CN117520406A - RPA flow recommendation method, device and storage medium - Google Patents
RPA flow recommendation method, device and storage medium Download PDFInfo
- Publication number
- CN117520406A CN117520406A CN202311851220.0A CN202311851220A CN117520406A CN 117520406 A CN117520406 A CN 117520406A CN 202311851220 A CN202311851220 A CN 202311851220A CN 117520406 A CN117520406 A CN 117520406A
- Authority
- CN
- China
- Prior art keywords
- rpa
- user
- flow
- representing
- nodes
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 230000008569 process Effects 0.000 claims abstract description 16
- 239000013598 vector Substances 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 6
- 238000013519 translation Methods 0.000 claims description 6
- 230000007704 transition Effects 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 4
- 239000000463 material Substances 0.000 abstract description 3
- 238000012545 processing Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000004801 process automation Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0633—Workflow analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Computational Linguistics (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Development Economics (AREA)
- Computing Systems (AREA)
- Educational Administration (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to an RPA process recommendation method, equipment and a storage medium. The RPA flow recommending method provided by the invention is a coarse-granularity recommending method, and can provide a series of complete RPA flow recommending results for sales personnel, so that financial resources and material resources required by a company in processing related business are reduced, and the working efficiency and benefit are improved.
Description
Technical Field
The present invention relates to the field of computer systems, and in particular, to an RPA process recommendation method, an RPA process recommendation device, and a storage medium.
Background
With rapid development and popularization of digital technologies such as software automation and artificial intelligence, the informatization and digitalization technologies are reconstructing the original business mode of the traditional enterprises. The RPA (Robotic Process Automation, RPA) technology is to simulate the operation of a mouse and a keyboard by means of element grabbing, workflow, operation function definition and the like, automatically execute tasks according to flow definition and replace auxiliary manual completion operation. The RPA technology realizes the automation of the original service by grabbing system elements in a pre-programmed operation flow, changes the original manual work into automatic machine execution, and is continuously executed for 7 x 24 hours.
On the basis of keeping the safety of an enterprise information system, the RPA technology realizes that digital labor force replaces manual work, and is beneficial to improving efficiency and reducing production cost of a company. Thus, RPA technology has received extensive attention since the advent of the technology and has been put to practical engineering use in many areas worldwide.
Although there are many excellent RPA companies and RPA platforms at home and abroad, almost all RPA technologies are enterprise-class client oriented, not personal developer oriented. Second, most RPA platforms require specialized developers to refine business process data, and the above-described manual process is repeated despite similar historical business data.
A knowledge graph is a data structure for representing and storing knowledge, which consists of entities, attributes and relationships. Entities are basic concepts in a knowledge graph, which may be people, places, events, items, etc. Attributes are characteristics of entities, which may be nouns, adjectives, or numerical values. Relationships are associations between entities, which may be verbs, prepositions, or compound words. The knowledge graph may be graphically or tabulated, with nodes representing entities and edges representing attributes or relationships. The knowledge graph has wide application fields including search engines, intelligent questions and answers, recommendation systems, natural language processing and the like.
A recommendation system is a system that uses artificial intelligence to recommend items, which may be merchandise, music, movies, articles, news, etc., to a user. The goal of the recommendation system is to predict items that a user may be interested in by analyzing information about the user's historical behavior, interests, preferences, etc., and recommend these items to the user. The recommendation system can help users find new products or services, improve shopping experience and loyalty of the users, and help enterprises to improve sales and customer satisfaction. In the fields of electronic commerce, social media, music videos, and the like, a recommendation system has become an important technology.
The RPA recommendation refers to the possible RPA proposal recommendation given to the current new user flow demand according to the historical business flow information or the field information. The RPA recommendation is not only an application of the existing domain knowledge, but also can reduce the development cost of developing new business processes in the RPA technology.
At present, the RPA recommendation does not pay much attention, and the pan-worker RPA platform developed by China mobile research and development performs preliminary exploration on the intelligent recommendation and generation of the RPA on the basis of the RPA field map. The pan worker RPA firstly collects flow knowledge and business knowledge and converts the flow knowledge and business knowledge into corresponding triples to construct a domain knowledge graph. And then inputting new service demands into the system by a user, obtaining service intentions through intention recognition by using the textCNN neural network, and inputting the service intentions into a knowledge graph to perform graph traversal to obtain associated service flows. In addition, there are no other methods for recommending RPA procedures.
Disclosure of Invention
In order to solve the problems that in the prior art, RPA flow recommending methods are few and most of enterprises are not opened to individuals, the invention provides an RPA flow recommending method, which comprises the following steps:
s1, constructing a complete RPA knowledge graph, and carrying out initial vector representation on each user node in the RPA knowledge graph by adopting a pre-training model to obtain initial vectors of all the user nodes;
s2, constructing a flow node set of the user based on the RPA knowledge graphP i ;
S3, calculating each user according to the initial vector of each user nodeU i Similarity to other users;
s4, according to the similarity, aiming at each userU i Get similar to the userFront with highest degreeKIndividual users and lowest similarityKIndividual users, build and usersU i Is a set of similar users of (a)U si And dissimilar user setsUN si ;
S5, for similar user setsU si And dissimilar user setsUN si Constructing a user according to step S2U i Is a set of similar flows of (1)P si And dissimilar flow setsPN si ;
S6, optimizing node representation of the RPA knowledge graph by adopting a translation-based model TransE;
and S7, obtaining final representation of all nodes in the optimized RPA knowledge graph.
A storage medium storing instructions and data for an RPA procedure recommendation method.
An RPA procedure recommendation device, comprising: a processor and a storage medium; the processor loads and executes instructions and data in a storage medium for implementing the RPA flow recommendation method.
The beneficial effects provided by the invention are as follows: by adopting the scheme based on knowledge graph representation learning, the potential interested RPA process of the user can be found by comprehensively considering the graph structure information and the process use information, so that the financial resources and the material resources required by the company in processing related services are reduced, and the working efficiency and the benefit are improved.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention;
fig. 2 is a schematic view of the apparatus structure of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be further described with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 is a schematic diagram of a process flow of the present invention;
the input of the method is a user to be recommended and a complete RPA knowledge graph, which comprises the structural information of the graph and the attribute information of the nodes. The output result is the final representation of all nodes of the whole graph and the RPA flow recommendation result for the user to be recommended.
The invention provides an RPA flow recommending method, which specifically comprises the following steps:
s1, constructing a complete RPA knowledge graph, and carrying out initial vector representation on each user node in the RPA knowledge graph by adopting a pre-training model to obtain initial vectors of all the user nodes;
the step S1 specifically comprises the following steps: after the complete RPA knowledge graph is obtained, an initial vectorization representation is pre-trained for all nodes and relations by adopting a pre-training model Bert according to the attribute and relation related information of the nodes.
S2, constructing a flow node set of the user based on the RPA knowledge graphP i ;
It should be noted that for each user in the RPA mapU i According to the structure of the RPA map, all used flow node sets of the user can be found out. Meanwhile, if the prior flow recommended information of the user exists in the RPA map, the invention also includes the part>Is a kind of medium.
S3, calculating each user according to the initial vector of each user nodeU i Similarity to other users;
it should be noted that, in obtaining the pre-training vector representation of all the nodes in the RPA spectrum, the similarity between each user and all the other user vectors in the RPA spectrum is calculated.
It should be noted that, in the similarity calculation formula between users, the present invention provides a method for calculating cosine similarity between user vectors. Suppose a userU i And a userU j The vector representations of (a) are respectivelyAndThe calculation formula of the similarity of the two user vectors is as follows:
wherein the method comprises the steps ofDot product representing vector,/>Representing the modulo length of the vector. In practice, the similarity between users may be calculated in various ways, for example, calculating the Levenshtein distance, sinusoidal similarity, etc. between users according to their names.
S4, according to the similarity, aiming at each userU i Taking the front with the highest similarity with the userKIndividual users and lowest similarityKIndividual users, build and usersU i Is a set of similar users of (a)U si And dissimilar user setsUN si ;
The invention calculates the similarity among all users, and aims at each userU i Respectively taking the front part with the highest similarity with the userKIndividual users and lowest similarityKIndividual users are used to build a set of similar users for that userU si And dissimilar usersUN si A collection;
s5, for similar user setsU si And dissimilar user setsUN si Constructing a user according to step S2U i Is a set of similar flows of (1)P si And dissimilar flow setsPN si ;
It should be noted that, for the similar user set obtained from the aboveP si And dissimilar user setsPN si Repeating S2, namely constructing a flow set of each user in the set. Building usersU i Is a set of similar flows of (1)P si And dissimilar flow setsPN si 。
S6, optimizing node representation of the RPA knowledge graph by adopting a translation-based model TransE;
in step S6, node optimization is performed by using the translation-based model transition, specifically, training of the model is performed by using a structure loss function and a preference loss function.
For this part of the map structure, the present invention uses a translation-based model, transE, to optimize the representation.
A triplet in the maph,r,t) WhereinhThe representation of the head-node is given,trepresenting the end node of the line,rrepresenting the relationship between the two entities being connected. The TransE considers the vector representation of the head node and the relationship representation and should approximate the vector representation of the tail node, namely:
in accordance with this constraint, the structure-dependent loss function used by the present invention is as follows:
wherein the method comprises the steps ofPosRepresenting the triplet, i.e., positive sample, in the RPA map.NegRepresenting a negative sample of the sample.d(h+r,t) Representing the modular length of the head entity plus relation minus the tail entity in the positive sample, i.ed(h+r,t)=||h+r-t||。γRepresenting the super parameter.
When the optimization is represented by the transition, the optimization is mainly represented by positive samples and sampled negative samples in the RPA map. For negative sampling it is proposed to use the most similar negative sampling method and for a positive sample triplet (h, r, t) the negative sample is constructed by looking for the most similar node substitution to the tail node t or the head node h. Doing so may make the representation learned by the model more accurate.
Meanwhile, the invention not only considers the information related to the map structure, but also considers the relationship between users and the process when optimizing the representation.
Suppose a userU i For the flowP j Is of the degree of preference ofR ij The calculation formula is as follows:=/>*/>. The smaller the value, the higher the preference degree.
For each user, it uses a certain flow node, the higher the preference of the flow node is. And the higher the preference level should be for the flow nodes used by users similar to themselves, and the lower the flows for dissimilar users.
In summary, the design of the preference loss function is as follows:
wherein the method comprises the steps ofThe sum of preference scores of a certain user and a flow node used by the user; />Representing the sum of preference scores of flow nodes of a certain user and other similar users; />Representing a negative sample, which is the sum of preference scores of flows of a user and a user dissimilar to the user; />And->Respectively representing the super parameters.
The two losses are combined, and the loss of the final model optimization is as follows:. Beta is a preset weight.
Finally, when the recommended user is already in the RPA map, all the information mentioned above should be present. If the recommended user is a new user, i.e. there is no information in the RPA map that the user has used the set of flows, the part of the preference loss function can be removed when vector optimization is performed.
And S7, obtaining final representation of all nodes in the optimized RPA knowledge graph.
After obtaining the final representation of all nodes in the RPA knowledge graph, it should be noted that, for any user in the RPA knowledge graphUWhen the flow recommendation is carried out, firstly, preference values of the flow recommendation and all flow nodes are calculated, and k flow nodes with the minimum preference values are selected as recommendation results.
For a certain user in the RPA knowledge graphUAnd when the preference values of the user and all the flow nodes are calculated, removing the used flow and the recommended flow of the user.
Referring to fig. 2, fig. 2 is a schematic diagram of an apparatus according to the present invention.
The apparatus 401 specifically includes: processor 402 and storage medium 403.
RPA procedure recommendation device 401: the RPA process recommendation device 401 implements the RPA process recommendation method.
Processor 402: the processor 402 loads and executes the instructions and data in the storage medium 403 for implementing the one RPA procedure recommendation method.
Storage medium 403: the storage medium 403 stores instructions and data; the storage medium 403 is configured to implement the RPA procedure recommendation method.
In combination, the invention has the beneficial effects that: by adopting the scheme based on knowledge graph representation learning, the potential interested RPA process of the user can be found by comprehensively considering the graph structure information and the process use information, so that the financial resources and the material resources required by the company in processing related services are reduced, and the working efficiency and the benefit are improved.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (9)
1. An RPA process recommendation method is characterized in that: the method comprises the following steps:
s1, constructing a complete RPA knowledge graph, and carrying out initial vector representation on each user node in the RPA knowledge graph by adopting a pre-training model to obtain initial vectors of all the user nodes;
s2, constructing a flow node set of the user based on the RPA knowledge graphP i ;
S3, calculating each user according to the initial vector of each user nodeU i Similarity to other users;
s4, according to the similarity, aiming at each userU i Taking the front with the highest similarity with the userKIndividual users and lowest similarityKIndividual users, build and usersU i Is a set of similar users of (a)U si And dissimilar user setsUN si ;
S5, for similar user setsU si And dissimilar user setsUN si Constructing a user according to step S2U i Is a set of similar flows of (1)P si And dissimilar flow setsPN si ;
S6, optimizing node representation of the RPA knowledge graph by adopting a translation-based model TransE;
and S7, obtaining final representation of all nodes in the optimized RPA knowledge graph.
2. The RPA procedure recommendation method of claim 1, wherein: the step S1 specifically comprises the following steps: after the complete RPA knowledge graph is obtained, an initial vectorization representation is pre-trained for all nodes and relations by adopting a pre-training model Bert according to the attribute and relation related information of the nodes.
3. The RPA procedure recommendation method of claim 1, wherein: in step S6, node optimization is performed by using the translation-based model transition, specifically, training of the model is performed by using a structure loss function and a preference loss function.
4. The RPA procedure recommendation method of claim 3, wherein: the structural loss function is as follows:
wherein, (h, r, t) represents a triplet positive sample in the RPA knowledge-graph; positive sample set at Pos;representing a negative sample in the RPA knowledge-graph;Negrepresenting a negative set of samples;hthe representation of the head-node is given,trepresenting the end node of the line,rrepresenting a relationship between connecting the two entities;d(h+r,t) Representing the modular length of the head entity in the positive sample after the relation is added and the tail entity is subtracted; gamma represents a super parameter; />Representing the modular length of the negative sample after the head entity plus relation minus the tail entity.
5. The RPA procedure recommendation method of claim 3, wherein: the preference loss function is as follows:
wherein the method comprises the steps ofThe sum of preference scores of a certain user and a flow node used by the user; />Representing the sum of preference scores of flow nodes of a certain user and other similar users; />Representing a negative sample, which is the sum of preference scores of flows of a user and a user dissimilar to the user; />And->Respectively representing the super parameters.
6. The RPA procedure recommendation method of claim 1, wherein: after the final representation of all the nodes in the RPA knowledge graph is obtained, for a certain user U in the RPA knowledge graph, firstly calculating preference values of the user U and all the flow nodes when recommending the flow, and selecting k flow nodes with the minimum preference values from the preference values as recommendation results.
7. The RPA procedure recommendation method of claim 6, wherein:
and when a certain user U in the RPA knowledge graph calculates preference values of the user U and all flow nodes, removing the used flow and recommended flow of the user.
8. A storage medium, characterized by: the storage medium stores instructions and data for implementing an RPA procedure recommendation method according to any one of claims 1 to 7.
9. An RPA process recommendation device, characterized in that: comprising the following steps: a processor and a storage medium; the processor loads and executes instructions and data in a storage medium for implementing an RPA procedure recommendation method according to any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311851220.0A CN117520406B (en) | 2023-12-29 | 2023-12-29 | RPA flow recommendation method, device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311851220.0A CN117520406B (en) | 2023-12-29 | 2023-12-29 | RPA flow recommendation method, device and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117520406A true CN117520406A (en) | 2024-02-06 |
CN117520406B CN117520406B (en) | 2024-03-26 |
Family
ID=89745983
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311851220.0A Active CN117520406B (en) | 2023-12-29 | 2023-12-29 | RPA flow recommendation method, device and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117520406B (en) |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008153625A2 (en) * | 2007-05-25 | 2008-12-18 | Peerset Inc. | Recommendation systems and methods |
CN113158033A (en) * | 2021-03-19 | 2021-07-23 | 浙江工业大学 | Collaborative recommendation model construction method based on knowledge graph preference propagation |
CN114780861A (en) * | 2022-06-20 | 2022-07-22 | 上海二三四五网络科技有限公司 | Clustering technology-based user multi-interest recommendation method, device, equipment and medium |
WO2022188534A1 (en) * | 2021-03-11 | 2022-09-15 | 北京沃东天骏信息技术有限公司 | Information pushing method and apparatus |
CN115935089A (en) * | 2023-02-06 | 2023-04-07 | 北京合思信息技术有限公司 | RPA technology-based boarding point recommendation optimization method and system |
CN116091152A (en) * | 2022-10-07 | 2023-05-09 | 西安工业大学 | Recommendation method and system based on multi-level comparison learning and multi-mode knowledge graph |
CN116304332A (en) * | 2023-03-20 | 2023-06-23 | 北京工业大学 | Knowledge graph mixed recommendation method |
CN116384494A (en) * | 2023-06-05 | 2023-07-04 | 安徽思高智能科技有限公司 | RPA flow recommendation method and system based on multi-modal twin neural network |
CN116451785A (en) * | 2023-06-16 | 2023-07-18 | 安徽思高智能科技有限公司 | RPA knowledge graph construction and operation recommendation method oriented to operation relation |
WO2023179689A1 (en) * | 2022-03-24 | 2023-09-28 | 重庆邮电大学工业互联网研究院 | Knowledge graph-based recommendation method for internet of things |
WO2023184226A1 (en) * | 2022-03-30 | 2023-10-05 | 京东方科技集团股份有限公司 | Article recommendation method, article knowledge graph training method and apparatus, and model training method and apparatus |
CN117216281A (en) * | 2022-05-30 | 2023-12-12 | 长沙理工大学 | Knowledge graph-based user interest diffusion recommendation method and system |
-
2023
- 2023-12-29 CN CN202311851220.0A patent/CN117520406B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008153625A2 (en) * | 2007-05-25 | 2008-12-18 | Peerset Inc. | Recommendation systems and methods |
WO2022188534A1 (en) * | 2021-03-11 | 2022-09-15 | 北京沃东天骏信息技术有限公司 | Information pushing method and apparatus |
CN113158033A (en) * | 2021-03-19 | 2021-07-23 | 浙江工业大学 | Collaborative recommendation model construction method based on knowledge graph preference propagation |
WO2023179689A1 (en) * | 2022-03-24 | 2023-09-28 | 重庆邮电大学工业互联网研究院 | Knowledge graph-based recommendation method for internet of things |
WO2023184226A1 (en) * | 2022-03-30 | 2023-10-05 | 京东方科技集团股份有限公司 | Article recommendation method, article knowledge graph training method and apparatus, and model training method and apparatus |
CN117216281A (en) * | 2022-05-30 | 2023-12-12 | 长沙理工大学 | Knowledge graph-based user interest diffusion recommendation method and system |
CN114780861A (en) * | 2022-06-20 | 2022-07-22 | 上海二三四五网络科技有限公司 | Clustering technology-based user multi-interest recommendation method, device, equipment and medium |
CN116091152A (en) * | 2022-10-07 | 2023-05-09 | 西安工业大学 | Recommendation method and system based on multi-level comparison learning and multi-mode knowledge graph |
CN115935089A (en) * | 2023-02-06 | 2023-04-07 | 北京合思信息技术有限公司 | RPA technology-based boarding point recommendation optimization method and system |
CN116304332A (en) * | 2023-03-20 | 2023-06-23 | 北京工业大学 | Knowledge graph mixed recommendation method |
CN116384494A (en) * | 2023-06-05 | 2023-07-04 | 安徽思高智能科技有限公司 | RPA flow recommendation method and system based on multi-modal twin neural network |
CN116451785A (en) * | 2023-06-16 | 2023-07-18 | 安徽思高智能科技有限公司 | RPA knowledge graph construction and operation recommendation method oriented to operation relation |
Non-Patent Citations (1)
Title |
---|
张茂宇等: "融合双重语义相似度的混合协同过滤推荐算法", 计算机工程与设计, 30 September 2023 (2023-09-30), pages 2671 - 2678 * |
Also Published As
Publication number | Publication date |
---|---|
CN117520406B (en) | 2024-03-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Gireesha et al. | IIVIFS-WASPAS: an integrated multi-criteria decision-making perspective for cloud service provider selection | |
Torfi et al. | Fuzzy AHP to determine the relative weights of evaluation criteria and Fuzzy TOPSIS to rank the alternatives | |
JP5921536B2 (en) | Computerized Agent System and User Instruction Semantic Networking | |
US20150317376A1 (en) | Method, system and computer program product for automating expertise management using social and enterprise data | |
CN112613602A (en) | Recommendation method and system based on knowledge-aware hypergraph neural network | |
CN113744032A (en) | Book recommendation method, related device, equipment and storage medium | |
Wang et al. | Hybrid customer requirements rating method for customer-oriented product design using QFD | |
CN116628228B (en) | RPA flow recommendation method and computer readable storage medium | |
CN115481325A (en) | Personalized news recommendation method and system based on user global interest migration perception | |
Liu et al. | Research and citation analysis of data mining technology based on Bayes algorithm | |
De Tré et al. | Handling veracity in multi-criteria decision-making: A multi-dimensional approach | |
CN115221387A (en) | Enterprise information integration method based on deep neural network | |
Ali et al. | The Journal of Hospitality and Tourism Technology (JHTT): a retrospective review using bibliometric analysis | |
CN117633193A (en) | Query question replying method, device, equipment and storage medium | |
CN117520406B (en) | RPA flow recommendation method, device and storage medium | |
CN117194771A (en) | Dynamic knowledge graph service recommendation method for graph model characterization learning | |
CN116401450A (en) | Recommendation method and device based on knowledge graph and computer equipment | |
US20230289696A1 (en) | Interactive tree representing attribute quality or consumption metrics for data ingestion and other applications | |
US20230289839A1 (en) | Data selection based on consumption and quality metrics for attributes and records of a dataset | |
CN115391662A (en) | Personalized recommendation method and device based on article attribute sampling and storage medium | |
CN113837847A (en) | Knowledge-intensive service recommendation method based on heterogeneous multivariate relation fusion | |
Zhao et al. | Folkrank++: an optimization of Folkrank tag recommendation algorithm integrating user and item information | |
Nguyen et al. | An approach to constructing a graph data repository for course recommendation based on IT career goals in the context of big data | |
Yin et al. | A dynamic MADM method for the selection of a big data service provider | |
Hsu et al. | Similarity search over personal process description graph |
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 |