CN113887941A - Business process generation method and device, electronic equipment and medium - Google Patents
Business process generation method and device, electronic equipment and medium Download PDFInfo
- Publication number
- CN113887941A CN113887941A CN202111158189.3A CN202111158189A CN113887941A CN 113887941 A CN113887941 A CN 113887941A CN 202111158189 A CN202111158189 A CN 202111158189A CN 113887941 A CN113887941 A CN 113887941A
- Authority
- CN
- China
- Prior art keywords
- service
- business
- flow
- business process
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 340
- 230000008569 process Effects 0.000 title claims abstract description 301
- 239000003795 chemical substances by application Substances 0.000 claims description 130
- 239000013598 vector Substances 0.000 claims description 38
- 238000010586 diagram Methods 0.000 claims description 36
- 230000006870 function Effects 0.000 claims description 36
- 238000012545 processing Methods 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 11
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 9
- 238000004806 packaging method and process Methods 0.000 claims description 8
- 239000000126 substance Substances 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 12
- 238000011161 development Methods 0.000 abstract description 11
- 238000013473 artificial intelligence Methods 0.000 abstract description 7
- 238000007726 management method Methods 0.000 description 19
- 230000018109 developmental process Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 238000012163 sequencing technique Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000000712 assembly Effects 0.000 description 2
- 238000000429 assembly Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 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
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/20—Software design
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)
- Software Systems (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an artificial intelligence technology, and discloses a business process generation method, which comprises the following steps: the method comprises the steps of obtaining agent service information, building an agent service process according to the agent service information, building a business component set according to process nodes in the agent service process, building a business process library by using the business component set, obtaining a user problem text, searching a candidate process set matched with the user problem text from the business process library, carrying out intention identification on the user problem text, and selecting a plurality of process nodes from the candidate process set according to the intention identification result to generate the business process. In addition, the invention also relates to a block chain technology, and the service flow can be stored in the node of the block chain. The invention also provides a business process generation device, electronic equipment and a computer readable storage medium. The invention can solve the problems of business process redundancy and large development amount caused by the business process redundancy.
Description
Technical Field
The present invention relates to the field of artificial intelligence technologies, and in particular, to a method and an apparatus for generating a business process, an electronic device, and a computer-readable storage medium.
Background
The user service system is an important component of a company, and can provide consultation for users of the company, help the users to solve problems and serve as a communication bridge between the users and internal departments of the company. The good user service system can improve the company image, increase the user viscosity, and avoid complaints of the user in other fields and the like.
In a conventional user service system, functions in related business fields are generally developed by respective IT teams, and are intensively used by customer service staff. Due to the wide business field of companies, a general user service system has more menus and functions, and based on the situation, much inconvenience is brought. Specific inconveniences are reflected in: (1) due to the fact that the business process is redundant, users of the user service system need to train for a long time to correctly and skillfully master the use of the system, and large cost is brought to the implementation of the system; (2) in order to prevent insufficient received information in the user service system, too much stacking information exists, however, the too much information can increase the identification difficulty of users, so that the business process in practical application is more redundant, and the development amount of the user service system is increased.
Disclosure of Invention
The invention provides a business process generation method, a business process generation device and a computer readable storage medium, and mainly aims to solve the problems of business process redundancy and large development amount caused by the business process redundancy.
In order to achieve the above object, a method for generating a business process provided by the present invention includes:
acquiring agent service information, constructing a flow tree diagram according to the agent service information, and acquiring an agent service flow based on the flow tree diagram;
constructing a business component set according to the process nodes in the agent service process;
constructing a business process library by utilizing the business component set;
acquiring a user question text, and searching a candidate flow set matched with the user question text from the business flow library;
and performing intention recognition on the user question text by using a pre-constructed semantic recognition model, and selecting a plurality of process nodes from the candidate process set according to the result of the intention recognition to generate a business process.
Optionally, the constructing a flow tree according to the agent service information, and obtaining an agent service flow based on the flow tree, includes:
classifying users involved in the seat service information to obtain classified users;
determining the agents and service systems related to the classified users;
and constructing a flow tree diagram by taking the classified users as first nodes, the agents as second nodes and the service system as third nodes, and determining branches formed by different nodes in the flow tree diagram as the agent service flow.
Optionally, the constructing a business component set according to the process node in the agent service process includes:
determining a business system corresponding to an agent in the agent service process;
packaging the service system into a service component according to a preset frame specification;
and summarizing the service components of the service system corresponding to all the seats to obtain the service component set.
Optionally, encapsulating the service system into a service component according to a preset framework specification includes:
generating a service component name according to the function of the service system;
and packaging the reference code of the service system and the name of the service component according to the frame specification to obtain the service component.
Optionally, the constructing a business process library by using the business component set includes:
setting the process names of different agent service processes in the process tree diagram;
extracting service components corresponding to all the agents in the agent service flow from the service component set, and taking the extracted service components as flow nodes;
and summarizing the process names and the process nodes of all the agents to obtain the business process library.
Optionally, the searching for the candidate process set matching with the user question text from the business process library includes:
performing word segmentation processing and stop word removal processing on the user question text to obtain one or more keywords;
and searching the service components in the service flow library by taking the keywords as indexes, and acquiring all candidate flow nodes fed back by the indexes to obtain the candidate flow set.
Optionally, the performing intent recognition on the user question text by using a pre-constructed semantic recognition model, and selecting a plurality of process nodes from the candidate process set according to a result of the intent recognition to generate a business process includes:
sequentially selecting the business component name of any flow node in the candidate flow set as a target text, and performing word segmentation processing on the user problem text and the target text by using the semantic recognition model to obtain two word vectors;
semantic matching is carried out on the two word vectors by utilizing the semantic recognition model respectively to obtain a semantic vector pair;
calculating the similarity of the semantic vector pairs to obtain node similarity, and selecting all process nodes with the node similarity more than or equal to a preset similarity threshold as a target process node set;
and arranging the process nodes in the target process node set based on the node similarity to obtain the business process.
In order to solve the above problem, the present invention further provides a business process generating apparatus, including:
the agent service flow construction module is used for acquiring agent service information, constructing a flow tree diagram according to the agent service information, and obtaining an agent service flow based on the flow tree diagram;
the business component construction module is used for constructing a business component set according to the process nodes in the agent service process;
the business process library construction module is used for constructing a business process library by utilizing the business component set;
the candidate process matching module is used for acquiring a user problem text and searching a candidate process set matched with the user problem text from the business process library;
and the business process generation module is used for performing intention recognition on the user question text by utilizing a pre-constructed semantic recognition model, and selecting a plurality of process nodes from the candidate process set according to the intention recognition result to generate a business process.
In order to solve the above problem, the present invention also provides an electronic device, including:
a memory storing at least one computer program; and
and the processor executes the computer program stored in the memory to realize the business process generation method.
In order to solve the above problem, the present invention further provides a computer-readable storage medium, in which at least one computer program is stored, and the at least one computer program is executed by a processor in an electronic device to implement the business process generating method described above.
According to the invention, the business component set is constructed through the process nodes in the agent service process, each process node has a corresponding business component, and customer service personnel can perform corresponding services through the functions of the business components without receiving other redundant information, so that the information in the process of processing the business process is more simplified, and the problem of business process redundancy can be solved. Meanwhile, by means of intention recognition of the user question text, a more accurate business process can be further generated, and therefore the service rate and accuracy of customer service personnel in use are improved. In addition, through the embodiment, only the business components corresponding to the process nodes need to be developed, so that the development amount of the user service system is greatly reduced. Therefore, the business process generation method, the business process generation device, the electronic equipment and the computer readable storage medium provided by the invention can solve the problems of business process redundancy and large development amount caused by the business process redundancy.
Drawings
Fig. 1 is a schematic flow chart of a business process generating method according to an embodiment of the present invention;
fig. 2 is a functional block diagram of a business process generating apparatus according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device for implementing the business process generating method according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the application provides a business process generation method. The execution subject of the business process generation method includes, but is not limited to, at least one of electronic devices that can be configured to execute the method provided by the embodiments of the present application, such as a server, a terminal, and the like. In other words, the business process generation method may be executed by software or hardware installed in the terminal device or the server device, and the software may be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.
Fig. 1 is a schematic flow chart of a business process generating method according to an embodiment of the present invention. In this embodiment, the business process generating method includes:
s1, obtaining the seat service information, constructing a flow tree diagram according to the seat service information, and obtaining the seat service flow based on the flow tree diagram.
In the embodiment of the invention, the agent service information refers to information of agent personnel (namely agents) in the customer service system when the agents service users, and comprises user appeal, related system functions, solutions and the like. The flow tree diagram reflects the relationship among the user, the seat and the service system used by the seat.
Specifically, the establishing of the agent service flow according to the agent service information includes:
classifying users involved in the seat service information to obtain classified users;
determining the agents and service systems related to the classified users;
and constructing a flow tree diagram by taking the classified users as first nodes, the agents as second nodes and the service system as third nodes, and determining branches formed by different nodes in the flow tree diagram as the agent service flow.
For example, when a user consults a nearby site, the user is determined to be a consultation site user, an agent needs to determine the location of the user, inquire several closest sites of the user in a site management system, determine the business hours of the sites, and finally send appropriate site information to the user through a short message, wherein the related business systems comprise a position positioning system, a site management system, an information sending system and the like.
In the embodiment of the invention, users of each seat service and the service system used by the users can be sorted out from the seat service information by service process personnel, and meanwhile, the seat service processes required by different users are displayed by utilizing the dendrogram, so that the method is more intuitive and is easy to maintain.
In an optional embodiment of the invention, users of different categories are determined according to user appeal in the agent service information, and the flow chart is constructed on the basis of the users of different categories, so that a more accurate agent service flow can be arranged.
For example, if the user a is a user at a consultation website, and the user a is served by using the website management system through the agent a, the agent service process corresponding to the user at the consultation website is as follows: consultation website users → agents → inquiry website management systems.
S2, constructing a business component set according to the process nodes in the agent service process.
In the embodiment of the invention, the service component set refers to components capable of independently completing the functions of the original service system, and comprises a card component, a note component and the like. For example, taking a card assembly as an example, the functions of the original different service systems are refined into one card, and each independent function becomes an independent card.
Specifically, the constructing a business component set according to the process node in the agent service process includes:
determining a business system corresponding to an agent in the agent service process;
packaging the service system into a service component according to a preset frame specification;
and summarizing the service components of the service system corresponding to all the seats to obtain the service component set.
In the embodiment of the invention, by taking the service component as the card component as an example, the seat personnel in the seat service process can correspond to different service systems, the functions of each service system are packaged into the card component, and the user is served through the process obtained by arranging and combining the card components, so that the service process can be simplified, and the efficiency of the seat service user can be improved.
In an optional embodiment of the present invention, the encapsulating the service system into a service component according to a preset frame specification includes:
generating a service component name according to the function of the service system;
and packaging the reference code of the service system and the name of the service component according to the frame specification to obtain the service component.
The preset frame specification may be in the component form of vue frame. Taking a service system as an example of a network management system, the network management system mainly comprises two functions: the positioning and inquiry can be subdivided into a network point positioning card and a network point inquiry card, codes for introducing two functions are respectively packaged under the corresponding cards, and a network point management system can be subdivided into two card assemblies according to the functions.
In the embodiment of the invention, because the service component is designed according to the unified specification (such as the card component), the agent does not need to receive excessive redundant information in the process of serving the user, each service is the simplest function, and the service efficiency is improved. Meanwhile, the seat does not need to train all services as before, the training time of the seat is greatly reduced, the same processing process is carried out according to the card assembly when all the seats serve users, and the users cannot feel that different seats have different processes, so that the service process is standardized, and the user experience is improved. And only the business components need to be developed, so that the development amount of the user service system is greatly reduced.
And S3, constructing a business process library by utilizing the business component set.
In the embodiment of the present invention, the business process library is constructed according to the agent service process and the business component set, and includes: a network point position consultation process, a network point information consultation process and the like.
Specifically, the constructing a business process library by using the business component set includes:
setting the process names of different agent service processes in the process tree diagram;
extracting service components corresponding to all the agents in the agent service flow from the service component set, and taking the extracted service components as flow nodes;
and summarizing the process names and the process nodes of all the agents to obtain the business process library.
In the embodiment of the invention, by taking the card assembly as an example, each agent in the agent service process can use a plurality of service systems to serve users, the service systems are split into one card assembly according to functions, and the original service process can be further refined by taking each card assembly as a process node, so that the efficiency of the agent personnel to serve the users is improved.
In an optional embodiment of the present invention, a key-value pair (key-value) may be used in the service flow library, where the flow name is used as a key value, the component corresponding to the flow node is used as a value, and a mapping relationship between the flow name and the component corresponding to the flow node is established, so as to implement one-to-one correspondence between the flow name and the flow node, and improve a flow search rate.
S4, obtaining the user question text, and searching the candidate process set matched with the user question text from the business process library.
In the embodiment of the present invention, the question text may be input by the user, or selected by the user from a question list. Such as "nearest business outlets", etc.
In detail, the searching the candidate process set matched with the user question text from the business process library includes:
performing word segmentation processing and stop word removal processing on the user question text to obtain one or more keywords;
and searching the service components in the service flow library by taking the keywords as indexes, and acquiring all candidate flow nodes fed back by the indexes to obtain the candidate flow set.
In an optional embodiment of the present invention, a preset language processing algorithm may be used to perform word segmentation and stop word removal processing on the user question text and extract keywords, where the preset language processing algorithm may be a TextRank algorithm, a keyword extraction algorithm based on semantics, and the like, where a stop word removal rule in a chinese corpus may be "also" or "yet" removal. Meanwhile, the search can be performed through a preset query engine, which can be an ES (elastic search) data query engine, and the ES data query engine is a distributed, highly-extended and highly-real-time search and data analysis engine, and can conveniently enable a large amount of data to have the capabilities of search, analysis and exploration.
And S5, performing intention recognition on the user question text by using a pre-constructed semantic recognition model, and selecting a plurality of process nodes from the candidate process set according to the result of the intention recognition to generate a business process.
In the embodiment of the invention, the intention of the problem text of the user is further identified, so that the accuracy of flow selection is improved.
Specifically, the performing intention recognition on the user question text by using a pre-constructed semantic recognition model, and selecting a plurality of process nodes from the candidate process set according to the result of intention recognition to generate a business process includes:
sequentially selecting the business component name of any flow node in the candidate flow set as a target text, and performing word segmentation processing on the user problem text and the target text by using the semantic recognition model to obtain two word vectors;
semantic matching is carried out on the two word vectors by utilizing the semantic recognition model respectively to obtain a semantic vector pair;
calculating the similarity of the semantic vector pairs to obtain node similarity, and selecting all process nodes with the node similarity more than or equal to a preset similarity threshold as a target process node set;
and arranging the process nodes in the target process node set based on the node similarity to obtain the business process.
In an optional embodiment of the present invention, the process nodes in the target process node set may be arranged from high to low according to the value of the node similarity, so as to obtain the service process.
Further, the calculating the similarity of the semantic vector pair includes:
calculating the cosine similarity of the semantic vector pair by using the following formula:
R(Q、D)＝cosine(yQ、yD)
q, D are the question text and the target text of the user, respectively, (y)Q、yD) For matched pairs of semantic vectors, yQ、yDAnd semantic vectors corresponding to the user question text and the target text respectively.
In the embodiment of the present invention, the pre-constructed Semantic recognition model may be a DSSM (Deep Structured Semantic Models). The DSSM comprises an input layer, a presentation layer and a matching layer, wherein the input layer obtains word vectors by dividing sentences, the word vectors are mapped into a vector space (namely the presentation layer), the presentation layer adopts a BOW (bag of words) mode, position information of the word vectors is discarded, words in the whole sentence are put in a bag without sequencing, then sequencing is carried out according to the weight of each word vector, the semantic vectors (which can be 128-dimensional) are obtained, and the matching layer calculates the semantic similarity (which can be cosine similarity) of the semantic vectors to serve as a matching score of any flow node in the user problem text and the candidate flow set.
According to the invention, the corresponding process nodes are matched after the intention of the user is identified, so that the accuracy of process matching can be improved, and a more accurate business process is generated.
In another optional embodiment of the present invention, after the selecting a plurality of process nodes from the candidate process set according to the result of the intent recognition to generate a business process, the method further includes:
recording the use information of each service component in the service flow;
and adjusting the service components of different seats in the service flow library according to the use information.
In the embodiment of the invention, the service components corresponding to each agent in the service flow library can be intelligently added or deleted by collecting the service conditions of each service component (such as a card component) in different service flows and the components used by the agent and not in the service flows on line in the using process of the agent, so that the service flow can be continuously optimized.
For example, when the agent a performs after-sales service on the user, a service flow generated according to the intention recognition on the user is a-b-c, wherein a service component in the node b does not belong to the agent a in the service flow library, and the service component in the node b is added as the service component corresponding to the agent a in the service flow library.
According to the invention, the business component set is constructed through the process nodes in the agent service process, each process node has a corresponding business component, and customer service personnel can perform corresponding services through the functions of the business components without receiving other redundant information, so that the information in the process of processing the business process is more simplified, and the problem of business process redundancy can be solved. Meanwhile, by means of intention recognition of the user question text, a more accurate business process can be further generated, and therefore the service rate and accuracy of customer service personnel in use are improved. In addition, through the embodiment, only the business components corresponding to the process nodes need to be developed, so that the development amount of the user service system is greatly reduced. Therefore, the business process generation method provided by the invention can solve the problems of business process redundancy and large development amount caused by the business process redundancy.
Fig. 2 is a functional block diagram of a business process generating apparatus according to an embodiment of the present invention.
The business process generating apparatus 100 of the present invention may be installed in an electronic device. According to the implemented functions, the business process generating apparatus 100 may include an agent service process constructing module 101, a business component constructing module 102, a business process library constructing module 103, a candidate process matching module 104, and a business process generating module 105. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the agent service flow construction module 101 is configured to obtain agent service information, construct a flow tree diagram according to the agent service information, and obtain an agent service flow based on the flow tree diagram;
the business component construction module 102 is configured to construct a business component set according to the process nodes in the agent service process;
the business process library construction module 103 is configured to construct a business process library by using the business component set;
the candidate process matching module 104 is configured to obtain a user question text, and search a candidate process set matched with the user question text from the business process library;
the business process generating module 105 is configured to perform intent recognition on the user question text by using a pre-constructed semantic recognition model, and select a plurality of process nodes from the candidate process set according to a result of the intent recognition to generate a business process.
In detail, the specific implementation of each module of the business process generating apparatus 100 is as follows:
step one, acquiring agent service information, constructing a flow tree diagram according to the agent service information, and acquiring an agent service flow based on the flow tree diagram.
In the embodiment of the invention, the agent service information refers to information of agent personnel (namely agents) in the customer service system when the agents service users, and comprises user appeal, related system functions, solutions and the like. The flow tree diagram reflects the relationship among the user, the seat and the service system used by the seat.
Specifically, the establishing of the agent service flow according to the agent service information includes:
classifying users involved in the seat service information to obtain classified users;
determining the agents and service systems related to the classified users;
and constructing a flow tree diagram by taking the classified users as first nodes, the agents as second nodes and the service system as third nodes, and determining branches formed by different nodes in the flow tree diagram as the agent service flow.
For example, when a user consults a nearby site, the user is determined to be a consultation site user, an agent needs to determine the location of the user, inquire several closest sites of the user in a site management system, determine the business hours of the sites, and finally send appropriate site information to the user through a short message, wherein the related business systems comprise a position positioning system, a site management system, an information sending system and the like.
In the embodiment of the invention, users of each seat service and the service system used by the users can be sorted out from the seat service information by service process personnel, and meanwhile, the seat service processes required by different users are displayed by utilizing the dendrogram, so that the method is more intuitive and is easy to maintain.
In an optional embodiment of the invention, users of different categories are determined according to user appeal in the agent service information, and the flow chart is constructed on the basis of the users of different categories, so that a more accurate agent service flow can be arranged.
For example, if the user a is a user at a consultation website, and the user a is served by using the website management system through the agent a, the agent service process corresponding to the user at the consultation website is as follows: consultation website users → agents → inquiry website management systems.
And step two, constructing a business component set according to the process nodes in the agent service process.
In the embodiment of the invention, the service component set refers to components capable of independently completing the functions of the original service system, and comprises a card component, a note component and the like. For example, taking a card assembly as an example, the functions of the original different service systems are refined into one card, and each independent function becomes an independent card.
Specifically, the constructing a business component set according to the process node in the agent service process includes:
determining a business system corresponding to an agent in the agent service process;
packaging the service system into a service component according to a preset frame specification;
and summarizing the service components of the service system corresponding to all the seats to obtain the service component set.
In the embodiment of the invention, by taking the service component as the card component as an example, the seat personnel in the seat service process can correspond to different service systems, the functions of each service system are packaged into the card component, and the user is served through the process obtained by arranging and combining the card components, so that the service process can be simplified, and the efficiency of the seat service user can be improved.
In an optional embodiment of the present invention, the encapsulating the service system into a service component according to a preset frame specification includes:
generating a service component name according to the function of the service system;
and packaging the reference code of the service system and the name of the service component according to the frame specification to obtain the service component.
The preset frame specification may be in the component form of vue frame. Taking a service system as an example of a network management system, the network management system mainly comprises two functions: the positioning and inquiry can be subdivided into a network point positioning card and a network point inquiry card, codes for introducing two functions are respectively packaged under the corresponding cards, and a network point management system can be subdivided into two card assemblies according to the functions.
In the embodiment of the invention, because the service component is designed according to the unified specification (such as the card component), the agent does not need to receive excessive redundant information in the process of serving the user, each service is the simplest function, and the service efficiency is improved. Meanwhile, the seat does not need to train all services as before, the training time of the seat is greatly reduced, the same processing process is carried out according to the card assembly when all the seats serve users, and the users cannot feel that different seats have different processes, so that the service process is standardized, and the user experience is improved. And only the business components need to be developed, so that the development amount of the user service system is greatly reduced.
And step three, constructing a business process library by utilizing the business component set.
In the embodiment of the present invention, the business process library is constructed according to the agent service process and the business component set, and includes: a network point position consultation process, a network point information consultation process and the like.
Specifically, the constructing a business process library by using the business component set includes:
setting the process names of different agent service processes in the process tree diagram;
extracting service components corresponding to all the agents in the agent service flow from the service component set, and taking the extracted service components as flow nodes;
and summarizing the process names and the process nodes of all the agents to obtain the business process library.
In the embodiment of the invention, by taking the card assembly as an example, each agent in the agent service process can use a plurality of service systems to serve users, the service systems are split into one card assembly according to functions, and the original service process can be further refined by taking each card assembly as a process node, so that the efficiency of the agent personnel to serve the users is improved.
In an optional embodiment of the present invention, a key-value pair (key-value) may be used in the service flow library, where the flow name is used as a key value, the component corresponding to the flow node is used as a value, and a mapping relationship between the flow name and the component corresponding to the flow node is established, so as to implement one-to-one correspondence between the flow name and the flow node, and improve a flow search rate.
And step four, acquiring a user question text, and searching a candidate flow set matched with the user question text from the business flow library.
In the embodiment of the present invention, the question text may be input by the user, or selected by the user from a question list. Such as "nearest business outlets", etc.
In detail, the searching the candidate process set matched with the user question text from the business process library includes:
performing word segmentation processing and stop word removal processing on the user question text to obtain one or more keywords;
and searching the service components in the service flow library by taking the keywords as indexes, and acquiring all candidate flow nodes fed back by the indexes to obtain the candidate flow set.
In an optional embodiment of the present invention, a preset language processing algorithm may be used to perform word segmentation and stop word removal processing on the user question text and extract keywords, where the preset language processing algorithm may be a TextRank algorithm, a keyword extraction algorithm based on semantics, and the like, where a stop word removal rule in a chinese corpus may be "also" or "yet" removal. Meanwhile, the search can be performed through a preset query engine, which can be an ES (elastic search) data query engine, and the ES data query engine is a distributed, highly-extended and highly-real-time search and data analysis engine, and can conveniently enable a large amount of data to have the capabilities of search, analysis and exploration.
And fifthly, performing intention recognition on the user question text by using a pre-constructed semantic recognition model, and selecting a plurality of process nodes from the candidate process set according to the result of the intention recognition to generate a business process.
In the embodiment of the invention, the intention of the problem text of the user is further identified, so that the accuracy of flow selection is improved.
Specifically, the performing intention recognition on the user question text by using a pre-constructed semantic recognition model, and selecting a plurality of process nodes from the candidate process set according to the result of intention recognition to generate a business process includes:
sequentially selecting the business component name of any flow node in the candidate flow set as a target text, and performing word segmentation processing on the user problem text and the target text by using the semantic recognition model to obtain two word vectors;
semantic matching is carried out on the two word vectors by utilizing the semantic recognition model respectively to obtain a semantic vector pair;
calculating the similarity of the semantic vector pairs to obtain node similarity, and selecting all process nodes with the node similarity more than or equal to a preset similarity threshold as a target process node set;
and arranging the process nodes in the target process node set based on the node similarity to obtain the business process.
In an optional embodiment of the present invention, the process nodes in the target process node set may be arranged from high to low according to the value of the node similarity, so as to obtain the service process.
Further, the calculating the similarity of the semantic vector pair includes:
calculating the cosine similarity of the semantic vector pair by using the following formula:
R(Q、D)＝cosine(yQ、yD)
q, D are the question text and the target text of the user, respectively, (y)Q、yD) For matched pairs of semantic vectors, yQ、yDAnd semantic vectors corresponding to the user question text and the target text respectively.
In the embodiment of the present invention, the pre-constructed Semantic recognition model may be a DSSM (Deep Structured Semantic Models). The DSSM comprises an input layer, a presentation layer and a matching layer, wherein the input layer obtains word vectors by dividing sentences, the word vectors are mapped into a vector space (namely the presentation layer), the presentation layer adopts a BOW (bag of words) mode, position information of the word vectors is discarded, words in the whole sentence are put in a bag without sequencing, then sequencing is carried out according to the weight of each word vector, the semantic vectors (which can be 128-dimensional) are obtained, and the matching layer calculates the semantic similarity (which can be cosine similarity) of the semantic vectors to serve as a matching score of any flow node in the user problem text and the candidate flow set.
According to the invention, the corresponding process nodes are matched after the intention of the user is identified, so that the accuracy of process matching can be improved, and a more accurate business process is generated.
In another optional embodiment of the present invention, after the selecting a plurality of process nodes from the candidate process set according to the result of the intent recognition to generate a business process, the method further includes:
recording the use information of each service component in the service flow;
and adjusting the service components of different seats in the service flow library according to the use information.
In the embodiment of the invention, the service components corresponding to each agent in the service flow library can be intelligently added or deleted by collecting the service conditions of each service component (such as a card component) in different service flows and the components used by the agent and not in the service flows on line in the using process of the agent, so that the service flow can be continuously optimized.
For example, when the agent a performs after-sales service on the user, a service flow generated according to the intention recognition on the user is a-b-c, wherein a service component in the node b does not belong to the agent a in the service flow library, and the service component in the node b is added as the service component corresponding to the agent a in the service flow library.
According to the invention, the business component set is constructed through the process nodes in the agent service process, each process node has a corresponding business component, and customer service personnel can perform corresponding services through the functions of the business components without receiving other redundant information, so that the information in the process of processing the business process is more simplified, and the problem of business process redundancy can be solved. Meanwhile, by means of intention recognition of the user question text, a more accurate business process can be further generated, and therefore the service rate and accuracy of customer service personnel in use are improved. In addition, through the embodiment, only the business components corresponding to the process nodes need to be developed, so that the development amount of the user service system is greatly reduced. Therefore, the business process generating device provided by the invention can solve the problems of business process redundancy and large development amount caused by the business process redundancy.
Fig. 3 is a schematic structural diagram of an electronic device for implementing a business process generating method according to an embodiment of the present invention.
The electronic device may include a processor 10, a memory 11, a communication interface 12 and a bus 13, and may further include a computer program, such as a business process generating program, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, for example a removable hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used to store not only application software installed in the electronic device and various types of data, such as codes of a business process generating program, but also temporarily store data that has been output or will be output.
The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device by running or executing programs or modules (e.g., a business process generating program, etc.) stored in the memory 11 and calling data stored in the memory 11.
The communication interface 12 is used for communication between the electronic device and other devices, and includes a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which are typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.
The bus 13 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus 13 may be divided into an address bus, a data bus, a control bus, etc. The bus 13 is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
Fig. 3 shows only an electronic device having components, and those skilled in the art will appreciate that the structure shown in fig. 3 does not constitute a limitation of the electronic device, and may include fewer or more components than those shown, or some components may be combined, or a different arrangement of components.
For example, although not shown, the electronic device may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management and the like are realized through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
Further, the electronic device may further include a network interface, and optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a bluetooth interface, etc.), which are generally used to establish a communication connection between the electronic device and other electronic devices.
Optionally, the electronic device may further comprise a user interface, which may be a Display (Display), an input unit (such as a Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The business process generating program stored in the memory 11 of the electronic device is a combination of a plurality of instructions, and when running in the processor 10, can realize:
acquiring agent service information, constructing a flow tree diagram according to the agent service information, and acquiring an agent service flow based on the flow tree diagram;
constructing a business component set according to the process nodes in the agent service process;
constructing a business process library by utilizing the business component set;
acquiring a user question text, and searching a candidate flow set matched with the user question text from the business flow library;
and performing intention recognition on the user question text by using a pre-constructed semantic recognition model, and selecting a plurality of process nodes from the candidate process set according to the result of the intention recognition to generate a business process.
Specifically, the specific implementation method of the processor 10 for the instruction may refer to the description of the relevant steps in the embodiment corresponding to fig. 1, which is not described herein again.
Further, the electronic device integrated module/unit, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device, may implement:
acquiring agent service information, constructing a flow tree diagram according to the agent service information, and acquiring an agent service flow based on the flow tree diagram;
constructing a business component set according to the process nodes in the agent service process;
constructing a business process library by utilizing the business component set;
acquiring a user question text, and searching a candidate flow set matched with the user question text from the business flow library;
and performing intention recognition on the user question text by using a pre-constructed semantic recognition model, and selecting a plurality of process nodes from the candidate process set according to the result of the intention recognition to generate a business process.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A business process generation method, the method comprising:
acquiring agent service information, constructing a flow tree diagram according to the agent service information, and acquiring an agent service flow based on the flow tree diagram;
constructing a business component set according to the process nodes in the agent service process;
constructing a business process library by utilizing the business component set;
acquiring a user question text, and searching a candidate flow set matched with the user question text from the business flow library;
and performing intention recognition on the user question text by using a pre-constructed semantic recognition model, and selecting a plurality of process nodes from the candidate process set according to the result of the intention recognition to generate a business process.
2. The business process generating method of claim 1, wherein said constructing a process tree according to said agent service information and obtaining an agent service process based on said process tree comprises:
classifying users involved in the seat service information to obtain classified users;
determining the agents and service systems related to the classified users;
and constructing a flow tree diagram by taking the classified users as first nodes, the agents as second nodes and the service system as third nodes, and determining branches formed by different nodes in the flow tree diagram as the agent service flow.
3. The business process generation method of claim 1, wherein said building a set of business components from process nodes in said agent service process comprises:
determining a business system corresponding to an agent in the agent service process;
packaging the service system into a service component according to a preset frame specification;
and summarizing the service components of the service system corresponding to all the seats to obtain the service component set.
4. The business process generation method of claim 3, wherein said encapsulating said business system into business components according to a preset framework specification comprises:
generating a service component name according to the function of the service system;
and packaging the reference code of the service system and the name of the service component according to the frame specification to obtain the service component.
5. The business process generation method of claim 2, wherein said building a business process library using said set of business components comprises:
setting the process names of different agent service processes in the process tree diagram;
extracting service components corresponding to all the agents in the agent service flow from the service component set, and taking the extracted service components as flow nodes;
and summarizing the process names and the process nodes of all the agents to obtain the business process library.
6. The business process generating method of claim 1, wherein said searching the candidate process set matching the user question text from the business process library comprises:
performing word segmentation processing and stop word removal processing on the user question text to obtain one or more keywords;
and searching the service components in the service flow library by taking the keywords as indexes, and acquiring all candidate flow nodes fed back by the indexes to obtain the candidate flow set.
7. The business process generation method of claim 6, wherein the performing intent recognition on the user question text by using the pre-constructed semantic recognition model, and selecting a plurality of process nodes from the candidate process set according to the result of intent recognition to generate the business process comprises:
sequentially selecting the business component name of any flow node in the candidate flow set as a target text, and performing word segmentation processing on the user problem text and the target text by using the semantic recognition model to obtain two word vectors;
semantic matching is carried out on the two word vectors by utilizing the semantic recognition model respectively to obtain a semantic vector pair;
calculating the similarity of the semantic vector pairs to obtain node similarity, and selecting all process nodes with the node similarity more than or equal to a preset similarity threshold as a target process node set;
and arranging the process nodes in the target process node set based on the node similarity to obtain the business process.
8. An apparatus for generating a business process, the apparatus comprising:
the agent service flow construction module is used for acquiring agent service information, constructing a flow tree diagram according to the agent service information, and obtaining an agent service flow based on the flow tree diagram;
the business component construction module is used for constructing a business component set according to the process nodes in the agent service process;
the business process library construction module is used for constructing a business process library by utilizing the business component set;
the candidate process matching module is used for acquiring a user problem text and searching a candidate process set matched with the user problem text from the business process library;
and the business process generation module is used for performing intention recognition on the user question text by utilizing a pre-constructed semantic recognition model, and selecting a plurality of process nodes from the candidate process set according to the intention recognition result to generate a business process.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the business process generating method of any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the business process generating method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111158189.3A CN113887941A (en) | 2021-09-30 | 2021-09-30 | Business process generation method and device, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111158189.3A CN113887941A (en) | 2021-09-30 | 2021-09-30 | Business process generation method and device, electronic equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113887941A true CN113887941A (en) | 2022-01-04 |
Family
ID=79004480
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111158189.3A Pending CN113887941A (en) | 2021-09-30 | 2021-09-30 | Business process generation method and device, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113887941A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114168113A (en) * | 2022-02-10 | 2022-03-11 | 湖南新云网科技有限公司 | Business process management and control configuration method |
| CN115061765A (en) * | 2022-06-20 | 2022-09-16 | 未鲲(上海)科技服务有限公司 | Message card ejection method and device, electronic equipment and storage medium |
| CN117608650A (en) * | 2024-01-15 | 2024-02-27 | 钱塘科技创新中心 | Business flow chart generation method, processing device and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100312781A1 (en) * | 2009-06-03 | 2010-12-09 | International Business Machines Corporation | Service grouping and allocation method and system |
| CN105844422A (en) * | 2016-04-01 | 2016-08-10 | 阿里巴巴集团控股有限公司 | Business flow execution method and device |
| CN108205266A (en) * | 2018-01-12 | 2018-06-26 | 北京华如科技股份有限公司 | Commanding and decision-making modeling method and storage medium based on information flow |
-
2021
- 2021-09-30 CN CN202111158189.3A patent/CN113887941A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100312781A1 (en) * | 2009-06-03 | 2010-12-09 | International Business Machines Corporation | Service grouping and allocation method and system |
| CN105844422A (en) * | 2016-04-01 | 2016-08-10 | 阿里巴巴集团控股有限公司 | Business flow execution method and device |
| CN108205266A (en) * | 2018-01-12 | 2018-06-26 | 北京华如科技股份有限公司 | Commanding and decision-making modeling method and storage medium based on information flow |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114168113A (en) * | 2022-02-10 | 2022-03-11 | 湖南新云网科技有限公司 | Business process management and control configuration method |
| CN114168113B (en) * | 2022-02-10 | 2022-06-07 | 湖南新云网科技有限公司 | Business process management and control configuration method |
| CN115061765A (en) * | 2022-06-20 | 2022-09-16 | 未鲲(上海)科技服务有限公司 | Message card ejection method and device, electronic equipment and storage medium |
| CN117608650A (en) * | 2024-01-15 | 2024-02-27 | 钱塘科技创新中心 | Business flow chart generation method, processing device and storage medium |
| CN117608650B (en) * | 2024-01-15 | 2024-04-09 | 钱塘科技创新中心 | Business flow chart generation method, processing device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113887941A (en) | Business process generation method and device, electronic equipment and medium | |
| CN113312461A (en) | Intelligent question-answering method, device, equipment and medium based on natural language processing | |
| CN115002200A (en) | User portrait based message pushing method, device, equipment and storage medium | |
| CN113378970B (en) | Sentence similarity detection method and device, electronic equipment and storage medium | |
| CN113806434B (en) | Big data processing method, device, equipment and medium | |
| CN114979120B (en) | Data uploading method, device, equipment and storage medium | |
| CN112364107A (en) | System analysis visualization method and device, electronic equipment and computer readable storage medium | |
| CN113946690A (en) | Potential customer mining method and device, electronic equipment and storage medium | |
| CN113821622A (en) | Answer retrieval method and device based on artificial intelligence, electronic equipment and medium | |
| CN114840684A (en) | Map construction method, device and equipment based on medical entity and storage medium | |
| CN114461777A (en) | Intelligent question and answer method, device, equipment and storage medium | |
| CN114416939A (en) | Intelligent question and answer method, device, equipment and storage medium | |
| CN114003704A (en) | Method and device for creating designated tag guest group, electronic equipment and storage medium | |
| CN114138243A (en) | Function calling method, device, equipment and storage medium based on development platform | |
| WO2023272862A1 (en) | Risk control recognition method and apparatus based on network behavior data, and electronic device and medium | |
| CN115346095A (en) | Visual question answering method, device, equipment and storage medium | |
| CN116362684A (en) | Library cluster-based book management method, library cluster-based book management device, library cluster-based book management equipment and storage medium | |
| CN114595321A (en) | Question marking method and device, electronic equipment and storage medium | |
| CN115146064A (en) | Intention recognition model optimization method, device, equipment and storage medium | |
| CN115510188A (en) | Text keyword association method, device, equipment and storage medium | |
| CN114610854A (en) | Intelligent question and answer method, device, equipment and storage medium | |
| CN114219367A (en) | User scoring method, device, equipment and storage medium | |
| CN113850643A (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN111859985A (en) | AI customer service model testing method, device, electronic equipment and storage medium | |
| CN115146627B (en) | Entity identification method, entity identification device, electronic equipment and storage medium |
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 |