CN112734181A - Business information approval method and device, computer equipment and storage medium - Google Patents
Business information approval method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112734181A CN112734181A CN202011604401.XA CN202011604401A CN112734181A CN 112734181 A CN112734181 A CN 112734181A CN 202011604401 A CN202011604401 A CN 202011604401A CN 112734181 A CN112734181 A CN 112734181A
- Authority
- CN
- China
- Prior art keywords
- information
- approval
- risk
- approved
- business
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/126—Character encoding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
Abstract
The invention discloses a method and a device for examining and approving service information, computer equipment and a storage medium, wherein the method comprises the following steps: the method comprises the steps of splitting business information to be approved into a plurality of information sections, obtaining a feature code corresponding to each information section, inputting the feature code into a risk analysis model for analysis to obtain a risk grade corresponding to each information section, adding a risk mark to the information section in a business information table to be approved according to the risk grade, obtaining an approval principal corresponding to each risk mark according to an approval chain and type information, correspondingly generating risk approval request information matched with each approval principal, and sending the risk approval request information to a corresponding approval terminal. The invention is based on a classification model technology, belongs to the technical field of artificial intelligence, and also relates to a block chain technology, which can accurately acquire the risk level of each information segment, add corresponding risk marks, generate risk approval request information and send the information to an approval terminal, thereby greatly improving the efficiency of approving business information.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, belongs to an application scene of intelligent approval of business information in a smart city, and particularly relates to a business information approval method, a business information approval device, computer equipment and a storage medium.
Background
In order to prevent the business risk, the enterprise needs to acquire the risk level of the corresponding business information in the business scene, and sends the business information to the corresponding responsible person in the enterprise for examination and approval according to the risk level, so that the risk prevention capability of the enterprise is improved. However, when the data volume of the service information is large, the overall risk cannot accurately reflect the local risk in the service information, and the content with the risk in the service information is difficult to accurately position by a responsible person of an enterprise, which affects the efficiency of examining and approving the service information, causes long time consumption for examining and approving the service information, and increases the operation cost of the enterprise. Therefore, the traditional technical method has the problem of low efficiency of examining and approving the service information.
Disclosure of Invention
The embodiment of the invention provides a business information approval method, a business information approval device, a computer device and a storage medium, and aims to solve the problem that the efficiency of approving business information is low in the prior art.
In a first aspect, an embodiment of the present invention provides a method for approving service information, where the method includes:
if the business information to be examined and approved from the user terminal is received, splitting the business information to be examined and approved into a plurality of information segments according to a preset splitting rule;
respectively converting the plurality of information segments into a plurality of feature codes according to a pre-stored conversion dictionary;
acquiring a risk level corresponding to each information segment according to a preset risk analysis model and the feature code of each information segment;
adding risk marks to the information matched with the information segments in the business information to be examined and approved according to the risk level of each information segment;
acquiring an approval responsible person corresponding to each risk mark according to a pre-stored approval chain and the type information of the service information to be approved;
and correspondingly generating risk approval request information matched with each approval responsible person according to the approval responsible person corresponding to each risk mark, and sending the risk approval request information to the approval terminal corresponding to each approval responsible person.
In a second aspect, an embodiment of the present invention provides a device for approving service information, including:
the service information splitting unit is used for splitting the service information to be approved into a plurality of information segments according to a preset splitting rule if the service information to be approved from the user terminal is received;
the characteristic code acquisition unit is used for respectively converting the information segments into a plurality of characteristic codes according to a pre-stored conversion dictionary;
the risk level obtaining unit is used for obtaining a risk level corresponding to each information segment according to a preset risk analysis model and the characteristic code of each information segment;
a risk mark adding unit, configured to add a risk mark to information, which is matched with each information segment, in the to-be-approved business information according to the risk level of each information segment;
the examination and approval responsible person acquisition unit is used for acquiring the examination and approval responsible persons corresponding to the risk marks according to a prestored examination and approval chain and the type information of the business information to be examined and approved;
and the risk approval request information sending unit is used for correspondingly generating risk approval request information matched with each approval responsible person according to the approval responsible person corresponding to each risk mark, and sending the risk approval request information to the approval terminal corresponding to each approval responsible person.
In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor, when executing the computer program, implements the service information approval method according to the first aspect.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and the computer program, when executed by a processor, causes the processor to execute the business information approval method according to the first aspect.
The embodiment of the invention provides a method and a device for examining and approving service information and a computer-readable storage medium. The method comprises the steps of splitting business information to be approved into a plurality of information sections, obtaining a feature code corresponding to each information section, inputting the feature code into a risk analysis model for analysis to obtain a risk grade corresponding to each information section, adding a risk mark to the information section in a business information table to be approved according to the risk grade, obtaining an approval principal corresponding to each risk mark according to an approval chain and type information, correspondingly generating risk approval request information matched with each approval principal, and sending the risk approval request information to a corresponding approval terminal. By the method, the risk grade of each information segment can be accurately acquired, the corresponding risk mark is added, the risk approval request information is generated and sent to the approval terminal, and the efficiency of approving the business information can be greatly improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are 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 schematic flow chart of a business information approval method according to an embodiment of the present invention;
fig. 2 is a schematic view of an application scenario of a service information approval method according to an embodiment of the present invention;
fig. 3 is a schematic sub-flow diagram of a business information approval method according to an embodiment of the present invention;
fig. 4 is another schematic sub-flow diagram of a business information approval method according to an embodiment of the present invention;
fig. 5 is a schematic view of another sub-process of the method for approving service information according to the embodiment of the present invention;
fig. 6 is another schematic sub-flow diagram of a business information approval method according to an embodiment of the present invention;
fig. 7 is another schematic sub-flow diagram of a business information approval method according to an embodiment of the present invention;
fig. 8 is another schematic flow chart of a method for approving service information according to an embodiment of the present invention;
fig. 9 is a schematic block diagram of a service information approval apparatus according to an embodiment of the present invention;
FIG. 10 is a schematic block diagram of a computer device provided by an embodiment of the present invention.
Detailed Description
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 some, not all, embodiments of the present invention. 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 will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
Referring to fig. 1 and fig. 2, fig. 1 is a schematic flowchart of a business information approval method according to an embodiment of the present invention, and fig. 2 is a schematic application scenario diagram of the business information approval method according to the embodiment of the present invention; the business information approval method is applied to a management server 10, the business information approval method is executed through application software installed in the management server 10, a user terminal 20 and an approval terminal 30 are simultaneously connected with the management server 10 through a network to realize data information transmission, a user of the user terminal 20 is a submitter of business information, a user of the approval terminal 30 is an approval responsible person of an enterprise or a government organization, the user terminal 20 is a terminal device, such as a desktop computer, a notebook computer, a tablet computer or a mobile phone, for acquiring business information input by the submitter and sending the business information to the management server 10, the approval terminal 30 is a terminal device, such as a desktop computer, a notebook computer, a tablet computer or a mobile phone, for acquiring risk approval request information from the management server 10 to approve the business information to be approved and generating a risk approval request, the management server 10 is a terminal device, such as a desktop computer, a notebook computer, a tablet computer or a mobile phone, for acquiring the business information to be approved from the user terminal 20 and the information is sent to the server side of the approval terminal 30, the user of the management server 10 may be an administrator of an enterprise or a government agency, the management server 10 may be a server set up by an enterprise, a government agency, or other organization, only one user terminal 20 and one approval terminal 30 are shown in fig. 2 to perform information transmission with the management server 10, and in practical applications, the management server 10 may also perform information transmission with a plurality of user terminals 20 and a plurality of approval terminals at the same time. As shown in fig. 1, the method includes steps S110 to S160.
S110, if the business information to be examined from the user terminal is received, splitting the business information to be examined into a plurality of information segments according to a preset splitting rule.
And if the business information to be examined and approved from the user terminal is received, splitting the business information to be examined and approved into a plurality of information segments according to a preset splitting rule. The method comprises the steps that a submitter of an enterprise submits business information to be approved to a management server through a user terminal, the business information to be approved is generally generated according to different business scenes or different purposes, the business information to be approved comprises corresponding type information, the type information can be used for identifying the type of the business information to be approved, and the type information can be department regulations, policy contracts or purchase and sale agreements and the like. The business information to be examined and approved comprises a large amount of information recorded in a character form, and the management server can split the business information to be examined and approved into a plurality of information sections according to splitting rules after receiving the business information to be examined and approved, wherein each information section comprises a plurality of characters.
In an embodiment, as shown in fig. 3, step S110 includes sub-steps S111, S112 and S113.
S111, acquiring characters matched with preset symbols of the splitting rule in the business information to be examined and approved as segmentation marks; and S112, splitting the service information to be examined and approved into a plurality of information segments according to the segmentation marks.
Specifically, the splitting rule includes a plurality of preset symbols, the pending service information includes a plurality of characters, the characters matching the preset symbols in the pending service information can be obtained as segmentation marks, the pending service information is split according to the segmentation marks, a plurality of characters between a segment head of a paragraph and a first character mark of the paragraph are combined into an information segment, and a plurality of characters between two segmentation marks are also combined into an information segment. Specifically, the default symbols include commas, periods, and semicolons.
S113, adding corresponding position mark information to each information segment according to the position of each information segment in the business information to be audited.
The corresponding position marking information can be obtained according to the position of the information segment and added into each information segment, the specific position of each information segment in the business information to be approved can be grasped through the position marking information, and the information segment can be quickly and accurately positioned through the position marking information.
For example, the position mark information corresponding to one information section located in the first section of the first page may be "1Y 1D".
And S120, respectively converting the plurality of information segments into a plurality of feature codes according to a pre-stored conversion dictionary.
And respectively converting characters contained in the plurality of information segments into a plurality of feature codes according to a pre-stored conversion dictionary. The conversion dictionary is a dictionary for converting characters, each character can be matched with a corresponding characteristic value in the conversion dictionary, the characters contained in each information segment can be converted according to the conversion dictionary, the characteristic values corresponding to a plurality of characters contained in each information segment are combined to obtain a characteristic code matched with each information segment, and the obtained characteristic code expresses the corpus characteristics of the information segment in a coding mode. The conversion dictionary comprises a part of speech matching table and a character coding table.
In an embodiment, as shown in fig. 4, step S120 includes sub-steps S121, S122 and S123.
And S121, obtaining the part-of-speech information of the characters in each information field according to the part-of-speech matching table.
The part-of-speech information table is an information table for recording the part of speech of the phrase, the part-of-speech information table contains part-of-speech information corresponding to each phrase, the phrase contains at least two characters, and a plurality of characters in one phrase share the part-of-speech information of the phrase. Specifically, the part of speech of the phrase may be a noun, a verb, an adjective or a pronoun, etc.
For example, a word group in the part-of-speech information table is "happy", the part-of-speech information of the word group is an adjective, and the part-of-speech information of two consecutive characters matching the word group in the information field is an adjective.
S122, acquiring a code value corresponding to each character according to the character code table and the part-of-speech information of each character; and S123, combining the coded values of the characters in each information segment to obtain a feature code corresponding to each information segment.
The corresponding code value can be obtained from the character code table according to the part-of-speech information of each character, and if the part-of-speech information of the same character is different, the same character is different from the corresponding code value.
For example, the part-of-speech information of the character "fast" is an "adjective" whose corresponding code value in the character code table is "325", and the part-of-speech information of the character "fast" is a "verb" whose corresponding code value in the character code table is "327".
And after the code value of the character in each information segment is obtained, combining the code values to obtain a feature code with a specific length, wherein the length of the feature code of each information segment is equal. The specific size of the feature code is (N, N), which indicates that the feature code is 1 row and N columns, the length N of the feature code can be preset by an administrator of the management server, if the number of code values in the feature code is set to 30(N is 30), the feature values of the characters included in each information segment are sequentially combined to obtain the feature code, and if the number of characters included in the information segment is less than a specific length, the missing part is correspondingly filled with "0" as a code value.
And S130, acquiring a risk level corresponding to each information segment according to a preset risk analysis model and the feature code of each information segment.
And acquiring a risk level corresponding to each information segment according to a preset risk analysis model and the feature code of each information segment. The risk analysis model comprises a plurality of corpus analysis networks and a convolutional neural network, each type of information corresponds to one corpus analysis network in the risk analysis model, the corpus analysis networks can be constructed based on BERT (bidirectional Encoder retrieval from transformations) neural networks, the initial BERT neural network can be trained by adopting a plurality of service information matched with one type of information, and one corpus analysis network matched with the corpus characteristics of the type of information is obtained.
In an embodiment, as shown in fig. 5, step S130 includes sub-steps S131, S132, and S133.
S131, acquiring a corpus analysis network matched with the type information of the business information to be examined and approved in the risk analysis model as a target corpus analysis network; s132, respectively inputting the feature codes of each information segment into the target corpus analysis network to obtain a corpus analysis result of each information segment.
A target corpus analysis network matched with the type information can be obtained according to the type information of the service information to be approved, and the feature codes of each information segment are respectively input into the target corpus analysis network, so that the corresponding corpus analysis result can be obtained. Specifically, the target corpus analysis network is composed of an input layer, a plurality of intermediate layers, and an output layer, and the input layer and the intermediate layers, the intermediate layers and other adjacent intermediate layers, and the intermediate layers and the output layer are all associated by association formulas, for example, a certain association formula may be represented as y ═ r × x + t, and r and t are parameter values in the association formula. The number of input nodes contained in the input layer is equal to the number of characteristic values in the characteristic codes, the characteristic values in the characteristic codes correspond to one input node, the characteristic codes of each information segment are respectively input into a target corpus analysis network through the input layer to be calculated, the corpus analysis result can be obtained from the output layer, the corpus analysis result is represented by an array (N, M), the corpus analysis result corresponding to each information segment is an array of N rows and M columns, and the value range of each numerical value in the array is [0, 1 ].
And S133, respectively inputting the corpus analysis result into a convolutional neural network in the risk analysis model to obtain the risk grade of each information segment.
And inputting the obtained corpus analysis result as input information into a convolutional neural network for processing to obtain the matching degree between each information segment and a plurality of risk grades, and selecting the risk grade with the highest matching degree as the risk grade matched with each information segment. Specifically, the convolutional neural network may be composed of an input layer, a plurality of intermediate layers, and an output layer, where the input layer includes a plurality of input nodes, the number of the input nodes is equal to the number of values included in an array corresponding to a corpus analysis result, the output layer includes a plurality of output nodes, and the input layer and the intermediate layers, the intermediate layers and other adjacent intermediate layers, and the intermediate layers and the output layer are all associated by association formulas. And inputting a corpus analysis result into the intention recognition model for calculation to obtain the matching degree of the corpus analysis result and each risk level, wherein the risk level can be no risk, low risk, medium risk and high risk, and the value range of the matching degree corresponding to each risk level is [0, 1 ]. Before the convolutional neural network is used, a plurality of corpus analysis networks can be respectively combined with the convolutional neural network, and gradient descent training is carried out on the convolutional neural network according to a gradient descent training method to obtain the trained convolutional neural network.
And pre-training the initial BERT neural network according to the corpus data of the type information and a pre-training rule to obtain a corpus analysis network corresponding to the corpus data, namely obtaining a corpus analysis network suitable for the language environment of the type information. Each type of information comprises a plurality of pieces of linguistic data, and each piece of linguistic data comprises a piece of text information. Specifically, the process of training the BERT neural network includes: (1) randomly selecting part of corpus data corresponding to a proportion value in a pre-training rule from corpus data of one type of information as target corpus data; each corpus data is a complete sentence, each corpus data is composed of a plurality of characters, a proportion value is set in the pre-training rule, and a corresponding amount of corpus data can be randomly selected from the corpus data of one type of information according to the proportion value to serve as target corpus data, for example, the proportion value can be set to be 10-90%. (2) Carrying out random replacement processing on the target corpus data to obtain corpus processing data; each corpus consists of a plurality of characters, and any one character in each corpus can be replaced to obtain corpus processing data containing replaced characters. (3) Respectively converting the target corpus data and the corpus processing data according to the conversion dictionary to obtain a first feature code and a second feature code; each character can be matched with a corresponding characteristic value in the conversion dictionary, so that the characters contained in the target corpus data can be converted according to the conversion dictionary to obtain a corresponding first characteristic code, and the corpus processing data is converted in a unified mode to obtain a second characteristic code. The specific method for acquiring the first feature code and the second feature code is the same as the method for acquiring the feature code of the information segment. (4) Encoding one of the first features with a corresponding one of the second featuresInputting the feature codes into the initial BERT neural network to calculate to respectively obtain a first array and a second array; and respectively inputting one first feature code and one corresponding second feature code into an initial BERT neural network for calculation to respectively obtain a first analysis result and a second analysis result. Specifically, the first feature code is input into the initial BERT neural network for calculation to obtain a corresponding first analysis result, the second feature code is input into the initial BERT neural network for calculation to obtain a corresponding second analysis result, the specific method for obtaining the first analysis result and the second analysis result is the same as the method for obtaining the corpus analysis result of the information segment, and the first analysis result and the second analysis result can be represented by an array (N, M). (5) Calculating a loss value between the first analysis result and the second analysis result according to a loss function calculation formula in the pre-training rule; the pre-training rule further includes a loss function, the loss value can be used for quantitatively representing a difference between the first analysis result and the second analysis result, and specifically, the first analysis result S can be obtained by calculating with a loss function calculation formula1And the second analysis result S2Value of loss in between
Wherein Ls is the calculated loss value, axyAs a first analysis result S1Value in the x-th row and y-th column, bxyAs a second analysis result S2The x-th row and the y-th column in the first analysis result, N is the total row number of the first analysis result S1, and M is the total column number of the first analysis result S1. (6) And calculating an update value of a corresponding parameter in the initial BERT neural network according to a gradient calculation formula in the pre-training rule, the loss value and a calculation value of the initial BERT neural network so as to update the parameter value of the parameter.
Specifically, a calculation value obtained by calculating the first feature code by one parameter in the initial BERT neural network is input into a gradient calculation formula, and an update value corresponding to the parameter can be calculated by combining the loss value, and the calculation process is also gradient descent calculation.
Specifically, the gradient calculation formula can be expressed as:
One piece of target corpus data and one piece of corpus processing data corresponding to the item taggant data can update the parameter value of the initial BERT neural network once, namely, a pre-training process is completed, and the initial BERT neural network is subjected to iterative pre-training according to a plurality of pieces of target corpus data and a plurality of pieces of corpus processing data corresponding to one type of information, so that a corpus analysis network corresponding to the type of information can be obtained.
And S140, adding risk marks to the information matched with the information segments in the business information to be examined and approved according to the risk level of each information segment.
And adding risk marks to the information matched with the information segments in the business information to be examined and approved according to the risk level of each information segment. Specifically, each information segment comprises corresponding position mark information, a risk mark matched with the risk level is added to a position corresponding to the position mark information in the business information to be approved according to the position mark information corresponding to each information segment and the corresponding risk level, the risk mark can mark the content with risk and the corresponding risk level in the business information to be approved, and the content with different risk levels is marked by adopting different forms of risk marks.
S150, acquiring an approval responsible person corresponding to each risk mark according to a pre-stored approval chain and the type information of the service information to be approved.
And acquiring an approval responsible person corresponding to each risk mark according to a pre-stored approval chain and the type information of the service information to be approved. The examination and approval chain is link information which is configured in the management server and used for storing examination and approval paths, and the examination and approval chain comprises a plurality of examination and approval paths.
In one embodiment, as shown in FIG. 6, step S150 includes sub-steps S151 and S152.
S151, acquiring an approval path matched with the type information in the approval chain as a target approval path; and S152, acquiring an approval responsible person matched with each risk mark in the business information to be approved according to the information of the approver of each approval level in the target approval path.
Each approval path corresponds to one type of information, a target approval path matched with the type of the service information to be approved can be obtained, and the approval responsible persons matched with the risk grades of each risk mark are determined according to the corresponding approval levels in the target approval paths. Specifically, each approval path includes a plurality of approval levels, each approval level corresponds to one risk level, an approval level matched with the corresponding risk level in the target approval path can be determined according to the risk level of each risk mark, information of an approver of the approval level matched with each risk mark is acquired as an approval principal of each risk mark, the same approval principal can belong to a plurality of approval levels at the same time, and one or more approval principals matched with the risk marks can exist.
And S160, correspondingly generating risk approval request information matched with each approval responsible person according to the approval responsible person corresponding to each risk mark, and sending the risk approval request information to the approval terminal corresponding to each approval responsible person.
And correspondingly generating risk approval request information matched with each approval responsible person according to the approval responsible person corresponding to each risk mark, and sending the risk approval request information to the approval terminal corresponding to each approval responsible person. After the approval responsible person of each risk mark is obtained, risk approval request information matched with each approval responsible person can be generated according to the risk mark and the business information to be approved, the risk approval request information is the request information containing the business information to be approved and the corresponding risk mark, the generated risk approval request information is sent to the corresponding approval terminal, the approval responsible person can use the approval terminal to approve the risk approval request information, and the approval result obtained by the approval responsible person through approval of the business information to be approved can be obtained.
In one embodiment, as shown in fig. 7, step S160 includes sub-steps S161 and S162.
And S161, determining the highest risk level of each approval principal according to the risk mark corresponding to each approval principal.
The risk marks contained by each examination and approval responsible person can be determined according to the examination and approval responsible persons corresponding to the risk marks, and the highest risk level matched with the examination and approval responsible persons is determined according to the risk levels of the examination and approval responsible persons containing the risk marks.
And S162, generating risk approval request information matched with each approval principal according to the highest risk grade and the risk mark corresponding to each approval principal.
And acquiring a sending template matched with the highest risk grade in a pre-stored template library according to the highest risk grade of each examination and approval responsible person, wherein different risk grades correspond to different sending templates in the template library, and correspondingly generating risk examination and approval request information matched with each examination and approval responsible person according to the sending template and the business information to be examined and approved. Specifically, according to the method, a risk mark corresponding to the current examination and approval person is reserved in the business information to be approved, other risk marks are deleted, a sending mode contained in a sending template matched with the examination and approval person is added to the business information to be approved containing the risk mark to obtain risk examination and approval request information, the risk examination and approval request information can be correspondingly sent according to the sending mode contained in the sending template, and the sending template can comprise a plurality of preset interval time; if the approval result is not received within a first interval time preset after the risk approval request information is sent, sending mail prompt information to an approval terminal corresponding to an approval principal of the current approval risk request, wherein the first interval time can be 12 hours, for example; if the approval result is not received within a preset second interval time after the risk approval request information is sent, sending mail prompt information and voice telephone prompt information to an approval terminal corresponding to the approval principal of the current approval risk request, wherein the second interval time can be 18 hours, for example; if the examination and approval result is not received within a preset third interval after the risk examination and approval request information is sent, sending voice telephone prompting information to an examination and approval terminal corresponding to an examination and approval principal of the current examination and approval risk request, and copying mail prompting information to a user terminal corresponding to a superior leader of the current examination and approval principal, wherein the third interval can be 24 hours, for example; if the approval result is not received within a preset fourth interval time after the risk approval request information is sent, sending voice telephone prompt information to the approval terminal corresponding to the approval principal of the current approval risk request every unit time, wherein the fourth interval time can be 36 hours and the unit time is 1 hour, for example. Specifically, if only one approval hierarchy corresponding to the highest risk level of the approval principals comprises one approval principal, the risk approval request information is sent to the approval terminal corresponding to the approval principal; if one approval level corresponding to the highest risk level of the approval principals comprises a plurality of approval principals, the risk approval request information is sent to an approval terminal corresponding to a first approval principal in the approval level, a first approval result fed back by the approval terminal corresponding to the first approval principal is obtained, if the approval result is passed, the first approval result and the risk approval request information are sent to an approval terminal corresponding to a second approval principal in the approval level until all the approval principals in the approval level approve the risk approval request information.
In one embodiment, as shown in fig. 8, step S170 is included after step S160.
S170, obtaining the approval results fed back by each approval terminal, and synchronously uploading the approval results to a block chain for storage.
And uploading the approval result to a block chain for storage, and obtaining corresponding digest information based on the approval result, specifically, obtaining the digest information by performing hash processing on the approval result, for example, by using the sha256s algorithm. Uploading summary information to the blockchain can ensure the safety and the fair transparency of the user. The user equipment may download the summary information from the blockchain to verify whether the approval result is tampered. The blockchain referred to in this example is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm, and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
The technical method can be applied to application scenes including intelligent examination and approval of business information, such as intelligent government affairs, intelligent city management, intelligent community, intelligent security, intelligent logistics, intelligent medical treatment, intelligent education, intelligent environmental protection and intelligent traffic, so that the construction of the intelligent city is promoted.
In the business information approval method provided by the embodiment of the invention, the business information to be approved is divided into a plurality of information sections, the characteristic code corresponding to each information section is obtained, the characteristic code is input into a risk analysis model for analysis to obtain the risk grade corresponding to each information section, the information sections in the business information table to be approved are added with risk marks according to the risk grades, the approval responsible persons corresponding to each risk mark are obtained according to the approval chain and the type information, and the risk approval request information matched with each approval responsible person is correspondingly generated and sent to the corresponding approval terminal. By the method, the risk grade of each information segment can be accurately acquired, the corresponding risk mark is added, the risk approval request information is generated and sent to the approval terminal, and the efficiency of approving the business information can be greatly improved.
The embodiment of the present invention further provides a service information approval apparatus, which can be configured in the management server 10, and the service information approval apparatus is configured to execute any one of the embodiments of the service information approval methods described above. Specifically, referring to fig. 9, fig. 9 is a schematic block diagram of a service information approval apparatus according to an embodiment of the present invention.
As shown in fig. 9, the service information approval apparatus 100 includes a service information splitting unit 110, a feature code obtaining unit 120, a risk level obtaining unit 130, a risk flag adding unit 140, an approval principal obtaining unit 150, and a risk approval request information sending unit 160.
The service information splitting unit 110 is configured to, if the service information to be approved is received from the user terminal, split the service information to be approved into a plurality of information segments according to a preset splitting rule.
In an embodiment, the service information splitting unit 110 includes sub-units: a segmentation mark acquisition unit, configured to acquire a character, which is in the to-be-approved service information and matches with a preset symbol of the splitting rule, as a segmentation mark; the splitting unit is used for splitting the business information to be examined and approved into a plurality of information segments according to the segmentation marks; and the position mark information adding unit is used for adding corresponding position mark information to each information segment according to the position of each information segment in the business information to be audited.
A feature code obtaining unit 120, configured to convert the plurality of information segments into a plurality of feature codes according to a pre-stored conversion dictionary, respectively.
In one embodiment, the feature code obtaining unit 120 includes sub-units: a part-of-speech information obtaining unit, configured to obtain, according to the part-of-speech matching table, part-of-speech information of the character in each information field; the coded value acquisition unit is used for acquiring a coded value corresponding to each character according to the character coded list and the part-of-speech information of each character; and the coded value combining unit is used for combining the coded values of the characters in each information segment to obtain the characteristic codes corresponding to each information segment.
A risk level obtaining unit 130, configured to obtain a risk level corresponding to each information segment according to a preset risk analysis model and a feature code of each information segment.
In an embodiment, the risk level obtaining unit 130 includes sub-units: a target corpus analysis network obtaining unit, configured to obtain a corpus analysis network in the risk analysis model, where the corpus analysis network matches the type information of the to-be-examined and approved service information, as a target corpus analysis network; a corpus analysis result obtaining unit, configured to input the feature code of each information segment into the target corpus analysis network respectively to obtain a corpus analysis result of each information segment; and the risk analysis unit is used for respectively inputting the corpus analysis result into a convolutional neural network in the risk analysis model to obtain the risk grade of each information segment.
And a risk mark adding unit 140, configured to add a risk mark to the information matching the information segment in the pending service information according to the risk level of each information segment.
And an approval responsible person obtaining unit 150, configured to obtain, according to a pre-stored approval chain and the type information of the service information to be approved, an approval responsible person corresponding to each risk label.
In one embodiment, the approval principal obtaining unit 150 includes sub-units: the target approval path acquisition unit is used for acquiring one approval path matched with the type information in the approval chain as a target approval path; and the examination and approval responsible person matching unit is used for acquiring the examination and approval responsible persons matched with each risk mark in the business information to be examined and approved according to the examination and approval person information of each examination and approval level in the target examination and approval path.
And the risk approval request information sending unit 160 is configured to generate risk approval request information matched with each approval principal according to the approval principal corresponding to each risk marker, and send the risk approval request information to the approval terminal corresponding to each approval principal.
In one embodiment, the risk approval request information sending unit 160 includes sub-units: the highest risk level determining unit is used for determining the highest risk level of each examination and approval responsible person according to the risk mark corresponding to each examination and approval responsible person; and the risk approval request information generating unit is used for generating risk approval request information matched with each approval responsible person according to the highest risk grade and the risk mark corresponding to each approval responsible person.
In an embodiment, the service information approval apparatus 100 further includes a sub-unit: and the synchronous storage unit is used for acquiring the approval results fed back by each approval terminal and synchronously uploading the approval results to the block chain for storage.
The business information approval device provided by the embodiment of the invention applies the business information approval method, the business information to be approved is divided into a plurality of information sections, the characteristic code corresponding to each information section is obtained, the characteristic code is input into a risk analysis model to be analyzed to obtain the risk grade corresponding to each information section, the information sections in the business information table to be approved are added with risk marks according to the risk grades, the approval responsible persons corresponding to each risk mark are obtained according to the approval chain and the type information, and the risk approval request information matched with each approval responsible person is correspondingly generated and sent to the corresponding approval terminal. By the method, the risk grade of each information segment can be accurately acquired, the corresponding risk mark is added, the risk approval request information is generated and sent to the approval terminal, and the efficiency of approving the business information can be greatly improved.
The service information approval apparatus may be implemented in the form of a computer program, and the computer program may be run on a computer device as shown in fig. 10.
Referring to fig. 10, fig. 10 is a schematic block diagram of a computer device according to an embodiment of the present invention. The computer device may be a management server 10 for performing a business information approval method to intelligently approve business information.
Referring to fig. 10, the computer device 500 includes a processor 502, memory, and a network interface 505 connected by a system bus 501, where the memory may include a storage medium 503 and an internal memory 504.
The storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032, when executed, may cause the processor 502 to perform a business information approval method, wherein the storage medium 503 may be a volatile storage medium or a non-volatile storage medium.
The processor 502 is used to provide computing and control capabilities that support the operation of the overall computer device 500.
The internal memory 504 provides an environment for the operation of the computer program 5032 in the storage medium 503, and when the computer program 5032 is executed by the processor 502, the processor 502 can execute the business information approval method.
The network interface 505 is used for network communication, such as providing transmission of data information. Those skilled in the art will appreciate that the configuration shown in fig. 10 is a block diagram of only a portion of the configuration associated with aspects of the present invention and is not intended to limit the computing device 500 to which aspects of the present invention may be applied, and that a particular computing device 500 may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
The processor 502 is configured to run a computer program 5032 stored in the memory to implement the corresponding functions in the service information approval method.
Those skilled in the art will appreciate that the embodiment of a computer device illustrated in fig. 10 does not constitute a limitation on the specific construction of the computer device, and that in other embodiments a computer device may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components. For example, in some embodiments, the computer device may only include a memory and a processor, and in such embodiments, the structures and functions of the memory and the processor are consistent with those of the embodiment shown in fig. 10, and are not described herein again.
It should be understood that, in the embodiment of the present invention, the Processor 502 may be a Central Processing Unit (CPU), and the Processor 502 may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
In another embodiment of the invention, a computer-readable storage medium is provided. The computer readable storage medium may be a volatile or non-volatile computer readable storage medium. The computer readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps included in the above-mentioned business information approval method.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses, devices and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided by the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only a logical division, and there may be other divisions when the actual implementation is performed, or units having the same function may be grouped into one unit, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention essentially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a computer-readable storage medium, which includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned computer-readable storage media comprise: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only memory (ROM), a magnetic disk, or an optical disk.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A business information examination and approval method is applied to a management server, the management server is connected with a user terminal and an examination and approval terminal through a network to transmit data information, and the method is characterized by comprising the following steps:
if the business information to be examined and approved from the user terminal is received, splitting the business information to be examined and approved into a plurality of information segments according to a preset splitting rule;
respectively converting the plurality of information segments into a plurality of feature codes according to a pre-stored conversion dictionary;
acquiring a risk level corresponding to each information segment according to a preset risk analysis model and the feature code of each information segment;
adding risk marks to the information matched with the information segments in the business information to be examined and approved according to the risk level of each information segment;
acquiring an approval responsible person corresponding to each risk mark according to a pre-stored approval chain and the type information of the service information to be approved;
and correspondingly generating risk approval request information matched with each approval responsible person according to the approval responsible person corresponding to each risk mark, and sending the risk approval request information to the approval terminal corresponding to each approval responsible person.
2. The method for approving service information according to claim 1, wherein the splitting the service information to be approved into a plurality of information segments according to a preset splitting rule includes:
acquiring characters matched with preset symbols of the splitting rule in the business information to be examined and approved as segmentation marks;
splitting the business information to be examined and approved into a plurality of information segments according to the segmentation marks;
and adding corresponding position mark information to each information segment according to the position of each information segment in the service information to be audited.
3. The method of claim 1, wherein the transformation dictionary comprises a part-of-speech matching table and a character encoding table, and the transforming the plurality of information segments into a plurality of feature codes according to a pre-stored transformation dictionary comprises:
acquiring part-of-speech information of characters in each information field according to the part-of-speech matching table;
acquiring a coding value corresponding to each character according to the character coding table and the part-of-speech information of each character;
and combining the coded values of the characters in each information segment to obtain the characteristic code corresponding to each information segment.
4. The method according to claim 1, wherein the risk analysis model includes a plurality of corpus analysis networks and a convolutional neural network, and the obtaining a risk level corresponding to each of the information segments according to a preset risk analysis model and a feature code of each of the information segments includes:
acquiring a corpus analysis network matched with the type information of the business information to be examined and approved in the risk analysis model as a target corpus analysis network;
respectively inputting the feature codes of each information segment into the target corpus analysis network to obtain a corpus analysis result of each information segment;
and respectively inputting the corpus analysis result into a convolutional neural network in the risk analysis model to obtain the risk grade of each information segment.
5. The method for approving service information according to claim 1, wherein the approval chain includes a plurality of approval paths, and the method for acquiring an approval responsible person corresponding to each risk label according to a pre-stored approval chain and type information of the service information to be approved comprises:
acquiring an approval path matched with the type information in the approval chain as a target approval path;
and acquiring an approval responsible person matched with each risk mark in the business information to be approved according to the information of the approver of each approval level in the target approval path.
6. The business information approval method according to claim 1, wherein the generating of the risk approval request information matched with each approval principal according to the approval principal corresponding to each risk label comprises:
determining the highest risk level of each examination and approval responsible person according to the risk mark corresponding to each examination and approval responsible person;
and generating risk approval request information matched with each approval principal according to the highest risk grade and the risk mark corresponding to each approval principal.
7. The method for approving business information according to claim 1, wherein the method further comprises, after the generating the risk approval request information matched with each approval principal according to the approval principal corresponding to each risk label and sending the risk approval request information to the approval terminal corresponding to each approval principal:
and acquiring the approval result fed back by each approval terminal, and synchronously uploading the approval results to a block chain for storage.
8. A business information approval apparatus, comprising:
the service information splitting unit is used for splitting the service information to be approved into a plurality of information segments according to a preset splitting rule if the service information to be approved from the user terminal is received;
the characteristic code acquisition unit is used for respectively converting the information segments into a plurality of characteristic codes according to a pre-stored conversion dictionary;
the risk level obtaining unit is used for obtaining a risk level corresponding to each information segment according to a preset risk analysis model and the characteristic code of each information segment;
a risk mark adding unit, configured to add a risk mark to information, which is matched with each information segment, in the to-be-approved business information according to the risk level of each information segment;
the examination and approval responsible person acquisition unit is used for acquiring the examination and approval responsible persons corresponding to the risk marks according to a prestored examination and approval chain and the type information of the business information to be examined and approved;
and the risk approval request information sending unit is used for correspondingly generating risk approval request information matched with each approval responsible person according to the approval responsible person corresponding to each risk mark, and sending the risk approval request information to the approval terminal corresponding to each approval responsible person.
9. A business information approval apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the business information approval method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the business information approval method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011604401.XA CN112734181A (en) | 2020-12-30 | 2020-12-30 | Business information approval method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011604401.XA CN112734181A (en) | 2020-12-30 | 2020-12-30 | Business information approval method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112734181A true CN112734181A (en) | 2021-04-30 |
Family
ID=75610652
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011604401.XA Pending CN112734181A (en) | 2020-12-30 | 2020-12-30 | Business information approval method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112734181A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113421009A (en) * | 2021-07-02 | 2021-09-21 | 招商局金融科技有限公司 | Accessory approval method and device, electronic equipment and readable storage medium |
| CN113723777A (en) * | 2021-08-16 | 2021-11-30 | 南京航空航天大学 | Method and device for managing civil aircraft operation risk |
| CN113992668A (en) * | 2021-10-25 | 2022-01-28 | 深圳市华创智慧健康科技有限公司 | Multi-concurrency-based information real-time transmission method, device, equipment and medium |
| CN116029681A (en) * | 2023-02-21 | 2023-04-28 | 中信联合云科技有限责任公司 | Method and system for managing review business process based on data processing |
| CN116664088A (en) * | 2023-08-02 | 2023-08-29 | 美宜佳控股有限公司 | File approval data processing method, device, equipment and medium based on LBS |
| CN117132244A (en) * | 2023-10-26 | 2023-11-28 | 国网浙江省电力有限公司 | Classification processing method, device and storage medium for intelligent compliance management system |
-
2020
- 2020-12-30 CN CN202011604401.XA patent/CN112734181A/en active Pending
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113421009A (en) * | 2021-07-02 | 2021-09-21 | 招商局金融科技有限公司 | Accessory approval method and device, electronic equipment and readable storage medium |
| CN113421009B (en) * | 2021-07-02 | 2022-12-27 | 招商局金融科技有限公司 | Accessory approval method and device, electronic equipment and readable storage medium |
| CN113723777A (en) * | 2021-08-16 | 2021-11-30 | 南京航空航天大学 | Method and device for managing civil aircraft operation risk |
| CN113992668A (en) * | 2021-10-25 | 2022-01-28 | 深圳市华创智慧健康科技有限公司 | Multi-concurrency-based information real-time transmission method, device, equipment and medium |
| CN116029681A (en) * | 2023-02-21 | 2023-04-28 | 中信联合云科技有限责任公司 | Method and system for managing review business process based on data processing |
| CN116029681B (en) * | 2023-02-21 | 2023-08-18 | 中信联合云科技有限责任公司 | Method and system for managing review business process based on data processing |
| CN116664088A (en) * | 2023-08-02 | 2023-08-29 | 美宜佳控股有限公司 | File approval data processing method, device, equipment and medium based on LBS |
| CN116664088B (en) * | 2023-08-02 | 2024-02-23 | 美宜佳控股有限公司 | File approval data processing method, device, equipment and medium based on LBS |
| CN117132244A (en) * | 2023-10-26 | 2023-11-28 | 国网浙江省电力有限公司 | Classification processing method, device and storage medium for intelligent compliance management system |
| CN117132244B (en) * | 2023-10-26 | 2024-01-09 | 国网浙江省电力有限公司 | Classification processing method, device and storage medium for intelligent compliance management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112734181A (en) | Business information approval method and device, computer equipment and storage medium | |
| US11636264B2 (en) | Stylistic text rewriting for a target author | |
| JP7000341B2 (en) | Machine learning-based web interface generation and testing system | |
| EP2084620A1 (en) | Document processor and associated method | |
| CN110741376B (en) | Automatic document analysis for different natural languages | |
| WO2021208727A1 (en) | Text error detection method and apparatus based on artificial intelligence, and computer device | |
| CN113283238A (en) | Text data processing method and device, electronic equipment and storage medium | |
| CN112529429A (en) | Customer information checking method and device, computer equipment and storage medium | |
| CN114372475A (en) | Network public opinion emotion analysis method and system based on RoBERTA model | |
| CN113239668B (en) | Keyword intelligent extraction method and device, computer equipment and storage medium | |
| CN113268971B (en) | Intelligent generation method and device of demonstration report, computer equipment and storage medium | |
| CN110298038B (en) | Text scoring method and device | |
| CN111797247B (en) | Case pushing method and device based on artificial intelligence, electronic equipment and medium | |
| Goyal et al. | Developing a chatbot | |
| CN116402166B (en) | Training method and device of prediction model, electronic equipment and storage medium | |
| CN113626576A (en) | Method and device for extracting relational characteristics in remote supervision, terminal and storage medium | |
| CN116562263A (en) | Method, device, equipment and storage medium for evaluating document link continuity | |
| CN116629423A (en) | User behavior prediction method, device, equipment and storage medium | |
| CN114610903A (en) | Text relation extraction method, device, equipment and storage medium | |
| Barrero et al. | Automatic Web data extraction based on genetic algorithms and regular expressions | |
| CN114491004A (en) | Title generation method and device, electronic equipment and storage medium | |
| Sietsma et al. | Progress on climate action: a multilingual machine learning analysis of the global stocktake | |
| CN113688206A (en) | Text recognition-based trend analysis method, device, equipment and medium | |
| CN114265560A (en) | Self-standardization storage system for hundred million-level compliance index service data | |
| CN113269179A (en) | Data processing method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |