. The memory of the terminal includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the terminal is used to exchange information between the processor and an external device. The communication interface of the terminal is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for source screening is implemented. The display unit of the terminal is used to form a visually visible image, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the terminal can be a touch layer covering the display screen, or a button, trackball or touchpad set on the terminal housing, or an external keyboard, touchpad or mouse, etc.

[0101] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the terminal to which the solution of the present invention is applied. The specific terminal may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0102] In some embodiments, a terminal is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0103] Obtain domain keywords corresponding to the target domain, and search for potential information sources based on the domain keywords;

[0104] Integrating and classifying the potential information sources to obtain candidate information sources;

[0105] Performing quality assessment on the candidate information sources to obtain a quality assessment result, and determining a target information source based on the quality assessment result.

[0106] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0107] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0108] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0109] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for selecting a source of information, characterized in that: The method comprises the following steps: Obtain domain keywords corresponding to the target domain, and search for potential information sources based on the domain keywords; Integrating and classifying the potential information sources to obtain candidate information sources; Performing quality assessment on the candidate information sources to obtain a quality assessment result, and determining a target information source based on the quality assessment result.

2. The information source screening method according to claim 1, characterized in that: The obtaining of domain keywords corresponding to the target domain includes: Obtain the network search records corresponding to the target field; determining a search frequency of each search term based on the network search records; A field keyword corresponding to the target field is determined based on the search frequency.

3. The information source screening method according to claim 1, characterized in that: The integrating and classifying the potential information sources to obtain candidate information sources includes: Determining attribute information of the potential information source, wherein the attribute information is used to reflect key information in the potential information source; Based on the attribute information, the potential information sources are integrated and classified to obtain the candidate information sources.

4. The information source screening method according to claim 3, characterized in that: The integrating and classifying the potential information sources based on the attribute information to obtain the candidate information sources includes: Based on the attribute information, using a pre-trained language model to determine the similarity between the potential information sources; Based on the similarity, the potential information sources are integrated and classified to obtain the candidate information sources.

5. The information source screening method according to claim 1, wherein: The performing quality assessment on the candidate information source to obtain a quality assessment result includes: Scoring the candidate information sources to obtain scoring information of the candidate information sources; Based on the scoring information, a quality evaluation result of the candidate information source is obtained.

6. The information source screening method according to claim 5, characterized in that: Scoring the candidate information sources to obtain scoring information of the candidate information sources includes: Obtaining publisher information of the candidate information source and / or browsing information of the candidate information source; The weight information corresponding to the publisher information and / or the weight information corresponding to the browsing information are respectively obtained, and the score information of the candidate information source is determined based on the weight information corresponding to the publisher information and / or the weight information corresponding to the browsing information.

7. The information source screening method according to claim 1, characterized in that: The method further comprises: After selecting the target information source, determining the information source keywords based on the target information source; The domain keywords are updated based on the information source keywords.

8. A source screening system, characterized in that: The system is used to implement the steps of the information source screening method according to any one of claims 1 to 7, and the system includes: A potential information source search module is used to obtain domain keywords corresponding to the target domain and search for potential information sources based on the domain keywords; a candidate information source determination module, configured to integrate and classify the potential information sources to obtain candidate information sources; The candidate information source evaluation module is used to perform quality evaluation on the candidate information sources, obtain a quality evaluation result, and determine a target information source based on the quality evaluation result.

9. A terminal, characterized in that: The terminal includes a memory, a processor, and an information source screening program stored in the memory and executable on the processor. When the processor executes the information source screening program, the steps of the information source screening method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores an information source screening program, and when the information source screening program is executed by the processor, the steps of the information source screening method according to any one of claims 1 to 7 are implemented.

Images