News keyword library construction method and device and storage medium

Abstract

The invention relates to the field of information processing, and discloses a news keyword library construction method and device and a storage medium, and the method comprises the steps: for each newly-added keyword, determining keyword news corresponding to the newly-added keyword in a first preset period, and according to the keyword news, judging whether the newly-added keyword is valid in traffic information; and updating the news keyword library according to the newly-added keywords in response to the fact that the newly-added keywords are valid on the traffic information. According to the technical scheme, the news keyword library related to the traffic information is periodically updated, so that the traffic information can be provided for the user based on the news keyword library.

Description

Technical Field

[0001] The present invention relates to the field of information processing, and in particular to a news keyword library construction method, device and storage medium. Background Art

[0002] Traffic information primarily includes road conditions, traffic restrictions, traffic controls, traffic incidents, traffic weather, and road environment information. Currently, the internet, as a convenient and efficient information carrier, has attracted a large number of government agencies, professional information providers, and individual users to publish traffic information on professional websites, forums, and microblogging platforms.

[0003] However, the volume of internet news continues to grow with the number of users, creating a massive information load. Furthermore, not every piece of internet news is relevant to traffic. Analyzing every piece of internet news would waste significant resources and slow down news recognition. Using fixed keywords to filter internet news would also result in unreliable traffic information and miss significant amounts of valid news.

[0004] In view of this, the present invention is proposed. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention provides a news keyword library construction method, device and storage medium, which realizes the effect of combining existing news and periodically updating the news keyword library related to traffic information, so as to provide users with traffic information based on the news keyword library.

[0006] An embodiment of the present invention provides a method for constructing a news keyword library, the method comprising:

[0007] For each newly added keyword, determining keyword news corresponding to the newly added keyword within a first preset period, and judging whether the newly added keyword is valid in traffic information based on the keyword news;

[0008] In response to the newly added keyword being valid in the traffic information, the news keyword library is updated according to the newly added keyword.

[0009] An embodiment of the present invention provides an electronic device, comprising:

[0010] processor and memory;

[0011] The processor is configured to execute the steps of the method for constructing a news keyword library described in any embodiment by calling the program or instruction stored in the memory.

[0012] An embodiment of the present invention provides a computer-readable storage medium storing a program or instruction. The program or instruction enables a computer to execute the steps of the method for constructing a news keyword library described in any embodiment.

[0013] The embodiments of the present invention have the following technical effects:

[0014] By determining the keyword news corresponding to each new keyword within the first preset period for each new keyword, part of the news corresponding to the new keyword can be obtained from the massive amount of news, and based on the keyword news, whether the new keyword is effective in traffic information is judged, and targeted analysis is performed in combination with the keyword news corresponding to the new keyword to judge the traffic-related reliability of the new keyword. Multi-level effective analysis can be performed through the traffic information recognition model. In response to the new keyword being effective in traffic information, the news keyword library is updated according to the new keyword to expand the news keyword library, so that the news keyword library related to traffic information can keep up with the changes of the times. In addition, the new keywords can also be actually verified to ensure the effectiveness of the new keywords in actual applications, thereby achieving the effect of periodically updating the news keyword library related to traffic information in combination with existing news. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 This is a flowchart of a method for building a news keyword library provided by an embodiment of the present invention;

[0017] Figure 2 This is a flowchart of another method for building a news keyword library provided by an embodiment of the present invention;

[0018] Figure 3 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention are described clearly and completely below. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are also within the scope of protection of the present invention.

[0020] The news keyword library construction method provided by the embodiment of the present invention is mainly applicable to extracting traffic information from news and providing it to vehicles for the attention of vehicle drivers. The news keyword library construction method provided by the embodiment of the present invention can be executed by an electronic device.

[0021] Figure 1 This is a flow chart of a method for building a news keyword library provided by an embodiment of the present invention. Figure 1 , the news keyword library construction method specifically includes:

[0022] S110 : For each newly added keyword, determine keyword news corresponding to the newly added keyword within a first preset period, and determine whether the newly added keyword is valid in traffic information based on the keyword news.

[0023] The first preset period is a pre-set period for searching to add keywords to the news keyword library. New keywords are keywords discovered during the first preset period that are not already in the news keyword library. The news keyword library is a database constructed to filter news for rapid extraction of traffic information. Keyword news is news that contains a new keyword during the first preset period.

[0024] Specifically, for each newly added keyword, all news articles within a first preset period are searched using the newly added keyword, and news articles containing the newly added keyword are designated as keyword news articles corresponding to the newly added keyword. Furthermore, the keyword news articles are analyzed to determine whether the newly added keyword is effective in traffic information. For example, the traffic information content of the keyword news articles is determined, and then the effectiveness of the newly added keyword in traffic information is determined using preset rules. Alternatively, actual vehicle verification can be used to determine whether the newly added keyword is effective in traffic information, that is, whether it is truly strongly correlated with traffic information.

[0025] Based on the above example, before determining the keyword news corresponding to each newly added keyword within the first preset period and judging whether the newly added keyword is effective in traffic information based on the keyword news, the newly added keyword can also be preliminarily obtained by the following methods, specifically:

[0026] According to the first preset period, news to be screened within the first preset period is obtained, and new keywords are determined based on the news to be screened.

[0027] The news to be screened is all the news within the first preset period.

[0028] Specifically, all news within a first preset period is periodically obtained as news to be screened. Then, keyword extraction and mining are performed on the news to be screened. For each extracted and mined keyword, a determination is made as to whether the extracted and mined keyword is already in the news keyword library. If not, the keyword may be added as a new keyword; if so, it is not processed.

[0029] S120: In response to the newly added keyword being valid in the traffic information, the news keyword library is updated according to the newly added keyword.

[0030] Specifically, if the newly added keyword is valid, it means that the newly added keyword is highly correlated with the traffic information, and therefore, the newly added keyword can be added to the news keyword library.

[0031] Based on the above example, after the news keyword library is updated according to the newly added keywords, the updated news keyword library can be used, for example, to push traffic information to the target device using the updated news keyword library. Specifically, the following can be used:

[0032] According to the updated news keyword library, valid news corresponding to the news keyword library is obtained in real time, and news traffic information is determined based on the valid news, and the news traffic information is pushed to the corresponding target device.

[0033] Valid news refers to the portion of real-time news that matches news keywords in the updated news keyword library. News traffic information refers to traffic information extracted from valid news. Target devices are devices near the location and time of the news traffic information, specifically those that require news traffic information alerts. These devices can include mobile phones, in-car computers, and can also be installed on various vehicles.

[0034] Specifically, using the updated news keyword library, real-time news is filtered to obtain news related to each news keyword in the news keyword library as valid news. Furthermore, traffic information is extracted from the valid news, such as location, direction, and time information, as news traffic information. For each piece of news traffic information, the device associated with the news traffic information, i.e., the target device, is pushed to the corresponding target device, e.g., a device traveling at the time or predicted to travel at the location mentioned in the news traffic information, to draw the attention of the target device's user.

[0035] It is understandable that the news keyword library construction method in the above example is applied to the field of traffic information extraction. Of course, the news keyword library construction method of this example can also be applied to other technical fields that require confirmation and updating of news keywords.

[0036] Based on the above example, before updating the news keyword library based on the newly added keywords, you can also pre-verify the newly added keywords through automated testing, specifically:

[0037] Determine the corresponding verification news based on the newly added keywords, and determine the information to be verified based on the verification news;

[0038] For each verified news item, determine the timeliness of the verified news item;

[0039] In response to the timeliness being predictive or mixed, automatic verification is performed based on simulated navigation according to the information to be verified to determine the validity of the verified news;

[0040] In response to the timeliness of the verification news being delayed, the information to be verified is sent to each information-related user, response information from each information-related user is received, and the validity of the verification news is determined based on the response information from each information-related user;

[0041] Determine the effective proportion of news based on the effectiveness of each verified news;

[0042] In response to the effective proportion of news being greater than or equal to the preset proportion, an operation of updating the news keyword library according to the newly added keywords is triggered.

[0043] Verification news is news used to verify the usability of new keywords in actual applications. It can be news related to the new keywords within the first verification period after the new keywords are confirmed to be valid. The first verification period is a pre-set time period for validating valid new keywords. Information to be verified is information extracted from traffic information in the verification news, including the time, location, and event to be verified. Timeliness can be predictive, delayed, or mixed. Predictive news is news that announces events that have not yet occurred, delayed news is news that reports on completed events, and mixed news is news released while ongoing events are ongoing. Information-associated users are vehicles located near the location and time of verification in the delayed verification information, i.e., vehicles requiring verification assistance. Response information is feedback from information-associated users on the validity of the verification information. Validity can be either true or false. The news validity ratio is the proportion of true and valid verified news to the total number of verified news. The preset ratio is a pre-set ratio used to determine whether the new keywords have been verified.

[0044] Specifically, before the news keyword library is updated according to the newly added keywords, only a simple validity screening is performed using past news, and no verification is performed using real-time news. In order to ensure the effectiveness of the newly added keywords, a verification process is introduced. For each newly added keyword, the same method can be used for verification, and one of them is used as an example for explanation. During the first verification time period after determining that the newly added keyword is valid, the news corresponding to the newly added keyword is obtained in real time as verification news. There can be multiple verification news, and they can be subsequently verified as a whole. Determine whether the verification news is related to traffic information. If so, extract the traffic information to obtain the information to be verified. For each verification news, the timeliness of the verification news can be determined in combination with the information to be verified. If the timeliness is predictive or mixed, the information to be verified can be automatically verified based on simulated navigation to obtain the validity of the verification news. If the timeliness of the verified news is lagging, it means that the verified news has already occurred and cannot be automatically verified. The information-associated users corresponding to the information to be verified can be determined. The information-associated users can be the vehicle users located around the location to be verified during the time to be verified in the information to be verified. The information to be verified is sent to each information-associated user to inquire whether the event to be verified in the information to be verified actually occurred during the time to be verified and at the location to be verified, and then receive the response information of each information-associated user. After receiving the response information of each information-associated user, the number of users who believe that the information to be verified is true and valid and the number of users who believe that the information to be verified is false and invalid can be counted. The validity of the verified news can be analyzed using preset rules (for example, the minority obeys the majority, the number of users who feedback that the information to be verified is true and valid exceeds the first threshold and is considered valid, or the number of users who feedback that the information to be verified is false and invalid exceeds the second threshold and is considered invalid, etc.). In this way, the validity of each verified news corresponding to the newly added keyword can be obtained. The number of verified news with true and valid validity divided by the total number of verified news can be used to obtain the effective news ratio of the newly added keyword. If the effective news ratio is greater than or equal to the preset ratio, it means that the new keyword has passed the verification, and the operation of updating the news keyword library based on the new keyword can be triggered. If the effective news ratio is less than the preset ratio, it means that the new keyword verification fails. In order to ensure the validity of the news keywords in the news keyword library, the new keyword cannot be used to update the news keyword library.

[0045] The present invention has the following technical effects: by determining the keyword news corresponding to the new keyword within the first preset period for each new keyword, a part of the news corresponding to the new keyword is obtained from a large amount of news, and based on the keyword news, whether the new keyword is effective in traffic information is judged, and targeted analysis is performed in combination with the keyword news corresponding to the new keyword to judge the traffic-related reliability of the new keyword. In response to the new keyword being effective in traffic information, the news keyword library is updated according to the new keyword to expand the news keyword library, so that the news keyword library related to traffic information can keep up with the changes of the times. In addition, the new keyword can also be actually verified to ensure the effectiveness of the new keyword in actual use, thereby achieving the effect of periodically updating the news keyword library related to traffic information in combination with existing news.

[0046] Figure 2 This is a flowchart of another method for building a news keyword library provided by an embodiment of the present invention. Figure 2 , the news keyword library construction method specifically includes:

[0047] S210: For each newly added keyword, determine the keyword news corresponding to the newly added keyword within a first preset period, and judge whether the newly added keyword is valid in traffic information based on the keyword news.

[0048] Based on the above example, the following method can be used to determine whether the new keywords are effective in traffic information based on keyword news:

[0049] Identifying the keyword news based on the first traffic information identification model to determine the first traffic information content;

[0050] In response to the first traffic information content being greater than or equal to a target threshold, determining that the newly added keyword is valid on the traffic information;

[0051] In response to the first traffic information content being less than the target threshold, identifying the keyword news according to the second traffic information identification model to determine the second traffic information content;

[0052] In response to the second traffic information content being greater than or equal to the target threshold, determining that the newly added keyword is valid on the traffic information;

[0053] In response to the second traffic information content being less than the target threshold, it is determined that the newly added keyword is invalid in the traffic information.

[0054] Among them, the first traffic information recognition model is a model used to roughly analyze whether the news contains traffic information. The second traffic information recognition model is a model used to accurately analyze whether the news contains traffic information. The first traffic information recognition model is less effective than the second traffic information recognition model in identifying traffic information, but is faster. Both the first traffic information recognition model and the second traffic information recognition model can be neural network models or intelligent entities, etc. The first traffic information content is the ratio of the number of keyword news containing traffic information identified by the first traffic information recognition model to the total amount of keyword news. The second traffic information content is the ratio of the number of keyword news containing traffic information identified by the second traffic information recognition model to the total amount of keyword news. The target threshold is a pre-set ratio used to determine whether the newly added keywords are effective in traffic information.

[0055] Specifically, keyword news is input into the first traffic information recognition model to identify keyword news. It can be determined whether each keyword news contains traffic information. The number of keyword news containing traffic information is divided by the total amount of keyword news to obtain the first traffic information content. If the first traffic information content is greater than or equal to the target threshold, it is determined that the newly added keyword is valid for traffic information. If the first traffic information content is less than the target threshold, a more accurate model can be used for further investigation, that is, keyword news is input into the second traffic information recognition model to identify keyword news. It can be determined whether each keyword news contains traffic information. The number of keyword news containing traffic information is divided by the total amount of keyword news to obtain the second traffic information content. If the second traffic information content is greater than or equal to the target threshold, it is determined that the newly added keyword is valid for traffic information. If the second traffic information content is less than the target threshold, it is determined that the newly added keyword is invalid for traffic information.

[0056] Optionally, the target threshold may include a first recognition threshold and a second recognition threshold. The first recognition threshold is used for the first traffic information recognition model, and the second recognition threshold is used for the second traffic information recognition model. Usually, the second recognition threshold is greater than or equal to the first recognition threshold. However, the specific sizes of the first recognition threshold and the second recognition threshold can also be set according to actual needs.

[0057] Optionally, a second traffic information recognition model is used for identification. In order to reduce the amount of data processing, the keyword news identified as invalid by the first traffic information recognition model can be identified for the second time, that is, the second traffic information recognition model is used for identification. At this time, the sum of the number of keyword news containing traffic information identified by the first traffic information recognition model and the number of keyword news containing traffic information identified by the second traffic information recognition model is divided by the total amount of keyword news, which is used as the second traffic information content.

[0058] Because the first traffic information recognition model has a faster recognition speed but lower accuracy than the second traffic information recognition model, the first traffic information recognition model is used for initial screening. If the initial screening passes, there is no need for more precise recognition, which can effectively improve the recognition speed. If the initial screening fails, the second traffic information recognition model is used for re-screening to ensure the accuracy of the screening. Therefore, this method can improve the screening speed while maintaining the screening accuracy.

[0059] S220: In response to the newly added keyword being valid in the traffic information, obtaining verification news corresponding to the newly added keyword within a first verification time period corresponding to the newly added keyword.

[0060] Specifically, for each newly added keyword, the same method can be used for verification, and one of them is used as an example for explanation. In response to the newly added keyword being valid in traffic information, news corresponding to the newly added keyword is obtained in real time during the first verification time period as verification news.

[0061] S230: Extract traffic information based on the verification news and determine the information to be verified corresponding to the newly added keywords.

[0062] Specifically, it is determined whether the verification news is related to the traffic information. If so, the traffic information is extracted to obtain the information to be verified.

[0063] S240: Send the information to be verified to each verification user, receive feedback information from each verification user, and determine the verification result of the newly added keyword based on the feedback information from each verification user.

[0064] The verifying user can be a user who was present at the time and location of the information to be verified, or a user who was expected to be present at the time and location of the information to be verified. Feedback information is the user's feedback on the validity of the information to be verified, which can be true or false. The verification result can be either passed or failed.

[0065] Specifically, based on the historical itineraries, planned itineraries, and / or actual locations of each user's vehicle, the corresponding verification users can be determined. The verification information can then be sent to each verification user, and feedback from each verification user can be received. The feedback from each verification user is then counted, and the verification results for the newly added keywords are determined according to pre-set statistical rules.

[0066] Based on the above example, the verification results of the newly added keywords can be determined according to the feedback information of each verification user in the following way:

[0067] In response to the verification users including a highly trusted user, determining the verification result of the newly added keyword based on the feedback information of each highly trusted user;

[0068] In response to the fact that no highly trusted user is included among the verified users, the feedback information of the verified users is classified according to information type to determine the information type of each feedback information; and the verification result of the newly added keyword is determined based on the feedback information corresponding to each information type and the passing threshold.

[0069] Highly trusted users are those whose feedback is highly credible. These can include personnel specializing in road verification or users whose feedback accuracy exceeds a threshold (e.g., 95%). Information types can be voice-to-text or photo-based. Voice-to-text is a simple text or voice description of the feedback, while photo-based feedback is a photo taken and uploaded on-site. The pass threshold is the threshold used to determine the verification result for different information types. The pass thresholds for different information types can be different or the same.

[0070] Specifically, determine whether highly trusted users are included in each verified user. If included, the feedback information of highly trusted users can be used to analyze whether the verification result of the newly added keyword is verified. The analysis process can be that the minority obeys the majority, and the proportion of valid feedback information reaches a certain threshold to be considered valid. If not included, the feedback information of each verified user is classified according to the information type to determine the information type of each feedback information. For each information type, the feedback information corresponding to the information type is analyzed to determine the ratio of the number of valid information to the number of feedback information corresponding to the information type, and the ratio is compared with the passing threshold to obtain a comparison result. By combining the comparison results corresponding to each information type, the verification result of the newly added keyword can be obtained.

[0071] Based on the above example, the information types include voice and text types and photo and video types, and the pass thresholds include a first pass threshold corresponding to the voice and text type and a second pass threshold corresponding to the photo and video type; if the second pass threshold is lower than the first pass threshold, the verification result of the newly added keyword can be determined based on the feedback information corresponding to each information type and the pass threshold in the following manner:

[0072] In the case where the information type is a voice and text type, determining a first feedback pass rate according to each piece of feedback information corresponding to the voice and text type;

[0073] In the case where the information type is a photo-taking feedback type, determining a second feedback pass rate according to each piece of feedback information corresponding to the photo-taking feedback type;

[0074] In response to the first feedback pass rate being greater than or equal to the first pass threshold or the second feedback pass rate being greater than or equal to the second pass threshold, determining that the verification result of the newly added keyword is verification passed;

[0075] In response to the first feedback pass rate being less than the first pass threshold and the second feedback pass rate being less than the second pass threshold, it is determined that the verification result of the newly added keyword is verification failure.

[0076] The first feedback pass rate is the ratio of the number of voice-to-text feedback messages that deemed verification information valid to the total number of voice-to-text feedback messages corresponding to the verification information. The second feedback pass rate is the ratio of the number of photo-return feedback messages that deemed verification information valid to the total number of photo-return feedback messages corresponding to the verification information. The first pass threshold is a pre-set threshold for determining whether the first feedback pass rate for voice-to-text has passed verification. The second pass threshold is a pre-set threshold for determining whether the second feedback pass rate for photo-return has passed verification.

[0077] Specifically, if the information type is voice and text, the total amount of feedback information corresponding to the voice and text type and the number of verification information deemed valid are counted. The ratio of the number of verification information deemed valid to the total amount of feedback information corresponding to the voice and text type is used as the first feedback pass rate. If the information type is photo and upload, the total amount of feedback information corresponding to the photo and upload type and the number of verification information deemed valid are counted. The ratio of the number of verification information deemed valid to the total amount of feedback information corresponding to the photo and upload type is used as the second feedback pass rate. If at least one of the first feedback pass rate and the second feedback pass rate meets the pass threshold requirement, the verification result for the newly added keyword is considered passed. Specifically, if the first feedback pass rate is greater than or equal to the first pass threshold or the second feedback pass rate is greater than or equal to the second pass threshold, the verification result for the newly added keyword is determined to be passed. If the first feedback pass rate is less than the first pass threshold and the second feedback pass rate is less than the second pass threshold, the verification result for the newly added keyword is determined to be failed.

[0078] S250: In response to the verification result being a passed verification, the news keyword library is updated according to the newly added keywords.

[0079] Specifically, if the verification result is "passed," it means the newly added keyword is valid and has been verified by news reports within the first verification period. Therefore, it can be determined that the newly added keyword is strongly related to traffic information and is authentic and reliable. Therefore, the newly added keyword is updated to the news keyword database. If the verification result is "failed," no further steps are required.

[0080] Based on the above example, we can also perform expiration judgment on the news keywords in the news keyword library, that is, to judge whether the news keywords are still applicable to traffic information extraction. This is because some words have the characteristics of the times or are popular. Therefore, it is necessary to judge whether the news keywords are expired and need to be deleted. Specifically, it can be:

[0081] Based on the second preset period, obtaining the existence time of each news keyword in the news keyword library;

[0082] For each news keyword, in response to the existence time being greater than the preset time, obtaining the identified news corresponding to the news keyword within the second verification time period;

[0083] Identify the identified news according to a preset traffic information identification model to determine the third traffic information content;

[0084] In response to the third traffic information content being less than a deletion threshold, the news keyword is deleted from the news keyword library.

[0085] Among them, the second preset period is the period for triggering the deletion of news keywords in the news keyword library. The existence duration is the length of time from the time when the news keyword is added to the news keyword library to the current time. The second verification time period is the time period before the current time, which is used to judge the recent usage of news keywords. Identified news is news related to the news keywords that triggered the deletion detection within the second verification time period. The preset traffic information recognition model is a model used to determine whether the news contains traffic information. It can be a neural network model, a language processing model, etc., or it can be the first traffic information recognition model or the second traffic information recognition model in the above example. The third traffic information content is the ratio of the number of identified news containing traffic information identified by the preset traffic information recognition model to the total amount of identified news. The deletion threshold is a pre-set threshold that always triggers the deletion of news keywords, such as 10% or 20%.

[0086] Specifically, when the second preset period is reached, the existence time of each news keyword in the news keyword library is obtained. For each news keyword, determine whether the existence time is greater than the preset time. If it is not greater than, it means that the news keyword was recently added and there is no need to trigger deletion detection. If it is greater than, deletion detection needs to be triggered. The deletion detection method is to obtain all the news in the second verification time period before the current time, and use the part of the news corresponding to the news keyword as the identified news. The identified news is input into the preset traffic information recognition model, and the identified news is subjected to traffic information recognition. The ratio of the number of identified news containing traffic information to the total amount of identified news is used as the third traffic information content. If the third traffic information content is less than the deletion threshold, it means that the recent use effect of the news keyword is not good. Therefore, the deletion operation is triggered to delete the news keyword from the news keyword library.

[0087] Based on the above example, we can also consider some holiday event cancellation announcements to process the news keyword library, specifically:

[0088] For each news keyword in the news keyword library, determine whether the news keyword is a festival activity type;

[0089] In response to the news keyword being a festival activity type, determining whether the news keyword is explicitly cancelled based on official news corresponding to the news keyword;

[0090] In response to the news keyword being explicitly cancelled, the news keyword is deleted from the news keyword library.

[0091] The festival event type can be a festival or a large-scale event, such as a marathon, a lantern festival, National Day, or Spring Festival. Official news refers to news from large-scale event groups, event groups, and administrative departments at all levels.

[0092] Specifically, for each news keyword in the news keyword database, a determination is made as to whether the news keyword is related to a holiday event, so that official news can be retrieved later. If the news keyword is related to a holiday event, the official news corresponding to the news keyword is further retrieved to determine whether the news keyword has been explicitly removed. If the news keyword has been explicitly removed, it indicates that there will be no traffic information in the news corresponding to this news keyword in the future. Therefore, the news keyword is deleted from the news keyword database.

[0093] The present invention has the following technical effects: in response to the new keywords being valid in traffic information, verification news corresponding to the new keywords is obtained within the first verification time period corresponding to the new keywords, traffic information is extracted based on the verification news, information to be verified corresponding to the new keywords is determined, the information to be verified is sent to each verification user, feedback information from each verification user is received, and verification results of the new keywords are determined based on the feedback information from each verification user. In response to the verification result being passed, the news keyword library is updated based on the new keywords, so that after determining that the new keywords are valid in combination with past news, news verification in the first verification time period is added to ensure the authenticity and reliability of the new keywords, and the validity judgment of the new keywords is realized in combination with past news. In addition, verification logic is introduced for the valid new keywords, thereby improving the accuracy and reliability of the keywords in the news keyword library, and thereby improving the efficiency of providing traffic information to users based on the news keyword library.

[0094] Figure 3 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, the electronic device 300 includes one or more processors 301 and a memory 302 .

[0095] The processor 301 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 300 to perform desired functions.

[0096] The memory 302 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 301 may execute the program instructions to implement the news keyword library construction method of any embodiment of the present invention described above and / or other desired functions. Various contents such as initial external parameters, thresholds, etc. may also be stored in the computer-readable storage medium.

[0097] In one example, the electronic device 300 may further include an input device 303 and an output device 304, which are interconnected via a bus system and / or other connection mechanisms (not shown). The input device 303 may include, for example, a keyboard, a mouse, etc. The output device 304 may output various information to the outside, including warning information, braking force, etc. The output device 304 may include, for example, a display, a speaker, a printer, a communication network, and remote output devices connected thereto.

[0098] Of course, to simplify, Figure 3 Only some of the components related to the present invention in the electronic device 300 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, the electronic device 300 may further include any other appropriate components according to specific application scenarios.

[0099] In addition to the above methods and devices, an embodiment of the present invention may also be a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor, the processor executes the steps of the news keyword library construction method provided by any embodiment of the present invention.

[0100] The computer program product may be written in any combination of one or more programming languages ​​to implement the operations of embodiments of the present invention, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as C or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's computing device, as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0101] In addition, an embodiment of the present invention may also be a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, the processor executes the steps of the news keyword library construction method provided by any embodiment of the present invention.

[0102] The computer-readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can, for example, include but is not limited to a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable 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 thereof.

[0103] It should be noted that the terms used in the present invention are only for describing specific embodiments and are not intended to limit the scope of this application. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "an", "a kind of" and / or "the" do not specifically refer to the singular and may also include the plural. The terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method or device comprising a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also include elements inherent to such process, method or device. In the absence of further restrictions, the elements defined by the sentence "comprise a..." do not exclude the presence of other identical elements in the process, method or device comprising the elements.

[0104] It should also be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, they cannot be understood as limitations on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be a communication between the internal parts of two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0105] 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 above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a news keyword library, characterized in that: include: For each newly added keyword, determining keyword news corresponding to the newly added keyword within a first preset period, and judging whether the newly added keyword is valid in traffic information based on the keyword news; In response to the newly added keyword being valid in the traffic information, the news keyword library is updated according to the newly added keyword.

2. The method according to claim 1, characterized in that The determining, based on the keyword news, whether the newly added keyword is effective in traffic information includes: Identifying the keyword news according to the first traffic information identification model to determine the first traffic information content; In response to the first traffic information content being greater than or equal to a target threshold, determining that the newly added keyword is valid on the traffic information; In response to the first traffic information content being less than the target threshold, identifying the keyword news according to a second traffic information identification model to determine a second traffic information content; In response to the second traffic information content being greater than or equal to the target threshold, determining that the newly added keyword is valid in the traffic information; In response to the second traffic information content being less than the target threshold, it is determined that the newly added keyword is invalid in the traffic information.

3. The method according to claim 1, characterized in that Before updating the news keyword library according to the newly added keywords, the method further includes: Acquiring verification news corresponding to the newly added keyword within a first verification time period corresponding to the newly added keyword; Extracting traffic information based on the verification news to determine the information to be verified corresponding to the newly added keyword; Sending the information to be verified to each verification user, receiving feedback information from each verification user, and determining the verification result of the newly added keyword based on the feedback information from each verification user; In response to the verification result being a passed verification, the operation of updating the news keyword library according to the newly added keywords is triggered.

4. The method according to claim 3, characterized in that Determining the verification result of the newly added keyword based on the feedback information of each verification user includes: In response to the verification users including a highly trusted user, determining the verification result of the newly added keyword according to the feedback information of each highly trusted user; In response to the fact that no highly trusted user is included among the verified users, the feedback information of the verified users is classified according to information type to determine the information type of each feedback information; and the verification result of the newly added keyword is determined based on the feedback information corresponding to each information type and the passing threshold.

5. The method according to claim 4, characterized in that The information type includes a voice and text type and a photo and return type; the pass threshold includes a first pass threshold corresponding to the voice and text type and a second pass threshold corresponding to the photo and return type; the second pass threshold is less than the first pass threshold; The step of determining the verification result of the newly added keyword based on the feedback information corresponding to each information type and the passing threshold includes: In a case where the information type is a voice and text type, determining a first feedback pass rate according to each piece of feedback information corresponding to the voice and text type; In a case where the information type is a photo-taking feedback type, determining a second feedback pass rate according to each piece of feedback information corresponding to the photo-taking feedback type; In response to the first feedback pass rate being greater than or equal to the first pass threshold or the second feedback pass rate being greater than or equal to the second pass threshold, determining that the verification result of the newly added keyword is verification passed; In response to the first feedback pass rate being less than the first pass threshold and the second feedback pass rate being less than the second pass threshold, determining that the verification result of the newly added keyword is verification failure.

6. The method according to claim 1, characterized in that Before updating the news keyword library according to the newly added keywords, the method further includes: Determine corresponding verification news based on the newly added keywords, and determine information to be verified based on the verification news; wherein the information to be verified includes the time to be verified, the location to be verified, and the event to be verified; For each piece of verified news, determine the timeliness of the verified news; wherein the timeliness includes predictive, delayed, and mixed timeliness; In response to the timeliness being predictive or mixed, performing automated verification based on simulated navigation according to the information to be verified to determine the validity of the verification news; In response to the timeliness of the verification news being delayed, the information to be verified is sent to each information-related user, response information from each information-related user is received, and the validity of the verification news is determined based on the response information from each information-related user; Determine the effective proportion of news based on the effectiveness of each verified news; In response to the effective proportion of the news being greater than or equal to the preset proportion, the operation of updating the news keyword library according to the newly added keywords is triggered.

7. The method according to claim 1, characterized in that Also includes: Based on a second preset period, obtaining the existence time of each news keyword in the news keyword library; For each news keyword, in response to the existence duration being greater than a preset duration, obtaining identified news corresponding to the news keyword within a second verification time period; Identifying the identified news according to a preset traffic information identification model to determine third traffic information content; In response to the third traffic information content being less than a deletion threshold, the news keyword is deleted from the news keyword library.

8. The method according to claim 1, characterized in that Also includes: For each news keyword in the news keyword library, determining whether the news keyword is a festival activity type; In response to the news keyword being of a festival activity type, determining whether the news keyword is explicitly cancelled based on official news corresponding to the news keyword; In response to the news keyword being explicitly cancelled, the news keyword is deleted from the news keyword library.

9. An electronic device, characterized in that: The electronic device comprises: processor and memory; The processor is configured to execute the steps of the method for constructing a news keyword library according to any one of claims 1 to 8 by calling the program or instruction stored in the memory.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a program or instruction, and the program or instruction enables a computer to execute the steps of the method for constructing a news keyword library according to any one of claims 1 to 8.

Images