CN116167605A - Business process generation method, device, equipment and medium - Google Patents
Business process generation method, device, equipment and medium Download PDFInfo
- Publication number
- CN116167605A CN116167605A CN202310460091.6A CN202310460091A CN116167605A CN 116167605 A CN116167605 A CN 116167605A CN 202310460091 A CN202310460091 A CN 202310460091A CN 116167605 A CN116167605 A CN 116167605A
- Authority
- CN
- China
- Prior art keywords
- data
- interaction
- factor
- business process
- target
- 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 182
- 230000008569 process Effects 0.000 title claims abstract description 137
- 230000003993 interaction Effects 0.000 claims abstract description 261
- 230000002452 interceptive effect Effects 0.000 claims abstract description 80
- 230000006399 behavior Effects 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims description 35
- 238000012545 processing Methods 0.000 claims description 23
- 238000000605 extraction Methods 0.000 claims description 13
- 238000010276 construction Methods 0.000 claims description 12
- 238000002372 labelling Methods 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 238000012546 transfer Methods 0.000 claims description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 28
- 230000008447 perception Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000005065 mining Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000007704 transition Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000001149 cognitive effect Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000036962 time dependent Effects 0.000 description 2
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0633—Workflow analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- 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
- G06N5/025—Extracting rules from data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Computational Linguistics (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a business process generation method, a business process generation device, business process generation equipment and business process generation media, and relates to the technical field of artificial intelligence. The method comprises the steps of constructing a first knowledge graph based on first data, wherein the first data is business data generated under a first interaction scene; obtaining a target interaction factor according to the first data and the first knowledge graph, wherein the target interaction factor is an interaction factor applicable to the first interaction scene, and the interaction factor is a word capable of enabling interaction behaviors to occur between interaction objects; according to the first data and the target interaction factor, an interaction factor time sequence map is obtained; and generating a target business process according to the interaction factor time sequence map. According to the invention, the interactive flow in the specific field is automatically constructed through data driving, and the excellent business flow is mined, so that the purpose of improving the business efficiency is achieved.
Description
Technical Field
The present invention relates to the field of artificial intelligence technologies, and in particular, to a method, an apparatus, a device, and a medium for generating a business process.
Background
The four intelligent stages of artificial intelligence (Artificial Intelligence, AI) technology development are: computing intelligence, perception intelligence, cognitive intelligence, and decision intelligence. Wherein, the computing intelligence is realized, the perception intelligence is gradually maturing, and how to transition from the perception intelligence to the perception intelligence is still a difficult problem to be determined.
The knowledge graph is used as one of important technologies from perception intelligence to cognition intelligence, and is also subjected to bottlenecks in practical business application, besides the conventional search, recommendation and question-answer application based on the domain knowledge graph, namely the application mode of taking the knowledge graph as visual detection, the knowledge graph is only applied to a very narrow space of related business of enterprises, and is separated from the practical business front, for example, what business flow is designed in an interactive scene so as to improve the business efficiency, and effective technical means and methods are also lacking.
Disclosure of Invention
The invention aims to provide a business process generation method, a device, equipment and a medium, which are used for mining excellent business processes under an interactive scene so as to achieve the purpose of improving business efficiency.
In order to achieve the above object, in a first aspect, the present invention provides a business process generating method, including:
Constructing a first knowledge graph based on first data, wherein the first data is business data generated under a first interaction scene;
obtaining a target interaction factor according to the first data and the first knowledge graph, wherein the target interaction factor is an interaction factor applicable to the first interaction scene, and the interaction factor is a word capable of enabling interaction behaviors to occur between interaction objects;
according to the first data and the target interaction factor, an interaction factor time sequence map is obtained;
and generating a target business process according to the interaction factor time sequence map.
The constructing a first knowledge graph based on the first data includes:
obtaining entities and relations in the first data by utilizing a knowledge extraction model obtained through pre-training;
and obtaining the first knowledge graph based on the entity and the relation in the first data.
Wherein the method further comprises:
acquiring annotation data in second data, wherein the second data is part of data in the first data, and the annotation data comprises an entity to be annotated and an annotation relation;
and carrying out model training based on the labeling data to obtain the knowledge extraction model.
The obtaining the first knowledge graph based on the entity and the relation in the first data includes:
performing entity matching on the entities in the first data by utilizing a pre-trained entity chain finger model;
and obtaining the first knowledge graph according to the matched entity and relation.
Wherein the method further comprises:
recording entity chain index annotation behaviors aiming at partial entities in the first data;
and performing model training based on the entity chain index annotation behavior to obtain the entity chain index model.
The obtaining the target interaction factor according to the first data and the first knowledge graph includes:
model training is carried out based on third data and the first knowledge graph to obtain an interactive factor recognition model, wherein the third data is part of data in the first data;
and identifying a target interaction factor from the first data by using the interaction factor identification model.
The model training is performed based on the third data and the first knowledge graph to obtain an interaction factor identification model, which comprises the following steps:
extracting a moving guest relation in the third data;
obtaining a marked interaction factor according to the entity and the relation included in the first knowledge graph and the moving guest relation in the third data, wherein the marked interaction factor is applicable to the first interaction scene;
And training a model based on the noted interactive factors to obtain the interactive factor identification model.
Wherein, the obtaining the interaction factor timing diagram according to the first data and the target interaction factor includes:
clustering the target interactive factors, and determining standard factor names of the interactive factors which are gathered into the same class, wherein a first factor name is the standard factor name of the interactive factors which are gathered into the same class, and the number of the interactive factors corresponding to the first factor name in the interactive factors which are gathered into the same class is the largest;
replacing all other factor names except the standard factor name in the interactive factors collected into the same class with the standard factor name to obtain a quasi interactive factor;
and carrying out association combination on the quasi-interaction factors according to the time sequence of the quasi-interaction factors in the first data, and generating the interaction factor timing sequence map.
Wherein the generating a target business process according to the interaction factor timing diagram includes:
acquiring first-class service data, second-class service data and third-class service data in the first interaction scene, wherein the service efficiency corresponding to the first-class service data is higher than the service efficiency corresponding to the second-class service data, and the service efficiency corresponding to the second-class service data is higher than the service efficiency corresponding to the third-class service data;
For each type of service data, acquiring the probability of transferring the corresponding type of service data to the next node after mapping the corresponding type of service data to the interaction factor time sequence map, and outputting a service flow corresponding to the corresponding type of service data according to a path of the maximum probability;
if the difference value between any two of the first business process, the second business process and the third business process is larger than a first threshold value, the first business process is determined to be the target business process, wherein the first business process is a business process based on the first type business data output, the second business process is a business process based on the second type business data output, and the third business process is a business process based on the third type business data output.
After the corresponding type of service data is mapped to the interaction factor timing diagram, the probability of transferring from one node to the next node is obtained, which comprises the following steps:
mapping the corresponding type of service data into the interactive factor time sequence map;
counting each edge in the interaction factor time sequence map according to the transfer quantity among nodes based on the corresponding type of service data;
The count for each edge in the interaction factor timing graph is converted to a probability of transitioning from one node to the next.
In a second aspect, the present invention further provides a service flow generating device, including:
the map construction module is used for constructing a first knowledge map based on first data, wherein the first data is business data generated in a first interaction scene;
the first processing module is used for obtaining a target interaction factor according to the first data and the first knowledge graph, wherein the target interaction factor is an interaction factor applicable to the first interaction scene, and the interaction factor is a word capable of enabling interaction behaviors to occur between interaction objects;
the second processing module is used for obtaining an interaction factor time sequence map according to the first data and the target interaction factor;
and the generating module is used for generating a target business process according to the interaction factor time sequence map.
In a third aspect, the present invention also provides a service flow generating device, including a processor and a transceiver, where the transceiver receives and transmits data under the control of the processor, and the processor is configured to perform the following operations:
constructing a first knowledge graph based on first data, wherein the first data is business data generated under a first interaction scene;
Obtaining a target interaction factor according to the first data and the first knowledge graph, wherein the target interaction factor is an interaction factor applicable to the first interaction scene, and the interaction factor is a word capable of enabling interaction behaviors to occur between interaction objects;
according to the first data and the target interaction factor, an interaction factor time sequence map is obtained;
and generating a target business process according to the interaction factor time sequence map.
In a fourth aspect, the present invention also provides a business process generating device, including a memory, a processor, and a program stored in the memory and executable on the processor; the processor implements the business process generation method according to the first aspect described above when executing the program.
In a fifth aspect, the present invention also provides a computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, implements the steps of the business process generation method according to the first aspect described above.
The technical scheme of the invention has at least the following beneficial effects:
in the embodiment of the invention, a first knowledge graph is firstly constructed based on first data, wherein the first data is business data generated in a first interaction scene; then, according to the first data and the first knowledge graph, a target interaction factor is obtained, wherein the target interaction factor is an interaction factor applicable to the first interaction scene, and the interaction factor is a word capable of enabling interaction behaviors to occur between interaction objects; according to the first data and the target interaction factor, an interaction factor time sequence map is obtained; and finally, generating a target business process according to the interactive factor time sequence map, thus carrying out automatic process construction on the interactive process in the specific field through data driving, and excavating an excellent business process from the interactive process, thereby achieving the purpose of improving the business efficiency.
Drawings
Fig. 1 shows a flow diagram of a business flow generating method according to an embodiment of the present invention;
FIG. 2 shows a schematic diagram of a domain Schema constructed in accordance with an embodiment of the present invention;
FIG. 3 is a schematic diagram of a first knowledge-graph according to an embodiment of the invention;
FIG. 4 is a schematic diagram of an interactive factor timing diagram according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of business process construction according to an embodiment of the present invention;
fig. 6 shows a schematic block diagram of a business process generating device according to an embodiment of the present invention;
fig. 7 is a schematic diagram of a hardware structure of a business process generating device according to an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantages to be solved more apparent, the following detailed description will be given with reference to the accompanying drawings and specific embodiments.
In an interactive scenario of an enterprise, such as a sales scenario, a customer service scenario, etc., a business scenario requiring interaction between enterprise personnel and customers has more complex interaction logic. Enterprises have conventional coarse-grained flow designs in the scenes, and in the actual operation process, the fine-grained flow often can determine the solution efficiency of the scene problems. Different salespersons basically keep the consistency of coarse-granularity flow in the actual sales process, and larger difference exists in fine-granularity flow links, so that the mining of the fine-granularity flow has higher application value for helping enterprises to improve the interaction effect of interaction scenes such as sales and the like.
The current knowledge graph is only applied to a very narrow space of the related business of the enterprise, and is separated from the actual business front line, for example, what business process is designed in an interactive scene to improve the business efficiency, and effective technical means and methods are not available.
In order to solve the above problems, the embodiments of the present invention provide a method, an apparatus, a device, and a medium for generating a business process. The method and the device are based on the same application, and because the principles of solving the problems by the method and the device are similar, the implementation of the device and the method can be referred to each other, and the repetition is not repeated.
As shown in fig. 1, a flow diagram of a business flow generation method according to an embodiment of the present invention may include:
here, the first interaction scenario may be a business scenario, such as a sales scenario, a customer service scenario, etc., of interactions between an enterprise attendant and a customer. For example, the first data may be data of a sales scene of an automobile, including full-flow conversation data of customers and consultants at a 4S store of the automobile
It should be noted that the first knowledge graph is a factual knowledge graph corresponding to the first interaction scenario. The first knowledge graph includes entities, relationships, and attributes. Here, the person, thing, and thing related to the first interaction scenario in the first knowledge graph are generally referred to as entities, and the relationship is used to represent a certain relationship between different entities, where in the first knowledge graph, the side represents the relationship in the knowledge graph. The entities and relationships in the first knowledge-graph may each have a respective attribute.
102, obtaining a target interaction factor according to the first data and the first knowledge graph, wherein the target interaction factor is an interaction factor applicable to the first interaction scene, and the interaction factor is a word capable of enabling interaction behaviors to occur between interaction objects;
specifically, the implementation principle of this step may be: mining a moving guest relation in the first data through syntactic analysis, and combining the moving guest relation with an entity in the first knowledge graph to generate candidate interaction factors; and then, screening candidate interaction factors through man-machine cooperation to obtain target interaction factors.
It should be noted that, the mined target interaction factors are combined according to the time sequence of the mined target interaction factors in the first data, so as to generate an interaction factor timing diagram.
And 104, generating a target business process according to the interaction factor time sequence map.
Because the interaction factor timing diagram is related to time, and the interaction flow is embodied; the business process is also time-dependent, so that the target business process can be generated in an assisted manner based on the interaction factor timing diagram. Here, the target business process is an excellent business process required by the enterprise. Thus, the enterprise can copy the excellent flow and improve interactive business of the intersection, thereby improving business efficiency of the enterprise in the interactive scene.
It should be noted that, when constructing the knowledge graph, the Schema construction is performed first. It should be understood that Schema defines explicitly the entities, attributes and relationships in the knowledge graph, and defines explicitly the scope of the possibilities. The method is essentially to establish a general standard for 'consensus', maximize the efficiency of knowledge sharing and reduce the redundancy of knowledge.
In the embodiment of the present invention, the Schema for constructing the first knowledge graph may specifically be:
(1) The business specialists constructed by the field Schema are determined, for example, a business specialist team consisting of Zhang three, li four and Wang five is determined.
(2) The service specialist cooperates with the co-constructed field Schema. Such as entities designing customers, advisors, vehicles, brands, train, etc., and relationships between entities, such as (customers, intended brands, brands), (vehicles, assemblies, engines), (stars, representatives, brands), etc., are shown in fig. 2.
Thereafter, in an alternative embodiment, the step 101 may specifically include:
step 1011, obtaining entities and relations in the first data by using a knowledge extraction model obtained by training in advance;
specifically, the first data is output to the knowledge extraction model, and the entity and the relation in the first data are output.
Before this, the training process of the knowledge extraction model may specifically include:
1) Acquiring annotation data in second data, wherein the second data is part of data in the first data, and the annotation data comprises an entity to be annotated and an annotation relation;
note that, the labeling data in the second data is manually labeled data, and is then acquired by the device side.
2) And carrying out model training based on the labeling data to obtain the knowledge extraction model.
Specifically, model training is performed by using an active learning method based on the labeling data, and when the knowledge extraction model obtained by training reaches the model measurement index, labeling is stopped manually, so that the efficiency of manual labeling and model training can be improved. For example, if the actual model measurement index F1 of an entity (such as a brand entity) reaches the standard, the labeling of the entity is stopped manually.
Step 1012, obtaining the first knowledge-graph based on the entities and the relationships in the first data.
The method specifically comprises the following steps:
1. performing entity matching on the entities in the first data by utilizing a pre-trained entity chain finger model;
it should be appreciated that, by using the entity chain index model, entity matching, that is, entity alignment, is performed on the entities in the first data, specifically, identifying the words (i.e., entity references) in the unstructured data that represent the entities, and referring the entity reference chain to the entity that has the same or similar meaning as the entity (this entity is the entity defined in Schema that created the first knowledge-graph before).
Before this step is performed, the training process of the entity chain finger model may specifically include:
(1) Recording entity chain index annotation behaviors aiming at partial entities in the first data;
it should be noted that, the entity chain index annotating action of the entity is an artificial annotating action, and the equipment end records the action. The labeling personnel performs entity chain index labeling on part of the entities in the first data, for example, the brand letter identification chain identified by the model is pointed to the brand character names of the existing knowledge graph.
(2) And performing model training based on the entity chain index annotation behavior to obtain the entity chain index model.
Specifically, model training is performed by using an active learning method based on entity chain index annotation behaviors, and entity chain index annotation is stopped when the training obtained entity chain index model reaches the standard. For example, if the brand class entity chain index model is up to standard, stopping the entity chain index label of the brand class.
2. And obtaining the first knowledge graph according to the matched entity and relation.
The first knowledge-graph is a factual knowledge-graph corresponding to the first interaction scenario. Here, the person, thing, and thing related to the first interaction scenario in the first knowledge graph are generally referred to as entities, and the relationship is used to represent a certain relationship between different entities, where in the first knowledge graph, the side represents the relationship in the knowledge graph. The entities and relationships in the first knowledge-graph may each have a respective attribute. For the automobile sales scenario, the first knowledge graph obtained by the method can be seen in fig. 3.
In an alternative embodiment, the step 102 may specifically include:
step 1021, performing model training based on third data and the first knowledge graph to obtain an interactive factor recognition model, wherein the third data is part of data in the first data;
specifically, the step 1021 may include:
(1) extracting a moving guest relation in the third data;
specifically, the semantic syntax tree analysis is performed on the third data, and the guest-moving relation in the third data is extracted.
(2) Obtaining a marked interaction factor according to the entity and the relation included in the first knowledge graph and the moving guest relation in the third data, wherein the marked interaction factor is applicable to the first interaction scene;
here, the interaction factor of the label is an interaction factor of the manual label, and is obtained by the equipment end. Specifically, when the interactive factors are manually marked, the manual marking of the interactive factors is performed according to the reference interactive factors. For example, will "do it possible to try to drive this horse (brand name) X3? The "test driving" and the "certain horse X3" in the "are marked as interaction factors, and the marks can be designed into but not limited to the form" can be tested P-B Driving device P-E One go down to O-B Horse O-I X O-1 3 O-E Does it.
Wherein the reference interaction factor is applicable to the first interaction scenario, and is obtained in advance. The specific acquisition process of the reference cross factor is as follows:
firstly, extracting predicates in first data; then, combining the extracted predicates and the entities of the first knowledge graph in pairs (which can be Cartesian combination) to obtain an interaction factor candidate set; and finally, screening out the interaction factors suitable for the first interaction scene from the interaction factor candidate set through man-machine cooperation as reference interaction factors.
(3) And training a model based on the noted interactive factors to obtain the interactive factor identification model.
Combining the entity vector, the syntax tree vector (representing the dynamic guest relation) and the vector of each character (representing the marked interactive factors) into a new vector, and constructing an interactive factor recognition model by utilizing a pre-training model such as Bert to obtain the interactive factor recognition model.
Step 1022, using the interaction factor identification model, identifying a target interaction factor from the first data.
Specifically, the first data is output to the interaction factor recognition model, and the target interaction factor is output.
In an alternative embodiment, the step 103 may specifically include:
Step 1031, clustering the target interactive factors, and determining standard factor names of the interactive factors which are gathered into the same class, wherein a first factor name is the standard factor name of the interactive factors which are gathered into the same class, and the number of the interactive factors corresponding to the first factor name in the interactive factors which are gathered into the same class is the largest;
it should be noted that, the purpose of clustering the target interaction factors is to unify the naming of the interaction factors (factor names). For example, similar interaction factors such as "go to test" and "go to test drive" are clustered into one type of interaction factor, and the largest number of factors are used as the factor names of the one type.
Step 1032, replacing all other factor names except the standard factor name in the interactive factors collected into the same class with the standard factor name to obtain a quasi interactive factor;
and step 1033, performing association combination on the quasi-interaction factors according to the time sequence of the quasi-interaction factors in the first data, and generating the interaction factor timing diagram.
That is, the interactive factors are combined in association with the order of the actual conversation time series in the first data, and the interactive factor timing map is generated, see fig. 4. The interaction factor timing diagram is related to time, and the interaction flow is reflected to a certain extent. The business process is also time-dependent, so that the target business process can be generated in an assisted manner based on the interaction factor timing diagram.
In an alternative embodiment, the step 104 may specifically include:
step 1041, obtaining first-class service data, second-class service data and third-class service data in the first interaction scenario, where the service efficiency corresponding to the first-class service data is higher than the service efficiency corresponding to the second-class service data, and the service efficiency corresponding to the second-class service data is higher than the service efficiency corresponding to the third-class service data;
for example, the first interaction scene is an automobile sales scene, sales performance of sales personnel is extracted from a business system, and sales personnel of a 4S shop are classified into good, medium and poor categories according to the sales performance. According to the embodiment, business data corresponding to sales personnel with good sales performance (dialogue data between the sales personnel and clients in the sales process) is first-class business data, business data corresponding to sales personnel with poor sales performance is second-class business data, and business data corresponding to sales personnel with poor sales performance is third-class business data.
Step 1042, for each type of service data, obtaining the probability of transferring from one node to the next node after mapping the corresponding type of service data to the interaction factor timing diagram, and outputting the service flow corresponding to the corresponding type of service data according to the path of the maximum probability;
In this step, for each type of service data, after mapping the corresponding type of service data to the interaction factor timing diagram, the probability of transferring from one node to the next node may be obtained, which specifically includes:
(1) mapping the corresponding type of service data into the interactive factor time sequence map;
specifically, for each type of service data, the interaction factors in the corresponding type of service data are mapped into an interaction factor timing diagram.
(2) Counting each edge in the interaction factor time sequence map according to the transfer quantity among nodes based on the corresponding type of service data;
it should be noted that, an edge in the interaction factor timing diagram connects two nodes, where a node represents an interaction factor, and two nodes on an edge are in time sequence. It should be understood that, for example, the number of transitions between nodes refers to the number of transitions from node a to node B of business data corresponding to a plurality of sales personnel with good sales performance.
(3) The count for each edge in the interaction factor timing graph is converted to a probability of transitioning from one node to the next.
For example, A.fwdarw.B, A.fwdarw.C, the probability of A to B is 50% and the probability of A to C is 50%. Here, the sales flows of the sales personnel of the good, medium and bad categories are output according to the path of the maximum probability, and the sales flows of the good, medium and bad categories are obtained.
In step 1043, if the difference value between any two of the first business process, the second business process and the third business process is greater than the first threshold, the first business process is determined as the target business process, wherein the first business process is a business process based on the first type business data output, the second business process is a business process based on the second type business data output, and the third business process is a business process based on the third type business data output.
Specifically, the edit distance may be used to calculate a difference value between any two of the first business process, the second business process, and the third business process.
Here, if the difference value between any two of the first business process, the second business process and the third business process is larger than the first threshold value, the difference value is obvious, and the first business process, the second business process and the third business process are all effective processes, and the first business process is determined to be a target business process, namely, an excellent business process is dug. After the excellent business process is mined, the enterprise can copy the excellent business process to improve interactive business of the intersection, so that business efficiency of the enterprise in an interactive scene is improved.
According to the method provided by the embodiment of the invention, the knowledge graph is established from the bottom to the top through the flow graph from the data drive, and particularly referring to FIG. 5, so that the cognitive intelligence of an enterprise on the self-related business is realized.
According to the business process generation method, a first knowledge graph is constructed based on first data, wherein the first data is business data generated in a first interaction scene; then, according to the first data and the first knowledge graph, a target interaction factor is obtained, wherein the target interaction factor is an interaction factor applicable to the first interaction scene, and the interaction factor is a word capable of enabling interaction behaviors to occur between interaction objects; according to the first data and the target interaction factor, an interaction factor time sequence map is obtained; and finally, generating a target business process according to the interactive factor time sequence map, thus carrying out automatic process construction on the interactive process in the specific field through data driving, and excavating an excellent business process from the interactive process, thereby achieving the purpose of improving the business efficiency.
As shown in fig. 6, an embodiment of the present invention further provides a service flow generating device, where the device includes:
the map construction module 601 is configured to construct a first knowledge map based on first data, where the first data is service data generated in a first interaction scenario;
The first processing module 602 is configured to obtain a target interaction factor according to the first data and the first knowledge graph, where the target interaction factor is an interaction factor applicable to the first interaction scenario, and the interaction factor is a word that enables interaction behavior between interaction objects;
a second processing module 603, configured to obtain an interaction factor timing map according to the first data and the target interaction factor;
and the generating module 604 is configured to generate a target business process according to the interaction factor timing diagram.
Optionally, the map construction module 601 may include:
the first processing unit is used for obtaining entities and relations in the first data by utilizing a knowledge extraction model obtained through pre-training;
and the map construction unit is used for obtaining the first knowledge map based on the entity and the relation in the first data.
Optionally, the device of the embodiment of the present invention further includes:
the acquisition module is used for acquiring annotation data in second data, wherein the second data is part of data in the first data, and the annotation data comprises an entity to be annotated and a relationship to be annotated;
and the third processing module is used for carrying out model training based on the labeling data to obtain the knowledge extraction model.
Optionally, the map construction unit is specifically configured to:
performing entity matching on the entities in the first data by utilizing a pre-trained entity chain finger model;
and obtaining the first knowledge graph according to the matched entity and relation.
Optionally, the device of the embodiment of the present invention further includes:
the recording module is used for recording entity chain index annotation behaviors aiming at part of entities in the first data;
and the fourth processing module is used for performing model training based on the entity chain index annotation behavior to obtain the entity chain index model.
Optionally, the first processing module 602 includes:
the second processing unit is used for performing model training based on third data and the first knowledge graph to obtain an interactive factor recognition model, wherein the third data is part of data in the first data;
and the third processing unit is used for identifying the target interaction factor from the first data by utilizing the interaction factor identification model.
Optionally, the second processing unit is specifically configured to:
extracting a moving guest relation in the third data;
obtaining a marked interaction factor according to the entity and the relation included in the first knowledge graph and the moving guest relation in the third data, wherein the marked interaction factor is applicable to the first interaction scene;
And training a model based on the noted interactive factors to obtain the interactive factor identification model.
Optionally, the second processing module 603 includes:
the clustering unit is used for clustering the target interaction factors and determining standard factor names of the interaction factors which are gathered into the same class, wherein the first factor names are the standard factor names of the interaction factors which are gathered into the same class, and the number of the interaction factors corresponding to the first factor names in the interaction factors which are gathered into the same class is the largest;
the fourth processing unit is used for replacing all factor names except the standard factor name in the interactive factors which are gathered into the same class with the standard factor name to obtain a quasi interactive factor;
and the time sequence map generation unit is used for carrying out association combination on the quasi-interaction factors according to the time sequence of the quasi-interaction factors in the first data to generate the interaction factor time sequence map.
Optionally, the generating module 604 includes:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring first-class service data, second-class service data and third-class service data in the first interaction scene, wherein the service efficiency corresponding to the first-class service data is higher than the service efficiency corresponding to the second-class service data, and the service efficiency corresponding to the second-class service data is higher than the service efficiency corresponding to the third-class service data;
The fifth processing unit is used for acquiring the probability of transferring from one node to the next node after mapping the corresponding type of service data to the interaction factor time sequence map according to each type of service data, and outputting a service flow corresponding to the corresponding type of service data according to a path of the maximum probability;
the flow generation unit is configured to determine, when the difference value between any two of a first service flow, a second service flow and a third service flow is greater than a first threshold, the first service flow as the target service flow, where the first service flow is a service flow based on the first type of service data output, the second service flow is a service flow based on the second type of service data output, and the third service flow is a service flow based on the third type of service data output.
Optionally, the fifth processing unit is specifically configured to:
mapping the corresponding type of service data into the interactive factor time sequence map;
counting each edge in the interaction factor time sequence map according to the transfer quantity among nodes based on the corresponding type of service data;
the count for each edge in the interaction factor timing graph is converted to a probability of transitioning from one node to the next.
The business process generating device of the embodiment of the invention firstly constructs a first knowledge graph based on first data, wherein the first data is business data generated in a first interaction scene; then, according to the first data and the first knowledge graph, a target interaction factor is obtained, wherein the target interaction factor is an interaction factor applicable to the first interaction scene, and the interaction factor is a word capable of enabling interaction behaviors to occur between interaction objects; according to the first data and the target interaction factor, an interaction factor time sequence map is obtained; and finally, generating a target business process according to the interactive factor time sequence map, thus carrying out automatic process construction on the interactive process in the specific field through data driving, and excavating an excellent business process from the interactive process, thereby achieving the purpose of improving the business efficiency.
In order to better achieve the above objects, as shown in fig. 7, an embodiment of the present invention further provides a business process generating device, including a processor 700 and a transceiver 710, where the transceiver 710 receives and transmits data under the control of the processor 700, and the processor 700 is configured to perform the following procedures:
constructing a first knowledge graph based on first data, wherein the first data is business data generated under a first interaction scene;
Obtaining a target interaction factor according to the first data and the first knowledge graph, wherein the target interaction factor is an interaction factor applicable to the first interaction scene, and the interaction factor is a word capable of enabling interaction behaviors to occur between interaction objects;
according to the first data and the target interaction factor, an interaction factor time sequence map is obtained;
and generating a target business process according to the interaction factor time sequence map.
Optionally, the processor 700 is further configured to:
obtaining entities and relations in the first data by utilizing a knowledge extraction model obtained through pre-training;
and obtaining the first knowledge graph based on the entity and the relation in the first data.
Optionally, the processor 700 is further configured to:
acquiring annotation data in second data, wherein the second data is part of data in the first data, and the annotation data comprises an entity to be annotated and an annotation relation;
and carrying out model training based on the labeling data to obtain the knowledge extraction model.
Optionally, the processor 700 is further configured to:
performing entity matching on the entities in the first data by utilizing a pre-trained entity chain finger model;
And obtaining the first knowledge graph according to the matched entity and relation.
Optionally, the processor 700 is further configured to:
recording entity chain index annotation behaviors aiming at partial entities in the first data;
and performing model training based on the entity chain index annotation behavior to obtain the entity chain index model.
Optionally, the processor 700 is further configured to:
model training is carried out based on third data and the first knowledge graph to obtain an interactive factor recognition model, wherein the third data is part of data in the first data;
and identifying a target interaction factor from the first data by using the interaction factor identification model.
Optionally, the processor 700 is further configured to:
extracting a moving guest relation in the third data;
obtaining a marked interaction factor according to the entity and the relation included in the first knowledge graph and the moving guest relation in the third data, wherein the marked interaction factor is applicable to the first interaction scene;
and training a model based on the noted interactive factors to obtain the interactive factor identification model.
Optionally, the processor 700 is further configured to:
clustering the target interactive factors, and determining standard factor names of the interactive factors which are gathered into the same class, wherein a first factor name is the standard factor name of the interactive factors which are gathered into the same class, and the number of the interactive factors corresponding to the first factor name in the interactive factors which are gathered into the same class is the largest;
Replacing all other factor names except the standard factor name in the interactive factors collected into the same class with the standard factor name to obtain a quasi interactive factor;
and carrying out association combination on the quasi-interaction factors according to the time sequence of the quasi-interaction factors in the first data, and generating the interaction factor timing sequence map.
Optionally, the processor 700 is further configured to:
acquiring first-class service data, second-class service data and third-class service data in the first interaction scene, wherein the service efficiency corresponding to the first-class service data is higher than the service efficiency corresponding to the second-class service data, and the service efficiency corresponding to the second-class service data is higher than the service efficiency corresponding to the third-class service data;
for each type of service data, acquiring the probability of transferring the corresponding type of service data to the next node after mapping the corresponding type of service data to the interaction factor time sequence map, and outputting a service flow corresponding to the corresponding type of service data according to a path of the maximum probability;
if the difference value between any two of the first business process, the second business process and the third business process is larger than a first threshold value, the first business process is determined to be the target business process, wherein the first business process is a business process based on the first type business data output, the second business process is a business process based on the second type business data output, and the third business process is a business process based on the third type business data output.
Optionally, the processor 700 is further configured to:
mapping the corresponding type of service data into the interactive factor time sequence map;
counting each edge in the interaction factor time sequence map according to the transfer quantity among nodes based on the corresponding type of service data;
the count for each edge in the interaction factor timing graph is converted to a probability of transitioning from one node to the next.
The business process generating device of the embodiment of the invention firstly constructs a first knowledge graph based on first data, wherein the first data is business data generated in a first interaction scene; then, according to the first data and the first knowledge graph, a target interaction factor is obtained, wherein the target interaction factor is an interaction factor applicable to the first interaction scene, and the interaction factor is a word capable of enabling interaction behaviors to occur between interaction objects; according to the first data and the target interaction factor, an interaction factor time sequence map is obtained; and finally, generating a target business process according to the interactive factor time sequence map, thus carrying out automatic process construction on the interactive process in the specific field through data driving, and excavating an excellent business process from the interactive process, thereby achieving the purpose of improving the business efficiency.
The embodiment of the invention also provides a business process generating device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes each process in the business process generating method embodiment when executing the program and can achieve the same technical effect, and the repetition is avoided, so that the description is omitted.
The embodiment of the present invention also provides a computer readable storage medium, on which a computer program is stored, where the program when executed by a processor implements each process in the embodiment of the business process generating method described above, and the same technical effects can be achieved, and for avoiding repetition, a detailed description is omitted herein. Wherein the computer readable storage medium is selected from Read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), magnetic disk or optical disk.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, magnetic disk storage and optical storage, etc.) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block or blocks.
These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.
Claims (14)
1. A business process generation method, comprising:
constructing a first knowledge graph based on first data, wherein the first data is business data generated under a first interaction scene;
obtaining a target interaction factor according to the first data and the first knowledge graph, wherein the target interaction factor is an interaction factor applicable to the first interaction scene, and the interaction factor is a word capable of enabling interaction behaviors to occur between interaction objects;
According to the first data and the target interaction factor, an interaction factor time sequence map is obtained;
and generating a target business process according to the interaction factor time sequence map.
2. The method of claim 1, wherein constructing a first knowledge-graph based on the first data comprises:
obtaining entities and relations in the first data by utilizing a knowledge extraction model obtained through pre-training;
and obtaining the first knowledge graph based on the entity and the relation in the first data.
3. The method according to claim 2, wherein the method further comprises:
acquiring annotation data in second data, wherein the second data is part of data in the first data, and the annotation data comprises an entity to be annotated and an annotation relation;
and carrying out model training based on the labeling data to obtain the knowledge extraction model.
4. The method of claim 2, wherein the obtaining the first knowledge-graph based on the entities and relationships in the first data comprises:
performing entity matching on the entities in the first data by utilizing a pre-trained entity chain finger model;
And obtaining the first knowledge graph according to the matched entity and relation.
5. The method of claim 4, wherein the method further comprises:
recording entity chain index annotation behaviors aiming at partial entities in the first data;
and performing model training based on the entity chain index annotation behavior to obtain the entity chain index model.
6. The method of claim 1, wherein the obtaining the target interaction factor from the first data and the first knowledge-graph comprises:
model training is carried out based on third data and the first knowledge graph to obtain an interactive factor recognition model, wherein the third data is part of data in the first data;
and identifying a target interaction factor from the first data by using the interaction factor identification model.
7. The method of claim 6, wherein the model training based on the third data and the first knowledge-graph to obtain the interaction factor recognition model comprises:
extracting a moving guest relation in the third data;
obtaining a marked interaction factor according to the entity and the relation included in the first knowledge graph and the moving guest relation in the third data, wherein the marked interaction factor is applicable to the first interaction scene;
And training a model based on the noted interactive factors to obtain the interactive factor identification model.
8. The method of claim 1, wherein the obtaining an interaction factor timing graph from the first data and the target interaction factor comprises:
clustering the target interactive factors, and determining standard factor names of the interactive factors which are gathered into the same class, wherein a first factor name is the standard factor name of the interactive factors which are gathered into the same class, and the number of the interactive factors corresponding to the first factor name in the interactive factors which are gathered into the same class is the largest;
replacing all other factor names except the standard factor name in the interactive factors collected into the same class with the standard factor name to obtain a quasi interactive factor;
and carrying out association combination on the quasi-interaction factors according to the time sequence of the quasi-interaction factors in the first data, and generating the interaction factor timing sequence map.
9. The method of claim 1, wherein generating the target business process from the interaction factor timing graph comprises:
acquiring first-class service data, second-class service data and third-class service data in the first interaction scene, wherein the service efficiency corresponding to the first-class service data is higher than the service efficiency corresponding to the second-class service data, and the service efficiency corresponding to the second-class service data is higher than the service efficiency corresponding to the third-class service data;
For each type of service data, acquiring the probability of transferring the corresponding type of service data to the next node after mapping the corresponding type of service data to the interaction factor time sequence map, and outputting a service flow corresponding to the corresponding type of service data according to a path of the maximum probability;
if the difference value between any two of the first business process, the second business process and the third business process is larger than a first threshold value, the first business process is determined to be the target business process, wherein the first business process is a business process based on the first type business data output, the second business process is a business process based on the second type business data output, and the third business process is a business process based on the third type business data output.
10. The method of claim 9, wherein obtaining the probability of transitioning from one node to the next node after mapping the corresponding type of traffic data to the interaction factor timing graph comprises:
mapping the corresponding type of service data into the interactive factor time sequence map;
counting each edge in the interaction factor time sequence map according to the transfer quantity among nodes based on the corresponding type of service data;
The count for each edge in the interaction factor timing graph is converted to a probability of transitioning from one node to the next.
11. A business process generation apparatus, comprising:
the map construction module is used for constructing a first knowledge map based on first data, wherein the first data is business data generated in a first interaction scene;
the first processing module is used for obtaining a target interaction factor according to the first data and the first knowledge graph, wherein the target interaction factor is an interaction factor applicable to the first interaction scene, and the interaction factor is a word capable of enabling interaction behaviors to occur between interaction objects;
the second processing module is used for obtaining an interaction factor time sequence map according to the first data and the target interaction factor;
and the generating module is used for generating a target business process according to the interaction factor time sequence map.
12. A business process generating device comprising a processor and a transceiver, the transceiver receiving and transmitting data under the control of the processor, the processor being configured to:
constructing a first knowledge graph based on first data, wherein the first data is business data generated under a first interaction scene;
Obtaining a target interaction factor according to the first data and the first knowledge graph, wherein the target interaction factor is an interaction factor applicable to the first interaction scene, and the interaction factor is a word capable of enabling interaction behaviors to occur between interaction objects;
according to the first data and the target interaction factor, an interaction factor time sequence map is obtained;
and generating a target business process according to the interaction factor time sequence map.
13. A business process generation device comprising a memory, a processor and a program stored on the memory and executable on the processor; a business process generation method according to any one of claims 1 to 10, wherein the processor when executing the program.
14. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the business process generation method of any of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310460091.6A CN116167605B (en) | 2023-04-26 | 2023-04-26 | Business process generation method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310460091.6A CN116167605B (en) | 2023-04-26 | 2023-04-26 | Business process generation method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116167605A true CN116167605A (en) | 2023-05-26 |
| CN116167605B CN116167605B (en) | 2023-07-25 |
Family
ID=86413635
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310460091.6A Active CN116167605B (en) | 2023-04-26 | 2023-04-26 | Business process generation method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116167605B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117034019A (en) * | 2023-10-09 | 2023-11-10 | 腾讯科技（深圳）有限公司 | Service processing method and device, electronic equipment and storage medium |
| CN118014334A (en) * | 2024-04-08 | 2024-05-10 | 微神马科技（大连）有限公司 | Service recording method and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108804521A (en) * | 2018-04-27 | 2018-11-13 | 南京柯基数据科技有限公司 | A kind of answering method and agricultural encyclopaedia question answering system of knowledge based collection of illustrative plates |
| CN109697050A (en) * | 2019-01-07 | 2019-04-30 | 浙江大学 | A kind of Requirements description model design method of the knowledge based map towards electric business field |
| CN110162641A (en) * | 2019-05-17 | 2019-08-23 | 五竹科技(天津)有限公司 | Marketing method, device and storage medium based on speech enabled |
| CN110175240A (en) * | 2019-05-16 | 2019-08-27 | 五竹科技(天津)有限公司 | Construction method, device and the storage medium of knowledge mapping relevant to outgoing call process |
| CN111177322A (en) * | 2019-12-30 | 2020-05-19 | 成都数之联科技有限公司 | Ontology model construction method of domain knowledge graph |
| CN114020929A (en) * | 2021-11-03 | 2022-02-08 | 北京航空航天大学 | Intelligent education system platform design method based on course knowledge graph |
| CN114090755A (en) * | 2021-11-30 | 2022-02-25 | 平安科技（深圳）有限公司 | Reply sentence determination method and device based on knowledge graph and electronic equipment |
| CN115391552A (en) * | 2022-08-19 | 2022-11-25 | 东软集团股份有限公司 | Knowledge graph construction method and device, storage medium and electronic equipment |
-
2023
- 2023-04-26 CN CN202310460091.6A patent/CN116167605B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108804521A (en) * | 2018-04-27 | 2018-11-13 | 南京柯基数据科技有限公司 | A kind of answering method and agricultural encyclopaedia question answering system of knowledge based collection of illustrative plates |
| CN109697050A (en) * | 2019-01-07 | 2019-04-30 | 浙江大学 | A kind of Requirements description model design method of the knowledge based map towards electric business field |
| CN110175240A (en) * | 2019-05-16 | 2019-08-27 | 五竹科技(天津)有限公司 | Construction method, device and the storage medium of knowledge mapping relevant to outgoing call process |
| CN110162641A (en) * | 2019-05-17 | 2019-08-23 | 五竹科技(天津)有限公司 | Marketing method, device and storage medium based on speech enabled |
| CN111177322A (en) * | 2019-12-30 | 2020-05-19 | 成都数之联科技有限公司 | Ontology model construction method of domain knowledge graph |
| CN114020929A (en) * | 2021-11-03 | 2022-02-08 | 北京航空航天大学 | Intelligent education system platform design method based on course knowledge graph |
| CN114090755A (en) * | 2021-11-30 | 2022-02-25 | 平安科技（深圳）有限公司 | Reply sentence determination method and device based on knowledge graph and electronic equipment |
| CN115391552A (en) * | 2022-08-19 | 2022-11-25 | 东软集团股份有限公司 | Knowledge graph construction method and device, storage medium and electronic equipment |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117034019A (en) * | 2023-10-09 | 2023-11-10 | 腾讯科技（深圳）有限公司 | Service processing method and device, electronic equipment and storage medium |
| CN117034019B (en) * | 2023-10-09 | 2024-01-09 | 腾讯科技（深圳）有限公司 | Service processing method and device, electronic equipment and storage medium |
| CN118014334A (en) * | 2024-04-08 | 2024-05-10 | 微神马科技（大连）有限公司 | Service recording method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116167605B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116167605B (en) | Business process generation method, device, equipment and medium | |
| CN110245496B (en) | Source code vulnerability detection method and detector and training method and system thereof | |
| CN111159249A (en) | Target identification method, device and system based on knowledge graph and storage medium | |
| CN106294520B (en) | Carry out identified relationships using the information extracted from document | |
| CN111930956B (en) | Multi-innovation method recommendation and flow driving integrated system adopting knowledge graph | |
| CN113742488B (en) | Embedded knowledge graph completion method and device based on multitask learning | |
| KR102634624B1 (en) | Methods and systems to generate the process models of plant procedures | |
| CN117271767B (en) | Operation and maintenance knowledge base establishing method based on multiple intelligent agents | |
| Liu et al. | Behavior2vector: Embedding users’ personalized travel behavior to vector | |
| Newberry et al. | Constructing causal loop diagrams from large interview data sets | |
| CN112948510A (en) | Construction method of knowledge graph in media industry | |
| Li et al. | A new fuzzy ontology development methodology (FODM) proposal | |
| CN110909174A (en) | Knowledge graph-based method for improving entity link in simple question answering | |
| CN116049376A (en) | Method, device and system for retrieving and replying information and creating knowledge | |
| Banerjee et al. | Neural language model based intelligent semantic information retrieval on NCDOT projects for knowledge management | |
| Chen et al. | Text-based requirements preprocessing using nature language processing techniques | |
| Wang et al. | Using workflow patterns to model and validate service requirements | |
| De Vries | Reducing ambiguity during enterprise design | |
| CN109754159A (en) | A kind of information extracting method and system of operation of power networks log | |
| Chen et al. | Robust and Efficient Annotation based on Ontology Evolution for Deep Web Data. | |
| Xu et al. | Research on intelligent campus and visual teaching system based on Internet of things | |
| CN117827650A (en) | Integrated equipment testing and diagnosing method based on interface model intelligent mining | |
| Buis | Applying intelligence amplification to the problem of schema matching | |
| Svensson et al. | Expert Knowledge Elicitation for Machine Learning: Insights from a Survey and Industrial Case Study | |
| Wasserfuhr | A Literature Review of Methods, Approaches and Tools to Automate the Process of Systematic Literature Reviews |
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 | ||
| CP03 | Change of name, title or address |
Address after: Room 228, 2nd Floor, No. 5 Guanghua Road, Zhangjiawan Town, Tongzhou District, Beijing, 101113 Patentee after: BEIJING ZHONGGUANCUN KEJIN TECHNOLOGY Co.,Ltd. Country or region after: China Address before: 130, 1st Floor, Building 5, Courtyard 1, Shangdi Fourth Street, Haidian District, Beijing, 100085 Patentee before: BEIJING ZHONGGUANCUN KEJIN TECHNOLOGY Co.,Ltd. Country or region before: China |