WO2019169766A1

WO2019169766A1 - Electronic apparatus, method and system for early warning regarding system sensitive content, and storage medium

Info

Publication number: WO2019169766A1
Application number: PCT/CN2018/089460
Authority: WO
Inventors: 赵骏
Original assignee: 平安科技（深圳）有限公司
Priority date: 2018-03-06
Filing date: 2018-06-01
Publication date: 2019-09-12
Also published as: CN108446270A; CN108446270B

Abstract

The present application relates to an electronic apparatus, a method and system for early warning regarding system sensitive content, and a storage medium. The method comprises: acquiring each anti-sensitive parameter corresponding to a service system and a weight corresponding to each anti-sensitive parameter, and computing, according to each anti-sensitive parameter and the corresponding weight, a system anti-sensitive index of the service system; acquiring a content sensitive index of the content released by each user, and a historical user behavior index in the service system, computing a system sensitive index of the user according to the content sensitive index and the historical user behavior index, and adding the system sensitive indexes of all users in the service system to obtain a system sensitive index sum; and computing the difference between the system anti-sensitive index corresponding to the service system and the system sensitive index sum, and determining whether to raise an early warning according to the difference. According to the present application, hierarchical determination can be carried out on sensitive information by combining a service scenario and a user behavior to raise a more accurate early warning regarding sensitive information.

Description

Early warning method, system and storage medium for electronic device and system sensitive content

Priority claim

This application is based on the priority of the Chinese Patent Application for the application of the Chinese Patent Application entitled "Electronic Device, Systematic Sensitive Contents and Storage Media", filed on March 6, 2018, with the application number CN 201810182928.4, which is filed on March 06, 2018. The content is incorporated herein by reference.

Technical field

The present application relates to the field of communications technologies, and in particular, to an electronic device, an early warning method, system, and storage medium for sensitive content of a system.

Background technique

At present, for large-scale integrated enterprise institutions, the company usually covers a variety of businesses, such as financial institutions, including securities, insurance, banking and other financial services, each of which can correspond to one or more social platforms, such as stock BBS, financial management. Explain the live broadcast and so on. A variety of sensitive information may appear in these platforms, such as pornography, politics, advertising, etc., which are prone to adverse effects. There are some methods in the industry to judge the content of the platform and to warn sensitive information, but the evaluation of sensitive information is relatively solid, generally only pay attention to the correct rate of judgment, and it is prone to a one-size-fits-all situation.

Summary of the invention

The purpose of the present application is to provide an electronic device, an early warning method for a sensitive content of a system, a system, and a storage medium, which are designed to hierarchically evaluate sensitive information in combination with business scenarios and user behaviors, and provide more accurate early warning of sensitive information.

To achieve the above object, the present application provides an electronic device including a memory and a processor coupled to the memory, the memory storing a processing system operable on the processor, the processing The system implements the following steps when executed by the processor:

The anti-allergy index processing step acquires each anti-allergy parameter corresponding to the business system and the weight corresponding to each anti-allergy parameter, and calculates a system anti-allergy index of the business system according to each anti-allergy parameter and corresponding weight;

The sensitive index processing step acquires the content sensitivity index and the user historical behavior index of each user's published content in the business system, calculates the system sensitivity index of the user according to the content sensitivity index and the user historical behavior index, and sensitive the system of all users in the business system. The sum of the indices gives the sum of the system sensitivity indices;

The early warning step is determined, and the difference between the system anti-allergy index corresponding to the business system and the sum of the system sensitivity indexes is calculated, and whether the early warning is issued is determined according to the difference.

To achieve the above object, the present application further provides an early warning method for system sensitive content, and the method for alerting sensitive content of the system includes:

S1, obtaining respective anti-allergy parameters corresponding to the service system and weights corresponding to the respective anti-allergy parameters, and calculating a system anti-allergy index of the service system according to each anti-allergy parameter and corresponding weight;

S2: obtaining a content sensitivity index and a user historical behavior index of content published by each user in the business system, calculating a system sensitivity index of the user according to the content sensitivity index and the user historical behavior index, and adding system sensitivity indexes of all users in the business system Get the sum of the system sensitivity index;

S3: Calculate the difference between the system anti-allergy index corresponding to the service system and the sum of the system sensitivity indexes, and determine whether to issue an early warning according to the difference.

To achieve the above objective, the present application further provides an early warning system for system sensitive content, wherein the system early warning system for sensitive content includes:

The obtaining module is configured to obtain each anti-allergy parameter corresponding to the service system and a weight corresponding to each anti-allergy parameter, and calculate a system anti-allergy index of the service system according to each anti-allergy parameter and the corresponding weight;

The processing module is configured to obtain a content sensitivity index and a user historical behavior index of each user published content in the business system, calculate a system sensitivity index of the user according to the content sensitivity index and the user historical behavior index, and sensitivity the system of all users in the business system. The sum of the indices gives the sum of the system sensitivity indices;

The early warning module is configured to calculate a difference between the system anti-allergy index corresponding to the business system and the sum of the system sensitivity indexes, and determine whether to issue an early warning according to the difference.

The present application also provides a computer readable storage medium having stored thereon a processing system that, when executed by a processor, implements the steps of the method described above.

The beneficial effects of the present application are: the present application calculates a system anti-allergy index for judging its ability to resist sensitive information for different business systems, and calculates a system sensitivity index for judging the degree of sensitive influence of the user's behavior on the business system. Sum, according to the difference between the two to determine whether the business system issues an early warning, this application comprehensively considers the actual application of the business system, each business system has different tolerance for sensitive information, and the rigor of users in each business system is different. Based on these two aspects, from the perspective of the practical application of the business system, combined with the business scenario and user behavior, the sensitive information is hierarchically evaluated, and the sensitive information is more accurately alerted.

DRAWINGS

1 is a schematic diagram of a hardware architecture of an embodiment of an electronic device according to the present application;

FIG. 2 is a schematic flowchart of an embodiment of an early warning method for sensitive content of the system of the present application.

Detailed ways

In order to make the objects, technical solutions, and advantages of the present application more comprehensible, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the application and are not intended to be limiting. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope are the scope of the present application.

It should be noted that the descriptions of "first", "second" and the like in the present application are for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. . Thus, features defining "first" or "second" may include at least one of the features, either explicitly or implicitly. In addition, the technical solutions between the various embodiments may be combined with each other, but must be based on the realization of those skilled in the art, and when the combination of the technical solutions is contradictory or impossible to implement, it should be considered that the combination of the technical solutions does not exist. Nor is it within the scope of protection required by this application.

1 is a schematic diagram of a hardware architecture of an embodiment of an electronic device of the present application. The electronic device 1 is an apparatus capable of automatically performing numerical calculation and/or information processing in accordance with an instruction set or stored in advance. The electronic device 1 may be a computer, a single network server, a server group composed of multiple network servers, or a cloud-based cloud composed of a large number of hosts or network servers, where cloud computing is a type of distributed computing. A super virtual computer consisting of a group of loosely coupled computers.

In the present embodiment, the electronic device 1 may include, but is not limited to, a memory 11 communicably connected to each other through a system bus, a processor 12, and a network interface 13, and the memory 11 stores a processing system operable on the processor 12. It should be noted that FIG. 1 only shows the electronic device 1 having the components 11-13, but it should be understood that not all illustrated components are required to be implemented, and more or fewer components may be implemented instead.

The memory 11 includes a memory and at least one type of readable storage medium. The memory provides a cache for the operation of the electronic device 1; the readable storage medium may be, for example, a flash memory, a hard disk, a multimedia card, a card type memory (eg, SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM). A non-volatile storage medium such as a read only memory (ROM), an electrically erasable programmable read only memory (EEPROM), a programmable read only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, or the like. In some embodiments, the readable storage medium may be an internal storage unit of the electronic device 1, such as a hard disk of the electronic device 1; in other embodiments, the non-volatile storage medium may also be external to the electronic device 1. The storage device, for example, a plug-in hard disk provided on the electronic device 1, a smart memory card (SMC), a Secure Digital (SD) card, a flash card, or the like. In this embodiment, the readable storage medium of the memory 11 is generally used to store an operating system and various types of application software installed in the electronic device 1, such as program code for storing a processing system in an embodiment of the present application. Further, the memory 11 can also be used to temporarily store various types of data that have been output or are to be output.

The processor 12 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 12 is typically used to control the overall operation of the electronic device 1, such as performing control and processing related to data interaction or communication with other devices. In this embodiment, the processor 12 is configured to run program code or process data stored in the memory 11, such as running a processing system or the like.

The network interface 13 may comprise a wireless network interface or a wired network interface, which is typically used to establish a communication connection between the electronic device 1 and other electronic devices.

The processing system is stored in the memory 11 and includes at least one computer readable instruction stored in the memory 11, the at least one computer readable instruction being executable by the processor 12 to implement the methods of various embodiments of the present application; The at least one computer readable instruction can be classified into different logic modules depending on the functions implemented by its various parts.

In an embodiment, when the processing system is executed by the processor 12, the following steps are implemented:

Among them, the system anti-allergy index is an indicator of the ability of the business system to resist sensitive information or sensitive content. The higher the system anti-allergy index, the stronger the ability of the business system to resist sensitive vocabulary. In an embodiment, the anti-allergy parameter includes a system important level coefficient, a user quantity level coefficient, and a system information propagation coefficient; in another embodiment, the anti-allergy parameter includes a system important level coefficient, a user quantity level coefficient, and a system information propagation coefficient. , emergency response coefficient, sensitive vocabulary attention coefficient.

The smaller the system important level coefficient is, the more important the service system is. The smaller the user quantity level coefficient is, the more the number of users of the service system is. The smaller the system information propagation coefficient is, the stronger the information dissemination capability of the service system is. The smaller the coefficient, the weaker the emergency response capability of the business system, and the smaller the sensitive vocabulary attention coefficient, the higher the sensitivity of the sensitive vocabulary in the business system.

In a specific example, the system important grade coefficient has a range of [0, 1]. When the system important grade coefficient is 0, the business system has the highest importance, and the system important grade coefficient can be divided into three levels: 0 is a level. , 0.5 is the second level, and 1 is the third level;

The user quantity level coefficient ranges from [0, 1]. When the user quantity level coefficient is 0, the user quantity is the highest, and the user quantity level coefficient can be divided into three levels: 0 is the user quantity is above 10000, and 0.5 is the user quantity. Within 1000 to 10000, 1 is less than 1000 for the user;

The system information propagation coefficient ranges from [0, 1]. When the system information propagation coefficient is 0, the system information is the easiest to propagate. The system information propagation coefficient can be divided into three levels: 0 is the pure Internet as the transmission route, and 0.5 is the enterprise. The mixed transmission route in the network composed of the local area network and the Internet, 1 is only the local area network as the transmission route;

The range of emergency response coefficient is [0,1]. When the emergency response coefficient is 0, the system has no emergency treatment. The emergency treatment coefficient can be divided into three levels: 0 for no emergency response and 0.5 for quickly deleting sensitive content in the system. 1 is to locate the forwarding address and delete it while deleting the sensitive content quickly;

The sensitivity vocabulary attention coefficient range is [0,1]. When the sensitive vocabulary attention degree coefficient is 0, the sensitive vocabulary attention degree is the highest. The sensitive vocabulary attention degree coefficient can be divided into 3 levels: 0 is pornography, politics, advertisement, illegal All of the concerns, 0.5 is not harmful to the attention of advertising, etc., 1 is already sensitive to other means, so do not pay attention.

The anti-allergy parameters include the system important grade coefficient x1, the user magnitude coefficient x2, the system information propagation coefficient x3, the emergency processing coefficient x4, the sensitive vocabulary attention degree coefficient x5, for example, the system important grade coefficient x1, the user magnitude grade coefficient x2, the system The weights of information propagation coefficient x3, emergency processing coefficient x4, and sensitive vocabulary attention degree coefficient x5 are respectively w1, w2, w3, w4, w5, then the system anti-allergy index = x1 * w1 + x2 * w2 + x3 * w3 + x4 *w4+x5*w5. The weights w1, w2, w3, w4, and w5 are pre-configured values greater than 1, and may be the same value or different values. In an embodiment, w1=w2=w3=w4=w5=20.

According to the description of the above example, the more important the business system, the larger the user volume, the easier the information dissemination, the weaker the emergency processing capability, and the higher the sensitivity of the sensitive vocabulary, the smaller the system anti-allergic index of the business system and the resistance to sensitive vocabulary. The weaker the ability; the greater the system's system sensitivity index, the stronger the ability to resist sensitive vocabulary.

In another example, the system important level coefficient x1 may be measured according to the weight of each service scenario in the service system and the service volume corresponding to each service scenario, and the financial service system is taken as an example, and the business scenario includes a financial transaction scenario and a common transaction scenario. Financial transaction scenarios include, for example, bank transfers, fund purchases, etc., and general transactions include, for example, premium payments, premium renewals, and the like. The weight of the financial transaction scenario is k1, the weight of the common transaction scenario is k2, the traffic volume of the financial transaction scenario is c1, the traffic volume of the common transaction scenario is c2, and the traffic volume can be measured by the amount of data sent and received, and the amount of data sent and received. The larger the traffic, the larger the traffic. The system important rank coefficient of the business system is x1=(k1+k2)/((πk1/2arctan(c1/α)+πk2/2arctan(c2/α)), where α is the average traffic of the business scenario of the business system , α = (c1 + c2) / 2, the system important level coefficient x1 range is [0, 1]. Of course, the business scenario can be further subdivided to more objectively and comprehensively judge the importance of the business system. For example, a financial transaction scenario, a common transaction scenario, a core business scenario, and a non-core business scenario, etc., various scenarios have corresponding traffic volumes, and the system important rank coefficient x1 can be calculated by the same principle calculation method as above.

Among them, the user's system sensitivity index is used to judge the degree of sensitive influence of the user's behavior on the business system. The smaller the user's system sensitivity index, the less sensitive the impact on the business system, and the greater the user's system sensitivity index, the greater the sensitivity to the business system.

The content sensitivity index refers to the sensitivity or metric of the content published by the user. If the content involves sensitive vocabulary or sensitive information, the content sensitivity index is larger, and the sensitive vocabulary or sensitive information includes pornography, politics, advertisement, illegality, etc. .

In an embodiment, the process of obtaining the content sensitivity index includes: segmenting the content of the user by using the sentence as a unit, matching the word after the word segmentation with the word in the pre-established thesaurus, to match the corresponding keyword, The keywords include nouns, verbs, words related to pornography, politics, advertisements, illegals, etc., and the corresponding core viewpoint information of each sentence is analyzed according to the keyword. In an embodiment, the keywords may be directly composed. The new statement, the information of the statement is the core viewpoint information, and the content sensitive index associated with the core viewpoint information is obtained according to the association relationship between the pre-established core viewpoint information and the content sensitive index. Wherein, the content sensitive index corresponding to the core viewpoint information is obtained by identifying the core program in advance and stored in the thesaurus. In an embodiment, the core view information is pornographic information, the content sensitivity index corresponds to n1, the core view information is illegal information, the content sensitivity index corresponds to n2, the core view information is political information, and the content sensitivity index corresponds to n3. The core viewpoint information is advertisement information, and its content sensitivity index corresponds to n4, n1≥n2≥n3≥n4.

In a specific example, for example, for the content published by the user in a certain platform system, "*** Cosmetics Today Promotion Promotion", the sentence is divided into "*** Cosmetics", "Today", "Promotion" ", "big discount", matching these participles with the words in the thesaurus, the keywords obtained are "cosmetics", "promotion", "big discount", according to these keywords, the core viewpoint of the statement can be analyzed The information is “cosmetic promotion offer”, and its core viewpoint information belongs to advertisement information.

The user historical behavior index is a description of the behavior of the user to the content published by other users. In an embodiment, the user's historical behavior index has a base of 1. If the user reports that other users publish sensitive vocabulary or sensitive information, The user's historical behavior index is (1-0.2). If the user has published a behavior involving sensitive vocabulary or sensitive information, the user's historical behavior index is (1+0.2).

After obtaining the content sensitivity index and the user historical behavior index of each user's published content in the business system, the system sensitivity index=content sensitivity index*user historical behavior index of the user is calculated, and the system sensitivity indexes of all users in the business system are added. Get the sum of the system sensitivity index.

In other embodiments, the words in the thesaurus may be maintained, and the evaluation of the content sensitivity index corresponding to the core viewpoint information in the existing thesaurus may be adjusted in real time according to the operation of the business system, and the specific adjustment algorithm includes: according to the vocabulary The total frequency of occurrence, the breadth of vocabulary in each business system, the feedback rating of the operator, and the feedback frequency of the operator are comprehensively assessed. If the above four indicators are higher, the content sensitivity index is larger.

Wherein, if the difference between the system anti-allergy index and the sum of the system sensitivity index is larger, the system anti-allergy index is larger, and the sum of the system sensitivity index is smaller, the business system

In an embodiment, the step specifically includes:

If the difference is greater than a preset first threshold, determining that the service system does not issue an early warning;

If the difference is less than or equal to the first threshold and greater than a preset second threshold, determining that the service system issues a slight alert;

If the difference is less than or equal to the second threshold and greater than a preset third threshold, determining that the service system issues a medium alert;

If the difference is less than or equal to the third threshold, it is determined that the service system issues a severe warning.

In a specific example, if the difference is greater than 90, it is determined that the service system does not issue an early warning; if the difference is less than or equal to 90 and greater than 60, it is determined that the service system issues a slight warning; if the difference is less than If it is equal to 60 and greater than 30, it is determined that the service system issues a medium warning; if the difference is less than or equal to 30, it is determined that the service system issues a severe warning.

Compared with the prior art, the present application calculates a system anti-allergy index for judging its ability to resist sensitive information for different business systems, and calculates a system sensitivity index for judging the degree of sensitive influence of the user's behavior on the business system. Sum, according to the difference between the two to determine whether the business system issues an early warning, this application comprehensively considers the actual application of the business system, each business system has different tolerance for sensitive information, and the rigor of users in each business system is different. Based on these two aspects, from the perspective of the practical application of the business system, combined with the business scenario and user behavior, the sensitive information is hierarchically evaluated to provide more accurate warning of sensitive information.

As shown in FIG. 2, FIG. 2 is a schematic flowchart of an embodiment of an early warning method for sensitive content of a system according to the present application. The method for alerting sensitive content of the system includes the following steps:

Step S1: acquiring respective anti-allergy parameters corresponding to the service system and weights corresponding to the respective anti-allergy parameters, and calculating a system anti-allergy index of the service system according to each anti-allergy parameter and corresponding weight;

Among them, the system anti-allergy index is an indicator of the ability of the business system to resist sensitive vocabulary. The higher the system anti-allergic index, the stronger the ability of the business system to resist sensitive vocabulary. In an embodiment, the anti-allergy parameter includes a system important level coefficient, a user quantity level coefficient, and a system information propagation coefficient; in another embodiment, the anti-allergy parameter includes a system important level coefficient, a user quantity level coefficient, and a system information propagation coefficient. , emergency response coefficient, sensitive vocabulary attention coefficient.

Step S2: acquiring a content sensitivity index and a user historical behavior index of each user published content in the service system, calculating a system sensitivity index of the user according to the content sensitivity index and the user historical behavior index, and comparing system sensitivity indexes of all users in the service system. Add the sum of the system sensitivity index;

Among them, the user's system sensitivity index is used to judge the degree of sensitive influence of the user's behavior on the business system. The smaller the user's system sensitivity index is, the smaller the sensitivity impact on the business system is. The greater the user's system sensitivity index, the greater the sensitivity to the business system.

Step S3: Calculate a difference between the system anti-allergy index corresponding to the service system and the sum of the system sensitivity indexes, and determine whether to issue an early warning according to the difference.

In an embodiment, the step specifically includes:

The present application calculates a system anti-allergy index for judging its ability to resist sensitive information for different business systems, and calculates a system sensitivity index for judging the degree of sensitive influence of the user's behavior on the business system, according to the difference between the two. The value determines whether the service system issues an early warning. The application considers that in the actual application of the service system, each service system has different tolerances for sensitive information, and the rigor of users in each service system is different, based on these two aspects. Based on the practical application of the business system, combined with the business scenario and user behavior, the sensitive information is hierarchically evaluated to provide more accurate warning of sensitive information.

The present application also provides a computer readable storage medium having stored thereon a processing system, the processing system being executed by a processor to implement the steps of the early warning method of system sensitive content.

The serial numbers of the embodiments of the present application are merely for the description, and do not represent the advantages and disadvantages of the embodiments.

Through the description of the above embodiments, those skilled in the art can clearly understand that the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in many cases, the former is better. Implementation. Based on such understanding, the technical solution of the present application, which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk, The optical disc includes a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present application.

The above is only a preferred embodiment of the present application, and is not intended to limit the scope of the patent application, and the equivalent structure or equivalent process transformations made by the specification and the drawings of the present application, or directly or indirectly applied to other related technical fields. The same is included in the scope of patent protection of this application.

Claims

An electronic device, comprising: a memory and a processor coupled to the memory, wherein the memory stores a processing system operable on the processor, the processing system being The processor implements the following steps when it executes:

The anti-allergy index processing step acquires each anti-allergy parameter corresponding to the business system and the weight corresponding to each anti-allergy parameter, and calculates a system anti-allergy index of the business system according to each anti-allergy parameter and corresponding weight;

The sensitive index processing step acquires the content sensitivity index and the user historical behavior index of each user's published content in the business system, calculates the system sensitivity index of the user according to the content sensitivity index and the user historical behavior index, and sensitive the system of all users in the business system. The sum of the indices gives the sum of the system sensitivity indices;

The early warning step is determined, and the difference between the system anti-allergy index corresponding to the business system and the sum of the system sensitivity indexes is calculated, and whether the early warning is issued is determined according to the difference.
The electronic device according to claim 1, wherein the anti-allergy parameter comprises a system importance level coefficient x1, a user quantity level coefficient x2, a system information propagation coefficient x3, an emergency processing coefficient x4, a sensitive vocabulary attention degree coefficient x5, The weights of the system important level coefficient x1, the user quantity level coefficient x2, the system information propagation coefficient x3, the emergency processing coefficient x4, and the sensitive vocabulary attention degree coefficient x5 are respectively w1, w2, w3, w4, w5, and the system is resistant. Sensitivity index = x1 * w1 + x2 * w2 + x3 * w3 + x4 * w4 + x5 * w5.
The electronic device according to claim 2, wherein the system important level coefficient x1 is calculated according to the weight of each business scenario in the service system and the traffic volume corresponding to each service scenario, and the business scenario includes a financial transaction scenario. And a common transaction scenario, the weight of the financial transaction scenario is k1, the weight of the common transaction scenario is k2, the traffic volume of the financial transaction scenario is c1, and the traffic volume of the common transaction scenario is c2, The system important level coefficient x1 of the business system is (k1+k2)/((πk1/2arctan(c1/α)+πk2/2arctan(c2/α)), where α is the average of the business scenarios of the business system Traffic, α = (c1 + c2) / 2.
The electronic device according to any one of claims 1 to 3, wherein the process of acquiring the content sensitivity index comprises: segmenting the content of the user to the sentence, and dividing the word after the word segmentation with the pre-established word. The words in the library are matched to match the corresponding keywords, and the corresponding core viewpoint information of each sentence is analyzed according to the keyword, and the core viewpoint information association is obtained according to the association relationship between the pre-established core viewpoint information and the content sensitive index. Content sensitivity index.
The electronic device according to any one of claims 1 to 3, wherein the determining the warning step comprises:

If the difference is greater than a preset first threshold, determining that the service system does not issue an early warning;

If the difference is less than or equal to the first threshold and greater than a preset second threshold, determining that the service system issues a slight alert;

If the difference is less than or equal to the second threshold and greater than a preset third threshold, determining that the service system issues a medium alert;

If the difference is less than or equal to the third threshold, it is determined that the service system issues a severe warning.
An early warning method for system sensitive content, characterized in that the method for warning the sensitive content of the system comprises:

S1, obtaining respective anti-allergy parameters corresponding to the service system and weights corresponding to the respective anti-allergy parameters, and calculating a system anti-allergy index of the service system according to each anti-allergy parameter and corresponding weight;

S2: obtaining a content sensitivity index and a user historical behavior index of content published by each user in the business system, calculating a system sensitivity index of the user according to the content sensitivity index and the user historical behavior index, and adding system sensitivity indexes of all users in the business system Get the sum of the system sensitivity index;

S3: Calculate the difference between the system anti-allergy index corresponding to the service system and the sum of the system sensitivity indexes, and determine whether to issue an early warning according to the difference.
The early warning method for sensitive content of a system according to claim 6, wherein the anti-allergy parameter comprises a system important level coefficient x1, a user quantity level coefficient x2, a system information propagation coefficient x3, an emergency processing coefficient x4, a sensitive vocabulary concern. The degree coefficient x5, the system important level coefficient x1, the user quantity level coefficient x2, the system information propagation coefficient x3, the emergency processing coefficient x4, the sensitive vocabulary attention degree coefficient x5 have weights corresponding to w1, w2, w3, w4, w5, respectively. The system anti-allergy index = x1 * w1 + x2 * w2 + x3 * w3 + x4 * w4 + x5 * w5.
The early warning method for the sensitive content of the system according to claim 7, wherein the system important level coefficient x1 is calculated according to the weight of each service scenario in the service system and the service volume corresponding to each service scenario, the service scenario Including a financial transaction scenario and a common transaction scenario, the financial transaction scenario has a weight of k1, the common transaction scenario has a weight of k2, the financial transaction scenario has a traffic volume of c1, and the normal transaction scenario has a traffic volume of C2, the system important level coefficient x1=(k1+k2)/((πk1/2arctan(c1/α)+πk2/2arctan(c2/α))) of the service system, wherein the α is the service system The average traffic of the business scenario, α = (c1 + c2) / 2.
The system for alerting the sensitive content of the system according to any one of claims 6 to 8, wherein the process of obtaining the content sensitive index comprises: segmenting the content of the user by using the sentence as a unit, and dividing the word after the word segmentation The words in the pre-established thesaurus are matched to match the corresponding keywords, and the corresponding core viewpoint information of each sentence is analyzed according to the keyword, and the relationship is obtained according to the association relationship between the pre-established core viewpoint information and the content sensitive index. The content sensitivity index associated with the core view information.
The method for alerting the sensitive content of the system according to any one of claims 6 to 8, wherein the step S3 comprises:

If the difference is greater than a preset first threshold, determining that the service system does not issue an early warning;

If the difference is less than or equal to the first threshold and greater than a preset second threshold, determining that the service system issues a slight alert;

If the difference is less than or equal to the second threshold and greater than a preset third threshold, determining that the service system issues a medium alert;

If the difference is less than or equal to the third threshold, it is determined that the service system issues a severe warning.
An early warning system for system sensitive content, characterized in that the early warning system for sensitive content of the system comprises:

The obtaining module is configured to obtain each anti-allergy parameter corresponding to the service system and a weight corresponding to each anti-allergy parameter, and calculate a system anti-allergy index of the service system according to each anti-allergy parameter and the corresponding weight;

The processing module is configured to obtain a content sensitivity index and a user historical behavior index of each user published content in the business system, calculate a system sensitivity index of the user according to the content sensitivity index and the user historical behavior index, and sensitivity the system of all users in the business system. The sum of the indices gives the sum of the system sensitivity indices;

The early warning module is configured to calculate a difference between the system anti-allergy index corresponding to the business system and the sum of the system sensitivity indexes, and determine whether to issue an early warning according to the difference.
The early warning system for sensitive content of a system according to claim 11, wherein the anti-allergy parameter comprises a system important level coefficient x1, a user quantity level coefficient x2, a system information propagation coefficient x3, an emergency processing coefficient x4, a sensitive vocabulary concern. The degree coefficient x5, the system important level coefficient x1, the user quantity level coefficient x2, the system information propagation coefficient x3, the emergency processing coefficient x4, the sensitive vocabulary attention degree coefficient x5 have weights corresponding to w1, w2, w3, w4, w5, respectively. The system anti-allergy index = x1 * w1 + x2 * w2 + x3 * w3 + x4 * w4 + x5 * w5.
The early warning system for system sensitive content according to claim 12, wherein the system important level coefficient x1 is calculated according to the weight of each service scenario in the service system and the traffic volume corresponding to each service scenario, the service scenario Including a financial transaction scenario and a common transaction scenario, the financial transaction scenario has a weight of k1, the common transaction scenario has a weight of k2, the financial transaction scenario has a traffic volume of c1, and the normal transaction scenario has a traffic volume of C2, the system important level coefficient x1=(k1+k2)/((πk1/2arctan(c1/α)+πk2/2arctan(c2/α))) of the service system, wherein the α is the service system The average traffic of the business scenario, α = (c1 + c2) / 2.
The early warning system for sensitive content of a system according to any one of claims 11 to 13, wherein the processing module is specifically configured to: perform word segmentation on a sentence-by-sentence basis for a user to post content, and pre-establish a word after the word segmentation. The words in the thesaurus are matched to match the corresponding keywords, and the corresponding core viewpoint information of each sentence is analyzed according to the keyword, and the core viewpoint is obtained according to the association relationship between the pre-established core viewpoint information and the content sensitive index. Content-sensitive index of information association.
The early warning system for the sensitive content of the system according to any one of claims 11 to 13, wherein the early warning module is specifically configured to: if the difference is greater than a preset first threshold, determine that the service system is not And sending an early warning; if the difference is less than or equal to the first threshold and greater than a preset second threshold, determining that the service system issues a slight warning; if the difference is less than or equal to the second threshold and greater than a preset The three thresholds determine that the service system issues a medium alert; if the difference is less than or equal to the third threshold, it is determined that the service system issues a severe alert.
A computer readable storage medium, wherein the computer readable storage medium stores a processing system, and when the processing system is executed by the processor, the steps are:

The anti-allergy index processing step acquires each anti-allergy parameter corresponding to the business system and the weight corresponding to each anti-allergy parameter, and calculates a system anti-allergy index of the business system according to each anti-allergy parameter and corresponding weight;

The sensitive index processing step acquires the content sensitivity index and the user historical behavior index of each user's published content in the business system, calculates the system sensitivity index of the user according to the content sensitivity index and the user historical behavior index, and sensitive the system of all users in the business system. The sum of the indices gives the sum of the system sensitivity indices;

The early warning step is determined, and the difference between the system anti-allergy index corresponding to the business system and the sum of the system sensitivity indexes is calculated, and whether the early warning is issued is determined according to the difference.
The computer readable storage medium according to claim 16, wherein the anti-allergy parameter comprises a system importance level coefficient x1, a user quantity level coefficient x2, a system information propagation coefficient x3, an emergency processing coefficient x4, a sensitive vocabulary attention degree. The coefficient x5, the weight of the system important level coefficient x1, the user quantity level coefficient x2, the system information propagation coefficient x3, the emergency processing coefficient x4, and the sensitive vocabulary attention degree coefficient x5 are respectively w1, w2, w3, w4, w5, The system anti-allergy index = x1 * w1 + x2 * w2 + x3 * w3 + x4 * w4 + x5 * w5.
The computer readable storage medium according to claim 17, wherein the system importance level coefficient x1 is calculated according to the weight of each service scenario in the service system and the traffic volume corresponding to each service scenario, where the service scenario includes The financial transaction scenario and the common transaction scenario, the weight of the financial transaction scenario is k1, the weight of the common transaction scenario is k2, the traffic volume of the financial transaction scenario is c1, and the traffic volume of the common transaction scenario is c2 The system important rank coefficient x1=(k1+k2)/((πk1/2arctan(c1/α)+πk2/2arctan(c2/α))), wherein the α is the service of the service system The average traffic of the scene, α = (c1 + c2) / 2.
The computer readable storage medium according to any one of claims 16 to 18, wherein the process of obtaining the content sensitivity index comprises: segmenting the content of the user to the sentence, and segmenting the word after the word segmentation with the word The words in the established thesaurus are matched to match the corresponding keywords, and the corresponding core viewpoint information of each sentence is analyzed according to the keyword, and the core is obtained according to the association relationship between the pre-established core viewpoint information and the content sensitive index. The content sensitivity index associated with the opinion information.
The computer readable storage medium according to any one of claims 16 to 18, wherein the determining the warning step comprises:

If the difference is greater than a preset first threshold, determining that the service system does not issue an early warning;

If the difference is less than or equal to the first threshold and greater than a preset second threshold, determining that the service system issues a slight alert;

If the difference is less than or equal to the second threshold and greater than a preset third threshold, determining that the service system issues a medium alert;

If the difference is less than or equal to the third threshold, it is determined that the service system issues a severe warning.