CN117669567B - Document management method - Google Patents
Document management method Download PDFInfo
- Publication number
- CN117669567B CN117669567B CN202410134581.1A CN202410134581A CN117669567B CN 117669567 B CN117669567 B CN 117669567B CN 202410134581 A CN202410134581 A CN 202410134581A CN 117669567 B CN117669567 B CN 117669567B
- Authority
- CN
- China
- Prior art keywords
- latest
- approval
- bill
- abstract
- layer
- 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.)
- Active
Links
- 238000007726 management method Methods 0.000 title claims abstract description 18
- 238000000034 method Methods 0.000 claims abstract description 11
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 239000013598 vector Substances 0.000 claims description 44
- 238000000605 extraction Methods 0.000 claims description 19
- 210000002569 neuron Anatomy 0.000 claims description 15
- 238000005457 optimization Methods 0.000 claims 1
- 238000013523 data management Methods 0.000 abstract description 2
- 239000002699 waste material Substances 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- 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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Document Processing Apparatus (AREA)
Abstract
The invention discloses a bill management method, which belongs to the technical field of data management and comprises the following steps: s1, acquiring the content of a latest to-be-examined bill, and generating an examination and approval abstract for the latest to-be-examined bill; s2, preprocessing an approval abstract of the latest document to be approved to generate the latest approval abstract; s3, determining the optimal position of the latest to-be-examined batch data in the original examination and approval sequence; s4, generating a latest approval sequence; s5, transmitting the latest approval abstract of the latest to-be-approved bill to the user terminal, and transmitting a plurality of original to-be-approved bill and latest to-be-approved bill data to the user terminal according to the latest approval sequence. The method and the system can accurately determine the optimal position of the latest to-be-examined batch data in the original examination and approval sequence, ensure that the latest to-be-examined batch data is timely sent to the user terminal, facilitate the timely examination and approval of the user, avoid the waste of resources in the process and effectively improve the office capability of enterprises.
Description
Technical Field
The invention belongs to the technical field of data management, and particularly relates to a bill management method.
Background
In enterprise management, a plurality of approval documents are commonly existed, the approval documents comprise a plurality of business processes, and the approval documents of the enterprise have the characteristics of various types, large quantity, frequent change and the like. At present, the approval document management of enterprises still adopts a manual management mode, namely, the approval sequence of a large number of approval documents is mainly managed manually by a manager, the document management is disordered, the abstract which is convenient for the manager to quickly acquire the document information can not be generated for the approval document, and the management efficiency is low.
Disclosure of Invention
The invention provides a bill management method for solving the problems.
The technical scheme of the invention is as follows: the bill management method comprises the following steps:
S1, acquiring the content of a latest to-be-examined bill, and generating an examination and approval abstract for the latest to-be-examined bill;
s2, preprocessing an approval abstract of the latest document to be approved to generate the latest approval abstract;
s3, acquiring original approval orders of a plurality of original to-be-approved documents, and determining the optimal position of the latest to-be-approved documents in the original approval orders;
s4, inserting the latest to-be-examined batch data into the original examination and approval sequence according to the optimal position to generate the latest examination and approval sequence;
S5, transmitting the latest approval abstract of the latest to-be-approved bill to the user terminal, and transmitting a plurality of original to-be-approved bill and latest to-be-approved bill data to the user terminal according to the latest approval sequence.
Further, in S1, the specific method for generating the approval digest for the latest pending lot data includes: and constructing a abstract extraction model, inputting the content of the latest document to be examined into the abstract extraction model, and generating an examination and approval abstract.
Further, the abstract extraction model comprises a plurality of convolution layers, a cache layer, a context representation layer, an arithmetic unit and a context splicing layer;
The input ends of the convolution layers are all used as the input ends of the abstract extraction model; the output ends of the convolution layers are connected with the input ends of the buffer layers; the first output end of the cache layer is connected with the input end of the context representation layer; the second output end of the buffer layer is connected with the first input end of the arithmetic unit; the output end of the context representation layer is connected with the second input end of the arithmetic unit; the output end of the arithmetic unit is connected with the input end of the context splicing layer; the output end of the context stitching layer is used as the output end of the abstract extraction model.
The beneficial effects of the above-mentioned further scheme are: in the invention, each convolution layer is used for extracting word vectors of each field in the content of the latest approval document. The caching layer is used for caching word vectors of all the fields, and the context representation layer is convenient for extracting the word vectors of all the fields from the caching layer. The context representation layer performs vector transformation on word vectors of all fields stored in the cache layer to obtain deep word vector features, and the expression capability of the abstract extraction model is improved. The arithmetic unit utilizes a plurality of neurons to fuse each output vector in the cache layer with the output of the context representation layer, so as to obtain a plurality of outputs. And the context splicing layer splices the outputs of the plurality of neurons in the arithmetic unit to obtain an approval abstract.
Further, the expression of the context representation layer is: ; wherein B represents the output of the context representation layer, H i represents the ith output vector of the cache layer, H i-1 represents the ith-1 th output vector of the cache layer, H i+1 represents the (i+1) th output vector of the cache layer, I represents the number of the output vectors of the cache layer, L p (DEG) represents the Min-type distance operation function, max (DEG) represents the maximum value operation function, and/> Representing a vector addition operation.
The number of output vectors of the buffer layer is the same as the number of convolution kernels in the convolution layer, and word vectors of the field extracted by each convolution kernel are independently buffered in the buffer layer, so that the ith output vector of the buffer layer is actually the word vector of the ith field input to the buffer layer by the convolution kernel.
Further, the expression of the operator is: ; where Y j represents the output corresponding to the jth neuron in the operator, H i represents the ith output vector of the buffer layer, I represents the number of output vectors of the buffer layer, w j represents the weight of the jth neuron in the operator, B j represents the bias of the jth neuron in the operator, and B represents the output of the context representation layer.
Further, in S2, the specific method for preprocessing the approval abstract of the latest document to be approved includes: and eliminating the stop words of the approval abstract to generate the latest approval abstract.
Further, S3 comprises the following sub-steps:
S31, constructing an approval sequence optimal condition;
S32, determining the optimal position of the latest to-be-examined batch data in the original approval sequence through the approval sequence optimal condition.
Further, in S31, the expression of the approval order optimum condition Z (u 0,u,u1) is: M=1, 2, …, M; in the formula, u 0 represents a preamble original to-be-inspected bill at the optimal position of the latest to-be-inspected bill, u 1 represents a follow-up original to-be-inspected bill at the optimal position of the latest to-be-inspected bill, u represents the latest to-be-inspected bill, z 1 (-) represents an approval waiting time difference after the latest to-be-inspected bill is inserted in the original approval sequence, u m-1 represents the original to-be-inspected bill at the M-1 th position in the original approval sequence, u m represents the original to-be-inspected bill at the M-th position in the original approval sequence, min (-) represents a minimum value operation function, t represents the approval time of the latest to-be-inspected bill, and M represents the number of the original to-be-inspected bill.
The beneficial effects of the invention are as follows: the invention discloses a bill management method, which is characterized in that an abstract extraction model is constructed to generate an approval abstract for the latest to-be-approved bill, so that a user can conveniently read the approval abstract, quickly know the main content of the latest to-be-approved bill, and accelerate the approval process; meanwhile, the invention can accurately determine the optimal position of the latest to-be-examined batch data in the original examination and approval sequence, ensures that the latest to-be-examined batch data is timely sent to the user terminal, is convenient for the user to examine and approve in time, avoids resource waste in the process, and effectively improves the office capability of enterprises.
Drawings
FIG. 1 is a flow chart diagram of a document management method;
fig. 2 is a schematic diagram of the structure of the abstract extraction model.
Detailed Description
Embodiments of the present invention are further described below with reference to the accompanying drawings.
As shown in fig. 1, the present invention provides a document management method, which includes the following steps:
S1, acquiring the content of a latest to-be-examined bill, and generating an examination and approval abstract for the latest to-be-examined bill;
s2, preprocessing an approval abstract of the latest document to be approved to generate the latest approval abstract;
s3, acquiring original approval orders of a plurality of original to-be-approved documents, and determining the optimal position of the latest to-be-approved documents in the original approval orders;
s4, inserting the latest to-be-examined batch data into the original examination and approval sequence according to the optimal position to generate the latest examination and approval sequence;
S5, transmitting the latest approval abstract of the latest to-be-approved bill to the user terminal, and transmitting a plurality of original to-be-approved bill and latest to-be-approved bill data to the user terminal according to the latest approval sequence.
In the embodiment of the invention, in S1, a specific method for generating an approval abstract for the latest pending batch data comprises the following steps: and constructing a abstract extraction model, inputting the content of the latest document to be examined into the abstract extraction model, and generating an examination and approval abstract.
In the embodiment of the invention, as shown in fig. 2, the abstract extraction model comprises a plurality of convolution layers, a cache layer, a context representation layer, an operator and a context splicing layer;
The input ends of the convolution layers are all used as the input ends of the abstract extraction model; the output ends of the convolution layers are connected with the input ends of the buffer layers; the first output end of the cache layer is connected with the input end of the context representation layer; the second output end of the buffer layer is connected with the first input end of the arithmetic unit; the output end of the context representation layer is connected with the second input end of the arithmetic unit; the output end of the arithmetic unit is connected with the input end of the context splicing layer; the output end of the context stitching layer is used as the output end of the abstract extraction model.
In the invention, each convolution layer is used for extracting word vectors of each field in the content of the latest approval document. The caching layer is used for caching word vectors of all the fields, and the context representation layer is convenient for extracting the word vectors of all the fields from the caching layer. The context representation layer performs vector transformation on word vectors of all fields stored in the cache layer to obtain deep word vector features, and the expression capability of the abstract extraction model is improved. The arithmetic unit utilizes a plurality of neurons to fuse each output vector in the cache layer with the output of the context representation layer, so as to obtain a plurality of outputs. And the context splicing layer splices the outputs of the plurality of neurons in the arithmetic unit to obtain an approval abstract.
In the embodiment of the present invention, the expression of the context expression layer is: ; wherein B represents the output of the context representation layer, H i represents the ith output vector of the cache layer, H i-1 represents the ith-1 th output vector of the cache layer, H i+1 represents the (i+1) th output vector of the cache layer, I represents the number of the output vectors of the cache layer, L p (DEG) represents the Min-type distance operation function, max (DEG) represents the maximum value operation function, and/> Representing a vector addition operation.
The number of output vectors of the buffer layer is the same as the number of convolution kernels in the convolution layer, and word vectors of the field extracted by each convolution kernel are independently buffered in the buffer layer, so that the ith output vector of the buffer layer is actually the word vector of the ith field input to the buffer layer by the convolution kernel.
In the embodiment of the present invention, the expression of the operator is: ; where Y j represents the output corresponding to the jth neuron in the operator, H i represents the ith output vector of the buffer layer, I represents the number of output vectors of the buffer layer, w j represents the weight of the jth neuron in the operator, B j represents the bias of the jth neuron in the operator, and B represents the output of the context representation layer.
In the embodiment of the invention, in S2, the specific method for preprocessing the approval abstract of the latest document to be approved is as follows: and eliminating the stop words of the approval abstract to generate the latest approval abstract.
In an embodiment of the present invention, S3 comprises the following sub-steps:
S31, constructing an approval sequence optimal condition;
S32, determining the optimal position of the latest to-be-examined batch data in the original approval sequence through the approval sequence optimal condition.
In the embodiment of the present invention, in S31, the expression of the approval order optimal condition Z (u 0,u,u1) is: M=1, 2, …, M; in the formula, u 0 represents a preamble original to-be-inspected bill at the optimal position of the latest to-be-inspected bill, u 1 represents a follow-up original to-be-inspected bill at the optimal position of the latest to-be-inspected bill, u represents the latest to-be-inspected bill, z 1 (-) represents an approval waiting time difference after the latest to-be-inspected bill is inserted in the original approval sequence, u m-1 represents the original to-be-inspected bill at the M-1 th position in the original approval sequence, u m represents the original to-be-inspected bill at the M-th position in the original approval sequence, min (-) represents a minimum value operation function, t represents the approval time of the latest to-be-inspected bill, and M represents the number of the original to-be-inspected bill.
Those of ordinary skill in the art will recognize that the embodiments described herein are for the purpose of aiding the reader in understanding the principles of the present invention and should be understood that the scope of the invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific modifications and combinations from the teachings of the present disclosure without departing from the spirit thereof, and such modifications and combinations remain within the scope of the present disclosure.
Claims (4)
1. A document management method, comprising the steps of:
S1, acquiring the content of a latest to-be-examined bill, and generating an examination and approval abstract for the latest to-be-examined bill;
s2, preprocessing an approval abstract of the latest document to be approved to generate the latest approval abstract;
s3, acquiring original approval orders of a plurality of original to-be-approved documents, and determining the optimal position of the latest to-be-approved documents in the original approval orders;
s4, inserting the latest to-be-examined batch data into the original examination and approval sequence according to the optimal position to generate the latest examination and approval sequence;
s5, transmitting the latest approval abstract of the latest to-be-approved bill to the user terminal, and transmitting a plurality of original to-be-approved bills and latest to-be-approved bill data to the user terminal according to the latest approval sequence;
In the step S1, a specific method for generating an approval abstract for the latest pending batch data is as follows: constructing a abstract extraction model, inputting the content of the latest document to be examined into the abstract extraction model, and generating an examination and approval abstract;
The abstract extraction model comprises a plurality of convolution layers, a cache layer, a context representation layer, an arithmetic unit and a context splicing layer;
The input ends of a plurality of convolution layers are all used as the input ends of the abstract extraction model; the output ends of the plurality of convolution layers are connected with the input end of the buffer layer; the first output end of the cache layer is connected with the input end of the context representation layer; the second output end of the buffer layer is connected with the first input end of the arithmetic unit; the output end of the context representation layer is connected with the second input end of the arithmetic unit; the output end of the arithmetic unit is connected with the input end of the context splicing layer; the output end of the context splicing layer is used as the output end of the abstract extraction model;
The expression of the context representation layer is: ; wherein B represents the output of the context representation layer, H i represents the ith output vector of the cache layer, H i-1 represents the ith-1 th output vector of the cache layer, H i+1 represents the (i+1) th output vector of the cache layer, I represents the number of the output vectors of the cache layer, L p (DEG) represents the Min-type distance operation function, max (DEG) represents the maximum value operation function, and/> Representing a vector addition operation;
The expression of the arithmetic unit is as follows: ; wherein Y j represents the output corresponding to the jth neuron in the operator, H i represents the ith output vector of the buffer layer, I represents the number of output vectors of the buffer layer, w j represents the weight of the jth neuron in the operator, B j represents the bias of the jth neuron in the operator, and B represents the output of the context representation layer;
The arithmetic unit utilizes a plurality of neurons to fuse each output vector in the cache layer with the output of the context representation layer to obtain a plurality of outputs; and the context splicing layer splices the outputs of the plurality of neurons in the arithmetic unit to obtain an approval abstract.
2. The document management method according to claim 1, wherein in S2, the specific method for preprocessing the approval digest of the latest document to be approved is as follows: and eliminating the stop words of the approval abstract to generate the latest approval abstract.
3. The document management method according to claim 1, wherein S3 comprises the sub-steps of:
S31, constructing an approval sequence optimal condition;
S32, determining the optimal position of the latest to-be-examined batch data in the original approval sequence through the approval sequence optimal condition.
4. A document management method according to claim 3, wherein in S31, the expression of the approval order optimization condition Z (u 0,u,u1) is: M=1, 2, …, M; in the formula, u 0 represents a preamble original to-be-inspected bill at the optimal position of the latest to-be-inspected bill, u 1 represents a follow-up original to-be-inspected bill at the optimal position of the latest to-be-inspected bill, u represents the latest to-be-inspected bill, z 1 (-) represents an approval waiting time difference after the latest to-be-inspected bill is inserted in the original approval sequence, u m-1 represents the original to-be-inspected bill at the M-1 th position in the original approval sequence, u m represents the original to-be-inspected bill at the M-th position in the original approval sequence, min (-) represents a minimum value operation function, t represents the approval time of the latest to-be-inspected bill, and M represents the number of the original to-be-inspected bill. /(I)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410134581.1A CN117669567B (en) | 2024-01-31 | 2024-01-31 | Document management method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410134581.1A CN117669567B (en) | 2024-01-31 | 2024-01-31 | Document management method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117669567A CN117669567A (en) | 2024-03-08 |
| CN117669567B true CN117669567B (en) | 2024-04-23 |
Family
ID=90073489
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410134581.1A Active CN117669567B (en) | 2024-01-31 | 2024-01-31 | Document management method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117669567B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20200124076A (en) * | 2019-04-23 | 2020-11-02 | 에스케이플래닛 주식회사 | Method for providing cloud streaming service based on minimum drive mode and apparatus therefor |
| CN112288582A (en) * | 2020-10-27 | 2021-01-29 | 北京鼎立保险经纪有限责任公司 | Information processing method and device for improving policy approval efficiency |
| CN113887869A (en) * | 2021-09-01 | 2022-01-04 | 北京奇艺世纪科技有限公司 | Multimedia data quality auditing and scheduling method and device and electronic equipment |
| CN114187160A (en) * | 2020-09-14 | 2022-03-15 | 三星电子株式会社 | Graphics processor and data processing method |
| WO2022105135A1 (en) * | 2020-11-23 | 2022-05-27 | 平安普惠企业管理有限公司 | Information verification method and apparatus, and electronic device and storage medium |
| CN115237998A (en) * | 2021-04-23 | 2022-10-25 | 北京小米移动软件有限公司 | Information auditing processing method and device |
| CN116109277A (en) * | 2023-02-22 | 2023-05-12 | 上海乾臻信息科技有限公司 | Contract approval method, device, equipment and storage medium |
| CN116881258A (en) * | 2023-07-21 | 2023-10-13 | 浪潮通用软件有限公司 | Business data storage method, equipment and medium based on ERP system |
| CN116976836A (en) * | 2023-09-22 | 2023-10-31 | 中节能大数据有限公司 | Intelligent management analysis method and system based on visual interface |
| CN117235250A (en) * | 2023-09-19 | 2023-12-15 | 华南师范大学 | Dialogue abstract generation method, device and equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230081641A1 (en) * | 2021-09-10 | 2023-03-16 | Nvidia Corporation | Single-image inverse rendering |
-
2024
- 2024-01-31 CN CN202410134581.1A patent/CN117669567B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20200124076A (en) * | 2019-04-23 | 2020-11-02 | 에스케이플래닛 주식회사 | Method for providing cloud streaming service based on minimum drive mode and apparatus therefor |
| CN114187160A (en) * | 2020-09-14 | 2022-03-15 | 三星电子株式会社 | Graphics processor and data processing method |
| CN112288582A (en) * | 2020-10-27 | 2021-01-29 | 北京鼎立保险经纪有限责任公司 | Information processing method and device for improving policy approval efficiency |
| WO2022105135A1 (en) * | 2020-11-23 | 2022-05-27 | 平安普惠企业管理有限公司 | Information verification method and apparatus, and electronic device and storage medium |
| CN115237998A (en) * | 2021-04-23 | 2022-10-25 | 北京小米移动软件有限公司 | Information auditing processing method and device |
| CN113887869A (en) * | 2021-09-01 | 2022-01-04 | 北京奇艺世纪科技有限公司 | Multimedia data quality auditing and scheduling method and device and electronic equipment |
| CN116109277A (en) * | 2023-02-22 | 2023-05-12 | 上海乾臻信息科技有限公司 | Contract approval method, device, equipment and storage medium |
| CN116881258A (en) * | 2023-07-21 | 2023-10-13 | 浪潮通用软件有限公司 | Business data storage method, equipment and medium based on ERP system |
| CN117235250A (en) * | 2023-09-19 | 2023-12-15 | 华南师范大学 | Dialogue abstract generation method, device and equipment |
| CN116976836A (en) * | 2023-09-22 | 2023-10-31 | 中节能大数据有限公司 | Intelligent management analysis method and system based on visual interface |
Non-Patent Citations (2)
| Title |
|---|
| distant context aware text generation from abstract meaning representation;sen yang et al.;《applied intelligence》;20200526;第1672-1685页 * |
| 基于J2EE的供应商审批系统的设计与实现;赵建涛;胡勋;;计算机与现代化;20090915(第09期);第143-145页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117669567A (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210103965A1 (en) | Account manager virtual assistant using machine learning techniques | |
| CN106649890B (en) | Data storage method and device | |
| CN110580308B (en) | Information auditing method and device, electronic equipment and storage medium | |
| CN109035028B (en) | Intelligent consultation strategy generation method and device, electronic equipment and storage medium | |
| CN111382279B (en) | Examination method and device | |
| CN112463968B (en) | Text classification method and device and electronic equipment | |
| CN112668320A (en) | Model training method and device based on word embedding, electronic equipment and storage medium | |
| CN109740642A (en) | Invoice category recognition methods, device, electronic equipment and readable storage medium storing program for executing | |
| CN111651552A (en) | Structured information determination method and device and electronic equipment | |
| CN117407726A (en) | Intelligent service data matching method, system and storage medium | |
| CN111582314A (en) | Target user determination method and device and electronic equipment | |
| CN111144409A (en) | Order following, accepting and examining processing method and system | |
| CN116071150A (en) | Data processing method, bank product popularization, wind control system, server and medium | |
| CN114004217B (en) | Message signature element extraction method and system | |
| CN117669567B (en) | Document management method | |
| CN114298845A (en) | Method and device for processing claim settlement bills | |
| CN117422428B (en) | Automatic examination and approval method and system for robot based on artificial intelligence | |
| CN113837307A (en) | Data similarity calculation method and device, readable medium and electronic equipment | |
| CN114385921B (en) | Bidding recommendation method, system, equipment and storage medium | |
| CN117251777A (en) | Data processing method, device, computer equipment and storage medium | |
| CN113743906A (en) | Method and device for determining service processing strategy | |
| CN116228384A (en) | Data processing method, device, electronic equipment and computer readable medium | |
| CN115841365A (en) | Model selection and quotation method, system, equipment and medium based on natural language processing | |
| CN113674081A (en) | Graph database-based wind control management system and method for small and medium-sized enterprises | |
| CN112380321A (en) | Primary and secondary database distribution method based on bill knowledge graph and related equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |