CN115439214A - Credit description text generation method and device, electronic equipment and storage medium - Google Patents
Credit description text generation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115439214A CN115439214A CN202211082378.1A CN202211082378A CN115439214A CN 115439214 A CN115439214 A CN 115439214A CN 202211082378 A CN202211082378 A CN 202211082378A CN 115439214 A CN115439214 A CN 115439214A
- Authority
- CN
- China
- Prior art keywords
- user
- evaluated
- description text
- betweenness
- network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 230000011218 segmentation Effects 0.000 claims abstract description 43
- 230000006399 behavior Effects 0.000 claims description 40
- 238000012163 sequencing technique Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 16
- 238000011156 evaluation Methods 0.000 claims description 9
- 230000000007 visual effect Effects 0.000 abstract description 4
- 238000004891 communication Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000012502 risk assessment Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- ZRHANBBTXQZFSP-UHFFFAOYSA-M potassium;4-amino-3,5,6-trichloropyridine-2-carboxylate Chemical group [K+].NC1=C(Cl)C(Cl)=NC(C([O-])=O)=C1Cl ZRHANBBTXQZFSP-UHFFFAOYSA-M 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/103—Formatting, i.e. changing of presentation of documents
- G06F40/109—Font handling; Temporal or kinetic typography
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a credit description text generation method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring behavior data of each user node in a user association relation segmentation network of a user to be evaluated; matching the behavior data of each user node in the user incidence relation segmentation network of the user to be evaluated in a story label library to obtain a story label of the user to be evaluated; and generating a user credit description text based on the story line label of the user to be evaluated. Through the technical scheme, the user credit description text is generated, so that the risk identification is more visual, and the identification difficulty is reduced.
Description
Technical Field
The invention relates to the technical field of risk management, in particular to a credit description text generation method and device, electronic equipment and a storage medium.
Background
Risk management is a major and difficult point for user credit and credit management.
At present, when an individual enterprise has operation problems and financial crisis, domino effect is often generated, risks soon infect the whole user relationship network, the enterprise in the relationship network is trapped in a dilemma, and regional and systemic financial risks are very easy to occur.
In the process of implementing the invention, the inventor finds that at least the following technical problems exist in the prior art: in the existing risk management scheme, the risk data is complex, and the problems of non-visual risk identification and high difficulty exist.
Disclosure of Invention
The invention provides a credit description text generation method and device, electronic equipment and a storage medium, and aims to solve the problems of non-intuitive risk identification and high difficulty.
According to an aspect of the present invention, there is provided a credit description text generation method, including:
acquiring behavior data of each user node in a user association relation segmentation network of a user to be evaluated;
matching the behavior data of each user node in the user incidence relation segmentation network of the user to be evaluated in a story label library to obtain a story label of the user to be evaluated;
and generating a user credit description text based on the story line label of the user to be evaluated.
According to another aspect of the present invention, there is provided a credit description text generating apparatus including:
the behavior data acquisition module is used for acquiring the behavior data of each user node in the user association relation segmentation network of the user to be evaluated;
the plot label matching module is used for matching the behavior data of each user node in the user incidence relation segmentation network of the user to be evaluated in a plot label library to obtain a plot label of the user to be evaluated;
and the description text generation module is used for generating a user credit description text based on the story line label of the user to be evaluated.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform a credit description text generation method according to any of the embodiments of the invention.
According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the credit description text generation method according to any one of the embodiments of the present invention when the computer instructions are executed.
According to the technical scheme of the embodiment of the invention, the behavior data of each user node in the network is segmented by acquiring the association relation of the user to be evaluated, so that the evaluation data is enriched; matching the behavior data of each user node in the user incidence relation segmentation network of the user to be evaluated in a story label library to obtain a story label of the user to be evaluated; and generating a user credit description text based on the story line label of the user to be evaluated, so that the risk identification is more intuitive, and the identification difficulty is reduced.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a credit description text generation method according to an embodiment of the present invention;
FIG. 2 is a flowchart of a credit description text generation method according to a second embodiment of the present invention;
FIG. 3 is a flowchart of a credit description text generation method according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a credit description text generating device according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device implementing the credit description text generation method according to the embodiment of the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Moreover, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example one
Fig. 1 is a flowchart of a credit description text generation method according to an embodiment of the present invention, where the embodiment is applicable to a case where a credit story of a user is automatically generated according to user behavior data, and the method may be performed by a credit description text generation apparatus, which may be implemented in a form of hardware and/or software, and may be configured in a computer terminal. As shown in fig. 1, the method includes:
s110, acquiring behavior data of each user node in the user association relation segmentation network of the user to be evaluated.
In this embodiment, the user to be assessed refers to a user to be credit assessed, for example, the user to be assessed may be a bank personal client, a bank enterprise client, or the like. The user association relation segmentation network is a sub-network which is segmented by the user association relation network and comprises a plurality of user nodes, wherein the user association relation network is a network formed by mutually connecting a plurality of clients through risk association relations, and each user node represents one client.
It should be noted that the user association relationship network may be an authorized network, and the authorized network refers to a network in which user nodes are associated with each other.
For example, after determining the user incidence relation segmentation network where the user to be evaluated is located, the electronic device may retrieve behavior data of each user node in the user incidence relation segmentation network where the user to be evaluated is located from a local or cloud preset storage location, where the behavior data may include, but is not limited to, shopping data, income data, liability data, and the like.
S120, matching the behavior data of each user node in the user association relation segmentation network of the user to be evaluated in a story label library to obtain a story label of the user to be evaluated.
The storyline tag library is a database in which storyline tags are stored. The story line label can be made by analyzing past user behaviors. For example, if the stock client previews the payment information a plurality of times after the credit card arrears but does not pay, the tag may be: the client has insufficient capital investment capacity but repayment intention; if the client does not log in the relevant system for querying relevant information for a long time after the credit card arrears, and pays immediately after logging in a certain day, the label can be as follows: the customer is not vigilant for payment, but has the ability to make a payment.
For example, the electronic device may extract keywords from behavior data of each user node in the user association relation segmentation network where the user to be evaluated is located, to obtain user key information, and further, may perform matching in a story line label library according to the user key information, and may use a story line label whose text similarity exceeds a preset similarity threshold as a story line label of the user to be evaluated.
And S130, generating a user credit description text based on the story line label of the user to be evaluated.
In this embodiment, the number of story line tags of the user to be evaluated may be one or more; when the number of the story line labels of the user to be evaluated is multiple, the multiple story line labels can be integrated into a story example to form a user credit description text. The user credit description text refers to a credit story of the user to be evaluated. Typically, the user credit description text may be an immersive instantiation story. It can be understood that the credit description text of the user has the characteristics of intuition and strong readability, so that risk identification is more intuitional, and the identification difficulty is reduced.
For example, the content in the user credit description text may include: the king is a device which always pays attention to financial information, is high in financial consciousness but is poor in repayment capacity, and has no repayment risk temporarily if the borrowing is under 10 ten thousand of credit card and consumption credit, but has 65 percent of possibility of delayed repayment possibility if the borrowing exceeds 10 ten thousand, but has 95 percent of possibility of finishing the repayment finally.
In some optional embodiments, generating the user credit description text based on the story line label of the user to be evaluated comprises: and inputting the story plot labels of the users to be evaluated into a pre-established story generation template to obtain the credit description text of the users.
The story generation template can perform operations such as sequencing, word replacement, typesetting and the like on the input story plot labels, so that the generated user credit description text content is smooth and has high readability.
According to the technical scheme of the embodiment of the invention, the behavior data of each user node in the network is segmented by acquiring the user association relation of the user to be evaluated, so that the evaluation data is enriched; matching the behavior data of each user node in the user incidence relation segmentation network of the user to be evaluated in a story label library to obtain a story label of the user to be evaluated; and generating a user credit description text based on the story line label of the user to be evaluated, so that the risk identification is more intuitive, and the identification difficulty is reduced.
Example two
Fig. 2 is a flowchart of a credit description text generation method provided in the second embodiment of the present invention, and the method of the present embodiment may be combined with various alternatives in the credit description text generation method provided in the foregoing embodiments. The credit description text generation method provided by the embodiment is further optimized. Optionally, the obtaining of the behavior data of each user node in the user association relationship segmentation network where the user to be evaluated is located includes: acquiring a user association relationship network, wherein the user association relationship network comprises a plurality of user nodes; determining betweenness information of a connection edge between every two user nodes in the user association relationship network, wherein the betweenness information comprises edge betweenness and relative betweenness; dividing the user association relationship network based on betweenness information of a connecting edge between every two user nodes in the user association relationship network to obtain a plurality of user association relationship divided networks; and determining the user association relation segmentation network of the user to be evaluated, and calling behavior data of each user node in the user association relation segmentation network of the user to be evaluated.
As shown in fig. 2, the method includes:
s210, obtaining a user association relationship network, wherein the user association relationship network comprises a plurality of user nodes.
S220, determining betweenness information of a connection edge between every two user nodes in the user association relationship network, wherein the betweenness information comprises edge betweenness and relative betweenness.
In this embodiment, the relative betweenness indicates the possibility of the connection edge being a connection edge of a different guest group in the user association relationship network structure. The larger the relative betweenness of the connecting edges is, the smaller the possibility that the connecting edges are taken as connecting edges of different guest groups is, that is, the smaller the possibility that two user nodes connected by the connecting edges belong to two different guest groups is, and the larger the possibility that the user nodes belong to the same guest group is; conversely, the smaller the relative betweenness of the connection edges, the greater the probability that the connection edge is a connection edge of a different guest group, that is, the greater the probability that two user nodes connected by the connection edge belong to two different guest groups, and the smaller the probability that the two user nodes belong to the same guest group. The edge betweenness of the connection edge represents the number of the shortest paths containing the connection edge between any two user nodes in the user association relationship network.
In some optional embodiments, determining betweenness information of a connection edge between every two user nodes in the user association relationship network includes: respectively confirming the shortest path between every two user nodes in the user association relationship network to obtain a shortest path set; determining edge betweenness of connecting edges between every two user nodes in the user association relationship network based on the shortest path set; and determining the relative betweenness of the connecting edges between every two user nodes in the user association relationship network based on the edge betweenness of the connecting edges between every two user nodes in the user association relationship network and the conduction coefficient of the connecting edges between every two user nodes in the user association relationship network.
Specifically, in the user association relationship network, due to the complexity of the client relationship, two user nodes may be directly connected or indirectly connected. For the user nodes with direct risk association relationship, the shortest path between the two user nodes is the connecting edge between the two user nodes. For a user node which has no direct risk association relationship but has indirect risk association relationship, the shortest path between the two user nodes is the shortest path from one user node, through the intermediate connection node and finally to the other user node. It is understood that there may be a variety of connection paths between indirectly connected user nodes, and the shortest connection path among them is of interest to embodiments of the present invention. The calculation formula of the edge betweenness is as follows:
C(f)=∑ i≠j g ij (f)
wherein C (f) represents the number of edge gaps connecting the edges f, g ij (f) The number of shortest paths passing through the connecting edge f with i as the starting point and j as the end point is shown.
Further, according to the conduction coefficient of the connection edge between every two user nodes in the user association relationship network, the weight of the connection edge between every two user nodes can be calculated:
W f =1-(1-W f1 )×(1-W f2 )=W f1 +W f2 -W f1 *W f2
wherein, W f Is the weight of the connecting edge f, W, in the user association network f1 And W f2 Representing the two client nodes a and B corresponding to the connecting edge f, respectively, the conductivity of a to B and the conductivity of B to a.
The relative betweenness of a connecting edge in the user incidence relation network is equal to the ratio of the weight of the connecting edge to the edge betweenness of the connecting edge, namely:
wherein R is f The relative betweenness of the connecting sides f is shown.
It can be understood that the relative betweenness of the connecting edges is influenced by two aspects, namely the weight of the connecting edges and the betweenness of the connecting edges. The greater the weight of the connecting edge, the more closely the two nodes are related. The smaller the number of edge intermediaries of the connecting edge is, the smaller the influence of the edge on the network is, and the less likely the edge is to be divided at the time of division. The weight of the connecting edge is related to the conduction coefficient between the client nodes connected by the connecting edge, and the larger the weight of the connecting edge is, the closer the relationship between the two nodes is, and the higher the probability of risk conduction is.
S230, based on the betweenness information of the connection edge between every two user nodes in the user association relationship network, the user association relationship network is segmented, and a plurality of user association relationship segmented networks are obtained.
It can be understood that the relative betweenness can represent the possibility of the connection edge serving as the connection edge of different customer groups on the user association relationship network structure.
In this embodiment, a division stop condition may be preset, for example, the number of subnets is greater than or equal to 3, in other words, when the number of user association relation divided networks is greater than or equal to 3, the division is ended. After the segmentation is finished, the user nodes in the same user association segmentation network can be marked with the same number.
In some optional embodiments, segmenting the user association network based on betweenness information of a connection edge between every two user nodes in the user association network to obtain a plurality of user association segmented networks, including: sequencing based on edge betweenness of connecting edges between every two user nodes in the user incidence relation network to obtain a first sequencing result; under the condition that the first sequencing result has the connecting edges with the same edge betweenness, sequencing the first sequencing result based on the relative betweenness of the connecting edges between every two user nodes in the user association relationship network to obtain a second sequencing result; and sequentially deleting the connection side with the minimum relative betweenness from the connection sides with the maximum betweenness in the user association relationship network based on the second sequencing result to obtain a plurality of user association relationship segmentation networks.
Specifically, the edge betweenness of the connecting edges between every two user nodes in the user association relationship network are sorted from large to small to obtain a first sorting result, and under the condition that the first sorting result has the connecting edges with the same edge betweenness, the parts with the same edge betweenness in the first sorting result are sorted from small to large based on the relative betweenness of the connecting edges between every two user nodes in the user association relationship network to obtain a second sorting result; the connection side with the smallest relative betweenness in the connection sides with the largest betweenness number in the user association relationship network is deleted in sequence based on the second sorting result, and the multiple user association relationship split networks are obtained.
S240, determining the user association relation segmentation network where the user to be evaluated is located, and calling behavior data of each user node in the user association relation segmentation network where the user to be evaluated is located.
And S250, matching the behavior data of each user node in the user association relation segmentation network of the user to be evaluated in a story label library to obtain the story label of the user to be evaluated.
And S260, generating a user credit description text based on the story line label of the user to be evaluated.
According to the technical scheme of the embodiment of the invention, the user association relationship network is repeatedly segmented according to the betweenness information between every two user nodes in the user association relationship network until the obtained segmented user association relationship network accords with the preset network segmentation result. The processing process realizes quantification and clustering of the client group according to risk association between the clients to obtain the user association relationship segmentation network with risk association relationship, and is beneficial to performing group risk management on the clients.
EXAMPLE III
Fig. 3 is a flowchart of a credit description text generation method provided in a third embodiment of the present invention, and the method of the present embodiment may be combined with various alternatives in the credit description text generation method provided in the foregoing embodiment. The credit description text generation method provided by the embodiment is further optimized. Optionally, after generating the user credit description text based on the story line tag of the user to be evaluated, the method further includes: and determining the risk level of the user to be evaluated based on the user credit description text.
As shown in fig. 3, the method includes:
s310, acquiring behavior data of each user node in the user association relation segmentation network of the user to be evaluated.
S320, matching the behavior data of each user node in the user association relation segmentation network of the user to be evaluated in a story label library to obtain a story label of the user to be evaluated.
S330, generating a user credit description text based on the story line label of the user to be evaluated.
S340, determining the risk level of the user to be evaluated based on the user credit description text.
Wherein, the risk level refers to a risk rating of the user credit description text, for example, the risk level may include, but is not limited to, a high risk level, a medium risk level, a low risk level, and the like. After the risk level of the user to be evaluated is obtained, whether the user credit description text is online or not can be determined according to the risk level of the user to be evaluated, for example, if the risk level is a low risk level, the user credit description text is online, or if the risk level is a high risk level, the user credit description text is offline.
Specifically, a risk value corresponding to each story node in a user credit description text can be acquired; determining a risk evaluation score based on the risk value corresponding to each story node in the user credit description text; and determining the risk level of the user to be evaluated based on the risk evaluation score.
In this embodiment, the risk value may be empirically given by an expert. The risk assessment score can be obtained through weighted calculation of risk values of all user nodes, wherein the story nodes correspond to the story line labels.
Illustratively, the story nodes may include A, B and C, the electronic device may receive the weights corresponding to risk values 1, 2, 3,A, B and C of A, B and C, respectively, which are empirically given by an expert, and may be 0.2, 0.3 and 0.5, respectively, and the risk assessment score =1 × 0.2 × 0.3+3 × 0.5=2.3; further, the risk level of the credit description text of the user is determined according to the risk level threshold interval where the risk assessment score is located, for example, when the risk assessment score is 2.3, the risk assessment score is at a low risk level.
In some embodiments, after the user credit description text is generated, integrity verification may also be performed on the user credit description text. Specifically, if the story nodes in the user credit description text are more than 3, and the sum of the weights of the story nodes is more than a preset threshold, the user credit description text is verified, and the client is added to a list allowing money to be placed.
In some embodiments, if the behavior data is detected to be changed, the credit description text of the user is automatically regenerated, so that the accuracy and the real-time performance of the credit description text of the user are improved.
In some embodiments, the user credit description text may also be scored periodically, and if the score is smaller than a preset threshold, the user credit description text is offline; and if the score is larger than a preset threshold value, the credit description text of the user is put on line.
According to the technical scheme of the embodiment of the invention, the risk grade of the user to be evaluated is determined through the user credit description text, so that a reliable basis is provided for the user credit description text to be on-line, the risk identification is more visual, and the identification difficulty is reduced.
Example four
Fig. 4 is a schematic structural diagram of a credit description text generating device according to a fourth embodiment of the present invention. As shown in fig. 4, the apparatus includes:
a behavior data obtaining module 410, configured to obtain behavior data of each user node in a user association relationship segmentation network where a user to be evaluated is located;
the plot tag matching module 420 is configured to match behavior data of each user node in the user association relationship segmentation network where the user to be evaluated is located in a plot tag library to obtain a plot tag of the user to be evaluated;
and the description text generation module 430 is used for generating a user credit description text based on the story line label of the user to be evaluated.
According to the technical scheme of the embodiment of the invention, the behavior data of each user node in the network is segmented by acquiring the association relation of the user to be evaluated, so that the evaluation data is enriched; matching the behavior data of each user node in the user incidence relation segmentation network of the user to be evaluated in a story label library to obtain a story label of the user to be evaluated; and generating a user credit description text based on the story line label of the user to be evaluated, so that the risk identification is more intuitive, and the identification difficulty is reduced.
In some optional embodiments, the behavior data obtaining module 410 includes:
the system comprises a relation network acquisition unit, a relation network acquisition unit and a relation management unit, wherein the relation network acquisition unit is used for acquiring a user incidence relation network, and the user incidence relation network comprises a plurality of user nodes;
the betweenness information determining unit is used for determining betweenness information of a connection edge between every two user nodes in the user association relationship network, wherein the betweenness information comprises edge betweenness and relative betweenness;
the network segmentation unit is used for segmenting the user association relationship network based on the betweenness information of the connection edge between every two user nodes in the user association relationship network to obtain a plurality of user association relationship segmented networks;
and the behavior data calling unit is used for determining the user association relation segmentation network where the user to be evaluated is located and calling the behavior data of each user node in the user association relation segmentation network where the user to be evaluated is located.
In some optional embodiments, the betweenness information determining unit is specifically configured to:
respectively confirming the shortest path between every two user nodes in the user association relationship network to obtain a shortest path set;
determining edge betweenness of connecting edges between every two user nodes in the user association relationship network based on the shortest path set;
and determining the relative betweenness of the connecting edge between every two user nodes in the user association relationship network based on the edge betweenness of the connecting edge between every two user nodes in the user association relationship network and the conduction coefficient of the connecting edge between every two user nodes in the user association relationship network.
In some optional embodiments, the network segmentation unit is specifically configured to:
sequencing based on edge betweenness of connecting edges between every two user nodes in the user incidence relation network to obtain a first sequencing result;
when the first sequencing result has connecting edges with the same edge betweenness, sequencing the first sequencing result based on the relative betweenness of the connecting edges between every two user nodes in the user association relationship network to obtain a second sequencing result;
and sequentially deleting the connection side with the minimum relative betweenness from the connection sides with the maximum betweenness number in the user association relationship network based on the second sequencing result to obtain a plurality of user association relationship split networks.
In some optional embodiments, the apparatus further comprises:
and the risk level determining module is used for determining the risk level of the user to be evaluated based on the user credit description text.
In some optional embodiments, the risk level determination module is specifically configured to:
acquiring a risk value corresponding to each story node in the user credit description text;
determining a risk evaluation score based on a risk value corresponding to each story node in the user credit description text;
and determining the risk level of the user to be evaluated based on the risk evaluation score.
In some optional embodiments, the description text generation module 430 is specifically configured to:
and inputting the story line label of the user to be evaluated into a pre-established story generation template to obtain a credit description text of the user.
The credit description text generation device provided by the embodiment of the invention can execute the credit description text generation method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
EXAMPLE five
FIG. 5 illustrates a schematic diagram of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to the bus 14.
A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
acquiring behavior data of each user node in a user association relation segmentation network of a user to be evaluated;
matching the behavior data of each user node in the user association relation segmentation network of the user to be evaluated in a story label library to obtain a story label of the user to be evaluated;
and generating a user credit description text based on the story line label of the user to be evaluated.
In some embodiments, the credit description text generation method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the above described credit description text generation method may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the credit description text generation method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on 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 compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include a client and a server. A user terminal and server are generally remote from each other and typically interact through a communication network. The relationship of user side and server arises by virtue of computer programs running on the respective computers and having a user side-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above, reordering, adding or deleting steps, may be used. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with 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 (10)
1. A credit description text generation method, comprising:
acquiring behavior data of each user node in a user association relation segmentation network of a user to be evaluated;
matching the behavior data of each user node in the user association relation segmentation network of the user to be evaluated in a story label library to obtain a story label of the user to be evaluated;
and generating a user credit description text based on the story line label of the user to be evaluated.
2. The method according to claim 1, wherein the obtaining of the behavior data of each user node in the user association relationship segmentation network where the user to be evaluated is located comprises:
acquiring a user association relationship network, wherein the user association relationship network comprises a plurality of user nodes;
determining betweenness information of a connecting edge between every two user nodes in the user association relationship network, wherein the betweenness information comprises edge betweenness and relative betweenness;
dividing the user association relationship network based on betweenness information of a connecting edge between every two user nodes in the user association relationship network to obtain a plurality of user association relationship divided networks;
and determining the user association relation segmentation network of the user to be evaluated, and calling behavior data of each user node in the user association relation segmentation network of the user to be evaluated.
3. The method of claim 2, wherein the determining the betweenness information of the connection edge between each two user nodes in the user association relationship network comprises:
respectively confirming the shortest path between every two user nodes in the user association relationship network to obtain a shortest path set;
determining edge betweenness of connecting edges between every two user nodes in the user association relationship network based on the shortest path set;
and determining the relative betweenness of the connecting edges between every two user nodes in the user association relationship network based on the edge betweenness of the connecting edges between every two user nodes in the user association relationship network and the conduction coefficient of the connecting edges between every two user nodes in the user association relationship network.
4. The method according to claim 2, wherein the segmenting the user association network based on the betweenness information of the connection edge between each two user nodes in the user association network to obtain a plurality of user association split networks comprises:
sequencing based on edge betweenness of connecting edges between every two user nodes in the user incidence relation network to obtain a first sequencing result;
when the first sequencing result has connecting edges with the same edge betweenness, sequencing the first sequencing result based on the relative betweenness of the connecting edges between every two user nodes in the user association relationship network to obtain a second sequencing result;
and sequentially deleting the connection side with the minimum relative betweenness from the connection sides with the maximum betweenness number in the user association relationship network based on the second sequencing result to obtain a plurality of user association relationship split networks.
5. The method of claim 1, wherein after generating a user credit description text based on the storyline tag of the user to be evaluated, the method further comprises:
and determining the risk level of the user to be evaluated based on the user credit description text.
6. The method of claim 5, wherein the determining the risk level of the user to be assessed based on the user credit description text comprises:
acquiring a risk value corresponding to each story node in the user credit description text;
determining a risk evaluation score based on the risk value corresponding to each story node in the user credit description text;
and determining the risk level of the user to be evaluated based on the risk evaluation score.
7. The method of claim 1, wherein generating a user credit description text based on the storyline tag of the user to be evaluated comprises:
and inputting the story line label of the user to be evaluated into a pre-established story generation template to obtain a credit description text of the user.
8. A credit description text generation apparatus, comprising:
the behavior data acquisition module is used for acquiring the behavior data of each user node in the user association relation segmentation network of the user to be evaluated;
the plot label matching module is used for matching the behavior data of each user node in the user incidence relation segmentation network of the user to be evaluated in a plot label library to obtain a plot label of the user to be evaluated;
and the description text generation module is used for generating a user credit description text based on the story line label of the user to be evaluated.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the credit description text generation method of any one of claims 1-7.
10. A computer-readable storage medium storing computer instructions for causing a processor to implement the credit description text generation method of any one of claims 1-7 when executed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211082378.1A CN115439214A (en) | 2022-09-06 | 2022-09-06 | Credit description text generation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211082378.1A CN115439214A (en) | 2022-09-06 | 2022-09-06 | Credit description text generation method and device, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115439214A true CN115439214A (en) | 2022-12-06 |
Family
ID=84246852
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211082378.1A Pending CN115439214A (en) | 2022-09-06 | 2022-09-06 | Credit description text generation method and device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115439214A (en) |
-
2022
- 2022-09-06 CN CN202211082378.1A patent/CN115439214A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111861596A (en) | Text classification method and device | |
CN112989235A (en) | Knowledge base-based internal link construction method, device, equipment and storage medium | |
CN115049446A (en) | Merchant identification method and device, electronic equipment and computer readable medium | |
CN114444514B (en) | Semantic matching model training method, semantic matching method and related device | |
CN115456634A (en) | Data processing method and device, electronic equipment and storage medium | |
CN111429257B (en) | Transaction monitoring method and device | |
CN115439214A (en) | Credit description text generation method and device, electronic equipment and storage medium | |
CN114996930A (en) | Modeling method and device, electronic equipment and storage medium | |
CN116244740B (en) | Log desensitization method and device, electronic equipment and storage medium | |
CN114492409B (en) | Method and device for evaluating file content, electronic equipment and program product | |
CN118427289A (en) | Entity relation extraction method, device and equipment based on document format information | |
CN115935054A (en) | Information pushing method and device, electronic equipment and storage medium | |
CN115619413A (en) | Method, device, equipment and storage medium for determining abnormal transactions | |
CN117251733A (en) | Rule generation method and device, electronic equipment and storage medium | |
CN113360602A (en) | Method, apparatus, device and storage medium for outputting information | |
CN117609723A (en) | Object identification method and device, electronic equipment and storage medium | |
CN115099927A (en) | Loan risk analysis method and device based on social network analysis | |
CN114549018A (en) | Method and device for determining anti-fraud policy and electronic equipment | |
CN115827743A (en) | Auditing method, device, equipment and storage medium | |
CN115760462A (en) | Accounting method, device, equipment and storage medium for capital flow | |
CN116308455A (en) | Method and device for identifying hub area in trade network | |
CN114627410A (en) | Video verification method and related device for obtaining service | |
CN117172803A (en) | Bid risk determination method, device, equipment and storage medium | |
CN115619411A (en) | Suspicious transaction monitoring method, device, equipment and storage medium | |
CN115221421A (en) | Data processing method and device, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |