CN117952721A - Special fund monitoring method and device based on natural language algorithm - Google Patents
Special fund monitoring method and device based on natural language algorithm Download PDFInfo
- Publication number
- CN117952721A CN117952721A CN202410207114.7A CN202410207114A CN117952721A CN 117952721 A CN117952721 A CN 117952721A CN 202410207114 A CN202410207114 A CN 202410207114A CN 117952721 A CN117952721 A CN 117952721A
- Authority
- CN
- China
- Prior art keywords
- contract
- information
- order
- type
- equipment
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 65
- 230000002159 abnormal effect Effects 0.000 claims description 22
- 230000007246 mechanism Effects 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 18
- 238000013145 classification model Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 12
- 238000012806 monitoring device Methods 0.000 claims description 7
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 14
- 238000004891 communication Methods 0.000 description 11
- 238000012545 processing Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000012827 research and development Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009440 infrastructure construction Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Abstract
The embodiment of the invention provides a special fund monitoring method and device based on a natural language algorithm, which can be used in the technical field of artificial intelligence, and the method comprises the following steps: acquiring contract/order information and equipment information associated with the contract/order information; classifying the contract/order information and the equipment information through a pre-constructed classifier to obtain the contract/order type and the purchased equipment type, wherein the classifier is constructed based on a natural language algorithm; and carrying out compliance matching on the contract/order type and the purchased equipment type to obtain a special fund monitoring result, automatically monitoring the scientific and technological special fund by utilizing the collected contract, order and purchase equipment information, accurately identifying the special fund which is not in compliance, and timely carrying out risk positioning, thereby improving the monitoring accuracy and timeliness of problem positioning after risk occurrence, reducing the manual checking cost and ensuring the fund safety.
Description
Technical Field
The invention relates to the technical field of information technology and information security, in particular to the technical field of artificial intelligence, and particularly relates to a special fund monitoring method and device based on a natural language algorithm.
Background
A special fund refers to a fund having a specific designated purpose or special use. The funds all require separate accounting, are special and cannot be moved to other uses. Technological funds are funds established for improving the technological level, and in the actual use process, equipment or matters which do not meet the technological funds requirements may be purchased in a purchase contract or order, and risks that special money is not dedicated exist. In the related technology, only the auditor can manually check funds of each contract or order, a unified special funds management method is lacked, the manual checking cost is extremely high, the accuracy is low only by means of manual monitoring and checking, and the funds safety cannot be guaranteed.
Disclosure of Invention
The invention aims to provide a special fund monitoring method based on a natural language algorithm, which utilizes collection contract, order and purchase equipment information to automatically monitor technical special fund, can accurately identify the non-compliant special fund and timely perform risk positioning, improves monitoring accuracy and timeliness of problem positioning after risk occurrence, reduces manual checking cost and ensures fund safety. Another object of the present invention is to provide a specific funds monitoring device based on natural language algorithm. It is yet another object of the present invention to provide a computer readable medium. It is a further object of the invention to provide a computer device.
In order to achieve the above object, the present invention discloses a specific fund monitoring method based on a natural language algorithm, which comprises the following steps:
Acquiring contract/order information and equipment information associated with the contract/order information;
classifying the contract/order information and the equipment information through a pre-constructed classifier to obtain the contract/order type and the purchased equipment type, wherein the classifier is constructed based on a natural language algorithm;
And carrying out compliance matching on the contract/order type and the purchased equipment type to obtain a special fund monitoring result.
Preferably, the classifier comprises a first classifier and a second classifier;
classifying the contract/order information and the equipment information by a pre-constructed classifier to obtain the contract/order type and the purchased equipment type, wherein the method comprises the following steps:
Classifying the contract/order information through a first classifier to generate a contract/order type;
and classifying the equipment information through a second classifier to generate the purchased equipment type.
Preferably, the natural language algorithm comprises a text classification model, the method further comprising:
Acquiring historical contracts/orders;
Generating a historical contract/order text file according to the historical contract/order, wherein the historical contract/order text file comprises a plurality of pieces of historical contract/order text information;
Adding corresponding contract/order type labels to each piece of historical contract/order text information;
Training a text classification model according to the historical contract/order text information and the corresponding contract/order type label, and constructing a first classifier.
Preferably, the natural language algorithm comprises a text classification model, the method further comprising:
Acquiring historical purchased equipment information;
generating a historical purchased equipment text file according to the historical purchased equipment information, wherein the historical purchased equipment text file comprises a plurality of pieces of historical purchased equipment text information;
adding a corresponding purchased device type label to each piece of historical purchased device text information;
training a text classification model according to the historical purchased equipment text information and the corresponding purchased equipment type label, and constructing a second classifier.
Preferably, compliance matching is performed on the syndication/order type and the purchased equipment type to obtain a special fund monitoring result, including:
Acquiring a special fund abnormal type matching table;
Inquiring the type of the abnormal purchased equipment corresponding to the contract/order type according to the special fund abnormal type matching table;
if the abnormal purchased equipment type comprises the purchased equipment type, determining that the special fund monitoring result is not compliant;
and if the abnormal purchased equipment type does not include the purchased equipment type, determining that the special fund monitoring result is compliance.
Preferably, the method further comprises:
if the special fund monitoring result is not compliant, corresponding executing mechanism information is determined according to contract/order information;
and early warning is carried out on the executing mechanism indicated by the executing mechanism information, and the equipment purchasing member information is positioned.
Preferably, the method further comprises:
If the special fund monitoring result is not compliant, generating a special fund early warning message according to the contract/order type and the purchased equipment type;
And sending the special fund early warning message to a supervision party.
The invention also discloses a special fund monitoring device based on the natural language algorithm, which comprises:
the information to be monitored acquisition unit is used for acquiring contract/order information and equipment information associated with the contract/order information;
the classification unit is used for classifying the contract/order information and the equipment information through a pre-constructed classifier, so as to obtain the contract/order type and the purchased equipment type, wherein the classifier is constructed based on a natural language algorithm;
and the compliance monitoring unit is used for carrying out compliance matching on the contract/order type and the purchased equipment type to obtain a special fund monitoring result.
The invention also discloses a computer readable medium having stored thereon a computer program which when executed by a processor implements a method as described above.
The invention also discloses a computer device comprising a memory for storing information comprising program instructions and a processor for controlling the execution of the program instructions, the processor implementing the method as described above when executing the program.
The invention also discloses a computer program product comprising a computer program/instruction which, when executed by a processor, implements a method as described above.
The method comprises the steps of acquiring contract/order information and equipment information associated with the contract/order information; classifying the contract/order information and the equipment information through a pre-constructed classifier to obtain the contract/order type and the purchased equipment type, wherein the classifier is constructed based on a natural language algorithm; and carrying out compliance matching on the contract/order type and the purchased equipment type to obtain a special fund monitoring result, automatically monitoring the scientific and technological special fund by utilizing the collected contract, order and purchase equipment information, accurately identifying the special fund which is not in compliance, and timely carrying out risk positioning, thereby improving the monitoring accuracy and timeliness of problem positioning after risk occurrence, reducing the manual checking cost and ensuring the fund safety.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for dedicated funds monitoring based on natural language algorithm according to an embodiment of the invention;
FIG. 2 is a flow chart of another method for dedicated funds monitoring based on natural language algorithm according to an embodiment of the invention;
FIG. 3 is a schematic structural diagram of a specific funds monitoring device based on a natural language algorithm according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that the method and the device for monitoring the special funds based on the natural language algorithm disclosed by the application can be used in the technical field of artificial intelligence and can also be used in any field except the technical field of artificial intelligence, and the application field of the method and the device for monitoring the special funds based on the natural language algorithm disclosed by the application is not limited.
In order to facilitate understanding of the technical scheme provided by the application, the following description will explain relevant contents of the technical scheme of the application. The technological funds are special funds for supporting technological level promotion and are established for developing activities such as infrastructure construction, research and development services, innovation research and the like related to the information system, and the special funds are reasonably controllable, orderly executed and special money is required. In the actual use process, equipment or matters which do not meet the technological funds requirements may be purchased in a purchase contract or order, and there is a risk of non-special compliance of the special money.
Based on the collected contracts, orders and logs of purchased equipment, the invention utilizes natural language processing technology to automatically analyze the condition that special money is not special, provides a unified checking tool for auditors, and greatly reduces the manual checking cost.
The implementation process of the special fund monitoring method based on the natural language algorithm provided by the embodiment of the invention is described below by taking the special fund monitoring device based on the natural language algorithm as an execution subject. It can be understood that the execution subject of the private funds monitoring method based on the natural language algorithm provided by the embodiment of the invention includes, but is not limited to, a private funds monitoring device based on the natural language algorithm.
Fig. 1 is a flowchart of a specific funds monitoring method based on a natural language algorithm according to an embodiment of the present invention, as shown in fig. 1, the method includes:
step 101, acquiring contract/order information and equipment information associated with the contract/order information.
Step 102, classifying the contract/order information and the equipment information through a pre-constructed classifier, so as to obtain the contract/order type and the purchased equipment type, wherein the classifier is constructed based on a natural language algorithm.
In the embodiment of the invention, the classifier comprises a first classifier and a second classifier.
And 103, compliance matching is carried out on the contract/order type and the purchased equipment type, so that a special fund monitoring result is obtained.
In the technical scheme provided by the embodiment of the invention, the contract/order information and the equipment information associated with the contract/order information are acquired; classifying the contract/order information and the equipment information through a pre-constructed classifier to obtain the contract/order type and the purchased equipment type, wherein the classifier is constructed based on a natural language algorithm; and carrying out compliance matching on the contract/order type and the purchased equipment type to obtain a special fund monitoring result, automatically monitoring the scientific and technological special fund by utilizing the collected contract, order and purchase equipment information, accurately identifying the special fund which is not in compliance, and timely carrying out risk positioning, thereby improving the monitoring accuracy and timeliness of problem positioning after risk occurrence, reducing the manual checking cost and ensuring the fund safety.
Fig. 2 is a flowchart of another specific funds monitoring method based on a natural language algorithm according to an embodiment of the invention, as shown in fig. 2, the method includes:
step 201, acquiring contract/order information and equipment information associated with the contract/order information.
In the embodiment of the invention, the contract/order information comprises contract information or order information, wherein the contract information is related information of project contracts signed by financial institutions and enterprise users, and the order information is related information of project orders signed by the financial institutions and the enterprise users.
In the embodiment of the invention, the equipment information is associated with the contract or the order through the contract number of the contract information or the order number of the order information. The device information is related information of purchased devices.
As an alternative, the contract/order information is as shown in table 1:
TABLE 1
The contract/order information comprises contract/order numbers, contract/order names, contract/order profiles, execution mechanisms and responsible persons. The contract/order number can uniquely identify a contract or order, the name of the contract/order is the subject name of the contract or order, the brief description of the contract/order is the brief description of the contract or order, and the executing mechanism is the mechanism for executing the contract or order and is responsible for the responsible person who takes charge of the contract or order.
As an alternative, the device information is as shown in table 2:
TABLE 2
The equipment information comprises equipment contract/order numbers, resource numbers, model series, attribution manufacturers, affiliated institutions and responsible persons. Wherein the equipment contract/order number is capable of uniquely identifying a contract or order, the equipment contract/order number being associated with the contract/order number in the contract/order information; the resource number is the number of the equipment; the model series is the model of the equipment; the attribution manufacturer is the manufacturer to which the equipment belongs; the mechanism is a mechanism for purchasing the equipment; responsible for the person buying the device.
Step 202, classifying the contract/order information through a first classifier to generate a contract/order type.
Specifically, the contract/order information is input into a first classifier to be classified, and a contract/order type is generated. The contract/order type comprises one of machine room facility purchase, office foundation purchase, self-service tool purchase, external research and development resource purchase and open platform purchase.
In an embodiment of the present invention, the first classifier is pre-constructed based on a natural language algorithm, which includes a text classification model (fastText). The specific construction process of the first classifier comprises the following steps:
step a1, acquiring historical contracts/orders.
In the embodiment of the invention, a history contract or a history order is acquired, and the history contract and the history order are stored in a database.
And a2, generating a historical contract/order text file according to the historical contract/order.
In the embodiment of the invention, the historical contracts/orders comprise various attribute information, the contract/order number, the contract/order name, the contract/order profile, the executing mechanism and the responsible person of each historical contract/order are extracted, and the historical contract/order text file is generated. The history contract/order text file includes a plurality of pieces of history contract/order text information.
And a step a3, adding corresponding contract/order type labels to each piece of historical contract/order text information.
In the embodiment of the invention, the contract/order type label starts with a prefix of __ label __, and the contract/order type label comprises: machine room facility purchase, office foundation purchase, self-service machine purchase, external research and development resource purchase and open platform purchase.
In the embodiment of the invention, each piece of historical contract/order text information corresponds to a contract/order type label. Specifically, each piece of historical contract text information corresponds to one contract type label, and each piece of historical order text information corresponds to one order type label.
And a step a4 of training a text classification model according to the historical contract/order text information and the corresponding contract/order type label to construct a first classifier.
Specifically, the historical contract text information and the corresponding contract type label, and the historical order text information and the corresponding order type label are used as contract/order marking data (contact. Txt) input fastText to perform iterative training until the model meets the preset precision requirement, and a first classifier is generated.
And 203, classifying the equipment information through a second classifier to generate the purchased equipment type.
Specifically, the equipment information is input into a second classifier to be classified, and the purchased equipment type is generated. The purchased equipment type comprises one of office machines, storage equipment, servers, microcomputers, auxiliary peripherals, consumables, air conditioners, software, network communication, banking machines and self-service equipment.
In an embodiment of the invention, the second classifier is pre-constructed based on a natural language algorithm that includes a text classification model (fastText). The specific construction process of the second classifier comprises the following steps:
And b1, acquiring historical purchased equipment information.
In the embodiment of the invention, the information of the historical purchased equipment is acquired and stored in the database.
And b2, generating a historical purchased equipment text file according to the historical purchased equipment information.
In the embodiment of the invention, the historical purchased equipment information comprises various attribute information, equipment contract/order numbers, resource numbers, model series, attribution manufacturers, affiliated institutions and responsible persons of each piece of the historical purchased equipment information are extracted, and a historical purchased equipment text file is generated, wherein the historical purchased equipment text file comprises a plurality of pieces of historical purchased equipment text information.
And b3, adding corresponding purchased equipment type labels to each piece of historical purchased equipment text information.
In the embodiment of the present invention, the purchased device type tag starts with a prefix "__ label __", and the purchased device type tag includes: office machines, storage equipment, servers, microcomputers, auxiliary peripherals, consumables, air conditioners, software, network communication, banking machines and self-service equipment.
In the embodiment of the invention, each piece of historical purchased equipment text information corresponds to one purchased equipment type label.
And b4, training the text classification model according to the historical purchased equipment text information and the corresponding purchased equipment type label, and constructing a second classifier.
Specifically, the historical purchased device text information and the corresponding purchased device type label are used as device marking data (dev. Txt) to be input fastText for iterative training until the model meets the preset precision requirement, and a second classifier is generated.
Step 204, obtaining a special fund abnormal type matching table.
In the embodiment of the invention, the special fund abnormal type matching table is preset, and comprises the corresponding relation between the contract type and the type of the non-compliant purchased equipment. As an alternative, the special fund anomaly type matching table is shown in table 3:
TABLE 3 Table 3
| Contract/order type | Non-compliant purchased device types |
| Machine room facility purchase | Office machine, software, microcomputer, bank machine and self-service equipment |
| Office foundation purchasing | Server, air conditioner, banking machine and self-service equipment |
| Self-service machine purchasing | Office machine, storage device, server, microcomputer, air conditioner and network communication |
| External research and development resource purchasing | All device types |
| Open platform procurement | Office machine, microcomputer, air conditioner, network communication, bank machine and self-service equipment |
Wherein the contract/order types include: machine room facility purchase, office foundation purchase, self-service machine purchase, external research and development resource purchase and open platform purchase. The equipment types purchased corresponding to the purchase of the machine room are set to comprise office machines, software, microcomputers, banking machines and self-service equipment; the type of the non-compliant purchased equipment corresponding to the office foundation purchase comprises a server, an air conditioner, a banking machine and self-service equipment; the self-service machine purchase corresponding non-compliance purchased equipment types comprise office machines, storage equipment, servers, microcomputers, air conditioners and network communication; the type of the non-compliant purchased equipment corresponding to the purchase of the external research and development resources is all equipment types; the type of the purchased equipment corresponding to the open platform purchase is selected from office machines, microcomputers, air conditioners, network communication, banking machines and self-service equipment.
Step 205, according to the special fund abnormal type matching table, inquiring the abnormal purchased equipment type corresponding to the contract/order type.
Specifically, the contract/order type output by the first classifier is matched with the contract/order type in the special fund abnormal type matching table, and the corresponding non-compliant purchased equipment type is obtained.
Step 206, judging whether the abnormal purchased device type includes the purchased device type, if yes, executing step 207; if not, go to step 208.
In the embodiment of the present invention, if the abnormal purchased equipment type includes the purchased equipment type output by the second classifier, it indicates that the purchased equipment does not belong to the equipment type that should be purchased by the associated contract/order, that is: the special funds fail to be dedicated for special money, and step 207 is continued; if the abnormal purchased device type does not include the purchased device type, the purchased device is indicated to belong to the device type which the associated contract/order should purchase, namely: the special funds are dedicated for special money and step 208 is continued.
Step 207, determining that the special funds monitoring result is not compliant, and continuing to execute step 209.
In the embodiment of the present invention, if the special funds cannot be transferred, it indicates that the monitored special funds are not compliant, and the corresponding supervisor is pre-warned according to the preset risk treatment policy, and step 209 is continuously executed.
It should be noted that, the risk treatment policy may be set according to actual requirements, which is not limited in the embodiment of the present invention.
And step 208, determining the special fund monitoring result as compliance, and ending the flow.
In the embodiment of the invention, if the special funds realize special transfer, the monitored special funds are indicated to be compliant in monitoring result, and the process is ended.
Step 209, determining corresponding actuator information according to the contract/order information.
In the embodiment of the invention, corresponding executing mechanism information is queried according to contract/order number through contract/order information, wherein the executing mechanism information comprises an executing mechanism and a responsible person.
Step 210, early warning is carried out on the execution mechanism indicated by the execution mechanism information, and the equipment purchasing member information is positioned.
In the embodiment of the invention, the early warning message is respectively sent to the executing mechanism and the responsible person, the early warning message comprises, but is not limited to, non-compliance contract/order information, equipment information, contract/order type and purchased equipment type, and the information of the buyer responsible for purchasing the equipment is positioned, so that the quick positioning and risk early warning are realized, and the safety of special funds is ensured.
Step 211, generating a special fund early warning message according to the contract/order type and the purchased equipment type.
In an embodiment of the present invention, the special funds warning message includes, but is not limited to, non-compliance contract/order information, equipment information, contract/order type, and purchased equipment type.
As an alternative, the message form of the special funds warning message is one of mail, short message or application message or any combination thereof.
Step 212, sending the special funds early warning message to the supervisor.
In embodiments of the present invention, the supervisors include, but are not limited to, responsible persons and security auditors. And sending the special fund early warning message to the supervision party so as to remind the supervision party to pay attention to and process in time.
The invention is suitable for various special fund application scenes, especially for science and technology purchasing scenes, can cover full data inspection without changing the existing environment, does not occupy extra resources, and has wide application range. And the auditing efficiency is improved. Based on collected contract and equipment data information, centralized processing and analysis are carried out, so that automatic full-quantity monitoring on non-compliance use of purchased funds is realized, and auditing efficiency of special funds is greatly improved.
It is worth to be noted that, in the technical scheme of the application, the acquisition, storage, use, processing and the like of the data all conform to the relevant regulations of laws and regulations. The user information in the embodiment of the application is obtained through legal compliance approaches, and the user information is obtained, stored, used, processed and the like through the approval of the client.
It is worth to say that the information collected in the application is information and data authorized by the user or fully authorized by each party, and the processing of the collection, storage, use, processing, transmission, provision, disclosure, application and the like of the related data all obeys the related laws and regulations and standards of the related country and region, necessary security measures are taken, the public welfare is not violated, and corresponding operation entrance is provided for the user to select the authorization or rejection.
It is worth to say that, the technical scheme provided by the application provides a corresponding operation entrance for the user, so that the user can choose to agree or reject the automatic decision result; if the user selects refusal, the expert decision flow is entered.
In the technical scheme of the special fund monitoring method based on the natural language algorithm, contract/order information and equipment information associated with the contract/order information are acquired; classifying the contract/order information and the equipment information through a pre-constructed classifier to obtain the contract/order type and the purchased equipment type, wherein the classifier is constructed based on a natural language algorithm; and carrying out compliance matching on the contract/order type and the purchased equipment type to obtain a special fund monitoring result, automatically monitoring the scientific and technological special fund by utilizing the collected contract, order and purchase equipment information, accurately identifying the special fund which is not in compliance, and timely carrying out risk positioning, thereby improving the monitoring accuracy and timeliness of problem positioning after risk occurrence, reducing the manual checking cost and ensuring the fund safety.
Fig. 3 is a schematic structural diagram of a special fund monitoring device based on a natural language algorithm according to an embodiment of the present invention, where the device is configured to execute the special fund monitoring method based on the natural language algorithm, as shown in fig. 3, and the device includes: an information acquisition unit 11 to be monitored, a classification unit 12 and a compliance monitoring unit 13.
The information to be monitored acquisition unit 11 is configured to acquire contract/order information and equipment information associated with the contract/order information.
The classifying unit 12 is configured to classify the contract/order information and the equipment information by a classifier constructed in advance, wherein the classifier is constructed based on a natural language algorithm, so as to obtain the contract/order type and the purchased equipment type.
The compliance monitoring unit 13 is configured to perform compliance matching on the contract/order type and the purchased equipment type, so as to obtain a special fund monitoring result.
In the embodiment of the invention, the classifier comprises a first classifier and a second classifier; the classifying unit 12 is specifically configured to classify the contract/order information by using a first classifier, and generate a contract/order type; and classifying the equipment information through a second classifier to generate the purchased equipment type.
In the embodiment of the invention, the natural language algorithm comprises a text classification model; the apparatus further comprises: a first acquisition unit 14, a first file generation unit 15, a first tag adding unit 16, and a first classifier training unit 17.
The first acquisition unit 14 is used for acquiring history contracts/orders.
The first file generating unit 15 is configured to generate a history contract/order text file including a plurality of pieces of history contract/order text information according to the history contract/order.
The first tag adding unit 16 is configured to add a corresponding contract/order type tag to each piece of history contract/order text information.
The first classifier training unit 17 is configured to train the text classification model according to the historical contract/order text information and the corresponding contract/order type label, and construct a first classifier.
In the embodiment of the invention, the natural language algorithm comprises a text classification model; the apparatus further comprises: a second acquisition unit 18, a second file generation unit 19, a second tag adding unit 20 and a second classifier training unit 21.
The second acquisition unit 18 is for acquiring historic purchased device information.
The second file generating unit 19 is configured to generate a history purchased device text file including a plurality of pieces of history purchased device text information, based on the history purchased device information.
The second tag adding unit 20 is configured to add a corresponding purchased device type tag to each piece of historical purchased device text information.
The second classifier training unit 21 is configured to train the text classification model according to the historical purchased device text information and the corresponding purchased device type label, and construct a second classifier.
In the embodiment of the present invention, the compliance monitoring unit 13 is specifically configured to obtain a special fund exception type matching table; inquiring the type of the abnormal purchased equipment corresponding to the contract/order type according to the special fund abnormal type matching table; if the abnormal purchased equipment type comprises the purchased equipment type, determining that the special fund monitoring result is not compliant; and if the abnormal purchased equipment type does not include the purchased equipment type, determining that the special fund monitoring result is compliance.
In the embodiment of the invention, the device further comprises: a determining unit 22 and an early warning unit 23.
The determining unit 22 is configured to determine corresponding actuator information according to the contract/order information if the special funds monitoring result is not compliant.
The early warning unit 23 is used for early warning the execution mechanism indicated by the execution mechanism information and locating the information of the equipment purchasing member.
In the embodiment of the invention, the device further comprises: an early warning message generation unit 24 and a transmission unit 25.
The early warning message generating unit 24 is configured to generate a special fund early warning message according to the contract/order type and the purchased equipment type if the special fund monitoring result is not compliant.
The sending unit 25 is configured to send a special funds warning message to the supervisor.
In the scheme of the embodiment of the invention, the contract/order information and the equipment information associated with the contract/order information are acquired; classifying the contract/order information and the equipment information through a pre-constructed classifier to obtain the contract/order type and the purchased equipment type, wherein the classifier is constructed based on a natural language algorithm; and carrying out compliance matching on the contract/order type and the purchased equipment type to obtain a special fund monitoring result, automatically monitoring the scientific and technological special fund by utilizing the collected contract, order and purchase equipment information, accurately identifying the special fund which is not in compliance, and timely carrying out risk positioning, thereby improving the monitoring accuracy and timeliness of problem positioning after risk occurrence, reducing the manual checking cost and ensuring the fund safety.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. A typical implementation device is a computer device, which may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
The embodiment of the invention provides a computer device, which comprises a memory and a processor, wherein the memory is used for storing information comprising program instructions, the processor is used for controlling the execution of the program instructions, and the program instructions realize the steps of the embodiment of the special fund monitoring method based on the natural language algorithm when being loaded and executed by the processor.
Referring now to FIG. 4, there is illustrated a schematic diagram of a computer device 600 suitable for use in implementing embodiments of the present application.
As shown in fig. 4, the computer apparatus 600 includes a Central Processing Unit (CPU) 601, which can perform various appropriate works and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data required for the operation of the computer device 600 are also stored. The CPU601, ROM602, and RAM603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, mouse, etc.; an output portion 607 including a Cathode Ray Tube (CRT), a liquid crystal feedback device (LCD), and the like, and a speaker, and the like; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The drive 610 is also connected to the I/O interface 605 as needed. Removable media 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on drive 610 as needed, so that a computer program read therefrom is mounted as needed as storage section 608.
In particular, according to embodiments of the present invention, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising program code for performing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 609, and/or installed from the removable medium 611.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in the same piece or pieces of software and/or hardware when implementing the present application.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
The technical scheme of the application obtains, stores, uses, processes and the like the data, which all meet the relevant regulations of national laws and regulations.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (11)
1. A method for dedicated funds monitoring based on natural language algorithm, the method comprising:
Acquiring contract/order information and equipment information associated with the contract/order information;
classifying the contract/order information and the equipment information through a pre-constructed classifier to obtain the contract/order type and the purchased equipment type, wherein the classifier is constructed based on a natural language algorithm;
And carrying out compliance matching on the contract/order type and the purchased equipment type to obtain a special fund monitoring result.
2. The natural language algorithm based private funds monitoring method of claim 1, wherein the classifier comprises a first classifier and a second classifier;
the classifying, by a pre-constructed classifier, the contract/order information and the equipment information to obtain a contract/order type and a purchased equipment type, including:
Classifying the contract/order information through the first classifier to generate the contract/order type;
and classifying the equipment information through the second classifier to generate the purchased equipment type.
3. The natural language algorithm-based private funds monitoring method of claim 2, wherein the natural language algorithm includes a text classification model, the method further comprising:
Acquiring historical contracts/orders;
Generating a historical contract/order text file according to the historical contract/order, wherein the historical contract/order text file comprises a plurality of pieces of historical contract/order text information;
Adding corresponding contract/order type labels to each piece of historical contract/order text information;
Training a text classification model according to the historical contract/order text information and the corresponding contract/order type label, and constructing a first classifier.
4. The natural language algorithm-based private funds monitoring method of claim 2, wherein the natural language algorithm includes a text classification model, the method further comprising:
Acquiring historical purchased equipment information;
Generating a historical purchased equipment text file according to the historical purchased equipment information, wherein the historical purchased equipment text file comprises a plurality of pieces of historical purchased equipment text information;
adding a corresponding purchased device type label to each piece of historical purchased device text information;
Training a text classification model according to the historical purchased equipment text information and the corresponding purchased equipment type label, and constructing a second classifier.
5. The method for dedicated funds monitoring based on natural language algorithm according to claim 1, wherein the compliance matching of the contract/order type and the purchased equipment type, to obtain dedicated funds monitoring results, comprises:
Acquiring a special fund abnormal type matching table;
inquiring the type of the abnormal purchased equipment corresponding to the contract/order type according to the special fund abnormal type matching table;
If the abnormal purchased equipment type comprises the purchased equipment type, determining that the special fund monitoring result is not compliant;
And if the abnormal purchased equipment type does not include the purchased equipment type, determining that the special fund monitoring result is compliance.
6. The natural language algorithm based private funds monitoring method of claim 1, further comprising:
if the special fund monitoring result is not compliant, corresponding executing mechanism information is determined according to the contract/order information;
and early warning is carried out on the executing mechanism indicated by the executing mechanism information, and the information of the equipment purchasing member is positioned.
7. The natural language algorithm based private funds monitoring method of claim 1, further comprising:
If the special fund monitoring result is not compliant, generating a special fund early warning message according to the contract/order type and the purchased equipment type;
And sending the special fund early warning message to a supervision party.
8. A natural language algorithm-based special funds monitoring device, the device comprising:
The information to be monitored acquisition unit is used for acquiring contract/order information and equipment information associated with the contract/order information;
The classifying unit is used for classifying the contract/order information and the equipment information through a pre-constructed classifier to obtain the contract/order type and the purchased equipment type, wherein the classifier is constructed based on a natural language algorithm;
And the compliance monitoring unit is used for carrying out compliance matching on the contract/order type and the purchased equipment type to obtain a special fund monitoring result.
9. A computer readable medium having stored thereon a computer program, which when executed by a processor implements the natural language algorithm based funds monitoring method of any one of claims 1 to 7.
10. A computer device comprising a memory for storing information including program instructions and a processor for controlling execution of the program instructions, wherein the program instructions when loaded and executed by the processor implement the natural language algorithm-based fund monitoring method of any one of claims 1 to 7.
11. A computer program product comprising computer programs/instructions which when executed by a processor implement the natural language algorithm based dedicated funds monitoring method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410207114.7A CN117952721A (en) | 2024-02-26 | 2024-02-26 | Special fund monitoring method and device based on natural language algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410207114.7A CN117952721A (en) | 2024-02-26 | 2024-02-26 | Special fund monitoring method and device based on natural language algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117952721A true CN117952721A (en) | 2024-04-30 |
Family
ID=90805334
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410207114.7A Pending CN117952721A (en) | 2024-02-26 | 2024-02-26 | Special fund monitoring method and device based on natural language algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117952721A (en) |
-
2024
- 2024-02-26 CN CN202410207114.7A patent/CN117952721A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111383101B (en) | Post-credit risk monitoring method, post-credit risk monitoring device, post-credit risk monitoring equipment and computer readable storage medium | |
| CN102663650A (en) | System for analyzing enterprise credit risk and application method thereof | |
| US20230351396A1 (en) | Systems and methods for outlier detection of transactions | |
| CN111145009A (en) | Method and device for evaluating risk after user loan and electronic equipment | |
| US20180314977A1 (en) | Computing device for machine learning based risk analysis | |
| CN110659961A (en) | Method and device for identifying off-line commercial tenant | |
| CN112598249A (en) | Object evaluation method, device and equipment | |
| CN109284978B (en) | System and method for accurately identifying poverty-stricken user | |
| CN111210332A (en) | Method and device for generating post-loan management strategy and electronic equipment | |
| CN117575775A (en) | Service risk detection method, device, equipment and storage medium | |
| CN112950359A (en) | User identification method and device | |
| CN115439264A (en) | Insurance business customization method, device and system | |
| CN116662387A (en) | Service data processing method, device, equipment and storage medium | |
| CN117952721A (en) | Special fund monitoring method and device based on natural language algorithm | |
| CN109377155A (en) | The loan information measures and procedures for the examination and approval and device | |
| KR102416998B1 (en) | Appatus for automatically collecting and classification tax related documents and method thereof | |
| CN114819820A (en) | Intelligent supply chain management method, device, system and medium based on artificial intelligence | |
| CN114493853A (en) | Credit rating evaluation method, credit rating evaluation device, electronic device and storage medium | |
| CN115082179A (en) | Data processing method, device, equipment and storage medium | |
| CN113570450A (en) | Financing risk monitoring method and device based on credit asset batch classification | |
| CN114066478A (en) | Target classification evaluation method and device based on informed production information | |
| CN112766871A (en) | Capital issuing system | |
| CN112085469A (en) | Data approval method, device, equipment and storage medium based on vector machine model | |
| CN111652501B (en) | Financial product evaluation device and method, electronic equipment and storage medium | |
| CN112465509A (en) | Signing contract early warning method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |