CN114090795A - Two-way interaction intelligent service system and method based on equipment knowledge graph - Google Patents
Two-way interaction intelligent service system and method based on equipment knowledge graph Download PDFInfo
- Publication number
- CN114090795A CN114090795A CN202210024746.0A CN202210024746A CN114090795A CN 114090795 A CN114090795 A CN 114090795A CN 202210024746 A CN202210024746 A CN 202210024746A CN 114090795 A CN114090795 A CN 114090795A
- Authority
- CN
- China
- Prior art keywords
- keyword
- entity
- feedback scheme
- service
- user
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Abstract
The invention relates to the technical field of intelligent services, and discloses a two-way interactive intelligent service system and a method based on an equipment knowledge graph.
Description
Technical Field
The invention relates to the technical field of intelligent services, in particular to a two-way interactive intelligent service system and a method based on an equipment knowledge graph.
Background
At present, for a supplier of advanced equipment, when a customer of the equipment has problems in the aspects of equipment selection, application, maintenance, troubleshooting and the like, a customer service engineer is often required to perform manual remote service, even door-to-door service, so that the labor cost is increased, the customer service engineer can only perform treatment according to own experience and knowledge accumulation, and the defects of low time efficiency, poor accuracy and unsatisfactory problem solving condition exist.
As disclosed in patent document No. CN 108647233B, there is a case in the prior art where a robot using an artificial intelligence algorithm performs customer service through man-machine interaction. However, if the artificial intelligence algorithm needs to accurately understand the service requirement expressed by the client in the natural language and further output the reply feedback matched with the service requirement, a large amount of dialog samples are often required for training, and a huge reply corpus is also required to support effective feedback to the client.
However, for the advanced equipment related problems, since the target customer population of many advanced equipment is not large and there is a tendency of customized design and manufacture, it is difficult to accumulate a large amount of dialogue samples and applicable reply corpora in terms of the number of customers, the frequency of customer service and the difference of the man-machine dialogue contents in the past, and a general artificial intelligent dialogue robot cannot be competent due to the specialty of the equipment related customer service problems.
Disclosure of Invention
The invention mainly provides a two-way interactive intelligent service system and a method based on an equipment knowledge graph, and solves the problems that in the prior art, massive conversation samples and applicable reply corpora are difficult to accumulate, so that effective feedback is carried out, and the professional nature of the service problem of relevant customers is provided, and a common artificial intelligent conversation robot cannot be competent.
In order to solve the technical problems, the invention adopts the following technical scheme:
the two-way interactive intelligent service method based on the equipment knowledge graph comprises the following steps:
collecting data information input by a user, and extracting a service demand directing entity based on the data information;
based on an entity concept network equipped with a knowledge graph, fitting the service requirement directed entity with a service interaction feedback scheme preset in the entity concept network, thereby determining an optimal feedback scheme;
and providing the optimal feedback scheme to a user.
Further, the collecting data information input by the user and extracting a service demand directing entity based on the data information includes:
collecting data information, matching the data information with a designation library, and extracting a keyword designation;
forming a named word sequence based on the keyword designation, and inputting the named word sequence into a single-layer GRU encoder to obtain a named word vector;
defining a classification support set, acquiring a service demand directional entity based on the referent vector, and forming a directional entity set.
Further, the acquiring data information, matching the data information with a reference library, and extracting the keyword reference includes:
acquiring text information or character information converted from voice input information, and extracting keywords based on the text information and the character information;
matching the keyword with a reference library based on the reference library, judging whether the keyword is effective or not based on a matching result, and directly extracting the keyword reference if the keyword is effective;
if the keyword is invalid, asking a question for the user according to a preset guide type question; and comparing the keywords obtained by questioning based on the index library again, thereby extracting the keyword index.
Further, the entity concept network based on the equipment knowledge graph fits the service requirement directed to the entity and a service interaction feedback scheme preset in the entity concept network, so as to determine an optimal feedback scheme, including:
presetting a plurality of service interaction feedback schemes, and forming an interaction feedback scheme entity set based on the service interaction feedback schemes;
defining a correlation matrix between entities, and assigning the correlation matrix between the entities based on the pointed entity set and the interactive feedback scheme entity set;
and calculating the fitting degree of the service demand direction based on the assigned correlation matrix between the entities, and selecting an optimal feedback scheme according to the fitting degree.
Further, providing the optimal feedback scheme to a user, comprising:
providing the optimal feedback scheme to a user in a text mode;
and providing the optimal feedback scheme to a user in a voice mode.
Two-way interactive intelligent service system based on equipment knowledge graph includes:
the data information acquisition, analysis and extraction module is used for acquiring data information input by a user and extracting a service requirement pointing entity based on the data information;
the feedback scheme fitting judgment module is used for fitting the service requirement directing entity and a preset service interaction feedback scheme in the entity concept network based on the entity concept network equipped with the knowledge graph so as to determine an optimal feedback scheme;
and the scheme feedback module is used for providing the optimal feedback scheme for the user.
Further, the data information collecting, analyzing and extracting module comprises:
the keyword extraction submodule is used for acquiring data information, matching the data information with the designation library and extracting a keyword designation;
a nominal word vector calculation generation submodule for forming a nominal word sequence based on the keyword and inputting the nominal word sequence into a single-layer GRU encoder to obtain a nominal word vector;
and the classification support set calculation submodule is used for defining the classification support set, acquiring a service demand directing entity based on the nominal word vector and forming a directing entity set.
Further, the keyword extraction sub-module includes:
the keyword and character extraction unit is used for acquiring text type information or character information converted from voice input information and extracting keywords based on the text type information and the character information;
a keyword index matching and extracting unit, configured to match the keyword with an index library based on the index library, determine whether the keyword is valid based on a matching result, and directly extract the keyword index if the keyword is valid;
the user question-asking guiding unit is used for judging whether the keyword is invalid or not, and asking the user questions according to a preset guiding type question; and comparing the keywords obtained by questioning based on the index library again, thereby extracting the keyword index.
Further, the feedback scheme fitting judgment module includes:
the preset scheme storage submodule is used for presetting a plurality of service interaction feedback schemes and forming an interaction feedback scheme entity set based on the service interaction feedback schemes;
a correlation matrix assignment submodule between the entities, configured to define a correlation matrix between the entities, and assign a correlation matrix between the entities based on the pointed entity set and the interactive feedback scheme entity set;
and the fitting degree calculation submodule is used for calculating the fitting degree pointed by the service demand based on the assigned correlation matrix between the entities and selecting an optimal feedback scheme according to the fitting degree.
Further, the scheme feedback module includes:
the text feedback sub-module is used for providing the optimal feedback scheme to a user in a text mode;
and the voice feedback sub-module is used for providing the optimal feedback scheme to the user in a voice mode.
Has the advantages that: according to the method, the service demand directional entity is extracted by collecting the data information in the continuous interaction with the user, so that the service demand of the user is well recognized, the service demand directional and service interaction feedback scheme is fitted based on the equipment knowledge graph, the accumulation of a conversation sample and a suitable reply corpus is reduced, the optimal feedback scheme is accurately obtained by calculating the corresponding fitting degree, the feedback accuracy is improved, and the professional degree and the working efficiency of artificial intelligence are improved.
Drawings
FIG. 1 is a schematic flow chart of the bi-directional interactive intelligent service method based on equipment knowledge graph;
FIG. 2 is a flowchart of step S101 of the present embodiment;
FIG. 3 is a flowchart of step S1011 according to the present embodiment;
FIG. 4 is a flowchart of step S102 according to the present embodiment;
FIG. 5 is a flowchart of step S103 of the present embodiment;
fig. 6 is a block diagram of the two-way interactive intelligent service system based on the equipment knowledge graph according to the embodiment.
Detailed Description
The technical solutions of the system and the method for bi-directional interactive intelligent service based on equipment knowledge graph according to the present invention will be further described in detail with reference to the following embodiments.
As shown in fig. 1, the two-way interactive intelligent service method based on equipment knowledge graph of the present embodiment includes: s101 to S103:
s101, collecting data information input by a user, and extracting a service demand directing entity based on the data information;
s102, based on an entity concept network equipped with a knowledge graph, fitting the service requirement directed to an entity and a service interaction feedback scheme preset in the entity concept network, and determining an optimal feedback scheme;
s103, providing the optimal feedback scheme to a user.
According to the method, the service demand directional entity is extracted by collecting the data information in the continuous interaction with the user, so that the service demand of the user is well recognized, the service demand directional and service interaction feedback scheme is fitted based on the equipment knowledge graph, the accumulation of a conversation sample and a suitable reply corpus is reduced, the optimal feedback scheme is accurately obtained by calculating the corresponding fitting degree, the feedback accuracy is improved, and the professional degree and the working efficiency of artificial intelligence are improved.
The present application has a keyword designation library in which various keyword designations related to equipment are stored in advance, such as: including but not limited to equipment name, brand name of goods, model name, main performance parameter name, mating parts name, common fault description keyword, etc.
The knowledge graph is a semantic network between entities-relation-entities, and the equipment knowledge graph of the application is a semantic network formed by entities related to equipment and relations thereof, wherein the entities in the knowledge graph include but are not limited to: equipment name, equipment commodity brand, equipment model, main performance parameters, matched parts, equipment operation mode subject items, common fault items, fault solution subject items, equipment upgrading subject items and the like, wherein the entities form an entity-relationship-entity knowledge graph based on the relationship among the entities.
Further, as shown in fig. 2, the acquiring data information input by the user in step S101, and extracting a service requirement directing entity based on the data information includes:
s1011, collecting data information, matching the data information with a designation library, and extracting a keyword designation;
aiming at the matched keyword index, forming an index word sequence according to the keyword index and the context words in the word cutting window taking the keyword index as the centerWherein, in the step (A),for the purpose of the designation of the keyword,、respectively representing the keywords, the following words and the previous words in the word cutting window.
S1012, forming a named word sequence based on the keyword designation, and inputting the named word sequence into a single-layer GRU encoder to obtain a named word vector;
by referring to word sequencesInput into a single-layer GRU encoder to obtain a word vector representation of a sequence of term references, the term vectors being represented asI.e. by
Wherein the content of the first and second substances,indicating that the word sequence will be referred toAs an input single layer GRU encoder.
S1013, defining a classification support set, acquiring a service demand direction entity based on the reference word vector, and forming a direction entity set.
Using a set of classified supports, according to the nominal word vectorThe entity to which the service requirement is directed is obtained.
In particular, the set of classification supports may be represented asWhereinA sample word vector is represented that represents a sample word vector,representing the entities corresponding to the sample word vectors, which point to the service requirements corresponding to the sample word vectors.
According to the nominal word vectorWith respective sample word vectorsThe vector distance between the two, the sample word vector with the minimum distance is determined, and the entity corresponding to the sample word vector is taken as the entity pointed by the service requirement and is marked as the entity pointed by the service requirement(ii) a Extracting the entity pointed by the service requirement, thereby obtaining a service requirement pointed entity set, which is recorded as:
further, as shown in fig. 3, the acquiring data information in step S1011, matching the data information with a reference library, and extracting the keyword reference includes:
s10111, collecting text information or character information converted from voice input information, and extracting keywords based on the text information and the character information;
the data information comprises key information which is input by a user in a character mode or is converted into a character mode after being input by voice, the key information is matched with a keyword designation library, and keyword designations contained in the key information are extracted.
S10112, matching the keyword with the reference library based on the reference library, judging whether the keyword is effective or not based on a matching result, and directly extracting the keyword reference if the keyword is effective;
s10113, if the keyword is invalid, asking a question for the user according to a preset guide type question; and comparing the keywords obtained by questioning based on the index library again, thereby extracting the keyword index.
For example: including, but not limited to, the name, model, etc. of the equipment please provide your consultation.
Further, as shown in fig. 4, in the entity concept network based on the equipment knowledge graph in step S102, fitting the service requirement to the entity and a service interaction feedback scheme preset in the entity concept network to determine an optimal feedback scheme, including:
s1021, presetting a plurality of service interaction feedback schemes, and forming an interaction feedback scheme entity set based on the service interaction feedback schemes;
the service interaction feedback scheme also aims at the entities contained in the scheme, and each service interaction feedback scheme forms an entity set of the service interaction feedback scheme and is marked as
S1022, defining a correlation matrix between entities, and assigning the correlation matrix between the entities based on the pointed entity set and the interactive feedback scheme entity set;
directing a set of entities for a determined service requirementAnd each service interaction feedback scheme entity setAnd calculating a correlation matrix between the entities based on the equipment knowledge graph:
whereinTo representAnda correlation coefficient between;and the above equipmentEntities in knowledge graphAndthe number of hops in the relationship between is proportional: for example "entity 1-relationship-entity 2-relationship-entity 3-relationship-entity 4", the number of relationship hops between entity 1 and entity 4 is 3 hops.
And S1023, calculating the fitting degree of the service demand direction based on the assigned correlation matrix between the entities, and selecting an optimal feedback scheme according to the fitting degree.
The degree of fit of each service interaction feedback scheme to the service requirement direction of the user is expressed as:
and the service interaction feedback scheme with the optimal fitting degree further provides interaction feedback for the user.
Further, as shown in fig. 5, the providing the optimal feedback scheme to the user in step S103 includes:
s1031, providing the optimal feedback scheme to a user in a text mode;
s1032, providing the optimal feedback scheme to a user in a voice mode.
As shown in fig. 6, the two-way interactive intelligent service system 6 based on equipment knowledge graph of the present embodiment includes:
the data information acquisition, analysis and extraction module 61 is used for acquiring data information input by a user and extracting a service demand directing entity based on the data information;
a feedback scheme fitting and judging module 62, configured to fit the service requirement directed to the entity and a service interaction feedback scheme preset in the entity concept network based on the entity concept network equipped with the knowledge graph, so as to determine an optimal feedback scheme;
and a scheme feedback module 63, configured to provide the optimal feedback scheme to a user.
Further, the data information collecting, analyzing and extracting module 61 includes:
the keyword extraction sub-module 611 is configured to collect data information, match the data information with a designation library, and extract a keyword designation;
a nominal word vector calculation generation submodule 612, configured to form a nominal word sequence based on the keyword, and input the nominal word sequence into a single-layer GRU encoder to obtain a nominal word vector;
a classification support set calculation submodule 613, configured to define the classification support set, obtain a service requirement directed entity based on the term vector, and form a directed entity set.
Further, the keyword extraction sub-module 611 includes:
a keyword/character extraction unit 6111, configured to collect text information or character information converted from voice input information, and extract a keyword based on the text information and the character information;
a keyword index matching extraction unit 6112, configured to match the keyword with the index library based on the index library, determine whether the keyword is valid based on a matching result, and directly extract the keyword index if the keyword is valid;
the user question-asking guidance unit 6113 is configured to determine that, if the keyword is invalid, ask a question of the user according to a preset guidance-type question; and comparing the keywords obtained by questioning based on the index library again, thereby extracting the keyword index.
Further, the feedback scheme fitting judgment module 62 includes:
a preset scheme storage sub-module 621, configured to preset a plurality of service interaction feedback schemes, and form an interaction feedback scheme entity set based on the service interaction feedback schemes;
the assignment submodule 622 of the correlation matrix between the entities is configured to define the correlation matrix between the entities, and assign the correlation matrix between the entities based on the set of the pointed entities and the set of the interactive feedback scheme entities;
and the fitting degree calculating sub-module 623 is configured to calculate a fitting degree pointed by a service demand based on the assigned correlation matrix between the entities, and select an optimal feedback scheme according to the fitting degree.
Further, the scheme feedback module 63 includes:
a text feedback sub-module 631 for providing the optimal feedback scheme to a user textually;
a voice feedback sub-module 632 for providing the optimal feedback scheme to the user in a voice manner.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. The two-way interactive intelligent service method based on the equipment knowledge graph is characterized by comprising the following steps:
collecting data information input by a user, and extracting a service demand directing entity based on the data information;
based on an entity concept network equipped with a knowledge graph, fitting the service requirement directed entity with a service interaction feedback scheme preset in the entity concept network, thereby determining an optimal feedback scheme;
and providing the optimal feedback scheme to a user.
2. The method of claim 1, wherein the collecting data information input by a user and extracting service requirement directing entities based on the data information comprises:
collecting data information, matching the data information with a designation library, and extracting a keyword designation;
forming a named word sequence based on the keyword designation, and inputting the named word sequence into a single-layer GRU encoder to obtain a named word vector;
defining a classification support set, acquiring a service demand directional entity based on the referent vector, and forming a directional entity set.
3. The method of claim 2, wherein collecting data information, matching the data information to a library of designations, and extracting the keyword designations comprises:
acquiring text information or character information converted from voice input information, and extracting keywords based on the text information and the character information;
matching the keyword with a reference library based on the reference library, judging whether the keyword is effective or not based on a matching result, and directly extracting the keyword reference if the keyword is effective;
if the keyword is invalid, asking a question for the user according to a preset guide type question; and comparing the keywords obtained by questioning based on the index library again, thereby extracting the keyword index.
4. The method of claim 2, wherein the step of fitting the service requirement directed to the entity to a service interaction feedback scheme preset in the entity concept network to determine an optimal feedback scheme comprises:
presetting a plurality of service interaction feedback schemes, and forming an interaction feedback scheme entity set based on the service interaction feedback schemes;
defining a correlation matrix between entities, and assigning the correlation matrix between the entities based on the pointed entity set and the interactive feedback scheme entity set;
and calculating the fitting degree of the service demand direction based on the assigned correlation matrix between the entities, and selecting an optimal feedback scheme according to the fitting degree.
5. The method of claim 1, wherein providing the optimal feedback scheme to a user comprises:
providing the optimal feedback scheme to a user in a text mode;
and providing the optimal feedback scheme to a user in a voice mode.
6. Two-way mutual intelligent service system based on equipment knowledge map, its characterized in that includes:
the data information acquisition, analysis and extraction module is used for acquiring data information input by a user and extracting a service requirement pointing entity based on the data information;
the feedback scheme fitting judgment module is used for fitting the service requirement directing entity and a preset service interaction feedback scheme in the entity concept network based on the entity concept network equipped with the knowledge graph so as to determine an optimal feedback scheme;
and the scheme feedback module is used for providing the optimal feedback scheme for the user.
7. The system of claim 6, wherein the data information collection, analysis and extraction module comprises:
the keyword extraction submodule is used for acquiring data information, matching the data information with the designation library and extracting a keyword designation;
a nominal word vector calculation generation submodule for forming a nominal word sequence based on the keyword and inputting the nominal word sequence into a single-layer GRU encoder to obtain a nominal word vector;
and the classification support set calculation submodule is used for defining the classification support set, acquiring a service demand directing entity based on the nominal word vector and forming a directing entity set.
8. The system of claim 7, wherein the keyword extraction sub-module comprises:
the keyword and character extraction unit is used for acquiring text type information or character information converted from voice input information and extracting keywords based on the text type information and the character information;
a keyword index matching and extracting unit, configured to match the keyword with an index library based on the index library, determine whether the keyword is valid based on a matching result, and directly extract the keyword index if the keyword is valid;
the user question-asking guiding unit is used for judging whether the keyword is invalid or not, and asking the user questions according to a preset guiding type question; and comparing the keywords obtained by questioning based on the index library again, thereby extracting the keyword index.
9. The system of claim 7, wherein the feedback scheme fitting determination module comprises:
the preset scheme storage submodule is used for presetting a plurality of service interaction feedback schemes and forming an interaction feedback scheme entity set based on the service interaction feedback schemes;
a correlation matrix assignment submodule between the entities, configured to define a correlation matrix between the entities, and assign a correlation matrix between the entities based on the pointed entity set and the interactive feedback scheme entity set;
and the fitting degree calculation submodule is used for calculating the fitting degree pointed by the service demand based on the assigned correlation matrix between the entities and selecting an optimal feedback scheme according to the fitting degree.
10. The system of claim 6, wherein the recipe feedback module comprises:
the text feedback sub-module is used for providing the optimal feedback scheme to a user in a text mode;
and the voice feedback sub-module is used for providing the optimal feedback scheme to the user in a voice mode.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210024746.0A CN114090795B (en) | 2022-01-11 | 2022-01-11 | Two-way interaction intelligent service system and method based on equipment knowledge graph |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210024746.0A CN114090795B (en) | 2022-01-11 | 2022-01-11 | Two-way interaction intelligent service system and method based on equipment knowledge graph |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114090795A true CN114090795A (en) | 2022-02-25 |
CN114090795B CN114090795B (en) | 2022-05-10 |
Family
ID=80308619
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210024746.0A Active CN114090795B (en) | 2022-01-11 | 2022-01-11 | Two-way interaction intelligent service system and method based on equipment knowledge graph |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114090795B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100049590A1 (en) * | 2008-04-03 | 2010-02-25 | Infosys Technologies Limited | Method and system for semantic analysis of unstructured data |
CN108959270A (en) * | 2018-08-10 | 2018-12-07 | 新华智云科技有限公司 | A kind of entity link method based on deep learning |
CN110377715A (en) * | 2019-07-23 | 2019-10-25 | 天津汇智星源信息技术有限公司 | Reasoning type accurate intelligent answering method based on legal knowledge map |
CN113139036A (en) * | 2020-01-20 | 2021-07-20 | 海信视像科技股份有限公司 | Information interaction method and equipment |
-
2022
- 2022-01-11 CN CN202210024746.0A patent/CN114090795B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100049590A1 (en) * | 2008-04-03 | 2010-02-25 | Infosys Technologies Limited | Method and system for semantic analysis of unstructured data |
CN108959270A (en) * | 2018-08-10 | 2018-12-07 | 新华智云科技有限公司 | A kind of entity link method based on deep learning |
CN110377715A (en) * | 2019-07-23 | 2019-10-25 | 天津汇智星源信息技术有限公司 | Reasoning type accurate intelligent answering method based on legal knowledge map |
CN113139036A (en) * | 2020-01-20 | 2021-07-20 | 海信视像科技股份有限公司 | Information interaction method and equipment |
Also Published As
Publication number | Publication date |
---|---|
CN114090795B (en) | 2022-05-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109145294B (en) | Text entity identification method and device, electronic equipment and storage medium | |
CN111026842B (en) | Natural language processing method, natural language processing device and intelligent question-answering system | |
CN109685056B (en) | Method and device for acquiring document information | |
CN107766511A (en) | Intelligent answer method, terminal and storage medium | |
CN106777296A (en) | Method and system are recommended in a kind of talent's search based on semantic matches | |
CN110795913B (en) | Text encoding method, device, storage medium and terminal | |
CN112348519A (en) | Method and device for identifying fraudulent user and electronic equipment | |
CN111191000A (en) | Dialog management method, device and system of intelligent voice robot | |
CN111626813A (en) | Product recommendation method and system | |
CN114547072A (en) | Method, system, equipment and storage medium for converting natural language query into SQL | |
CN112449700A (en) | Semantic model instantiation method, system and device | |
CN101000624A (en) | Method, system and device for implementing data mining model conversion and application | |
CN114238655A (en) | Enterprise association relation identification method, device, equipment and medium | |
CN110674276A (en) | Robot self-learning method, robot terminal, device and readable storage medium | |
CN116304115B (en) | Knowledge-graph-based material matching and replacing method and device | |
CN112417996A (en) | Information processing method and device for industrial drawing, electronic equipment and storage medium | |
CN114090795B (en) | Two-way interaction intelligent service system and method based on equipment knowledge graph | |
JP6550628B1 (en) | Dialog management server, dialog management method, and program | |
CN110442716B (en) | Intelligent text data processing method and device, computing equipment and storage medium | |
CN115358473A (en) | Power load prediction method and prediction system based on deep learning | |
CN110737749B (en) | Entrepreneurship plan evaluation method, entrepreneurship plan evaluation device, computer equipment and storage medium | |
CN111859896B (en) | Formula document detection method and device, computer readable medium and electronic equipment | |
CN112559697A (en) | Method and device for recognizing conversational intention | |
CN117668205B (en) | Smart logistics customer service processing method, system, equipment and storage medium | |
CN110795539B (en) | Short text label identification method based on logic expression |
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 |