Method, device, electronic device and storage medium for processing public opinion

Abstract

The present invention discloses a method, device, electronic device and storage medium for processing public opinion, and relates to the field of computer technology. A specific implementation of the method includes: crawling public opinion data from a target data source, determining the data type of the public opinion data based on the data source type corresponding to the public opinion data, calling the calculation model corresponding to the data type, and calculating the public opinion label of the public opinion data; judging whether the data type is the target type; if so, querying the early warning strategy corresponding to the data type, and determining the early warning strategy hit by the public opinion data based on the public opinion label, so as to generate and send an early warning message; if not, integrating the public opinion data based on the public opinion label and combining with a preset user information library to obtain an integration result, and then generating and sending an early warning message. This implementation can solve the problem that the method of public opinion processing in the prior art cannot timely control the risks in public opinion and reduce the accuracy of public opinion risk control.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device, electronic device and storage medium for processing public opinion. Background Art

[0002] With the development of network technology, various public information such as the Internet has also grown rapidly, so the public opinion processing of public information has become an important issue. The public opinion processing method in the prior art is usually to process the relevant public opinion information after a public event or a negative event occurs. However, when no public event or negative event occurs, there will be certain risks in the public information on the Internet, and the public opinion processing method in the prior art is not applicable, so that the risks in public opinion cannot be controlled in time, reducing the accuracy of public opinion risk control. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a method, device, electronic device and storage medium for public opinion processing, which can solve the problem that the public opinion processing method in the prior art cannot timely control the risks in public opinion and reduce the accuracy of public opinion risk control.

[0004] To achieve the above objective, according to one aspect of an embodiment of the present invention, a method for handling public opinion is provided.

[0005] A method for processing public opinion in an embodiment of the present invention includes: crawling public opinion data from a target data source, determining the data type of the public opinion data based on the data source type corresponding to the public opinion data, calling the calculation model corresponding to the data type, and calculating the public opinion label of the public opinion data; judging whether the data type is the target type; if so, querying the early warning strategy corresponding to the data type, determining the early warning strategy hit by the public opinion data based on the public opinion label, so as to generate and send an early warning message; if not, integrating the public opinion data based on the public opinion label and a preset user information library to obtain an integration result, and then generating and sending an early warning message.

[0006] In one embodiment, the effective data is integrated based on the public opinion tag and combined with a preset user information database to obtain an integration result, including:

[0007] Based on the public opinion label, determining whether the public opinion data is valid data;

[0008] If not, no processing is performed; if so, the user attribute values ​​included in the public opinion data are extracted, and user information matching the user attribute values ​​is queried from a preset user information database to generate a corresponding character portrait in combination with the user attribute values, which is then determined as the integration result.

[0009] In yet another embodiment, if the public opinion data is valid data, the method further includes:

[0010] An abnormal link in the valid data is identified, a tool and a file corresponding to the valid data are downloaded, and the abnormal link, the tool and the file are determined as the integration result.

[0011] In yet another embodiment, determining an early warning strategy for the public opinion data hit based on the public opinion tag includes:

[0012] If the data type belongs to the first type, determining an early warning strategy for the public opinion data based on the public opinion label;

[0013] If the data type belongs to the second type, key characters in the public opinion data are extracted, and combined with the public opinion label, an early warning strategy for the public opinion data is determined.

[0014] In another embodiment, the public opinion label includes a validity label and a risk level;

[0015] The extracting key characters from the public opinion data, combining the public opinion tags, and determining the early warning strategy for the public opinion data hits includes:

[0016] Determining whether the key character is included in the preset monitoring indicator library;

[0017] If yes, then determine the early warning strategy for the public opinion data hit based on the validity label and risk level;

[0018] If not, the public opinion data will not be processed.

[0019] In another embodiment, the public opinion label includes a validity label and a risk level, and the key characters include an item attribute value;

[0020] The extracting key characters from the public opinion data, combining the public opinion tags, and determining the early warning strategy for the public opinion data hits includes:

[0021] The risk public opinion data in the public opinion data is determined based on the validity label and the risk level, and the item attribute values ​​included in the risk public opinion data are extracted to determine the item identification corresponding to the risk public opinion data, and the monitoring data corresponding to the item identification is queried from the monitoring database to determine the hit early warning strategy.

[0022] In another embodiment, the public opinion label includes whether it is a valid label, a risk level and a heat value;

[0023] Determining an early warning strategy for the public opinion data hit based on the public opinion tag includes:

[0024] The risk public opinion data in the public opinion data is filtered based on the validity label, and the risk score of the risk public opinion data is calculated based on the risk level and heat value of the risk public opinion data to determine the hit early warning strategy.

[0025] To achieve the above objective, according to another aspect of an embodiment of the present invention, a device for processing public opinion is provided.

[0026] A public opinion processing device according to an embodiment of the present invention includes: a computing unit, used to crawl public opinion data from a target data source, determine the data type of the public opinion data based on the data source type corresponding to the public opinion data, call the computing model corresponding to the data type, and calculate the public opinion label of the public opinion data; an early warning unit, used to determine whether the data type is a target type; if so, query the early warning strategy corresponding to the data type, determine the early warning strategy hit by the public opinion data based on the public opinion label, generate and send an early warning message; if not, integrate the public opinion data based on the public opinion label and a preset user information library to obtain an integration result, and then generate and send an early warning message.

[0027] In one embodiment, the early warning unit is specifically used to:

[0028] Based on the public opinion label, determining whether the public opinion data is valid data;

[0029] If not, no processing is performed; if so, the user attribute values ​​included in the public opinion data are extracted, and user information matching the user attribute values ​​is queried from a preset user information database to generate a corresponding character portrait in combination with the user attribute values, which is then determined as the integration result.

[0030] In yet another embodiment, the early warning unit is specifically used to:

[0031] An abnormal link in the valid data is identified, a tool and a file corresponding to the valid data are downloaded, and the abnormal link, the tool and the file are determined as the integration result.

[0032] In yet another embodiment, the early warning unit is specifically used to:

[0033] If the data type belongs to the first type, determining an early warning strategy for the public opinion data based on the public opinion label;

[0034] If the data type belongs to the second type, key characters in the public opinion data are extracted, and combined with the public opinion label, an early warning strategy for the public opinion data is determined.

[0035] In another embodiment, the public opinion label includes a validity label and a risk level;

[0036] The early warning unit is specifically used for:

[0037] Determining whether the key character is included in the preset monitoring indicator library;

[0038] If yes, then determine the early warning strategy for the public opinion data hit based on the validity label and risk level;

[0039] If not, the public opinion data will not be processed.

[0040] In another embodiment, the public opinion label includes a validity label and a risk level, and the key characters include an item attribute value;

[0041] The early warning unit is specifically used for:

[0042] The risk public opinion data in the public opinion data is determined based on the validity label and the risk level, and the item attribute values ​​included in the risk public opinion data are extracted to determine the item identification corresponding to the risk public opinion data, and the monitoring data corresponding to the item identification is queried from the monitoring database to determine the hit early warning strategy.

[0043] In another embodiment, the public opinion label includes whether it is a valid label, a risk level and a heat value;

[0044] The early warning unit is specifically used for:

[0045] The risk public opinion data in the public opinion data is filtered based on the validity label, and the risk score of the risk public opinion data is calculated based on the risk level and heat value of the risk public opinion data to determine the hit early warning strategy.

[0046] To achieve the above objective, according to another aspect of an embodiment of the present invention, an electronic device is provided.

[0047] An electronic device according to an embodiment of the present invention includes: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method for public opinion processing provided by the embodiment of the present invention.

[0048] To achieve the above objective, according to another aspect of an embodiment of the present invention, a computer readable medium is provided.

[0049] A computer-readable medium according to an embodiment of the present invention stores a computer program, which, when executed by a processor, implements the method for public opinion processing provided by an embodiment of the present invention.

[0050] An embodiment of the above invention has the following advantages or beneficial effects: In the embodiment of the present invention, after crawling public opinion data from the target data source, the data type of the public opinion data can be determined based on the type of the data source, and then the calculation model corresponding to the data type can be called to calculate the public opinion label of the public opinion data; then, based on the public opinion label, the public opinion data of different data types can be processed in different ways. In this way, in the embodiment of the present invention, the crawled public opinion data is classified, and the corresponding public opinion labels are calculated, and then based on the public opinion labels, the public opinion data is warned in a corresponding way, thereby improving the accuracy of public opinion warning, that is, improving the accuracy of public opinion risk control; and in the embodiment of the present invention, the public opinion data is combined with the preset user information to determine the warning message, and the public data can be combined with the internal data, thereby improving the accuracy and efficiency of public opinion risk control.

[0051] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0053] Figure 1 is a schematic diagram of a main process of a method for handling public opinion according to an embodiment of the present invention;

[0054] Figure 2 is a schematic diagram of another main process of the method for public opinion processing according to an embodiment of the present invention;

[0055] Figure 3 is a schematic diagram of another main process of the method for public opinion processing according to an embodiment of the present invention;

[0056] Figure 4 is a schematic diagram of main units of a device for processing public opinion according to an embodiment of the present invention;

[0057] Figure 5 is another exemplary system architecture diagram to which the embodiments of the present invention can be applied;

[0058] Figure 6 It is a schematic diagram of the structure of a computer system suitable for implementing the embodiment of the present invention. DETAILED DESCRIPTION

[0059] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, which include various details of the embodiments of the present invention to facilitate understanding, and they should be considered to be merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description. The acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. For example, the character portraits, user attribute values, user information, etc. in this application are only used in legal situations.

[0060] It should be pointed out that the embodiments of the present invention and the features in the embodiments may be combined with each other if there is no conflict.

[0061] The embodiment of the present invention provides a method for processing public opinion, which can be executed by a server, such as Figure 1 As shown, the method includes:

[0062] S101: crawling public opinion data from a target data source, determining the data type of the public opinion data based on the data source type corresponding to the public opinion data, calling a calculation model corresponding to the data type, and calculating a public opinion label of the public opinion data.

[0063] Among them, the target data source may include multiple types, for example, news websites, complaint websites, social media websites, wool party forums, online earning forums, cracking technology forums, artificial latent social groups, account trading websites, code sharing forums, non-mainstream chat software and dark web, etc. In the embodiment of the present invention, public opinion data can be classified based on different data sources. Specifically, since news websites, complaint websites, social media websites, etc. are mostly used for current news awareness, word-of-mouth monitoring, corporate image maintenance, etc. inside and outside the industry, these data sources can be divided into one type, and the public opinion data crawled from these data sources belong to the same data type, that is, the first data type. Data sources such as wool party forums, online earning forums, cracking technology forums, and artificial latent social groups can provide public opinion related to business risks in real time, such as wool-pulling information, price setting error information, coupon information that is eagerly concerned by wool parties, the company's business process has been completed or the loopholes of the website, mostly presented in the form of chat information, posts, questions, etc., so these data sources can be divided into one type, and the public opinion data crawled from these data sources belong to the same data type, that is, the second data type. Data sources such as platform account transaction information, platform leaked order information, automated scripts or software, and contact information released by black and gray production gangs (such as black and gray production studios) are usually published online and contain information that violates platform regulations or even laws and regulations. This type of information mostly comes from specialized account trading websites, code sharing forums, non-mainstream chat software, and the dark web. Therefore, the public opinion data crawled by these data sources belong to the same data type, namely the third data type.

[0064] Since the data in each type of data source focuses on different contents and plays different roles, in an embodiment of the present invention, a calculation model corresponding to each data type can be set to calculate the public opinion label corresponding to the public opinion data.

[0065] It should be noted that in the embodiment of the present invention, public opinion data can be crawled from the target data source through a crawler model, and the crawled public opinion data can be stored in a database for subsequent processing. For public opinion data of the first data type and the second data type, keywords for crawling public opinion data can be set according to needs or experience when crawling.

[0066] In the embodiment of the present invention, the calculation model is pre-set, and the calculation model corresponding to each data type is different, so the public opinion labels calculated for each data type are also different. Specifically, in the embodiment of the present invention, the public opinion label corresponding to the public opinion data of the first data type may include whether it is valid, risk level and heat value, the public opinion label corresponding to the public opinion data of the second data type may include whether it is valid, risk level and key characters, and the public opinion label of the third data type may include whether it is valid.

[0067] The public opinion data corresponding to the third data type has a higher risk, so it can usually be used as traceability data to be combined with internal data for traceability processing. The public opinion data corresponding to the first data type and the second data type can be set up with a monitoring plan to set an early warning strategy for risk monitoring based on demand, and then issue an early warning through the early warning strategy. Therefore, in an embodiment of the present invention, the first data type and the second data type are determined as target types, and the third data type is determined as a non-target type, so as to issue early warnings in different ways respectively.

[0068] S102: Determine whether the data type is the target type; if so, query the warning strategy corresponding to the data type, and determine the warning strategy hit by the public opinion data based on the public opinion label to generate and send a warning message; if not, integrate the public opinion data based on the public opinion label and the preset user information library to obtain the integration result, and then generate and send a warning message.

[0069] Since the data types are divided into target types and non-target types in the embodiment of the present invention, it is possible to first determine whether the data type of the public opinion data is the target type. If so, it means that the public opinion data is of the first data type or the second data type, and the early warning strategy corresponding to the data type can be queried, and the early warning strategy hit by the public opinion data can be determined based on the public opinion label to generate and send an early warning message; if not, the public opinion data is of the third data type, and the public opinion data can be integrated based on the public opinion label and combined with the preset user information library to obtain the integration result, and then generate and send an early warning message.

[0070] Specifically, the public opinion label of the third data type may include whether it is valid, to indicate whether the public opinion data has the effect of early warning and the value of traceability, so based on the public opinion label, public opinion data that is effective for early warning and has traceability value, that is, valid data, can be screened from the public opinion data. After determining that the public opinion data is valid data, the public opinion data can be integrated in combination with the preset user information database to obtain the integration result, so that based on the integration result, an early warning message for early warning can be generated, and then the early warning message can be sent.

[0071] Therefore, in this step, the public opinion data is integrated based on the public opinion label and combined with the preset user information database, and the integration result can be executed as follows: based on the public opinion label, determine whether the public opinion data is valid data; if not, do not process it; if so, extract the user attribute values ​​included in the public opinion data, and query the user information matching the user attribute values ​​from the preset user information database, so as to generate the corresponding character portrait in combination with the user attribute values, and then determine it as the integration result.

[0072] When it is determined that the public opinion data is not valid data, it can no longer be processed. After determining that the public opinion data is valid data, it can be traced back to its source, that is, the user attribute values ​​included in the public opinion data are extracted, and the user information matching the user attribute values ​​is searched from the preset user information database to generate the corresponding character portrait in combination with the user attribute values, and then determined as the integration result.

[0073] User attribute values ​​may include user ID, name, mobile phone number, email address, forum ID, address information, etc. After extracting the user attribute value from the public opinion data, it can be matched with the preset user information database, that is, querying the user information that matches the user attribute value from the preset user information database, that is, querying the user information that is consistent with the user attribute value. In this way, the two can be combined to obtain more attributes of the user, and then a character portrait can be made based on this, and this character portrait is determined as the integration result of the public opinion data to issue an early warning. The preset user information database can be established based on internal data. Through the above process, risky users and the user information of the user can be determined, and early warnings can be issued, thereby improving the efficiency of early warnings.

[0074] Furthermore, if the public opinion data includes links, the links can be identified by calling third-party services or manually to identify abnormal links, annotate and store the abnormal links, and also determine them as integration results for early warning. At the same time, if the public opinion data includes information corresponding to tools and files, they can also be downloaded and stored to determine them as integration results for early warning.

[0075] It should be noted that when searching for user information that matches the user attribute value from the preset user information database, if no matching user information is found, the user information can be obtained through fuzzy matching or manual processing. In the embodiment of the present invention, a fixed template for the integration result can be pre-set, and then the integration result can be generated based on the fixed template, and the integration result can be stored in the corresponding database, and an early warning message can be generated at the same time for early warning. In addition, after the integration result is stored in the database, a prompt message can be sent to prompt relevant personnel to check and process it in time.

[0076] Although the first type and the second type are both target types, different processing methods can also be set in the embodiment of the present invention.

[0077] For the first type, public opinion labels may include whether the label is valid, the risk level and the heat value, where the heat value can be calculated by weighted comprehensive calculation based on the number of readings, likes, comments, reposts, and similar or related articles on the entire network of the public opinion data. Then, based on the public opinion labels, the early warning strategy for public opinion data hits can be determined, which can be specifically implemented as follows: based on whether the label is valid, the risk public opinion data in the public opinion data is screened, based on the risk level and heat value of the risk public opinion data, the risk score of the risk public opinion data is calculated to determine the early warning strategy for the hit.

[0078] Risky public opinion data in public opinion data can be screened based on whether the label is valid or not. For example, if the label of the public opinion data is yes, it can be determined as risky public opinion data; if the label of the public opinion data is no, it can be not processed. For risky public opinion data, the risk score of the risky public opinion data can be calculated based on the risk level and heat value. For example, the risk score can be weighted according to the heat value and risk level. The early warning strategy is pre-configured. Specifically, it can be warned if the risk score is greater than the risk threshold, or if the heat value is greater than the first score and the risk level is "high", etc. In this way, it can be determined whether the public opinion data hits the early warning strategy, and which early warning strategy it hits.

[0079] It should be noted that if the risk public opinion data hits the warning strategy, it does not need to be processed.

[0080] For the second type, the public opinion label may include whether it is a valid label and the risk level. The early warning strategy for public opinion data hits can be determined based on the public opinion label. The specific implementation is: extract key characters in the public opinion data, combine the public opinion label, and determine the early warning strategy for public opinion data hits.

[0081] Key words can be specifically hot words, and then a "hot word" word cloud can be generated based on the hot words to reflect the focus, context, subject and other information of the public opinion data, and then the risk strategy for the hit is determined in combination with whether the label is valid and the risk level. The risk strategy can be set according to needs.

[0082] The key characters can be specifically preset monitoring indicators. In this case, this step can be performed as follows: determine whether the preset monitoring indicator library includes the key characters; if so, determine the early warning strategy for public opinion data hits based on whether the label is valid and the risk level; if not, do not process the public opinion data. Monitoring indicators can be set based on demand. For example, if a popular item needs to be monitored recently, the monitoring indicator can be the name of the item. Determine whether the preset monitoring indicator library includes key characters to determine whether the key characters are preset monitoring indicators. After determining that the key characters are monitoring indicators, the early warning strategy for public opinion data hits can be determined based on whether the label is valid and the risk level; after determining that the key characters are not monitoring indicators, no processing is required.

[0083] The key characters may also be preset item attribute values, such as item names, item numbers, etc. At this time, this step may be performed as follows: determining the risk public opinion data in the public opinion data based on whether the label is valid and the risk level, extracting the item attribute values ​​included in the risk public opinion data to determine the item identification corresponding to the risk public opinion data, and querying the monitoring data corresponding to the item identification from the monitoring database to determine the hit early warning strategy.

[0084] Based on whether the label is valid and the risk level, it can be determined whether the public opinion data is risky public opinion data, and then the risky public opinion data in the public opinion data can be determined, and then the key characters, that is, the item attribute values ​​included, can be extracted from the risky public opinion data, and then the item identification can be determined based on the extracted item attribute values, so that the item corresponding to the risky public opinion data can be determined, and then the monitoring data corresponding to the item identification can be queried from the monitoring database, and then it can be determined based on the monitoring data whether the warning strategy is hit. Specifically, if the monitoring data is abnormal, it means that the item has risks in both the public opinion data and the internal monitoring data, then it can be determined that it hits the warning strategy and an early warning is issued.

[0085] It should be noted that the public opinion data may include image data or links. For image data, in the embodiment of the present invention, the text contained in the image is identified by OCR technology and invalid or unrecognizable garbled characters are removed, leaving recognizable data that can be matched with the monitoring database, such as item codes, coupon codes, order numbers, item names, prices, etc. For links, in this step, connections (long links or short links) including preset characters can be screened out, and then the text public opinion corresponding to the link can be identified and parsed for the link, and data that can be matched with the monitoring database can be parsed from the link, such as item codes, coupon codes, order numbers, item names, prices, etc. Through the above process, it is possible to convert unstructured public opinion data into structured data, and then execute the corresponding processing process.

[0086] In an embodiment of the present invention, the crawled public opinion data is classified and the corresponding public opinion labels are calculated, and then based on the public opinion labels, the public opinion data is warned in a corresponding manner, thereby improving the accuracy of public opinion warnings, that is, improving the accuracy of public opinion risk control; and in an embodiment of the present invention, the public opinion data is combined with preset user information to determine the warning message, and public data can be combined with internal data, thereby improving the accuracy and efficiency of public opinion risk control.

[0087] Combine the following Figure 1 In the embodiment shown, the key characters are used as the attribute values ​​of items as an example to specifically illustrate the processing method of the public opinion data of the second data type in the embodiment of the present invention. Figure 2As shown, the method includes:

[0088] S201: Calling the calculation model corresponding to the second type to calculate the public opinion label of the public opinion data.

[0089] Among them, public opinion labels may include whether the labels are valid and the risk level.

[0090] S202: Determine risky public opinion data in the public opinion data based on whether the label is valid and the risk level.

[0091] S203: extracting the item attribute values ​​included in the risk public opinion data to determine the item identification corresponding to the risk public opinion data, querying the monitoring data corresponding to the item identification from the monitoring database to determine the hit early warning strategy.

[0092] S204: Generate and send a warning message.

[0093] It should be noted that the data processing principle in the embodiment of the present invention has been Figure 1 The above is described in the embodiment shown and will not be described in detail here.

[0094] In an embodiment of the present invention, the crawled public opinion data is classified and the corresponding public opinion labels are calculated, and then based on the public opinion labels, the public opinion data is warned in a corresponding manner, thereby improving the accuracy of public opinion warnings, that is, improving the accuracy of public opinion risk control; and in an embodiment of the present invention, the public opinion data is combined with preset user information to determine the warning message, and public data can be combined with internal data, thereby improving the accuracy and efficiency of public opinion risk control.

[0095] Combine the following Figure 1 The embodiment shown in the figure specifically describes the method for processing the public opinion data of the third data type in the embodiment of the present invention. Figure 3 As shown, the method includes:

[0096] S301: Calling the calculation model corresponding to the third type to calculate the public opinion label of the public opinion data, and judging whether the public opinion data is valid data based on the public opinion label.

[0097] Among them, public opinion data may include designated data, black and gray software, scripts and script codes, vulnerability information, suspicious links (such as fraud, gambling, phishing links), etc.

[0098] Public opinion labels can include whether they are valid labels and whether they have value labels. Whether they have value labels can be calculated based on multiple indicator scores, such as validity (whether they are related to the specified data), source (different intelligence sources have different weight scores), sensitivity score (automatically classify intelligence, different types have different weight scores), whether they have attachments, links, etc.

[0099] If not, the public opinion data may not be processed.

[0100] S302: If yes, extract the user attribute values ​​included in the public opinion data, query the user information matching the user attribute values ​​from the preset user information database, generate the corresponding character portrait in combination with the user attribute values, and then determine it as the integration result.

[0101] S303: Identify abnormal links in valid data, download tools and files corresponding to the valid data, and determine the abnormal links, tools and files as integration results.

[0102] S304: Store the integration results in the database, generate and send an early warning message.

[0103] It should be noted that the data processing principle in the embodiment of the present invention has been Figure 1 The above is described in the embodiment shown and will not be described in detail here.

[0104] In an embodiment of the present invention, the crawled public opinion data is classified and the corresponding public opinion labels are calculated, and then based on the public opinion labels, the public opinion data is warned in a corresponding manner, thereby improving the accuracy of public opinion warnings, that is, improving the accuracy of public opinion risk control; and in an embodiment of the present invention, the public opinion data is combined with preset user information to determine the warning message, and public data can be combined with internal data, thereby improving the accuracy and efficiency of public opinion risk control.

[0105] In order to solve the problems existing in the prior art, an embodiment of the present invention provides a public opinion processing device 400, such as Figure 4 As shown, the device 400 includes:

[0106] The calculation unit 401 is used to crawl public opinion data from a target data source, determine the data type of the public opinion data based on the data source type corresponding to the public opinion data, call the calculation model corresponding to the data type, and calculate the public opinion label of the public opinion data;

[0107] The early warning unit 402 is used to determine whether the data type is the target type; if so, query the early warning strategy corresponding to the data type, and determine the early warning strategy hit by the public opinion data based on the public opinion label to generate and send a warning message; if not, integrate the public opinion data based on the public opinion label and the preset user information library to obtain the integration result, and then generate and send a warning message.

[0108] It should be understood that the manner of implementing the embodiments of the present invention is different from the Figure 1 The method of the illustrated embodiment is the same and will not be repeated here.

[0109] In one implementation of the embodiment of the present invention, the early warning unit 402 is specifically configured to:

[0110] Based on the public opinion label, determining whether the public opinion data is valid data;

[0111] If not, no processing is performed; if so, the user attribute values ​​included in the public opinion data are extracted, and user information matching the user attribute values ​​is queried from a preset user information database to generate a corresponding character portrait in combination with the user attribute values, which is then determined as the integration result.

[0112] In another implementation of the embodiment of the present invention, the early warning unit 402 is specifically configured to:

[0113] An abnormal link in the valid data is identified, a tool and a file corresponding to the valid data are downloaded, and the abnormal link, the tool and the file are determined as the integration result.

[0114] In another implementation of the embodiment of the present invention, the early warning unit 402 is specifically configured to:

[0115] If the data type belongs to the first type, determining an early warning strategy for the public opinion data based on the public opinion label;

[0116] If the data type belongs to the second type, key characters in the public opinion data are extracted, and combined with the public opinion label, an early warning strategy for the public opinion data is determined.

[0117] In another implementation of the embodiment of the present invention, the public opinion label includes a validity label and a risk level;

[0118] The early warning unit 402 is specifically used for:

[0119] Determining whether the key character is included in the preset monitoring indicator library;

[0120] If yes, then determine the early warning strategy for the public opinion data hit based on the validity label and risk level;

[0121] If not, the public opinion data will not be processed.

[0122] In another implementation of the embodiment of the present invention, the public opinion label includes whether the label is valid and the risk level, and the key characters include the attribute value of the item;

[0123] The early warning unit 402 is specifically used for:

[0124] The risk public opinion data in the public opinion data is determined based on the validity label and the risk level, and the item attribute values ​​included in the risk public opinion data are extracted to determine the item identification corresponding to the risk public opinion data, and the monitoring data corresponding to the item identification is queried from the monitoring database to determine the hit early warning strategy.

[0125] In another implementation of the embodiment of the present invention, the public opinion label includes whether it is a valid label, a risk level and a heat value;

[0126] The early warning unit 402 is specifically used for:

[0127] The risk public opinion data in the public opinion data is filtered based on the validity label, and the risk score of the risk public opinion data is calculated based on the risk level and heat value of the risk public opinion data to determine the hit early warning strategy.

[0128] It should be understood that the manner of implementing the embodiments of the present invention is different from the Figure 1-3 The method of the illustrated embodiment is the same and will not be repeated here.

[0129] In an embodiment of the present invention, the crawled public opinion data is classified and the corresponding public opinion labels are calculated, and then based on the public opinion labels, the public opinion data is warned in a corresponding manner, thereby improving the accuracy of public opinion warnings, that is, improving the accuracy of public opinion risk control; and in an embodiment of the present invention, the public opinion data is combined with preset user information to determine the warning message, and public data can be combined with internal data, thereby improving the accuracy and efficiency of public opinion risk control.

[0130] According to an embodiment of the present invention, the embodiment of the present invention further provides an electronic device and a readable storage medium.

[0131] The electronic device of an embodiment of the present invention includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the one processor, and the instructions are executed by the at least one processor so that the at least one processor executes the method for public opinion processing provided by the embodiment of the present invention.

[0132] Figure 5 An exemplary system architecture 500 is shown to which the method or apparatus for processing public opinion according to an embodiment of the present invention can be applied.

[0133] like Figure 5As shown, system architecture 500 may include terminal devices 501, 502, 503, a network 504 and a server 505. Network 504 is used to provide a medium for communication links between terminal devices 501, 502, 503 and server 505. Network 504 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0134] The user can use the terminal devices 501, 502, 503 to interact with the server 505 through the network 504 to receive or send messages, etc. Various client applications can be installed on the terminal devices 501, 502, 503.

[0135] The terminal devices 501 , 502 , and 503 may be, but are not limited to, smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0136] The server 505 may be a server that provides various services. The server may analyze and process the received data such as the product information query request, and feed back the processing result (such as product information - just an example) to the terminal device.

[0137] It should be noted that the method for processing public opinion provided in the embodiment of the present invention is generally executed by the server 505 , and accordingly, the apparatus for processing public opinion is generally arranged in the server 505 .

[0138] It should be understood that Figure 5 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0139] Reference below Figure 6 , which shows a schematic diagram of the structure of a computer system 600 suitable for implementing an embodiment of the present invention. Figure 6 The computer system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0140] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0141] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0142] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present invention are executed.

[0143] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0144] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a unit, a program segment, or a part of a code, and the above-mentioned unit, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0145] The units involved in the embodiments of the present invention may be implemented by software or hardware. The units described may also be arranged in a processor, for example, it may be described as: a processor includes a computing unit and an early warning unit. The names of these units do not constitute a limitation on the units themselves in some cases, for example, the computing unit may also be described as a "unit of the function of the computing unit".

[0146] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device executes the method for public opinion processing provided by the present invention.

[0147] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for handling public opinion, characterized in that: include: Crawl public opinion data from a target data source, determine the data type of the public opinion data based on the data source type corresponding to the public opinion data, call a calculation model corresponding to the data type, and calculate a public opinion label of the public opinion data; Determine whether the data type is a target type; If yes, query the warning strategy corresponding to the data type, determine the warning strategy hit by the public opinion data based on the public opinion tag, and generate and send a warning message; If not, then based on the public opinion tag, the public opinion data is integrated in combination with a preset user information database to obtain an integration result, and then a warning message is generated and sent; Determining an early warning strategy for the public opinion data hit based on the public opinion tag includes: If the data type belongs to the first type, determining an early warning strategy for the public opinion data based on the public opinion label; If the data type belongs to the second type, key characters in the public opinion data are extracted, and combined with the public opinion label, an early warning strategy for the public opinion data is determined.

2. The method according to claim 1, characterized in that The step of integrating the public opinion data based on the public opinion tag and in combination with a preset user information database to obtain an integration result includes: Based on the public opinion label, determining whether the public opinion data is valid data; If not, no processing is performed; if so, the user attribute values ​​included in the public opinion data are extracted, and user information matching the user attribute values ​​is queried from a preset user information database to generate a corresponding character portrait in combination with the user attribute values, which is then determined as the integration result.

3. The method according to claim 2, characterized in that If the public opinion data is valid data, the method further includes: An abnormal link in the valid data is identified, a tool and a file corresponding to the valid data are downloaded, and the abnormal link, the tool and the file are determined as the integration result.

4. The method according to claim 1, characterized in that: The public opinion label includes whether it is a valid label and the risk level; The extracting key characters from the public opinion data, combining the public opinion tags, and determining the early warning strategy for the public opinion data hits includes: Determining whether the key character is included in the preset monitoring indicator library; If yes, then determine the early warning strategy for the public opinion data hit based on the validity label and risk level; If not, the public opinion data will not be processed.

5. The method according to claim 1, characterized in that The public opinion label includes whether the label is valid and the risk level, and the key characters include the attribute value of the item; The extracting key characters from the public opinion data, combining the public opinion tags, and determining the early warning strategy for the public opinion data hits includes: The risk public opinion data in the public opinion data is determined based on the validity label and the risk level, and the item attribute values ​​included in the risk public opinion data are extracted to determine the item identification corresponding to the risk public opinion data, and the monitoring data corresponding to the item identification is queried from the monitoring database to determine the hit early warning strategy.

6. The method according to claim 1, characterized in that The public opinion label includes whether it is a valid label, risk level and heat value; Determining an early warning strategy for the public opinion data hit based on the public opinion tag includes: The risk public opinion data in the public opinion data is filtered based on the validity label, and the risk score of the risk public opinion data is calculated based on the risk level and heat value of the risk public opinion data to determine the hit early warning strategy.

7. A device for processing public opinion, characterized in that: include: A computing unit, used to crawl public opinion data from a target data source, determine the data type of the public opinion data based on the data source type corresponding to the public opinion data, call a computing model corresponding to the data type, and calculate a public opinion label of the public opinion data; An early warning unit, used to determine whether the data type is a target type; If yes, query the warning strategy corresponding to the data type, determine the warning strategy hit by the public opinion data based on the public opinion tag, and generate and send a warning message; If not, then based on the public opinion tag, the public opinion data is integrated in combination with a preset user information database to obtain an integration result, and then a warning message is generated and sent; The early warning unit is specifically used for: If the data type belongs to the first type, determining an early warning strategy for the public opinion data based on the public opinion label; If the data type belongs to the second type, key characters in the public opinion data are extracted, and combined with the public opinion label, an early warning strategy for the public opinion data is determined.

8. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images