CN113869067A - Response method and system based on intelligent customer service - Google Patents
Response method and system based on intelligent customer service Download PDFInfo
- Publication number
- CN113869067A CN113869067A CN202111111415.2A CN202111111415A CN113869067A CN 113869067 A CN113869067 A CN 113869067A CN 202111111415 A CN202111111415 A CN 202111111415A CN 113869067 A CN113869067 A CN 113869067A
- Authority
- CN
- China
- Prior art keywords
- interactive
- content
- pairing
- consultation request
- layer
- 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
- 230000004044 response Effects 0.000 title claims abstract description 68
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000002452 interceptive effect Effects 0.000 claims abstract description 435
- 238000004458 analytical method Methods 0.000 claims abstract description 165
- 238000012545 processing Methods 0.000 claims abstract description 63
- 238000012549 training Methods 0.000 claims description 74
- 238000012216 screening Methods 0.000 claims description 39
- 230000010354 integration Effects 0.000 claims description 35
- 238000004364 calculation method Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 11
- 238000009792 diffusion process Methods 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 4
- 230000003993 interaction Effects 0.000 abstract description 14
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000006872 improvement Effects 0.000 description 4
- 238000010835 comparative analysis Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000000644 propagated effect Effects 0.000 description 3
- 241000894007 species Species 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000010977 jade Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000003607 modifier Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
-
- 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
- G06F16/35—Clustering; Classification
- G06F16/355—Class or cluster creation or modification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Probability & Statistics with Applications (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
According to the response method and system based on the intelligent customer service, the current interactive consultation request received by the front-end customer service interaction equipment in real time is input into the interactive content analysis thread obtained through pre-configuration for analysis, and the interactive content analysis result is obtained. And marking out interactive content description items in the current interactive consultation request according to the label of each key content attribute in the interactive content analysis result, comparing the interactive content description items of the current interactive consultation request with the interactive content description items of the historical interactive consultation requests of the current interactive consultation request, and determining the target description items of the current interactive consultation request. Therefore, the back-end response processing equipment can accurately identify the interactive content of the interactive consultation request according to the determined target description items, and effectively compares the interactive consultation request with the historical interactive consultation request so as to improve the accurate understanding of the intention of the user and further solve the problem of incomplete response of the customer service.
Description
Technical Field
The application relates to the technical field of intelligent customer service interaction, in particular to a response method and a response system based on intelligent customer service.
Background
In the continuously developing process of the information age, a user can contact the corresponding intelligent customer service end in various online modes, questions and problems met by the user are solved through the intelligent customer service end, the handling efficiency can be improved, and the user can be quickly served, so that good experience can be brought to the user.
However, the internet communication may cause disorder of the related data or error of the related data, which may result in that the intelligent customer service end may not accurately understand the service requirement of the user, in other words, when the intelligent customer service end does not accurately understand and identify the response service requirement of the user, it is difficult to accurately respond, and it is difficult to ensure the intelligence degree of the intelligent customer service end in processing the response service.
Disclosure of Invention
In view of this, the present application provides a response method and system based on intelligent customer service.
In a first aspect, a response method based on intelligent customer service is provided, where the method includes:
inputting a current interactive consultation request received by front-end customer service interactive equipment in real time into an interactive content analysis thread obtained by pre-configuration for analysis, and outputting an interactive content analysis result corresponding to the current interactive consultation request;
marking out interactive content description items in the current interactive consultation request according to the label of each key content attribute in the interactive content analysis result;
comparing the interactive content description items of the current interactive consultation request with the interactive content description items of the historical interactive consultation requests of the current interactive consultation request to determine the target description items of the current interactive consultation request;
and sending the target description items of the current interactive consultation request to a back-end response processing device for response.
Further, the interactive content analysis thread is obtained according to candidate standard texts which are received in advance and cover the interactive content texts through pairing network thread configuration.
Further, the interactive content analysis thread comprises a first analysis training layer, a second analysis training layer, a third analysis training layer and a fourth analysis training layer; the step of inputting the current interactive consultation request received by the front-end customer service interactive device in real time into an interactive content analysis thread obtained by pre-configuration for analysis and outputting an interactive content analysis result corresponding to the current interactive consultation request comprises the following steps:
sequentially utilizing the first analysis training layer and the second analysis training layer to calculate and process the current interactive consultation request to obtain the description content of the current interactive consultation request;
performing interactive semantic screening and interactive semantic integration processing on the description content by using the third analysis training layer to obtain an interactive semantic integration result of the current interactive consultation request;
and performing calculation processing and feature diffusion processing on the interactive semantic integration result by using the fourth analysis training layer to obtain an interactive content analysis result corresponding to the current interactive consultation request.
Further, the first analysis training layer comprises a plurality of first pairing layers and a plurality of second pairing layers, the first pairing layers and the second pairing layers are randomly arranged, at least one second pairing layer is arranged between two adjacent first pairing layers, and the second analysis training layer comprises a plurality of third pairing layers which are sequentially connected; the step of sequentially utilizing the first analysis training layer and the second analysis training layer to calculate and process the current interactive consultation request to obtain the description content of the current interactive consultation request comprises the following steps:
sequentially inputting the node word senses of the current interactive consultation request into a first pairing layer and a second pairing layer in the first analysis training layer for calculation processing to obtain a first description content event;
sequentially inputting the first description content event into a plurality of third pairing layers in the second analysis training layer for pairing processing to obtain the description content of the current interactive consultation request; calculating the input node word senses of each first pairing layer pair to obtain corresponding first pairing description contents, and outputting the first pairing description contents to a next pairing layer of the first pairing layers;
performing interactive semantic screening on the input node word senses by each second pairing layer to obtain second pairing description contents, and simultaneously outputting the second pairing description contents and the node word senses input into the second pairing layer to the next pairing layer;
and each third pairing layer pair carries out calculation processing on the input node word senses to obtain corresponding third pairing description contents, and the third pairing description contents are output to the next pairing layer of the third pairing layer pairs.
Further, the third analysis training layer comprises a plurality of fourth pairing layers and a fifth pairing layer; the step of performing interactive semantic screening and interactive semantic integration processing on the description content of the current interactive consultation request by using the third analysis training layer to obtain an interactive semantic integration result of the current interactive consultation request includes:
inputting the description content of the current interactive consultation request into each fourth pairing layer, sequentially performing interactive semantic screening processing to obtain a plurality of fourth pairing description contents, and outputting each obtained fourth pairing description content to the fifth pairing layer;
and the fifth pairing layer performs interactive semantic integration processing on each fourth pairing description content to obtain an interactive semantic integration result of the current interactive consultation request.
Further, the fourth analysis training layer comprises an upper screening layer and a sixth pairing layer, and the sixth pairing layer is sequentially connected to any one first pairing layer or any one second pairing layer in the upper screening layer and the first analysis training layer; the step of performing calculation processing and feature diffusion processing on the interactive semantic integration result of the current interactive consultation request by using the fourth analysis training layer to obtain an interactive content analysis result corresponding to the current interactive consultation request includes:
inputting the interactive semantic integration result of the current interactive consultation request into the upper screening layer to perform feature diffusion processing to obtain a screening node word sense and outputting the screening node word sense to the sixth pairing layer;
the sixth pairing layer receives the first pairing description content output by the connected first pairing layer or the second pairing description content output by the second pairing layer and the screening node word senses output by the upper screening layer, integrates the received node word senses to obtain an integrated node word sense, and calculates the integrated node word sense to obtain an interactive content analysis result corresponding to the current interactive consultation request.
Further, the step of defining the interactive content description item of the current interactive consultation request according to the label of each key content attribute in the interactive content parsing result includes:
determining all key content attributes with labels of 1 in the interactive content analysis result by using a minimum statistical unit;
judging whether the interactive content analysis result contains interactive content description items or not according to the importance degree of the key content attribute with the label of 1 in the minimum statistical unit in all the key content attributes of the minimum statistical unit;
if the interactive content description items are contained, the interactive content description items of the current interactive consultation request are planned according to the interactive content description items in the interactive content analysis result;
wherein, the step of determining all key content attributes with labels of 1 in the interactive content analysis result by using the minimum statistical unit includes:
acquiring key content attributes with relevance strength in a first dimension and a second dimension in sequence from all key content attributes with labels of 1 in the interactive content analysis result, wherein the relevance strength comprises a relevance maximum value and a relevance minimum value;
defining a minimum statistical unit according to the range type of the acquired key content attribute with the relevance strength in the interactive content analysis result, wherein each boundary of the minimum statistical unit passes through any key content attribute with the relevance strength;
wherein, the step of judging whether the interactive content analysis result includes the interactive content description item according to the importance degree of the key content attribute with the label of 1 in the minimum statistical unit in all the key content attributes of the minimum statistical unit includes:
calculating a first statistical type expression of interactive label description items consisting of key content attributes with labels of 1 in the minimum statistical unit, and calculating a second statistical type expression of the minimum statistical unit;
calculating a difference value between the first statistical species expression and the second statistical species expression;
and when the difference value is larger than a preset value, determining that the interactive label description item formed by the key content attribute with the label of 1 in the interactive content analysis result is the interactive content description item.
Further, the step of comparing the interactive content description item of the current interactive consultation request with the interactive content description item of the historical interactive consultation request of the current interactive consultation request to determine the target description item of the current interactive consultation request includes:
calculating to obtain the discrimination between the interactive content description items of the current interactive consultation request and the interactive content description items of the historical interactive consultation request of the current interactive consultation request;
when the discrimination is less than or equal to a preset threshold value, a target description item is defined in the current interactive consultation request according to the category of the interactive content description items of the historical interactive consultation request;
and when the discrimination is greater than the preset threshold value, taking the interactive content description item of the current interactive consultation request as the target description item.
In a second aspect, a response system based on intelligent customer service is provided, which comprises a processor and a memory, which are communicated with each other, wherein the processor is used for reading a computer program from the memory and executing the computer program, so as to realize the method.
In a third aspect, a computer-readable storage medium has stored thereon a computer program which, when executed, performs the above-described method.
According to the response method and system based on the intelligent customer service, the current interactive consultation request received by the front-end customer service interaction equipment in real time is input into the interactive content analysis thread obtained through pre-configuration for analysis, and the interactive content analysis result corresponding to the current interactive consultation request is obtained. And the interactive content description items in the current interactive consultation request are planned according to the label of each key content attribute in the interactive content analysis result, and then the interactive content description items of the current interactive consultation request are compared with the interactive content description items of the historical interactive consultation requests of the current interactive consultation request, so that the target description items of the current interactive consultation request are determined. Therefore, through mutual cooperation among the front-end customer service interaction equipment, the response system and the rear-end response processing equipment, the interactive consultation request can be accurately identified in interactive content according to the determined target description items, and the historical interactive consultation request is flexibly combined for comparative analysis, so that the understanding precision of the intention of the user can be improved, the rear-end response processing equipment can be ensured to pertinently determine an accurate response result based on the target description items, accurate and efficient response is facilitated, the response defect of the intelligent customer service is improved, and the intelligentization degree of the intelligent customer service in processing response services is ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a flowchart of a response method based on an intelligent customer service according to an embodiment of the present application.
Fig. 2 is a block diagram of an answer response device based on an intelligent customer service according to an embodiment of the present application.
Fig. 3 is an architecture diagram of an intelligent customer service-based response system according to an embodiment of the present application.
Detailed Description
In order to better understand the technical solutions, the technical solutions of the present application are described in detail below with reference to the drawings and specific embodiments, and it should be understood that the specific features in the embodiments and examples of the present application are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application, and the technical features in the embodiments and examples of the present application may be combined with each other without conflict.
Referring to fig. 1, a response method based on intelligent customer service is shown, which may include the technical solutions described in the following steps 100-400.
Step 100, inputting a current interactive consultation request received by the front-end customer service interactive equipment in real time into an interactive content analysis thread obtained by pre-configuration for analysis, and outputting an interactive content analysis result corresponding to the current interactive consultation request.
For example, the front-end customer service interaction device is used for collecting consultation information and complaint information input by a user (such as a service user device).
For example, the current interactive consultation request is used for representing data corresponding to communication between a user (such as business user equipment) and a customer service (such as a response system) (for example, an online article which needs to be purchased by the user, the article and the customer service are communicated with each other, and information of the article is known.
Further, the interactive content parsing thread is obtained by configuring the paired network thread according to candidate standard texts covering interactive content texts received in advance, such as an AI network.
Illustratively, the labels of the key content attributes are used for representing important information classifications (such as a post-service class, a complaint class and the like) expressed by the user of the interactive content parsing result.
Illustratively, the interactive content description items of the historical interactive consultation requests are used to characterize the content that the user interacted with the customer service in the interaction record.
Further, the objective descriptive matter of the current interactive consultation request is used for representing data (such as communication network faults, business operation problems, basic service problems and the like) which accurately represent the intention of the user.
Step 400, sending the object description item of the current interactive consultation request to a back-end response processing device for response.
For example, the back-end reply processing device may be a cloud processing platform, and is configured to further process related data transmitted by the reply response system. The answer response is used to indicate content to reply to the meaning expressed by the user (such as a service user equipment). Such as a user consulting an after-market question for a product, the response may be content related to the after-market service.
It can be understood that, when the technical solutions described in the above steps 100 to 400 are executed, the current interactive consultation request received by the front-end customer service interaction device in real time is input into the interactive content analysis thread configured in advance for analysis, so as to obtain an interactive content analysis result corresponding to the current interactive consultation request. And the interactive content description items in the current interactive consultation request are planned according to the label of each key content attribute in the interactive content analysis result, and then the interactive content description items of the current interactive consultation request are compared with the interactive content description items of the historical interactive consultation requests of the current interactive consultation request, so that the target description items of the current interactive consultation request are determined. Therefore, through mutual cooperation among the front-end customer service interaction equipment, the response system and the rear-end response processing equipment, the interactive consultation request can be accurately identified in interactive content according to the determined target description items, and the historical interactive consultation request is flexibly combined for comparative analysis, so that the understanding precision of the intention of the user can be improved, the rear-end response processing equipment can be ensured to pertinently determine an accurate response result based on the target description items, accurate and efficient response is facilitated, the response defect of the intelligent customer service is improved, and the intelligentization degree of the intelligent customer service in processing response services is ensured.
In order to illustrate the overall scheme more pictorially, an overall example is described below. The service user equipment a (mobile phone, tablet, etc.) may be a device for inputting user consultation information, then the front-end customer service interaction device B (may be an intelligent counter, etc.) collects and arranges the user consultation information in the service user equipment, then the response system C (may be a server, etc.) processes the relevant data arranged by the front-end customer service interaction device to determine the accuracy of the user intention, and finally the back-end response processing device D (may be a cloud processing platform, etc.) processes the data processed by the response system again, replies the data for the intention, and sends the replied information to the service user equipment.
In an actual implementation process, the inventor finds, through research and analysis, that when a current interactive consultation request received by a front-end customer service interactive device in real time is input into an interactive content analysis thread configured in advance for analysis, there is a problem that a plurality of analysis layers cause analysis disorder, so that it is difficult to accurately output an interactive content analysis result corresponding to the current interactive consultation request, and in order to improve the above technical problem, in an alternative embodiment, the interactive content analysis thread described in step 100 includes a first analysis training layer, a second analysis training layer, a third analysis training layer, and a fourth analysis training layer; the step of inputting the current interactive consultation request received by the front-end customer service interaction device in real time into an interactive content analysis thread configured in advance for analysis and outputting an interactive content analysis result corresponding to the current interactive consultation request may specifically include the following technical scheme described in step q 1-step q 3.
And q1, calculating the current interactive consultation request by sequentially utilizing the first analysis training layer and the second analysis training layer to obtain the description content of the current interactive consultation request.
And q2, performing interactive semantic screening and interactive semantic integration processing on the description content by using the third analysis training layer to obtain an interactive semantic integration result of the current interactive consultation request.
And q3, performing calculation processing and feature diffusion processing on the interactive semantic integration result by using the fourth analysis training layer to obtain an interactive content analysis result corresponding to the current interactive consultation request.
It is understood that, when the technical solution described in the above step q 1-step q3 is executed, the interactive content parsing thread includes a first analysis training layer, a second analysis training layer, a third analysis training layer and a fourth analysis training layer; when the current interactive consultation request received by the front-end customer service interactive equipment in real time is input into the interactive content analysis thread obtained by pre-configuration for analysis, the problem of analysis disorder caused by various analysis layers is solved, and therefore the interactive content analysis result corresponding to the current interactive consultation request can be accurately output.
In practical implementation of the technical solution, long-term analysis by the inventor finds that, when the first analysis training layer and the second analysis training layer are sequentially utilized to perform calculation processing on the current interactive consultation request, there is a problem that a first description content event is inaccurate, so that it is difficult to accurately obtain a description content of the current interactive consultation request, in order to improve the above technical problem, in an alternative embodiment, the first analysis training layer described in step q1 includes a plurality of first pairing layers and a plurality of second pairing layers, the first pairing layers and the second pairing layers are randomly arranged, at least one second pairing layer is provided between two adjacent first pairing layers, and the second analysis training layer includes a plurality of third pairing layers connected in sequence; the step of performing calculation processing on the current interactive consultation request by sequentially using the first analysis training layer and the second analysis training layer to make it difficult to accurately obtain the description content of the current interactive consultation request may specifically include the technical solutions described in the following steps q11 to q 14.
And q11, sequentially inputting the node word senses of the current interactive consultation request into a first pairing layer and a second pairing layer in the first analysis training layer for calculation processing to obtain a first description content event.
Step q12, sequentially inputting the first description content event into a plurality of third pairing layers in the second analysis training layer for pairing processing to obtain the description content of the current interactive consultation request; and each first pairing layer pair carries out calculation processing on the input node word senses to obtain corresponding first pairing description contents, and the first pairing description contents are output to the next pairing layer of the first pairing layer pairs.
And q13, performing interactive semantic screening on the input node word senses of each second pairing layer to obtain second pairing description contents, and simultaneously outputting the second pairing description contents and the node word senses input into the second pairing layer to the next pairing layer.
And q14, calculating the input node word senses of each third pairing layer pair to obtain corresponding third pairing description contents, and outputting the third pairing description contents to a next pairing layer of the third pairing layer.
It is understood that when the technical solutions described in the above steps q 11-q 14 are implemented, the first analysis training layer includes a plurality of first paired layers and a plurality of second paired layers, the first paired layers and the second paired layers are randomly arranged, at least one second paired layer is arranged between two adjacent first paired layers, and the second analysis training layer includes a plurality of sequentially connected third paired layers; when the first analysis training layer and the second analysis training layer are sequentially utilized to calculate and process the current interactive consultation request, the problem that a first description content event is inaccurate is solved, and therefore the description content of the current interactive consultation request can be accurately obtained.
When the inventor implements the method, it is found that when the third analysis training layer is used to perform interactive semantic screening and interactive semantic integration processing on the description content of the current interactive consultation request, there is a problem that the fourth pairing description content is not accurately output to the fifth pairing layer, so that it is difficult to accurately obtain the interactive semantic integration result of the current interactive consultation request, and in order to improve the above technical problem, in an alternative embodiment, the third analysis training layer described in step q2 includes a plurality of fourth pairing layers and a fifth pairing layer; the step of performing interactive semantic screening and interactive semantic integration processing on the description content of the current interactive consultation request by using the third analysis training layer to obtain an interactive semantic integration result of the current interactive consultation request may specifically include the following technical solutions described in step q21 and step q 22.
Step q21, inputting the description content of the current interactive consultation request into each fourth pairing layer, sequentially performing interactive semantic screening processing to obtain a plurality of fourth pairing description contents, and outputting each obtained fourth pairing description content to the fifth pairing layer.
And q22, performing interactive semantic integration processing on each fourth pairing description content by the fifth pairing layer to obtain an interactive semantic integration result of the current interactive consultation request.
It is understood that, when the technical solutions described in the above steps q21 and q22 are performed, the third analysis training layer includes a plurality of fourth pairing layers and a fifth pairing layer; when the third analysis training layer is used for carrying out interactive semantic screening and interactive semantic integration processing on the description content of the current interactive consultation request, the problem that the fourth pairing description content is inaccurate to be output to the fifth pairing layer is solved, and therefore the interactive semantic integration result of the current interactive consultation request can be accurately obtained.
In the application of the technical solution of the present application, the inventor finds that, when the fourth analysis training layer is used to perform calculation processing and feature diffusion processing on the interactive semantic integration result of the current interactive consultation request, there is a problem that a word sense of a screening node is not accurate, so that an interactive content analysis result corresponding to the current interactive consultation request can be accurately obtained, in order to improve the above technical problem, in an alternative embodiment, the fourth analysis training layer described in step q3 includes an upper screening layer and a sixth pairing layer, and the sixth pairing layer is sequentially connected to any one of the upper screening layer and the first analysis training layer or any one of the second pairing layer; the step of performing calculation processing and feature diffusion processing on the interactive semantic integration result of the current interactive consultation request by using the fourth analysis training layer to obtain the interactive content analysis result corresponding to the current interactive consultation request may specifically include the following technical solutions described in step q31 and step q 32.
And q31, inputting the interactive semantic integration result of the current interactive consultation request into the upper screening layer to perform feature diffusion processing to obtain a screening node word sense, and outputting the screening node word sense to the sixth pairing layer.
Step q32, the sixth pairing layer receives the first pairing description content output by the connected first pairing layer or the second pairing description content output by the second pairing layer and the screening node word senses output by the upper screening layer, integrates the received node word senses to obtain an integration node word sense, and calculates the integration node word sense to obtain an interactive content analysis result corresponding to the current interactive consultation request.
It is understood that when the technical solutions described in the above steps q31 and q32 are implemented, the fourth analysis training layer includes an upper screening layer and a sixth pairing layer, which is sequentially connected to any one first pairing layer or any one second pairing layer of the upper screening layer and the first analysis training layer; when the fourth analysis training layer is used for carrying out calculation processing and feature diffusion processing on the interactive semantic integration result of the current interactive consultation request, the problem that the word meaning of the screening node is inaccurate is solved, and therefore the interactive content analysis result corresponding to the current interactive consultation request can be accurately obtained.
The inventor finds that, when the interactive content description item of the current interactive consultation request is defined according to the label of each key content attribute in the interactive content analysis result, there is a problem that the key content attribute is inaccurate, so that it is difficult to precisely define the interactive content description item of the current interactive consultation request, and in order to improve the above technical problem, in an alternative embodiment, the step of defining the interactive content description item of the current interactive consultation request according to the label of each key content attribute in the interactive content analysis result, which is described in step 300, may specifically include the technical solutions described in the following steps w 1-w 3.
And step w1, determining all key content attributes with the label of 1 in the interactive content analysis result by using the minimum statistical unit. Illustratively, the minimum statistical unit is used to represent the minimum range of key content attributes for each category.
And step w2, judging whether the interactive content analysis result contains the interactive content description item according to the importance degree of the key content attribute with the label of 1 in the minimum statistical unit in all the key content attributes of the minimum statistical unit.
And step w3, if the interactive content description item is contained, the interactive content description item of the current interactive consultation request is planned according to the interactive content description item in the interactive content analysis result.
It can be understood that, when the technical solution described in the above-mentioned step w 1-step w3 is performed, when the interactive content description item of the current interactive consultation request is defined according to the label of each key content attribute in the interactive content parsing result, the problem of inaccuracy of the key content attribute is improved, so that the interactive content description item of the current interactive consultation request can be defined accurately.
It can be understood that, in practical applications, the inventor finds that, when the minimum statistical unit is used, there is a problem that the key content attribute of the relevance strength is inaccurate, so that it is difficult to accurately determine all key content attributes labeled as 1 in the interactive content parsing result, and in order to improve the above technical problem, in an alternative embodiment, the step of determining all key content attributes labeled as 1 in the interactive content parsing result by using the minimum statistical unit described in step w1 may specifically include the technical solutions described in steps w11 and w12 below.
And step w11, acquiring key content attributes with relevance strength sequentially in the first dimension and the second dimension from all key content attributes with the label of 1 in the interactive content analysis result, wherein the relevance strength comprises a maximum relevance value and a minimum relevance value.
And step w12, defining a minimum statistical unit according to the range type of the acquired key content attribute with the relevance strength in the interactive content analysis result, wherein each boundary of the minimum statistical unit passes through any key content attribute with the relevance strength.
It can be understood that when the technical solutions described in the above steps w11 and w12 are performed, the problem that the key content attribute improving the strength of association is inaccurate when the minimum statistical unit is used is solved, so that all the key content attributes labeled as 1 in the interactive content parsing result can be accurately determined.
In the process of applying the present application, the inventor finds that, when the importance degree of the key content attribute with the label of 1 in the minimum statistical unit is in all the key content attributes of the minimum statistical unit, there is a problem that the second statistical category of the minimum statistical unit is inaccurately expressed, so that it is difficult to accurately determine whether the interactive content parsing result covers the interactive content description item, and in order to improve the above technical problem, in one possible embodiment, the step w2 of determining whether the interactive content parsing result covers the interactive content description item according to the importance degree of the key content attribute with the label of 1 in the minimum statistical unit is in all the key content attributes of the minimum statistical unit may specifically include the technical solutions described in the following steps w 21-w 23.
And step w21, calculating a first statistical type expression of the interactive label description item consisting of the key content attribute with the label of 1 in the minimum statistical unit, and calculating a second statistical type expression of the minimum statistical unit.
And step w22, calculating the difference value between the first statistical type expression and the second statistical type expression.
And step w23, when the difference value is greater than a preset value, determining that the interactive label description item formed by the key content attribute with the label of 1 in the interactive content analysis result is the interactive content description item.
It can be understood that, when the technical solutions described in steps w 21-w 23 are executed, according to the importance degree of the key content attribute labeled as 1 in the minimum statistical unit in all the key content attributes of the minimum statistical unit, the problem that the second statistical category of the minimum statistical unit expresses inaccurately is improved, so that whether the interactive content description item is included in the interactive content parsing result can be accurately determined.
In the actual implementation process, the inventors have analyzed and researched, and found that when the interactive content description item of the current interactive consultation request is compared with the interactive content description item of the historical interactive consultation request of the current interactive consultation request, there is a problem that the discrimination is not accurate, so that it is difficult to accurately determine the target description item of the current interactive consultation request, and in order to improve the above technical problem, for some alternative embodiments, the step of comparing the interactive content description item of the current interactive consultation request with the interactive content description item of the historical interactive consultation request of the current interactive consultation request, and determining the target description item of the current interactive consultation request, which is described in step 300, may specifically include the technical solutions described in the following step e1 and step e 2.
Step e1, calculating the discrimination between the interactive content description items of the current interactive consultation request and the interactive content description items of the historical interactive consultation request of the current interactive consultation request; when the discrimination is smaller than or equal to a preset threshold value, a target description item is defined in the current interactive consultation request according to the category of the interactive content description items of the historical interactive consultation request.
And e2, when the discrimination is greater than the preset threshold, taking the interactive content description item of the current interactive consultation request as the target description item.
It can be understood that when the technical solutions described in the above steps e1 and e2 are performed, and the interactive contents description item of the current interactive consultation request is compared with the interactive contents description item of the historical interactive consultation request of the current interactive consultation request, the problem of inaccurate discrimination is improved, so that the target description item of the current interactive consultation request can be accurately determined.
The inventor finds that, when the discrimination between the interactive content description item of the current interactive consultation request and the interactive content description item of the historical interactive consultation request of the current interactive consultation request is calculated, there is a problem of inaccurate discrimination caused by a plurality of first sub-description items, and in order to improve the above technical problem, in one possible embodiment, the step of calculating the discrimination between the interactive content description item of the current interactive consultation request and the interactive content description item of the historical interactive consultation request of the current interactive consultation request described in step e1 may specifically include the technical solutions described in the following step e11 and step e 22.
And e11, sequentially dividing the interactive content description items of the current interactive consultation request into a plurality of first sub-description items and the interactive content description items of the historical interactive consultation request into a plurality of second sub-description items according to the same dividing rule.
Step e12, for each first sub-description item, calculating to obtain the discrimination between the side emphasis point of the first sub-description item and the side emphasis point of the corresponding second sub-description item.
It can be understood that when the technical solutions described in the above steps e11 and e22 are performed, the discrimination between the interactive contents description item of the current interactive consultation request and the interactive contents description item of the historical interactive consultation request of the current interactive consultation request is calculated, and the problem of inaccurate discrimination caused by the plurality of first sub-description items is improved.
On the basis, please refer to fig. 2 in combination, there is provided a response apparatus 200 based on intelligent customer service, which is applied to a response system, and the apparatus includes:
a result analysis module 210, configured to input a current interactive consultation request received by a front-end customer service interaction device in real time into an interactive content analysis thread configured in advance for analysis, and output an interactive content analysis result corresponding to the current interactive consultation request;
the item planning module 220 is configured to plan an interactive content description item in the current interactive consultation request according to a tag of each key content attribute in the interactive content parsing result;
an item comparison module 230, configured to compare the interactive content description item of the current interactive consultation request with the interactive content description item of the historical interactive consultation request of the current interactive consultation request, and determine a target description item of the current interactive consultation request;
and the data response module 240 is configured to send the target description item of the current interactive consultation request to a back-end response processing device for response.
On the basis of the above, please refer to fig. 3, which shows a response system 300 based on intelligent customer service, comprising a processor 310 and a memory 320, which are communicated with each other, wherein the processor 310 is configured to read a computer program from the memory 320 and execute the computer program, so as to implement the above method.
On the basis of the above, there is also provided a computer-readable storage medium on which a computer program is stored, which when executed implements the above-described method.
In summary, based on the above scheme, the current interactive consultation request received by the front-end customer service interaction device in real time is input into the interactive content analysis thread configured in advance for analysis, so as to obtain an interactive content analysis result corresponding to the current interactive consultation request. And the interactive content description items in the current interactive consultation request are planned according to the label of each key content attribute in the interactive content analysis result, and then the interactive content description items of the current interactive consultation request are compared with the interactive content description items of the historical interactive consultation requests of the current interactive consultation request, so that the target description items of the current interactive consultation request are determined. Therefore, through mutual cooperation among the front-end customer service interaction equipment, the response system and the rear-end response processing equipment, the interactive consultation request can be accurately identified in interactive content according to the determined target description items, and the historical interactive consultation request is flexibly combined for comparative analysis, so that the understanding precision of the intention of the user can be improved, the rear-end response processing equipment can be ensured to pertinently determine an accurate response result based on the target description items, accurate and efficient response is facilitated, the response defect of the intelligent customer service is improved, and the intelligentization degree of the intelligent customer service in processing response services is ensured.
It should be appreciated that the system and its modules shown above may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory for execution by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided, for example, on a carrier medium such as a diskette, CD-or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, for example, or by a combination of the above hardware circuits and software (e.g., firmware).
It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.
Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered merely illustrative and not restrictive of the broad application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.
Also, this application uses specific language to describe embodiments of the application. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the present application is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the present application may be combined as appropriate.
Moreover, those skilled in the art will appreciate that aspects of the present application may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereon. Accordingly, various aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.
The computer storage medium may comprise a propagated data signal with the computer program code embodied therewith, for example, on baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, etc., or any suitable combination. A computer storage medium may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated over any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or any combination of the preceding.
Computer program code required for the operation of various portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, a conventional programming language such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages, and the like. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).
Additionally, the order in which elements and sequences of the processes described herein are processed, the use of alphanumeric characters, or the use of other designations, is not intended to limit the order of the processes and methods described herein, unless explicitly claimed. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.
Similarly, it should be noted that in the preceding description of embodiments of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.
Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the numbers allow for adaptive variation. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.
The entire contents of each patent, patent application publication, and other material cited in this application, such as articles, books, specifications, publications, documents, and the like, are hereby incorporated by reference into this application. Except where the application is filed in a manner inconsistent or contrary to the present disclosure, and except where the claim is filed in its broadest scope (whether present or later appended to the application) as well. It is noted that the descriptions, definitions and/or use of terms in this application shall control if they are inconsistent or contrary to the statements and/or uses of the present application in the material attached to this application.
Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present application. Other variations are also possible within the scope of the present application. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the present application can be viewed as being consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to only those embodiments explicitly described and depicted herein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A response method based on intelligent customer service is characterized in that the response method is applied to a response system, and the method comprises the following steps:
inputting a current interactive consultation request received by front-end customer service interactive equipment in real time into an interactive content analysis thread obtained by pre-configuration for analysis, and outputting an interactive content analysis result corresponding to the current interactive consultation request;
marking out interactive content description items in the current interactive consultation request according to the label of each key content attribute in the interactive content analysis result;
comparing the interactive content description items of the current interactive consultation request with the interactive content description items of the historical interactive consultation requests of the current interactive consultation request to determine the target description items of the current interactive consultation request;
and sending the target description items of the current interactive consultation request to a back-end response processing device for response.
2. The response method of intelligent customer service according to claim 1, wherein the interactive content parsing thread is obtained by matching network thread configuration according to candidate standard texts covering interactive content texts received in advance.
3. The response method of intelligent customer service according to claim 1, wherein the interactive contents parsing thread includes a first analysis training layer, a second analysis training layer, a third analysis training layer and a fourth analysis training layer; the step of inputting the current interactive consultation request received by the front-end customer service interactive device in real time into an interactive content analysis thread obtained by pre-configuration for analysis and outputting an interactive content analysis result corresponding to the current interactive consultation request comprises the following steps:
sequentially utilizing the first analysis training layer and the second analysis training layer to calculate and process the current interactive consultation request to obtain the description content of the current interactive consultation request;
performing interactive semantic screening and interactive semantic integration processing on the description content by using the third analysis training layer to obtain an interactive semantic integration result of the current interactive consultation request;
and performing calculation processing and feature diffusion processing on the interactive semantic integration result by using the fourth analysis training layer to obtain an interactive content analysis result corresponding to the current interactive consultation request.
4. The response method of the intelligent customer service according to claim 3, wherein the first analysis training layer comprises a plurality of first pairing layers and a plurality of second pairing layers, the first pairing layers and the second pairing layers are randomly arranged, at least one second pairing layer is arranged between two adjacent first pairing layers, and the second analysis training layer comprises a plurality of third pairing layers which are sequentially connected; the step of sequentially utilizing the first analysis training layer and the second analysis training layer to calculate and process the current interactive consultation request to obtain the description content of the current interactive consultation request comprises the following steps:
sequentially inputting the node word senses of the current interactive consultation request into a first pairing layer and a second pairing layer in the first analysis training layer for calculation processing to obtain a first description content event;
sequentially inputting the first description content event into a plurality of third pairing layers in the second analysis training layer for pairing processing to obtain the description content of the current interactive consultation request; calculating the input node word senses of each first pairing layer pair to obtain corresponding first pairing description contents, and outputting the first pairing description contents to a next pairing layer of the first pairing layers;
performing interactive semantic screening on the input node word senses by each second pairing layer to obtain second pairing description contents, and simultaneously outputting the second pairing description contents and the node word senses input into the second pairing layer to the next pairing layer;
and each third pairing layer pair carries out calculation processing on the input node word senses to obtain corresponding third pairing description contents, and the third pairing description contents are output to the next pairing layer of the third pairing layer pairs.
5. The response method of intelligent customer service according to claim 3, wherein the third analysis training layer comprises a plurality of fourth pairing layers and a fifth pairing layer; the step of performing interactive semantic screening and interactive semantic integration processing on the description content of the current interactive consultation request by using the third analysis training layer to obtain an interactive semantic integration result of the current interactive consultation request includes:
inputting the description content of the current interactive consultation request into each fourth pairing layer, sequentially performing interactive semantic screening processing to obtain a plurality of fourth pairing description contents, and outputting each obtained fourth pairing description content to the fifth pairing layer;
and the fifth pairing layer performs interactive semantic integration processing on each fourth pairing description content to obtain an interactive semantic integration result of the current interactive consultation request.
6. The response method of intelligent customer service according to claim 4, wherein the fourth analysis training layer comprises an upper screening layer and a sixth pairing layer, and the sixth pairing layer is sequentially connected to any one first pairing layer or any one second pairing layer of the upper screening layer and the first analysis training layer; the step of performing calculation processing and feature diffusion processing on the interactive semantic integration result of the current interactive consultation request by using the fourth analysis training layer to obtain an interactive content analysis result corresponding to the current interactive consultation request includes:
inputting the interactive semantic integration result of the current interactive consultation request into the upper screening layer to perform feature diffusion processing to obtain a screening node word sense and outputting the screening node word sense to the sixth pairing layer;
the sixth pairing layer receives the first pairing description content output by the connected first pairing layer or the second pairing description content output by the second pairing layer and the screening node word senses output by the upper screening layer, integrates the received node word senses to obtain an integrated node word sense, and calculates the integrated node word sense to obtain an interactive content analysis result corresponding to the current interactive consultation request.
7. The response method of intelligent customer service according to any one of claims 1-6, wherein said step of defining interactive content description items of said current interactive consultation request according to the label of each key content attribute in said interactive content parsing result comprises:
determining all key content attributes with labels of 1 in the interactive content analysis result by using a minimum statistical unit;
judging whether the interactive content analysis result contains interactive content description items or not according to the importance degree of the key content attribute with the label of 1 in the minimum statistical unit in all the key content attributes of the minimum statistical unit;
if the interactive content description items are contained, the interactive content description items of the current interactive consultation request are planned according to the interactive content description items in the interactive content analysis result;
wherein, the step of determining all key content attributes with labels of 1 in the interactive content analysis result by using the minimum statistical unit includes:
acquiring key content attributes with relevance strength in a first dimension and a second dimension in sequence from all key content attributes with labels of 1 in the interactive content analysis result, wherein the relevance strength comprises a relevance maximum value and a relevance minimum value;
defining a minimum statistical unit according to the range type of the acquired key content attribute with the relevance strength in the interactive content analysis result, wherein each boundary of the minimum statistical unit passes through any key content attribute with the relevance strength;
wherein, the step of judging whether the interactive content analysis result includes the interactive content description item according to the importance degree of the key content attribute with the label of 1 in the minimum statistical unit in all the key content attributes of the minimum statistical unit includes:
calculating a first statistical type expression of interactive label description items consisting of key content attributes with labels of 1 in the minimum statistical unit, and calculating a second statistical type expression of the minimum statistical unit;
calculating a difference value between the first statistical species expression and the second statistical species expression;
and when the difference value is larger than a preset value, determining that the interactive label description item formed by the key content attribute with the label of 1 in the interactive content analysis result is the interactive content description item.
8. The response method of intelligent customer service according to any one of claims 1-6, wherein said step of comparing the interactive content description items of the current interactive consultation request with the interactive content description items of the historical interactive consultation requests of the current interactive consultation request to determine the target description items of the current interactive consultation request comprises:
calculating to obtain the discrimination between the interactive content description items of the current interactive consultation request and the interactive content description items of the historical interactive consultation request of the current interactive consultation request;
when the discrimination is less than or equal to a preset threshold value, a target description item is defined in the current interactive consultation request according to the category of the interactive content description items of the historical interactive consultation request;
and when the discrimination is greater than the preset threshold value, taking the interactive content description item of the current interactive consultation request as the target description item.
9. An intelligent customer service based response system, comprising a processor and a memory in communication with each other, the processor being configured to read a computer program from the memory and execute the computer program to implement the method of any one of claims 1-8.
10. A computer-readable storage medium, in which a computer program is stored which, when running, performs the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111111415.2A CN113869067A (en) | 2021-09-23 | 2021-09-23 | Response method and system based on intelligent customer service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111111415.2A CN113869067A (en) | 2021-09-23 | 2021-09-23 | Response method and system based on intelligent customer service |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113869067A true CN113869067A (en) | 2021-12-31 |
Family
ID=78993281
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111111415.2A Pending CN113869067A (en) | 2021-09-23 | 2021-09-23 | Response method and system based on intelligent customer service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113869067A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114358420A (en) * | 2022-01-04 | 2022-04-15 | 苏州博士创新技术转移有限公司 | Business workflow intelligent optimization method and system based on industrial ecology |
-
2021
- 2021-09-23 CN CN202111111415.2A patent/CN113869067A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114358420A (en) * | 2022-01-04 | 2022-04-15 | 苏州博士创新技术转移有限公司 | Business workflow intelligent optimization method and system based on industrial ecology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200005117A1 (en) | Artificial intelligence assisted content authoring for automated agents | |
| Miric et al. | Using supervised machine learning for large‐scale classification in management research: The case for identifying artificial intelligence patents | |
| CN105573966A (en) | Adaptive Modification of Content Presented in Electronic Forms | |
| US11367008B2 (en) | Artificial intelligence techniques for improving efficiency | |
| CN113378554B (en) | Intelligent interaction method and system for medical information | |
| CN111210321B (en) | Risk early warning method and system based on contract management | |
| CN113869067A (en) | Response method and system based on intelligent customer service | |
| CN114661994A (en) | User interest data processing method and system based on artificial intelligence and cloud platform | |
| CN114090878A (en) | Position recommendation method, position recommendation device, electronic equipment, readable medium and program product | |
| US20220004947A1 (en) | Logistics route prediction method and apparatus | |
| CN113380363B (en) | Medical data quality evaluation method and system based on artificial intelligence | |
| US10353929B2 (en) | System and method for computing critical data of an entity using cognitive analysis of emergent data | |
| CN115470790A (en) | Method and device for identifying named entities in file | |
| US11803792B2 (en) | Risk management | |
| US11113081B2 (en) | Generating a video for an interactive session on a user interface | |
| CN114020916A (en) | Text classification method and device, storage medium and electronic equipment | |
| CN114611478B (en) | Information processing method and system based on artificial intelligence and cloud platform | |
| Meng et al. | Forecasting service quality dynamics based on integrated method with GM (1, 1) model and Markov chain | |
| Yaremchuck et al. | Search of similar programs using code metrics and big data-based assessment of software reliability | |
| CN110955755A (en) | Method and system for determining target standard information | |
| Rath et al. | Role of artificial intelligence and machine learning in product design and manufacturing | |
| Valtonen et al. | Human-in-the-loop: Explainable or accurate artificial intelligence by exploiting human bias? | |
| CN111782776A (en) | Method and device for realizing intention identification through slot filling | |
| Turgut et al. | Business Analytics for Managers | |
| US20240062016A1 (en) | Systems and Methods for Textual Classification Using Natural Language Understanding Machine Learning Models for Automating Business Processes |
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 |