CN116541491A - Flow mining system and mining method based on session scene - Google Patents
Flow mining system and mining method based on session scene Download PDFInfo
- Publication number
- CN116541491A CN116541491A CN202310344360.2A CN202310344360A CN116541491A CN 116541491 A CN116541491 A CN 116541491A CN 202310344360 A CN202310344360 A CN 202310344360A CN 116541491 A CN116541491 A CN 116541491A
- Authority
- CN
- China
- Prior art keywords
- intention
- customer service
- dialogue
- text
- session
- 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 52
- 238000005065 mining Methods 0.000 title claims abstract description 31
- 238000013500 data storage Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 5
- 238000009412 basement excavation Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—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
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F16/338—Presentation of query results
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a flow mining system and a mining method based on a session scene, which belong to the technical field of flow mining, and can automatically acquire corresponding user intention and a session flow corresponding to the user intention after analyzing historical session data; according to the method, the complete dialogue text is automatically analyzed, the dialogue text logs are divided into groups according to the purpose directions, the difference of the same group of dialogue text logs is reduced, the reasonability and the accuracy of the formed mining flow are improved, the manual analysis workload can be remarkably reduced, and the negative influence of personal experience on the accuracy of the division result is reduced.
Description
Technical Field
The invention belongs to the technical field of flow mining, and particularly relates to a flow mining system and a flow mining method based on a session scene.
Background
Flow mining is a newer application of data mining in the field of workflow management. The original purpose of workflow mining is to reproduce the real process of the business process by analyzing the log generated by the workflow operation, and to analyze and optimize the workflow by using the knowledge.
With the development of internet technology, the use of intelligent customer service has been very extensive, but in the prior art, customer service consultation service field is mainly through the division of user intention type and the design of flow of experience of staff when making the intelligent customer service flow, but this kind of method is influenced by factors such as staff experience on the one hand, the flow of design may have the problem of not brief, and with the increase of user intention, design work load and completion degree can all be influenced, in addition to the incomplete customer flow that causes some user intention to have not designed for statistics of user intention correspond, still need the manual transfer to answer to the answer of corresponding customer service consultation problem in the actual use, in order to solve above-mentioned problem, provide a flow excavation system and excavation method that can carry out the flow excavation automatically, and promote the flow design quality notably, the invention has proposed following technical scheme.
Disclosure of Invention
The invention aims to provide a flow mining system and a mining method based on a session scene, which solve the problems that in the prior art, the design of a customer service flow in customer service consultation service depends on experience of staff, so that the efficiency is low, statistics of user intention is incomplete, and the comprehensiveness of the customer service flow is affected.
The aim of the invention can be achieved by the following technical scheme:
the process mining method based on the session scene comprises the following steps:
s1, acquiring a dialogue text, and dividing the dialogue text into a plurality of dialogue text combinations according to the destination directions of the dialogue text;
s2, for the dialogue texts in the same dialogue text combination, acquiring customer service intentions therein, and marking the customer service intentions in the dialogue texts with more than gamma% in the dialogue text combination as necessary customer service intentions, wherein gamma is a preset value;
assigning values to the customer service intentions according to the time sequence of each necessary customer service intention, and sequentially assigning values of 1, 2, … and v according to the sequence of the necessary customer service intentions in a dialogue text within the range of dialogue texts in which all the necessary customer service intentions exist, wherein v is the number of the necessary customer service intentions;
calculating the sum Fh of the values of a necessary customer service intention in all dialogue texts, and sequencing the necessary customer service intention according to the sequence from small to large of the sum Fh of the values;
s3, acquiring corresponding dialogue sentences according to the necessary customer service intention;
and generating a conversation process according to the ordering of the necessary customer service intents and the conversation sentences corresponding to the necessary customer service intents.
As a further aspect of the present invention, the γ has a value of 70.
As a further scheme of the invention, the method for acquiring the destination direction of the dialogue text comprises the following steps:
s11, acquiring an intention set of a user and an intention set of customer service in a dialogue text through intention recognition based on the complete dialogue text;
s12, processing dialogue texts in a dialogue data storage unit to obtain an intention set of a user and an intention set of customer service in each dialogue text, and representing the user intention A and the customer service intention B as A { B1k1, B2k2, … and Bnkn }, wherein Biki represents that the number of dialogue texts in which the ith customer service intention Bi is positioned is ki in n dialogue texts with the user intention A;
wherein i is more than or equal to 1 and less than or equal to n;
s13, when ki/n is more than or equal to beta, considering the corresponding customer service intention Bi as a sub intention corresponding to the user intention A, wherein beta is a preset percentage coefficient;
s14, sequentially marking the number of dialog texts comprising each sub-intention corresponding to the user intention A in n dialog texts with the user intention A as z1, z2, … and zs;
and calculating according to the formula Y= (z 1/n+z2/n+, …, +zs/n) s to obtain an intensity value Y of the user intention A, and when Y is larger than a preset value Y1, considering the user intention A corresponding to Y as an upper intention, wherein the upper intention is the destination direction of the corresponding dialogue text.
As a further aspect of the present invention, the β has a value of 0.65.
As a further scheme of the invention, when two or more than two upper intention exist in one dialogue text at the same time, the corresponding dialogue text is deleted from the dialogue data storage unit, and the subsequent dialogue text combination division is not performed as a sample.
As a further scheme of the invention, when customer service session is carried out, the intention of the user is analyzed through intention recognition, and the corresponding session flow is matched according to different session scenes.
As a further scheme of the present invention, the present invention also discloses a process mining system based on a session scene, where the process mining system includes:
a session data storage unit for storing session data;
the text log generating unit is used for analyzing and processing the session data to generate a dialogue text;
the intention recognition unit is used for analyzing the dialogue text through an intention recognition algorithm, acquiring user intention and customer service intention, and transmitting the acquired user intention and customer service intention to the control unit;
the control unit is used for analyzing the user intention and the customer service intention in the dialogue text and acquiring the appearance sequence of the customer service intention corresponding to the dialogue text pointed by different purposes;
and the conversation process generating unit is used for generating a conversation process according to the customer service intention and the appearance sequence of the customer service intention.
As a further aspect of the present invention, the dialog text is a text log generated from a text chat log.
As a further aspect of the present invention, the dialog text is a text log generated by converting a voice log.
The invention has the beneficial effects that:
(1) Compared with the traditional method for dividing user intention types and designing flows through experience, the method has higher efficiency, and the considered user intention is more comprehensive, so that the problem of missing of the corresponding conversation flows caused by statistics of the user intention due to the condition of limited personal energy and capability is avoided;
(2) The invention utilizes the characteristic that only the user intention with a higher relation with a plurality of corresponding customer service intentions is the main purpose of surrounding the dialogue text content, and the invention automatically analyzes a complete dialogue text, divides dialogue text logs according to the purpose directions, reduces the difference of the same group of dialogue text logs, is beneficial to the follow-up analysis work, improves the rationality and accuracy of the formed excavation flow, automatically divides the groups according to the text content, obviously reduces the manual analysis workload and reduces the negative influence of personal experience on the accuracy of the division result;
(3) According to the invention, a certain threshold is set to delete a part of customer service intentions, the threshold is reasonably adjusted according to an actual application scene, the customer service intentions which do not need to appear in the corresponding dialogue text combination for completing the main purpose can be deleted, the interference caused by personal habits is reduced or eliminated, and in addition, the integral appearance sequence of the necessary customer service intentions can be intuitively expressed through calculation of the sum of the assignment after the assignment is sequentially carried out, so that the ordering is automatically completed.
Drawings
The invention is further described below with reference to the accompanying drawings.
Fig. 1 is a schematic frame structure of a process mining system based on a session scene of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The process mining system based on the session scene, as shown in fig. 1, comprises:
the session data storage unit is used for storing session data in a certain range;
wherein the certain range includes a certain range in time and a certain range in content, the certain range in time includes a dialogue text within a preset time t1 in the past when the dialogue text is selected as a sample, the update of the sample is ensured, and the certain range in content includes a dialogue text generated when a user problem in a certain field in the same industry is solved, and the method is characterized in that the intention of the user is limited;
the text log generating unit is used for analyzing and processing the session data to generate a dialogue text;
the dialogue text can be a text log generated by text chat records or a text log generated by conversion of voice logs;
the intention recognition unit is used for analyzing the dialogue text through an intention recognition algorithm, acquiring user intention and customer service intention, and transmitting the acquired user intention and customer service intention to the control unit;
the user intention refers to an intention obtained by analyzing and identifying the dialogue text of the user, and the customer service intention refers to an intention obtained by analyzing and identifying the dialogue text of a customer service staff;
the control unit is used for analyzing the user intention and the customer service intention in the dialogue text and acquiring the appearance sequence of the customer service intention corresponding to the dialogue text pointed by different purposes;
a session flow generation unit for generating a session flow according to customer service intention and the appearance sequence of the customer service intention;
the invention also discloses a process mining method based on the session scene, which is carried out by the mining system and comprises the following steps:
s1, acquiring a dialogue text, and dividing the dialogue text into a plurality of dialogue text combinations according to the destination directions of the dialogue text;
in one embodiment of the invention, the method for acquiring the destination direction of the dialogue text is as follows:
s11, acquiring an intention set of a user and an intention set of customer service in a dialogue text through intention recognition based on the complete dialogue text;
the complete dialogue text refers to the text of a session completed in the process of solving the same user problem;
s12, processing dialogue texts in a dialogue data storage unit to obtain an intention set of a user and an intention set of customer service in each dialogue text, and representing user intention A and customer service intention B as A { B1k1, B2k2, … and Bnkn }, wherein Biki represents the number of dialogue texts where the ith customer service intention Bi is located as ki in n dialogue texts with the user intention A;
wherein i is more than or equal to 1 and less than or equal to n;
s13, when ki/n is more than or equal to beta, considering the corresponding customer service intention Bi as a sub intention corresponding to the user intention A;
wherein β is a predetermined percentage factor, and in one embodiment of the present invention, the β has a value of 0.65;
s14, sequentially marking the number of dialog texts comprising each sub-intention corresponding to the user intention A in n dialog texts with the user intention A as z1, z2, … and zs;
calculating according to the formula Y= (z 1/n+z2/n+, …, +zs/n) x to obtain an intensity value Y of the user intention A, and when Y is larger than a preset value Y1, considering the user intention A corresponding to Y as an upper intention, wherein the upper intention is the destination direction of the corresponding dialogue text;
dividing the dialogue texts with the same upper intention into the same dialogue text combination when dividing a plurality of dialogue text combinations;
in one embodiment of the invention, when two or more than two upper intents exist in one dialogue text at the same time, deleting the corresponding dialogue text from the dialogue data storage unit, and not taking the corresponding dialogue text as a sample to carry out subsequent dialogue text combination division;
in an actual customer service session scene, a user generally has one or more main purposes, and around the main purposes, the customer service and the user usually carry out question and answer for 3-5 times to obtain required auxiliary information and solve the main purposes, when different manual customers and users solve the same main purposes, although the word order and the process of the question and answer have certain difference, the auxiliary information required to be known is approximately the same, so that the invention utilizes the characteristic, only the user intention with a higher relation with a plurality of corresponding customer service intentions is the main purpose surrounded by dialogue text content, the invention automatically analyzes a complete dialogue text and carries out grouping division on dialogue text logs according to the purpose, reduces the difference of the same group of dialogue text logs, is beneficial to the follow-up analysis work, improves the rationality and accuracy of the formed excavation flow, and in addition, automatically carries out grouping division according to text content, can also obviously reduce the manual analysis workload and reduce the negative influence of individual experience on the accuracy of division results;
s2, for the dialogue texts in the same dialogue text combination, acquiring customer service intentions therein, and marking the customer service intentions in the dialogue texts with more than gamma% in the dialogue text combination as necessary customer service intentions;
wherein γ is a preset value, and in one embodiment of the present invention, the γ takes a value of 70;
assigning a value to the customer service intention according to the time sequence of each necessary customer service intention, and specifically:
sequentially assigning 1, 2, … and v according to the sequence of the necessary customer service intentions in a dialogue text in the range of the dialogue text in which all the necessary customer service intentions exist, wherein v is the number of the necessary customer service intentions;
calculating the sum Fh of the values of a necessary customer service intention in all dialogue texts, and sequencing the necessary customer service intention according to the sequence from small to large of the sum Fh of the values, wherein the necessary customer service intention with the minimum sum Fh of the values is the first;
according to the method, a certain threshold is set to delete a part of customer service intentions, the threshold is reasonably adjusted according to an actual application scene, the customer service intentions which do not need to appear in the corresponding dialogue text combination for completing main purposes can be deleted, interference caused by personal habits is reduced or eliminated, in addition, the integral appearance sequence of the necessary customer service intentions can be intuitively expressed through calculation of the sum of assignment after sequential assignment, and therefore sorting is automatically completed;
s3, inputting or generating corresponding dialogue sentences according to the necessary customer service intention;
generating a conversation process according to the ordering of the necessary customer service intents and the conversation sentences corresponding to the necessary customer service intents;
when customer service session is carried out, user intention is analyzed through intention recognition, and corresponding session flows are matched according to different session scenes.
Compared with the traditional method for dividing user intention types and designing flows through experience, the method has higher efficiency, the considered user intention is more comprehensive, and the problem of missing of corresponding conversation flows caused by statistics of the user intention due to the condition of limited personal energy and capability is avoided.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing is merely illustrative and explanatory of the invention, as various modifications and additions may be made to the particular embodiments described, or in a similar manner, by those skilled in the art, without departing from the scope of the invention or exceeding the scope of the invention as defined in the claims.
Claims (9)
1. The process mining method based on the session scene is characterized by comprising the following steps:
s1, acquiring a dialogue text, and dividing the dialogue text into a plurality of dialogue text combinations according to the destination directions of the dialogue text;
s2, for the dialogue texts in the same dialogue text combination, acquiring customer service intentions therein, and marking the customer service intentions in the dialogue texts with more than gamma% in the dialogue text combination as necessary customer service intentions, wherein gamma is a preset value;
assigning values to the customer service intentions according to the time sequence of each necessary customer service intention, and sequentially assigning values of 1, 2, … and v according to the sequence of the necessary customer service intentions in a dialogue text within the range of dialogue texts in which all the necessary customer service intentions exist, wherein v is the number of the necessary customer service intentions;
calculating the sum Fh of the values of a necessary customer service intention in all dialogue texts, and sequencing the necessary customer service intention according to the sequence from small to large of the sum Fh of the values;
s3, acquiring corresponding dialogue sentences according to the necessary customer service intention;
and generating a conversation process according to the ordering of the necessary customer service intents and the conversation sentences corresponding to the necessary customer service intents.
2. The session scene based process mining method according to claim 1, wherein the γ takes a value of 70.
3. The process mining method based on the conversation scene as claimed in claim 1, wherein the method for obtaining the destination direction of the conversation text is as follows:
s11, acquiring an intention set of a user and an intention set of customer service in a dialogue text through intention recognition based on the complete dialogue text;
s12, processing dialogue texts in a dialogue data storage unit to obtain an intention set of a user and an intention set of customer service in each dialogue text, and representing the user intention A and the customer service intention B as A { B1k1, B2k2, … and Bnkn }, wherein Biki represents that the number of dialogue texts in which the ith customer service intention Bi is positioned is ki in n dialogue texts with the user intention A;
wherein i is more than or equal to 1 and less than or equal to n;
s13, when ki/n is more than or equal to beta, considering the corresponding customer service intention Bi as a sub intention corresponding to the user intention A, wherein beta is a preset percentage coefficient;
s14, sequentially marking the number of dialog texts comprising each sub-intention corresponding to the user intention A in n dialog texts with the user intention A as z1, z2, … and zs;
and calculating according to the formula Y= (z 1/n+z2/n+, …, +zs/n) s to obtain an intensity value Y of the user intention A, and when Y is larger than a preset value Y1, considering the user intention A corresponding to Y as an upper intention, wherein the upper intention is the destination direction of the corresponding dialogue text.
4. A session scene based process mining method according to claim 3, wherein said β has a value of 0.65.
5. The session scene-based process mining method according to claim 3, wherein when two or more upper intents exist in one dialog text at the same time, the corresponding dialog text is deleted from the session data storage unit, and the subsequent dialog text combination division is not performed as a sample.
6. A method of mining a session scene based process according to claim 3, wherein the user intention is analyzed by intention recognition and the corresponding session processes are matched according to the different session scenes when the customer service session is performed.
7. A session scene-based process mining system, comprising:
a session data storage unit for storing session data;
the text log generating unit is used for analyzing and processing the session data to generate a dialogue text;
the intention recognition unit is used for analyzing the dialogue text through an intention recognition algorithm, acquiring user intention and customer service intention, and transmitting the acquired user intention and customer service intention to the control unit;
the control unit is used for analyzing the user intention and the customer service intention in the dialogue text and acquiring the appearance sequence of the customer service intention corresponding to the dialogue text pointed by different purposes;
and the conversation process generating unit is used for generating a conversation process according to the customer service intention and the appearance sequence of the customer service intention.
8. The conversation scene based process mining system of claim 7 wherein the conversation text is a text log generated from a text chat log.
9. The conversational scene-based process mining system of claim 8, wherein the dialog text is a text log that is converted from a voice log.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310344360.2A CN116541491A (en) | 2023-04-03 | 2023-04-03 | Flow mining system and mining method based on session scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310344360.2A CN116541491A (en) | 2023-04-03 | 2023-04-03 | Flow mining system and mining method based on session scene |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116541491A true CN116541491A (en) | 2023-08-04 |
Family
ID=87453221
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310344360.2A Pending CN116541491A (en) | 2023-04-03 | 2023-04-03 | Flow mining system and mining method based on session scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116541491A (en) |
-
2023
- 2023-04-03 CN CN202310344360.2A patent/CN116541491A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108052605A (en) | A kind of intelligent Answer System based on client feature library | |
| CN110162611A (en) | A kind of intelligent customer service answer method and system | |
| CN110489749B (en) | Business process optimization method of intelligent office automation system | |
| CN110516057B (en) | Petition question answering method and device | |
| CN106022708A (en) | Method for predicting employee resignation | |
| CN116644145A (en) | Session data processing method, device, equipment and storage medium | |
| CN117688165B (en) | Multi-edge collaborative customer service method, device, equipment and readable storage medium | |
| CN111144116B (en) | Document knowledge structured extraction method and device | |
| CN114265921A (en) | Question-answer knowledge base construction method and device, equipment, medium and product thereof | |
| CN116541491A (en) | Flow mining system and mining method based on session scene | |
| CN115438995B (en) | Business processing method and equipment for clothing customization enterprise based on knowledge graph | |
| CN115168603B (en) | Automatic feedback response method, device and storage medium for color ring back tone service process | |
| CN115203617A (en) | Webpage access single-button auxiliary input system based on RPA | |
| CN115687581A (en) | Power customer service interactive question and answer method and device based on attention mechanism | |
| CN113516454A (en) | Enterprise information management system and method based on cloud computing platform | |
| CN113159528A (en) | Post matching evaluation method and device | |
| CN115080732A (en) | Complaint work order processing method and device, electronic equipment and storage medium | |
| CN112153636A (en) | Method for predicting number portability and roll-out of telecommunication industry user based on machine learning | |
| CN116389644B (en) | Outbound system based on big data analysis | |
| CN116600053B (en) | Customer service system based on AI large language model | |
| CN117221447B (en) | Online telephone communication auxiliary support system based on AI technology | |
| CN117763120A (en) | Intention recognition system and method suitable for client chat records | |
| CN114090795B (en) | Two-way interaction intelligent service system and method based on equipment knowledge graph | |
| CN117349425B (en) | Knowledge item generation method, device, equipment and storage medium | |
| CN114706957B (en) | Trademark recommendation platform and method |
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 |