CN113449202A - Information matching method, device, equipment and medium - Google Patents

Information matching method, device, equipment and medium Download PDF

Info

Publication number
CN113449202A
CN113449202A CN202110735961.7A CN202110735961A CN113449202A CN 113449202 A CN113449202 A CN 113449202A CN 202110735961 A CN202110735961 A CN 202110735961A CN 113449202 A CN113449202 A CN 113449202A
Authority
CN
China
Prior art keywords
information
account
shared
sharing
tag
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
Application number
CN202110735961.7A
Other languages
Chinese (zh)
Inventor
林卫旋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Weikun Shanghai Technology Service Co Ltd
Original Assignee
Weikun Shanghai Technology Service Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Weikun Shanghai Technology Service Co Ltd filed Critical Weikun Shanghai Technology Service Co Ltd
Priority to CN202110735961.7A priority Critical patent/CN113449202A/en
Publication of CN113449202A publication Critical patent/CN113449202A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9536Search customisation based on social or collaborative filtering
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/20Natural language analysis
    • G06F40/205Parsing
    • G06F40/216Parsing using statistical methods
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/30Semantic analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Probability & Statistics with Applications (AREA)
  • Data Mining & Analysis (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

The application relates to the technical field of knowledge graphs and discloses an information matching method, device, medium and equipment, wherein the method comprises the following steps: acquiring target account information and historical behavior information; obtaining label information corresponding to the target account information according to the historical behavior information; acquiring first sharing information corresponding to the information sharing instruction; performing semantic recognition on the first shared information through a preset semantic recognition model; acquiring the tag information of the sharing account, and judging whether the semantic feature information of the first sharing information is matched with the tag information of the sharing account; if so, judging whether the tag information of the account to be shared is matched with the tag information of the shared account; and if the account number is matched with the account number to be shared, the account number to be shared is used as a shared account number, and first sharing information is sent to the shared account number. Therefore, the effectiveness and pertinence of information sharing are improved.

Description

Information matching method, device, equipment and medium
Technical Field
The present application relates to the field of knowledge graph technology, and in particular, to a method, an apparatus, a device, and a medium for matching information.
Background
With the development of information technology, the message sharing mode of people is gradually changed from offline sharing to online sharing. On-line sharing is also a basic form of the existing marketing campaign, and can spread various activities and contents and spread among customers, so that the customers can participate spontaneously and actively, the product contents are approved and spread, and the influence and the activity of the product are improved.
The existing online sharing has few limitations, and shared objects have no difference, such as content sharing of WeChat, Taobao, microblog and the like, and can share objects and shared content without limitation, and sharees can also receive shared content without limitation.
For products such as daily necessities or food with large daily demands and large covering area of users, customers of sharers and sharees are treated indiscriminately, so that the missing of audiences can be reduced, and the products are diffused and spread to the greatest extent. However, with the development of industries, especially financial industries, financial products have great differentiation on different client bodies, such as private fund and private client products, and have strict element limitations on participation of shared clients and sharees, and the existing non-differentiated sharing mode for the client group main body cannot meet the business development and supervision requirements, so that the sharing effectiveness and pertinence are greatly reduced under the condition of the same sharing amount.
Disclosure of Invention
The application mainly aims to provide an information matching method, an information matching device, an information matching medium and information matching equipment, and aims to solve the technical problems of low sharing effectiveness and low pertinence under the condition that the information sharing quantity is the same in the prior art.
In order to achieve the above object, the present application provides an information matching method, including:
acquiring target account information and historical behavior information corresponding to the target account information, wherein the target account information comprises a sharing account and an account to be shared;
obtaining label information corresponding to each target account information according to the historical behavior information, and marking the target account information according to the label information;
responding to an information sharing instruction sent by the sharing account, and acquiring first sharing information corresponding to the information sharing instruction;
performing semantic recognition on the first shared information through a preset semantic recognition model to obtain semantic feature information of the first shared information;
acquiring the tag information of the sharing account, and judging whether the semantic feature information is matched with the tag information of the sharing account;
if so, acquiring the label information of the account to be shared, and judging whether the label information of the account to be shared is matched with the label information of the shared account;
and if the account number is matched with the account number to be shared, the account number to be shared is used as a shared account number, and the first sharing information is sent to the shared account number.
Further, the semantic recognition of the first shared information through a preset semantic recognition model to obtain semantic feature information of the first shared information includes:
identifying keywords in the first shared information, and counting the frequency of occurrence of each keyword;
performing semantic recognition on the first shared information through a preset semantic recognition model to obtain a plurality of semantic labels;
associating the keywords with the semantic tags, and calculating the semantic weight of the semantic tags associated with the keywords according to the frequency of occurrence of the keywords;
and obtaining semantic feature information of the first shared information according to the semantic weight.
Further, the obtaining tag information corresponding to the account information of the sharing account and determining whether the semantic feature information is matched with the tag information of the sharing account includes:
identifying header information of the first shared information;
judging whether the first sharing information meets a sharing standard or not according to the header information, the semantic label and the semantic weight;
if the sharing account number does not meet the requirement, pushing information that the sharing standard does not meet the requirement to a terminal logged in by the sharing account number;
if yes, obtaining the tag information of the sharing account, and judging whether the semantic feature information is matched with the tag information of the sharing account.
Further, responding to the information sharing instruction sent by the sharing account further includes:
judging whether the label information of the analysis account is a dangerous label or not;
if the information is a dangerous label, no longer responding to an information sharing instruction sent by the sharing account, and sending warning information to a terminal logged by the sharing account;
and if the sharing account is not a danger label, responding to an information sharing instruction sent by the sharing account.
Further, after determining whether the semantic feature information is matched with the tag information of the shared account, the method further includes:
if not, pushing sharing abnormal information to a terminal logged by the sharing account;
responding to a first shared information complaint instruction sent by the shared account, sending the first shared information to an artificial semantic recognition unit, so that the artificial semantic recognition unit returns an artificial semantic recognition result of the first shared information;
if the artificial semantic recognition result is matching, acquiring the label information of the account to be shared, and judging whether the label information of the account to be shared is matched with the label information of the shared account;
and if the account number is matched with the account number to be shared, the account number to be shared is used as a shared account number, and the first sharing information is sent to the shared account number.
Further, before the account to be shared is used as a shared account, the method further includes:
acquiring a sharing range label corresponding to the information sharing instruction;
the taking the account to be shared as a shared account and sending the first sharing information to the shared account includes:
if the tag information of the account to be shared is matched with the tag information of the sharing account, judging whether the tag information of the account to be shared is matched with the sharing range tag;
and if the account number is matched with the account number to be shared, the account number to be shared is used as a shared account number, and the first sharing information is sent to the shared account number.
Further, before the account to be shared is used as a shared account, the method further includes:
acquiring a receiving range label preset by the account to be shared;
the taking the account to be shared as a shared account and sending the first sharing information to the shared account includes:
if the tag information corresponding to the account information of the account to be shared is matched with the sharing range tag, judging whether the semantic feature information of the first sharing information is matched with the receiving range tag;
and if the account number is matched with the account number to be shared, the account number to be shared is used as a shared account number, and the first sharing information is sent to the shared account number.
The present application further provides an information matching apparatus, which includes:
the information acquisition module is used for acquiring target account information and historical behavior information corresponding to the target account information, wherein the target account information comprises a sharing account and an account to be shared;
the information marking module is used for obtaining label information corresponding to each target account information according to the historical behavior information and marking the target account information according to the label information;
the sharing information acquisition module is used for responding to an information sharing instruction sent by the sharing account number and acquiring first sharing information corresponding to the information sharing instruction;
the feature recognition module is used for performing semantic recognition on the first shared information through a preset semantic recognition model to obtain semantic feature information of the first shared information;
the first matching module is used for acquiring the tag information of the sharing account and judging whether the semantic feature information is matched with the tag information of the sharing account;
the second matching module is used for acquiring the label information of the account to be shared if the account to be shared is matched with the sharing account, and judging whether the label information of the account to be shared is matched with the label information of the sharing account or not;
and the information sharing module is used for taking the account to be shared as a shared account and sending the first sharing information to the shared account if the account to be shared is matched with the account to be shared.
The present application also proposes a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the method of any one of the above mentioned items when executing the computer program.
The present application also proposes a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of any of the above.
According to the information matching method, the device, the medium and the equipment, the target account information and the historical behavior information corresponding to the target account information are obtained, so that the historical behavior of the user is analyzed, and a reference basis is provided for matching of shared information; the label marking is carried out on the information of each target account through the historical behavior information, so that the accuracy of acquiring the characteristics of each target object is improved, and the accuracy of matching the shared information is improved; the sharing information which is intended to be shared by the target object is obtained by receiving and responding to the information sharing instruction of the target object, so that each sharing information has traceability, and the source of the sharing information is convenient to position subsequently; the identity of the target object is dynamically calibrated, so that the dynamic identity conversion of different target objects in the whole sharing process is realized, and the flexibility of sharing information matching is improved; the semantic feature recognition is carried out through the semantic recognition model, so that the accuracy of the feature recognition of the first shared information is improved, and the problems of manpower fatigue and low efficiency caused by manual examination of a large amount of shared information are solved; by matching the tag information of the shared account with the semantic feature information of the shared information, the spreading of the shared information of the shared account is limited, the economic loss of other target objects caused by the massive spreading of the shared information with false content is avoided, and the safety and reliability of information sharing are improved; the account to be shared which is suitable for receiving the first sharing information is screened out by matching the tag information of the account to be shared and the tag information of the account to be shared with the tag information of the account to be analyzed, so that the waste of propagation resources caused by non-differentiated sharing is avoided, and the matching degree and pertinence of information sharing are improved by sharing the information of the matched account to be shared.
Drawings
Fig. 1 is a schematic flowchart of an information matching method according to an embodiment of the present application;
fig. 2 is a block diagram schematically illustrating a structure of an information matching apparatus according to an embodiment of the present application;
fig. 3 is a block diagram illustrating a structure of a computer device according to an embodiment of the present application.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, in order to achieve the above object, the present application proposes an information matching method, including:
s1: acquiring target account information and historical behavior information corresponding to the target account information, wherein the target account information comprises a sharing account and an account to be shared;
s2: obtaining label information corresponding to each target account information according to the historical behavior information, and marking the target account information according to the label information;
s3: responding to an information sharing instruction sent by the sharing account, and acquiring first sharing information corresponding to the information sharing instruction;
s4: performing semantic recognition on the first shared information through a preset semantic recognition model to obtain semantic feature information of the first shared information;
s5: acquiring the tag information of the sharing account, and judging whether the semantic feature information is matched with the tag information of the sharing account;
s6: if so, acquiring label information of the account to be shared, and judging whether the label information of the account to be shared is matched with the label information of the shared account;
s7: and if the account number is matched with the account number to be shared, the account number to be shared is used as a shared account number, and the first sharing information is sent to the shared account number.
In the embodiment, the target account information and the historical behavior information corresponding to the target account information are acquired, so that the historical behavior of the user is analyzed, and a reference basis is provided for information matching; the label marking is carried out on the information of each target account through the historical behavior information, so that the accuracy of acquiring the characteristics of each target object is improved, and the accuracy of information matching is improved; the sharing information which is intended to be shared by the target object is obtained by receiving and responding to the information sharing instruction of the target object, so that each sharing information has traceability, and the source of the sharing information is convenient to position subsequently; the identity of the target object is dynamically calibrated, so that the dynamic identity conversion of different target objects in the whole sharing process is realized, and the flexibility of sharing information matching is improved; the semantic feature recognition is carried out through the semantic recognition model, so that the accuracy of the feature recognition of the first shared information is improved, and the problems of manpower fatigue and low efficiency caused by manual examination of a large amount of shared information are solved; by matching the tag information of the shared account with the semantic feature information of the shared information, the spreading of the shared information of the shared account is limited, the economic loss of other target objects caused by the massive spreading of the shared information with false content is avoided, and the safety and reliability of information sharing are improved; the account to be shared which is suitable for receiving the first sharing information is screened out by matching the tag information of the account to be shared and the tag information of the account to be shared with the tag information of the account to be analyzed, so that the waste of propagation resources caused by non-differentiated sharing is avoided, and the matching degree and pertinence of information sharing are improved by sharing the information of the matched account to be shared.
In step S1, the target account information is generated after the user performs account registration, and a corresponding account ID is usually generated for each account registered by the user. Before information sharing, historical behavior information corresponding to each target account information is identified, so that behavior characteristics of the account can be obtained according to the historical behavior information. Specifically, the historical behavior information includes historical behavior records such as historical transfer records, historical business transaction records, and the like of the target account information. Specifically, the target account information and the historical behavior information corresponding to the target account information are obtained, so that the historical behavior of the user is analyzed, and a reference basis is provided for matching of the shared information.
It should be noted that, in different information sharing processes, a sharing account and an account to be shared in the target account information are dynamically changed, and one piece of target account information may be a sharing account of shared information and an account to be shared of another piece of shared information at the same time, which is only exemplified by the first piece of shared information.
In step S2, the behavior characteristics of the target account information are obtained by analyzing the historical behavior information, where the historical behavior information may include business items, transaction information, deposit information, product purchase information, and the like that the user transacts, so as to determine the elements such as the privacy level, financial performance qualification, whether to perform fraudulent activities, whether to perform money laundering activities, and identity region limitation of the user according to the deposit amount of the user, and further obtain the label information corresponding to the target account information according to the elements, where the label information includes private product labels, financial qualification labels, private product labels, region labels, and the like. Specifically, each piece of target account information is labeled through the historical behavior information, so that the accuracy of obtaining the information characteristics of each piece of target account information is improved, and the accuracy of information sharing matching is improved.
For step S3, because there are often multiple pieces of target account information in an information sharing process, and the target account information may be used as a sharing account and an account to be shared at the same time, that is, the identity of the target object is dynamically changed. For one target account information A, if the target account information A provides sharing information A ' and sends an information sharing instruction of the sharing information A ', regarding the sharing information A ', a target object A is a sharing account, and other target objects except the target account information A are automatically used as accounts to be shared; for another target account information B, if the sharing information B ' is provided and an information sharing instruction of the sharing information B ' is issued, for the sharing information B ', the target account information B is a sharing account, and the target account information a and other target account information except B are all used as accounts to be shared. Specifically, the sharing information which is intended to be shared by the target account information is obtained by receiving and responding to the information sharing instruction of the target account information, so that the traceability of each sharing information exists, and the subsequent positioning of the source of the sharing information is facilitated; the identity of the target account information is dynamically calibrated, so that the dynamic identity conversion of different target account information in the whole sharing process is realized, and the flexibility of information sharing matching is improved.
For step S4, the preset semantic recognition model may be a hidden markov model or a paraphrase recognition model based on a neural network, a semantic similarity recognition model, etc., and identifies corresponding feature information in the first shared information, generally speaking, a plurality of semantic feature information may appear in a shared information; the semantic feature recognition is carried out through the semantic recognition model, the accuracy of the first shared information feature recognition is improved, and the problems of manpower fatigue and low efficiency caused by manual audit of a large amount of shared information are solved.
For step S5, after obtaining the semantic feature information of the first sharing information, the semantic feature information may be verified with the sharing account; exemplarily, if the tag information corresponding to one shared account includes a private product tag, an X area tag, and does not include a financial work qualification tag, and the semantic feature information in the first shared information matches the financial work qualification, it may be determined that the two are not matched; at this time, the first shared information may be considered to have a high possibility of being false or to have no sharing authority, and the first shared information is no longer shared. Specifically, the sharing information propagation of the shared account is limited by matching the tag information of the shared account with the semantic feature information of the sharing information, so that economic loss of other target objects caused by mass propagation of the sharing information carrying false content is avoided, and the safety and reliability of information sharing are improved.
For step S6, when the semantic feature information of the first shared information matches the tag information of the shared account, the shared account may be considered to have a higher credibility in the act of sharing the first shared information, and at this time, the shared account is matched with the tag information corresponding to the account to be shared; exemplarily, if the tag information corresponding to one sharing account includes a private product tag and an X area tag, and the tag information corresponding to an account to be shared includes a private product tag and a Y area tag, but does not include an X area tag, that is, even if the account to be shared receives the first sharing information of the sharing account, the behavior content corresponding to the first sharing information cannot be executed, that is, the account to be shared and the first sharing information are considered to be mismatched; the account to be shared which is suitable for receiving the first sharing information is screened out through the matching mode, and therefore waste of propagation resources caused by non-differential sharing is avoided.
For step S7, if there is a match between the tag information corresponding to the account to be shared and the shared account, it may be determined that the first sharing information has sharing significance and practical value for the account to be shared, and therefore, the account to be shared may be used as the shared account and the first sharing information is sent to the shared account through the network, so that the matching degree and pertinence of information sharing are improved. In a specific implementation manner, the manner of sending the first sharing information to the shared account may be pushing in a short message manner through a mobile phone number registered by the shared account, so that the shared account can quickly and conveniently acquire the first sharing information.
In an embodiment, the semantic recognition of the first shared information through a preset semantic recognition model to obtain semantic feature information S4 of the first shared information includes:
s41: identifying keywords in the first shared information, and counting the frequency of occurrence of each keyword;
s42: performing semantic recognition on the first shared information through a preset semantic recognition model to obtain a plurality of semantic labels;
s43: associating the keywords with the semantic tags, and calculating the semantic weight of the semantic tags associated with the keywords according to the frequency of occurrence of the keywords;
s44: and obtaining semantic feature information of the first shared information according to the semantic weight.
In the embodiment, the keywords are identified, and the occurrence frequency of the keywords is calculated, so that the importance degree of different keywords in the first shared information is obtained, and the calculation accuracy of the semantic feature information is improved.
With respect to step S43, if the frequency of occurrence of the keyword 1 in the first shared information is 50 times and the frequency of occurrence of the keyword 2 in the first shared information is 7, it is obvious that the importance of the keyword 1 in the first shared information is higher. The semantic tags may be associated with a plurality of keywords, and one keyword is usually associated with only one semantic tag, for example, if the semantic tag is an X region, and on the actual map, X1, X2 and X3 are all alternative names of the X region, and the X region is a sub-region in the X region, the keywords X1, X2, X3 and the X region are all associated with the semantic tag of the X region, and if the semantic tag is a private product, different keywords such as a stock investment fund and a stock fund can be associated with the semantic tag of the private product; illustratively, if the first shared information includes two semantic tags "X region" and "personal products", and the sum of the frequency of occurrence of the keywords X1, X2, X3 and X region in the first shared information is 45 times, and the sum of the frequency of occurrence of the keywords securities investment fund and securities fund in the first shared information is 5 times, the semantic weight of the "X region" semantic tag may be considered as 0.9, and the semantic weight of the "personal products" semantic tag is 0.1; at this time, the semantic feature information includes a 0.9-weight "X region" semantic tag and a 0.1-weight "private product" semantic tag.
In one embodiment, the obtaining the tag information of the sharing account, and determining whether the semantic feature information matches the tag information of the sharing account S5 include:
s51: identifying header information of the first shared information;
s52: judging whether the first sharing information meets a sharing standard or not according to the header information, the semantic label and the semantic weight;
s53: if the weight is not met, pushing information with the weight not meeting to a terminal logged in by account information of the sharing account;
s54: if yes, obtaining the tag information of the sharing account, and judging whether the semantic feature information of the first sharing information is matched with the tag information of the sharing account.
According to the method and the device, the weight verification is carried out on the information shared by the users, the sharing standard unsatisfied information is pushed to the users of the sharing information which does not meet the sharing standard, and the users replace or modify the sharing information, so that the content quality of the sharing information is improved, and the information acquisition efficiency and the information acquisition effectiveness are improved.
With step S51, it is determined whether the body in the first shared information coincides with the title by identifying the title information of the first shared information.
In step S52, it is determined whether the first shared information meets the sharing criterion through the header information, the semantic tag, and the semantic weight, so as to determine whether the first shared information is suitable for sharing. Illustratively, if it is recognized that the title of the first shared information includes a "private product", the semantic tag of the "private product" in the text of the first shared information needs to occupy a certain weight to consider that the first shared information meets the sharing standard, for example, the semantic tag of the "private product" needs to occupy 0.5, that is, the keyword associated with the private product needs to occupy 50% of the occurrence frequency, the first shared information related to the private product is considered to meet the title, that is, the content of the shared information is meaningful, otherwise, a title fraud condition of the "title party" is likely to exist, if in the first shared information, the semantic weight corresponding to the semantic tag of the "private product" is 0.1, and the semantic weight corresponding to the semantic tag of the "X region" is 0.9, it is obvious that the first shared information at this time does not meet the sharing standard related to the title information "private product", therefore, the sharing standard can not meet the information pushed by the user, and the user can replace or modify the first shared information, so that the content quality of the shared information is improved, and the information acquisition efficiency and the information acquisition effectiveness are improved.
In an embodiment, the information sharing instruction S3 sent in response to the sharing account includes:
s31: judging whether the tag information of the sharing account is a dangerous tag or not;
s32: if the information is a dangerous label, no longer responding to an information sharing instruction sent by the sharing account, and sending warning information to a terminal logged by the sharing account;
s33: and if the sharing account is not a danger label, responding to an information sharing instruction sent by the sharing account.
According to the embodiment, the account sharing number with the dangerous label is identified through the historical behavior information, and the information shared by the sharing account number with the dangerous label is not published, so that the safety of pushing the shared information is improved, and the risk of the shared information received by the user is reduced.
For step S31, the dangerous tags include behavior exception tags and fund exception tags, for example, if the sharing account has a fraud activity record, the tag information is marked as the behavior exception tag, and if the sharing account has a money laundering activity record or has a loan overdue behavior for multiple times, the tag information is marked as the fund exception tag.
In step S32, the account information marked with the danger label is not pushed any more, and the account information is warned, so that the safety of pushing the shared information is improved, and the risk of the shared information received by the user is reduced.
In an embodiment, after the determining whether the semantic feature information matches the tag information of the sharing account S5, the method further includes:
s56: if not, pushing sharing abnormal information to a terminal logged by the sharing account;
s57: responding to a first sharing information complaint instruction sent by the account information of the sharing account, and sending the first sharing information to an artificial semantic recognition unit so that the artificial semantic recognition unit returns an artificial semantic recognition result of the first sharing information;
s58: if the artificial semantic recognition result is matching, acquiring the label information of the account to be shared, and judging whether the label information of the account to be shared is matched with the label information of the shared account;
s59: and if the account number is matched with the account number to be shared, the account number to be shared is used as a shared account number, and the first sharing information is sent to the shared account number.
In the embodiment, the semantic recognition model is screened once, so that the workload of manual recognition is reduced, errors of the semantic recognition model are corrected through manual recognition, and the safety of information sharing and the accuracy of tag matching are improved.
For step S55, when the preset semantic recognition model determines that the first sharing information does not match the tag information of the sharing account, pushing sharing abnormal information to the sharing account, so as to facilitate the sharing account to know the determination result. If the user using the sharing account considers that the judgment result is inaccurate, a complaint instruction aiming at the first sharing information can be submitted, so that the system sends the first sharing information to a terminal used by a worker, namely, an artificial semantic recognition unit, so that the worker can perform secondary recognition through artificial reading, if the secondary recognition passes, subsequent matching and sharing operations can be performed, namely, primary screening is performed through a semantic recognition model, and therefore, when the workload of the artificial recognition is reduced, errors of the semantic recognition model are corrected through the artificial recognition, and the safety of information sharing and the accuracy of label matching are improved.
In an embodiment, before the step S7 of taking the account to be shared as the shared account, the method further includes:
s61: acquiring a sharing range label corresponding to the information sharing instruction;
the taking the account to be shared as a shared account and sending the first sharing information S7 to the shared account includes:
s71: if the tag information of the account to be shared is matched with the tag information of the sharing account, judging whether the tag information of the account to be shared is matched with the sharing range tag;
s72: and if the account number is matched with the account number to be shared, the account number to be shared is used as a shared account number, and the first sharing information is sent to the shared account number.
According to the information sharing method and device, the sharing range label corresponding to the information sharing instruction is obtained, the sharing account number is convenient to limit the diffusion range of the first sharing information, and therefore the directivity and the controllability of information sharing are improved
For step S71, when the information sharing instruction of the sharing account is received, the sharing range tag corresponding to the information sharing instruction may also be obtained; the information sharing instruction is actively set by the sharing account, for example, the sharing account can set the sharing range label as a Y region, and the first sharing information is not pushed to an object whose label information is not the Y region, so that the sharing account can limit the diffusion range of the first sharing information, and the directivity and controllability of information sharing are improved.
In an embodiment, before the step S7 of taking the account to be shared as the shared account, the method further includes:
s62: acquiring a receiving range label preset by the account to be shared;
the taking the account to be shared as a shared account and sending the first sharing information S7 to the shared account includes:
s73: if the tag information of the account to be shared is matched with the sharing range tag, judging whether the semantic feature information is matched with the receiving range tag;
s74: and if the account number is matched with the account number to be shared, the account number to be shared is used as a shared account number, and the first sharing information is sent to the shared account number.
According to the embodiment, the preset receiving range tags are matched before the first shared information is pushed to the shared account, so that the two-way selection of the shared account and the shared account is realized, and the information sharing efficiency and the information acquisition effectiveness are improved.
In step S62, if the receiving range label of the account to be shared may be preset to be a private product, information other than the private product is not pushed to the account to be shared, and if the receiving range label is also in a certain form, for example, if it is preset that a "private product label" is not accepted, the relevant sharing information of the private product is not pushed to the account to be shared, thereby implementing bidirectional selection of the sharing account and the shared account, and improving the information sharing efficiency and the effectiveness of information acquisition.
Referring to fig. 2, the present application further provides an information matching apparatus, including:
the information obtaining module 100 is configured to obtain target account information and historical behavior information corresponding to the target account information, where the target account information includes a sharing account and an account to be shared;
the information marking module 200 is configured to obtain tag information corresponding to each piece of target account information according to the historical behavior information, and mark the target account information according to the tag information;
the shared information obtaining module 300 is configured to obtain, in response to an information sharing instruction sent by the sharing account, first shared information corresponding to the information sharing instruction;
the feature recognition module 400 is configured to perform semantic recognition on the first shared information through a preset semantic recognition model to obtain semantic feature information of the first shared information;
the first matching module 500 is configured to acquire tag information of the shared account, and determine whether the semantic feature information matches the tag information of the shared account;
the second matching module 600 is configured to, if the account id is matched with the tag information of the account to be shared, obtain the tag information of the account to be shared, and determine whether the tag information of the account to be shared is matched with the tag information of the shared account;
and the information sharing module 700 is configured to, if the account to be shared is matched with the account to be shared, use the account to be shared as a shared account, and send the first sharing information to the shared account.
In the embodiment, the target account information and the historical behavior information corresponding to the target account information are acquired, so that the historical behavior of the user is analyzed, and a reference basis is provided for information matching; the label marking is carried out on the information of each target account through the historical behavior information, so that the accuracy of acquiring the characteristics of each target object is improved, and the accuracy of information matching is improved; the sharing information which is intended to be shared by the target object is obtained by receiving and responding to the information sharing instruction of the target object, so that each sharing information has traceability, and the source of the sharing information is convenient to position subsequently; the identity of the target object is dynamically calibrated, so that the dynamic identity conversion of different target objects in the whole sharing process is realized, and the flexibility of sharing information matching is improved; the semantic feature recognition is carried out through the semantic recognition model, so that the accuracy of the feature recognition of the first shared information is improved, and the problems of manpower fatigue and low efficiency caused by manual examination of a large amount of shared information are solved; by matching the tag information of the shared account with the semantic feature information of the shared information, the spreading of the shared information of the shared account is limited, the economic loss of other target objects caused by the massive spreading of the shared information with false content is avoided, and the safety and reliability of information sharing are improved; the account to be shared which is suitable for receiving the first sharing information is screened out by matching the tag information of the account to be shared and the tag information of the account to be shared with the tag information of the account to be analyzed, so that the waste of propagation resources caused by non-differentiated sharing is avoided, and the matching degree and pertinence of information sharing are improved by sharing the information of the matched account to be shared.
In one embodiment, the feature recognition module 400 is configured to:
identifying keywords in the first shared information, and counting the frequency of occurrence of each keyword;
performing semantic recognition on the first shared information through a preset semantic recognition model to obtain a plurality of semantic labels;
associating the keywords with the semantic tags, and calculating the semantic weight of the semantic tags associated with the keywords according to the frequency of occurrence of the keywords;
and obtaining semantic feature information of the first shared information according to the semantic weight.
In one embodiment, the first matching module 500 is configured to:
identifying header information of the first shared information;
judging whether the first sharing information meets a sharing standard or not according to the header information, the semantic label and the semantic weight;
if the sharing account number does not meet the requirement, pushing information that the sharing standard does not meet the requirement to a terminal logged in by the sharing account number;
if yes, obtaining the tag information of the sharing account, and judging whether the semantic feature information is matched with the tag information of the sharing account.
In one embodiment, the shared information obtaining module 300 is configured to:
judging whether the tag information of the sharing account is a dangerous tag or not;
if the information is a dangerous label, no longer responding to an information sharing instruction sent by the sharing account, and sending warning information to a terminal logged by the sharing account;
and if the sharing account is not a danger label, responding to an information sharing instruction sent by the sharing account.
In one embodiment, a human recognition module 800 is further included for:
if not, pushing sharing abnormal information to a terminal logged by the sharing account;
responding to a first shared information complaint instruction sent by the shared account, sending the first shared information to an artificial semantic recognition unit, so that the artificial semantic recognition unit returns an artificial semantic recognition result of the first shared information;
if the artificial semantic recognition result is matching, acquiring the label information of the account to be shared, and judging whether the label information of the account to be shared is matched with the label information of the shared account;
and if the account number is matched with the account number to be shared, the account number to be shared is used as a shared account number, and the first sharing information is sent to the shared account number.
In one embodiment, a tag obtaining module 900 is further included for:
acquiring a sharing range label corresponding to the information sharing instruction;
the information sharing module 700 is further configured to:
if the tag information of the account to be shared is matched with the tag information of the sharing account, judging whether the tag information of the account to be shared is matched with the sharing range tag;
and if the account number is matched with the account number to be shared, the account number to be shared is used as a shared account number, and the first sharing information is sent to the shared account number.
In one embodiment, the tag obtaining module 900 is further configured to:
acquiring a receiving range label preset by the account to be shared;
the information sharing module 700 is further configured to:
if the tag information of the account to be shared is matched with the sharing range tag, judging whether the semantic feature information is matched with the receiving range tag;
and if the account number is matched with the account number to be shared, the account number to be shared is used as a shared account number, and the first sharing information is sent to the shared account number.
Referring to fig. 3, a computer device, which may be a server and whose internal structure may be as shown in fig. 3, is also provided in the embodiment of the present application. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used for storing data such as matching methods of information. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of matching information. The information matching method comprises the following steps: acquiring target account information and historical behavior information corresponding to the target account information, wherein the target account information comprises a sharing account and an account to be shared; obtaining label information corresponding to each target account information according to the historical behavior information, and marking the target account information according to the label information; responding to an information sharing instruction sent by the sharing account, and acquiring first sharing information corresponding to the information sharing instruction; performing semantic recognition on the first shared information through a preset semantic recognition model to obtain semantic feature information of the first shared information; acquiring the tag information of the sharing account, and judging whether the semantic feature information is matched with the tag information of the sharing account; if so, acquiring the label information of the account to be shared, and judging whether the label information of the account to be shared is matched with the label information of the shared account; and if the account number is matched with the account number to be shared, the account number to be shared is used as a shared account number, and the first sharing information is sent to the shared account number.
An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements an information matching method, including the steps of: acquiring target account information and historical behavior information corresponding to the target account information, wherein the target account information comprises a sharing account and an account to be shared; obtaining label information corresponding to each target account information according to the historical behavior information, and marking the target account information according to the label information; responding to an information sharing instruction sent by the sharing account, and acquiring first sharing information corresponding to the information sharing instruction; performing semantic recognition on the first shared information through a preset semantic recognition model to obtain semantic feature information of the first shared information; acquiring the tag information of the sharing account, and judging whether the semantic feature information is matched with the tag information of the sharing account; if so, acquiring the label information of the account to be shared, and judging whether the label information of the account to be shared is matched with the label information of the shared account; and if the account number is matched with the account number to be shared, the account number to be shared is used as a shared account number, and the first sharing information is sent to the shared account number.
In the executed information matching method, the target account information and the historical behavior information corresponding to the target account information are acquired, so that the historical behavior of the user is analyzed, and a reference basis is provided for information matching; the label marking is carried out on the information of each target account through the historical behavior information, so that the accuracy of acquiring the characteristics of each target object is improved, and the accuracy of information matching is improved; the sharing information which is intended to be shared by the target object is obtained by receiving and responding to the information sharing instruction of the target object, so that each sharing information has traceability, and the source of the sharing information is convenient to position subsequently; the identity of the target object is dynamically calibrated, so that the dynamic identity conversion of different target objects in the whole sharing process is realized, and the flexibility of sharing information matching is improved; the semantic feature recognition is carried out through the semantic recognition model, so that the accuracy of the feature recognition of the first shared information is improved, and the problems of manpower fatigue and low efficiency caused by manual examination of a large amount of shared information are solved; by matching the tag information of the shared account with the semantic feature information of the shared information, the spreading of the shared information of the shared account is limited, the economic loss of other target objects caused by the massive spreading of the shared information with false content is avoided, and the safety and reliability of information sharing are improved; the account to be shared which is suitable for receiving the first sharing information is screened out by matching the tag information of the account to be shared and the tag information of the account to be shared with the tag information of the account to be analyzed, so that the waste of propagation resources caused by non-differentiated sharing is avoided, and the matching degree and pertinence of information sharing are improved by sharing the information of the matched account to be shared.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.

Claims (10)

1. A method for matching information, the method comprising:
acquiring target account information and historical behavior information corresponding to the target account information, wherein the target account information comprises a sharing account and an account to be shared;
obtaining label information corresponding to each target account information according to the historical behavior information, and marking the target account information according to the label information;
responding to an information sharing instruction sent by the sharing account, and acquiring first sharing information corresponding to the information sharing instruction;
performing semantic recognition on the first shared information through a preset semantic recognition model to obtain semantic feature information of the first shared information;
acquiring the tag information of the sharing account, and judging whether the semantic feature information is matched with the tag information of the sharing account;
if so, acquiring the label information of the account to be shared, and judging whether the label information of the account to be shared is matched with the label information of the shared account;
and if the account number is matched with the account number to be shared, the account number to be shared is used as a shared account number, and the first sharing information is sent to the shared account number.
2. The information matching method according to claim 1, wherein the semantic recognition of the first shared information by a preset semantic recognition model to obtain semantic feature information of the first shared information includes:
identifying keywords in the first shared information, and counting the frequency of occurrence of each keyword;
performing semantic recognition on the first shared information through a preset semantic recognition model to obtain a plurality of semantic labels;
associating the keywords with the semantic tags, and calculating the semantic weight of the semantic tags associated with the keywords according to the frequency of occurrence of the keywords;
and obtaining semantic feature information of the first shared information according to the semantic weight.
3. The information matching method according to claim 2, wherein the obtaining of the tag information of the sharing account and the determining of whether the semantic feature information matches with the tag information of the sharing account include:
identifying header information of the first shared information;
judging whether the first sharing information meets a sharing standard or not according to the header information, the semantic label and the semantic weight;
if the sharing account number does not meet the requirement, pushing information that the sharing standard does not meet the requirement to a terminal logged in by the sharing account number;
if yes, obtaining the tag information of the sharing account, and judging whether the semantic feature information is matched with the tag information of the sharing account.
4. The information matching method according to claim 1, wherein the information sharing instruction sent in response to the sharing account includes:
judging whether the tag information of the sharing account is a dangerous tag or not;
if the information is a dangerous label, no longer responding to an information sharing instruction sent by the sharing account, and sending warning information to a terminal logged by the sharing account;
and if the sharing account is not a danger label, responding to an information sharing instruction sent by the sharing account.
5. The information matching method according to claim 1, wherein after determining whether the semantic feature information matches the tag information of the shared account, the method further includes:
if not, pushing sharing abnormal information to a terminal logged by the sharing account;
responding to a first shared information complaint instruction sent by the shared account, sending the first shared information to an artificial semantic recognition unit, so that the artificial semantic recognition unit returns an artificial semantic recognition result of the first shared information;
if the artificial semantic recognition result is matching, acquiring the label information of the account to be shared, and judging whether the label information of the account to be shared is matched with the label information of the shared account;
and if the account number is matched with the account number to be shared, the account number to be shared is used as a shared account number, and the first sharing information is sent to the shared account number.
6. The information matching method according to claim 1, wherein before the account to be shared is used as a shared account, the method further includes:
acquiring a sharing range label corresponding to the information sharing instruction;
the taking the account to be shared as a shared account and sending the first sharing information to the shared account includes:
if the tag information of the account to be shared is matched with the tag information of the sharing account, judging whether the tag information of the account to be shared is matched with the sharing range tag;
and if the account number is matched with the account number to be shared, the account number to be shared is used as a shared account number, and the first sharing information is sent to the shared account number.
7. The information matching method according to claim 1, wherein before the account to be shared is used as a shared account, the method further includes:
acquiring a receiving range label preset by the account to be shared;
the taking the account to be shared as a shared account and sending the first sharing information to the shared account includes:
if the tag information of the account to be shared is matched with the sharing range tag, judging whether the semantic feature information of the first sharing information is matched with the receiving range tag;
and if the account number is matched with the account number to be shared, the account number to be shared is used as a shared account number, and the first sharing information is sent to the shared account number.
8. An apparatus for matching information, comprising:
the information acquisition module is used for acquiring target account information and historical behavior information corresponding to the target account information, wherein the target account information comprises a sharing account and an account to be shared;
the information marking module is used for obtaining label information corresponding to each target account information according to the historical behavior information and marking the target account information according to the label information;
the sharing information acquisition module is used for responding to an information sharing instruction sent by the sharing account number and acquiring first sharing information corresponding to the information sharing instruction;
the feature recognition module is used for performing semantic recognition on the first shared information through a preset semantic recognition model to obtain semantic feature information of the first shared information;
the first matching module is used for acquiring the tag information of the sharing account and judging whether the semantic feature information is matched with the tag information of the sharing account;
the second matching module is used for acquiring the label information of the account to be shared if the account to be shared is matched with the sharing account, and judging whether the label information of the account to be shared is matched with the label information of the sharing account or not;
and the information sharing module is used for taking the account to be shared as a shared account and sending the first sharing information to the shared account if the account to be shared is matched with the account to be shared.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of any one of claims 1 to 7.
CN202110735961.7A 2021-06-30 2021-06-30 Information matching method, device, equipment and medium Pending CN113449202A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110735961.7A CN113449202A (en) 2021-06-30 2021-06-30 Information matching method, device, equipment and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110735961.7A CN113449202A (en) 2021-06-30 2021-06-30 Information matching method, device, equipment and medium

Publications (1)

Publication Number Publication Date
CN113449202A true CN113449202A (en) 2021-09-28

Family

ID=77814611

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110735961.7A Pending CN113449202A (en) 2021-06-30 2021-06-30 Information matching method, device, equipment and medium

Country Status (1)

Country Link
CN (1) CN113449202A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105282010A (en) * 2015-09-14 2016-01-27 小米科技有限责任公司 Information sharing processing method, device, and server
US20170075991A1 (en) * 2015-09-14 2017-03-16 Xerox Corporation System and method for classification of microblog posts based on identification of topics
CN108280692A (en) * 2018-02-05 2018-07-13 广州华多网络科技有限公司 Reward distribution method, device, computer readable storage medium and terminal
CN109145301A (en) * 2018-08-29 2019-01-04 上海汽车集团股份有限公司 Information classification approach and device, computer readable storage medium
CN110457679A (en) * 2019-07-01 2019-11-15 深圳追一科技有限公司 Construction method, device, computer equipment and the storage medium of user's portrait
CN111740896A (en) * 2020-07-07 2020-10-02 腾讯科技(深圳)有限公司 Content sharing control method and device, electronic equipment and storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105282010A (en) * 2015-09-14 2016-01-27 小米科技有限责任公司 Information sharing processing method, device, and server
US20170075991A1 (en) * 2015-09-14 2017-03-16 Xerox Corporation System and method for classification of microblog posts based on identification of topics
CN108280692A (en) * 2018-02-05 2018-07-13 广州华多网络科技有限公司 Reward distribution method, device, computer readable storage medium and terminal
CN109145301A (en) * 2018-08-29 2019-01-04 上海汽车集团股份有限公司 Information classification approach and device, computer readable storage medium
CN110457679A (en) * 2019-07-01 2019-11-15 深圳追一科技有限公司 Construction method, device, computer equipment and the storage medium of user's portrait
CN111740896A (en) * 2020-07-07 2020-10-02 腾讯科技(深圳)有限公司 Content sharing control method and device, electronic equipment and storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
公周: "用户画像标签维度_用户画像之标签权重算法", 《CSDN HTTPS://BLOG.CSDN.NET/WEIXIN_32894769/ARTICLE/DETAILS/112827534?》 *
蕾姆233: "文本内容画像&用户画像理解之最终版", 《CSDN HTTPS://BLOG.CSDN.NET/QQ_34333481/ARTICLE/DETAILS/84065592?》 *

Similar Documents

Publication Publication Date Title
CN108876133B (en) Risk assessment processing method, device, server and medium based on business information
CN110493190B (en) Data information processing method and device, computer equipment and storage medium
CN109087208B (en) Pre-loan data processing method, pre-loan data processing device, computer equipment and storage medium
CN110659800A (en) Risk monitoring processing method and device, computer equipment and storage medium
CN112668859A (en) Big data based customer risk rating method, device, equipment and storage medium
CN110636106B (en) Information pushing method and device, computer equipment and storage medium
CN110619065A (en) Resource scheduling service processing method and device, computer equipment and storage medium
US10325235B2 (en) Method and system for analyzing and optimizing distribution of work from a plurality of queues
US11954174B2 (en) Sharing financial crime knowledge
CN111506710B (en) Information sending method and device based on rumor prediction model and computer equipment
CN112163131A (en) Configuration method and device of business data query platform, computer equipment and medium
CN112632409A (en) Same user identification method, device, computer equipment and storage medium
CN112434335A (en) Business problem processing method and device, computer equipment and storage medium
CN113989020A (en) Loan overdue information processing method and device, computer equipment and storage medium
Wilson et al. Concern about threatened species and ecosystem disservices underpin public willingness to pay for ecological restoration
CN111476508A (en) Risk identification method and system for target operation
CN115564449A (en) Risk control method and device for transaction account and electronic equipment
CN111340365A (en) Enterprise data processing method and device, computer equipment and storage medium
CN110458633B (en) Invoice data generation method and system based on block chain technology and computer equipment
CN115269437A (en) Test case recommendation method and device, computer equipment and storage medium
CN115423578A (en) Bidding method and system based on micro-service containerization cloud platform
CN110458710B (en) Request processing method, apparatus, computer device and storage medium
CN111382944A (en) Job behavior risk identification method and device, computer equipment and storage medium
CN113687800A (en) File printing processing method and device, computer equipment and storage medium
CN113449202A (en) Information matching method, device, equipment and 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
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20210928

WD01 Invention patent application deemed withdrawn after publication