CN112000784A - User data processing method, device and equipment combining RPA and AI and storage medium - Google Patents
User data processing method, device and equipment combining RPA and AI and storage medium Download PDFInfo
- Publication number
- CN112000784A CN112000784A CN202010795925.5A CN202010795925A CN112000784A CN 112000784 A CN112000784 A CN 112000784A CN 202010795925 A CN202010795925 A CN 202010795925A CN 112000784 A CN112000784 A CN 112000784A
- Authority
- CN
- China
- Prior art keywords
- user
- intention
- word slot
- word
- conversation
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 22
- 230000003993 interaction Effects 0.000 claims abstract description 91
- 238000000034 method Methods 0.000 claims abstract description 63
- 238000012545 processing Methods 0.000 claims description 66
- 230000014759 maintenance of location Effects 0.000 claims description 9
- 230000009191 jumping Effects 0.000 claims description 7
- 238000013500 data storage Methods 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 36
- 238000003058 natural language processing Methods 0.000 abstract 2
- 238000010586 diagram Methods 0.000 description 9
- 238000004801 process automation Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000002360 preparation method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Human Computer Interaction (AREA)
- Development Economics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a user data processing method, device and equipment combining RPA and AI and a storage medium. Natural Language Processing (NLP) applied to artificial intelligence AI, the method comprising: acquiring access information of a user; determining a target business intention of the user according to the access information, wherein the target business intention corresponds to a plurality of word slots, and each word slot corresponds to a group of inquiry sentences; performing conversation interaction with the user by adopting the query sentence of the word slot corresponding to the target service intention to obtain a conversation sentence input by the user; and generating and outputting user data corresponding to the target business intention according to the conversation statement so as to understand the intention. According to the method and the device, interaction with the user can be automatically carried out through the word slot and the inquiry sentence corresponding to the preset service intention, the user data is obtained, and therefore the efficiency of obtaining the user data is improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a storage medium for processing user data in combination with an RPA (robot Process Automation) and an AI (Artificial Intelligence).
Background
Robot Process Automation (RPA) simulates the operation of a human on a computer through specific robot software and automatically executes Process tasks according to rules. Artificial Intelligence (AI) is a technical science that studies and develops theories, methods, techniques and application systems for simulating, extending and expanding human Intelligence.
With the development of internet technology, more and more enterprises carry out product publicity through networks. The user can learn about the interested business product by browsing the product publicity page provided by the enterprise. The enterprise carries out conversation interaction with the user browsing the page through the dialog box on the page, and records data such as business intention, contact information and the like of the user so as to carry out proper product popularization on the user in the following process.
In the related art, a manual customer service performs session interaction with a user browsing a page, and fills the data of the user in a user data sheet.
However, since one manual customer service can only perform session interaction with several users at the same time, and the speed of manually filling in user data is slow, the user data acquisition efficiency is low.
Disclosure of Invention
The embodiment of the application provides a user data processing method, device, equipment and storage medium combining RPA and AI, so as to solve the problem of low efficiency of manually acquiring user data.
In a first aspect, an embodiment of the present application provides a user data processing method combining an RPA and an AI, including:
acquiring access information of a user;
determining a target business intention of the user according to the access information, wherein the target business intention corresponds to a plurality of word slots, and each word slot corresponds to a group of inquiry sentences;
performing conversation interaction with the user by adopting the query sentence of the word slot corresponding to the target service intention to obtain a conversation sentence input by the user;
and generating and outputting user data corresponding to the target business intention according to the conversation statement.
In one possible embodiment, the unfilled word slots are at least one;
adopting the query sentence corresponding to the unfilled word slot to perform conversation interaction with a user, wherein the conversation interaction comprises the following steps:
for each unfilled word slot, pushing an inquiry statement corresponding to the unfilled word slot to a user, and receiving a conversation statement input by the user;
after receiving the conversational sentence input by the user, the method further comprises:
determining whether a new service intention exists according to the conversation statement, and carrying out conversation interaction with a user by adopting an inquiry statement of a word slot corresponding to the new service intention when the new service intention exists, and filling the word slot corresponding to the new service intention;
after the word slot corresponding to the new service intention is filled, skipping to execute the following steps: and performing conversation interaction with the user by adopting the query sentence of the word slot corresponding to the target business intention.
In one possible implementation, before performing a conversational interaction with a user using a query statement of a word slot corresponding to the new business intent, the method further includes:
and data storage is carried out on the word slot which is preset and shared with the new service intention in the filled word slots.
In a possible implementation manner, generating and outputting user data corresponding to the target business intention according to the conversation statement includes:
extracting vocabularies matched with the word slots corresponding to the target business intents from the conversation sentences, and filling the vocabularies into the corresponding word slots;
and generating and outputting user data corresponding to the target business intention according to the word slot corresponding to the target business intention and the words filled in the word slot.
In one possible implementation, the word slot comprises a contact address word slot;
generating and outputting user data corresponding to the target service intention according to the word slot corresponding to the target service intention and the words filled in the word slot, wherein the user data comprises:
determining whether the contact word slot is populated;
and when the contact way word slot is filled, generating and outputting user data corresponding to the target business intention according to the word slot corresponding to the target business intention and the filled words.
In one possible implementation, when the contact word slot is filled, the method further comprises:
and determining that a jump instruction exists, and before jumping, carrying out data retention on a preset word slot shared with the target service intention.
In one possible embodiment, the conversational utterances comprise question utterances;
the method further comprises the following steps:
and extracting the vocabulary matched with the word slot corresponding to the target business intention from the question sentence, and filling the vocabulary into the corresponding word slot.
In one possible embodiment, the method further comprises:
replying the question statement, and after replying the question statement, skipping to execute the following steps: performing conversation interaction with a user by adopting an inquiry statement of the word slot corresponding to the target service intention;
wherein replying to the question statement comprises:
after receiving the question sentences, searching questions matched with the question sentences from a preset question-answer database, and pushing answer texts corresponding to the questions matched with the question sentences to a user, wherein the question-answer database comprises a plurality of groups of corresponding questions and answer texts;
or based on table look-up logic corresponding to the question sentence, searching data matched with the question sentence from a preset knowledge data table, generating an answer text according to the data matched with the question sentence, and pushing the answer text to a user.
In one possible embodiment, the access information includes:
keywords of the user search.
In one possible embodiment, the access information further includes:
attribute information of a user, wherein the attribute information includes at least one of: page information of a page currently accessed by a user, question statements sent by the user on the currently accessed page, tags of the user and network address information of the user;
determining a welcome language according to the attribute information, and pushing the welcome language to a user.
In a second aspect, an embodiment of the present application provides a user data processing apparatus combining an RPA and an AI, including:
the acquisition module is used for acquiring the access information of the user;
the processing module is used for determining a target business intention of the user according to the access information, wherein the target business intention corresponds to a plurality of word slots, and each word slot corresponds to a group of inquiry sentences;
the interaction module is used for carrying out conversation interaction with the user by adopting the inquiry sentences of the word slots corresponding to the target business intents to obtain conversation sentences input by the user;
and the output module is used for generating and outputting the user data corresponding to the target service intention according to the conversation statement.
In a possible implementation manner, the interaction module is specifically configured to:
determining unfilled word slots in the word slots corresponding to the target business intention;
and performing conversation interaction with the user by adopting the query sentences corresponding to the unfilled word slots.
In one possible embodiment, the unfilled word slots are at least one;
the interaction module is specifically configured to:
for each unfilled word slot, pushing an inquiry statement corresponding to the unfilled word slot to a user, and receiving a conversation statement input by the user;
the interaction module is further configured to:
determining whether a new service intention exists according to the conversation statement, and carrying out conversation interaction with a user by adopting an inquiry statement of a word slot corresponding to the new service intention when the new service intention exists, and filling the word slot corresponding to the new service intention;
after the word slot corresponding to the new service intention is filled, skipping to execute the following steps: and performing conversation interaction with the user by adopting the query sentence of the word slot corresponding to the target business intention.
In a possible implementation, the interaction module is further configured to:
and before conversation interaction is carried out between the inquiry statement of the word slot corresponding to the new business intention and the user, data storage is carried out on the preset word slot shared with the new business intention in the filled word slot.
In a possible implementation, the output module is specifically configured to:
extracting vocabularies matched with the word slots corresponding to the target business intents from the conversation sentences, and filling the vocabularies into the corresponding word slots;
and generating and outputting user data corresponding to the target business intention according to the word slot corresponding to the target business intention and the words filled in the word slot.
In one possible implementation, the word slot comprises a contact address word slot;
the output module is specifically configured to:
determining whether the contact word slot is populated;
and when the contact way word slot is filled, generating and outputting user data corresponding to the target business intention according to the word slot corresponding to the target business intention and the filled words.
In a possible implementation, the output module is further configured to:
and when the contact way word slot is filled, determining that a jump instruction exists, and before jumping, carrying out data retention on a preset word slot shared with the target service intention.
In one possible embodiment, the conversational utterances comprise question utterances;
the output module is further configured to:
and extracting the vocabulary matched with the word slot corresponding to the target business intention from the question sentence, and filling the vocabulary into the corresponding word slot.
In a possible implementation, the interaction module is further configured to:
after the question statement is received, replying the question statement, and after the question statement is replied, skipping to executing the following steps: performing conversation interaction with a user by adopting an inquiry statement of the word slot corresponding to the target service intention;
wherein replying to the question statement comprises:
searching questions matched with the question sentences from a preset question-answer database, and pushing answer texts corresponding to the questions matched with the question sentences to a user, wherein the question-answer database comprises a plurality of groups of corresponding questions and answer texts;
or based on table look-up logic corresponding to the question sentence, searching data matched with the question sentence from a preset knowledge data table, generating an answer text according to the data matched with the question sentence, and pushing the answer text to a user.
In one possible embodiment, the access information includes:
keywords of the user search.
In one possible embodiment, the access information further includes:
attribute information of a user, wherein the attribute information includes at least one of: page information of a page currently accessed by a user, question statements sent by the user on the currently accessed page, tags of the user and network address information of the user;
the interaction module is further configured to:
determining a welcome language according to the attribute information, and pushing the welcome language to a user.
In a third aspect, an embodiment of the present application provides a user data processing apparatus, including: at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the method of user data processing in combination with RPA and AI as described above in the first aspect and in various possible implementations of the first aspect.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where a computer executing instruction is stored, and when a processor executes the computer executing instruction, the method for processing user data in combination with an RPA and an AI according to the first aspect and various possible implementations of the first aspect is implemented.
According to the user data processing method, device, equipment and storage medium combining RPA and AI, the access information of a user is obtained, the target service intention of the user is determined according to the access information, the target service intention corresponds to a plurality of word slots, each word slot corresponds to one group of inquiry sentences, then conversation interaction is carried out between the inquiry sentences of the word slots corresponding to the target service intention and the user, conversation sentences input by the user are obtained, user data corresponding to the target service intention are generated and output according to the conversation sentences, interaction can be automatically carried out between the user and the user through the preset word slots corresponding to the service intention and the inquiry sentences, and user data are obtained, so that the efficiency of obtaining the user data is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
FIG. 1 is a block diagram of a user data processing system incorporating RPA and AI according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a user data processing method combining an RPA and an AI according to an embodiment of the present application;
fig. 3 is a schematic diagram of a session window provided in an embodiment of the present application;
fig. 4 is a schematic flowchart of a user data processing method combining RPA and AI according to another embodiment of the present application;
fig. 5 is a schematic flowchart of a user data processing method combining RPA and AI according to another embodiment of the present application;
fig. 6 is a schematic diagram of a program element for implementing a user data processing method in conjunction with RPA and AI according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of a user data processing apparatus incorporating an RPA and an AI according to an embodiment of the present application;
fig. 8 is a schematic hardware structure diagram of a user data processing device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 is a schematic architecture diagram of a user data processing system combining an RPA and an AI according to an embodiment of the present application. As shown in fig. 1, the user data processing system combining RPA and AI may include a terminal 11 and a server 12. The terminal may be a mobile phone, a tablet, a notebook computer, a desktop computer, and the like, which is not limited herein.
In one application scenario, the server 12 may serve as an execution subject of the RPA and AI combined user data processing method provided by the present embodiment. The user can access the web page of the enterprise through the terminal 11, and the terminal 11 transmits the access information of the user to the server 12. The server 12 may determine a target service intention of the user according to the access information of the user, and then transmit an inquiry sentence of a word slot corresponding to the target service intention to the terminal 11. The terminal 11 displays the inquiry sentence to the user and transmits the conversation sentence input by the user to the server 12, thereby realizing conversation interaction with the user. The server 12 generates user data according to the conversation statement in the conversation interaction process with the user, and sends the user data to the terminal of the enterprise staff, so that the enterprise staff can sort the user data, or carry out product promotion according to the user data, and the like.
In another application scenario, the terminal 11 may be used as an execution subject of the user data processing method combining RPA and AI provided in this embodiment. The user can access the web page of the enterprise through the terminal 11, the terminal 11 can determine the target business intention of the user according to the access information of the user, then display the query sentence of the word slot corresponding to the target business intention to the user, receive the conversation sentence input by the user, and realize conversation interaction with the user. The terminal 11 generates user data from a conversation sentence in a conversation interaction process with the user. The terminal 11 may send the user data to a terminal of an enterprise worker through the server 12, so that the enterprise worker may sort the user data, or may promote products according to the user data.
Compared with the prior art that session interaction is performed between the manual customer service and the user accessing the page, and the manual customer service records user data, the efficiency is low, the embodiment can automatically interact with the user through the word slot and the query sentence corresponding to the preset service intention, so that the user data is obtained, and the efficiency of obtaining the user data is further improved.
Fig. 2 is a schematic flowchart of a user data processing method combining an RPA and an AI according to an embodiment of the present application. The main body of the user data processing method combining RPA and AI provided in this embodiment is a user data processing device, which may be the above-mentioned terminal or server, and is not limited herein.
It should be noted that "processing" in the present application refers to a data processing process combining robot process automation RPA and artificial intelligence AI, that is, the data processing process is a full-process automation data processing process, and the data processing process is also combined with artificial intelligence AI to implement full-process automation parsing processing on user data.
For example, in the application, the access information of the user is automatically acquired in the full process based on the full-process automatic data processing process, the step of determining the target business intention of the user according to the access information is executed, wherein the target business intention corresponds to a plurality of word slots, and each word slot corresponds to a group of query sentences; and generating and outputting user data corresponding to the target business intention according to the conversation statement.
As shown in fig. 2, the method includes:
s201, obtaining access information of a user.
S202, determining a target business intention of the user according to the access information, wherein the target business intention corresponds to a plurality of word slots, and each word slot corresponds to a group of inquiry sentences.
In the present application, the term "plurality" means two or more, that is, a plurality of grooves means two or more grooves.
The business intention may be used to characterize a business intention of the user, that is, the business intention may be used to describe a business service that the user needs to acquire.
In this embodiment, when the user accesses the page, the user data processing device may obtain access information of the user. Optionally, the access information may include: keywords of the user search. The access information may further include: the page information of the page currently accessed by the user, the question and statement sent by the user on the currently accessed page, and the like, which are not limited herein. The user data processing device may determine the user's target business intent based on the one or more access information.
For example, the keyword may be a keyword entered by a user on a search page of an enterprise. The user data processing device may determine the user's target business intent from the keywords searched by the user. Taking the academic consultation scene as an example, if the user searches for "learning to swim" on the search page of the enterprise, the page jumps from the search page of the enterprise to the business display page of the enterprise, and the business displayed on the business display page comprises "learning to swim", "leaving to school", and the like. The user data processing equipment can determine that the target business intention of the user is 'learning tour' instead of 'leaving to learn' according to the fact that the keyword searched by the user is 'learning tour', and then performs conversation interaction with the user by adopting the inquiry statement of the word slot corresponding to the 'learning tour'.
Optionally, the accessing information may further include:
attribute information of the user, wherein the attribute information includes but is not limited to at least one of the following: the method comprises the following steps of page information of a page currently visited by a user, question statements sent by the user on the currently visited page, tags of the user and network address information of the user.
For example, if the page of the page currently visited by the user is a page of a "learning to swim" business, the user data processing device may determine that the target business intent of the user is "learning to swim". The question statement sent by the user on the currently visited page is "leave to learn which country is good", and the user data processing device may determine that the user's target business intent is "learn to swim". The tag of the user may be a tag generated by the user data processing device for the user according to the historical browsing record and the session of the user, or may be a tag set by the user, which is not limited herein. For example, the user may set the label "leave student" and the user data processing device may determine that the user's target business intent is "leave school. The user data processing device may determine the location of the user according to the network address information of the user, for example, if the user data processing device determines that the location of the user is in the united states, a conversation is performed with the user in english.
The above method may further comprise:
and determining the welcome words according to the attribute information, and pushing the welcome words to the user.
In this embodiment, when the user accesses the current page, the user data processing device may determine the welcome language according to the attribute information. For example, welcome words of different languages, different user tags and different service intentions can be preset, the user data processing device determines the corresponding welcome words according to the attribute information and pushes the welcome words to the user, so that personalized welcome word push is realized, and the user is attracted to carry out conversation. For example, welcome words of different country introduction information may be pushed according to the user's visit to different country pages.
A plurality of service intents are preset in the user data processing equipment, each service intention corresponds to a plurality of word slots, and each word slot corresponds to a group of inquiry sentences. The set of query statements may include one query statement or may include a plurality of query statements, which is not limited herein. A word slot corresponding to a business intention is corresponding to information in user data required to be acquired by the business intention. The query sentence corresponding to one word slot is used for asking a question for the user so as to extract the word slot from the conversation sentence replied by the user.
Taking a academic scene as an example, three service intentions, namely 'study reservation', 'tour study' and 'exam culture', are preset in the user data processing equipment. Wherein, the word slot corresponding to the "study reservation" can include: country of study, degree of study, personal status, at reading level, preparation stage, phone, social network account, salutation, city, customer source, etc. The term "learning" may include: country of school tour, personal situation, phone, social network account, salutation, city, customer source, etc. The word slot corresponding to "coper" may include: language lessons, language conditions, phone calls, social network account numbers, salutations, cities, customer sources, and the like.
The query sentence corresponding to the word slot study-reserving country may include "ask for study-reserving country considered by classmates? For example: united states, uk, canada, etc.; the query sentence corresponding to the word slot entrance degree may include "what stage the classmates are to think out and read? E.g., Benke, graduate, etc.; the query statement for the word slot at the reading grade may include "at which grade the classmate is currently reading, for example: high two, big three, etc. The query statement corresponding to the word slot preparation phase may include "roughly say the next current preparation phase to the student, for example: usual achievements, language conditions, etc.
S203, carrying out conversation interaction with the user by adopting the query sentence of the word slot corresponding to the target business intention to obtain the conversation sentence input by the user.
And S204, generating and outputting user data corresponding to the target business intention according to the conversation statement.
In this embodiment, after determining the target service intention of the user, the user data processing device obtains an inquiry statement of a word slot corresponding to the target service intention, pushes the inquiry statement to the user, and then receives a conversation statement replied by the user, thereby implementing conversation interaction with the user. The user data processing equipment can extract words used for filling word slots from the conversation sentences, further generate user data corresponding to the target business intention according to the word slots and the corresponding words, and output the user data to workers of an enterprise in forms of tables, texts and the like, for example, the user data is sent to terminals of the workers, so that the users can check or download the user data from the terminals.
In one possible application scenario, the user data processing device is a server. And the server acquires the query sentence of the word slot corresponding to the target service intention and sends the query sentence to the terminal. The terminal displays the inquiry sentences in the conversation window, receives the conversation sentences input by the user in the conversation window, and sends the speaking sentences to the server to realize conversation interaction with the user. The conversation window is shown in fig. 3, wherein the conversation window is superimposed on the current page for display, the terminal displays the query sentence sent by the server in the conversation window, and the user can input the conversation sentence in text form in the conversation window by selecting the conversation window. The content of the session interaction in this example takes the business intent "study retention" as an example, and the current page may be a page showing the study retention business.
In one possible application scenario, the user data processing device is a terminal. The terminal acquires the inquiry sentences of the word slots corresponding to the target service intentions, displays the inquiry sentences in the conversation window, receives the conversation sentences input by the user in the conversation window, and realizes conversation interaction with the user.
According to the embodiment of the application, the access information of the user is obtained, the target business intention of the user is determined according to the access information, the target business intention corresponds to a plurality of word slots, each word slot corresponds to a group of inquiry sentences, then conversation interaction is carried out on the inquiry sentences of the word slots corresponding to the target business intention and the user to obtain conversation sentences input by the user, user data corresponding to the target business intention are generated and output according to the conversation sentences, the user data can be automatically interacted with the user through the preset word slots and the inquiry sentences corresponding to the business intention, and the user data are obtained, so that the efficiency of obtaining the user data is improved.
Optionally, the conversational sentence comprises a question sentence. The above method may further comprise:
and extracting the vocabulary matched with the word slot corresponding to the target business intention from the question sentence, and filling the vocabulary into the corresponding word slot.
In this embodiment, in the session interaction process, the session statement input by the user may be a reply to the pushed query statement, or may be a question statement actively proposed by the user. For the question sentence input by the user, the user data processing equipment can identify whether a vocabulary matched with the word slot corresponding to the target business intention exists in the question sentence, and if so, the vocabulary can be extracted and filled into the corresponding word slot.
For example, during the conversational interaction, the user enters a question statement "what the school rank of the united states is," the user data processing device may reply to the question statement and extract the word "united states" from the question statement and fill in the word slot study country.
In the conversation interaction process with the user, the word slot filling is carried out according to the reply of the user to the question, the vocabulary matched with the word slot is identified from the question sentence actively asked by the user to carry out the word slot filling, and the word slot is filled when the user actively asks, so that the word slot filling efficiency can be improved.
Optionally, the method may further include:
after receiving the question statement, replying the question statement, and after replying the question statement, jumping to execute the following steps: and carrying out conversation interaction with the user by adopting the query sentence of the word slot corresponding to the target business intention.
In this embodiment, when performing session interaction with a user by using an inquiry statement of a word slot corresponding to a target service intention, if a question statement input by the user is received, the session flow of the original target service intention is terminated, the question statement input by the user is first replied, after replying the question statement, the session flow of the original target service intention is skipped back, and a session with the user is continued.
Wherein, replying to the question statement comprises:
and searching questions matched with the question sentences from a preset question-answer database, and pushing answer texts corresponding to the questions matched with the question sentences to the user, wherein the question-answer database comprises a plurality of groups of corresponding questions and answer texts.
Or based on the table look-up logic corresponding to the question sentence, searching data matched with the question sentence from a preset knowledge data table, generating an answer text according to the data matched with the question sentence, and pushing the answer text to the user.
In this embodiment, the user data processing device may reply to the question statement by using any one of the following two implementation manners.
In a first possible implementation manner, the user data processing device may determine the answer text of the question sentence based on a preset question and answer database, and push the answer text to the user. The question-answer database comprises a plurality of groups of corresponding question and answer texts. The user data processing device can search the question and answer database for the question matched with the question sentence, and the answer text of the question is pushed to the user.
In a second possible implementation manner, the user data processing device may search data matching the question statement from a preset knowledge data table, generate answer text from the data, and push the answer text to the user. For example, the knowledge data table may record the scholarship fee of each grade of each school in the united states, and when the question sentence is "what the scholarship fee of the grade one of the university of school X in the united states is", the user data processing device may look up the scholarship fee value corresponding to the grade one of the school X and the university as Y from the knowledge data table, generate an answer text such as "the scholarship fee of the grade one of the school X university is Y" from the school fee value, and push the answer text to the user.
According to the embodiment, the answer text of the question sentence can be accurately determined through the preset question-answer database or the preset knowledge data table, and the accuracy of answering the question is improved.
Fig. 4 is a schematic flowchart of a user data processing method combining an RPA and an AI according to another embodiment of the present application. The embodiment describes in detail a specific implementation process of performing session interaction with a user by using an inquiry statement of a word slot corresponding to a target business intention. As shown in fig. 4, the method includes:
s401, obtaining access information of a user.
In this embodiment, S401 is similar to S201 in the embodiment of fig. 2, and is not described here again.
S402, determining a target business intention of the user according to the access information, wherein the target business intention corresponds to a plurality of word slots, and each word slot corresponds to a group of inquiry sentences.
In this embodiment, S402 is similar to S202 in the embodiment of fig. 2, and is not described here again.
And S403, determining unfilled word slots in the word slots corresponding to the target business intention.
And S404, performing conversation interaction with the user by adopting the inquiry sentences corresponding to the unfilled word slots.
In this embodiment, after the user data processing device determines the target service intention, all word slots corresponding to the target service intention may be obtained. Since some of the word slots corresponding to the target business intent may be filled or unfilled, the user data processing device may determine the unfilled word slots therein. For example, after the welcome language is pushed to the user, the question sentences input by the user are received, some word slots are filled with words extracted from the question sentences of the user, and then the query sentences of the word slots do not need to be pushed to the user. And the user data processing equipment adopts the inquiry sentences corresponding to the unfilled word slots to carry out conversation interaction with the user.
According to the embodiment, only the query sentences of the unfilled word slots are pushed to the user, the problem of repeated pushing is avoided, the user experience can be improved, and the efficiency of obtaining user data is improved.
Optionally, the unfilled word slot is at least one. S404 may include:
and for each unfilled word slot, pushing an inquiry statement corresponding to the unfilled word slot to the user, and receiving a conversation statement input by the user.
In this embodiment, when the target service intention has a plurality of unfilled word slots, the query statement corresponding to each unfilled word slot may be pushed to the user in sequence for multiple times according to a preset sequence, and the conversation statement input by the user is received.
Optionally, the method may further include:
and determining whether a new business intention exists according to the conversation statement, and carrying out conversation interaction with the user by adopting an inquiry statement of the word slot corresponding to the new business intention when determining that the new business intention exists, and filling the word slot corresponding to the new business intention.
After the word slot corresponding to the new service intention is filled, skipping to execute the following steps: and carrying out conversation interaction with the user by adopting the query sentence of the word slot corresponding to the target business intention.
In this embodiment, in the process of performing session interaction with the user by using the query statement of the target service intention, if the session statement input by the user is related to another service intention, it is determined that a new service intention exists, and the query statement of the new service intention is used for performing session interaction with the user, so as to obtain user data corresponding to the new service intention. And after the word slot corresponding to the new service intention is filled, jumping back, and continuously adopting the query statement of the target service intention to interact with the user session.
Taking a academic scene as an example, if the conversation sentence input by the user is "what condition is needed for learning a tour" in the conversation interaction process between the inquiry sentence adopting the word slot corresponding to the "leave-study" and the user, the conversation process about the "leave-study" is stopped, and the inquiry sentence adopting the word slot corresponding to the "learn-tour" is used for carrying out conversation interaction with the user. And after the word slot corresponding to the learning tour is filled, switching to a conversation process related to the leaving learning, and continuing to perform conversation interaction with the user.
In the embodiment, when a user generates a new service intention, the user can perform session interaction with the user in time according to the new service intention, so that the user experience can be improved, the willingness of the user to continue the session can be enhanced, and the success rate of user data acquisition can be improved.
In one embodiment, before conversation interaction is carried out with a user by adopting an inquiry statement of a word slot corresponding to a new business intention, data retention is carried out on a preset word slot shared with the new business intention in the filled word slot.
In this embodiment, the same word slot may exist in word slots of different service intentions, and two or more same word slots of service intentions may be set as shared word slots in advance. Still taking the academic scenario as an example, the word slot corresponding to the business intent "study retention" may include: country of study, degree of study, personal status, at reading grade, preparation stage, phone, social network account, salutation, city, customer source. The word slot corresponding to the business intent "learning to swim" may include: country of school tour, personal situation, phone, social network account, phone, salutation, city, customer source. The word slot corresponding to the business intent "Coffe" may include: language lessons, language conditions, phone calls, social network account numbers, salutation, city, customer source. The word slots can be preset as shared word slots of the three service intentions; in the personal case, this word slot can be preset as a shared word slot for "stay on study" and "learn about".
When the business intention of the user is switched from the target business intention to a new business intention, before conversation interaction is carried out, word slots shared with the new business intention in currently filled word slots can be subjected to data retention, for example, words of the shared word slots are automatically filled into corresponding word slots of the new business intention, or words of the shared word slots are stored so as to be used when user data of the new business intention is generated, or the word slots are shared by two business intents, when the new business intention needs to be filled with the corresponding word slots, feedback that the word slots are filled can be obtained, so that when conversation interaction is carried out with the user according to inquiry sentences of the word slots corresponding to the new business intention, the user does not need to be inquired by repeating the problems of the word slots. Through word slot sharing, avoid with regard to same problem repeated inquiry to same user, improve the intelligence of robot, promote user experience.
And S405, generating and outputting user data corresponding to the target business intention according to the conversation statement.
In this embodiment, S405 is similar to S204 in the embodiment of fig. 2, and is not described herein again.
Fig. 5 is a flowchart illustrating a user data processing method according to another embodiment of the present application. This embodiment describes in detail a specific implementation process for generating user data corresponding to a target business intention according to a conversation statement. As shown in fig. 5, the method includes:
s501, obtaining access information of a user.
In this embodiment, S501 is similar to S201 in the embodiment of fig. 2, and is not described here again.
S502, determining a target business intention of the user according to the access information, wherein the target business intention corresponds to a plurality of word slots, and each word slot corresponds to a group of inquiry sentences.
In this embodiment, S502 is similar to S202 in the embodiment of fig. 2, and is not described here again.
S503, carrying out conversation interaction with the user by adopting the query sentence of the word slot corresponding to the target business intention, and obtaining the conversation sentence input by the user.
In this embodiment, S503 is similar to S203 in the embodiment of fig. 2, and is not described here again.
S504, extracting vocabularies matched with the word slots corresponding to the target business intentions from the conversation sentences, and filling the vocabularies into the corresponding word slots.
And S505, generating and outputting user data corresponding to the target business intention according to the word slot corresponding to the target business intention and the filled words.
In this embodiment, in the session interaction process, the user data processing device may identify a vocabulary in the session sentence that matches the word slot corresponding to the target service intention, extract the vocabulary, and fill the vocabulary into the corresponding word slot. And after the conversation interaction is finished, generating user data corresponding to the target business intention according to the word slot corresponding to the target business intention and the filled words, and outputting the user data.
Optionally, the word slot comprises a contact way word slot; s505 may include:
determining whether a contact word slot is populated;
and when the contact way word slot is filled, generating and outputting user data corresponding to the target business intention according to the word slot corresponding to the target business intention and the filled words.
In this embodiment, the contact information may be a phone number, a social account, a mailbox account, and the like, which is not limited herein. And all the word slots corresponding to each business intention are provided with at least one contact way word slot, and the word slots are used for filling the contact way of the user so that the following staff can contact the user through the contact way to promote products or provide services. And judging whether the contact way word slot of the target business intention is filled or not by the user data processing equipment in the conversation process with the user, if so, generating and outputting user data corresponding to the target business intention according to the word slot corresponding to the target business intention and the filled words, and otherwise, not generating the user data.
Because the contact way of the user in the user data is the most critical, the follow-up staff can contact the user only by acquiring the contact way of the user. If the contact information of the user cannot be acquired, the user data corresponding to the target service intention is useless even if the user data is generated. According to the embodiment, the generation and output of the user data are performed only when the contact way word slot is filled by judging whether the contact way word slot is filled, so that useless user data can be prevented from being generated, and the effect of acquiring the user data is improved.
Optionally, the user data processing device may guide the user to leave the contact address according to a preset funding flow and a conversation. For example, the user is preferably guided to leave the phone call, and if the user refuses to leave the phone call, the user can obtain other contact information.
In one embodiment, when it is determined that the contact address word slot is filled, if it is determined that a jump instruction exists, data retention is performed on a preset word slot shared with the target service intention before the jump.
In this embodiment, when it is determined that the contact word slot is filled, it may be determined whether there is a jump instruction, where the jump instruction is used to instruct a jump from a session flow of a target business intention to a session flow of another business intention. And correspondingly skipping is carried out when the skipping instruction is determined to exist, data is reserved in a preset word slot shared with the target service intention before skipping, repeated inquiry on the same problem of the same user is avoided through word slot sharing, the intelligence of the robot is improved, and the user experience is improved.
Fig. 6 is a schematic diagram of a program element for implementing a user data processing method in conjunction with RPA and AI according to an embodiment of the present application. The user data processing method combining RPA and AI provided in this embodiment can be implemented by the following program elements: a preprocessing unit 601, an event triggering unit 602, a total service central control unit 603, a branch service central control unit 604, and a branch service execution unit 605. These program elements are run in the user data processing device.
The preprocessing unit 601 is used for initializing settings, such as loading and initializing other units, a question-answer database, a knowledge data table, and the like.
The event trigger unit 602 is configured to, on one hand, actively initiate a corresponding session or welcome language to a user when a page is initially loaded or switched, and on the other hand, read access information of the user, for example: keywords searched by the user, user identification, client source, equipment information, page information of a page currently visited by the user, question sentences sent by the user on the page currently visited, tags of the user, network address information of the user and the like.
A total service central control unit 603, configured to identify a current target service intention of a user according to access information of the user, and allocate a control program flow to corresponding branch service central control units 604, where each branch service central control unit 604 is configured to control a session flow corresponding to a service intention, and the session flow is specifically executed by a branch service execution unit 605, so as to implement session interaction, word slot filling, and generation of output user data with the user according to an inquiry statement of a word slot corresponding to the service intention. After each branch service central control unit 604 controls and executes the session flow, the program flow will jump back to the total service central control unit 603.
A branch service central control unit 604, configured to control a process of the corresponding branch service execution unit 605 executing the session flow. Each of the branch service central control units 604 controls one branch service execution unit 605.
The branch service execution unit 605 is configured to execute a session flow of a corresponding service intention according to the control of the branch service central control unit 604, perform session interaction with a user according to an inquiry statement of a word slot corresponding to the service intention, and obtain user data corresponding to the word slot through multiple rounds of sessions. Each branch service execution unit 605 corresponds to a service intention. In this embodiment, taking an academic scene as an example, the number of the branch service execution units 605 is three, and the three branch service execution units respectively correspond to three service intentions "study keeping", "tourism" and "exam culture".
When one branch service central control unit 604 controls the corresponding branch service execution unit 605 to execute the session flow of the service intention, if it is determined that the user generates a new service intention according to the session statement input by the user, the branch service central control unit 604 controls the branch service execution unit 605 to stop the session flow, the program flow is switched back to the total service central control unit 603, and the total service central control unit 603 allocates the program flow to the branch service central control unit 604 corresponding to the new service intention, so as to implement switching of the service intention. After the execution of the session flow of the new service intention is completed, the total service central control unit 603 jumps the program flow to the original branch service execution unit 604 to continue executing the previously terminated session flow.
In the prior art, a manual customer service is used for carrying out session interaction with a user browsing a page, and the data of the user is filled in a user data sheet by the manual customer service. Because one manual customer service can only carry out session interaction with a plurality of users at the same time, and the speed of manually filling in user data is slow, the acquisition efficiency of the user data is low. In addition, there are also the following problems: the number of manual customer services is small in the peak period of the passenger flow and at night, and the manual customer services are difficult to interact with users in time; the interaction level of the manual customer service is uneven, and the quality of the obtained user data is difficult to ensure.
According to the user data processing method combining the RPA and the AI, the preset word slots and the query sentences corresponding to the service intentions are used for automatically interacting with the user to acquire the user data, so that the efficiency of acquiring the user data is improved, the intention of the user can be guided, the requirements of the user can be mined, and the collection of the user data can be efficiently completed. The embodiment can be used for simultaneously carrying out conversation with a plurality of users, processing the repeatability problem and subsequently transferring manual work or continuing independent reception; conversation with a user can be carried out at night, labor cost is reduced, and experience and effect can be improved; can imitate the best sales service and maintain stable business capability.
Fig. 7 is a schematic structural diagram of a user data processing apparatus combining an RPA and an AI according to an embodiment of the present application. As shown in fig. 7, the user data processing apparatus 70 combining RPA and AI includes: an acquisition module 701, a processing module 702, an interaction module 703 and an output module 704.
An obtaining module 701, configured to obtain access information of a user.
A processing module 702, configured to determine a target business intent of the user according to the access information, where the target business intent corresponds to a plurality of word slots, and each word slot corresponds to a group of query statements.
The interaction module 703 is configured to perform session interaction with the user by using the query statement of the word slot corresponding to the target service intention, so as to obtain a session statement input by the user.
And the output module 704 is used for generating and outputting the user data corresponding to the target service intention according to the conversation statement.
Optionally, the interaction module 703 is specifically configured to:
determining unfilled word slots in the word slots corresponding to the target service intention;
and carrying out conversation interaction with the user by adopting the query sentences corresponding to the unfilled word slots.
Optionally, the unfilled word slots are at least one;
the interaction module 703 is specifically configured to:
for each unfilled word slot, pushing an inquiry statement corresponding to the unfilled word slot to a user, and receiving a conversation statement input by the user;
the interaction module 703 is further configured to:
determining whether a new business intention exists according to the conversation statement, and carrying out conversation interaction with the user by adopting an inquiry statement of a word slot corresponding to the new business intention when the new business intention exists, and filling the word slot corresponding to the new business intention;
after the word slot corresponding to the new service intention is filled, skipping to execute the following steps: and carrying out conversation interaction with the user by adopting the query sentence of the word slot corresponding to the target business intention.
Optionally, the interaction module 703 is further configured to:
and before conversation interaction is carried out between the inquiry statement of the word slot corresponding to the new business intention and the user, data storage is carried out on the preset word slot shared with the new business intention in the filled word slot.
Optionally, the output module 704 is specifically configured to:
extracting vocabularies matched with the word slots corresponding to the target business intentions from the conversation sentences, and filling the vocabularies into the corresponding word slots;
and generating and outputting user data corresponding to the target business intention according to the word slot corresponding to the target business intention and the words filled in the word slot.
Optionally, the word slot comprises a contact way word slot;
the output module 704 is specifically configured to:
determining whether a contact word slot is populated;
and when the contact way word slot is filled, generating and outputting user data corresponding to the target business intention according to the word slot corresponding to the target business intention and the filled words.
Optionally, the output module 704 is further configured to:
and when the contact way word slot is filled, determining that a jump instruction exists, and before jumping, storing data in a preset word slot shared with the target service intention.
Optionally, the conversational sentence comprises a question sentence;
an output module 704, further configured to:
and extracting the vocabulary matched with the word slot corresponding to the target business intention from the question sentence, and filling the vocabulary into the corresponding word slot.
Optionally, the interaction module 703 is further configured to:
after receiving the question statement, replying the question statement, and after replying the question statement, jumping to execute the following steps: performing conversation interaction with the user by adopting an inquiry statement of a word slot corresponding to the target business intention;
wherein, replying to the question statement comprises:
searching questions matched with the question sentences from a preset question-answer database, and pushing answer texts corresponding to the questions matched with the question sentences to a user, wherein the question-answer database comprises a plurality of groups of corresponding questions and answer texts;
or based on the table look-up logic corresponding to the question sentence, searching data matched with the question sentence from a preset knowledge data table, generating an answer text according to the data matched with the question sentence, and pushing the answer text to the user.
Optionally, the accessing information comprises:
keywords of the user search.
Optionally, the accessing information further comprises:
attribute information of a user, wherein the attribute information includes at least one of: page information of a page currently accessed by a user, question statements sent by the user on the currently accessed page, tags of the user and network address information of the user;
the interaction module 703 is further configured to:
and determining the welcome words according to the attribute information, and pushing the welcome words to the user.
The user data processing apparatus combining RPA and AI provided in the embodiment of the present application may be used to implement the method embodiments described above, and the implementation principle and technical effect are similar, which is not described herein again.
Fig. 8 is a schematic hardware structure diagram of a user data processing device according to an embodiment of the present application. As shown in fig. 8, the user data processing apparatus 80 provided in the present embodiment includes: at least one processor 801 and a memory 802. The user data processing device 80 further comprises a communication section 803. The processor 801, the memory 802, and the communication unit 803 are connected by a bus 804.
In particular implementations, execution of computer-executable instructions stored by the memory 802 by the at least one processor 801 causes the at least one processor 801 to perform the user data processing method in conjunction with RPA and AI as described above.
For a specific implementation process of the processor 801, reference may be made to the above method embodiments, which have similar implementation principles and technical effects, and details of this embodiment are not described herein again.
In the embodiment shown in fig. 8, it should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose processors, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in the incorporated application may be directly implemented by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.
The memory may comprise high speed RAM memory and may also include non-volatile storage NVM, such as at least one disk memory.
The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.
The present application also provides a computer-readable storage medium having stored therein computer-executable instructions that, when executed by a processor, implement the user data processing method in combination with RPA and AI as above.
The readable storage medium may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks. Readable storage media can be any available media that can be accessed by a general purpose or special purpose computer.
An exemplary readable storage medium is coupled to the processor such the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium may also reside as discrete components in the apparatus.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.
Claims (14)
1. A user data processing method combining RPA and AI, comprising:
acquiring access information of a user;
determining a target business intention of the user according to the access information, wherein the target business intention corresponds to a plurality of word slots, and each word slot corresponds to a group of inquiry sentences;
performing conversation interaction with the user by adopting the query sentence of the word slot corresponding to the target service intention to obtain a conversation sentence input by the user;
and generating and outputting user data corresponding to the target business intention according to the conversation statement.
2. The method of claim 1, wherein performing conversational interaction with the user using the query statement of the word slot corresponding to the target business intent comprises:
determining unfilled word slots in the word slots corresponding to the target business intention;
and performing conversation interaction with the user by adopting the query sentences corresponding to the unfilled word slots.
3. The method of claim 2, wherein the unfilled word trench is at least one; adopting the query sentence corresponding to the unfilled word slot to perform conversation interaction with a user, wherein the conversation interaction comprises the following steps:
for each unfilled word slot, pushing an inquiry statement corresponding to the unfilled word slot to the user;
receiving a conversation sentence input by a user;
after receiving the conversational sentence input by the user, the method further comprises:
determining whether a new service intention exists according to the conversation statement, carrying out conversation interaction with a user by adopting an inquiry statement of a word slot corresponding to the new service intention when the new service intention exists, filling the word slot corresponding to the new service intention, and after the word slot corresponding to the new service intention is filled, skipping and executing the following steps: and performing conversation interaction with the user by adopting the query sentence of the word slot corresponding to the target business intention.
4. The method of claim 3, wherein before conversational interaction with the user using the query statement of the word slot corresponding to the new business intent, the method further comprises:
and data storage is carried out on the word slot which is preset and shared with the new service intention in the filled word slots.
5. The method of claim 1, wherein generating and outputting user data corresponding to the target business intention according to the conversational sentence comprises:
extracting vocabularies matched with the word slots corresponding to the target business intents from the conversation sentences, and filling the vocabularies into the corresponding word slots;
and generating and outputting user data corresponding to the target business intention according to the word slot corresponding to the target business intention and the words filled in the word slot.
6. The method of claim 5, wherein the word slot comprises a contact-address word slot;
generating and outputting user data corresponding to the target service intention according to the word slot corresponding to the target service intention and the words filled in the word slot, wherein the user data comprises:
determining whether the contact word slot is populated;
and when the contact way word slot is filled, generating and outputting user data corresponding to the target business intention according to the word slot corresponding to the target business intention and the filled words.
7. The method of claim 6, wherein when the contact word slot is filled, the method further comprises:
and determining that a jump instruction exists, and before jumping, carrying out data retention on a preset word slot shared with the target service intention.
8. The method of claim 1, wherein the conversational utterances comprise question utterances; the method further comprises the following steps:
and extracting the vocabulary matched with the word slot corresponding to the target business intention from the question sentence, and filling the vocabulary into the corresponding word slot.
9. The method of claim 8, further comprising:
after the question statement is received, replying the question statement, and after the question statement is replied, skipping to executing the following steps: performing conversation interaction with a user by adopting an inquiry statement of the word slot corresponding to the target service intention;
wherein replying to the question statement comprises:
searching questions matched with the question sentences from a preset question-answer database, and pushing answer texts corresponding to the questions matched with the question sentences to a user, wherein the question-answer database comprises a plurality of groups of corresponding questions and answer texts; alternatively, the first and second electrodes may be,
and searching data matched with the question sentences from a preset knowledge data table based on table searching logic corresponding to the question sentences, generating answer texts according to the data matched with the question sentences, and pushing the answer texts to users.
10. The method of any of claims 1-9, wherein the accessing information comprises:
keywords of the user search.
11. The method of any of claims 1-9, wherein the accessing information further comprises:
attribute information of a user, wherein the attribute information includes at least one of: page information of a page currently accessed by a user, question statements sent by the user on the currently accessed page, tags of the user and network address information of the user;
the method further comprises the following steps:
determining a welcome language according to the attribute information, and pushing the welcome language to a user.
12. A user data processing apparatus combining RPA and AI, comprising:
the acquisition module is used for acquiring the access information of the user;
the processing module is used for determining a target business intention of the user according to the access information, wherein the target business intention corresponds to a plurality of word slots, and each word slot corresponds to a group of inquiry sentences;
the interaction module is used for carrying out conversation interaction with the user by adopting the inquiry sentences of the word slots corresponding to the target business intents to obtain conversation sentences input by the user;
and the output module is used for generating and outputting the user data corresponding to the target service intention according to the conversation statement.
13. A user data processing device, comprising: at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the method of user data processing in conjunction with RPA and AI according to any of claims 1-11.
14. A computer-readable storage medium having stored thereon computer-executable instructions which, when executed by a processor, implement a method of user data processing in combination with RPA and AI according to any one of claims 1-11.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2020101871965 | 2020-03-17 | ||
| CN202010187196 | 2020-03-17 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112000784A true CN112000784A (en) | 2020-11-27 |
Family
ID=73464238
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010795925.5A Pending CN112000784A (en) | 2020-03-17 | 2020-08-10 | User data processing method, device and equipment combining RPA and AI and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112000784A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112597288A (en) * | 2020-12-23 | 2021-04-02 | 北京百度网讯科技有限公司 | Man-machine interaction method, device, equipment and storage medium |
| CN113127618A (en) * | 2021-04-16 | 2021-07-16 | 北京奇艺世纪科技有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN113220187A (en) * | 2021-04-30 | 2021-08-06 | 中国银行股份有限公司 | Micro banking business interaction method and related equipment |
| CN113420125A (en) * | 2021-06-25 | 2021-09-21 | 深圳索信达数据技术有限公司 | Question-answer pair determining method, system, storage medium and equipment based on industry types |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109003605A (en) * | 2018-07-02 | 2018-12-14 | 北京百度网讯科技有限公司 | Intelligent sound interaction processing method, device, equipment and storage medium |
| CN110659360A (en) * | 2019-10-09 | 2020-01-07 | 初米网络科技(上海)有限公司 | Man-machine conversation method, device and system |
| CN110825865A (en) * | 2020-01-09 | 2020-02-21 | 浩鲸云计算科技股份有限公司 | Multi-round conversation intelligent customer service system based on special word correction and cold start |
| US20200074374A1 (en) * | 2018-08-31 | 2020-03-05 | Kinaxis Inc. | Conversational business tool |
-
2020
- 2020-08-10 CN CN202010795925.5A patent/CN112000784A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109003605A (en) * | 2018-07-02 | 2018-12-14 | 北京百度网讯科技有限公司 | Intelligent sound interaction processing method, device, equipment and storage medium |
| US20200074374A1 (en) * | 2018-08-31 | 2020-03-05 | Kinaxis Inc. | Conversational business tool |
| CN110659360A (en) * | 2019-10-09 | 2020-01-07 | 初米网络科技(上海)有限公司 | Man-machine conversation method, device and system |
| CN110825865A (en) * | 2020-01-09 | 2020-02-21 | 浩鲸云计算科技股份有限公司 | Multi-round conversation intelligent customer service system based on special word correction and cold start |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112597288A (en) * | 2020-12-23 | 2021-04-02 | 北京百度网讯科技有限公司 | Man-machine interaction method, device, equipment and storage medium |
| CN112597288B (en) * | 2020-12-23 | 2023-07-25 | 北京百度网讯科技有限公司 | Man-machine interaction method, device, equipment and storage medium |
| CN113127618A (en) * | 2021-04-16 | 2021-07-16 | 北京奇艺世纪科技有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN113127618B (en) * | 2021-04-16 | 2023-09-01 | 北京奇艺世纪科技有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN113220187A (en) * | 2021-04-30 | 2021-08-06 | 中国银行股份有限公司 | Micro banking business interaction method and related equipment |
| CN113420125A (en) * | 2021-06-25 | 2021-09-21 | 深圳索信达数据技术有限公司 | Question-answer pair determining method, system, storage medium and equipment based on industry types |
| CN113420125B (en) * | 2021-06-25 | 2023-09-19 | 深圳索信达数据技术有限公司 | Question-answer pair determining method, system, storage medium and equipment based on industry type |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11960694B2 (en) | Method of using a virtual assistant | |
| CN112000784A (en) | User data processing method, device and equipment combining RPA and AI and storage medium | |
| CN111930940B (en) | Text emotion classification method and device, electronic equipment and storage medium | |
| US11599729B2 (en) | Method and apparatus for intelligent automated chatting | |
| CN105893465B (en) | Automatic question answering method and device | |
| US10049152B2 (en) | Generating natural language dialog using a questions corpus | |
| US11010700B2 (en) | Identifying task and personality traits | |
| CN109635094B (en) | Method and device for generating answer | |
| KR20200032893A (en) | Communication information processing system for chat bot service and control method thereof | |
| CN110187780B (en) | Long text prediction method, long text prediction device, long text prediction equipment and storage medium | |
| CN110929045B (en) | Construction method and system of poetry-semantic knowledge map | |
| CN111898643A (en) | Semantic matching method and device | |
| CN108268450B (en) | Method and apparatus for generating information | |
| CN110909145A (en) | Training method and device for multi-task model | |
| EP3614297A1 (en) | Hybrid natural language understanding | |
| CN111639162A (en) | Information interaction method and device, electronic equipment and storage medium | |
| CN116541493A (en) | Interactive response method, device, equipment and storage medium based on intention recognition | |
| CN112579733B (en) | Rule matching method, rule matching device, storage medium and electronic equipment | |
| CN110232920B (en) | Voice processing method and device | |
| CN111402864A (en) | Voice processing method and electronic equipment | |
| CN107885872B (en) | Method and device for generating information | |
| CN112926308B (en) | Method, device, equipment, storage medium and program product for matching text | |
| CN111931503B (en) | Information extraction method and device, equipment and computer readable storage medium | |
| CN117648422A (en) | Question-answer prompt system, question-answer prompt, library construction and model training method and device | |
| KR20200032873A (en) | Parsing system for chat bot service based on book information and control method thereof |
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 |