CN113761908A

CN113761908A - Method and device for processing stock user information

Info

Publication number: CN113761908A
Application number: CN202011355371.3A
Authority: CN
Inventors: 范瑞丰
Original assignee: Beijing Jingdong Century Trading Co Ltd; Beijing Wodong Tianjun Information Technology Co Ltd
Current assignee: Beijing Jingdong Century Trading Co Ltd; Beijing Wodong Tianjun Information Technology Co Ltd
Priority date: 2020-11-26
Filing date: 2020-11-26
Publication date: 2021-12-07

Abstract

The invention discloses a method and a device for processing stock user information, and relates to the technical field of computers. One embodiment of the method comprises: responding to a processing request for the storage user information, and training by adopting a natural language processing algorithm and a gradient lifting tree algorithm to obtain a recognition model; acquiring stock user information, calling an identification model to detect the stock user information, acquiring target words and target word grades existing in the stock user information, and generating a grade set of the stock user information; and calling a corresponding flow in the processing flow library according to the highest level in the level set to process the storage user information. The implementation method can adopt a natural language processing algorithm and a gradient lifting tree algorithm to train to obtain the recognition model, and calls the recognition model to detect the storage user information to obtain the target words and the target word grades existing in the storage user information, so as to call a corresponding flow to process, and perform safety control on the storage user information content.

Description

Method and device for processing stock user information

Technical Field

The invention relates to the technical field of computers, in particular to a method and a device for processing stock user information.

Background

The user information content in the internet system needs to be subjected to content security management from the system level, so that the user information content is prevented from violating national laws and regulations or infringing rights and interests of other people. In the prior art, a fixed target word bank is generally used for detecting and processing newly registered information or newly released information of a user.

In the process of implementing the invention, the prior art at least has the following problems:

since the target word stock is fixed, there is little effect in detecting the user information of the stock, and thus the content of the user information of the stock cannot be safely controlled.

Disclosure of Invention

In view of this, embodiments of the present invention provide a method and an apparatus for processing stock user information, which can perform model training by using a natural language processing algorithm and a gradient lifting tree algorithm to obtain an identification model capable of identifying a target word and an extension word of the target word, and call the identification model to detect the stock user information to obtain a target word and a target word level existing in the stock user information, and further call a corresponding process in a processing flow library to perform processing, so as to perform security control on the content of the stock user information.

To achieve the above object, according to an aspect of an embodiment of the present invention, there is provided a method for processing user information in stock, including:

in response to a processing request for the storage user information, a user information sample, sample characteristics and a sample label are called, and an algorithm and a gradient lifting tree algorithm are adopted for training to obtain an identification model;

acquiring stock user information, calling the identification model to detect the stock user information, acquiring target words and target word grades existing in the stock user information, and generating a grade set of the stock user information;

and calling a process corresponding to the highest grade in a process flow library according to the highest grade in the grade set, and updating the authority configuration information of the stock user.

Optionally, the retrieving the user information sample, the sample feature, and the sample tag includes:

calling user information historical data of a known processing result, and selecting a preset amount of historical user information from the historical user information as the user information sample;

taking the characteristics of the historical user information as the sample characteristics; and taking the corresponding grade of the historical user information in the processing result and the grade of the historical target word in the historical user information as the sample label.

Optionally, the training by using a natural language processing algorithm and a gradient lifting tree algorithm obtains a recognition model, including:

performing word segmentation processing on the historical user information by adopting a natural language processing algorithm, and performing voice and semantic expansion on words obtained by word segmentation processing on the basis of the called public opinion information to obtain a historical expansion word set;

and using the historical user information and the historical extension word set as training samples together, and training by adopting a gradient lifting tree algorithm according to the training samples, the sample characteristics and the sample labels to obtain the recognition model.

Optionally, the level set of inventory user information includes: the target words, the target word grades, the stock user information corresponding to the target words and the user identifications of the stock users corresponding to the target words;

the step of calling a process corresponding to the highest level in a process library according to the highest level in the level set, and updating the authority configuration information of the stock user comprises the following steps:

for the same user identification, taking the highest level in the target word levels of the target words in the stock user information as the level of the stock user information; taking the highest grade in the grades of all the stock user information of the stock users as the grade of the stock user;

and calling a process corresponding to the level of the stock user in a process flow library, and updating the authority configuration information of the stock user.

Optionally, the invoking a process corresponding to the level of the stock user in the process flow library, and updating the authority configuration information of the stock user includes:

when the level of the stock user is high, forbidding the use permission of the user account of the stock user, and informing the stock user;

when the level of the stock user is middle, forbidding the display authority of the user information in the level of the stock user, and informing the stock user;

when the level of the stock user is low, limiting the display authority of the target word with the low level in the user information of the stock user, and informing the stock user;

wherein the user information at least comprises: user registration information and user release information.

Optionally, after the step of calling the recognition model to detect the inventory user information, the method further includes:

generating an expanded target word set according to the target words and the target word grades existing in the stock user information and the expanded words and the expanded word grades generated in the detection process;

and the expanded target word set is used for detecting new user registration information or new user release information.

Optionally, the method for processing the stock user information further includes:

obtaining model evaluation data, evaluating the recognition model according to the model evaluation data, and generating a first evaluation result; optimizing the recognition model according to the first evaluation result; and/or the presence of a gas in the gas,

after the authority configuration information of the stock user is updated, receiving user feedback information sent by a client, and generating a second evaluation result according to the user feedback information; and optimizing the recognition model according to the second evaluation result.

According to still another aspect of an embodiment of the present invention, there is provided a processing apparatus of stock user information, including:

the training module is used for responding to a processing request of the storage user information, calling a user information sample, sample characteristics and a sample label, and training by adopting a natural language processing algorithm and a gradient lifting tree algorithm to obtain an identification model;

the detection module is used for acquiring stock user information, calling the identification model to detect the stock user information, acquiring a target word and a target word grade existing in the stock user information, and generating a grade set of the stock user information;

and the processing module is used for calling a process corresponding to the highest level in a process flow library according to the highest level in the level set and updating the authority configuration information of the stock user.

Optionally, the processing device of the stock user information is further configured to:

According to another aspect of the embodiments of the present invention, there is provided an electronic device for processing user information on an inventory, including:

one or more processors;

a storage device for storing one or more programs,

when the one or more programs are executed by the one or more processors, the one or more processors implement the method for processing the user information inventory provided by the present invention.

According to still another aspect of an embodiment of the present invention, there is provided a computer-readable medium on which a computer program is stored, the program implementing the method for processing user information on an inventory provided by the present invention when executed by a processor.

One embodiment of the above invention has the following advantages or benefits: because the model training is carried out by adopting the natural language processing algorithm and the gradient lifting tree algorithm, the recognition model capable of recognizing the target word and the expansion word of the target word is obtained, and the recognition model is called to detect the storage user information so as to carry out corresponding processing; after detecting the stock user information, an expansion word set can be obtained for detecting new user information; therefore, the technical problems that safety control cannot be carried out on the stored user information content and the safety control effect of the user information by using the fixed word bank is poor in the prior art are solved; and then the safety control can be carried out on the content of the stored user information, and the technical effect of better controlling the new user information can be achieved based on the original fixed word bank and the obtained expansion word set.

Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.

Drawings

The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:

fig. 1 is a schematic diagram of a main flow of a processing method of stock user information according to a first embodiment of the present invention;

fig. 2 is a schematic diagram of a flow of a method of processing inventory user information according to a second embodiment of the present invention;

FIG. 3 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;

fig. 4 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.

Detailed Description

Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Fig. 1 is a schematic diagram of a main flow of a method for processing user information on an inventory according to a first embodiment of the present invention, as shown in fig. 1, including:

step 101, responding to a processing request of user information of stock, calling a user information sample, sample characteristics and a sample label, and training by adopting a natural language processing algorithm and a gradient lifting tree algorithm to obtain an identification model;

102, obtaining stock user information, calling the identification model to detect the stock user information, obtaining target words and target word grades in the stock user information, and generating a grade set of the stock user information;

step 103, according to the highest level in the level set, calling a process corresponding to the highest level in a process flow library, and updating the authority configuration information of the stock user.

The user information may be information sent by the user to the internet through the client, such as: information registered by a user (such as a user name, address information filled by the user and the like), information published by the user on a platform (such as short sentence information and article information published by the user in a forum, comment information and message information published in a certain shopping website, communication information in a net friend group and the like); the stock user information can be user information which is currently reserved in the Internet; the target word may be a word that violates national laws and regulations or infringes the interests of others, such as a commonly recognized "sensitive word", or a word that cannot be exhibited based on platform regulations; the target word level can be preset, can be represented by numbers (such as 0, 1, 2, 3, and the like) or language descriptions (such as none, low, medium, high, zero level, first level, second level, and the like), and can be safely managed and controlled as the level number is higher; the flow library may store preset processing method flows corresponding to the respective levels, and may set a processing method having a higher corresponding level as a stricter processing method.

The embodiment of the invention provides a method and a device for processing stock user information, which can adopt a natural language processing algorithm and a gradient lifting tree algorithm to carry out model training to obtain an identification model capable of identifying a target word and an extension word of the target word, and call the identification model to detect the stock user information to obtain the target word and the grade of the target word existing in the stock user information, so as to call a corresponding flow in a processing flow library to process and safely control the information content of the stock user.

In some embodiments, the retrieving the user information sample, the sample feature, and the sample label includes:

calling user information historical data of a known processing result, and selecting a preset amount of historical user information from the historical user information as the user information sample; taking the characteristics of the historical user information as the sample characteristics; and taking the corresponding grade of the historical user information in the processing result and the grade of the historical target word in the historical user information as the sample label.

Further, in some embodiments, the training using the natural language processing algorithm and the gradient lifting tree algorithm obtains the recognition model, including:

performing word segmentation processing on the historical user information by adopting a natural language processing algorithm, and performing voice and semantic expansion on words obtained by word segmentation processing on the basis of the called public opinion information to obtain a historical expansion word set; and using the historical user information and the historical extension word set as training samples together, and training by adopting a gradient lifting tree algorithm according to the training samples, the sample characteristics and the sample labels to obtain the recognition model.

The features may be used to describe user information, such as: the change frequency of the user information, whether the user information contains known target words, the number of the contained known target words or the grade of the target words, whether a safety control record exists in a user account corresponding to the user information, whether a complaint request has never been initiated by the user account corresponding to the user information, and the like. The sample characteristics can be obtained through learning in other modes or obtained according to the stipulations of a network platform, and the selection of the sample characteristics can be updated through subsequent optimization; the public opinion information can comprise public opinion condition information and also can comprise information categories which are specified by national relevant laws and regulations or a network platform and need security control;

the natural language processing algorithm is adopted to carry out voice and semantic expansion on the target word to obtain an expanded word of the target word, and the expanded word can be considered as a word which has certain association with the target word in voice and/or semantic; based on the association, the corresponding target words can be associated with the expanded words in daily language use of people; therefore, since the target word needs to be securely managed, security management needs to be performed on the extension word, which is lacking in the prior art. The identification model is trained by the method, so that the identification model can be identified according to the input user information based on the existing sample, sample characteristics, sample labels and public opinion information, and target words and target word grades in the user information are output; at this time, words expanded from known target words may exist in the target words in the identified user information, so that an effect of more comprehensive security control on the user information is achieved.

In some embodiments, the set of levels of inventory user information comprises: the target words, the target word grades, the stock user information corresponding to the target words and the user identifications of the stock users corresponding to the target words;

for the same user identification, taking the highest level in the target word levels of the target words in the stock user information as the level of the stock user information; taking the highest grade in the grades of all the stock user information of the stock users as the grade of the stock user; and calling a process corresponding to the level of the stock user in a process flow library, and updating the authority configuration information of the stock user.

Further, in some embodiments, the invoking a process corresponding to the level of the stock user in the process flow library, and updating the authority configuration information of the stock user includes:

when the level of the stock user is high, forbidding the use permission of the user account of the stock user, and informing the stock user; when the level of the stock user is middle, forbidding the display authority of the user information in the level of the stock user, and informing the stock user; when the level of the stock user is low, limiting the display authority of the target word with the low level in the user information of the stock user, and informing the stock user;

After the stock user information is detected by using the identification model, the target words and the target word grades in the stock user information can be obtained, so that a grade set of the stock user information is generated, and the grade of the stock user information and the grade of the stock user can be determined according to the grade set by the method; such as:

for user identity a, it registers user account a 1; if the inventory user A1 publishes the information B1 and the information B2, the detection confirms that the target word c and the target word d exist in the information B1, the grade of the target word c is 1, the grade of the target word d is 3, and the information B2 is detected to contain no target word; the following information can be derived from the above information: the level of the stock user information B1 is determined to be 3 by the level of the target word d, and the level of the stock user information B2 is 0; the rank of the inventory user a1 is determined to be 3 by the rank of the inventory user information B1.

In the processing flow, when the level of the user in stock is high, the account number of the user in high level can be frozen after manual examination; when the level of the inventory user is middle, corresponding user information can be reset for the middle-level account; when the level of the inventory user is low, the corresponding user information can be displayed by using a mask.

In some practical applications, there may be multiple user identities for the same real user (natural person) (e.g., multiple accounts registered with different authentication information), in which case the natural person may be rated: through the identification of the natural person, the level of the natural person is the same as the highest level in all the user levels, and the authority configuration information of all the users registered by the natural person is updated according to the flow corresponding to the level of the natural person.

In some embodiments, after invoking the recognition model to detect the inventory user information, the method further includes:

According to the recognition model obtained by training, when stock user information is detected, an expanded target word set can be generated according to the target words and the target word grades existing in the obtained stock user information and the expanded words and the expanded word grades generated in the detection process, so that new user registration information or new user release information can be detected. In some practical applications, the extended target word set may also be called by other system interfaces or other network platforms, and is directly used for detecting security control of other information.

In some embodiments, the method for processing the stock user information further includes:

By the method, the recognition model can be optimized in time so as to be more accurate in recognition and obtain better use effect.

Fig. 2 is a schematic diagram of main blocks of a stock user information processing apparatus 200 according to a third embodiment of the present invention, and as shown in fig. 2, the stock user information processing apparatus 200 includes:

the training module 201 is used for responding to a processing request for the storage user information, calling a user information sample, sample characteristics and a sample label, and training by adopting a natural language processing algorithm and a gradient lifting tree algorithm to obtain an identification model;

the detection module 202 is configured to obtain stock user information, call the identification model to detect the stock user information, obtain a target word and a target word level that are present in the stock user information, and generate a level set of the stock user information;

and the processing module 203 is configured to invoke a process corresponding to the highest level in a process flow library according to the highest level in the level set, and update the authority configuration information of the stock user.

According to the recognition model obtained by training, storage user information can be detected, and meanwhile, an expanded target word set can be generated according to the target words and the target word grades in the obtained storage user information and the expanded words and the expanded word grades generated in the detection process, so that new user registration information or new user release information can be detected. In some practical applications, the extended target word set may also be called by other system interfaces or other network platforms, and is directly used for detecting security control of other information.

In some embodiments, the processing device of the inventory user information is further configured to:

Fig. 3 illustrates an exemplary system architecture 300 of a method of processing inventory user information or a device for processing inventory user information to which embodiments of the present invention may be applied.

As shown in fig. 3, the system architecture 300 may include

terminal devices

301, 302, 303, a network 304, and a server 305. The network 304 serves as a medium for providing communication links between the

terminal devices

301, 302, 303 and the server 305. Network 304 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The user may use the

terminal device

301, 302, 303 to interact with the server 305 via the network 304 to receive or send messages or the like. The

terminal devices

301, 302, 303 may have various client applications installed thereon, such as shopping-like applications, blog-like applications, search-like applications, instant messaging tools, mailbox clients, social platform software, and the like.

The

terminal devices

301, 302, 303 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 305 may be a server providing various services, such as a background management server providing support for shopping websites browsed by the user using the

terminal devices

301, 302, 303. The background management server can process the received data such as the user information detection request and the like and feed back the processing result to the terminal equipment.

It should be noted that the method for processing the user information of the stock quantity provided by the embodiment of the present invention is generally executed by the server 305, and accordingly, a processing device for the user information of the stock quantity is generally disposed in the server 305.

It should be understood that the number of terminal devices, networks, and servers in fig. 3 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

Referring now to FIG. 4, a block diagram of a computer system 400 suitable for use with a terminal device implementing an embodiment of the invention is shown. The terminal device shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.

As shown in fig. 4, the computer system 400 includes a Central Processing Unit (CPU)401 that can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)402 or a program loaded from a storage section 408 into a Random Access Memory (RAM) 403. In the RAM 403, various programs and data necessary for the operation of the system 400 are also stored. The CPU 401, ROM 402, and RAM 403 are connected to each other via a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.

The following components are connected to the I/O interface 405: an input section 406 including a keyboard, a mouse, and the like; an output section 407 including a display device such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 408 including a hard disk and the like; and a communication section 409 including a network interface card such as a LAN card, a modem, or the like. The communication section 409 performs communication processing via a network such as the internet. A driver 410 is also connected to the I/O interface 405 as needed. A removable medium 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 410 as necessary, so that a computer program read out therefrom is mounted into the storage section 408 as necessary.

In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 409, and/or installed from the removable medium 411. The computer program performs the above-described functions defined in the system of the present invention when executed by a Central Processing Unit (CPU) 401.

It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor comprises a training module, a detection module and a processing module. Wherein the names of the modules do not in some cases constitute a limitation of the module itself.

As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: step 101, responding to a processing request of user information of stock, calling a user information sample, sample characteristics and a sample label, and training by adopting a natural language processing algorithm and a gradient lifting tree algorithm to obtain an identification model; 102, obtaining stock user information, calling the identification model to detect the stock user information, obtaining target words and target word grades in the stock user information, and generating a grade set of the stock user information; step 103, according to the highest level in the level set, calling a process corresponding to the highest level in a process flow library, and updating the authority configuration information of the stock user.

According to the technical scheme of the embodiment of the invention, the model training is carried out by adopting a natural language processing algorithm and a gradient lifting tree algorithm to obtain the recognition model capable of recognizing the target word and the expansion word of the target word, and the recognition model is called to detect the storage user information so as to carry out corresponding processing; after detecting the stock user information, an expansion word set can be obtained for detecting new user information; therefore, the technical problems that safety control cannot be carried out on the stored user information content and the safety control effect of the user information by using the fixed word bank is poor in the prior art are solved; and then the safety control can be carried out on the content of the stored user information, and the technical effect of better controlling the new user information can be achieved based on the original fixed word bank and the obtained expansion word set.

The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for processing stock user information is characterized by comprising the following steps:

in response to a processing request for the storage user information, calling a user information sample, sample characteristics and a sample label, and training by adopting a natural language processing algorithm and a gradient lifting tree algorithm to obtain an identification model;

2. The method of claim 1, wherein the retrieving the user information sample, the sample feature, and the sample tag comprises:

3. The method of claim 2, wherein training with a natural language processing algorithm and a gradient-boosting tree algorithm yields a recognition model, comprising:

4. The method of any of claims 1-3, wherein the hierarchical set of inventory user information comprises: the target words, the target word grades, the stock user information corresponding to the target words and the user identifications of the stock users corresponding to the target words;

5. The method according to claim 4, wherein the calling a process corresponding to the level of the stock user in the process flow library to update the authorization configuration information of the stock user comprises:

6. The method according to any one of claims 1-3, after invoking the recognition model to detect the inventory user information, further comprising:

7. The method of any of claims 1-3, further comprising:

8. An apparatus for processing user information on an inventory, comprising:

9. An electronic device for processing inventory user information, comprising:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-7.

10. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-7.