CN112464103A - Service processing method, device, server and storage medium - Google Patents
Service processing method, device, server and storage medium Download PDFInfo
- Publication number
- CN112464103A CN112464103A CN201910842052.6A CN201910842052A CN112464103A CN 112464103 A CN112464103 A CN 112464103A CN 201910842052 A CN201910842052 A CN 201910842052A CN 112464103 A CN112464103 A CN 112464103A
- Authority
- CN
- China
- Prior art keywords
- service
- content detection
- words
- content
- level
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title abstract description 11
- 238000001514 detection method Methods 0.000 claims abstract description 155
- 230000002159 abnormal effect Effects 0.000 claims abstract description 101
- 238000012545 processing Methods 0.000 claims abstract description 81
- 238000000034 method Methods 0.000 claims abstract description 52
- 230000008569 process Effects 0.000 claims description 23
- 230000000694 effects Effects 0.000 abstract description 8
- 238000011161 development Methods 0.000 description 7
- 230000035945 sensitivity Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000002860 competitive effect Effects 0.000 description 2
- 230000007123 defense Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Machine Translation (AREA)
Abstract
The disclosure discloses a service processing method, a service processing device, a server and a storage medium, and belongs to the technical field of internet. The method comprises the following steps: receiving a processing request for a target service, wherein the processing request carries a content detection level for detecting abnormal content of to-be-detected content of the target service; selecting a word stock matched with the content detection level from a service word stock for detecting target services in a word stock set, wherein the word stock set comprises at least one word stock for detecting the content of various services, and different word stocks correspond to different content detection levels; and performing abnormal content detection on the content to be detected based on the selected word stock. When a request for processing a target service is received, a word stock matched with the content detection level is selected according to the content detection level carried in the request, and then abnormal content detection is carried out on the content to be detected based on the selected word stock, so that the service requirements of the target service at different stages are met, and the service processing effect is good.
Description
Technical Field
The present disclosure relates to the field of internet technologies, and in particular, to a service processing method, an apparatus, a server, and a storage medium.
Background
In the technical field of internet, sensitive words are used as a first line of defense for text risk control and an indispensable link in basic text precautionary measures, and play a great role in a plurality of business scenes. And the service processing is carried out based on the sensitive words, and abnormal contents related to the text contents of the service can be detected, so that the damages of black products and competitive products are avoided, and the safe operation of the service is maintained.
At present, when the related technology carries out service processing based on sensitive words, the following method is mainly adopted: and a sensitive word library is preset for the service, and when a service processing request is received, abnormal content detection is carried out on the text content of the service based on the set sensitive word library so as to complete the processing process of the service.
However, the requirements for performing abnormal content detection on services at different stages are different, and the requirement for performing abnormal content detection at the initial stage is lower; the requirement for detecting abnormal content in the development stage is high, however, when the related technology performs service processing, the same processing mode is adopted for services with different requirements, resulting in poor service processing effect.
Disclosure of Invention
The embodiment of the disclosure provides a service processing method, a service processing device, a server and a storage medium, which can select different word banks for abnormal content detection aiming at services with different requirements, thereby greatly improving the service processing effect. The technical scheme is as follows:
in one aspect, a method for processing a service is provided, where the method includes:
receiving a processing request for a target service, wherein the processing request carries a content detection level for performing abnormal content detection on to-be-detected content of the target service;
selecting a word stock matched with the content detection level from a word stock set used for detecting the service word stock of the target service, wherein the word stock set comprises at least one word stock used for detecting the content of various services, and different word stocks correspond to different content detection levels;
and detecting abnormal contents of the contents to be detected based on the selected word stock.
In another embodiment of the present disclosure, the selecting a thesaurus matching the content detection level from the service thesaurus used for detecting the target service in the thesaurus set includes:
determining a service word stock used for detecting the target service in the word stock set;
if the content detection level is a first level, acquiring a first type word bank from the service word bank, wherein the first type word bank comprises sensitive words for abnormal content detection;
if the content detection level is a second level, acquiring a first type word bank and a second type word bank from the service word bank, wherein the second type word bank comprises service words for abnormal content detection;
and the second level is higher than the first level, and the association degree of the service words and the target service is greater than that of the sensitive words and the target service.
In another embodiment of the present disclosure, before the obtaining the first type lexicon and the second type lexicon from the service lexicon, the method further includes:
acquiring a third type word bank from the service word bank, wherein the third type word bank comprises core service words for abnormal content detection;
and deleting the core service words in the third type word bank, wherein the association degree of the core service words is greater than the association degree of the core service words with the target service, so as to obtain the second type word bank, and the core service is the service of which the user quantity exceeds a specified threshold value.
In another embodiment of the present disclosure, the performing, based on the selected lexicon, abnormal content detection on the content to be detected includes:
when the content detection level is a first level, performing abnormal content detection on the content to be detected based on the first type lexicon;
and when the content detection level is a second level, performing abnormal content detection on the content to be detected based on the first type word bank and the second type word bank.
In another embodiment of the present disclosure, before selecting a thesaurus matching the content detection level from the service thesaurus for detecting the target service in the thesaurus set, the method further includes:
sensitive words for detecting abnormal contents are obtained, and the obtained sensitive words form the first type word bank;
acquiring core service words for abnormal content detection, and forming the acquired core service words into the third type word bank;
and constructing the word stock set at least according to the first type word stock and the third type word stock.
In another embodiment of the present disclosure, after the obtaining of the core service word related to the core service and used for performing abnormal content detection, the method further includes:
and dividing the core service words in the third type word bank into different levels, wherein the core service words of each level have different processing modes when abnormal content detection is carried out.
In another embodiment of the present disclosure, after the detecting abnormal content of the content to be detected based on the selected lexicon, the method further includes:
when abnormal content detection is carried out on the content to be detected of the target service, new service words related to the target service are obtained;
and updating the second type word bank and the third type word bank based on the new service words related to the target service.
In another embodiment of the present disclosure, after the detecting abnormal content of the content to be detected based on the selected lexicon, the method further includes:
when abnormal content detection is carried out on the content to be detected of the core service, new service words related to the core service are obtained;
and updating the second type word bank and the third type word bank based on the new service words related to the core service.
In another aspect, a traffic processing apparatus is provided, and the apparatus includes:
the system comprises a receiving module, a processing module and a processing module, wherein the receiving module is used for receiving a processing request of a target service, and the processing request carries a content detection level for performing abnormal content detection on to-be-detected content of the target service;
a selecting module, configured to select a thesaurus matched with the content detection level from a service thesaurus for detecting the target service in a thesaurus set, where the thesaurus set includes at least one thesaurus for detecting contents of multiple services, and different thesaurus correspond to different content detection levels;
and the detection module is used for detecting abnormal contents of the contents to be detected based on the selected word stock.
In another embodiment of the present disclosure, the selecting module is configured to determine a service thesaurus in the thesaurus set, where the service thesaurus is used for detecting the target service; if the content detection level is a first level, acquiring a first type word bank from the service word bank, wherein the first type word bank comprises sensitive words for abnormal content detection; if the content detection level is a second level, acquiring a first type word bank and a second type word bank from the service word bank, wherein the second type word bank comprises service words for abnormal content detection;
and the second level is higher than the first level, and the association degree of the service words and the target service is greater than that of the sensitive words and the target service.
In another embodiment of the present disclosure, the apparatus further comprises:
the acquisition module is used for acquiring a third type word bank from the service word bank, wherein the third type word bank comprises core service words for abnormal content detection;
and the deleting module is used for deleting the core service words in the third type word bank, wherein the association degree of the core service words with the core service is greater than the association degree of the core service words with the target service, so as to obtain the second type word bank, and the core service is the service of which the user quantity exceeds a specified threshold value.
In another embodiment of the present disclosure, the detection module is configured to, when the content detection level is a first level, perform abnormal content detection on the content to be detected based on the first type lexicon; and when the content detection level is a second level, performing abnormal content detection on the content to be detected based on the first type word bank and the second type word bank.
In another embodiment of the present disclosure, the apparatus further comprises:
the acquisition module is used for acquiring sensitive words for abnormal content detection and forming the acquired sensitive words into the first type word bank;
the acquisition module is used for acquiring core service words for abnormal content detection and forming the acquired core service words into the third type word bank;
and the construction module is used for constructing the word stock set at least according to the first type word stock and the third type word stock.
In another embodiment of the present disclosure, the apparatus further comprises:
and the dividing module is used for dividing the core service words in the third type word bank into different levels, and when abnormal content detection is carried out, the core service words of each level have different processing modes.
In another embodiment of the present disclosure, the apparatus further comprises:
the acquisition module is used for acquiring a new service word related to the target service when the abnormal content detection is carried out on the content to be detected of the target service;
and the updating module is used for updating the second type word bank and the third type word bank based on the new service words related to the target service.
In another embodiment of the present disclosure, the apparatus further comprises:
the acquisition module is used for acquiring a new service word related to the core service when the abnormal content detection is carried out on the content to be detected of the core service;
and the updating module is used for updating the second type word bank and the third type word bank based on the new service words related to the core service.
In another aspect, a server is provided that includes a processor and a memory having stored therein at least one instruction, at least one program, set of codes, or set of instructions that is loaded and executed by the processor to implement a business process method.
In another aspect, a computer-readable storage medium is provided having stored therein at least one instruction, at least one program, set of codes, or set of instructions that is loaded and executed by a processor to implement a business process method.
The technical scheme provided by the embodiment of the disclosure has the following beneficial effects:
when a request for processing the target service is received, a word stock matched with the content detection level is selected according to the content detection level carried in the request, and then abnormal content detection is carried out on the content to be detected based on the selected word stock, so that the service requirements of the target service at different stages are met, and the service processing effect is good.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
Fig. 1 is an implementation environment related to a service processing method provided by an embodiment of the present disclosure;
fig. 2 is a flowchart of a service processing method according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a sensitive word hierarchy according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a process for updating a service thesaurus according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a service processing apparatus according to an embodiment of the present disclosure;
fig. 6 is a server illustrating a business process according to an example embodiment.
Detailed Description
To make the objects, technical solutions and advantages of the present disclosure more apparent, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.
Referring to fig. 1, an implementation environment related to a service processing method provided by the embodiment of the present disclosure is shown, where the implementation environment includes: a terminal 101 and a server 102.
The terminal 101 may be a smart phone, a tablet computer, a notebook computer, an e-book reader, and the like, and the product type of the terminal 101 is not specifically limited in the embodiments of the present disclosure. In order to meet the use requirements of users, at least one application program is installed in the terminal 101, and in the process of providing services to the users on the basis of each application program, the terminal 101 sends a service processing request to the server 102, so that the server 102 processes various services of each application program.
The server 102 is a background server, the server 102 maintains a thesaurus set, and can perform abnormal content detection on the text content in the service processing request, and when detecting that the text content contains abnormal content, the text content is processed, where the processing includes determining that the service processing process is invalid, replacing the abnormal content, and the like. For example, for the username change service, when the modified username involves abnormal content, the server 102 determines that the username change service is invalid.
The terminal 101 and the server 102 may communicate with each other through a wired network or a wireless network.
An embodiment of the present disclosure provides a service processing method, and referring to fig. 2, a flow of the method provided in the embodiment of the present disclosure includes:
201. the server constructs a word stock set in advance.
It can be known from analysis of different service scenarios that sensitive words often have indispensable relevance to sensitivity degrees in the actual application process, and the processing modes of the sensitive words with different sensitivity degrees are different when service processing is performed. For example, for some sensitive words that are pornographic, these sensitive words are not allowed to be published; for some rough statements of simply announcing the emotion of the content, different adjustments are usually made according to different application scenes; for the interplay terms of the daily circle, the words are allowed to be published freely in the social circle. According to the sensitivity degree, the sensitive words are classified finely, the method and the device are applicable to more service scenes, and the defense capability of the sensitive words in the aspect of content safety is expanded to a greater extent.
When the sensitive words are classified, the sensitive words can be classified into forbidden words, dangerous words and business words based on the black-white-grey attributes of the sensitive words. The attribute of the forbidden word is a blacklist, and the forbidden word is a word forbidden to be used in any service scene, for example, a word related to contents such as pornography, terrorism, murder and the like; the attribute of the dangerous words is a grey list, the dangerous words are words with illegal discipline and misleading user tendency, for example, words related to national politics, military affairs and leaders, the words are not available in most business scenes and can be used only in specific scenes, for example, scenes related to propagating leaders' spirit, singing countries and the like, and the words are generally required to be specially identified when being used; the attribute of the service word is a white list, the service word is a sensitive word defined in the current service scene, the service word can be repeatedly used in other service scenes, and the service word can be accumulated through service development. Considering that the user usage amounts of different services are different and the reliability of the obtained service words is also different, for some services in the initial stage, the user usage amount is smaller, and therefore the core service words related to the core service may not be obtained or the obtained service words are fewer. The core service is a service whose usage amount reaches a preset threshold or has a large influence, and the preset threshold can be set according to experience.
Based on the classification of the sensitive words, a word bank set for abnormal content detection can be constructed according to the sensitivity degree of the included sensitive words, the word bank set comprises at least one word bank for detecting the contents of various services, and different word banks correspond to different content detection levels. The at least one thesaurus comprises a first type thesaurus, a third type thesaurus and the like. The first type word bank comprises sensitive words for abnormal content detection, and the sensitive words comprise forbidden words and dangerous words in the classification. The third type word bank contains core service words for abnormal content detection.
When the server is used for the word stock set for abnormal content detection, the following method can be adopted:
2011. the server acquires sensitive words for abnormal content detection, and the acquired sensitive words form a first type word bank.
The server analyzes the sensitive words related to different service scenes to obtain the sensitive words used for abnormal content detection in different service scenes, such as the words related to pornography, terrorism, murder and the like, and further forms the obtained sensitive words into a first type word bank.
2012. The server acquires core service words for abnormal content detection, and the acquired core service words form a third type word bank.
In the core service operation process, the server collects core service words related to the core service and used for abnormal content detection, and the obtained core service words form a third type word bank.
2013. The server at least constructs a word stock set according to the first type word stock and the third type word stock.
And based on the obtained first type word bank and the third type word bank, the server constructs a word bank set according to the first type word bank and the third type word bank. In the process of processing other services, the server also constructs other types of word banks containing service words for abnormal content detection according to the third type of word bank, and then adds the constructed other types of word banks into the word bank set, thereby continuously enriching the word bank set.
In another embodiment of the present disclosure, considering that the application scenario of the service words is relatively complex, the core service words in the third type lexicon may be divided into different levels according to the sensitivity, and when abnormal content detection is performed, the core service words of each level have different processing modes. For example, as shown in fig. 1, the core service words are divided into level 1 words, level 2 words, level 3 words, level 4 words, and level 5 words, where the level 1 words correspond to a processing mode in which the related service words are replaced with similar non-sensitive words, the level 2 words correspond to a processing mode in which the related service words are deleted, the level 3 words correspond to a processing mode in which the text content is not published, the level 4 words correspond to a processing mode in which the user is prohibited from performing any operation for a period of time, and the level 5 words correspond to a processing mode in which an alarm processing is performed.
Fig. 3 is a schematic structural diagram of fine classification of sensitive words, referring to fig. 3, the sensitive words can be classified into three categories, namely forbidden words, dangerous words and business words, and the business words can be classified into five categories, namely level 1 words, level 2 words, level 3 words, level 4 words and level 5 words.
It should be noted that, when the service words are classified, the specific number of the classified categories may be divided according to actual service requirements, and the categories of the service words may be different in different service scenarios.
202. The server receives a processing request for the target service.
In the initial stage of the service, iteration and development of the service are usually concerned, content prevention and control does not belong to the core task of the service, but sometimes the service needs a certain degree of basic content security prevention and control capability, and the service is prevented from being damaged by black products or competitive products in the initial stage. With the continuous development of services, the content security and the service security are raised to a certain level, the interference of resisting black products is also raised to an important position, and at the moment, the first type word bank can not meet the security requirements of the services, and the service words are required to be protected together. It can be seen that the content detection levels for performing abnormal content detection on services at different stages are different, the content detection level at the initial stage is lower, and the content detection level at the development stage is higher.
When a user needs to process a certain service, the user can use the terminal to send a service processing request to the server, and considering that the content detection levels corresponding to target services at different stages are different, in order to process the target services at different stages in a targeted manner, when the terminal sends the service processing request to the server, the processing request can carry a content detection level for detecting abnormal content of the content to be detected of the target service, wherein the content detection level comprises a first level, a second level and the like, the second level is higher than the first level, the first level is used in a service initial stage, and the second level is used in a service development stage.
203. And the server selects a word bank matched with the content detection level from the service word bank which is concentrated in the word bank and used for detecting the target service.
When a service processing request is received, the server selects a word stock matched with the content detection level from the service word stocks which are concentrated in the word stock and used for detecting the target service according to the content detection level carried in the service processing request. When the process is implemented, the following method can be adopted:
2031. the server determines a service word stock used for detecting the target service in the word stock set.
The word stock set comprises a plurality of different types of word stocks, each service corresponds to different service word stocks, the server can determine a service word stock for detecting the target service from the word stock set according to the current target service to be processed, and the service word stock comprises different types of word stocks according to the content detection level carried in the processing request of the target service.
2032. And if the content detection level is the first level, the server acquires the first type word bank from the service word bank.
And when the content detection level is a first level, according to the content detection requirement of the first level, the server acquires a first type word bank from the business word bank, wherein the first type word bank comprises sensitive words for abnormal content detection.
2033. And if the content detection level is the second level, the server acquires the first type word bank and the second type word bank from the business word bank.
And when the content detection level is a second level, the server acquires the first type word bank and the second type word bank from the business word bank according to the content detection requirement of the first level. And the second type word bank comprises service words for detecting abnormal contents.
In order to avoid the explosive increase of the number of sensitive words in the word stock set along with the expansion of the service, only one part of the same words is reserved in the whole word stock set, so that before the server acquires the first type word stock and the second type word stock from the service word stock, the server can acquire the third type word stock from the service word stock, and a second type word stock is obtained by deleting core service words in the third type word stock, wherein the association degree of the core service words with the core service is greater than the association degree of the core service words with the target service, the second type word stock contains service words for detecting abnormal content of the target service, and the association degree of the service words in the second type word stock with the target service is greater than the association degree of the sensitive words in the first type word stock with the target service.
204. And the server detects abnormal content of the content to be detected based on the selected word stock.
And aiming at different content detection levels, the server detects abnormal content of the content to be detected of the target service based on the selected word stock. Specifically, the following two cases can be classified:
in the first case, when the content detection level is the first level, the server may perform abnormal content detection on the content to be detected based on the first type lexicon.
In the initial stage of the target service, the detection level for detecting the abnormal content of the target service is the first level, when a processing request with the content detection level being the first level is received, the server selects a first type lexicon from the lexicon set, and then the abnormal content detection is carried out on the content to be detected based on the first type lexicon. For example, when a processing request that the user changes the user name to a country leader is received, the server performs abnormal content detection based on the first type lexicon, and the target service is not processed because the text content of the processing request relates to the country leader.
In the second case, when the content detection level is the second level, the server may perform abnormal content detection on the content to be detected based on the first type lexicon and the second type lexicon.
In the development stage of the target service, the detection level for detecting the abnormal content of the target service is the second level, when a processing request with the detection level of the content being the second level is received, the server selects a first type lexicon and a second type lexicon from the lexicon set, and then the abnormal content detection is carried out on the content to be detected based on the first type lexicon and the second type lexicon.
After the abnormal content detection is carried out on the content to be detected based on the selected word stock, the server can also obtain a new service word related to the target service when the abnormal content detection is carried out on the content to be detected of the target service, and then update the second type word stock based on the new service word related to the target service. And after the second type word bank is updated, the server sends a notification message to a third type word bank, wherein the notification message comprises a new service word related to the target service, and the notification message is used for updating the third type word bank. Of course, when the abnormal content detection is performed on the content to be detected of the core service, the server may also obtain a new service word related to the core service, and update the third type lexicon based on the new service word related to the core service. And after the third type word bank is updated, the server sends a notification message to the second type word bank, wherein the notification message comprises a new service word related to the core service, and the notification message is used for updating the second type word bank. By adopting the mode, the second type word stock and the third type word stock can be updated mutually, and the mutual word stocks are continuously enriched.
Considering that the service words in the second-type word bank and the third-type word bank are divided into different levels, the service words of the same level can be adopted for updating when the divided levels are updated with each other. For example, fig. 4 shows an updating process of a third type word bank, and referring to fig. 4, in the core service processing process, when a level 1 word in the core service is updated, the level 1 word in the third type word bank may be updated according to the level 1 word updated by the core service, and the updated level 1 word is sent to the new service, so that the level 1 word in the type word bank of the new service is updated according to the level 1 word updated by the core service; when the level 1 word in the type word bank of the new service is updated, the level 1 word in the type word bank of the new service can be updated according to the level 1 word updated by the new service, and the updated level 1 word is sent to a third type word bank corresponding to the core service, so that the level 1 word in the third type word bank is updated according to the level 1 word updated by the new service. The above-mentioned example only uses the update of the level 1 word as an example, and the update process for the level 2 word, the level 3 word, the level 4 word and the level 5 word is the same as the above-mentioned process, and is not described again here.
According to the method provided by the embodiment of the disclosure, when a request for processing the target service is received, the word stock matched with the content detection level is selected according to the content detection level carried in the request, and then the abnormal content detection is performed on the content to be detected based on the selected word stock, so that the service requirements of the target service at different stages are met, and the service processing effect is good.
The embodiment of the disclosure also has the following beneficial effects:
firstly, the same word stock set is adopted to process different businesses, so that the maintenance cost of sensitive words is reduced, and the influence on service performance caused by the outbreak of word volumes due to business expansion is avoided.
Secondly, the use of the initial stage of the business is very convenient and maintenance is not needed, and the production process of the new business is directly accelerated.
Thirdly, the mapping between the service words is updated, so that the service word libraries corresponding to the two services can be cooperated and enriched.
Referring to fig. 5, an embodiment of the present disclosure provides a service processing apparatus, where the apparatus includes:
a receiving module 501, configured to receive a processing request for a target service, where the processing request carries a content detection level for performing abnormal content detection on to-be-detected content of the target service;
a selecting module 502, configured to select a thesaurus matched with the content detection level from a service thesaurus that is used for detecting a target service in a thesaurus set, where the thesaurus set includes at least one thesaurus for detecting contents of multiple services, and different thesaurus correspond to different content detection levels;
the detecting module 503 is configured to perform abnormal content detection on the content to be detected based on the selected lexicon.
In another embodiment of the present disclosure, the selecting module 502 is configured to determine a service thesaurus in a thesaurus set for detecting a target service; if the content detection level is a first level, acquiring a first type word bank from the business word bank, wherein the first type word bank comprises sensitive words for abnormal content detection; if the content detection level is a second level, acquiring a first type word bank and a second type word bank from the business word bank, wherein the second type word bank comprises business words for abnormal content detection;
and the second level is higher than the first level, and the association degree of the service words and the target service is higher than that of the sensitive words and the target service.
In another embodiment of the present disclosure, the apparatus further comprises:
the acquisition module is used for acquiring a third type word bank from the service word bank, wherein the third type word bank comprises core service words for abnormal content detection;
and the deleting module is used for deleting the core service words in the third type word bank, wherein the association degree of the core service words is greater than the association degree of the core service words with the target service, so as to obtain a second type word bank, and the core service is the service of which the user quantity exceeds the specified threshold value.
In another embodiment of the present disclosure, the detecting module 503 is configured to, when the content detection level is a first level, perform abnormal content detection on the content to be detected based on the first type lexicon; and when the content detection level is a second level, performing abnormal content detection on the content to be detected based on the first type word bank and the second type word bank.
In another embodiment of the present disclosure, the apparatus further comprises:
the acquisition module is used for acquiring sensitive words for abnormal content detection and forming a first type word bank by the acquired sensitive words;
the acquisition module is used for acquiring core service words for abnormal content detection and forming a third type word bank by the acquired core service words;
and the building module is used for building a word stock set at least according to the first type word stock and the third type word stock.
In another embodiment of the present disclosure, the apparatus further comprises:
and the dividing module is used for dividing the core service words in the third type word bank into different levels, and when abnormal content detection is carried out, the core service words of each level have different processing modes.
In another embodiment of the present disclosure, the apparatus further comprises:
the acquisition module is used for acquiring a new service word related to the target service when the abnormal content detection is carried out on the content to be detected of the target service;
and the updating module is used for updating the second type word bank and the third type word bank based on the new service words related to the target service.
In another embodiment of the present disclosure, the apparatus further comprises:
the acquisition module is used for acquiring a new service word related to the core service when the abnormal content detection is carried out on the content to be detected of the core service;
and the updating module is used for updating the second type word bank and the third type word bank based on the new service words related to the core service.
In summary, when a request for processing a target service is received, the device provided in the embodiment of the present disclosure selects a lexicon matched with the content detection level according to the content detection level carried in the request, and further performs abnormal content detection on the content to be detected based on the selected lexicon, so that the service requirements of the target service at different stages are met, and the service processing effect is good.
Fig. 6 is a server illustrating a business process according to an example embodiment. Referring to fig. 6, server 600 includes a processing component 622 that further includes one or more processors and memory resources, represented by memory 632, for storing instructions, such as applications, that are executable by processing component 622. The application programs stored in memory 632 may include one or more modules that each correspond to a set of instructions. Further, the processing component 622 is configured to execute instructions to perform the functions performed by the server in sensitive word-based business processing described above.
The server 600 may also include a power component 626 configured to perform power management of the server 600, a wired or wireless network interface 650 configured to connect the server 600 to a network, and an input/output (I/O) interface 658. The Server 600 may operate based on an operating system, such as Windows Server, stored in the memory 632TM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTMOr the like.
According to the server provided by the embodiment of the disclosure, when a request for processing a target service is received, a word stock matched with a content detection level is selected according to the content detection level carried in the request, and then abnormal content detection is performed on the content to be detected based on the selected word stock, so that the service requirements of the target service at different stages are met, and the service processing effect is good.
The embodiment of the present disclosure provides a computer-readable storage medium, in which at least one instruction, at least one program, a code set, or a set of instructions is stored, and the at least one instruction, the at least one program, the code set, or the set of instructions is loaded and executed by a processor to implement the service processing method shown in fig. 2.
When a request for processing a target service is received, a lexicon matched with the content detection level is selected according to the content detection level carried in the request, and then abnormal content detection is performed on the content to be detected based on the selected lexicon, so that the service requirements of the target service at different stages are met, and the service processing effect is good.
It should be noted that: in the service processing apparatus provided in the foregoing embodiment, when performing service processing, only the division of the functional modules is illustrated, and in practical applications, the function allocation may be completed by different functional modules according to needs, that is, the internal structure of the service processing apparatus is divided into different functional modules to complete all or part of the functions described above. In addition, the service processing apparatus and the service processing method provided by the above embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments for details, which are not described herein again.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only exemplary of the present disclosure and is not intended to limit the present disclosure, so that any modification, equivalent replacement, or improvement made within the spirit and principle of the present disclosure should be included in the scope of the present disclosure.
Claims (10)
1. A method for processing a service, the method comprising:
receiving a processing request for a target service, wherein the processing request carries a content detection level for performing abnormal content detection on to-be-detected content of the target service;
selecting a word stock matched with the content detection level from a word stock set used for detecting the service word stock of the target service, wherein the word stock set comprises at least one word stock used for detecting the content of various services, and different word stocks correspond to different content detection levels;
and detecting abnormal contents of the contents to be detected based on the selected word stock.
2. The method of claim 1, wherein selecting a thesaurus matching the content detection level from a set of thesaurus used for detecting the service target comprises:
determining a service word stock used for detecting the target service in the word stock set;
if the content detection level is a first level, acquiring a first type word bank from the service word bank, wherein the first type word bank comprises sensitive words for abnormal content detection;
if the content detection level is a second level, acquiring a first type word bank and a second type word bank from the service word bank, wherein the second type word bank comprises service words for abnormal content detection;
and the second level is higher than the first level, and the association degree of the service words and the target service is greater than that of the sensitive words and the target service.
3. The method of claim 2, wherein before obtaining the first type lexicon and the second type lexicon from the service lexicon, further comprising:
acquiring a third type word bank from the service word bank, wherein the third type word bank comprises core service words for abnormal content detection;
and deleting the core service words in the third type word bank, wherein the association degree of the core service words is greater than the association degree of the core service words with the target service, so as to obtain the second type word bank, and the core service is the service of which the user quantity exceeds a specified threshold value.
4. The method according to claim 2, wherein the performing abnormal content detection on the content to be detected based on the selected lexicon comprises:
when the content detection level is a first level, performing abnormal content detection on the content to be detected based on the first type lexicon;
and when the content detection level is a second level, performing abnormal content detection on the content to be detected based on the first type word bank and the second type word bank.
5. The method according to any one of claims 1 to 4, wherein before selecting the thesaurus matching the content detection level from the service thesaurus for detecting the target service in the thesaurus set, further comprising:
sensitive words for detecting abnormal contents are obtained, and the obtained sensitive words form the first type word bank;
acquiring core service words for abnormal content detection, and forming the acquired core service words into the third type word bank;
and constructing the word stock set at least according to the first type word stock and the third type word stock.
6. The method according to claim 3, wherein after the detecting the abnormal content of the content to be detected based on the selected lexicon, the method further comprises:
when abnormal content detection is carried out on the content to be detected of the target service, new service words related to the target service are obtained;
and updating the second type word bank and the third type word bank based on the new service words related to the target service.
7. The method according to claim 3, wherein after the detecting the abnormal content of the content to be detected based on the selected lexicon, the method further comprises:
when abnormal content detection is carried out on the content to be detected of the core service, new service words related to the core service are obtained;
and updating the second type word bank and the third type word bank based on the new service words related to the core service.
8. A traffic processing apparatus, characterized in that the apparatus comprises:
the system comprises a receiving module, a processing module and a processing module, wherein the receiving module is used for receiving a processing request of a target service, and the processing request carries a content detection level for performing abnormal content detection on to-be-detected content of the target service;
a selecting module, configured to select a thesaurus matched with the content detection level from a service thesaurus for detecting the target service in a thesaurus set, where the thesaurus set includes at least one thesaurus for detecting contents of multiple services, and different thesaurus correspond to different content detection levels;
and the detection module is used for detecting abnormal contents of the contents to be detected based on the selected word stock.
9. A server, characterized in that it comprises a processor and a memory, in which at least one instruction, at least one program, a set of codes or a set of instructions is stored, which is loaded and executed by the processor to implement the business process method of any one of claims 1 to 7.
10. A computer readable storage medium, having stored therein at least one instruction, at least one program, a set of codes, or a set of instructions, which is loaded and executed by a processor to implement a business process method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910842052.6A CN112464103A (en) | 2019-09-06 | 2019-09-06 | Service processing method, device, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910842052.6A CN112464103A (en) | 2019-09-06 | 2019-09-06 | Service processing method, device, server and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112464103A true CN112464103A (en) | 2021-03-09 |
Family
ID=74807129
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910842052.6A Pending CN112464103A (en) | 2019-09-06 | 2019-09-06 | Service processing method, device, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112464103A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113824804A (en) * | 2021-11-24 | 2021-12-21 | 飞狐信息技术（天津）有限公司 | Keyword detection method and related device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015154217A1 (en) * | 2014-04-08 | 2015-10-15 | 华为终端有限公司 | Failure detection method and device |
| CN107730841A (en) * | 2017-09-08 | 2018-02-23 | 深圳市盛路物联通讯技术有限公司 | Alarm processing method and related product |
| CN108718307A (en) * | 2018-05-10 | 2018-10-30 | 北京工业大学 | A kind of behavior retrospect detection method internally threatened below IaaS cloud environment |
| CN108763372A (en) * | 2018-05-17 | 2018-11-06 | 上海尬词教育科技有限公司 | Interactive learning methods, system, program product and mobile terminal |
| CN109032824A (en) * | 2018-05-31 | 2018-12-18 | 康键信息技术（深圳）有限公司 | Database method of calibration, device, computer equipment and storage medium |
| CN110162621A (en) * | 2019-02-22 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Disaggregated model training method, abnormal comment detection method, device and equipment |
-
2019
- 2019-09-06 CN CN201910842052.6A patent/CN112464103A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015154217A1 (en) * | 2014-04-08 | 2015-10-15 | 华为终端有限公司 | Failure detection method and device |
| CN107730841A (en) * | 2017-09-08 | 2018-02-23 | 深圳市盛路物联通讯技术有限公司 | Alarm processing method and related product |
| CN108718307A (en) * | 2018-05-10 | 2018-10-30 | 北京工业大学 | A kind of behavior retrospect detection method internally threatened below IaaS cloud environment |
| CN108763372A (en) * | 2018-05-17 | 2018-11-06 | 上海尬词教育科技有限公司 | Interactive learning methods, system, program product and mobile terminal |
| CN109032824A (en) * | 2018-05-31 | 2018-12-18 | 康键信息技术（深圳）有限公司 | Database method of calibration, device, computer equipment and storage medium |
| CN110162621A (en) * | 2019-02-22 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Disaggregated model training method, abnormal comment detection method, device and equipment |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113824804A (en) * | 2021-11-24 | 2021-12-21 | 飞狐信息技术（天津）有限公司 | Keyword detection method and related device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110677380B (en) | Method and related apparatus for cyber threat indicator extraction and response | |
| US10264009B2 (en) | Automated machine learning scheme for software exploit prediction | |
| US11159556B2 (en) | Predicting vulnerabilities affecting assets of an enterprise system | |
| CN106295333B (en) | method and system for detecting malicious code | |
| CN112564988B (en) | Alarm processing method and device and electronic equipment | |
| AU2018278877A1 (en) | Automatically detecting an event and determining whether the event is a particular type of event | |
| US20130290347A1 (en) | Systems and methods for providing data-driven document suggestions | |
| CN112422484B (en) | Method, apparatus, and storage medium for determining scenario for processing security event | |
| US11146586B2 (en) | Detecting a root cause for a vulnerability using subjective logic in social media | |
| US9123025B2 (en) | Detection and prevention of spam in tagging systems | |
| CN109413016B (en) | Rule-based message detection method and device | |
| CN111160624B (en) | User intention prediction method, user intention prediction device and terminal equipment | |
| CN105468975A (en) | Method, device and system for tracking malicious code misinformation | |
| CN111030974A (en) | APT attack event detection method, device and storage medium | |
| CN112464103A (en) | Service processing method, device, server and storage medium | |
| CN113992371A (en) | Method and device for generating threat tag of flow log and electronic equipment | |
| CN113849813A (en) | Data detection method and device, electronic equipment and storage medium | |
| CN113037714A (en) | Network security analysis method based on network big data and block chain financial cloud system | |
| CN106709353B (en) | Security detection method and device for search engine | |
| CN115310077A (en) | Page display method, device and equipment for abnormal information | |
| CN115809466B (en) | Security requirement generation method and device based on STRIDE model, electronic equipment and medium | |
| CN115269879B (en) | Knowledge structure data generation method, data search method and risk warning method | |
| CN115150130B (en) | Tracking analysis method, device, equipment and storage medium for attack group | |
| La | Prioritizing Cybersecurity Controls Based on the Coverage of Attack Techniques and Attack Probabilities | |
| CN115396280B (en) | Alarm data processing method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |