CN110705968A - Artificial intelligence-based approval flow solution method and device and computer equipment - Google Patents
Artificial intelligence-based approval flow solution method and device and computer equipment Download PDFInfo
- Publication number
- CN110705968A CN110705968A CN201910965548.2A CN201910965548A CN110705968A CN 110705968 A CN110705968 A CN 110705968A CN 201910965548 A CN201910965548 A CN 201910965548A CN 110705968 A CN110705968 A CN 110705968A
- Authority
- CN
- China
- Prior art keywords
- information
- training
- node
- module
- optimal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Abstract
The general OA system can only be solved by manually designating the next node approver by the personnel of the previous node or all the approvers on the same post to be handled. This also imposes a right obligation and makes the responsibility of the examination unclear. The invention aims to provide a method and a device for solving a business approval flow based on artificial intelligence and computer equipment.
Description
[ technical field ] A method for producing a semiconductor device
The application relates to the technical field of computers, in particular to a business approval method, a business approval device and computer equipment.
[ background of the invention ]
The approval node setting of the main OA system or the approval flow system in the market depends on the department organization structure, the post position level and the like. The design is suitable for most companies, but some companies with flexible architecture and unfixed reporting relation have limitations. For example, when the functional staff of the group headquarters needs to process the affairs for each branch shop, the approval flow needs to be entered to fill in the approval opinions and supplement the flow information, but the functional staff does not belong to the service line and cannot find the corresponding staff according to the organization architecture; and many functional personnel on the same post can not be specified according to the post. The general OA system can be solved only by manually designating the approver of the next node by the personnel of the previous node or by the way that all the approvers on the same post are to be handled. This also imposes a right obligation and makes the responsibility of the examination unclear.
[ summary of the invention ]
Aiming at the defects in the prior art, the invention aims to provide a method for solving the business approval flow based on artificial intelligence.
In order to achieve the above object, according to a first aspect of the present invention, there is provided a method for resolving a service approval flow based on artificial intelligence, comprising the steps of:
collecting flow information, task information, meeting information, in-station information, reading knowledge information, geographical position, attendance information and network information, creating a business examination and approval information database, and storing the information data in the database. Carrying out distributed training by utilizing the information in the database, wherein the distributed training is divided into two parts, and the training dimensionality of the first distributed training is set as: flow, task, meeting, station information and reading content; the dimensions of the second distributed training are set as: flow, task, meeting, geographic position, attendance information, network information; the first distribution training adopts 100 groups of random algorithm for training, the second distribution training adopts 100 groups of random distribution weights, and genetic optimization is carried out by using a genetic algorithm to obtain a training optimal model. And obtaining the approver of the next node through the optimal model.
Furthermore, due to the existence of two groups of optimal genetic algorithms, two different approvers may exist in the node, and when the approvers are different, the two approvers are arranged in parallel in the node, namely, any person passes the approval and then passes the node.
Further, the information stored in the database is historical data in almost six months, and two distributed trainings respectively promote an optimal algorithm group.
Further, genetic optimization is carried out for 50 generations by a genetic algorithm to obtain a final optimized calculation model.
Furthermore, a round of training is performed every day, the optimal algorithm is updated to the foreground, and the next day is calculated by using the set of algorithms.
Further, the solution method also comprises a feedback step, namely confirming whether an approver of the node promoted by the optimal model and related information are correct or not in the office system, if so, feeding back to the calculation model step to continue calculating the approver of the next node; and if not, manually selecting the next service processing room and the corresponding transactor in the office system, and performing the next service processing by the manually selected next service processing room and the corresponding transactor.
According to a second aspect of the present invention, there is provided an artificial intelligence based business approval apparatus, comprising:
and the acquisition module is used for collecting flow information, task information, meeting information, in-station information, reading knowledge information, user geographic position, attendance information and network information.
And the storage module is used for storing the information data and respectively storing the data into the flow module, the task module, the conference module, the station information module, the reading knowledge module, the user geographic position module, the user network information module and the user attendance information module.
The first distributed training module extracts 100 groups of data of processes, tasks, meetings, station letters and reading contents from the storage module, trains by adopting 100 groups of random algorithms, finally gives up an optimal calculation model, and calculates an approver of the next node;
and the second distribution training module extracts 100 groups of data of processes, tasks, meetings, geographic positions, attendance information and network information from the storage module, randomly allocates weights, performs genetic optimization by using a genetic algorithm to obtain an optimal training model, and calculates an approver of the next node.
And the execution module has two groups of optimal genetic algorithms, so that two different approvers may exist in the node, and when the approvers are different, the two approvers are set to be connected in parallel in the node, namely, any one approves the node and then passes the node.
The system further comprises a feedback module, which is used for receiving the approver information sent by the execution module, informing the staff whether the approver of the node recommended by the optimal model and the related information are correct or not in the office system, and if so, feeding back to the calculation model step to continue calculating the approver of the next node; and if not, manually selecting the next service processing room and the corresponding transactor in the office system, and performing the next service processing by the manually selected next service processing room and the corresponding transactor.
Further, the information in the storage module is historical data in almost six months, and two distributed trainings respectively promote an optimal algorithm group.
Further, the storage device comprises an updating module, and the updating module is used for regularly updating the personnel information database and the examination and approval opinion database.
Further, the genetic algorithm adopted by the training module is used for carrying out 50 generations of genetic optimization to obtain a final optimized calculation model.
Furthermore, the two distributed training modules perform one round of training every day, the optimal algorithm is updated to the foreground, and the next day is calculated by using the set of algorithms.
According to a third aspect of the present invention, there is provided a computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor when executing the computer program implements the steps of:
collecting flow information, task information, conference information, in-station information, reading knowledge information, geographic positions, attendance information and network information;
creating a service approval information database and storing the information data in the database;
carrying out distributed training by utilizing the information in the database, wherein the distributed training is divided into two parts, and the training dimensionality of the first distributed training is set as: flow, task, meeting, station information and reading content; the dimensions of the second distributed training are set as: flow, task, meeting, geographic position, attendance information, network information; the first distribution training adopts 100 groups of random algorithm for training, the second distribution training adopts 100 groups of random distribution weights, and genetic optimization is carried out by using a genetic algorithm to obtain a training optimal model. And obtaining the approver of the next node through the optimal model.
Furthermore, due to the existence of two groups of optimal genetic algorithms, two different approvers may exist in the node, and when the approvers are different, the two approvers are arranged in parallel in the node, namely, any person passes the approval and then passes the node.
Further, the information stored in the database is historical data in almost six months, and two distributed trainings respectively promote an optimal algorithm group.
Further, genetic optimization is carried out for 50 generations by a genetic algorithm to obtain a final optimized calculation model.
Furthermore, a round of training is performed every day, the optimal algorithm is updated to the foreground, and the next day is calculated by using the set of algorithms.
Further, a feedback step is included, namely whether the approver of the node promoted by the optimal model and the related information are correct or not is confirmed in the office system, and if yes, the next node approver is calculated continuously in the step of calculating the model; and if not, manually selecting the next service processing room and the corresponding transactor in the office system, and performing the next service processing by the manually selected next service processing room and the corresponding transactor.
[ description of the drawings ]
FIG. 1 is a flowchart illustrating a business approval method according to an embodiment
FIG. 2 is a block diagram of a business approval apparatus according to an embodiment
[ detailed description ] embodiments
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, an embodiment of the present invention provides a method for solving a business approval flow based on artificial intelligence, including the following steps:
s1, collecting flow information, task information, meeting information, in-station information, reading knowledge information, geographical position, attendance information and network information;
s2, creating a service approval information database and storing the information data in the database;
and S3, performing distributed training by using the information in the database, wherein the distributed training is divided into two parts, and the training dimension of the first distributed training is set as: flow, task, meeting, station information and reading content;
s4, setting the dimensionality of the second distributed training as follows: flow, task, meeting, geographic position, attendance information, network information; the first distribution training adopts 100 groups of random algorithm for training, the second distribution training adopts 100 groups of random distribution weights, and genetic optimization is carried out by using a genetic algorithm;
and S5, respectively carrying out two distributed trainings to promote an optimal algorithm group so as to obtain an approver of the next node.
Due to the existence of two groups of optimal genetic algorithms, two different approvers may exist in the node, and when the approvers are different, the two approvers are arranged in parallel in the node, namely, any person passes the approval and then passes the node.
Generally, transaction personnel performing business transaction may have abnormal actions, such as leaving office or turning department, and if the personnel information database stores all office information and the information of the transaction personnel in each office is not updated, the office and the transaction personnel recommended by the office system for the next business transaction may be inaccurate. Therefore, the information stored in the database is historical data in about six months, and the data is updated at any time.
In addition, in order to ensure that the node approver is expected by office staff, the solution further comprises the following steps:
s6: a feedback step, namely confirming whether the approver of the node promoted by the optimal model and the related information are correct or not in the office system, if so, feeding back to the calculation model step to continue calculating the approver of the next node; and if not, manually selecting the next service processing room and the corresponding transactor in the office system, and performing the next service processing by the manually selected next service processing room and the corresponding transactor.
In addition, in order to ensure that the algorithm obtained by the genetic algorithm is the optimal solution, the genetic algorithm is subjected to 50 generations of genetic optimization, historical data are trained within 6 months of each credit acquisition, and each optimal algorithm is promoted by one group. And performing one round of training every day, updating the optimal algorithm to the foreground, and calculating by using the set of algorithms the next day.
It should be noted that in practical use, the examination and approval opinions may be in various forms, and may only include one of the offices or the transactants for the next business transaction, so that the key information returned to the office system by the optimization result of the training step may only be the office or only the transactants. The office system searches out corresponding offices and transactants in the personnel information database according to the obtained key information, so that the corresponding offices and transactants can be obtained and serve as the offices and the transactants for the next recommended service transaction, the recommended information is more accurate and complete, the follow-up transactants can conveniently confirm the information, and the service transaction efficiency is higher.
Referring to fig. 2, an embodiment of the present invention provides a service approval apparatus based on artificial intelligence, including:
an acquisition module 101, a storage module 102, a first distribution training module 103, a second distribution training module 104, an execution module 105, and a feedback module 106;
the collection module 101 is configured to collect process information, task information, meeting information, in-station information, viewing knowledge information, user geographic position, attendance information, and network information.
The storage module 102 is used for storing the information data and storing the data into the flow module, the task module, the conference module, the in-station information module, the viewing knowledge module, the user geographic position module, the user network information module and the user attendance information module respectively.
The first distributed training module 103 extracts 100 groups of data of processes, tasks, meetings, station letters and reading contents from the storage module, trains by adopting 100 groups of random algorithms, finally gives up an optimal calculation model, and calculates an approver of the next node;
and the second distribution training module 104 is used for extracting 100 groups of data of processes, tasks, meetings, geographic positions, attendance information and network information from the storage module, randomly distributing weights, performing genetic optimization by using a genetic algorithm to obtain an optimal training model, and calculating an approver of the next node.
The execution module 105, because there are two sets of optimal genetic algorithms, may have two different approvers for the node, and when the approvers are different, the two approvers are set in parallel in the node, that is, any one approves the node and then passes the node.
Further, the system further comprises a feedback module 106, configured to receive approver information sent by the execution module, and notify a worker to confirm whether the approver of the node recommended by the optimal model and related information are correct in the office system, and if yes, feed back to the step of calculating the model to continue calculating the approver of the next node; and if not, manually selecting the next service processing room and the corresponding transactor in the office system, and performing the next service processing by the manually selected next service processing room and the corresponding transactor.
The embodiment of the invention provides a computer device, which is used for service approval and comprises the following components:
comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the following steps when executing the computer program:
collecting flow information, task information, conference information, in-station information, reading knowledge information, geographic positions, attendance information and network information;
creating a service approval information database and storing the information data in the database;
carrying out distributed training by utilizing the information in the database, wherein the distributed training is divided into two parts, and the training dimensionality of the first distributed training is set as: flow, task, meeting, station information and reading content; the dimensions of the second distributed training are set as: flow, task, meeting, geographic position, attendance information, network information; the first distribution training adopts 100 groups of random algorithm for training, the second distribution training adopts 100 groups of random distribution weights, and genetic optimization is carried out by using a genetic algorithm to obtain a training optimal model. And obtaining the approver of the next node through the optimal model.
Furthermore, due to the existence of two groups of optimal genetic algorithms, two different approvers may exist in the node, and when the approvers are different, the two approvers are arranged in parallel in the node, namely, any person passes the approval and then passes the node.
Further, the information stored in the database is historical data in almost six months, and two distributed trainings respectively promote an optimal algorithm group.
Further, genetic optimization is carried out for 50 generations by a genetic algorithm to obtain a final optimized calculation model.
Furthermore, a round of training is performed every day, the optimal algorithm is updated to the foreground, and the next day is calculated by using the set of algorithms.
Further, the solution method also comprises a feedback step, namely confirming whether an approver of the node promoted by the optimal model and related information are correct or not in the office system, if so, feeding back to the calculation model step to continue calculating the approver of the next node; and if not, manually selecting the next service processing room and the corresponding transactor in the office system, and performing the next service processing by the manually selected next service processing room and the corresponding transactor.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (18)
1. An approval flow solution method, device and computer equipment based on artificial intelligence comprises the following steps:
collecting flow information, task information, conference information, in-station information, reading knowledge information, geographic positions, attendance information and network information;
creating a service approval information database and storing the information data in the database;
carrying out distributed training by utilizing the information in the database, wherein the distributed training is divided into two parts, and the training dimensionality of the first distributed training is set as: flow, task, meeting, station information and reading content;
the dimensions of the second distributed training are set as: flow, task, meeting, geographic position, attendance information, network information; the first distribution training adopts 100 groups of random algorithm for training, the second distribution training adopts 100 groups of random distribution weights, and genetic optimization is carried out by using a genetic algorithm;
and training twice to obtain an optimal calculation model and obtain an approver of the next node.
2. The artificial intelligence based business approval flow solution of claim 1,
due to the existence of two groups of optimal genetic algorithms, two different approvers may exist in the node, and when the approvers are different, the two approvers are arranged in parallel in the node, namely, any person passes the approval and then passes the node.
3. The artificial intelligence based business approval flow solution of claim 1,
the information stored in the database is historical data in almost six months, and two distributed trainings respectively promote an optimal algorithm group.
4. The artificial intelligence based business approval flow solution of claim 1,
and (4) carrying out 50-generation genetic optimization by the genetic algorithm to obtain a final optimized calculation model.
5. The artificial intelligence based business approval flow solution of claim 1,
and performing one round of training every day, updating the optimal algorithm to the foreground, and calculating by using the set of algorithms the next day.
6. The artificial intelligence based business approval flow solution of claim 1,
the solution also comprises a feedback step, namely confirming whether an approver of the node recommended by the optimal model and related information are correct or not in the office system, if so, feeding back to the calculation model step to continue calculating the approver of the next node; and if not, manually selecting the next service processing room and the corresponding transactor in the office system, and performing the next service processing by the manually selected next service processing room and the corresponding transactor.
7. A business approval device based on artificial intelligence comprises:
and the acquisition module is used for collecting flow information, task information, meeting information, in-station information, reading knowledge information, user geographic position, attendance information and network information.
And the storage module is used for storing the information data and respectively storing the data into the flow module, the task module, the conference module, the station information module, the reading knowledge module, the user geographic position module, the user network information module and the user attendance information module.
The first distributed training module extracts 100 groups of data of processes, tasks, meetings, station letters and reading contents from the storage module, trains by adopting 100 groups of random algorithms, finally gives up an optimal calculation model, and calculates an approver of the next node;
and the second distribution training module extracts 100 groups of data of processes, tasks, meetings, geographic positions, attendance information and network information from the storage module, randomly allocates weights, performs genetic optimization by using a genetic algorithm to obtain an optimal training model, and calculates an approver of the next node.
And the execution module has two groups of optimal genetic algorithms, so that two different approvers may exist in the node, and when the approvers are different, the two approvers are set to be connected in parallel in the node, namely, any one approves the node and then passes the node.
8. The artificial intelligence based business approval apparatus according to claim 7, further comprising a feedback module, configured to receive the approver information sent by the execution module, notify the worker to confirm whether the approver of the node recommended by the optimal model and the related information are correct in the office system, and if yes, feed back to the calculation model step to continue calculating the approver of the next node; and if not, manually selecting the next service processing room and the corresponding transactor in the office system, and performing the next service processing by the manually selected next service processing room and the corresponding transactor.
9. The artificial intelligence based business approval apparatus of claim 7, wherein the information in the storage module is historical data in about six months, and two distributed trainings respectively promote an optimal algorithm group.
10. The artificial intelligence based business approval apparatus according to claim 7, wherein the storage means comprises an update module for periodically updating the personnel information database and the approval opinion database.
11. The artificial intelligence based business approval apparatus according to claim 7, wherein the genetic algorithm adopted by the training module performs 50 generations of genetic optimization to obtain the final optimized computational model.
12. The artificial intelligence based business approval apparatus of claim 7, wherein the two distributed training modules perform a round of training each day, update the optimal algorithm to the foreground, and perform the calculation using the set of algorithms the next day.
13. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor when executing the computer program implements the steps of:
collecting flow information, task information, conference information, in-station information, reading knowledge information, geographic positions, attendance information and network information;
creating a service approval information database and storing the information data in the database;
carrying out distributed training by utilizing the information in the database, wherein the distributed training is divided into two parts, and the training dimensionality of the first distributed training is set as: flow, task, meeting, station information and reading content; the dimensions of the second distributed training are set as: flow, task, meeting, geographic position, attendance information, network information; the first distribution training adopts 100 groups of random algorithm for training, the second distribution training adopts 100 groups of random distribution weights, and genetic optimization is carried out by using a genetic algorithm to obtain a training optimal model. And obtaining the approver of the next node through the optimal model.
14. The computer apparatus of claim 13, wherein there are two sets of optimized genetic algorithms, so that there may be two different approvers for the node, and when the approvers are different, the two approvers are set in parallel in the node, that is, any one approves the node and then passes the node.
15. The computer apparatus of claim 13, wherein the database stores information about historical data over approximately six months, and wherein each of the two distributed trainings elects a set of optimization algorithms.
16. The computer apparatus of claim 13, wherein the genetic algorithm performs 50 generations of genetic optimization to obtain a final optimized computational model.
17. The computer device of claim 13, wherein a round of training is performed daily, the optimal algorithm is updated to the foreground, and the next day is calculated using the set of algorithms.
18. The computer device of claim 13, further comprising a feedback step of confirming whether the approver of the node recommended by the optimal model and the related information are correct in the office system, and if so, feeding back to the calculation model step to continue calculating the approver of the next node; and if not, manually selecting the next service processing room and the corresponding transactor in the office system, and performing the next service processing by the manually selected next service processing room and the corresponding transactor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910965548.2A CN110705968A (en) | 2019-10-12 | 2019-10-12 | Artificial intelligence-based approval flow solution method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910965548.2A CN110705968A (en) | 2019-10-12 | 2019-10-12 | Artificial intelligence-based approval flow solution method and device and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110705968A true CN110705968A (en) | 2020-01-17 |
Family
ID=69199532
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910965548.2A Pending CN110705968A (en) | 2019-10-12 | 2019-10-12 | Artificial intelligence-based approval flow solution method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110705968A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112085469A (en) * | 2020-09-08 | 2020-12-15 | 中国平安财产保险股份有限公司 | Data approval method, device, equipment and storage medium based on vector machine model |
| CN112365224A (en) * | 2020-10-26 | 2021-02-12 | 南京集新萃信息科技有限公司 | Artificial intelligence automatic approval method suitable for project management system |
| CN113393065A (en) * | 2020-03-11 | 2021-09-14 | 中移智行网络科技有限公司 | Workflow node configuration method and device, storage medium and computer equipment |
| CN115373657A (en) * | 2022-06-30 | 2022-11-22 | 北京三维天地科技股份有限公司 | Method for automatically constructing application based on model drive |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108038162A (en) * | 2017-12-06 | 2018-05-15 | 国网江西省电力有限公司信息通信分公司 | Official document approver's intelligent recommendation method based on official document fragment and bipartite graph matching |
| CN108074072A (en) * | 2016-11-15 | 2018-05-25 | 北京合思信息技术有限公司 | A kind of financial transaction approval process management method |
-
2019
- 2019-10-12 CN CN201910965548.2A patent/CN110705968A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108074072A (en) * | 2016-11-15 | 2018-05-25 | 北京合思信息技术有限公司 | A kind of financial transaction approval process management method |
| CN108038162A (en) * | 2017-12-06 | 2018-05-15 | 国网江西省电力有限公司信息通信分公司 | Official document approver's intelligent recommendation method based on official document fragment and bipartite graph matching |
Non-Patent Citations (1)
| Title |
|---|
| WEIXIN_34238642: "jbpm的智能选择审批人及人工任务分配的实现思路", 《HTTPS://BLOG.CSDN.NET/WEIXIN_34238642/ARTICLE/DETAILS/89988083》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113393065A (en) * | 2020-03-11 | 2021-09-14 | 中移智行网络科技有限公司 | Workflow node configuration method and device, storage medium and computer equipment |
| CN112085469A (en) * | 2020-09-08 | 2020-12-15 | 中国平安财产保险股份有限公司 | Data approval method, device, equipment and storage medium based on vector machine model |
| CN112365224A (en) * | 2020-10-26 | 2021-02-12 | 南京集新萃信息科技有限公司 | Artificial intelligence automatic approval method suitable for project management system |
| CN115373657A (en) * | 2022-06-30 | 2022-11-22 | 北京三维天地科技股份有限公司 | Method for automatically constructing application based on model drive |
| CN115373657B (en) * | 2022-06-30 | 2023-06-13 | 北京三维天地科技股份有限公司 | Model-driven automatic application construction method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110705968A (en) | Artificial intelligence-based approval flow solution method and device and computer equipment | |
| Lu | Robust weighted vertex p-center model considering uncertain data: An application to emergency management | |
| Dekle et al. | A Florida county locates disaster recovery centers | |
| Al Shobaki et al. | The Reality of the Application of Electronic Document Management System in Governmental Institutions-an Empirical Study on the Palestinian Pension Agency | |
| Kshetri | Artificial Intelligence in Developing Countries. | |
| Zhang et al. | Ambulance deployment with relocation through robust optimization | |
| CN112016935A (en) | Enterprise customer information intelligent management system based on artificial intelligence | |
| CN108053323A (en) | Method, apparatus, computer equipment and the storage medium of service plan generation | |
| CN111401703B (en) | Resource information scheduling method and device | |
| JP6894275B2 (en) | Maintenance personnel accommodation support system and maintenance personnel accommodation support method | |
| Tanko et al. | Evaluation of the access to and utilization of information communication technology (ICT) facilities among extension officers in Shiroro LGA, Niger State, Nigeria | |
| Wales et al. | Optimizing vehicle fleet and assignment for concentrating solar power plant heliostat washing | |
| CN113052417A (en) | Resource allocation method and device | |
| CN110276648A (en) | Client's identification and based reminding method and device | |
| Marcikić et al. | Quantitative analysis of the demand for healthcare services | |
| CN114581059A (en) | Equipment supply and demand cooperative management method and device, computer equipment and storage medium | |
| CN114091797A (en) | Intelligent dispatching method and device | |
| Mahmudul et al. | The role of farmers’ education on income in Bangladesh | |
| Adriansyah et al. | Lean Management Implementation Training at The Pharmaceutical Unit of Islamic Hospital in Surabaya | |
| Stępniewska et al. | Possibilities of using the concept of ecosystem services at the regional level in experts’ opinions | |
| Aristi et al. | Design of Advertisement Tax Calculation Application Based on Android using the Extreme Programming at Dispenda Tasikmalaya | |
| Egorov et al. | Development of information and telecommunication technologies in the Republic of Sakha (Yakutia) in terms of the transition to a new technological mode | |
| Jadhav | Geographical Analysis of Spatial Distribution of Weekly Market Centers in Karad Tahsil | |
| CN102833673A (en) | Information real-time active correlation and push method based on element digit computing | |
| Yuliyanto | Quality Analysis of Infrastructure and Environmental Needs in CSR Activities of PT Indonesia Power Semarang Power Generation Unit |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200117 |